Pinki Roy

Pinki Roy
National Institute Of Technology Silchar | NIT Silchar · Department of Computer Science and Engineering

About

57
Publications
15,288
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,303
Citations

Publications

Publications (57)
Chapter
The problem of inadequate and class imbalanced data is one of the major problems in the classification tasks. Therefore applying synthetic data generation (SDG) approaches to handle class imbalances can be useful in improving Machine Learning (ML) classifier’s performance. The aim of this work is to explore various SDG approaches to improve diabete...
Chapter
The requirement for the fast and accurate detection of COVID-19 is of high importance to control the spread of the disease. Recently, Artificial Intelligence and Deep Learning-based techniques have shown great promise in the domain of medical imaging. Several important research works have already been carried out to design automatic systems that ca...
Article
Full-text available
Diabetes is a chronic condition caused by an uncontrolled blood sugar levels in the human body. Its early diagnosis may prevent severe complications such as diabetic foot ulcers (DFUs). A DFU is a critical condition that can lead to the amputation of a diabetic patient’s lower limb. The diagnosis of DFU is very complicated for the medical professio...
Chapter
Highly efficient breast ultrasound (BUS) segmentation models trained and tested on samples from one dataset do not usually have a high performance when inference is done on samples from other datasets. The solution to this data adaptation problem is crucial when it comes to deploying a trained model in a new diagnostic center. In this work, a novel...
Chapter
Diabetic Foot Ulcers (DFUs) are a major complication encountered by diabetic patients. The timely diagnosis of it helps in avoiding lower limbs or foot amputation. However, the traditional diagnosis process of DFU by clinicians and DFU experts is very costly and time-consuming. Therefore, deep learning in medical imaging opens up corridors to make...
Article
Full-text available
Early detection of malignant breast cancer can significantly improve the survival chances of the involved patients. Analysis of a non-invasive and non-radioactive modality like ultrasound imaging with the help of Machine Learning(ML) and Artificial Intelligence(AI) techniques can be crucial for achieving such effective early-stage detection of the...
Article
Full-text available
Education is a fundamental right that enriches everyone's life. However, physically challenged people often debar from the general and advanced education system. Audio-Visual Automatic Speech Recognition (AV-ASR) based system is useful to improve the education of physically challenged people by providing hands-free computing. They can communicate t...
Article
Full-text available
Automatic segmentation and classification of breast tumours in ultrasound images using deep learning approaches can help early detect breast cancer. Such predictive modelling can potentially significantly improve the survival chances of the involved patients. Most of the typical deep convolutional neural network (CNN) based approaches consider segm...
Article
Ultrasound imaging is one of the common modalities used nowadays during radiological screening of breast cancer. A novel residual deep convolutional neural network (DCNN) is proposed in this work to perform automatic benign vs. malignant classification of breast ultrasound (BUS) images. The key ideas presented in this work are- larger residual bloc...
Article
Full-text available
Breast ultrasound (BUS) tumor segmentation can help with the early detection of breast cancer; however, the lack of human-labeled training data is a big problem in this area. To deal with this, we propose a novel self-supervised learning approach (CR-SSL), where several related pretext tasks like unsupervised segmentation and edge detection are fir...
Article
Diabetes is one of the most common chronic disease causes severe life threatening complications. Therefore, it is important to diagnose diabetes at early stage to avoid health and financial burdens. In this work, a machine learning (ML) pipeline based systematic data-driven architecture is proposed to identify diabetes. The proposed ML pipeline con...
Article
Among all diabetic-related complications, the diabetic foot ulcer (DFU) is severe, demanding serious attention, and timely treatment. The purpose of the present study was to conduct features fusion of machine learning (ML) based handcrafted low-level and convolutional neural networks (CNNs) based high-level features for improving automatic diagnosi...
Article
Full-text available
Automatic language identification (LID) is the practice of detecting the language through linguistic content of speech spoken by certain anonymous speaker. In multi-lingual based Indian society, the capability to identify and classify a spoken language is an imperative task. In this work, convolutional neural network (CNN) based bidirectional long...
Article
Diabetic Foot Ulcer (DFU) is a complication of diabetes that causes lower limb amputation. In this work, a unique stacked parallel convolution layers-based network (DFU_SPNet) is proposed to perform DFU vs. normal skin classification. The main objective of this work is to design an effective CNN-based classification model, along with proper fine-tu...
Chapter
Full-text available
In multilingual-based Indian society, the capability to identify and classify a spoken language is an imperative task. Recently, deep learning algorithms, such as convolutional neural networks, seem to be effective in achieving better accuracy for images. Variants of convolutional neural networks such as VGG network, which are trained on large-scal...
Article
Full-text available
Diabetic foot ulcers (DFUs) result in amputation of lower limbs or feet without timely assessment and treatment. The assessment of DFUs is performed by the diagnosis of DFU ischaemia and infection. In this work, a new deep convolutional neural network (CNN) based approach (ResKNet) is proposed to perform such assessment. The proposed network consis...
Article
Full-text available
Prediction of breast tumour malignancy using ultrasound imaging, is an important step for early detection of breast cancer. An efficient prediction system can be a great help to improve the survival chances of the involved patients. In this work, a machine learning (ML)—radiomics based classification pipeline is proposed, to perform this predictive...
Article
With the advancements in the areas of Machine Learning (ML) and Data Mining, data driven medical decision support systems are becoming more and more prevalent. Using these techniques, researchers have been trying to build automatic diagnostic systems, that can learn from historical data and predict the presence of a disease for a new patient. This...
Article
Full-text available
Nowadays, audio–visual automatic speech recognition (AV-ASR) is an emerging field of research, but there is still lack of proper visual features for visual speech recognition. Visual features are mainly categorized into shape based and appearance based. Based on the different information embedded in shape and appearance features, this paper propose...
Chapter
Deep learning (DL) is an emerging technology in solving various real-life problems in the most efficient way. The increasing computational power makes it capable to handle large amounts of data without much human interactions. The successful applications of the most popular DL models like convolutional neural networks (CNNs), autoencoder (AEs), dee...
Article
Full-text available
Coronavirus Disease (COVID19) is a fast-spreading infectious disease that is currently causing a healthcare crisis around the world. Due to the current limitations of the reverse transcription-polymerase chain reaction (RT-PCR) based tests for detecting COVID19, recently radiology imaging based ideas have been proposed by various works. In this wor...
Article
With the increasing demand for security in many fastest growing applications, biometric recognition is the most prominent authentication system. User authentication through speech and face recognition is the important biometric technique to enhance the security. This paper proposes a speech and facial feature-based multi-modal biometric recognition...
Article
Full-text available
Latest and emerging approaches are essential to resolve the communication barrier among different languages in speech processing. The automatic language identification system is developed to identify the spoken language from speech utterances. Feature selection is a very challenging task in language identification. In this paper, bottleneck feature...
Chapter
One of the most common types of cancer among women is Breast Cancer which amounts to a staggeringly high number of deaths every year. According to the World Health Organization (WHO), the projected number of Breast Cancer cases in 2018 is 2.09 million. However, early diagnosis of Breast Cancer does lead to a much higher five year survival rate. In...
Article
With the advancements in the areas of Machine Learning (ML) and Data Mining, data driven medical decision support systems are becoming more and more prevalent. Using these techniques, researchers have been trying to build automatic diagnostic systems, that can learn from historical data and predict the presence of a disease for a new patient. This...
Article
Cost and quality of healthcare are the most challenging requirements in today's fastest growing medical technology and to meet these requirements automatic speech recognition (ASR) is one of the blessings to the medical world. ASR offers the potential to dramatically improve the cost and quality of healthcare service; many developments took place i...
Chapter
Automatic language identification has always been a challenging issue and an important research area in speech signal processing. It is the process of identifying a language from a random spoken utterance. This era is dominated by artificial intelligence and specifically, deep learning techniques. Prominent among the deep learning techniques are fe...
Article
Full-text available
Automatic language identification (LID) system has extensively recognized in a real world multilanguage speech specific applications. The formation speech is relying on the vocal tract area which explores the excitation source information for LID task. In this paper, LID system utilizes sub segmental, segmental and supra segmental features from Lin...
Article
Full-text available
This article describes how nowadays, cloud computing is one of the advanced areas of Information Technology (IT) sector. Since there are many hackers and malicious users on the internet, it is very important to secure the confidentiality of data in the cloud environment. In recent years, access control has emerged as a challenging issue of cloud co...
Research
Cost and quality of healthcare are the most challenging requirements in todays fastest growing medical technology and to meet these requirements Automatic Speech Recognition (ASR) is one of the blessings to the medical world. Automatic speech recognition offers the potential to dramatically improve the cost and quality of healthcare service; many d...
Conference Paper
Full-text available
A crucial step of speaker independent isolated word recognition is to extract meaningful information from speech signal. Speech signal contain meaningful acoustic features and selecting the significant and optimal features set is an important aspect to improve accuracy. This paper proposes a speaker independent isolated word recognition model by se...
Article
Full-text available
Data Mining is a powerful technology to help organization to concentrate on most important data by extracting useful information from large database. One of the most commonly used techniques in data mining is Artificial Neural Network due to its high performance in many application domains. Despite of many advantages of Artificial Neural Network, o...
Article
Full-text available
Cloud computing is a very trending technology because of its efficiency, cost effectiveness, pay-per-use, flexibility and scalability. Data security and access control are two significant issues experienced while availing these advantages of cloud computing. Access control can be defined as a procedure by which a user can access data or file or any...
Article
The uses of Big Data (BD) are gradually increasing in many new emerging applications, such as Facebook, eBay, Snapdeal, etc. BD is a term, which is used for describing a large volume of data. The data security is always a big concern of BD. Besides the data security, other issues of BD are data storage, high data accessing time, high data searching...
Article
Cloud computing is very emerging area in IT industries. In a cloud environment, many distributed systems are interconnected to provide software, hardware and resources over the internet. Since this new paradigm requires users to ensure the security of their personal data, there are gradually increasing security and privacy issues on outsourced data...
Article
Cloud computing is an emerging computing area that allows on-demand, scalable, flexible, and low-cost services to the users. In cloud computing, access control and security are two major problems. In this paper, a novel authentication scheme using Chebyshev chaotic maps has been presented. The proposed model satisfies many security factors, such as...
Conference Paper
Cloud computing is internet based computing where shared resource, software, hardware etc. are provided to devices and computers. Here in cloud computing, after negotiation, resources are provided to the users. Negotiation is done between Cloud Service Provider (CSP) and users. CSP should ensure to users that resources are secure in cloud server. A...
Article
Full-text available
Language identification (LID) is the process of converting an acoustic signal captured by microphone or telephone into a set of words of a particular language in real time thus controlling the computer by the use of spoken commands. The software for LID generally requires an initial training using appropriate classification algorithms in order to t...
Article
Language Identification is the task of identifying a language from a given spoken utterance. Main task of a language identifier is to design an efficient algorithm which helps a machine to identify correctly a particular language from a given audio sample. We have proposed here a hybrid approach for identifying a language which is a combination of...
Article
Language identification (LID) is always regarded to be a fascinating field to be studied. Studies on language identification has been carried out from early 1970's and up to now lot of research have been undergone in this area. In this paper a few of the papers are highlighted and reviewed based on the past history and the current state of research...
Article
Automatic Language Identification (LID) is the task of automatically recognizing a language from a given spoken utterance. The core problem in solving the language identification (LID) task is to find a way of reducing the complexity of human language such that an automatic algorithm can determine the language and identify it from a relatively brie...

Network

Cited By