Swati Aggarwal

• Mathur, Vidhu; Dadu, Tanvi & Aggarwal, Swati (2024). Evaluating neural networks’ ability to generalize against adversarial attacks in cross-lingual settings. Applied Sciences. ISSN 2076-3417. 14(13). doi: 10.3390/app14135440. Vis sammendrag

  Cross-lingual transfer learning using multilingual models has shown promise for improving performance on natural language processing tasks with limited training data. However, translation can introduce superficial patterns that negatively impact model generalization. This paper evaluates two state-of-the-art multilingual models, Cross-Lingual Model-Robustly Optimized BERT Pretraining Approach (XLM-Roberta) and Multilingual Bi-directional Auto-Regressive Transformer (mBART), on the cross-lingual natural language inference (XNLI) natural language inference task using both original and machine-translated evaluation sets. Our analysis demonstrates that translation can facilitate cross-lingual transfer learning, but maintaining linguistic patterns is critical. The results provide insights into the strengths and limitations of state-of-the-art multilingual natural language processing architectures for cross-lingual understanding.

• Aggarwal, Swati & Mittal, Anshul (2024). Futuristic hospitality conceptualized : DASH - Decentralized Autonomous and Smart Hotel system. Journal of Open Innovation: Technology, Market, and Complexity. ISSN 2199-8531. 10(1). doi: 10.1016/j.joitmc.2024.100223. Vis sammendrag

  Ubiquitous hospitality has stimulated a rise in expeditions to inspiring getaways and extraordinary destinations. It is imperative for hotels to create a distinct and immersive experience leveraging disruptive technologies like Artificial Intelligence, Machine Learning, Internet of Things, and Blockchain, while ensuring economic affordability for patrons. This study introduces an autonomous and agile smart hotel system, DASH-Decentralized Autonomous and Smart Hotel system, operating on a pay-per-use model, meticulously tracking the usage of amenities and utilities for patrons. The proposed system is an amalgamation of Internet of Things, Robots, Artificial Intelligence, and Blockchain, each enhancing trust, transparency, and underlying operations while reducing workforce and operational costs. This work distinguishes itself by focusing on the complete automation of hotels rather than merely complementing current activities with these technologies. Method: This research hinges on an extensive literature review, deepening the understanding of contemporary hospitality systems, technological advances, and emerging trends. Building on these insights, this work employed conceptual modelling to create a robust framework for the DASH system, strategically integrating decentralization, autonomy, and intelligence. This method bridges visionary ideals with practical implementation, shaping the future of hospitality through cutting-edge technology integration. Main Findings: DASH, as a Decentralized Autonomous and Smart Hotel System, successfully integrates disruptive technologies to create an innovative and automated hospitality experience. The pay-per-use model proves effective in tracking amenity and utility usage, ensuring a cost-efficient and tailored service for patrons. The amalgamation of Internet of Things, Robots, Artificial Intelligence, and Blockchain enhances trust, transparency, and operational efficiency within the hospitality institution. The study's approach of steering towards complete hotel automation distinguishes it from existing literature, showcasing a unique and forward-thinking perspective on the implementation of disruptive technologies in the hospitality sector.

• Chugh, Nupur & Aggarwal, Swati (2024). Spatial decoding for gaze independent brain–computer interface based on covert visual attention shift using electroencephalography. Clinical EEG and Neuroscience. ISSN 1550-0594. 55(4), s. 477–485. doi: 10.1177/15500594241229187. Vis sammendrag

  The gaze-independent brain–computer interface (BCI) device is used to re-establish interaction for individuals who have abnormal eye movement. It may be possible to control the BCI by shifting your attention spatially. However, spatial attention is rarely employed to increase the effectiveness of target detection and is typically used to provide a simple “yes” or “no” response to the target recognition inquiry. To improve the effectiveness of detecting target, it is crucial to take advantage of the possible advantages of spatial attention. N2-posterior-contralateral (N2pc) component reflects correlates of visual spatial attention and is used to determine target position. In this study, a long-short-term memory (LSTM) network is used to answer “yes/no” questions by decoding covert spatial attention based on N2pc characteristics using EEG signals. The proposed LSTM-based model's average decoding accuracy is 92.79%. The target detection efficiency was successfully increased by about 4% when compared to conventional machine learning algorithms. The proposed model is tested on the independent dataset to validate its performance. The results of this work show that N2pc characteristics can be employed in gaze-independent BCIs for tracking covert attention shifts, which may help persons with poor eye mobility to connect with their environment.

• Chugh, Nupur; Aggarwal, Swati & Balyan, Arnav (2024). The hybrid deep learning model for identification of attention-deficit/hyperactivity disorder Using EEG. Clinical EEG and Neuroscience. ISSN 1550-0594. 55(1), s. 22–33. doi: 10.1177/15500594231193511. Vis sammendrag

  Common misbehavior among children that prevents them from paying attention to tasks and interacting with their surroundings appropriately is attention-deficit/hyperactivity disorder (ADHD). Studies of children's behavior presently face a significant problem in the early and timely diagnosis of this disease. To diagnose this disease, doctors often use the patient's description and questionnaires, psychological tests, and the patient's behavior in which reliability is questionable. Convolutional neural network (CNN) is one deep learning technique that has been used for the diagnosis of ADHD. CNN, however, does not account for how signals change over time, which leads to low classification performances and ambiguous findings. In this study, the authors designed a hybrid deep learning model that combines long-short-term memory (LSTM) and CNN to simultaneously extract and learn the spatial features and long-term dependencies of the electroencephalography (EEG) data. The effectiveness of the proposed hybrid deep learning model was assessed using 2 publicly available EEG datasets. The suggested model achieves a classification accuracy of 98.86% on the ADHD dataset and 98.28% on the FOCUS dataset, respectively. The experimental findings show that the proposed hybrid CNN-LSTM model outperforms the state-of-the-art methods to diagnose ADHD using EEG. Hence, the proposed hybrid CNN-LSTM model could therefore be utilized to help with the clinical diagnosis of ADHD patients.

• Aggarwal, Swati; Vaid, Akhil; Kaushik, Paras; Goel, Anirudh & Kamboj, Aniket (2023). Performance evaluation of EfficientNet model towards malaria parasite detection in segmented blood cells from thin-blood smear images. I Gupta, Mousumi; Ghatak, Sujata; Gupta, Amlan & Mukherjee, Abir Lal (Red.), Artificial Intelligence on Medical Data : Proceedings of International Symposium, ISCMM 2021. Springer. ISSN 978-981-19-0153-9. s. 137–157. doi: 10.1007/978-981-19-0151-5_11. Vis sammendrag

  Malaria is a potentially fatal disease caused by infected Anopheles mosquitoes. Traditional diagnosis of malaria involves examination of thin blood smear slides under a microscope by trained microscopists to detect infected blood cells. This process is expensive, and results depend both on the quality of smear and on the expertise of the microscopist. Thus, work done in this field is focussed on automating this detection of infected cells. Early work for this task included using hand-engineered features and machine learning algorithms. This approach was taken over by the advent of CNNs which provided an end-to-end solution, right from feature extraction to classification. Work done in this field thus shifted towards using state-of-the-art CNNs. The authors of this paper found that most of the existing models that had been used for this problem had good classification accuracy but had big sizes that could not be run on a normal computing device. They identified that a new set of state-of-the-art CNNs, called EfficientNets which promised similar performance at much smaller sizes, had not been used for this task. So, they worked to evaluate the performance of EfficientNet models for this medical image classification task. The authors trained the EfficientNet-B0 model on the malaria images dataset taken from the National Library of Medicine (NLM) (Dataset used: https://lhncbc.nlm.nih.gov/LHC-publications/pubs/MalariaDatasets.html). The authors then computed the key performance parameters of the model and compared them against the existing models for this problem. The work done showed that using Efficient-Net models for this task achieved similar accuracy to existing models and significantly reduced the number of parameters.

• Chugh, Nupur & Aggarwal, Swati (2023). Hybrid brain–computer interface spellers : a walkthrough recent advances in signal processing methods and challenges. International Journal of Human-Computer Interaction. ISSN 1044-7318. 39(15), s. 3096–3113. doi: 10.1080/10447318.2022.2093445. Vis sammendrag

  Hybrid brain computer interfaces (hBCIs) have emerged as a possible path to integrated brain-computer interaction in current history. hBCI, is a device formed by the amalgamation of control signal and bio-signal combination of control signal with one or more bio-signals that enhances system performance and usability. Assistive technology, spelling, and gaming are some of the primary areas where hBCI can be used. Among these, hBCI spellers are the popular application that has opened up a slew of new possibilities of communication for paralyzed individuals. The goal of this review is to provide prospect on current state of hBCI spellers covering types of hBCI, signal processing methods and evaluation with emphasis on feature extraction techniques and classification methods used by these studies. The authors anticipate that this analysis will serve as a foundation for ongoing studies on hBCI spellers.

• Rajwal, Swati & Aggarwal, Swati (2023). Convolutional neural network-based EEG signal analysis : a systematic review. Archives of Computational Methods in Engineering. ISSN 1134-3060. 30, s. 3585–3615. doi: 10.1007/s11831-023-09920-1. Vis sammendrag

  The identification and classification of human brain activities are essential for many medical and Brain-Computer Interface (BCI) systems, saving human lives and time. Electroencephalogram (EEG) proves to be an efficient, non-invasive, and cost-effective means of recording electrical signals in the human brain. With the advancement in Artificial Intelligence, various techniques have emerged that provide efficient ways of classifying EEG signals to solve real-life challenges. One such method is Convolutional Neural Network (CNN), which has received considerable research attention. This paper presents a systematic review of CNN techniques for the identification and classification of EEG signals and their main achievements. The review has considered the most reliable studies from various fields and application domains where CNN has been used for EEG signal classification or identification. The review also highlights the approaches taken so far. While there are many available survey types of research, none has provided a comprehensive view of a particular model for EGG-signal analysis. This survey focuses on the successful deployment of CNN models in various application domains that use EEG signals. Additionally, this paper attempts to answer research questions and discusses current challenges. The presented detailed review strengthens the belief in the futuristic potential that CNN has in solving real-world problems using EEG signals. All of this indicates that CNN-based EEG-signal analysis is a promising field with exciting opportunities for research enthusiasts.

• Aggarwal, Swati; Gupta, Shubhi; Satia, Simrat Pal Singh; Saluja, Shivin & Gambhir, Varshika (2022). Pilot study to predict smartphone addiction through usage pattern of installed android applications and to derive correlations between addiction and phone usage behavior. ADDICTA: The Turkish Journal on Addictions. ISSN 2148-7286. 9(1), s. 63–74. doi: 10.5152/ADDICTA.2022.21069. Vis sammendrag

  Mobile phone technology has been completely revolutionized in recent years. From being used for calls and text messages, the usage pattern has now shifted, and involves heavy applications (apps) based on platforms such as Android and iOS. Therefore, people have become exceedingly dependent on smartphones, with most of them suffering from a smartphone addiction disorder. In this study, the authors collect app usage patterns and categorize all apps into five buckets: social, entertainment, utility, gaming, and shopping/food and beverage. The data were collected through a self-developed app, named Activity Tracker, installed in the smartphones of individuals participating in the study. Activity Tracker also collects additional phone usage features such as call duration, number of texts/calls, and screen-on duration. The authors predict smartphone addiction using supervised machine-learning algorithms with good accuracy. This is a promising attempt to uncover multi-dimensional aspects of smartphone addiction by studying the usage patterns of installed Android applications. The study also includes gender-wise variations of smartphone usage patterns and explicit parallelism between usage patterns of addicted and non-addicted users.

• Aggarwal, Swati & Chugh, Nupur (2022). Review of machine learning techniques for EEG based brain computer interface. Archives of Computational Methods in Engineering. ISSN 1134-3060. 29(5), s. 3001–3020. doi: 10.1007/s11831-021-09684-6. Vis sammendrag

  A brain computer interface (BCI) framework uses computer algorithms to detect mental activity patterns and manipulate external devices. Because of its simplicity and non-invasiveness, one of the most commonly used imaging technologies is electroencephalography (EEG). The evaluative method used in assessing the output of an EEG-based BCI system is classifying EEG signals for particular applications. The growth of artificial intelligence technology inspired researchers to use machine learning (ML) techniques and deep learning (DL) approaches to classify EEG-based BCI. Machine learning techniques enable the brain computer interface to learn from the subject's brain with each new session, adapting the generated rules for classifying thoughts and thus improving the system's efficiency. The authors present a concentrated survey on the use of various ML/DL techniques in EEG-based BCI. Three EEG paradigms for classification are used: motor imagery, p300, and steady state evoked potential. In addition, the challenges that recent EEG-based BCI systems face are addressed based on ideal signal processing methods, BCI functioning, performance assessment and commercialization. The authors hope that the information gathered would aid in application of suitable machine learning techniques, as well as provide a foundation for BCI researchers to enhance future BCI system.

• Aggarwal, Swati; Dadu, Tanvi & Aggarwal, Nisha (2022). A novel fuzzy modifier interpolation rule for computing with words. Informatica (Ljubljana, Tiskana izd.). ISSN 0350-5596. 46(1), s. 57–67. doi: 10.31449/inf.v46i1.3591. Vis sammendrag

  Computing with Words(CW) is a concept that is used to solve problems with input in natural language. Modifiers are transformation functions with predefined labels used extensively in the decision making systems to specify the desired value of a linguistic variable defined by fuzzy sets. In previous works, significant effort has been made to study the application of CW in many domains ranging from fraud detection systems to diagnosis systems in medicine. However, the application of CW in these fields with modified fuzzy sets didn't give satisfactory results. The existing interpolation rule, when applied to modified fuzzy sets, does not take care of the extreme left and extreme right-shifted fuzzy sets. Hence, there is a need to introduce a new interpolation rule when working with modifiers. In this paper, we propose a new Fuzzy Modifier Interpolation Rule to Type-1 Fuzzy sets and Interval Type-2 Fuzzy Sets to enhance the quality of results obtained when modifiers are applied.

• Agarwal, Sarthak; Saxena, Vaibhav; Singal, Vaibhav & Aggarwal, Swati (2021). Deep learning-based computer aided customization of speech therapy. I Choudhary, Ankur; Agrawal, Arun Prakash; Logeswaran, Rajasvaran & Unhelkar, Bhuvan (Red.), Applications of Artificial Intelligence and Machine Learning : Select Proceedings of ICAAAIML 2020. Springer. ISSN 978-981-16-3067-5. s. 483–494. doi: 10.1007/978-981-16-3067-5_36. Vis sammendrag

  Video frame interpolation is a computer vision technique used to synthesize intermediate frames between two subsequent frames. This technique has been extensively used for the purpose of video upsampling, video compression and video rendering. We present here an unexplored application of frame interpolation, by using it to join different phoneme videos in order to generate speech videos. Such videos can be used for the purpose of speech entrainment, as well as help to create lip reading video exercises. We propose an end-to-end convolutional neural network employing a U-net architecture that learns optical flows and generates intermediate frames between two different phoneme videos. The quality of the model is evaluated against qualitative measures like the Structural Similarity Index (SSIM) and the peak signal-to-noise ratio (PSNR), and performs favorably well, with an SSIM score of 0.870, and a PSNR score of 33.844.

• Sharma, Lakshita; Hooda, Prachi; Bansal, Raghav; Garg, Shivam & Aggarwal, Swati (2021). Analyzing app-based methods for internet de-addiction in young population. I Choudhary, Ankur; Agrawal, Arun Prakash; Logeswaran, Rajasvaran & Unhelkar, Bhuvan (Red.), Applications of Artificial Intelligence and Machine Learning : Select Proceedings of ICAAAIML 2020. Springer. ISSN 978-981-16-3067-5. s. 217–228. doi: 10.1007/978-981-16-3067-5_17. Vis sammendrag

  With recent advancements in technology and the excessive use of smartphones, all internet-based applications like WhatsApp, Facebook, Netflix, etc. are one tap away, thereby resulting in increased internet usage on an average, especially among the young population. This has affected the cognitive and affective processes of the users and has caused various problems like loss of focus, fatigue, and burning sensations in the eyes, severe harm to mental health, reduction in response to events happening around, and many more. An unconventional method of recovering from internet addiction could be the use of mobile applications that help users monitor their usage and motivate them to have better self-control. There are a number of such applications, henceforth called apps, available that claim to help recover from internet addiction. However, their efficacy in curbing internet use has not been studied previously. This study is primarily based on assessing the efficiency of these app-based recovery methods from internet addiction. Using statistical analysis and polynomial regression, it was found that these apps do help in lowering internet use. This effect is largely seen in the first week of app use, after which significant reduction is not observed.

• Oberoi, Karmanya; Tandon, Sarthak; Das, Abhishek & Aggarwal, Swati (2021). An evolutionary approach to combinatorial gameplaying using extended classifier systems. I Choudhary, Ankur; Agrawal, Arun Prakash; Logeswaran, Rajasvaran & Unhelkar, Bhuvan (Red.), Applications of Artificial Intelligence and Machine Learning : Select Proceedings of ICAAAIML 2020. Springer. ISSN 978-981-16-3067-5. s. 723–738. doi: 10.1007/978-981-16-3067-5_54. Vis sammendrag

  Extended classifier system (XCS) is an extension of a popular online rule-based machine learning technique, learning classifier system (LCS), in which a classifier’s fitness is based on its accuracy instead of the prediction itself, and a genetic algorithm (GA) and reinforcement learning (RL) component is utilized for exploratory and learning purposes, respectively. With the emergence of increasingly intricate rule-based learning techniques, there is a need to examine feasible methods of learning that can overcome the challenges posed by complex scenarios while supporting online performance. Checkers is a strategic, combinatorial game having a high branching factor and a complex state space that provides a promising avenue for scrutinizing novel approaches. This paper presents a preliminary investigation into feasibility of XCS in such complex avenues by taking 6 × 6 checkers as a specific case of study. The XCS agent was adapted to this problem, trained with random agent and was able to perform well against the alpha–beta pruning algorithm of various depths as well as human agents of different skill levels (beginner, intermediate and advanced).

• Manchanda, Haritima & Aggarwal, Swati (2021). Forecasting cryptocurrency time series using adaboost-based ensemble learning techniques. I Singh, Jawar; Kumar, Sudhir & Choudhury, Umakanta (Red.), Innovations in Cyber Physical Systems : Select Proceedings of ICICPS 2020. Springer. ISSN 978-981-16-4148-0. s. 207–219. doi: 10.1007/978-981-16-4149-7_17. Vis sammendrag

  The book presents a collection of peer-reviewed articles from the International Conference on Innovations in Cyber Physical Systems (ICICPS 2020). The conference provided opportunities for the presentation of new research results and discussion about them. It was also an opportunity to generation of new ideas in all CPS aspects, including theory, tools, applications, systems, test-beds and field deployments. The range of topics explored is wide, and covers security, control, optimization, machine learning, game theory, mechanism design, mobile and cloud computing, model-based design, verification, data mining/analytics, signal processing, and human-in-the-loop shared or supervisory control. This book will be useful to researchers, students, industrialist, developers, and practitioners alike.

• Aggarwal, Swati; Lamba, Mohit; Verma, Kandarp; Khuttan, Siddharth & Gautam, Hitesh (2021). A preliminary investigation for assessing attention levels for Massive Online Open Courses learning environment using EEG signals : an experimental study. Human Behavior and Emerging Technologies. ISSN 2578-1863. 3(5), s. 933–941. doi: 10.1002/hbe2.274. Vis sammendrag

  Rapid progress in expansion of the internet services have provided an alternative way for learning other than the traditional classroom learning. Due to the availability of multiple learning options, evaluating each option and judging the best use case plays a vital role. One of the most important characteristics that a human brain utilizes during process of learning is cognition that involves attention and retention. Student's attention span and situational interests during learning have always been a subject matter of research. Apart from classroom learning, e-learning (MOOC based learning) is the other most preferred way of learning. Therefore, the objective of this study is to assess attention levels of a learner in MOOC (Massive Open Online Courses) learning environments and compare it with conventional classroom learning using brain signals. The proposed method captures electroencephalogram (EEG) frequency bands of different subjects while going through a short lecture in MOOC/e-learning environment and classroom environment. The captured data points were annotated for attentiveness manually by referring to the subject's feedback and video clips. Machine learning classification model of support vector machines (SVM) was used to classify student's mental state as attentive or nonattentive. Promising results were obtained and experiments revealed that higher attention levels were maintained during MOOC learning environment in comparison to traditional learning approach.

• Aggarwal, Swati & Chugh, Nupur (2020). A decade of EEG analysis : prospects & challenges in biometric system. I ., Ukjent (Red.), 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence) . IEEE conference proceedings. ISSN 978-1-7281-2792-7. s. 474–479. doi: 10.1109/Confluence47617.2020.9058003. Vis sammendrag

  EEG signals have been investigated in medical and entertainment applications for many years. Recently, researchers have investigated EEG signals as a biometric trait for person identification and authentication. EEG biometric system has achieved reasonable accuracy, yet some of the challenges hinder the development of ready to deploy EEG based biometric systems. This paper highlights the emerging challenges of the EEG biometric system. The authors present the interrelationships among identified challenges and review the published articles quantitatively based on publication time and online library.

• Nagpal, Sidhant; Verma, Siddharth; Gupta, Shikhar & Aggarwal, Swati (2020). A guided learning approach for generative adversarial networks. I Roy, Asim (Red.), 2020 International Joint Conference on Neural Networks (IJCNN) : Conference Proceedings. IEEE (Institute of Electrical and Electronics Engineers). ISSN 978-1-7281-6926-2. s. 1–8. doi: 10.1109/IJCNN48605.2020.9206804. Vis sammendrag

  In this paper, we propose a novel technique for training Generative Adversarial Networks (GANs) using autoencoders. GANs, in recent years, have emerged as one of the most popular generative models. Despite their success, there are several challenges in maintaining the trade-off between diversity and quality of the generated distribution. Our idea stems from the fact that deeper layers of an autoencoder contain high-level feature representation of the input data distribution. Reusing these layers provides GAN with information about the representative characteristics of real data and hence can guide its adversarial training. We call our model Guided GAN since the autoencoder (guiding network) provides a direction to train the GAN (generative network). Guided GAN also minimizes both the forward and reverse Kullback-Leibler (KL) divergence in a single model, exploiting the complementary statistical properties of the two. We conduct extensive experiments and use various metrics for assessing the quality, diversity of generated images and convergence of the model. Our model is evaluated on two standard datasets: CIFAR-10 and CelebA demonstrating either superior or competitive performance compared to baseline GANs, especially in the earlier training stages. Our guided training procedure has been tested on different baseline GANs without any changes to their hyper-parameter configuration or architecture.

• Aggarwal, Swati; Sinha, Tushar; Kukreti, Yash & Shikhar, Siddarth (2020). Media bias detection and bias short term impact assessment. Array. ISSN 2590-0056. 6(July). doi: 10.1016/j.array.2020.100025. Vis sammendrag

  Today, media outlets are known to report news in a biased way, potentially affecting the beliefs of news consumers and altering their behaviors. Therefore, tracking bias in everyday news and building a platform where people can receive neutral and unequivocal news information is important. This research investigates media outlets for subjectivity versus objectivity by examining reported news events from their Twitter handles. The study subsequently proceeds to show how such subjective news articles program news consumers and condition their opinions. Eventually, a system which aids the detection of alarming biases in media is proposed through a unique bias short-term impact score calculation mechanism. With reference to a real-world event, ‘Demonetization in India’, a significant fraction of news tweets is found to be subjective in nature which are further observed as opinion conditioning agents for their consumers. Alarming biases are then detected in tweets in comparison with a neutral baseline.

• Mittal, Anshul & Aggarwal, Swati (2020). Hyperparameter optimization using sustainable proof of work in blockchain. Frontiers in Blockchain. 3. doi: 10.3389/fbloc.2020.00023. Vis sammendrag

  Hyperparameters are pivotal for machine learning models. The success of efficient calibration, often surpasses the results obtained by devising new approaches. Traditionally, human intervention is required to tune the models, however, this obtuse outlook restricts the proficiency and competence. Automating this crucial characteristic of learning sustainably, proffers a significant boost in performance and cost optimization. Blockchain technology has revolutionized industries utilizing its Proof-of-Work algorithms for consensus. This complicated solution generates a lot of useless computations across the nodes attached to the network and thus, fritters away a huge amount of precious energy. In this paper, we propose to exploit these inane computations for training deep learning models instead of calculating purposeless hash values, thus, suggesting a new consensus schema. This work distinguishes itself from other related works by capitalizing on the parallel processing prospects it generates for hyperparameter tuning of complex deep learning models. We address this aspect through the framework of Bayesian optimization which is an effective methodology for the global optimization of functions with expensive evaluations. We call our work, Proof of Deep Learning with Hyperparameter Optimization (PoDLwHO).

• Aggarwal, Swati; Saluja, Shivin; Gambhir, Varshika; Gupta, Shubhi & Satia, Simrat Pal Singh (2020). Predicting likelihood of psychological disorders in PlayerUnknown’s Battlegrounds (PUBG) players from Asian countries using supervised machine learning. Addictive Behaviours. ISSN 0306-4603. 101(February). doi: 10.1016/j.addbeh.2019.106132. Vis sammendrag

  Multiplayer Online Battle Arena (MOBA) has become one of the most popular genre of online video games played by gamers worldwide. Previous studies have exhibited that excessive engagement in games can lead to Internet Gaming Disorder (IGD). Internet Gaming Disorder has been associated with psychological disorders like impulsivity, anxiety and Attention Deficit Hyperactivity Disorder (ADHD). In this study, we propose an approach to use the game and player statistics along with self-esteem measure of a PlayerUnknown’s Battlegrounds (PUBG, a MOBA game) player to predict whether he/she suffers from IGD and psychological disorders namely ADHD and Generalized Anxiety Disorder (GAD). We extract the game and player statistics of PUBG players from Asian countries and then run several state of the art supervised machine learning models to predict the occurrence of IGD, ADHD, and GAD. Initial experiments and results show that we are able to predict IGD, ADHD, and GAD with an accuracy of 93.18%, 81.81% and 84.9% respectively. Game statistics of PUBG players show strong positive correlation with IGD and ADHD indicating detrimental effects of MOBA games.

• Aggarwal, Swati & Chugh, Nupur (2020). Ethical implications of closed loop brain device : 10‑year review. Minds and Machines. ISSN 0924-6495. 30(1), s. 145–170. doi: 10.1007/s11023-020-09518-7. Vis sammendrag

  Closed Loop medical devices such as Closed Loop Deep Brain Stimulation (CL-DBS) and Brain Computer Interface (BCI) are some of the emerging neurotechnologies. New generations of implantable brain–computer interfaces have recently gained success in human clinical trials. These implants detect specific neuronal patterns and provide the subject with information to respond to these patterns. Further, Closed Loop brain devices give control to the subject so that he can respond and decide on a therapeutic goal. Although the implants have improved subjects’ quality of life, their use has raised varied ethical concerns. The aim of this study is to provide an overview of the ethical implications specific to the therapeutic goals of closed loop brain implants. The authors analyze the related work qualitatively and quantitatively so as to help readers in understanding the various ethical implications of closed loop brain implants.

• Aggarwal, Swati; Agarwal, Nitika & Jain, Monal (2019). Performance analysis of uncertain k-means clustering algorithm using different distance metrics. I Verma, Nishchal K. & Ghosh, A. K. (Red.), Computational Intelligence : Theories, Applications and Future Directions - Volume I : ICCI-2017. Springer. ISSN 978-981-13-1132-1. s. 237–245. doi: 10.1007/978-981-13-1132-1_19. Vis sammendrag

  Real-world data generally deals with inconsistency. The uncertain k-means (UK-means) clustering algorithm, a modification of k-means, handles uncertain objects whose positions are represented by probability density functions (pdfs). Various techniques have been developed to enhance the performance of UK-means clustering algorithm but they are all centered on two major factors: choosing initial cluster centers and determining the number of clusters. This paper proposes that the measure of “closeness” is also a critical factor in deciding the quality of clusters. In this paper, the authors study the performance of UK-means clustering algorithm on four different distance functions using Haberman’s survival dataset. The analysis is performed on the basis of Davies–Bouldin index and purity values.

• Salik, Khwaja Mohd; Kumar, Yaman; Jain, Rohit; Aggarwal, Swati; Shah, Rajiv Ratn & Zimmermann, R. (2019). Lipper: speaker independent speech synthesis using multi-view lipreading, Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-57735-809-1. s. 10023–10024. doi: 10.1609/aaai.v33i01.330110023. Vis sammendrag

  Lipreading is the process of understanding and interpreting speech by observing a speaker's lip movements. In the past, most of the work in lipreading has been limited to classifying silent videos to a fixed number of text classes. However, this limits the applications of the lipreading since human language cannot be bound to a fixed set of words or languages. The aim of this work is to reconstruct intelligible acoustic speech signals from silent videos from various poses of a person which Lipper has never seen before. Lipper, therefore is a vocabulary and language agnostic, speaker independent and a near real-time model that deals with a variety of poses of a speaker. The model leverages silent video feeds from multiple cameras recording a subject to generate intelligent speech of a speaker. It uses a deep learning based STCNN+BiGRU architecture to achieve this goal. We evaluate speech reconstruction for speaker independent scenarios and demonstrate the speech output by overlaying the audios reconstructed by Lipper on the corresponding videos.

• Kumar, Yaman; Aggarwal, Swati; Mahata, Debanjan; Shah, Rajiv Ratn; Kumaraguru, Ponnurangam & Zimmermann, R. (2019). Get IT scored using AutoSAS : an automated system for scoring short answers, Proceedings of the AAAI Conference on Artificial Intelligence. AAAI Press. ISSN 978-1-57735-809-1. s. 9662–9669. doi: 10.1609/aaai.v33i01.33019662. Vis sammendrag

  In the era of MOOCs, online exams are taken by millions of candidates, where scoring short answers is an integral part. It becomes intractable to evaluate them by human graders. Thus, a generic automated system capable of grading these responses should be designed and deployed. In this paper, we present a fast, scalable, and accurate approach towards automated Short Answer Scoring (SAS). We propose and explain the design and development of a system for SAS, namely AutoSAS. Given a question along with its graded samples, AutoSAS can learn to grade that prompt successfully. This paper further lays down the features such as lexical diversity, Word2Vec, prompt, and content overlap that plays a pivotal role in building our proposed model. We also present a methodology for indicating the factors responsible for scoring an answer. The trained model is evaluated on an extensively used public dataset, namely Automated Student Assessment Prize Short Answer Scoring (ASAP-SAS). AutoSAS shows state-of-the-art performance and achieves better results by over 8% in some of the question prompts as measured by Quadratic Weighted Kappa (QWK), showing performance comparable to humans.

• Aggarwal, Swati & Chugh, Nupur (2019). Signal processing techniques for motor imagery brain computer interface : a review. Array. ISSN 2590-0056. 1-2(January-April). doi: 10.1016/j.array.2019.100003. Vis sammendrag

  Motor Imagery Brain Computer Interface (MI-BCI) provides a non-muscular channel for communication to those who are suffering from neuronal disorders. The designing of an accurate and reliable MI-BCI system requires the extraction of informative and discriminative features. Common Spatial Pattern (CSP) has been potent and is widely used in BCI for extracting features in motor imagery tasks. The classifiers translate these features into device commands. Many classification algorithms have been devised, among those Support Vector Machine (SVM) and Linear Discriminate Analysis (LDA) have been widely used. In recent studies, the researchers are using deep neural networks for the classification of motor imagery tasks. This paper provides a comprehensive review of dominant feature extraction methods and classification algorithms in brain-computer interface for motor imagery tasks. Authors discuss existing challenges in the domain of motor imagery brain-computer interface and suggest possible research directions.

• Mullick, Dhruv; Garg, Ayush; Bajaj, Arpit & Aggarwal, Swati (2018). Ant colony based fuzzy c-means clustering for very large data. I Kacprzyk, Janusz; Szmidt, Eulalia; Zadrożny, Slawomir; Atanassov, K. T. & Krawczak, Maciej (Red.), Advances in Fuzzy Logic and Technology 2017 : Proceedings of: EUSFLAT- 2017 – The 10th Conference of the European Society for Fuzzy Logic and Technology, September 11-15, 2017, Warsaw, Poland IWIFSGN’2017 – The Sixteenth International Workshop on Intuitionistic Fuzzy Sets and Generalized Nets, September 13-15, 2017, Warsaw, Poland, Volume 2. Springer. ISSN 978-3-319-66823-9. s. 578–591. Vis sammendrag

  Fuzzy C-Means (FCM) is a popular technique for clustering of data. It combines the concepts of K-Means algorithm and Fuzzy set theory. However, FCM faces the challenges of running into a local optimal value, and of producing results which are sensitive to initialisation conditions. To solve these problems, there has been prior work which incorporates Ant Colony Optimisation (ACO) into the conventional FCM algorithm. The authors of this paper find that though the FCM-ACO algorithm is a definite improvement over the traditional FCM, there is still scope for improving the scalability and accuracy of the system. The authors propose using a Multi Round Sampling (MRS) technique along with Ant colony Optimisation. The proposed algorithm allows us to cluster the dataset without considering it entirely, hence allowing for a more space and time efficient system. This makes the system highly scalable and hence suitable for large datasets. Moreover, extensive experiments on several publicly available datasets, both large and small, prove that the proposed algorithm of Multi Round Sampling of Ant Colony based Fuzzy C-Means (MRSA-FCM) gives superior clustering results, over the FCM and FCM-ACO systems.

• Kalra, Divyanshu; Dwivedi, Chaitanya & Aggarwal, Swati (2018). Classifier dependent dimensionality reduction for resource restricted environments. I Panda, Brajendra; Sharma, Sudeep & Roy, Nihar Ranjan (Red.), Data Science and Analytics : 4th International Conference on Recent Developments in Science, Engineering and Technology, REDSET 2017, Gurgaon, India, October 13-14, 2017, Revised Selected Papers. Springer. ISSN 978-981-10-8527-7. s. 177–186. doi: 10.1007/978-981-10-8527-7_16. Vis sammendrag

  High dimensionality problems have become prevalent in present day machine learning applications. The voluminous datasets acquired from sources like cameras, spectroscopes, and other sensors need to be analysed and modelled in a way that uses the available computational resources most efficiently. The paper proposes a genetic algorithm optimised neural network model that takes care of the issue mentioned above. A comparison is also drawn between the results produced by the proposed model and those produced by other contemporary dimensionality reduction algorithms.

• Aggarwal, Swati; Bhandari, Lehar; Kapoor, Karan & Kaur, Jaswin (2018). Weighted fuzzy KNN optimized by simulated annealing for classification of large data : a new approach to skin detection. I Panda, Brajendra; Sharma, Sudeep & Roy, Nihar Ranjan (Red.), Data Science and Analytics : 4th International Conference on Recent Developments in Science, Engineering and Technology, REDSET 2017, Gurgaon, India, October 13-14, 2017, Revised Selected Papers. Springer. ISSN 978-981-10-8527-7. s. 156–163. doi: 10.1007/978-981-10-8527-7_14. Vis sammendrag

  Machine learning is being used in every field. In almost all technical and financial domains, machine learning is being used enormously from predicting new outcomes to classifying a given data into multiple sets. In this research work it has been tried to build and expand upon previously built binary classifiers to develop a unique classifier for skin detection that separates the given input data into two sets – Skin segment and Non-Skin segment. Skin Detection essentially means detecting in an image or video pixels or regions which are of the skin color. The input data given to the classifier has three attributes - value of the red, green and blue channel. The combination of these three values is the color of the object seen. The classifier classifies the input data into the above two classes on the basis of these attributes. In general, this classifier can be extended to any binary class data.

• Kataria, Shreya; Sangal, Somya; Tyagi, Twishi & Aggarwal, Swati (2018). Augmented gene expression programming : a population diversifying paradigm. I Yen, Gary G. (Red.), 2018 IEEE Congress on Evolutionary Computation (CEC). IEEE conference proceedings. ISSN 978-1-5090-6017-7. s. 1–7. doi: 10.1109/CEC.2018.8477656.
• Bhutani, Kanika & Aggarwal, Swati (2018). A novel approach for data classification using neutrosophic entropy. I Muttoo, Sunil Kumar (Red.), System and Architecture : Proceedings of CSI 2015. Springer Nature. ISSN 978-981-10-8533-8. s. 305–317. doi: 10.1007/978-981-10-8533-8_29. Vis sammendrag

  Fuzzy classification is very necessary because it has the ability to use interpretable rules. It has got control over the limitations of crisp rule-based classification. This paper mainly deals with classification using fuzzy probability and Neutrosophic probability. Classification based on Neutrosophic probability employs Neutrosophic logic, Neutrosophic probability, and Neutrosophic entropy for its working and is compared with classification based on fuzzy probability on the basis of parameters such as probability and ambiguity in the results. Classification based on fuzzy and Neutrosophic probabilities is implemented on appendicitis dataset from knowledge extraction based on evolutionary learning.

• Sawhney, Ramit; Manchanda, Prachi; Singh, Raj & Aggarwal, Swati (2018). A computational approach to feature extraction for identification of suicidal ideation in tweets . I Shwartz, Vered; Tabassum, Jeniya; Voigt, Rob; Che, Wanxiang; de Marneffe, Marie-Catherine & Nissim, Malvina (Red.), Proceedings of ACL 2018, Student Research Workshop. Association for Computational Linguistics. ISSN 9781510867079. s. 91–98. doi: 10.18653/v1/P18-3013.
• Garg, Ayush; Naryani, Deepika; Aggarwal, Garvit & Aggarwal, Swati (2018). DL-GSA : a deep learning metaheuristic approach to missing data imputation. I Tan, Ying; Shi, Yuhui & Tang, Qirong (Red.), Advances in Swarm Intelligence : 9th International Conference, ICSI 2018, Shanghai, China, June 17-22, 2018, Proceedings, Part II. Springer. ISSN 978-3-319-93818-9. s. 513–521. doi: 10.1007/978-3-319-93818-9_49. Vis sammendrag

  Incomplete data has emerged as a prominent problem in the fields of machine learning, big data and various other academic studies. Due to the surge in deep learning techniques for problem-solving, in this paper, authors have proposed a deep learning-metaheuristic approach to combat the problem of imputing missing data. The proposed approach (DL-GSA) makes use of the nature inspired metaheuristic, Gravitational search algorithm, in combination with a deep-autoencoder and performs better than existing methods in terms of both accuracy and time. Owing to these improvements, DL-GSA has wider applications in both time and accuracy sensitive areas like imputation of scientific and research datasets, data analysis, machine learning and big data.

• Jain, Satvik; Verma, Siddharth; Kumar, Swaraj & Aggarwal, Swati (2018). An evolutionary learning approach to play Othello using XCS. I Yen, Gary G. (Red.), 2018 IEEE Congress on Evolutionary Computation (CEC). IEEE conference proceedings. ISSN 978-1-5090-6017-7. s. 1–18. doi: 10.1109/CEC.2018.8477644. Vis sammendrag

  Due to the multifarious challenges that emerge when developing an artificial intelligent (AI) agent that can compete with human players, the classic game of Othello has received a lot of attention from the Computational-Intelligence community. This paper proposes an AI agent that learns a winning strategy for the game of Othello using the eXtended Classifier System (XCS) algorithm which is a popular variant of the Learning Classifier System (LCS) algorithm. Othello has been a favourite in the study of AI due to its simple set of rules, low branching factor and well defined strategic concepts. The LCS system consists of a rule-set which is made to evolve using a combination of Reinforcement Learning (RL) and Genetic Algorithm (GA) such that the evolved rule-set learns an optimal action for each board state. A 6×6 Othello board will be used for this experiment in order to evaluate the applicability of the proposed agent in learning a winning game-playing strategy. The performance of the proposed agent was evaluated against three categories of agents: minimax, human and random agent. The XCS agent was able to outperform the above-mentioned agents showing the effectiveness of rule-based evolutionary learning in Othello. This work demonstrates the possibility of using the XCS algorithm in other strategy-based combinatorial games.

• Aggarwal, Swati; Bansal, Prakriti & Garg, Sameer (2018). EEG signals for measuring cognitive development. I Tiwary, Uma Shanker (Red.), Intelligent Human Computer Interaction : 10th International Conference, IHCI 2018, Allahabad, India, December 7–9, 2018, Proceedings. Springer. ISSN 978-3-030-04021-5. s. 69–77. doi: 10.1007/978-3-030-04021-5_7. Vis sammendrag

  The use of EEG signals for measuring cognitive development is an upcoming field of research for a strong cognitive analysis to revolutionize the field of biomedical informatics and neuroscience. This paper highlights the importance of EEG signals in cognitive development experimentation and the challenges faced in conducting an EEG experiment and its intelligent analysis. Solutions to these challenges have been elaborated upon as well. Finally, the paper discusses future prospects in EEG research. A focus on these issues is essential for conducting successful EEG experimentation and choosing an accurate and precise EEG signal analysis methodology.

• Dwivedi, Chaitanya; Kalra, Divyanshu; Naidu, Divesh & Aggarwal, Swati (2018). Keystroke dynamics based biometric authentication : a hybrid classifier approach. I Sundaram, Suresh (Red.), 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE conference proceedings. ISSN 978-1-5386-9276-9. s. 266–273. doi: 10.1109/SSCI.2018.8628852. Vis sammendrag

  The increased use of computers in our day to day activities has marked the necessity to develop efficient methods of user identification for authentication purposes. The tasks of utmost importance are becoming dependent on computers for their completion. Under such circumstances it is essential that the whole process is least susceptible to breaches. The ease of accessibility and availability of keyboards in a computer system make it an economical source to generate characteristic biometric data. Therefore, keystroke dynamics has become a topic of research interest in recent times. Despite the huge potential keystroke dynamics has, there are a few shortcomings in the prevalent approaches that need to be addressed. The current accuracy measures prevent this method from being accepted as an industry standard. Furthermore, in some cases the computational time required to train a model before deployment becomes so large that it is virtually impossible to use such algorithms in daily life. The model proposed in this paper tries to overcome these drawbacks and improves upon the current performance measures.

• Priyadarshi, Aman; Gupta, Aastha & Aggarwal, Swati (2018). Synthesis of neural networks using entangled neurons. I Sundaram, Suresh (Red.), 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE conference proceedings. ISSN 978-1-5386-9276-9. s. 2207–2211. doi: 10.1109/SSCI.2018.8628808. Vis sammendrag

  The large neural networks are computationally intensive and face the optimization issue that prevents efficient training. This led to having a strong interest in obtaining efficient neural networks for applications where computing resource is limited both in terms of speed and memory. In this paper, the authors propose to design efficient neural networks using genetic algorithm and cellular encoding. They also introduce the concept of entangled neurons. Entangled neurons are a group of neurons that share the same weight vector that can simulate filters of Convolutional Neural Network (or CNN). This helps in widening the search space of genetic algorithm by exploring complex architectures with neurons sharing weights. The resultant architecture is not only comparable to the state-of-art architecture in terms of test accuracy, it also reduces the training time and the number of trainable parameters compared to the state-of-art networks.

• Bhavan, Anjali & Aggarwal, Swati (2018). Stacked generalization with wrapper-based feature selection for human activity recognition. I Sundaram, Suresh (Red.), 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE conference proceedings. ISSN 978-1-5386-9276-9. s. 1064–1068. doi: 10.1109/SSCI.2018.8628830. Vis sammendrag

  Human Activity Recognition has widespread usage in the fields of healthcare and human-centric computing, which is why it is important to build efficient and robust systems for accurate predictions for the same. Ensemble-based methods are also fast gaining acceptance for their ability to significantly enhance prediction quality and accuracy while also maintaining efficiency. In this context a stacked ensemble for predicting human activity as measured by a smartphone is described. Boruta, a wrapper-based all-relevant feature selection method is used before model training, and its effect on model metrics with filter-based methods and a hybrid of both methods compared. Stacking with Boruta gave an overall accuracy of 97.01%, which is an improvement over previous work (including improved accuracy in individual activities as well) and also better than simple variance-based filtering and the hybrid of both methods, which gave an accuracy of 94.07% and 93.43% respectively.

• Agarwal, Sarthak; Saxena, Vaibhav; Singal, Vaibhav & Aggarwal, Swati (2018). LSTM based music generation with dataset preprocessing and reconstruction techniques. I Sundaram, Suresh (Red.), 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE conference proceedings. ISSN 978-1-5386-9276-9. s. 455–462. doi: 10.1109/SSCI.2018.8628712. Vis sammendrag

  Numerous approaches have been used by researchers for the purpose of music generation. Recurrent neural networks (RNNs) and Long short term memory (LSTM) networks are able to effectively model sequential data. LSTM networks have been extensively used to produce sheet music, character by character. These LSTM models, however, require a lot of time to train to be able to produce pleasant and syntactically correct sheet music. We introduce some effective dataset preprocessing and reconstruction techniques which facilitate the generation of syntactically correct sheet music, while reducing the training time. The quality of music generated is qualitatively measured by peers. The proposed model employing the dataset preprocessing and reconstruction techniques is compared with another model possessing no such techniques in a subjective manner.

• Agrawal, Shivli; Kirtani, Yukti; Girdhar, Yukti & Aggarwal, Swati (2018). Hindi sentence classification for expressive storytelling systems. I Sundaram, Suresh (Red.), 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE conference proceedings. ISSN 978-1-5386-9276-9. s. 2019–2025. doi: 10.1109/SSCI.2018.8628858. Vis sammendrag

  This paper proposes a method to classify sentences taken from short stories written in Hindi language into their discourse modes - narrative and dialogue. The automated classification improves the user experience with expressive speech. The classification has been attempted using the Bidirectional LSTM (Long Short Term Memory) units RNN (Recurrent Neural Network) model and a hybrid of CNN (Convolutional Neural Network) and LSTM. CNN-SVM (Support Vector Machine) which is the current best model has been taken as baseline. The proposed CNN-LSTM hybrid model with contextual word embeddings achieves better accuracy in Hindi language story sentence classification.

• Aggarwal, Sagar; Aggarwal, Luv; Rihal, Manshubh Singh & Aggarwal, Swati (2018). EEG based participant independent emotion classification using gradient boosting machines. I Goswami, Anurag (Red.), 2018 IEEE 8th International Advance Computing Conference (IACC) . IEEE conference proceedings. ISSN 978-1-5386-6678-4. s. 266–271. doi: 10.1109/IADCC.2018.8692106. Vis sammendrag

  Analysis of EEG (Electroencephalography) signals provides an alternative ingenious approach towards Emotion recognition. Nowadays, Gradient Boosting Machines (GBMs) have emerged as state-of-the-art supervised classification techniques used for robust modeling of various standard machine learning problems. In this paper, two GBM's (XGBoost and LightGBM) were used for emotion classification on DEAP Dataset. Furthermore, a participant independent model was fabricated by excluding participant number from features. The proposed approach performed well with high accuracies and faster training speed.

• Jain, Aashi; Gupta, Divya; Gupta, Garima & Aggarwal, Swati (2017). Applications of computing with words in medicine : promises and potential. I ., Ukjent (Red.), 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE conference proceedings. ISSN 978-1-5090-6034-4. s. 1–6. doi: 10.1109/FUZZ-IEEE.2017.8015480. Vis sammendrag

  Computing with Words (CW) is a concept which solves problems when input is provided in form of natural language. CW is at its initial stages and is not at its full potential Medicine is a pivotal field and CW has barely been explored here. This paper concentrates on how to use CW methods to overcome challenging problems in medicine. It especially focuses on finding a solution to help Dementia affected people whose symptoms are not curable. The latter part lists down some more ways in which CW can affect areas in medicine.

• Kumar, Megha & Aggarwal, Swati (2017). A novel model to handle uncertainity using Rough sets and Neutrosophic relational maps. I ., Ukjent (Red.), 2017 14th IEEE India Council International Conference (INDICON). IEEE conference proceedings. ISSN 978-1-5386-4318-1. s. 1–6. doi: 10.1109/INDICON.2017.8487741. Vis sammendrag

  Rough set theory is a new mathematical approach for uncertain knowledge. The main advantage of using rough sets is that it does not need any additional or prior information about data. This paper discusses about the hybrid model of rough sets with relational maps to represent the mapping between consistent set of attributes of the dataset to decision classes. The proposed model is tested on 7 led dataset where the rough sets are implemented to get the important reducts of the attributes for decision making and relational maps are used to map reducts with the decision classes. The two extensions of relational maps: Fuzzy relational maps and Neutrosophic relational maps are implemented in the dataset and is shown how Neutrosophic relational maps gives better results as compared to Fuzzy relational maps by considering indeterminate relations.

• Bhutani, Kanika & Aggarwal, Swati (2017). Neutrosophic rough soft set : a decision making approach to appendicitis problem. Neutrosophic Sets and Systems. ISSN 2331-608X. 16. Vis sammendrag

  Classification based on fuzzy logic techniques can handle uncertainty to a certain extent as it provides only the fuzzy membership of an element in a set. This paper implements the extension of fuzzy logic: Neutrosophic logic to handle indeterminacy, uncertainty effectively. Classification is done on various techniques based on Neutrosophic logic i.e. Neutrosophic soft set, rough Neutrosophic set, Neutrosophic ontology to provide better results in comparison to fuzzy logic based techniques. It is proved that rough neutrosophic soft set will handle indeterminacy effectively that exists in the medical domain as it provides the minimum and maximum degree of truth, indeterminacy, falsity for every element.

• Aggarwal, Swati & Azad, Venu (2016). A hybrid system based on FMM and MLP to diagnose heart disease. I Bhattacharyya, Siddhartha; De, Sourav; Pan, Indrajit & Dutta, Paramartha (Red.), Intelligent multidimensional data clustering and analysis. IGI Global. ISSN 9781522517764. s. 293–325. doi: 10.4018/978-1-5225-1776-4.ch011. Vis sammendrag

  In the medical field diagnosis of a disease at an early stage is very important. Nowadays soft computing techniques such as fuzzy logic, artificial neural network and Neuro- fuzzy networks are widely used for the diagnosis of various diseases at different levels. In this chapter, a hybrid neural network is designed to classify the heart disease data set the hybrid neural network consist of two types of neural network multilayer perceptron (MLP) and fuzzy min max (FMM) neural network arranged in a hierarchical manner. The hybrid system is designed for the dataset which contain the combination of continuous and non continuous attribute values. In the system the attributes with continuous values are classified using the FMM neural networks and attributes with non-continuous value are classified by using the MLP neural network and to synthesize the result the output of both the network is fed into the second MLP neural network to generate the final result.

• Aggarwal, Swati & Azim, Shambeel (2016). Outliers, missing values, and reliability : an integrated framework for pre-processing of coding data. I Sangaiah, Arun Kumar; Gao, Xiao-Zhi & Abraham, Ajith (Red.), Handbook of research on fuzzy and rough set theory in organizational decision making. IGI Global. ISSN 9781522510086. s. 316–330. doi: 10.4018/978-1-5225-1008-6.ch014. Vis sammendrag

  Reliability is a major concern in qualitative research. Most of the current research deals with finding the reliability of the data, but not much work is reported on how to improve the reliability of the unreliable data. This paper discusses three important aspects of the data pre-processing: how to detect the outliers, dealing with the missing values and finally increasing the reliability of the dataset. Here authors have suggested a framework for pre-processing of the inter-judged data which is incomplete and also contains erroneous values. The suggested framework integrates three approaches, Krippendorff's alpha for reliability computation, frequency based outlier detection method and a hybrid fuzzy c-means and multilayer perceptron based imputation technique. The proposed integrated approach results in an increase of reliability for the dataset which can be used to make strong conclusions.

• Aggarwal, Swati & Bishnoi, Anurag (2016). Neutrosophic trust evaluation model in B2C e-commerce. I Bhattacharyya, Siddhartha; Dutta, Paramartha & Chakraborty, Susanta (Red.), Hybrid soft computing approaches : research and applications. Springer. ISSN 978-81-322-2978-0. s. 405–427. doi: 10.1007/978-81-322-2544-7_14. Vis sammendrag

  Trust is an important term in the context of E-Commerce. It lies at the top in the present trend of E-Commerce. Trust lists the diverse prospects of trustworthiness that exist between the merchant and customer, inducing a better customer liking and Business-to-Customer (B2C) E-Commerce. Considering the imprecise nature of E-Commerce trust, various researchers proposed different trust models and integrated them with fuzzy logic to handle inherent uncertainty. Conventional models of trust are based on subjective logic which falls short in mapping the real-time environment of E-commerce that deals with tentative behavioural values. Though fuzzy logic representation of the facts is a way to deal with improbability but it fails to capture the indeterminacy and false values given by respondents during survey. Authors in this chapter have attempted to target the indeterminacy involved while capturing the perception of respondents during survey for any website. Quite recently, neutrosophic logic (NL) has been proposed by Florentine Smarandache that gives a mathematical model for representing uncertainty, vagueness, ambiguity, imprecision, incompleteness, inconsistency, redundancy and contradictions. All the factors stated are very integral to human thinking, as it is very rare that we tend to conclude/judge in definite environments, imprecision of human systems could be due to the imperfection of knowledge that the human receives (observation) from the external world. Imperfection leads to a doubt about the value of a variable, a decision to be taken or a conclusion to be drawn for the actual system. This chapter suggests computation of perceived trust value by integrating a neutrosophic logic with the proposed fuzzy based trust model that considers all the chief features which affect the trust in E-Commerce.

• Azim, Shambeel & Aggarwal, Swati (2016). Using fuzzy c means and multi layer perceptron for data imputation : simple v/s complex dataset. I ., Ukjent (Red.), 2016 3rd International Conference on Recent Advances in Information Technology (RAIT). IEEE conference proceedings. ISSN 9781479985807. s. 197–202. Vis sammendrag

  Data imputation is the process of filling in the missing value to generate complete records. Complete databases can be analyzed more accurately in comparison to incomplete databases. This paper implements a 2-stage hybrid model for filling in the missing values. Also the effect of the proposed model over simple and complex dataset with varying percentage of missing value and varying value of fuzzifier is evaluated. The accuracy of the model is checked with Mean Absolute Percentage Error (MAPE). The result obtained shows that the proposed model is more accurate in filling multiple values in a record compared to stage 1 alone.

• Gupta, Vidushi & Aggarwal, Swati (2016). Applications of fuzzy learning automata a review. I ., Ukjent (Red.), 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom). IEEE conference proceedings. ISSN 9781467394178. s. 3666–3671. Vis sammendrag

  In this paper, prominent work done on fuzzy learning automata by researchers in different domains during last decade (2005-2015) is discussed. It was observed that work has been done on applications of fuzzy learning automata only. Fuzzy Learning automata is used in the operation of image sharpening, detection of edge, to efficiently control traffic signal, and acknowledge normal and abnormal human behavior in real time. Another interesting application is Multi Objective Reactive Power Planning. In web page ranking, summarizing of text and car navigation system fuzzy learning automata plays an important role.

• Aggarwal, Swati; Sharma, Kushagra & Priyadarshini, Manisha (2016). Robot navigation : review of techniques and research challenges. I ., Ukjent (Red.), 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom). IEEE conference proceedings. ISSN 9781467394178. s. 3660–3665. Vis sammendrag

  Robot navigation has multi-spectral applications across a plethora of industries. Being one of the fastest evolving field of Artificial intelligence, it has garnered a lot of speculation and the problem of efficient Robot navigation has become a talking point in the “Artificial Intelligence research community”. Robot Navigation can be thought of as a collection of sub-problems that when solved efficiently will (most likely) give the complete and the most efficient solution. While the main Navigation problem can be divided into numerous smaller ones some of the prevalent (sub)-tasks associated with Robot Navigation are Path Planning, Collision Prevention, Search Algorithm and an appropriate pictorial (graphical) representation of the given environment. Path Planning gives us the most optimal path finding approach while keeping the dynamism of the environment and the objects in mind. Collision Prevention ensures the Robot reaches its goal without colliding with any of the objects present in the environment. Collision Prevention techniques' vitality increases considerably when the number of objects in the input space is large (>10, approximately). Search Algorithms are the functional units of this problem as they determine the path the Robot follows while traveling to its destination. Since the environment greatly affects the choice of technique for all the other tasks it is vital to have a clear, concise and a non-ambiguous representation of the same. The main aim of the paper is to summarise the development of various techniques in the multiple domains of the Robot Navigation problem in the last fifteen years (2000-2015) while stating the scope and the restriction of each of them.

• Aggarwal, Swati; Agarwal, Nitika & Jain, Monal (2016). Uncertain data mining : a review of optimization methods for UK-means. I ., Ukjent (Red.), 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom). IEEE conference proceedings. ISSN 9781467394178. s. 3672 –3677. Vis sammendrag

  Real world data generally deals with uncertainty. The complexity of data uncertainty poses many challenges. The most widely used k-means clustering algorithm is used for cluster analysis. However, it doesn't deal with uncertain data. The UK-means algorithm, a modification of k-means handles uncertain objects whose locations are represented by probability density functions (pdfs). It computes expected distances(EDs) between objects' pdf and cluster representatives using costly numerical integrations. This paper provides a review about the current state-of-the-art pruning techniques in order to improve the efficiency and countervail the computational complexity of UK-means based upon extensive research performed during the last decade. These are Min-Max bounding box (BB) based technique which uses two ways to calculate bounds: metric and trigonometric. Then, Voronoi based techniques to reduce ED calculations and indexing using R-Tree to reduce pruning overheads are discussed. Finally, hybrid techniques are observed to be feasible for real world employment.

• Bhutani, Kanika; Kumar, Megha; Garg, Gaurav & Aggarwal, Swati (2016). Assessing it projects success with extended fuzzy cognitive maps & neutrosophic cognitive maps in comparison to fuzzy cognitive maps. Neutrosophic Sets and Systems. ISSN 2331-608X. 12, s. 9–19. Vis sammendrag

  IT projects hold a huge importance to economic growth. Today, half of the capital investments are in IT technology. IT systems and projects are extensive and time consuming; thus implying that its failure is not affordable, so proper feasibility study of assessing project success factors is required. A current methodology like Fuzzy Cognitive Maps has been experimented for identifying and evaluating the success factors in IT projects, but this technique has certain limitations. This paper discusses two new approaches to evaluate IT project success: Extended Fuzzy Cognitive Maps (E-FCM) & Neutrosophic Cognitive Maps (NCM).The limitations of FCM like non consideration for non-linear, conditional, time delay weights and indeterminate relations are targeted using E-FCM and NCM in this paper.

• Gaurav, Megha Kumar; Bhutani, Kanika & Aggarwal, Swati (2016). Mapping causes and implications of India’s skewed sex ratio and poverty problem using Fuzzy & Neutrosophic Relational Maps. Neutrosophic Sets and Systems. ISSN 2331-608X. 11, s. 45–56. Vis sammendrag

  Numerous studies by different researchers have confirmed that skewed sex ratio is a critical social problem in India. This enduring problem of gender imbalance is the collective result of factors like sex selective abortion, gender discrimination, son preference for the preservation of tribe, emergence of new technologies in medical field and many more factors. Another severe problem to be addressed in India is poverty. Many factors contribute to the perpetuation of poverty such as illiteracy, bad governance, under employment and various other reasons. Despite of India's accelerated growth rate, poverty in India is still prevalent. This paper employs a new soft computing based methodology for identifying and analyzing the relationships among the causes and implications of the two challenging problems in India: unbalanced sex ratio and poverty. The methodology proposed by authors is based on Linked Fuzzy Relational Maps which is a variation to Fuzzy Relational Maps and Linked Neutrosophic Relational Maps which is a variation to Neutrosophic Relational Maps. The relationships among the causes and consequences can be easily drawn through the given methodologies. The authors have implemented two models for the two social problems under study, one using Fuzzy Relational Maps and the other using Neutrosophic Relational Maps. Neutrosophic Relational Maps can support decision making on uncertain and indeterminate data. Authors have demonstrated that the model implemented using Neutrosophic Relational Maps presents more realistic and sensitive results as compared to the model using Fuzzy Relational Maps.

• Gaurav, -; Kumar, Megha; Bhutani, Kanika & Aggarwal, Swati (2015). Understanding India's skewed sex ratio problem using cognitive maps. I ., Ukjent (Red.), 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE conference proceedings. ISSN 9781467374293. s. 1–8. doi: 10.1109/FUZZ-IEEE.2015.7337805. Vis sammendrag

  Recent studies have confirmed that the problem of female deficit in India is the result of sex selective abortion, negligence of girls, infanticides and foeticide, preference of son for the preservation for clan, gender bias and emergence of new technologies in medical field. This paper addresses this critical problem of gender inequality in India using fuzzy cognitive maps. Fuzzy cognitive maps model the world as a collection of classes and causal relation between classes. Authors have attempted to explore the relationships and the relative impacts among the causes; that fuels this crucial problem.

• Gaurav, -; Kumar, Megha; Bhutani, Kanika & Aggarwal, Swati (2015). Hybrid model for medical diagnosis using Neutrosophic Cognitive Maps with Genetic Algorithms. I ., Ukjent (Red.), 2015 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE conference proceedings. ISSN 9781467374293. s. 1–7. doi: 10.1109/FUZZ-IEEE.2015.7338015. Vis sammendrag

  This paper presents a combination of two soft computing techniques: Neutrosophic cognitive maps and Genetic algorithm for modeling of medical disease diagnosis. Earlier, medical decision support system was proposed by many researchers where cognitive maps along with genetic algorithm were experimented. The hybrid model of fuzzy cognitive maps with genetic algorithm was implemented to handle situations where decisions are not clearly distinct. In real world situation data is not always consistent so, authors proposed a new hybrid model of Neutrosophic Cognitive Maps with Genetic Algorithms to handle indeterminacy. The proposed model will provide distinct diagnosis of disease in medical decision support system.

• Bhutani, Kanika; Kumar, Megha; Dahiya, Sonakshi; Gaurav, - & Aggarwal, Swati (2015). Cognitive maps analysis of a social evil : corruption. I ., Ukjent (Red.), 2015 International Conference on Cognitive Computing and Information Processing(CCIP). IEEE conference proceedings. ISSN 9781479971725. s. 1–6. doi: 10.1109/CCIP.2015.7100684. Vis sammendrag

  These days corruption can be seen in every section of society. If certain changes are not made, corruption will continue to be an issue in the society. This paper surveys and discusses various issues related to the causes of corruption using soft computing technique known as FCM (Fuzzy Cognitive Mapping) and E-FCM (Extended Fuzzy Cognitive Maps). A comparative study between FCM and E-FCM is conducted showing E-FCM is a better technique than FCM.

• Bhutani, Kanika; Kumar, Megha & Aggarwal, Swati (2015). Multi-attribute data classification using Neutrosophic probability. I ., Ukjent (Red.), 2015 Annual IEEE India Conference (INDICON). IEEE conference proceedings. ISSN 9781467374002. s. 1–5. doi: 10.1109/INDICON.2015.7443599. Vis sammendrag

  Fuzzy classification is very necessary because it has the ability to use interpretable rules. It has got control over the limitations of crisp rule based classification. This paper mainly deals with classification using fuzzy probability and Neutrosophic probability. Classification based on Neutrosophic probability employs Neutrosophic logic and Neutrosophic probability for its working and is compared with classification based on fuzzy probability on the basis of parameters such as probability and ambiguity in the results. Classification based on fuzzy and Neutrosophic probability are implemented on appendicitis dataset from Knowledge extraction based on evolutionary learning.

• Bhutani, Kanika & Aggarwal, Swati (2015). Experimenting with neutrosophic ontologies for medical data classification. I ., Ukjent (Red.), 2015 IEEE Workshop on Computational Intelligence : Theories, Applications and Future Directions (WCI). IEEE conference proceedings. ISSN 9781467382199. s. 1–6. doi: 10.1109/WCI.2015.7495535. Vis sammendrag

  Ontology helps us to think about the real world with its semantic constraints. But there exist different uncertainties and ambiguities that cannot be considered using traditional ontologies. This paper mainly deals with classification using fuzzy ontology and Neutrosophic ontology. Classification based on Neutrosophic ontology incorporates Neutrosophic logic for its working and is compared with classification based on fuzzy ontology on appendicitis dataset from Knowledge extraction based on evolutionary learning.

• Azim, Shambeel & Aggarwal, Swati (2014). Hybrid model for data imputation : using fuzzy c means and multi layer perceptron. I ., Ukjent (Red.), 2014 IEEE International Advance Computing Conference (IACC). IEEE conference proceedings. ISSN 9781479925735. s. 1281–1285. doi: 10.1109/IAdCC.2014.6779512.
• Rathi, Venu & Aggarwal, Swati (2014). Comparing the performance of ANN with FNN on mammography mass data set. I ., Ukjent (Red.), 2014 IEEE International Advance Computing Conference (IACC). IEEE conference proceedings. ISSN 9781479925735. s. 1307–1314. doi: 10.1109/IAdCC.2014.6779516. Vis sammendrag

  Nowadays soft computing techniques such as fuzzy logic, artificial neural network and neuro- fuzzy networks are widely used for the diagnosis of various diseases at different levels. These diagnosing systems help in early detection of diseases and assist the patient to get proper medication in time. In this paper, the artificial neural network such as multilayer perceptron neural network and radial basis neural network and their hybrid model i.e. combination of fuzzy logic with neural networks (FNN) are introduced to classify the mammography mass data set into two classes benign and malignant on the basis of mammography mass data set attributes. The comparison of the ANNs' performance is done with the FNN models. In the system, the missing value of records is handled using mean substitution method. A four - fold cross validation method is used for the assessment of generalization of the system. The result shows that the FNN networks perform better than the artificial neural networks with an accuracy of 87.50% and 90.00 % and proving their usefulness in classification of mammography mass data.

• Anurag, - & Aggarwal, Swati (2014). Fuzzy based trust model to evaluate and analyse trust in B2C E-Commerce. I ., Ukjent (Red.), 2014 IEEE International Advance Computing Conference (IACC). IEEE conference proceedings. ISSN 9781479925735. s. 1300–1306. doi: 10.1109/IAdCC.2014.6779515. Vis sammendrag

  Trust lies at the acme in this competitive trend of E-Commerce. Trust enumerates the different prospects of trustworthiness that are sculpted between the vendor and customer, inducing a better customer satisfaction and Business-to-Customer (B2C) E-Commerce. Considering the vagueness and ambiguity of E-Commerce trust different trust models coupled with Fuzzy Logic (FL) have been implemented through time. In this paper we proposed a fuzzy based trust model where all the important facets that affect the trust are taken into account. Traditional trust models were based on subjective logic which fails to map the real time environment of E-commerce that deals with uncertain behavioral values, Fuzzy logic is a way to deal with uncertainty.

• Goyal, Lalit & Aggarwal, Swati (2014). C-based algorithm to avoid static obstacles in robot navigation. I ., Ukjent (Red.), 2014 IEEE International Advance Computing Conference (IACC). IEEE conference proceedings. ISSN 9781479925735. s. 68–73. doi: 10.1109/IAdCC.2014.6779296. Vis sammendrag

  Mobile robots have the capability to navigate in the environment. We need some approaches for their collision-free and stable navigation. Authors have given their own algorithm and have implemented in C- language to move a robot from initial to final position. They have also shown the comparison in path length required by robot with the model proposed by Sir Parhi et al. in 2009.

• Ansari, A. Q.; Biswas, Ranjit & Aggarwal, Swati (2013). Extension to fuzzy logic representation : moving towards neutrosophic logic - A new laboratory rat. I ., Ukjent (Red.), 2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). IEEE conference proceedings. ISSN 9781479900213. s. 1–8. doi: 10.1109/FUZZ-IEEE.2013.6622412. Vis sammendrag

  Real world problems have been effectively modeled using fuzzy logic that gives suitable representation of real-world data/information and enables reasoning that is approximate in nature. It is quite uncommon that the inputs captured by the fuzzy models are 100% complete and determinate. Though, humans can take intelligent decisions in such situations but fuzzy models require complete information. Incompleteness and indeterminacy in the data can arise from inherent non-linearity, time-varying nature of the process to be controlled, large unpredictable environmental disturbances, degrading sensors or other difficulties in obtaining precise and reliable measurements. Neutrosophic logic is an extended and general framework for measuring the truth, indeterminacy and falsehood-ness of the information. It is effective in representing different attributes of information like inaccuracy, incompleteness and ambiguous, thus giving fair estimate about the reliability of information. This paper suggests extending the capabilities of fuzzy representation and reasoning system by introducing Neutrosophic representation of the data and Neutrosophic reasoning system.

• Aggarwal, Swati; Chugh, Nupur & Balyan, Arnav (2013). Identification of ADHD disorder in children using EEG based on visual attention task by ensemble deep learning. I Saraswat, Mukesh; Chowdhury, Chandreyee; Kumar Mandal, Chintan & Gandomi, Amir H. (Red.), Proceedings of International Conference on Data Science and Applications : ICDSA 2022, Volume 2. Springer Nature. ISSN 978-981-19-6634-7. s. 243–259. doi: 10.1007/978-981-19-6634-7_18. Vis sammendrag

  Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental illness that is complicated, universal, and heterogeneous. Children with ADHD have a hard time staying focused and managing their activities. For children with ADHD, which is today a major issue, early screening and diagnosis are essential. The purpose of this research is to create a technology that will help doctors distinguish between ADHD and healthy youngsters using electroencephalography (EEG) based on the visual attention task. Because of the use of stand-alone classifiers, a few studies that employed EEG data to diagnose ADHD were unable to improve accuracy. As a result, the authors created a novel analysis framework in this research by performing an average ensemble on long short-term memory (LSTM) and gated recurrent unit (GRU), both of which have a lot of potential for diagnosing the problem. The suggested model obtained an accuracy of 97.9% and 95.33% for training and testing data, respectively. The accuracy of the model validates the detection efficiency over the performance of stand-alone deep learning models. As a result, this new ensemble model is thought to be a good option for detecting and diagnosing children with an attention disorder.

• Ansari, A. Q.; Biswas, Ranjit & Aggarwal, Swati (2013). Neutrosophic classifier : an extension of fuzzy classifer. Applied Soft Computing. ISSN 1568-4946. 13(1), s. 563–573. doi: 10.1016/j.asoc.2012.08.002. Vis sammendrag

  Fuzzy classification has become of great interest because of its ability to utilize simple linguistically interpretable rules and has overcome the limitations of symbolic or crisp rule based classifiers. This paper introduces an extension to fuzzy classifier: a neutrosophic classifier, which would utilize neutrosophic logic for its working. Neutrosophic logic is a generalized logic that is capable of effectively handling indeterminacy, stochasticity acquisition errors that fuzzy logic cannot handle. The proposed neutrosophic classifier employs neutrosophic logic for its working and is an extension of commonly used fuzzy classifier. It is compared with the commonly used fuzzy classifiers on the following parameters: nature of membership functions, number of rules and indeterminacy in the results generated. It is proved in the paper that extended fuzzy classifier: neutrosophic classifier; optimizes the said parameters in comparison to the fuzzy counterpart. Finally the paper is concluded with justifying that neutrosophic logic though in its nascent stage still holds the potential to be experimented for further exploration in different domains.

• Sood, Apoorvi & Aggarwal, Swati (2011). Crossroads in classification : comparison and analysis of fuzzy and neuro-fuzzy techniques. International Journal of Computer Applications. ISSN 0975-8887. 24(2), s. 13–17. doi: 10.5120/2924-3866. Vis sammendrag

  The paper introduces various methods for classification like fuzzy logic, and its combination with artificial neural networks. Datasets from UCI Repository have been used for the implementation of classification models using Matlab 7.0 for Fuzzy Inference System(FIS) and Anfis and Matlab R2007b for Anfis with variable labels and different membership functions.

• Ansari, A. Q.; Biswas, Ranjit & Aggarwal, Swati (2011). Proposal for applicability of neutrosophic set theory in medical AI . International Journal of Computer Applications. ISSN 0975-8887. 27(5), s. 5–11. doi: 10.5120/3299-4505. Vis sammendrag

  Soft computing is an enriching domain that helps to encode uncertainty and imprecision that exists in real world. Integration of soft computing techniques in the systems lends added advantage to the existing systems to allow solutions to otherwise unsolvable problems. Fuzzy architecture has been extensively researched and applied in medical domain. This paper suggests incorporating a new logic: Neutrosophic logic in medical domain and also discusses the possibility of extending the capabilities of the fuzzy systems by employing neutrosophic systems.

• Aggarwal, Swati; Biswas, Ranjit & Ansari, A. Q. (2010). Neutrosophic modeling and control. I ., Ukjent (Red.), 2010 International Conference on Computer and Communication Technology (ICCCT). IEEE conference proceedings. ISSN 9781424490332. s. 718–723. doi: 10.1109/ICCCT.2010.5640435. Vis sammendrag

  Quite recently, Neutrosophic Logic has been proposed by Florentine Smarandache which is based on non-standard analysis that was given by Abraham Robinson in 1960s. Neutrosophic Logic was developed to represent mathematical model of uncertainty, vagueness, ambiguity, imprecision, incompleteness, inconsistency, redundancy and contradiction in data. All the factors stated are very integral to human thinking, as it is very rare that we tend to conclude/judge in definite environments. This paper discusses how neutrosophic logic can be utilized for modeling and control for which block diagram of neutrosophic inference system is proposed, to illustrate this designing of relatively simple neutrosophic classifier has been attempted. Current problems and future directions for neutrosophic approaches are also addressed.

• Aggarwal, Swati; Biswas, Ranjit & Ansari, A. Q. (2010). From fuzzification to neutrosophication : a better interface between logic and human reasoning. I ., Ukjent (Red.), 2010 3rd International Conference on Emerging Trends in Engineering and Technology. IEEE conference proceedings. ISSN 9781424484812. s. 21–26. doi: 10.1109/ICETET.2010.26. Vis sammendrag

  Prof. L. A. Zadeh recognized that to simulate soft knowledge of human reasoning it is essential to use some formal approach to knowledge processing. So he pioneered by taking first step by proposing a novel logic, fuzzy logic in 1965, by releasing constraints imposed on existing formalisms to accommodate important properties of natural inference. This paper targets human reasoning domain, lists the limitations of fuzzy logic in this area and suggests a new logic: neutrosophic logic. Experimental data is provided by showing the comparison between fuzzy classifier and neutrosophic classifier, finally paper is concluded with a proposal that neutrosophic logic is a better candidate to simulate human reasoning.

Se alle arbeider i Cristin

• Aggarwal, Swati; Nenseth, Silje-Adelen Slydal & Meer, Audrey Lucia Hendrika van der (2024). Towards a brain-computer interface for monitoring visual motion perception in infants.
• Aggarwal, Swati; Vilhelmsen, Kenneth; Van der Weel, Frederikus & Van der Meer, Audrey (2022). Predictor for closed-loop Brain Computer Interface to facilitate perceptual learning in infants: A preliminary investigation.
• Goyal, Lalit & Aggarwal, Swati (2013). Approach in C for robot navigation.
• Azim, Shambeel & Aggarwal, Swati (2013). Data imputation using FuzzyC-means and multilayer perceptron .
• Bishnoi, Anurag & Aggarwal, Swati (2013). Trust evaluation model in B2CE-commerce using fuzzy logic .
• Rathi, Venu & Aggarwal, Swati (2013). Mammography mass classification in breast cancer using multilayer perceptron network .
• Ansari, A. Q.; Biswas, Ranjit & Aggarwal, Swati (2013). Neutrosophication of fuzzy models. Vis sammendrag

  Fuzzy logic given by Zadeh is a dominant and one of the extensively researched components in the domain of softcomputing. It deals with the representation of real-world data/information and enables reasoning that is approximate in nature. Lately, the focus has shifted to the reliability of the information, that is an important aspect for any sound decision making process. Zadeh in 2011, highlighted this impetus by introducing the concept of Z -number that relates to the issue of reliability of information and has also given method of computation with Z -numbers. Neutrosophic Logic is a new logic that was recently proposed by Florentine Smarandache in 1999. Neutrosophic logic is an extended and general framework to measure the truth, indeterminacy, and falsehood-ness of the information that closely resembles human psychological behaviour. It is effective in handling the difficult attributes of information like inaccuracy, incompleteness and ambiguous, thus giving fair estimate about the reliability of information. This paper suggests the use of Neutrosophic Logic for modelling real world uncertainties. The Neutrosophic models developed would be able to tackle the conflicting attributes of the information captured, also, as Neutrosophic Logic is a general logic, of which Fuzzy Logic is a special instance, so such Neutrosophic systems would exhibit Fuzzy behaviour under special circumstances. Authors in this paper have given the conceptual model and mathematical working of Neutrosophic systems. Neutrosophic model developed has been experimented with a UCI dataset. Analysis of the comparison of results derived from Neutrosophic model and Fuzzy model is encouraging, indicating the further exploration of Neutrosophic Logic. Hence, Neutrosophic Logic certainly holds a potential for experimentation in varied domains of decision-making, information fusion, prediction, medicine, military, cybernetics, and economics and invariably to any domain that involves high levels of uncertainty, complexity or nonlinearity.

Se alle arbeider i Cristin