- Advanced Image Processing Techniques
- Anomaly Detection Techniques and Applications
- Image and Signal Denoising Methods
- Advanced Neural Network Applications
- Domain Adaptation and Few-Shot Learning
- Image Processing and 3D Reconstruction
- Generative Adversarial Networks and Image Synthesis
- Smart Agriculture and AI
- Handwritten Text Recognition Techniques
- Spectroscopy and Chemometric Analyses
- Image Retrieval and Classification Techniques
- Distributed and Parallel Computing Systems
- Graph Theory and Algorithms
- EEG and Brain-Computer Interfaces
- Genetics, Aging, and Longevity in Model Organisms
- Single-cell and spatial transcriptomics
- Image Enhancement Techniques
- Integrated Circuits and Semiconductor Failure Analysis
- Emotion and Mood Recognition
- Human Pose and Action Recognition
- Advanced Fluorescence Microscopy Techniques
- Brain Tumor Detection and Classification
- Advanced Electron Microscopy Techniques and Applications
- Context-Aware Activity Recognition Systems
- Epilepsy research and treatment
Indraprastha Institute of Information Technology Delhi
2025
Indian Institute of Technology Delhi
2025
University of Wisconsin–Madison
2023-2024
Graphic Era University
2024
Vishwakarma University
2024
Delhi Technological University
2023
National Institute of Technology Kurukshetra
2021
Simon Fraser University
2019
Dayanand Medical College & Hospital
2015
DAV University
2013
Magnetic resonance imaging (MRI) is being increasingly utilized to assess, diagnose, and plan treatment for a variety of diseases. The ability visualize tissue in varied contrasts the form MR pulse sequences single scan provides valuable insights physicians, as well enabling automated systems performing downstream analysis. However, many issues like prohibitive time, image corruption, different acquisition protocols, or allergies certain contrast materials may hinder process acquiring...
Highlights•scCamAge leverages single-cell image, shape, and bioactivities for age prediction•scCamAge was rigorously validated using aging-associated drugs knockouts•Trained on yeast, scCamAge predicts human fibroblast senescence•scCamAge unveiled the evolutionary conservation of aging phenotypesSummaryCurrent deep-learning-based image-analysis solutions exhibit limitations in holistically capturing spatiotemporal cellular changes, particularly during aging. We present scCamAge, an advanced...
In an increasingly digital world, the significance of creating a Comprehensive Image Dataset Contemporary Indian Coins (CIDCIC) cannot be overstated. This research presents dataset comprising 6,672 images 53 different classes coins, including denominations 25 Paisa, 50 1 Rupee, 2 5 10 and 20 Rupee. The coins with various shapes sizes are taken from obverse reverse sides in environments backgrounds. core this unfolds its potential to offer invaluable assistance visually impaired individuals...
Image denoising is the first preprocessing step dealing with image processing. In an processed using certain restoration techniques to remove induced noise which may creep in during acquisition, transmission or compression process. Examples of can be Additive White Gaussian Noise (AWGN), Impulse Noise, etc. The goal obtain that as close original input possible. this paper objective evaluation methods are used judge efficiency different types spatial domain filters applied models, a...
Single molecule localization microscopy (SMLM) allows unprecedented insight into the three-dimensional organization of proteins at nanometer scale. The combination minimal invasive cell imaging with high resolution positions SMLM forefront scientific discovery in cancer, infectious, and degenerative diseases. By stochastic temporal spatial separation light emissions from fluorescent labelled proteins, is capable scale reconstruction cellular structures. Precise 3D astigmatic dependent on...
In this paper, a novel approach for the verification of offline handwritten signatures is proposed. Despite tremendous growth digital technologies in last 4 decades, most used authentication method today remains to be signature. It natural authenticating person's identity as compared other biometric and cryptographic forms authentication. We propose verifying signatory's by using Zernike Moments global shape descriptors. are image moments that rotation invariant. The also orthogonal on unit...
A significant maize crop cultivated all through the globe, maize, also known as Zea mays, serves vital to both financial wellness and security of food. The purpose this research paper is deliver an in-depth study diseases, with emphasis on trendy detection approaches, environmentally friendly management measurements, factors affecting how prevalent they are. Neural networks, which are commonly referred convolutional neural networks or a kind machine learning architecture that features layer...
Over the past decade, landscape of data analytics has seen a notable shift towards heterogeneous architectures, particularly integration GPUs to enhance overall performance. In realm in-memory analytics, which often grapples with memory bandwidth constraints, adoption proven advantageous, thanks their superior capabilities. The parallel processing prowess stands out, providing exceptional efficiency for data-intensive workloads and outpacing traditional CPUs in terms speed. While GPU...
ABSTRACT Exogenous allosteric modulators of GPCRs have been extensively investigated. To date, a few endogenous intracellular are known with inconclusive binding information and their associated phenotypes. This limited understanding stems from the non-availability robust computational techniques facilitating automated cavity identification, its topology-specific ligand design synthesis. Here, we introduce Gcoupler, which leverages an integrative approach combining de novo design,...
In this paper, we propose a machine learning approach for enhancing photos taken in low light conditions. We use symmetrical convolutional neural networks inspired by the Zero-DCE method to learn curve photos. also existing models decomposition based on retinex theory, including reflectance and illumination Kindling Darkness approach. addition, experiment with custom weighted loss functions optimize accuracy metrics such as structural similarity. Our yields slight improvements similarity...
The ability to predict cow calving easiness cost-effectively, especially in the dairy industry where cattle suffer from a variety of unpredictable deadly illnesses and high breeding expenses assist farmers improving reproductive performance and, thereby, profitability. In this research work, machine learning Internet-of-Things (IOT) based CALVEASE framework for monitoring herd predicting is studied as multi-classification problem. collects activity information through sensors deployed cow's...