A5003577135- Advanced Clustering Algorithms Research
- SARS-CoV-2 and COVID-19 Research
- Machine Learning in Bioinformatics
- Molecular Sensors and Ion Detection
- Face and Expression Recognition
- Metaheuristic Optimization Algorithms Research
- MicroRNA in disease regulation
- vaccines and immunoinformatics approaches
- Cancer-related molecular mechanisms research
- Bioinformatics and Genomic Networks
- Luminescence and Fluorescent Materials
- Gene expression and cancer classification
- Supramolecular Chemistry and Complexes
- Remote-Sensing Image Classification
- RNA modifications and cancer
- Data Mining Algorithms and Applications
- Rough Sets and Fuzzy Logic
- Evolutionary Algorithms and Applications
- Analytical Chemistry and Sensors
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Computational Drug Discovery Methods
- RNA and protein synthesis mechanisms
- Remote Sensing and Land Use
- COVID-19 diagnosis using AI
Ramakrishna Mission Vidyamandira
2025
National Institute of Technical Teachers’ Training and Research
2016-2024
University of Warsaw
2009-2024
Bankura Sammilani Medical College
2018-2023
National Institute of Technical Teachers Training and Research
2016-2020
Mahindra Group (India)
2020
Cognizant (United States)
2020
Recycled Materials Resource Center
2020
Jashore University of Science and Technology
2019
Mater Research
2019
The problem of classifying an image into different homogeneous regions is viewed as the task clustering pixels in intensity space. In particular, satellite images contain landcover types, some which cover significantly large areas while (e.g., bridges and roads) occupy relatively much smaller regions. Automatically detecting or clusters such widely varying sizes a challenging task. this paper, new real-coded modified differential evolution based automatic fuzzy algorithm proposed...
Abstract Calix[4]pyrroles and their congeners are conformationally flexible, nonplanar tetrapyrrolic macrocycles that can recognize anionic substrates. Although the mother calix[4]pyrrole was reported more than 100 years ago, anion recognition accompanied with conformational changes first discovered in 1996. These compounds have shown preferential binding of halide anions such as fluoride chloride well phosphate carboxylate anions. Extensive efforts been made to improve affinity selectivity....
In this article, we categorize presently available experimental and theoretical knowledge of various physicochemical biochemical features amino acids, as collected in the AAindex database known 544 acid (AA) indices. Previously reported 402 indices were categorized into six groups using hierarchical clustering technique 142 left unclustered. However, due to increasing diversity these are overlapping, therefore crisp method may not provide optimal results. Moreover, large-scale bioinformatics...
The Sustainable Development Goals (SDGs) include clean water (SDG‐6) and affordable energy (SDG‐7) for the sustenance of society. Material chemistry plays design new chemicals exploring versatile activities SDG‐6 SDG‐7. Copper, third abundant metal in human body following iron zinc, controls many health issues. It is essential to determine quantity Cu2+ a wide range consumables. A luminescent coordination polymer (LCP) Cd2+(d10) as node, fumaric acid (fuma²⁻) linker tripod N‐coordinated...
Protein–protein interactions are important for the majority of biological processes. A significant number computational methods have been developed to predict protein–protein using protein sequence, structural and genomic data. Vast experimental data is publicly available on Internet, but it scattered across numerous databases. This fact motivated us create evaluate new high-throughput datasets interacting proteins. We extracted interaction from DIP, MINT, BioGRID IntAct Then we constructed...
Prediction of binding sites for transcription factors is important to understand how the latter regulate gene expression and this regulation can be modulated therapeutic purposes. A consistent number references address issue with different approaches, Machine Learning being one most successful. Nevertheless, we note that many such approaches fail propose a robust meaningful method embed genetic data under analysis. We try overcome problem by proposing bidirectional transformer-based encoder,...
In contrast to classes of neural networks where the learned representations become increasingly expressive with network depth, in graph (GNNs), tend similar. This phenomena, known as oversmoothing, is characterized by that cannot be reliably differentiated leading reduced predictive performance. this paper, we propose an analogy between oversmoothing GNNs and consensus or agreement opinion dynamics. Through analogy, show message passing structure recent continuous-depth equivalent a special...
We show that low-field proton nuclear magnetic resonance (NMR) relaxation and diffusion experiments can be used to study asphaltene aggregation directly in crude oils. Relaxation was found multiexponential, reflecting the composition of a complex fluid. Remarkably, data for samples with different concentrations collapsed onto each other by simple rescaling time dimension concentration-dependent factor ξ, whereas observed behavior is unaffected concentration. interpret this finding terms...
The problem of fuzzy clustering categorical data, where no natural ordering among the elements a attribute domain can be found, is an important in exploratory data analysis. As result, few algorithms with focus on have been proposed. In this paper, modified differential evolution (DE)-based c-medoids (FCMdd) has algorithm combines both local as well global information adaptive weighting. performance proposed method compared those using genetic algorithm, simulated annealing, and classical DE...
The problem of unsupervised image segmentation a satellite in number homogeneous regions can be viewed as the task clustering pixels intensity space. This letter presents an approach that exploits capability some recently proposed fuzzy techniques, well support vector machine (SVM) classifiers, to yield improved solutions. All techniques are first used produce set different Each such solution has been by novel technique based on SVM classifier. Thereafter, cluster-based similarity partition...
We present here the 2011 update of AutoMotif Service (AMS 4.0) that predicts wide selection 88 different types single amino acid post-translational modifications (PTM) in protein sequences. The experimentally confirmed is acquired from latest UniProt and Phospho.ELM databases for training. sequence vicinity each modified residue represented using acids physico-chemical features encoded high quality indices (HQI) obtaining by automatic clustering known extracted AAindex database. For type...
A covalently coupled, dimeric tetra-cationic calix[4]pyrrole homodimer bearing anthracene linkers displayed distinctive cooperativity and fluoride selectivity with large positive allosterism.
The COVID-19 disease for Novel coronavirus (SARS-CoV-2) has turned out to be a global pandemic. high transmission rate of this pathogenic virus demands an early prediction and proper identification the subsequent treatment. However, polymorphic nature allows it adapt sustain in different kinds environment which makes difficult predict. On other hand, there are pathogens like SARS-CoV-1, MERS-CoV, Ebola, Dengue, Influenza as well, so that predictor is highly required distinguish them with use...