Samrat Mondal

ORCID: 0000-0002-2159-3410
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • User Authentication and Security Systems
  • Advanced Malware Detection Techniques
  • Data Quality and Management
  • Smart Grid Energy Management
  • Access Control and Trust
  • Topic Modeling
  • Cryptography and Data Security
  • Biometric Identification and Security
  • Electric Vehicles and Infrastructure
  • Advanced Authentication Protocols Security
  • COVID-19 diagnosis using AI
  • Privacy-Preserving Technologies in Data
  • Security and Verification in Computing
  • Domain Adaptation and Few-Shot Learning
  • Advanced Multi-Objective Optimization Algorithms
  • Building Energy and Comfort Optimization
  • Biomedical Text Mining and Ontologies
  • Microgrid Control and Optimization
  • Advanced Battery Technologies Research
  • Metaheuristic Optimization Algorithms Research
  • Transportation and Mobility Innovations
  • Web Data Mining and Analysis
  • Multimodal Machine Learning Applications
  • Evolutionary Algorithms and Applications
  • Data Mining Algorithms and Applications

Indian Institute of Technology Patna
2015-2024

University of Denver
2018

Dhirubhai Ambani Institute of Information and Communication Technology
2010

Indian Institute of Technology Kharagpur
2008-2009

Prompt engineering has emerged as an indispensable technique for extending the capabilities of large language models (LLMs) and vision-language (VLMs). This approach leverages task-specific instructions, known prompts, to enhance model efficacy without modifying core parameters. Rather than updating parameters, prompts allow seamless integration pre-trained into downstream tasks by eliciting desired behaviors solely based on given prompt. Prompts can be natural instructions that provide...

10.48550/arxiv.2402.07927 preprint EN arXiv (Cornell University) 2024-02-05

With ever-depleting fossil fuels and significant increase in the carbon footprint worldwide, efficient utilization of renewable energy sources plays an important role. Installation solar rooftops photovoltaic panels is getting a broader response, even residential commercial buildings. However, at same time, it paramount importance to manage appliances these buildings according local generated from obtain better supply–demand ratio. We address this problem by proposing coordinated scheduling...

10.1109/jsyst.2024.3352617 article EN IEEE Systems Journal 2024-01-26

In the past decade, demand for Electric Vehicle (EV) charging has increased, leading to an irregular fluctuation in EV inflow at Charging Stations (CS). The policy-makers, therefore, need have infrastructure planning mechanism that addresses this by estimating ideal location and capacity of these CSs. This problem is known as Station Siting Sizing Problem (CSSSP). Due uncertainty inflow, possible non-availability ports, resulting unpredictability queueing time, a limited number EVs can get...

10.1109/tits.2024.3384537 article EN IEEE Transactions on Intelligent Transportation Systems 2024-09-01

Cervical cancer is a severe and pervasive disease that poses significant health threat to women globally. The Pap smear test an efficient effective method for detecting cervical in its early stages. However, manual screening labor-intensive requires expert cytologists, leading potential delays inconsistencies diagnosis. Deep Learning-based Computer-Aided Diagnosis (CAD) has shown results can ease the problem of screening. one single model sometimes insufficient capture complex data pattern...

10.1109/access.2023.3346764 article EN cc-by-nc-nd IEEE Access 2023-01-01

Existing electrical grid systems have a limited amount of real-time monitoring and controlling capabilities energy generation consumption facilities, which trigger various technical issues including voltage overloading, demand–supply mismatch, peak load consumption, etc. Some the primary reasons for these key been identified to be inefficient utilization infrastructure uncoordinated power pattern among consumers. In this paper, we propose coordinated scheduling algorithm schedule...

10.1109/tii.2017.2781284 article EN IEEE Transactions on Industrial Informatics 2017-12-08

Many of the real-life problems involve simultaneous optimization multiple objectives. In recent years there is an enormous increase in number multi-objective related to different domains. Evolutionary algorithms are most popular solving these types problems. The non-dominating sorting one steps any multiobjective evolutionary algorithms. This used mostly select non-dominated set solutions from a given population. past various efficient approaches proposed literature reduce complexity this...

10.1109/cec.2016.7744336 article EN 2022 IEEE Congress on Evolutionary Computation (CEC) 2016-07-01

The problem of charge scheduling Electric Vehicles (EVs) at charging stations remains one the significant challenges due to high time and insufficient infrastructure leading unfulfilled demands. Moreover, most public (CSs) are equipped with ports that serve only a fixed rate. installation adaptable ports, can vary their rate time, has been observed alleviate these challenges. Hence, we propose an efficient EV plan, for CS improve its performance. aims maximizing not profit but also total...

10.1109/tvt.2022.3231901 article EN IEEE Transactions on Vehicular Technology 2022-12-26

Residential, commercial, and industrial buildings have been reported to consume a large portion of the generated energy. With introduction smart grid its energy optimization techniques, it is now possible efficiently manage control consumers’ usage fulfil their demands with existing generation infrastructure, which otherwise seems be backbreaking challenge. This paper presents an efficient management solution for number thermostatic devices (air conditioners) that maintain temperature...

10.1109/tii.2017.2695241 article EN IEEE Transactions on Industrial Informatics 2017-04-18

Author name disambiguation (AND) is a challenging problem due to several issues such as missing key identifiers, same corresponding multiple authors, along with inconsistent representation. Several techniques have been proposed but maintaining consistent accuracy levels over all data sets still major challenge. We identify two associated the AND problem. First, namesake in which or more authors publishes similar domain. Second, diverse topic one author topical domains different set of...

10.1002/asi.24212 article EN Journal of the Association for Information Science and Technology 2019-04-22

The worldwide energy consumption has been growing in aggregate at a tremendous rate, and majority of the same is due to heating ventilation air conditioning (HVAC) loads urban buildings. With help recent advances management optimization techniques, operations functioning these devices can now be managed controlled efficiently for an improved scenario thereby reducing cost. In this article, we propose multiobjective optimal scheduling framework based on Johnson's elementary circuit finding...

10.1109/jsyst.2019.2933308 article EN IEEE Systems Journal 2019-08-22

Name ambiguity is a prevalent problem in scholarly publications due to the unprecedented growth of digital libraries and number researchers. An author identified by their name absence unique identifier. The documents an are mistakenly assigned underlying ambiguity, which may lead improper assessment author. Various efforts have been made literature solve disambiguation with supervised unsupervised approaches. approaches for preferred availability large amount unlabeled data. Bibliographic...

10.1145/3502730 article EN ACM Transactions on Knowledge Discovery from Data 2022-03-09

10.1016/j.jvcir.2023.103857 article EN Journal of Visual Communication and Image Representation 2023-05-26

Abstract Chest Radiography is a non-invasive imaging modality for diagnosing and managing chronic lung disorders, encompassing conditions such as pneumonia, tuberculosis, COVID-19. While it crucial disease localization severity assessment, existing computer-aided diagnosis (CAD) systems primarily focus on classification tasks, often overlooking these aspects. Additionally, prevalent approaches rely class activation or saliency maps, providing only rough localization. This research endeavors...

10.1038/s41598-024-60861-6 article EN cc-by Scientific Reports 2024-05-29

An access control system is often viewed as a state transition system. Given set of policies, general safety requirement in such to determine whether desirable property satisfied all the reachable states. Such an analysis calls for formal verification. While on traditional RBAC has been done some extent, extensions lack analysis. In this paper, we propose technique perform security Generalized Temporal (GTRBAC) model which can be used express wide range temporal constraints different...

10.1145/1542207.1542214 article EN 2009-06-03
Coming Soon ...