Lokesh Kumar

ORCID: 0000-0001-6167-9625
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Malware Detection Techniques
  • Cloud Computing and Resource Management
  • Information and Cyber Security
  • Stock Market Forecasting Methods
  • Complex Systems and Time Series Analysis
  • Misinformation and Its Impacts
  • Spam and Phishing Detection
  • Business and Economic Development
  • Pulsars and Gravitational Waves Research
  • Network Security and Intrusion Detection
  • Optimization and Search Problems
  • Smart Parking Systems Research
  • Software Testing and Debugging Techniques
  • Caching and Content Delivery
  • Security and Verification in Computing
  • Forecasting Techniques and Applications
  • Library Collection Development and Digital Resources
  • Big Data and Business Intelligence
  • Digital Imaging for Blood Diseases
  • Human Mobility and Location-Based Analysis
  • Data Visualization and Analytics
  • Blockchain Technology in Education and Learning
  • Gamma-ray bursts and supernovae
  • Advanced Text Analysis Techniques
  • Advanced Data Compression Techniques

Indian Institute of Technology Roorkee
2023-2024

Graphic Era University
2024

Himalayan University
2024

Lovely Professional University
2024

Swami Rama Himalayan University
2024

Amity University
2014-2023

Emerald Group Publishing (United Kingdom)
2023

Banasthali University
2023

Chitkara University
2023

Birla Institute of Technology and Science, Pilani - Goa Campus
2021

A hybrid machine learning system based on Genetic Algorithm (GA) and Time Series Analysis is proposed. In stock market, a technical trading rule popular tool for analysts users to do their research decide buy or sell shares. The key issue the success of selection values all parameters combinations. However, range can vary in large domain, so it difficult find best parameter combination. this paper, we present overcome problem two steps. First, setting sub-domain with GA. Second, finding near...

10.58729/1941-6679.1099 article EN Journal of international technology and information management 2011-01-01

In fact, fake news has a huge impact on every aspect of our lives, including politics, finance, education, democracy and business. Our aim is to help provide ability the users classify real avoid harm spread unreal news. project, we have provided an optimal solution detect by using ensemble hybrid model that combination different classifiers: Naive Bayes Classifier, K –Nearest Neighbor classifier, Decision Tree, Bagging Boosting Random Forest, Logistic Regression Support Vector Machine. To...

10.1109/csnt57126.2023.10134688 article EN 2022 IEEE 11th International Conference on Communication Systems and Network Technologies (CSNT) 2023-04-08

This paper proposed a security compliance model that presents and access control features which are employed at the time of origin Big Data. The growth rate data dealing devices generation has increased exponentially led to massive explosion availability both in structured or unstructured form also known as big data. challenge is analyze this categories momentous form.The tool design process without considering feature mind its not inbuilt these systems. Moreover, because huge size it...

10.1109/csibig.2014.7056963 article EN 2014-03-01

<title>Abstract</title> As medical imaging technologies continue to proliferate and generate massive amounts of data, data compression has become increasingly important for their storage, transit, processing in the modern world. In telemedicine practices, it is common images be sent from one site another. It now minimize image size while maintaining diagnostic information order transmit keep these high-quality images. Medical a technique that helps save money on transfer storage by advising...

10.21203/rs.3.rs-3920380/v1 preprint EN cc-by Research Square (Research Square) 2024-04-10

10.1109/icccnt61001.2024.10725069 article EN 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT) 2024-06-24

The second Hot QCD Matter 2024 conference at IIT Mandi focused on various ongoing topics in high-energy heavy-ion collisions, encompassing theoretical and experimental perspectives. This proceedings volume includes 19 contributions that collectively explore diverse aspects of the bulk properties hot matter. encompass dynamics electromagnetic fields, transport properties, hadronic matter, spin hydrodynamics, role conserved charges environments. These studies significantly enhance our...

10.48550/arxiv.2412.10779 preprint EN arXiv (Cornell University) 2024-12-14

The Android operating system has constantly remained in the limelight, hence attracts attention of cyber-criminals. Understanding rising challenges, many researchers have bagged achievements by applying machine/deep learning techniques for construction malware detection models based on popular Drebin datasets. However, a cursory look at table frequency Dalvik opcodes leads us to believe that this dataset may massive number duplicate malicious files. Hence, we used technique called fitting...

10.1109/apcc49754.2021.9609892 article EN 2021-10-11

Web applications have become critical part of business. They hold a treasure trove data behind their front ends. Now-adays attackers are well aware the valuable information accessible through web applications, so website security has major problem today. The number vulnerabilities multiplied in recent years. Vulnerabilities like cross site scripting(XSS),sql injection and request forgery(CSRF) emerged as threat to applications. So, order protect from these modern threats, at first...

10.47893/ijcsi.2012.1061 article EN International Journal of Computer Science and Informatics 2012-07-01

Testing complex software is one of the most challenging steps in development lifecycle. Several testing methods are usually used from time subject component ready for until complete system where operates released distribution. In this paper, we describe to test SQL Engine Oracle database management (DBMS). This process has been designed track, detect and report quality problems along with detailed metrics that make it easier find root cause different types regressions (failures, result...

10.1145/1594156.1594159 article EN 2009-06-29

The purpose of a content-based recommendation system is to rank set results by how closely they match the user’s query. These days, virtually every online marketplace has some kind in place steer customers more goods and services might enjoy. In this piece, we’ll go through we used Generative Adversarial Networks build an image retrieval for e-commerce sites, with focus on locating best possible shoe photos along given product image. writers paper conducted study presented here. We...

10.58599/ijsmien.2023.1602 article EN International Journal of Scientific Methods in Intelligence Engineering Networks 2023-01-01

Recently, Convolutional neural network (CNN), a class of deep network, has been widely used for processing images and video data. The reason that CNN performs better than the classic on is basically because convolutional layers take advantage inherent properties images. Therefore, in this paper, we propose investigate two-step cascaded classification model using detection gravitational wave (GW) signals emitting from two different heavenly astronomical objects noisy time-series To build...

10.1016/j.procs.2023.08.205 article EN Procedia Computer Science 2023-01-01
Coming Soon ...