A5070283869- Smart Agriculture and AI
- Mobile Ad Hoc Networks
- Metaheuristic Optimization Algorithms Research
- Spectroscopy and Chemometric Analyses
- Parasite Biology and Host Interactions
- Leaf Properties and Growth Measurement
- Fish Biology and Ecology Studies
- Online Learning and Analytics
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Speech Recognition and Synthesis
- Speech and Audio Processing
- Neural Networks and Applications
- Evolutionary Algorithms and Applications
- Brain Tumor Detection and Classification
- Artificial Intelligence in Healthcare
- Energy Efficient Wireless Sensor Networks
- Cardiovascular Function and Risk Factors
- Digital Imaging for Blood Diseases
- COVID-19 diagnosis using AI
- Livestock and Poultry Management
- Cooperative Communication and Network Coding
- Face recognition and analysis
- Date Palm Research Studies
- Mobile Health and mHealth Applications
Lewisham and Greenwich NHS Trust
2024-2025
Chandigarh University
2021-2025
Lovely Professional University
2020-2024
Post Graduate Institute of Medical Education and Research
1996-2022
Himachal Pradesh University
2011-2022
Bennett University
2021
Bundelkhand University
2019-2020
Baddi University of Emerging Sciences and Technologies
2018
Punjab Technical University
2017
Central Forensic Science Laboratory
2016
Indian agriculture is striving to achieve sustainable intensification, the system aiming increase agricultural yield per unit area without harming natural resources and ecosystem. Modern farming employs technology improve productivity. Early accurate analysis diagnosis of plant disease very helpful in reducing diseases improving health food crop Plant experts are not available remote areas thus there a requirement automatic low-cost, approachable reliable solutions identify laboratory...
Automatic plant classification through leaf is a classical problem in Computer Vision. Plants challenging due to the introduction of new species with similar pattern and look-a-like. Many efforts are made automate using leaf, flower, bark, or stem. After much effort, it has been proven that most reliable source for classification. But identify help structure because shows similarity morphological variations, like sizes, textures, shapes, venation. Therefore, required normalize all leaves...
This paper proposes a hybrid bio-inspired search and optimization algorithm that combines the strengths of PB3C (Parallel Big Bang Crunch) 3PGA (3 Parent Genetic Algorithm) algorithms. The employs single population-based evolutionary coupled with multi-population parallel processing techniques to address problems. proposed is implemented in MATLAB software. We evaluate performance on CEC2021 standard test bench suite. approach compared other nine comparative analysis shows algorithms...
Abstract Background Artificial intelligence (AI) measurement has the potential to transform cardiac imaging, but what if it makes a mistake? Can AI also highlight when is most likely have mismeasured and can experts improve these measurements? As readers become increasingly reliant on automated measures for echocardiographic analysis, we need confidence that software will measure accurately, flag where human oversight needed. Purpose To develop test an open, scientific, machine-learning...
Global longitudinal strain (GLS) is reported to be more reproducible and prognostic than ejection fraction. Automated, transparent methods may increase trust uptake. The authors developed open machine-learning–based GLS methodology validate it using multiexpert consensus from the Unity UK Echocardiography AI Collaborative. We trained a multi-image neural network (Unity-GLS) identify annulus, apex, endocardial curve on 6,819 apical 4-, 2-, 3-chamber images. external validation dataset...
We conducted a study to ascertain the acceptability and feasibility of consultation by mobile phone in rural area northern India. The number community physician was advertised general public people were invited telephone at any time for medical consultation. Details calls received recorded. During seven-month study, 660 received. mean call duration 2.7 min. Eighty percent made men. Forty-eight during office hours. A total 417 (63%) seeking advice, 146 (22%) outpatient follow-up, 23 (4%)...
Convolutional Neural Networks (CNNs) operate within a wide variety of hyperparameters, the optimization which can greatly improve performance CNNs when performing task at hand. However, these hyperparameters be very difficult to optimize, either manually or by brute force. architecture search NAS methods have been developed address this problem and are used find best architectures for deep learning paradigm. In article, CNN has evolved with well-known nature-inspired metaheuristic paddy...
In the online education field, Massive open courses (MOOCs) have become popular in recent years. Educational institutions and Universities provide a variety of specialized that helps students to adapt with various needs learning preferences. Because this, institutional repositories creates preserve lot data about students' demographics, behavioral trends, academic achievement every day. Moreover, significant problem impeding their future advancement is high dropout rate. For solving this...
Plant identification and classification are critical to understand, protect, conserve biodiversity. Traditional plant requires years of intensive training experience, making it difficult for others classify plants. leaf is a challenging issue as similar features appears in different species plant. With the development automated image-based classification, machine learning (ML) becoming very popular. Deep (DL) methods have significantly improved image classification. In last decade,...
Convolutional neural networks (CNNs) are successfully used for solving image classification tasks. Manually designing efficient network architecture requires expertise in CNN and domain knowledge. In this paper, a novel approach is proposed automatically evolving using big bang–big crunch (BB–BC) algorithm. The can be to evolve obtain tuned hyper-parameters CNN. validated the 5932 on-field rice leaf images infected with bacterial blight, blast, brown spot tungro diseases. performed better...
In recent times, with rapid growth in technology, medical imaging has become popular healthcare. The impression of these improvements the field evident that technology can able to diagnose disease a much better way than before. Medical images play vital role detection and prediction but may tend corrupt by some kind noise or artifacts during image acquisition process. presence makes unclear, fine details features original are lost which leads inaccurate disease. Hence, different denoising...
Choosing significant features of on-field plant images and effectively classifying diseases is a challenging endeavor. This owing to the complexities images, which can be influenced by wide range variables such as illumination, soil conditions, growth phases, environmental influences. Feature selection regarded an optimization problem employing efficient optimizer choose informative feature subset from more extensive set features. The noisy, redundant, irrelevant dataset impede image...
A technique for testing analog and mixed-signal linear circuit components based on their impulse response (IR) signatures is presented in This work. simple DFT structure proposed to enable the on-chip generation of from corresponding step responses components. The circumvents need apply pseudorandom patterns perform complex cross-correlation IR generation. set post processing steps cross/auto-correlation are efficiently compare signatures. statistical approach regression outlier analysis...
Ayurveda is one of the oldest holistic treatment systems in world. Finding an accurate and correct plant key to working Ayurvedic treatment. Identification medicinal plants a tedious job due look-alike feature availability issue with other plants. This paper emphases on ideal identification classification use using deep learning approaches. Previously researchers have used traditional machine techniques identify plants, which lead mixed results. Such results are good but not enough as may...
In India, some indicators of leprosy transmission are on the rise and suggest that many cases currently go undetected. The lack active casefinding outreach activities, aiming to find hidden in communities, possible reasons for this. Lepra, an international non-governmental organisation, ran case-finding project Munger District, Bihar, from 15th June December 2016, screening 85,560 people. A combined approach using Contact Surveys, Focal Surveys Special Searches was implemented. total 321 new...