- Assam Don Bosco University, Computer Science & IT, Department MemberAssam Don Bosco University, Computer Science and Engineering, Faculty MemberLoyola College ,Chennai, Computer Science, Department Memberadd
- Machine Learning-Emotion& Behavior Recognition; Artificial Intelligence-Visual Perception and image processing Algorithms, Facial Expressions and Emotions, Facial Recognition, Facial Action Coding System (FACS), Computer Science, Image Processing, and 16 moreArtificial Neural Networks, Cyber Security, Cyberpsychology, Support Vector Machines, Cybercultures, Face Recognition, Cyberlaw, Principal Component Analysis, Face recognition using MATLAB, Digital Image Processing: Face Recognition, Emotion Recognition, Cyber Crimes, Facial Expression Recognition, Cyber Criminals, Face Recognition Using Eigenface, and Machine Learningedit
- Educator and Researcher, Educational assessment,Cooperative learning,Curriculum developer, Analytical thinker, Commun... moreEducator and Researcher, Educational assessment,Cooperative learning,Curriculum developer, Analytical thinker, Community outreach, Event Management, Singer( Vocal Classical, Rabindro Sangeet) , Fine Arts and Classical Dancer ( Kathak)
Description:
I am driven by passion and creativity! Being a researcher has given me the platform to analyse and sometimes over-analyse any situations. However, that keeps me motivated to explore and learn new avenues. Beside this, I like to articulate and express knowledges and experiences that I have acquired through Teaching; it is a great platform for me indeed. Educating youths who are fresh and energetic; bubbling to learn encourages me to impart knowledge.The teaching –learning experience with my students have enriched my mindset and everyday is learning experience for me as well. Hence, I am pursuing Ph.D. that is helping me to streamline my ideas into concrete findings and establish myself in the scientific world as well as in life. Additionally, I am in practice with my hobbies i.e., singing classical based songs to soothes my soul; tapping feet’- recalling Kathak mudraas and playing with colours, brushes and water on canvas by reliving my fondness of Fine Arts and sketches. These, not only allows me to use my creative side but rejuvenates me and enables to enjoy my life beyond the research life.
Usha Mary Sharma, pursuing PhD, NITAP,INDIAedit
The primary goal of this paper is to make a comparative study on various approaches used to identify the person’s face and thereafter recognize their emotion. Among the various techniques implemented, Neural Networks, Hidden Markov Model... more
The primary goal of this paper is to make a comparative study on various approaches used to identify the person’s face and thereafter recognize their emotion. Among the various techniques implemented, Neural Networks, Hidden Markov Model and Dimensionality reduction techniques have received lot of attention. The face and facial emotion recognition system would require care and efforts in data acquisition, pre-processing, feature extraction, classification and performance evaluation. The main aim of this review paper is to study and compare the well-known techniques used at different stages to recognize the face and its emotion.
Research Interests: Computer Science, Artificial Intelligence, Image Processing, Principal Component Analysis, Face Recognition, and 15 moreSupport Vector Machines, Facial expression, Dimensionality Reduction, Artificial Neural Networks, Emotion Recognition, hidden Markov model, Face recognition using MATLAB, Feature Extraction, SVM classifier, Principal component analysis (PCA), Face Emotion Recognition, matlab source code of face recognition using PCA and back propagation newral network, LDA, Facial Expression Recognition, and Face Recognition Using Eigenface
The estimation of sediment yield concentration is crucial for the development of stream ventures, watershed management, toxins estimation, soil disintegration, floods, and so on. In this study, we summarize various existing artificial... more
The estimation of sediment yield concentration is crucial for the development of stream ventures, watershed management, toxins estimation, soil disintegration, floods, and so on. In this study, we summarize various existing artificial intelligence (AI)-based suspended sediment load (SSL) estimation models to calculate the suspended sediment load, to our knowledge to date. The artificial neural network (ANN), generalized regression neural network (GRNN), neuro-fuzzy (NF), genetic algorithm (GA), gene expression programming (GEP), classification and regression tree (CART), linear regression (LR), multilinear regression (MLR), Chi-squared automatic interaction detection (CHAID), extreme learning machine (ELM), and support vector machine (SVM) are among the many AI-based models that have been successfully implemented for sediment load prediction. In this paper, we describe a few popular AI-based models that have been used for SSL prediction. ANN, SVM, and NF had overcome each other in different circumstances of prediction; and all three can be said as good predictors. Models using ANN with ELM or wavelet analysis in some ways are good predictors as their predicted values generally lie closer to the measured value. Performances of the algorithms are usually evaluated by applying various types of performance assessment methods most commonly RMSE, R2, MAE, etc. This review is required to bear some significance to the researchers and hydrologists while seeking models that have been effectively actualized inSSLestimation or in hydrology related aspects, however, mainly focused on the researches between January 2015 and November 2020.
Research Interests:
This paper proposes a fuzzy-based Lagrangian twin parametric-margin support vector machine (FLTPMSVM) to reduce the effect of the outliers presented in biomedical data. The proposed FLTPMSVM assigns the weights to each data sample on the... more
This paper proposes a fuzzy-based Lagrangian twin parametric-margin support vector machine (FLTPMSVM) to reduce the effect of the outliers presented in biomedical data. The proposed FLTPMSVM assigns the weights to each data sample on the basis of fuzzy membership values to reduce the effect of outliers. This paper also adopts the square of the 2-norm of slack variables to make the objective function more convex. The proposed FLTPMSVM solves simple linearly convergent iterative schemes instead of solving a pair of quadratic programming problems. No external toolbox is required for the proposed FLTPMSVM as compared to the other methods. To establish the applicability of the proposed FLTPMSVM in the area of biomedical data classification, numerical experiments are performed on several biomedical datasets. The proposed FLTPMSVM gives an improved generalization performance and reduced training cost as compared to support vector machine (SVM), twin support vector machine (TWSVM), fuzzy twin support vector machine (FTSVM), twin parametric-margin support vector machine (TPMSVM) and new fuzzy twin support vector machine (NFTSVM).
Research Interests:
Visual information is the new age of representing digital images in today's world. But in various digital communications, image authentication has become a main issue. Numerous techniques have been developed for image authenticity... more
Visual information is the new age of representing digital images in today's world. But in various digital communications, image authentication has become a main issue. Numerous techniques have been developed for image authenticity verification and tampering. Digital image forensics concern is to find out the authenticity of a digital media by recovering the processing history. In this paper, we have concentrated about some image forensic techniques.
Research Interests:
Image compression enacts a fundamental task in image processing. Images occupy huge amount of space and involves great deal of transmission time. Thus compression of images is necessary mutually for storage and transmission. This paper... more
Image compression enacts a fundamental task in image processing. Images occupy huge amount of space and involves great deal of transmission time. Thus compression of images is necessary mutually for storage and transmission. This paper endeavor's to provide a basic understanding of compression and overview various well-known compression algorithms and tries to compare their performances
Research Interests:
Cloud computing is mainly used in companies and organizations. The reason for its high demand in the market is primarily because it requires less planning, allowing people to start with minimum use of resources, but gradually increases... more
Cloud computing is mainly used in companies and organizations. The reason for its high demand in the market is primarily because it requires less planning, allowing people to start with minimum use of resources, but gradually increases with the increase of demand in services. However, there are many issues related to the security of data in Cloud computing. Data security and Privacy in data are the two main concern by the researchers and clients who want to opt for Cloud computing. Therefore, an attempt is made in this paper to analyze the security challenges in cloud computing that will further provide a better understanding on the various security issues and detection of those security issues. This paper also illustrates the countermeasures that have been adopted by the Cloud S ervice Industries.
Research Interests:
This paper proposes a fuzzy-based Lagrangian twin parametric-margin support vector machine (FLTPMSVM) to reduce the effect of the outliers presented in biomedical data. The proposed FLTPMSVM assigns the weights to each data sample on the... more
This paper proposes a fuzzy-based Lagrangian twin parametric-margin support vector machine (FLTPMSVM) to reduce the effect of the outliers presented in biomedical data. The proposed FLTPMSVM assigns the weights to each data sample on the basis of fuzzy membership values to reduce the effect of outliers. This paper also adopts the square of the 2-norm of slack variables to make the objective function more convex. The proposed FLTPMSVM solves simple linearly convergent iterative schemes instead of solving a pair of quadratic programming problems. No external toolbox is required for the proposed FLTPMSVM as compared to the other methods. To establish the applicability of the proposed FLTPMSVM in the area of biomedical data classification, numerical experiments are performed on several biomedical datasets. The proposed FLTPMSVM gives an improved generalization performance and reduced training cost as compared to support vector machine (SVM), twin support vector machine (TWSVM), fuzzy twin support vector machine (FTSVM), twin parametric-margin support vector machine (TPMSVM) and new fuzzy twin support vector machine (NFTSVM).
Research Interests:
The estimation of sediment yield concentration is crucial for the development of stream ventures, watershed management, toxins estimation, soil disintegration, floods, and so on. In this study, we summarize various existing artificial... more
The estimation of sediment yield concentration is crucial for the development of stream ventures, watershed management, toxins estimation, soil disintegration, floods, and so on. In this study, we summarize various existing artificial intelligence (AI)-based suspended sediment load (SSL) estimation models to calculate the suspended sediment load, to our knowledge to date. The artificial neural network (ANN), generalized regression neural network (GRNN), neuro-fuzzy (NF), genetic algorithm (GA), gene expression programming (GEP), classification and regression tree (CART), linear regression (LR), multilinear regression (MLR), Chi-squared automatic interaction detection (CHAID), extreme learning machine (ELM), and support vector machine (SVM) are among the many AI-based models that have been successfully implemented for sediment load prediction. In this paper, we describe a few popular AI-based models that have been used for SSL prediction. ANN, SVM, and NF had overcome each other in different circumstances of prediction; and all three can be said as good predictors. Models using ANN with ELM or wavelet analysis in some ways are good predictors as their predicted values generally lie closer to the measured value. Performances of the algorithms are usually evaluated by applying various types of performance assessment methods most commonly RMSE, R 2 , MAE, etc. This review is required to bear some significance to the researchers and hydrologists while seeking models that have been effectively actualized inSSLestimation or in hydrology related aspects, however, mainly focused on the researches between January 2015 and November 2020.
Research Interests:
MANETs or Mobile Ad Hoc Networks is a network that consists of mobile nodes, is selforganizing and short lived. Due to the openness, decentralized and infrastructure less architecture it can be prone to different types of attacks. One... more
MANETs or Mobile Ad Hoc Networks is a network that consists of mobile nodes, is selforganizing and short lived. Due to the openness, decentralized and infrastructure less architecture it can be prone to different types of attacks. One such attack is the JellyFish attack. It is a type of passive attack .It is very difficult to detect this attack as it complies with the protocols. In this paper we present a study on this attack and its variants. The first section gives a brief introduction on MANETs and the different types of attacks on it from different point of view. The later section we concentrate on the JellyFish Attack. Further a review on the analysis is carried out from different sources to understand the impact of this attack on the performance and its effect on the network. Keywords: Active attacks, Passive Attacks, JellyFish Attack, AODV, DSR, TORA, GRP
Research Interests:
Wireless Mobile ad-hoc network (MANETs) is an emerging technology which is infrastructure less without any centralized controller and also each node contains routing capability.Security is an essential service for wired and wireless... more
Wireless Mobile ad-hoc network (MANETs) is an emerging technology which is infrastructure less without any centralized controller and also each node contains routing capability.Security is an essential service for wired and wireless network communications. Due to lack of central monitoring system, security becomes major challenge. The characteristics of MANETs pose both challenges and opportunities in achieving security goals, such as confidentiality, authentication, integrity, availability,access control and non-repudiation. This paper contains a survey of attacks and countermeasures in Mobile ad hoc network.The countermeasures are features or functions that reduce security vulnerabilities and attacks. First, we give an overview of attacks and then we present preventive approaches for those attacks. We also put forward an overview of MANET intrusion detection systems (IDS).
Research Interests: Wireless Communications, Network Security, Computer Networks, Wireless security, Wireless Networks (Computer Science), and 9 moreWireless Network Security, Data Communication and Computer Networks, Wireless Computing, Intrusion Detection Systems (IDSs), Mobile Ad-hoc Networks (MANETs), Information Technology and Security, Intrusion Detection System, Security issues and TCP performance improvement in mobile adhoc network(MANET), and Intrution Detection System
Phishing is a scam that has evolved many years ago and it has been growing ever since. In this study we have collected much information regarding its new and improvised way of scamming the users without their knowledge and concern. Some... more
Phishing is a scam that has evolved many years ago and it has been growing ever since. In this study we have collected much information regarding its new and improvised way of scamming the users without their knowledge and concern. Some case studies are also included based on real life events. According to the report received from Home Depot Company, the United States and Canada had encountered a loss of $62 million where only $27million was covered by the insurance company but the rest is yet to be recovered. Our main aim is to let the users be informed of all the malicious crime created by the attackers. We have also listed out some of the preventive measures that a user should follow in order to prevent such crimes. Knowingly or unknowingly theusers are trapped by using this kind of attacks and the hackers always succeed to outsmart them by using new and different scams. This paper is an attempt to bring an awareness on the phishing types, causes and various preventive measures that can change the way how people reason about the hackers and their perception towards them.
Research Interests:
—Analysis of human activities from video is currently one of the ongoing research areas in computer science. Recognition of human activity from video has gained lot of attention because of its increasing demand in many real life... more
—Analysis of human activities from video is currently one of the ongoing research areas in computer science. Recognition of human activity from video has gained lot of attention because of its increasing demand in many real life applications, for e.g. video surveillance, entertainment, healthcare, child and old age homes, etc. In this paper, several steps involved in automatic human activity recognition systems, such as segmentation, tracking of motion, pose estimation and recognition of activities are studied. Common segmentation techniques such as background subtraction and Gaussian Mixture Model (GMM) are also discussed. Two different approaches for tracking of motion in video, i.e. representation and localization of the target and filtering and data association are also discussed. Finally some of the commonly available datasets used in automatic analysis of human activities from video are also mentioned in detail.
Research Interests:
een one of the most important concerns of the researchers due to its wide range of application especially in the areas where there has been a high demand for consistent identification electronic access system for an individual. This paper... more
een one of the most important concerns of the researchers due to its wide range of application especially in the areas
where there has been a high demand for consistent identification electronic access system for an individual. This paper
discusses an approach to verify the human face and recognize the person’s face through a still image. The proposed method
is a hybrid approach that considers the local components of the face as well as the entire face of a human being. The local
facial components comprises of the lips, nose, left eye and right eye. The proposed system has been implemented using
Principal Component Analysis (PCA) and the Artificial Neural Network (ANN). The system has been designed to handle the
noises, illumination variations and the facial emotions to some extent. Hence, the proposed system proves to be efficient as
it gives the correct recognition rate of 93.5% for ideal facial image and approximately 85% for noise affected image
where there has been a high demand for consistent identification electronic access system for an individual. This paper
discusses an approach to verify the human face and recognize the person’s face through a still image. The proposed method
is a hybrid approach that considers the local components of the face as well as the entire face of a human being. The local
facial components comprises of the lips, nose, left eye and right eye. The proposed system has been implemented using
Principal Component Analysis (PCA) and the Artificial Neural Network (ANN). The system has been designed to handle the
noises, illumination variations and the facial emotions to some extent. Hence, the proposed system proves to be efficient as
it gives the correct recognition rate of 93.5% for ideal facial image and approximately 85% for noise affected image
Research Interests:
Today, Cybercrime has caused lot of damages to individuals, organizations and even the Government. Cybercrime detection methods and classification methods have came up with varying levels of success for preventing and protecting data... more
Today, Cybercrime has caused lot of damages to individuals, organizations and even the Government. Cybercrime detection methods and classification methods have came up with varying levels of success for preventing and protecting data from such attacks. Several laws and methods have been introduced in order to prevent cybercrime and the penalties are laid down to the criminals. However, the study shows that there are many countries facing this problem even today and United States of America is leading with maximum damage due to the cybercrimes over the years. According to the recent survey carried out it was noticed that year 2013 saw the monetary damage of nearly 781.84 million U.S. dollars. This paper describes about the common areas where cybercrime usually occurs and the different types of cybercrimes that are committed today. The paper also shows the studies made on e-mail related crimes as email is the most common medium through which the cybercrimes occur. In addition, some of the case studies related to cybercrimes are also laid down.
Keywords-
financial crimes, cyber stalking, telecommunication frauds, e-mail related crimes, cyber criminals, email spoofing, email bombing.
website link : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.673.7865&rank=1
Keywords-
financial crimes, cyber stalking, telecommunication frauds, e-mail related crimes, cyber criminals, email spoofing, email bombing.
website link : http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.673.7865&rank=1