Lalit Kumar

Dr. Lalit Kumar

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 February 2025 in Life
Verified
Journal Article
Open access
PDF file
DRDeependra Rastogi
Deependra Rastogi
PJPrashant Johri
Prashant Johri
Massimo DonelliMassimo Donelli
Massimo Donelli
Lalit KumarLalit Kumar
Lalit Kumar
SBShantanu Bindewari
Shantanu Bindewari
SKSunil Kumar Khatri
Sunil Kumar Khatri
Brain tumor diagnosis is a complex task due to the intricate anatomy of the brain and the heterogeneity of tumors. While magnetic resonance imaging (MRI) is commonly used for brain imaging, accurately detecting brain tumors remains challenging. This study aims to enhance brain tumor classification via deep transfer learning architectures using fine-tuned transfer learning, an advanced approach within artificial intelligence. Deep learning methods facilitate the analysis of high-dimensional MRI data, automating the feature extraction process crucial for precise diagnoses. In this research, several transfer learning models, including InceptionResNetV2, VGG19, Xception, and MobileNetV2, were employed to improve the accuracy of tumor detection. The dataset, sourced from Kaggle, contains tumor and non-tumor images. To mitigate class imbalance, image augmentation techniques were applied. The models were pre-trained on extensive datasets and fine-tuned to recognize specific features in MRI brain images, allowing for improved classification of tumor versus non-tumor images. The experimental results show that the Xception model outperformed other architectures, achieving an accuracy of 96.11%. This result underscores its capability in high-precision brain tumor detection. The study concludes that fine-tuned deep transfer learning architectures, particularly Xception, significantly improve the accuracy and efficiency of brain tumor diagnosis. These findings demonstrate the potential of using advanced AI models to support clinical decision making, leading to more reliable diagnoses and improved patient outcomes.

27 February 2025 in International Journal of Information Technology
Verified
Journal Article
Closed access
PDF file
OSOmkar Singh
Omkar Singh
Ajay Shriram KushwahaAjay Shriram Kushwaha
Ajay Shriram Kushwaha
CSCol. Rahul Sharma
Col. Rahul Sharma
Lalit KumarLalit Kumar
Lalit Kumar

30 June 2024 in Journal of Quantum Science and Technology
Verified
Journal Article
Open access
PDF file
DBDinesh Nayak Banoth
Dinesh Nayak Banoth
RJRakesh Jena
Rakesh Jena
SVSatish Vadlamani
Satish Vadlamani
Lalit KumarLalit Kumar
Lalit Kumar
PGPunit Goel
Punit Goel
SSS P Singh
S P Singh
In the realm of data analytics, Power BI and SQL serve as essential tools for businesses aiming to derive actionable insights from their data. However, as datasets grow in complexity and volume, the efficiency of queries and the speed of data loading become critical factors affecting overall performance. This paper explores advanced performance tuning techniques for both Power BI and SQL, focusing on enhancing query efficiency and minimizing data load times. We investigate key strategies, including the optimization of data models, effective use of DAX (Data Analysis Expressions) functions, and the implementation of indexing and partitioning in SQL databases. Additionally, we analyze the impact of data source configurations and the importance of using best practices in report design to improve user experience. By conducting empirical tests and case studies, we illustrate how these tuning methods can lead to significant improvements in report rendering times and user interactions. Ultimately, our findings emphasize the need for a holistic approach to performance tuning, combining technical optimizations with best practices in data management. This research provides valuable insights for data professionals seeking to enhance the efficiency of their Power BI reports and SQL queries, ensuring that organizations can make data-driven decisions swiftly and effectively. The outcomes of this study not only contribute to the field of business intelligence but also pave the way for future research on optimizing analytics platforms.

31 March 2024 in Journal of Quantum Science and Technology
Verified
Journal Article
Open access
PDF file
SKSatish Krishnamurthy
Satish Krishnamurthy
SNSivaprasad Nadukuru
Sivaprasad Nadukuru
SDSaurabh Ashwini Kumar Dave
Saurabh Ashwini Kumar Dave
OGOm Goel
Om Goel
AJArpit Jain
Arpit Jain
Lalit KumarLalit Kumar
Lalit Kumar
Predictive analytics has emerged as a transformative force in the retail sector, enabling businesses to optimize their inventory management and demand forecasting processes. The retail industry faces several challenges, including fluctuating consumer demand, supply chain disruptions, and the need for enhanced operational efficiency. In this context, predictive analytics offers a data-driven approach to anticipate future trends, improve decision-making, and enhance customer satisfaction. This paper explores various strategies that retailers can adopt to leverage predictive analytics for effective inventory management and accurate demand forecasting. It begins by examining the fundamentals of predictive analytics, including data collection, processing, and analytical techniques. The integration of historical sales data, market trends, and consumer behavior insights allows retailers to develop sophisticated models that predict future demand patterns. Key strategies discussed in the paper include real-time inventory tracking, automated reordering systems, and the calculation of safety stock. These strategies enable retailers to maintain optimal inventory levels, reduce excess stock, and minimize stockouts. By implementing predictive analytics, retailers can improve their operational efficiency, leading to significant cost savings and enhanced service levels. Moreover, the paper delves into various demand forecasting techniques, such as time series analysis, machine learning models, and causal forecasting methods. Each technique is evaluated for its effectiveness in predicting demand accurately and its applicability in different retail contexts. Case studies are presented to illustrate successful implementations of predictive analytics in retail, highlighting the tangible benefits realized by organizations. Despite the significant advantages offered by predictive analytics, the paper also addresses the challenges faced by retailers in its implementation. Issues such as data quality, integration with existing systems, and organizational resistance to change are explored. Strategies to overcome these challenges are discussed, emphasizing the importance of a cultural shift within organizations to embrace data-driven decision-making.

31 March 2024 in Journal of Quantum Science and Technology
Verified
Journal Article
Open access
PDF file
RTRajesh Tirupathi
Rajesh Tirupathi
RRRamya Ramachandran
Ramya Ramachandran
IKImran Khan
Imran Khan
OGOm Goel
Om Goel
AJArpit Jain
Arpit Jain
Lalit KumarLalit Kumar
Lalit Kumar
In an era of rapid technological advancement, predictive maintenance has emerged as a pivotal strategy for enhancing operational efficiency and reducing costs in industrial settings. This research explores the integration of machine learning techniques into the SAP Plant Maintenance module to develop a robust predictive maintenance framework. Predictive maintenance leverages real-time data analytics to anticipate equipment failures, thus enabling organizations to transition from reactive to proactive maintenance strategies. This approach not only optimizes asset performance but also minimizes downtime and extends the lifespan of machinery. Results indicate that the application of machine learning in predictive maintenance leads to substantial improvements in key performance indicators. The models developed in this study achieved high levels of accuracy, with precision and recall metrics indicating a robust capability to forecast potential failures. Additionally, case studies illustrate how organizations implementing these predictive maintenance strategies experienced reduced maintenance costs, increased operational uptime, and enhanced asset reliability.

14 June 2019 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
Lalit KumarLalit Kumar
Lalit Kumar
VRVinay Rishiwal
Vinay Rishiwal