A5003000799- IoT and Edge/Fog Computing
- Context-Aware Activity Recognition Systems
- COVID-19 diagnosis using AI
- IoT-based Smart Home Systems
- Blockchain Technology Applications and Security
- Phonocardiography and Auscultation Techniques
- Video Surveillance and Tracking Methods
- Network Security and Intrusion Detection
- Cloud Computing and Resource Management
- Air Quality Monitoring and Forecasting
- Sentiment Analysis and Opinion Mining
- COVID-19 impact on air quality
- Anomaly Detection Techniques and Applications
- COVID-19 epidemiological studies
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Non-Invasive Vital Sign Monitoring
- Nursing Diagnosis and Documentation
- Radiomics and Machine Learning in Medical Imaging
- Data-Driven Disease Surveillance
- IoT Networks and Protocols
- COVID-19 Digital Contact Tracing
- Air Quality and Health Impacts
- Imbalanced Data Classification Techniques
- Human Pose and Action Recognition
- Mental Health via Writing
Linnaeus University
2022-2025
Symbiosis International University
2019-2024
Lupin Pharmaceuticals (India)
2022
Navrachana University
2018-2019
Maharaja Sayajirao University of Baroda
2018
Indian Institute of Information Technology Vadodara
2016-2018
Parul University
2016-2017
Institute of Engineering
2016
C. U. Shah University
2014
Nirma University
2014
Computer vision is becoming an increasingly trendy word in the area of image processing. With emergence computer applications, there a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited community by producing excellent results video processing, object recognition, picture classification and segmentation, natural language speech many other fields. Furthermore, introduction large amounts data readily available hardware opened new avenues...
Depression is a prevalent sickness, spreading worldwide with potentially serious implications. Timely recognition of emotional responses plays pivotal function at present, the profound expansion social media and users internet. Mental illnesses are highly hazardous, stirring more than three hundred million people. Moreover, that why research focused on this subject. With advancements machine learning availability sample data relevant to depression, there possibility developing an early...
In recent times, technologies such as machine learning and deep have played a vital role in providing assistive solutions to medical domain’s challenges. They also improve predictive accuracy for early timely disease detection using imaging audio analysis. Due the scarcity of trained human resources, practitioners are welcoming technology assistance it provides helping hand them coping with more patients. Apart from critical health diseases cancer diabetes, impact respiratory is gradually on...
The emergence of Explainable Artificial Intelligence (XAI) has enhanced the lives humans and envisioned concept smart cities using informed actions, user interpretations explanations, firm decision-making processes. XAI systems can unbox potential black-box AI models describe them explicitly. study comprehensively surveys current future developments in technologies for cities. It also highlights societal, industrial, technological trends that initiate drive towards presents key to enabling...
Information gathering has become an integral part of assessing people’s behaviors and actions. The Internet is used as online learning site for sharing exchanging ideas. People can actively give their reviews recommendations variety products services using popular social sites personal blogs. Social networking sites, including Twitter, Facebook, Google+, are examples the to share opinion. stock market (SM) essential area economy plays a significant role in trade industry development....
Recent technological developments, such as the Internet of Things (IoT), artificial intelligence, edge, and cloud computing, have paved way in transforming traditional healthcare systems into smart (SHC) systems. SHC escalates management with increased efficiency, convenience, personalization, via use wearable devices connectivity, to access information rapid responses. Wearable are equipped multiple sensors identify a person's movements. The unlabeled data acquired from these directly...
The primary objective of this proposed framework work is to detect and classify various lung diseases such as pneumonia, tuberculosis, cancer from standard X-ray images Computerized Tomography (CT) scan with the help volume datasets. We implemented three deep learning models namely Sequential, Functional & Transfer trained them on open-source training To augment patient's treatment, techniques are promising successful domains that extend machine domain where CNNs extract features offers...
Deep learning is nowadays a buzzword and considered new era of machine which trains the computers in finding pattern from massive amount data. It mainly describes at multiple levels representation helps to make sense on data consisting text, sound images. Many organizations are using type deep known as convolutional neural network deal with objects video sequence. Convolution Neural Networks (CNNs) have proved be impressive terms performance for detecting objects, classification images...
Background: Ambiguities and anomalies in the Activity of Daily Living (ADL) patterns indicate deviations from Wellness. The monitoring lifestyles could facilitate remote physicians or caregivers to give insight into symptoms disease provide health improvement advice residents; Objective: This research work aims apply lifestyle an ambient assisted living (AAL) system by diagnosing conduct distinguishing variation norm with slightest conceivable fake alert. In pursuing this aim, main objective...
Human Action Recognition (HAR) is the classification of an action performed by a human. The goal this study was to recognize human actions in video sequences. We present novel feature descriptor for HAR that involves multiple features and combining them using fusion technique. major focus exploits dissimilarities. key contribution proposed approach built robust can work underlying sequences various models. To achieve objective work, has been following manner. First, moving object detection...
Abstract Health complications during the gestation period have evolved as a global issue. These sometimes result in mortality of fetus, which is more prevalent developing and underdeveloped countries. The genesis machine learning (ML) algorithms healthcare domain brought remarkable progress disease diagnosis, treatment, prognosis. This research deploys various ML to predict fetal health from cardiotocographic (CTG) data by labelling state into normal, needs guarantee, pathology. work...
In the undertaken study, we have used a customized dataset termed ``Cardiac-200'' and benchmark ``PhysioNet.'' which contains 1500 heartbeat acoustic event samples (without augmentation) 1950 (with events such as normal, murmur, extrasystole, artifact, other unlabeled events. The primary reason for designing dataset, ``cardiac-200,'' is to balance total number of into categories normal abnormal average duration recorded 10-12 s. analyzed evaluated various using audio processing libraries...
The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic or activity detection from images video. Increases in use various sensor networks have also raised lightweight process frameworks. Much research has been carried out this area, but scope colossal as it deals with open-ended problems such able to achieve high accuracy little time using Convolution Neural Networks their variants are computer vision activities, most...
In the past few years, artificial intelligence (AI) techniques have been implemented in almost all verticals of human life. However, results generated from AI models often lag explainability. appear as a blackbox wherein developers are unable to explain or trace back reasoning behind specific decision. Explainable (XAI) is rapid growing field research which helps extract information and also visualize with an optimum transparency. The present study provides extensive review use XAI...
Abstract Air pollution has emerged as a major concern of the current century. In recent times, fellow researchers have conducted numerous researches in area air quality monitoring. Still, monitoring remains an open research due to various challenges such sophisticated topology design, privacy and security, power backup, large memory requirements deployment systems at resource-constrained sites. The proposed work is attempt address issues communication assessment Quality Service (QoS) levels...
Human movement is a significant factor in extensive spatial-transmission models of contagious viruses. The proposed COUNTERACT system recognizes infectious sites by retrieving location data from mobile phone device linked with particular infected subject. approach computing an incubation phase for the subject's infection, backpropagation through subjects' to investigate where subject has been during period. Classifying each such site as site, informing exposed suspects who have location, and...