JSJaspreet Singh

Jaspreet Singh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jaspreet Singh has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Deep Learning architectures for Glioma MRI segmentation: Comparative insights into morphology and clinical applicability

    by Paramjot Kaur Sarao, Manish Sharma, Jaspreet Singh

    The proper delineation of the multi-modal MRI of the gliomas and of the brain is important in diagnosis, surgical planning, and monitoring of treatment in neuro-oncology. There is no doubt that convolutional neural networks CNNs) have become the standard of medical image segmentation. But still there is a limited amount of comparative evidence on how different architectures model tumor morphology. This paper is a systematic evaluation of eight CNN-based segmentation models namely U-Net, ResU-Net, Attention U-Net, RAU-Net, Feature Pyramid Network (FPN), SegNet, BiSeNet and DeepLabV3+ using the BraTS 2020 dataset. Each model was trained with the same preprocessing and hyperparameter settings, without augmentation or pre-training, to determine architecture-based effects. Performance was evaluated on a variety of accuracy measures (mean Intersection over Union, precision, recall, specificity, AUC) and efficiency measures (inference time). Consistently, FPN and ResU-Net outperformed ground truth (mIoU ≈0.896), strong recall (>0.92), and sub-milliseconds inference time, indicating better ability to detect infiltrative tumor margins and still be clinically deployable. Attention U-Net presented the best accuracy (0.96), minimizing false positives, but lightweight BiSeNet did not capture tumor boundaries despite being able to run fast. This work contributes insights into the encoding of glioma morphology by deep learning models, and identifies directions to pursue biologically-informed model development, by connecting the architectural performance of the deep learning model to the clinically-relevant error profiles.

  • AI-Augmented Ransomware Detection with Real-Time Threat Intelligence Using AI Models

    by Roohani Pupneja, Jaspreet Singh

    The use of advanced AI algorithms in ransomware has made it more intelligent and dangerous, surpassing traditional security protection strategies. The paper explains the benefits of using AI in conjunction with real-time threat intelligence to equip cybersecurity practitioners with improved excellence to avert such attacks. Specifically, it highlights three major developments: (i) AI-based creation of smart indicators to detect new ransomware activities, (ii) GPT-4-based filtering of false positives to allow the analyst to prioritize actual threats, and (iii) live threat data provided by VirusTotal so that suspicious files and URLs could be analyzed fast. The proposed solution is more effective in detecting a ransomware attack, it is faster, and it helps to reduce alert fatigue, which is a common issue with security teams. Therefore, this solution enhances organizational resilience against evolving ransomware threats in 2025 and beyond.

  • Deep learning based brain tumor detection using MRI images with transfer learning technique

    by Akshit Saxena, Jaspreet Singh

    Early diagnosis of brain tumors depends on their detection and treatment of brain-related disorders. When it comes to diagnosing brain tumors, for example, deep


  • Open Access

    A Comprehensive Review of Cloud Computing Virtual Machine Consolidation

    by Jaspreet Singh, Navpreet Kaur Walia

    In the last decade, users can access their applications, data, and services via the cloud from any location with an internet connection. The scale of heterogeneous cloud environments is continuously growing due to the development of computing-intensive smart devices. A data center is the central processing unit of any cloud environment, and it is made up of hardware-oriented machines known as Physical Machines (PMs) or server and software-oriented machines known as Virtual Machines (VMs). The deployment of a huge number of physical servers as a result of the exponential development in demand for cloud services has resulted in high energy consumption and ineffective resource usage. Efficient resource utilization and minimizing power consumption by any data center have become crucial challenges. Virtual machine consolidation(VMC) is a method of optimizing computing resources by consolidating multiple VMs onto a reduced number of PMs. By consolidating VMs and running fewer physical servers, VM consolidation can lead to reducing power consumption and efficient resource utilization. This review paper presents a comprehensive analysis of cloud computing virtual machine consolidation, exploring various strategies, benefits, challenges, and future trends in this domain. By examining a wide range of literature from the year 2015 to 2023, this review attempts to provide insight into the current state of VM consolidation and its possible effects on the performance and sustainability of cloud computing. The main flaw in the articles is that the various authors focused on different assessment metrics while the emphasis should have been on improving energy efficiency and quality of service for cloud systems. Future research can be aimed at developing a multi-objective system that emphasizes minimizing cloud energy usage without sacrificing service quality, preventing service level agreements with cloud users from being compromised.


  • Application Based Categorization of Datasets for Implementing Data Mining Techniques

    by Shruti Aggarwal, Amit Verma, Jaspreet Singh

    Clustering, Classification, Prediction, Association, outlier analysis and evolution and deviation analysis are data mining functionalities which are widely used for improving health care, customer segmentation, fraud detection, etc. Variety of datasets are available for implementing these techniques. In this paper, various verified datasets used for implementing data mining techniques, are discussed in detail. All the datasets are described and are categorized based upon their application area. Various dataset repositories such as promise, UCI, kaggle, etc. contain further application based datasets which can be used as per database functionality implemented in research. Experiments are conducted to discuss the usage of these datasets to implement data mining applications. Scopus and Web of science resources are also used in this work to conduct experiments using global analysis, citation count, source-wise and author wise number of documents available, etc. The focus of this work is to conduct application based categorization of datasets and analyzing research trends in data mining domain.


  • Open Access

    Internet of Vehicles over Vanets: Smart and Secure Communication using IoT

    by Sumit Kumar, Jaspreet Singh

    The new age of the Internet of Things (IoT) is motivating the advancement of traditional Vehicular Ad-Hoc Networks (VANETs) into the Internet of Vehicles (IoV). This paper is an overview of smart and secure communications to reduce traffic congestion using IoT based VANETs, known as IoV networks. Studies and observations made in this paper suggest that the practice of combining IoT and VANET for a secure combination has rarely practiced. IoV uses real-time data communication between vehicles to everything (V2X) using wireless communication devices based on fog/edge computing; therefore, it has considered as an application of Cyber-physical systems (CPS). Various modes of V2X communication with their connecting technologies also discussed. This paper delivers a detailed introduction to the Internet of Vehicles (IoV) with current applications, discusses the architecture of IoV based on currently existing communication technologies and routing protocols, presenting different issues in detail, provides several open research challenges and the trade-off between security and privacy in the area of IoV has reviewed. From the analysis of previous work in the IoV network, we concluded the utilization of artificial intelligence and machine learning concept is a beneficial step toward the future of IoV model.