scispace - formally typeset
Search or ask a question
Author

Chinmay Chakraborty

Bio: Chinmay Chakraborty is an academic researcher from Birla Institute of Technology, Mesra. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 14, co-authored 97 publications receiving 900 citations. Previous affiliations of Chinmay Chakraborty include Birla Institute of Technology and Science & Indian Institute of Technology Kharagpur.


Papers
More filters
Journal ArticleDOI
01 Feb 2021
TL;DR: Supervised machine learning models for COVID-19 infection were developed in this work with learning algorithms which include logistic regression, decision tree, support vector machine, naive Bayes, and artificial neutral network using epidemiology labeled dataset for positive and negative CO VID-19 cases of Mexico.
Abstract: COVID-19 or 2019-nCoV is no longer pandemic but rather endemic, with more than 651,247 people around world having lost their lives after contracting the disease. Currently, there is no specific treatment or cure for COVID-19, and thus living with the disease and its symptoms is inevitable. This reality has placed a massive burden on limited healthcare systems worldwide especially in the developing nations. Although neither an effective, clinically proven antiviral agents' strategy nor an approved vaccine exist to eradicate the COVID-19 pandemic, there are alternatives that may reduce the huge burden on not only limited healthcare systems but also the economic sector; the most promising include harnessing non-clinical techniques such as machine learning, data mining, deep learning and other artificial intelligence. These alternatives would facilitate diagnosis and prognosis for 2019-nCoV pandemic patients. Supervised machine learning models for COVID-19 infection were developed in this work with learning algorithms which include logistic regression, decision tree, support vector machine, naive Bayes, and artificial neutral network using epidemiology labeled dataset for positive and negative COVID-19 cases of Mexico. The correlation coefficient analysis between various dependent and independent features was carried out to determine a strength relationship between each dependent feature and independent feature of the dataset prior to developing the models. The 80% of the training dataset were used for training the models while the remaining 20% were used for testing the models. The result of the performance evaluation of the models showed that decision tree model has the highest accuracy of 94.99% while the Support Vector Machine Model has the highest sensitivity of 93.34% and Naive Bayes Model has the highest specificity of 94.30%.

185 citations

Journal ArticleDOI
TL;DR: A novel privacy anonymous IoT model that leverages blockchain’s trust-oriented decentralization for on-chain data logging and retrieval that will make it easy to identify clusters of infection contacts and help deliver a notification for mass isolation while preserving individual privacy is designed and presented.
Abstract: Automated digital contact tracing is effective and efficient, and one of the non-pharmaceutical complementary approaches to mitigate and manage epidemics like Coronavirus disease 2019 (COVID-19). Despite the advantages of digital contact tracing, it is not widely used in the western world, including the US and Europe, due to strict privacy regulations and patient rights. We categorized the current approaches for contact tracing, namely: mobile service-provider-application, mobile network operators' call detail, citizen-application, and IoT-based. Current measures for infection control and tracing do not include animals and moving objects like cars despite evidence that these moving objects can be infection carriers. In this article, we designed and presented a novel privacy anonymous IoT model. We presented an RFID proof-of-concept for this model. Our model leverages blockchain's trust-oriented decentralization for on-chain data logging and retrieval. Our model solution will allow moving objects to receive or send notifications when they are close to a flagged, probable, or confirmed diseased case, or flagged place or object. We implemented and presented three prototype blockchain smart contracts for our model. We then simulated contract deployments and execution of functions. We presented the cost differentials. Our simulation results show less than one-second deployment and call time for smart contracts, though, in real life, it can be up to 25 seconds on Ethereum public blockchain. Our simulation results also show that it costs an average of $1.95 to deploy our prototype smart contracts, and an average of $0.34 to call our functions. Our model will make it easy to identify clusters of infection contacts and help deliver a notification for mass isolation while preserving individual privacy. Furthermore, it can be used to understand better human connectivity, model similar other infection spread network, and develop public policies to control the spread of COVID-19 while preparing for future epidemics.

164 citations

Journal ArticleDOI
TL;DR: The framework for integrating body area networks on telemedicine systems for patient monitoring in different scenarios is designed and the important aspects like major characteristics, research issues, and challenges with body area sensor networks in telemedics systems are described.
Abstract: Objective: In this article, we describe the important aspects like major characteristics, research issues, and challenges with body area sensor networks in telemedicine systems for patient monitoring in different scenarios. Present and emerging developments in communications integrated with the developments in microelectronics and embedded system technologies will have a dramatic impact on future patient monitoring and health information delivery systems. The important challenges are bandwidth limitations, power consumption, and skin or tissue protection. Materials and Methods: This article presents a detailed survey on wireless body area networks (WBANs). Results and Conclusions: We have designed the framework for integrating body area networks on telemedicine systems. Recent trends, overall WBAN-telemedicine framework, and future research scope have also been addressed in this article.

123 citations

Journal ArticleDOI
TL;DR: The main aim of the work is to propose a Machine learning-based healthcare model to early and accurately predict the different diseases and help doctors to diagnose the disease early.
Abstract: Artificial Intelligence (AI) is widely implemented in healthcare 4.0 for producing early and accurate results. The early predictions of disease help doctors to make early decisions to save the life of patients. Internet of things (IoT) is working as a catalyst to enhance the power of AI applications in healthcare. The patients' data are captured by IoT_sensor and analysis of the patient data is performed by machine learning techniques. The main aim of the work is to propose a Machine learning-based healthcare model to early and accurately predict the different diseases. In this work, seven machine learning classification algorithms such as decision tree, support vector machine, Naive Bayes, adaptive boosting, Random Forest (RF), artificial neural network, and K-nearest neighbor are used to predict the nine fatal diseases such as heart disease, diabetics breast cancer, hepatitis, liver disorder, dermatology, surgery data, thyroid, and spect heart. To evaluate the performance of the proposed model, four performance metrics (such as accuracy, sensitivity, specificity, and area under the curve) are used. The RF classifier observes the maximum accuracy of 97.62%, the sensitivity of 99.67%, specificity of 97.81%, and AUC of 99.32% for different diseases. The developed healthcare model will help doctors to diagnose the disease early.

81 citations

Journal ArticleDOI
TL;DR: A grape leaf disease detection network (GLDDN) is proposed that utilizes dual attention mechanisms for feature evaluation, detection, and classification and achieves an overall accuracy of 99.93% for esca, black-rot and isariopsis detection.
Abstract: The disease-free growth of a plant is highly influential for both environment and human life. However, there are numerous plant diseases such as viruses, fungus, and micro-organisms that affect the growth and agricultural production of a plant. Grape esca, black-rot, and isariopsis are multi-symptomatic soil-borne diseases. Often, these diseases may cause leaves drop or sometimes even vanishes the plant/plant vicinity. Hence, early detection and prevention becomes necessary and must be treated on time for better grape growth and productivity. The state-of-the-art either involve classical computer vision techniques such as edge detection/segmentation or regression-based object detection applied over UAV images. In addition, the treatment is not viable until detected leaves are classified for actual disease/symptoms. This results in increased time and cost consumption. Therefore, in this paper, a grape leaf disease detection network (GLDDN) is proposed that utilizes dual attention mechanisms for feature evaluation, detection, and classification. At evaluation stage, the experimentation performed over benchmark dataset confirms that disease detection network could be fairly befitting than the existing methods since it recognizes as well as detects the infected/diseased regions. With the proposed disease detection mechanism, we achieved an overall accuracy of 99.93% accuracy for esca, black-rot and isariopsis detection.

72 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: By selectively analyzing the literature, this paper systematically survey how the adoption of the above-mentioned Industry 4.0 technologies (and their integration) applied to the health domain is changing the way to provide traditional services and products.

431 citations

Journal ArticleDOI
TL;DR: The different medical applications and the most common technologies used in WBANs are presented and a matching between each application and the corresponding suitable technology is studied.

284 citations

Journal ArticleDOI
07 Jun 2016-Sensors
TL;DR: Researchers are provided with information to compare the existing low-power communication technologies that can potentially support the rapid development and deployment of WBAN systems, and mainly focuses on remote monitoring of elderly or chronically ill patients in residential environments.
Abstract: Current progress in wearable and implanted health monitoring technologies has strong potential to alter the future of healthcare services by enabling ubiquitous monitoring of patients. A typical health monitoring system consists of a network of wearable or implanted sensors that constantly monitor physiological parameters. Collected data are relayed using existing wireless communication protocols to a base station for additional processing. This article provides researchers with information to compare the existing low-power communication technologies that can potentially support the rapid development and deployment of WBAN systems, and mainly focuses on remote monitoring of elderly or chronically ill patients in residential environments.

266 citations

Journal ArticleDOI
TL;DR: The proposed method can work in tandem with human radiologists to improve performance, which is a fundamental purpose of computer-aided diagnosis.
Abstract: In this research, we exploited the deep learning framework to differentiate the distinctive types of lesions and nodules in breast acquired with ultrasound imaging. A biopsy-proven benchmarking dataset was built from 5151 patients cases containing a total of 7408 ultrasound breast images, representative of semi-automatically segmented lesions associated with masses. The dataset comprised 4254 benign and 3154 malignant lesions. The developed method includes histogram equalization, image cropping and margin augmentation. The GoogLeNet convolutionary neural network was trained to the database to differentiate benign and malignant tumors. The networks were trained on the data with augmentation and the data without augmentation. Both of them showed an area under the curve of over 0.9. The networks showed an accuracy of about 0.9 (90%), a sensitivity of 0.86 and a specificity of 0.96. Although target regions of interest (ROIs) were selected by radiologists, meaning that radiologists still have to point out the location of the ROI, the classification of malignant lesions showed promising results. If this method is used by radiologists in clinical situations it can classify malignant lesions in a short time and support the diagnosis of radiologists in discriminating malignant lesions. Therefore, the proposed method can work in tandem with human radiologists to improve performance, which is a fundamental purpose of computer-aided diagnosis.

263 citations

Journal ArticleDOI
TL;DR: An up-to-date picture of the novel healthcare applications enabled by the ICTs advancements, with a focus on their specific hottest research challenges is provided, to help the interested readership not to lose orientation in the complex landscapes possibly generated when advanced ICTS are adopted in application scenarios dictated by the critical healthcare domain.

233 citations