Badal Soni

• PhD Computer Science and Engineering
• Professor (Assistant) at National Institute Of Technology Silchar

Human Activity Recognition (HAR) is one of the most exploited areas in the field of artificial intelligence and wearable sensor technology. Most of the work on HAR classifies simple to complex human activities but does not manage to recognize the actions of an individual with distinct physical abnormalities. This paper proposes an efficient and lig...

Language prior is a pressing problem in the VQA domain where a model provides an answer favoring the most frequent related answer. There are some methods that are adopted to mitigate language prior issue, for example, ensemble approach, the balanced data approach, the modified evaluation strategy, and the modified training framework. In this articl...

In the current era, blockchain technology (BT) has emerged as a novel technique to maintain the operations of healthcare management systems. Assessment of blockchain technology (BT)-enabled hospitals can be considered as a multi-criteria decision making (MCDM) problem because of the existence of several criteria. The aim of this study is to develop...

Blockchain technology (BT) is a digitally decentralized, distributed and public ledger, which considers a secure and viable solution for storing and accessing the record transactions in a public or private peer-to-peer network and assures a smart world of automation of complex services. This paper aims to evaluate the factors persuading the BT adop...

Gait recognition is a biometric technology that identifies individuals based on their unique way of walking. Most of the work on human gait recognition (HGR) systems has minimal user records and is performed in a closed simulated environment, which hampers the performance in a real-world scenario. This letter presents an efficient ensemble framewor...

The proliferation of fake news poses a significant challenge in the digital era. Detecting false information, especially in non-English languages, is crucial to combating misinformation effectively. In this research, we introduce a novel approach for Dravidian fake news detection by harnessing the capabilities of the MuRIL transformer model, furthe...

Automated brain disorder classification for convenient treatment is one of the most complicated and widely spread problems. With the help of cutting-edge hardware, deep learning approaches are outperforming conventional brain disorder classification techniques in the medical image field. To solve this problem researchers have developed various tran...

Most current times Visual Question Answering (VQA) models fail to interpret the multimodal knowledge of visual and text simultaneously leading to language prior problem. Language prior or language bias is a scenario where a model is biased towards the question and provides answer favouring most frequent related answer. In this scenario, model ignor...

In this work, we present ENLUS, a parallel and monolingual corpus of the English-Mizo language pair developed for machine translation. ENLUS monolingual corpora have been collated from publicly available news and media websites in Mizo. The parallel data has been collected from various online and offline sources. Machine translation has recently ma...

Both service providers and patients require healthcare information. Electronic Healthcare Records (EHR) must be shared and maintained in a more secure manner. Blockchain technology has the potential to address many of the issues confronting the healthcare industry, including electronic health record security and privacy (EHRs). Blockchain technolog...

Breast cancer is among the most prevalent cancers in women and one of the highest reason for women’s fatality rates. Most of the works in breast cancer detection are done either using deep learning models or heavily concentrated neural networks that require high computational machine and large datasets. This paper incorporates four shallow machine...

As an extension of q-rung orthopair fuzzy set, interval-valued q-rung orthopair fuzzy set (IVq-ROFS) provides a more wider decision interval to express the fuzziness information. This study aims to propose an integrated multi-criteria group decision-making method based on combination of Einstein power weighted aggregation operators, the distance me...

Since its inception, particle swarm optimization and its improvement has been an active area of research, and the algorithm has found its application in multifarious domains such as highly constrained engineering problems as well as artificial intelligence. The focal point of this paper is to make the reader aware of the innumerable applications of...

Brain tumor classification is a significant issue in computer aided diagnosis to make a convenient treatment. Deep learning techniques are surpassing traditional brain tumor classification methods in the medical image field with advanced hardware technology. In this article, a novel classification framework has been proposed that includes pre-train...

Machine translation is effective in the presence of a substantial parallel corpus. In a multilingual country like India, with diverse linguistic origins and scripts, the vast majority of languages need more resources to produce high-quality translation models. Multilingual neural machine translation (MNMT) has the advantage of being scalable across...

Nowadays, fake news is spreading rapidly. Many resources are available for fake news detection in high-resource languages like English. Due to the lack of annotated data and corpora for low-resource languages, detecting fake news in low-resource languages is difficult. There is a need for a system for fake news detection in low-resource languages l...

Human Activity Recognition is the process of identifying daily living activities of a person using sensor attributes and intelligent learning algorithms. Identifying complex human activities is tedious, as capturing long-term dependencies and extracting efficient features from the raw sensor data is challenging. This paper proposes an efficient and...

Human Activity Recognition (HAR) is a process of identifying the daily living activities of an individual using a set of sensors and appropriate learning algorithms. Most of the works on HAR are done using a mix of sensor data that is collected in a simulated environment, and due to that, the real-time recognition suffers. This paper proposes an ef...

Gait, a biological trait, is extremely valuable for identifying personnel. Identifying gait is a complex process as it needs a combination of sensor data and efficient learning algorithms. In this paper, we incorporated activities of daily living data for recognizing gait using multiple shallow and ensemble learning models. The proposed model inclu...

Human Activity Recognition (HAR) has gained much attention since sensor technology has become more advanced and cost-effective. HAR is a process of identifying the daily living activities of an individual with the help of an efficient learning algorithm and prospective user-generated datasets. This paper addresses the technical advancement and clas...

Machine translation requires a vast amount of parallel data in order to generate high-quality translations. Since many Indian languages lack sufficient resources, enhancing translation performance for these language pairs can have a significant impact. This study aims to address the issue of low-resource neural machine translation between Mizo and...

With the exponential growth of video data, video summarization has become a challenging task. In this article, we propose a deep learning framework for video summarization that utilizes a sequence learning cum encoder-decoder network architecture with a key-shot selection model. We develop two RNN-based deep models, Additive Attentive Summariser (A...

Human Activity Recognition (HAR) is the process of identifying daily living activities using a set of sensors and optimal learning algorithms. It is a convoluted process, as there is no straightforward way to associate human action with the induced sensor data. Most of the work on HAR is done on highly augmented and pre-processed data. It optimizes...

These days, the world has become a non-denominational place due to cyberspace. Digital services such as search portals and social platforms have become intricate with the regular course of daily life. As a massive number of clients’ thoughts are available on the internet, sentiment analysis has become one of the most prolific investigation arenas i...

Appropriate brain hemorrhage classification is a very crucial task that needs to be solved by advanced medical treatment. Recently, various deep learning models have been introduced to classify such bleeding accurately, and research is in progress based on various aspects. This paper emphasizes on brain hemorrhage classification. The proposed syste...

The vast majority of languages in the world at present, are considered to be low-resource languages. Since the availability of large parallel data is crucial for the success of most modern machine translation approaches, improving machine translation for low-resource languages is a key challenge. Most unsupervised techniques for translation benefit...

DFND is a Dravidian fake news dataset for detecting fake news in Dravidian languages, namely Telugu, Kannada, Tamil, and Malayalam. We collected the data from different sources: for real news articles, we scrapped the data from various news websites like Eenadu, Dinamalar, Kannadaprabha, Malayala manorama, etc.; for fake news articles, we scrapped...

One of the most prominent cancers in women is breast cancer. This research study focuses on the development of an entropy-based fuzzy clustering and classification using Region-based Chaotic Mapping and Convolution Neural Networks. The proposed framework is comprised of four steps. Initially, pre-processing is performed using a median filter. After...

Past research suggests pre-trained word embedding strategies to assess and determine feelings conveyed in various text documents. However, using a single word embedding strategy makes it difficult to grasp the whole spectrum of intricate inter-dependencies among words in texts. This article presents hybrid and stacking-based ensemble approaches for...

Anime is quite well-received today, especially among the younger generations. As anime has recently garnered mainstream attention, we have insufficient information regarding users’ penchant and watching habits. Therefore, it is an uphill task to build a recommendation engine for this relatively obscure entertainment medium. In this attempt, we have...

There has been a lot of interest in blockchain technology in a lot of different fields over the last decade, including finance, government, energy and health. This article gives an in-depth look at how blockchain can be used in the healthcare sector. In reality, research in this area is moving very quickly. People can now use blockchain-based techn...

In recent years, multimodal learning has gained acceptability because of the availability of low resource-consuming fusion techniques and robust and powerful deep learning architectures. Visual question answering (VQA) is an interdisciplinary research domain in natural language processing and computer vision. In previous works, researchers have tri...

Breast Cancer Classification is important in the medical field for disease diagnosis and assists in decisions in treatment. Poor convergence and local optima are common limitations in the existing feature selection techniques. Overfitting and imbalance data problems are common limitations in existing classifiers. The hybrid method of Whale Optimiza...

Human Activity Recognition - HAR is one of the most popular area in the filed of sensor technology and smart learning algorithms. Deep learning algorithms are immensely exploited in HAR systems as it eliminates the need of manual feature engineering. Researchers use normal and hybrid deep learning schemes for training and comparing the models. This...

Human activity is one of the most exploited areas in the field of artificial intelligence and wearable sensor technology. Various users create different datasets in distinct environments to classify daily living activities using a suitable learning algorithm. Data collected in the simulated or controlled environment suffers in real-time activity re...

Bleeding within the cerebral part of brain is known as intracranial brain hemorrhage. Appropriate classification of brain hemorrhage is a challenging task need to solve for advancement of medical treatment. Recently, new developed deep learning architectures can efficiently detect such hemorrhage accurately, and researches based on various aspects...

Lung cancer is considered one of the leading causes of death all across the world. Various radiology-related fields increasingly have used Computer-aided diagnosis (CAD) systems. It just has already become a part of clinical work for lung cancer detection. In this article, we proposed an Adaptive Boost-based Grid Search Optimized Random Forest (Ada...

Fake news is the kind of news that is made deliberately to deceive the readers. It is a sort of purposeful publicity which is distributed as veritable information. Fake news is spread out through traditional news media and social media. Fake news has been an issue for quite a while. With the introduction of social media, the spread of fake news is...

In this chapter, a new architecture is introduced to address the CMFD issue using deep learning techniques. The extraction of features from an image is achieved through a series of pre-trained VGG16 [1] neural network convolution filters where a technique of back-propagation is used to learn the gradients. RPN was then used for proposing a collecti...

In this chapter, a detailed literature review about recent digital copy-move forgery detection techniques is given. The primary contributions of the chapter are.

To overcome the limitations of the systems implemented in Chaps. 3 and 4, in this chapter, an enhancement of block-based copy-move forgery detection using hybrid local features extraction is proposed [1]. In this system, the image is divided into non-overlapping blocks and SURF features are computed from each block. SURF features are matched using...

In this chapter, an improved system for copy-move forgery detection in digital images is proposed, which is based on the Fast Walsh Hadamard Transform (FWHT). Initially, the forged image is partitioned into fixed size overlapping blocks. Then FWHT features are extracted from each overlapping block. The block feature vectors are sorted, and consecut...

In this chapter, a new system for image copy-move forgery detection using Local Binary Pattern Histogram Fourier features (LBP-HF) [1] is proposed and implemented. In this system, initially, the input forged image is partitioned into constant-sized overlapping blocks, and all overlapping blocks are lexicographically sorted. Thereafter, LBP-HF featu...

In the present world, it is obvious to suggest that images play a vital role as a source of information. But with the technologies available, forgery of such precision is possible that is not detectable by the naked eye. The main purpose of forgery analysis is to check whether there is any manipulation in the content of an image. Various algorithms...

The work presented in this book is based on copy-move forgery detection (CMFD) in digital images. We find that CMFD is a popular research area due to increase or development in the image handling software technology, and the requirement of this can be seen by the rapid publications in the last 5 years.

The proposed CMFD system in the last chapter was robust against different geometric transformation attacks but was unable to detect multiple forgeries present in the image [1]. To overcome this limitation, in this chapter, an improved system for multiple copy-move forgeries detection using SIFT key-points and DBSCAN clustering algorithm is proposed...

Due to the increase in the availability of low cost and open source image handling softwares such as Photo-shop, Paint Shop, Photo-scape, Photo-plus, GIMP and Pixelmator, manipulation of digital images has become easier and a common practice. Using these powerful tools, it has become absolutely unfeasible to visually identify whether a given image...

Latest advancements in deep learning have led to an enthusiasm among biomedical researchers to explore the field of semantic segmentation further. Lungs segmentation plays a crucial role in the computer-aided diagnosis of several lung diseases. However, various anatomical varieties make lungs segmentation a challenging task. The main objective of o...

Since its inception, particle swarm optimization and its improvement has been an active area of research, and the algorithm has found its application in multifarious domains such as highly constrained engineering problems as well as artificial intelligence. The focal point of this paper is to make the reader aware of the innumerable applications of...

This book targets an audience with a basic understanding of deep learning, its architectures, and its application in the multimedia domain. Background in machine learning is helpful in exploring various aspects of deep learning. Deep learning models have a major impact on multimedia research and raised the performance bar substantially in many of t...

The mortality rate due to failure of brain tumor diagnosis and treatment is increasing extensively. The accurate and feasible interpretation of brain tumor is mandatory for consecutive prognostication as well as medication. By expert physicians, inspection of brain tumor can be done but it will make the process labor demanding as well as more time...

Anime is quite well-received today, especially among the younger generations. With many genres of available shows, more and more people are increasingly getting attracted to this niche section of the entertainment industry. As anime has recently garnered mainstream attention, we have insufficient information regarding users' penchant and watching h...

Machine Translation is an effort to bridge language barriers and misinterpretations, making communication more convenient through the automatic translation of languages. The quality of translations produced by corpus-based approaches predominantly depends on the availability of a large parallel corpus. Although machine translation of many Indian la...

Image enhancement is already a challenging process and is further intensified due to image degradation by several factors like absorption, reflection, bending and scattering of light. The light is attenuated while travelling underwater thereby causing different wavelengths of light to have varied attenuation rates. As the blue and green color have...

The proposed work solely focuses on transforming the manual task of pathologists in classifying a test mutation to a task automatically done by a machine. We collected the dataset from a Kaggle competition which distributes the three features, Gene, Variation and Text into nine different classes. These classes are provided by genomic researchers wh...

Artificial Neural Networks (ANNs) can be described as mapping of non-linear structures which are based on the functioning of the human brain. ANN simulates the intuitive way of thinking. It thus differs from the conventional computing methods in the sense that apart from replacing or speeding up the computations of human brain, it focuses on the or...

Case-based reasoning (CBR) is a technique which solves a problem using past experiences, where a case base stores these past experiences called cases. CBR is used to solve different kinds of problems where past information is available. With the advent of modern and efficient digital tools, huge amount of image data is being captured. Hence, huge a...

Copy-Move forgery is one of the popular image tempering procedure. In which the forger modifies the original image by creating multiple instances of some objects within the image itself. Recently, several deep convnet methods have been applied in the classification of images, forensic images, image hashing retrieval, and so on, showing better perfo...

Machine Translation alleviates the need of human translators for source to target languages translation by enabling instant translation in multiple languages. Neural Machine Translation (NMT) has exhibited remarkable results in case of high-resource languages. However, for resource scare languages, NMT does not perform equivalently well. In this pa...

India has witnessed 30% of the cases of breast cancer during the last few years and it is likely to increase. Breast cancer in India accounts that one woman is diagnosed every two minutes and every nine minutes, one woman dies. Early detection and diagnosis can save the lives of cancer patients. This paper presents a novel method to detect breast c...

Identification of disease in humans accurately is very difficult and also important for further treatment. One of the major tasks for a doctor is the identification of the disease. Once the disease is identified then it is very easy to perform diagnosis for the patient. In this chapter, we reviewed and presented various machine learning and deep le...

To improve the retrieval accuracy in CBIR system means reducing this semantic gap. Reducing semantic is a necessity to build a better, trusted system, since CBIR systems are applied to a lot of fields that require utmost accuracy. Time constraint is also a very important factor since a fast CBIR system leads to a fast completion of different tasks....

Presence of haze components in the atmosphere, degrade the contrast as well as the true color of the real images. As a result of this, images are difficult to comprehend and to be used in several applications like surveillance, navigation, detection etc. Therefore, it is important to remove hazy effect from the real world images to get clear or haz...

This two-volume set (CCIS 1240-1241) constitutes the refereed proceedings of the Second International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2020, held in Silchar, India. Due to the COVID-19 pandemic the conference has been postponed to July 2020. The 79 full papers and 4 short papers were thoro...

This two-volume set (CCIS 1240-1241) constitutes the refereed proceedings of the Second International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2020, held in Silchar, India. Due to the COVID-19 pandemic the conference has been postponed to July 2020. The 79 full papers and 4 short papers were thoro...

Due to the development of image handling tool or software, copy– move is increasingly becoming a common and on the other hand, the detection of such type Biswas, Debalina attack from digital images has become the challenging and active research area. This paper presents the recent block and keypoints-based Copy–Move Forgery Detection (CMFD) techniq...

Image Forgery is an illegal activity in the society as per cyber laws. There are various types of forgeries in which forgery on images is considered as an illegal activity. Image forgery may take place in different ways. One way for doing forgery on images is copy and move forgery which may result in loss of image integrity or authenticity. There a...

Image Forgery is an illegal activity in the society as per cyber laws. There are various types of forgeries in which forgery on images is considered as an illegal activity. Image forgery may take place in different ways. One way for doing forgery on images is copy and move forgery which may result in loss of image integrity or authenticity. There a...

Cancer is a disease, which develops, in human body due to gene mutation. Due to various factor cells turn into cancerous cell and grow rapidly while damaging normal cells. Many women get affected by breast cancer, which might even cause death if not treated at early stage. Early detection of breast cancer is highly important to increase the surviva...

Copy-move forgery in images is a popular tampering method, in which a portion of an image is copied and pasted on some other location of the same image. This paper proposes an enhancement of block based copy-move forgery detection using hybrid local features extraction. In this system, the image is divided into non-overlapping blocks and SURF featu...

Perceptual image hashing technique uses the appearance of the digital media object as human eye and generates a fixed size hash value. This hash value works as digital signature for the media object and it is robust against various digital manipulation done on the media object. This technique have been constantly in use in various application areas...

Underwater scenarios cause the quality of images to be degraded by absorption, reflection, bending and scattering of light. This causes dominance of blue and green color in underwater images. In order to improve the visual quality of underwater images, we proposed a fusion based technique by which combines the Contrast Limited Adaptive Histogram Eq...

In this study, the problem of detecting if an image has tampered is inquired; especially, the attention has been paid to the case in which the portion of an image is copied and then pasted onto another region to create a duplication or to hide some important portion of the image. The proposed copy-move forgery detection system is based on the scale...

Due to excess uses of digital contents for communication and using image handling software and tools manipulation of these contents, detection of copy-move manipulation has become a prominent and interesting research area. The proposed copy-move forgery detection system is based on SIFT key-points extraction and density-based clustering algorithm....

Copy-move forgery is a popular image tampering technique. In this paper, we propose two efficient block-based systems for detection of copy-move forgeries present in images. The first system is based on the extraction of Local Binary Pattern Histogram Fourier features from each overlapping block and forgery decision based on the matching of these b...