Prof(Dr.) Goutam Sanyal

• Ph.D(Engg.), M.Tech, B.Tech
• Head of Faculty at National Institute of Technology Durgapur

With the ubiquitous progress of information technology it is now possible to transfer multimedia information rapidly over the Internet. Significant growth of video data on the Internet insists the users towards video steganography as a popular choice for data hiding. Steganography algorithm must emphasis to improve the embedding efficiency, payload...

This paper presents human activity recognition problem from first-person view-point (ego-centric video). The task is to understand the activities of a person by an observer (wearable camera or robot) from real-time video data. An efficient human activity recognition system demands the choice of useful traits and the suitable kernels for those trait...

Evolutionary models are widely used to estimate the evolutionary relationship between the various biological taxa . Majority of the existing evolutionary models ignore insertion and deletion (indel) event, which reduces the computational difficulties, but at the same time, it causes loss of valuable phylogenetic information. In this study, we have...

Ensuring security in a communication network is one of the underlying challenges of wireless sensor network due to critical operational constraints. Wireless sensor network (WSN) is an easy target of malware (worm, virus, malicious code, etc.) attacks due to weak security mechanism. Malware propagation outsets from a compromised sensor node and spr...

The disorders that occur due to blockage or rupture of the blood vessels inside the brain are commonly termed as cerebrovascular malfunction (CVM). It is a menace for the middle-aged people worldwide, and one-third of deaths are caused due to CVM. After initial medication, rehabilitation is essential to return to the self-independence. Although reh...

Information is the backbone of today’s world. It acts as a base, on which all technologies stand upon firmly. Maintaining the secrecy of information is very crucial, especially if its content is sensitive. A huge number of researchers are continuously trying to bring up newer techniques of hiding data. In this paper, we have put together several ef...

Security, when referred to the context of data/information, is indeed a very vulnerable and necessary entity at present. Rigorous researches are cropping up for the betterment of the secured globe. Primarily, the term ‘Steganography’ has been in limelight to cater the extreme need of protection of sensitive and confidential data. This paper present...

Alzheimer’s Disease (AD) is a serious neurodegenerative and progressive disease. It annihilates memory power and other mental functionalities. Development of Computer aided diagnosis will provide a second opinion to the radiologist in the detection and diagnosis processes. So, herein a novel method has been developed to study the brain MR image to...

Recognition of human actions with optimum accuracy and with less computational overhead has always been a challenging task. A suitable framework towards this problem can provide a robust solution for numerous domains of expertise that demands automatic surveillance. In this paper, a two-fold framework has been proposed for the frame extraction and...

Traditional PC gaming system has remained unmodified over the years. While GPU’s and high graphics machines have taken the gaming industry to the next level, there is a need to physically improve the gamers’ experience. Facial landmarks are the localization of certain points on the face. This paper proposes a novel model to control the computer gam...

Sentiment Analysis has recently been considered as the most active research field in the natural language processing (NLP) domain. Deep Learning is a subset of the large family of Machine Learning and becoming a growing trend due to its automatic learning capability with impressive consequences across different NLP tasks. Hence, a fusion-based Mach...

Sentiment Analysis has recently been considered as the most active research field in the natural language processing (NLP) domain. Deep Learning is a subset of the large family of Machine Learning and becoming a growing trend due to its automatic learning capability with impressive consequences across different NLP tasks. Hence, a fusion-based Mach...

Network security poses a challenge to wireless sensor networks (WSNs) achieving its true potential. It is hard to tackle due to operational constraints of networks. Worms have become an emergent threat to the wireless networks. The spread of worms in the network is epidemic in nature. This article proposes a novel mathematical model with pre-vaccin...

Nowadays, global communication has no bounds. More information is being exchanged over some public channels that serve to be an important mode of communication. Without them, the field of technology seems to collapse. But awfully, these communications often turn out to be fatal in terms of preserving the sensitivity of vulnerable data. Unwanted sou...

The practice of information exchange through global media like internet extensively entails a security concern. This paper consists of a proposed approach that braces the security concern in the realm of image steganography. The adaptive technique of the Power Modulus Scrambling (PMS) has been preliminarily used so as to disturb the normal pixel or...

Face recognition is itself a very challenging task and it becomes more challenging when the input images have intra class variations and inter class similarities in a large scale. Yet the recognition accuracy can be improved in some extent by supporting the system with non-matched templates. Therefore a set of cohort images is used in this regard....

Steganography is adjudged to be a boon in the field of global conveyance of sensitive information. In this paper, a novel approach is proffered where all the ensued methods are epitomized in the dimensions of physics. The cardinal aim is to promote data hiding in terms of the explicit arena of applicability concerning physics. The initial step proc...

In the usual face recognition approach, system is getting trained through a large number of training samples. It means in the process of training, features are extracted from all the training images individually. In this process many redundant features are required to be eliminate also. During feature elimination, some features also get suppressed...

With the rapid escalation of the usage of sensitive data exchange through internet, information security has become a vulnerable realm of concern. Numerous security policies are incorporated, steganography being one of them. In this paper, a new image steganography technique facilitating embedding and extraction mechanisms have been proposed. The c...

Wireless sensor networks have imminent constraints that make security a crucial issue. Transmission starts from a single node and spread in the entire network through wireless communication. This process leads to the failure of whole wireless sensor network. In the proposed mathematical model based on epidemic theory, the different class of nodes w...

In a general scenario, while attending a scene containing multiple faces or looking towards a group photograph, our attention does not go equal towards all the faces. It means, we are naturally biased towards some faces. This biasness happens due to availability of dominant perceptual features in those faces. In visual saliency terminology it can b...

Purpose: The majority of rehabilitation systems for locked-in patients are used for therapeutic purposes. However, round-the-clock assistance and support are essential after discharge from hospitals or nursing homes. This inspired us to develop a round-the-clock rehabilitation-cum-assistance system operated by eye gazes of locked-in patients. To do...

Wireless sensor networks (WSNs) encounter critical challenge of “ Network Security” due to extreme operational constraints. The origin of challenge begins with the entry of worms in the wireless network. Just one infected node is enough to spread the worms across the entire network. The infected node rapidly infects the neighboring nodes in an unst...

Abstract Sentiment classification or sentiment analysis has been acknowledged as an open research domain. In recent years, an enormous research work is being performed in these fields by applying numerous methodologies. Feature generation and selection are consequent for text mining as the high dimensional feature set can affect the performance of...

In modern digital era, data is one of the important aspects and sensor node is one of the excellent devices to help in collecting data from any type of terrain but security is one of the issues in collection of data. To consider an epidemic \( SE_{1} E_{2} IR \) model, where (S)—Susceptible, (\( E_{1} \))—Exposed category of 1, \( E_{2} \)—Exposed...

This paper presents a steganographic technique using the theory of Brownian motion. In the beginning, the Brownian Based Scrambling procedure introduces traces of non linearity in the carrier medium so as to introduce one layer of security. A lighter pixel (in terms of its intensity) is presumed to experience a faster movement than the heavier ones...

Sentiment classification or sentiment analysis has been acknowledged as an open research domain. In recent years, an enormous research work is being performed in these fields by applying various numbers of methodologies. Feature generation and selection are consequent for text mining as the high-dimensional feature set can affect the performance of...

Magnetic resonance image analysis for detection of some neurodegenerative diseases are investigated and reported in this work. It is based on discrete wavelet transform in combination with different fractal analysis. The proposed action consists of two stages. In the first stage consists of image preprocessing which includes image enhancement, the...

Rehabilitation plays a very important role to achieve highest possible level of self-dependence by people with disability or affected with stroke or injury/surgery to spine or brain. Several assistive technologies, including the popular computer vision-based technologies made this task simpler and easier and affordable. The main difficulty is to tr...

DNA barcoding bloomed as a routine application in biodiversity assessment and species identification. Several improvements have occurred in the DNA sequence analysis approaches. Recently, R language and environment for statistical computing and graphics emerged as powerful tool in sequence and phylogenetic analysis. Bioinformaticians have written s...

Cohort selection benefits a biometric system by providing the information collected from non-match templates, whereas fusion benefits a system by combining information collected from different sources or from same source in different ways. The benefits of both approaches are availed here by proposing a cohort selection technique which is exploited...

The rapid sprout in the usage of secured information exchange through the Internet causes a major security concern today. In this paper, we have proposed a secured approach in the lexicon of modern image steganography frame. The adaptive form of the power modulus scrambling (PMS) technique has been used so as to scramble the pixels of the cover, th...

This paper presents rotation and size invariant English numerals recognition system with, competitive recognition rate. The novelty of this paper is the introduction of two unique methods of feature extraction namely Pixel Moment of Inertia (PMI) and Delta Distance Coding (DDC). The proposed Multiple Hidden Markov Model (MHMM) is a two tier model t...

Background & Objective: The wireless sensor networks (WSNs) have forthcoming constraints due to which there are serious security issues. In this paper, we study the dynamics of worm propagation in Wireless Sensor Networks is based on epidemic theory. The proposed model demonstrates the effect of quarantined and recovery state on worms propagation i...

The matching of two face images without any prior information is very much challenging task unlike a verification or identification system where already some knowledge about the images of each subjects are stored in the system's database. This paper proposes a methodology to enrich the performance of a face pair matching system by utilizing the com...

Steganography is the art and science of message hiding i.e. passing confidential message through the unsecure channel in such a way that the existence of secret message is unknown. Image and video are the very popular choice for cover media. Embedding efficiency, payload and robustness against attackers are the main key point to successfully design...

Sentiment analysis has recently been considered as most active research field in NLP domain. Deep learning is a growing trend of machine learning due to its automatic learning capability with impressive results across different NLP task. In this paper a model is proposed to analyze the deep sentiment representation based on CNN and LSTM (modified v...

With pervasive of mobile computing and wireless communication, the vehicular ad-hoc network has become a key technology in modern day's information exchange. Due to the fast growing number of vehicles and saturation of the transport infrastructure, it is inhabitable to come out with better solution considering the available resources. In this study...

Visual Saliency decides the focus of attention towards a region in a scene. When we talk about attending faces in a crowd or set of multiple faces, our focus of attention does not go equal for all the faces. The biasness of human's visual system towards a particular face, occurs due to some dominant features of it, over rest of the faces. So, for t...

Individuality of handwriting inserts varying curvatures and angles whenever someone writes a sample of a particular numeral which makes the task of its off-line recognition more challenging. The paper addresses both these issues in novel and robust ways by merging two Digital domains, namely Digital Communications and Digital Image Processing. Curv...

Saliency map is an efficient way to represent the salient objects in an image. In the area of object-based saliency, several researches have been accomplished. In these works, normal input images are taken in which salient region or arousal object are easily perceived by us. These experiments are validated based on ground truth obtained either from...

This paper presents a steganographic approach of concealing the secret data so as to facilitate secure communication. Arnold transformation has been imposed on the chosen cover image in the first stage. This results in the scrambling of the data bits, thereby disrupting the normal pixel orientation. Thereafter, Mid Position Value (MPV) technique is...

An image matching or face pair matching is purely different aspect with respect to the other problems of computer vision and pattern recognition. This is a very active and challenging topic due to the unavailability of any prior information to the matching expert about the input images to be matched. Therefore an additional set of images can resolv...

Network security poses a challenge to wireless sensor networks (WSNs) achieving its true potential. It is hard to tackle due to operational constraints of networks. Worms have become an emergent threat to the wireless networks. The spread of worms in the network is epidemic in nature. This article proposes a novel mathematical model with pre-vaccin...

Estimation of biological relationship among various taxa is usually measured on some evolutionary models. Majority of the existing evolutionary models ignore insertion and deletion (Indel) event which reduces the computational difficulties but at the same time it causes loss of valuable phylogenetic information. In this study, we developed a modifi...

As Cloud services are gaining importance, many recent works have discovered vulnerabilities unique to such systems. Specifically, like it promotes a risk of information leakage across virtual machine isolation via side-channels. Cloud environment allows mutually distrusting clients access to the shared hardware simultaneously, which can be termed a...

The dynamics of worm propagation in the Wireless Sensor Networks (WSNs) is one of the fundamental challenge due to critical operational constraints. In this paper we propose a modified Susceptible-Infectious-Quarantined-Recovered-Susceptible (SIQRS) model based on epidemic theory. The proposed model demonstrate the effect of quarantined state on wo...

Wireless Sensor is one of the important communication device through which data can be collected and transmitted from any type of terrain. The collection of sensors constitutes a network that is a self-organized autonomous network which is called Wireless Sensor Network (WSN). A number of security challenges are addressed in WSN and one of the secu...

The booming technological trends of the global world bring along with it several disincentives, surmounting which has become a challenging task. The realm of modern communication, in order to shun the attention of any third-party demands certain measure that affirms immense security along with the confidentiality of information. Steganography ratif...

In the recent years opinion mining plays an important role by business analyst before launching a product. Opinion mining mainly concerns about detecting and extracting the feature from various opinion rich resources like review sites, discussion forum, blogs and news corpora so on. The data obtained from those are highly unstructured in nature and...

The concept of cohort selection has been emerged as a very interesting and potential topic for ongoing research in biometrics. It has the capability to provide the traditional biometric systems to having a higher performance rate with lesser complexity and cost. This paper describes a novel matching technique incorporated with Bezier curve cohort s...

Eye tracking is very useful to monitor and assess the behaviors, needs, emotional states, and desires of human beings, such as monitoring the drowsiness of a driver, or providing rehabilitation support to stroke and locked-in patients. The commercial eye trackers, developed 20 years ago, have failed to become popular for several reasons. As a resul...

Alzheimer's disease (AD) is the common neurodegenerative and irreversible disease in the population. Early detection and treatment to this disease will control the disease progression. Mostly classification of this disease is performed manually in the clinical studies. It is time consuming as well as manual classification is difficult and it is pur...

Doctoral Symposium

Tracking humans in complex surroundings is a very vital, exciting and red-hot topic since last few decades. There are lots of opinions and approaches proposed and developed by different researchers to prove that their methodology is comparatively superior to others. Human activity can be tracked based on the appropriate motion of human being. This...

Background/Objectives: Security is one of the essential concern in wireless sensor network. To find the stability points when worms appears in the wireless sensor network. Methods/Statistical Analysis: By using ODE formulate the SITR model for wireless sensor network. Find the existence of positive equilibrium and perform the stability test with th...

The traditional biometric systems can be strengthened further with exploiting the concept of cohort selection to achieve the high demands of the organizations for a robust automated person identification system. To accomplish this task the researchers are being motivated towards developing robust biometric systems using cohort selection. This paper...

While viewing a crowd, the human vision automatically gets focused towards the most attentive face. This happens when a particular face in the crowd dominates the other faces in terms of beauty, expression, color, shape, size and structure, etc. Human attention towards such faces happens due to its higher visual saliency values. A computer vision s...

Attentiveness, identification and recognition of a human face in a crowd play a starring role in the perspective of visual surveillance. Human vision system is not attending, identifying and recognizing all the faces with the same perception. It is biased towards some faces in the crowd due to their higher relative visual saliency and segment wise...

Vehicular Ad-Hoc Network (VANET) has been emerged as a promising technology thanks to the recent advances in mechanics, networking, and information technologies. However, there is still a great deal of additional research required before it finally becomes a mature technology. This article concentrates on two factors which are holding back the deve...

We have modeled data flow in communication link using Random motion of a particle which results in a Gaussian pattern of traffic flow over a period of time. The varying degrees of spectral deviation present a coherent model of data flow for wired links. We have considered multiple link systems and presented an n-dimensional representation of traffi...

Globally acknowledged medium, like internet, does not guarantee full security to the secrecy of confidential data. Cryptography, a practice to secure secret data using encryption techniques, provides protection, only to a certain extent, due to its clearly visible low perceptual transparency. To recast this glitch, steganography comes into action....

While attending the crowd, humans do not look all the faces with same gaze. Human beings have naturally, extraordinary capability to focus their gaze towards a face carrying the ‘dominating look’ in the crowd in terms of beauty or ugliness. This happens due to relative saliency of that face with respect to their surrounding faces. To model the comp...