SSSwapnita Srivastava

Swapnita Srivastava

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Swapnita Srivastava has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EE‐FGO: Energy‐Efficient Fuzzy Grey Wolf Optimization for Cluster Head Selection in WSN

    by Vipul Narayan, Mohammad Faiz, Swapnita Srivastava, Vimal Kumar, Vikash Kumar Mishra, Vipin Balyan

    A crucial component of the Internet of Things (IoT) is the wireless sensor network (WSN), which comprises numerous sensor nodes detecting various atmospheric variations such as temperature, pressure and humidity. These sensor nodes rely on internal batteries to power their sensors and communicate data with other nodes within the network. Given the significance of energy consumption in WSN nodes, there is a growing focus on developing advanced models to address network challenges by minimizing overhead and optimizing energy efficiency. This paper introduces a novel approach that combines fuzzy logic with the Energy‐Efficient Fuzzy Grey Wolf Optimization (EE‐FGO) to facilitate cluster formation in determining optimal solutions for selecting aggregation points using cluster heads (CH) and computing the most efficient data transmission path from CHs to the base station (BS) inside the network. By strategically selecting multiple aggregation points, the proposed approach aims to maximise the node’s lifetime. Simulation results illustrate that the EE‐FGO approach outperforms several existing protocols, leading to significant network lifetime extension.


  • Unveiling skin disease patterns: leveraging explainable artificial intelligence for enhanced classification via ensemble learning

    by Ashok Kumar, Pankaj Kumar, Shalya Saxena, Ashish Srivastava, Vipul Narayan, Swapnita Srivastava

  • Open Access

    ADDP: The Data Prefetching Protocol for Monitoring Capacity Misses

    by Swapnita Srivastava, P. K. Singh

    Prefetching is essential to minimizing the number of misses in cache and improving processor performance. Many prefetchers have been proposed, including simple but highly effective stream-based prefetchers and prefetchers that predict complex access patterns based on structures such as history buffers and bit vectors. However, many cache misses still occur in many applications. After analyzing the various techniques in Instruction and Data Prefetcher, several key features were extracted which impact system performance. Data prefetching is an essential technique used in all commercial processors. Data prefetchers aim at hiding the long data access latency. In this paper, we present the design of an Adaptive Delta-based Data Prefetching (ADDP) that employs four different tables organized in a hierarchical manner to address the diversity of access patterns. Firstly, the Entry Table is queue, which tracks recent cache fill. Secondly, the Predict Table which has trigger (Program Counter) PCs as tags. Thirdly, the (Address Difference Table) ADT which has target PCs as tags. Lastly, the Prefetch Table is divided into two parts, i.e., Prefetch Filter and the actual Prefetch Table. The Prefetch Filter table filters unnecessary prefetch accesses and the Prefetch Table is used to track other additional information for each prefetch. The ADDP has been implemented in a multicache-level prefetching system under the 3rd Data Prefetching Championship (DPC-3) framework. ADDP is an effective solution for data-intensive applications since it shows notable gains in cache hit rates and latency reduction. The simulation results show that ADDP outperforms the top three data prefetchers MLOP, SPP and BINGO by 5.312 %, 13.213 % and 10.549 %, respectively.

  • KDSR: Hybrid Machine-Learning Solution for Intrusion Detection in Fog Computing Environment

    by Partha P. Adhikari, Pawan Kumar Mall, Abhinav Mishra, Swapnita Srivastava


  • Open Access

    Deep and Machine Learning for Acute Lymphoblastic Leukemia Diagnosis: A Comprehensive Review

    by Mohammad Faiz, Bakkanarappa Gari Mounika, Mohd Akbar, Swapnita Srivastava

    The medical condition known as acute lymphoblastic leukemia (ALL) is characterized by an excess of immature lymphocyte production, and it can affect people across all age ranges. Detecting it at an early stage is extremely important to increase the chances of successful treatment. Conventional diagnostic techniques for ALL, such as bone marrow and blood tests, can be expensive and time-consuming. They may be less useful in places with scarce resources. The primary objective of this research is to investigate automated techniques that can be employed to detect ALL at an early stage. This analysis covers both machine learning models (ML), such as support vector machine (SVM) & random forest (RF), as well as deep learning algorithms (DL), including convolution neural network (CNN), AlexNet, ResNet50, ShuffleNet, MobileNet, RNN. The effectiveness of these models in detecting ALL is evident through their ability to enhance accuracy and minimize human errors, which is essential for early diagnosis and successful treatment. In addition, the study also highlights several challenges and limitations in this field, including the scarcity of data available for ALL types, and the significant computational resources required to train and operate deep learning models.


  • Open Access

    An Efficient Scientific Programming Technique for MRI Classification using Deep Residual Networks

    by Rahul Sawhney, Shilpi Sharma, Vipul Narayan, Swapnita Srivastava

    Classifying brain tumors is crucial for both diagnosing and treating patients with these diseases. Imaging techniques of many kinds are used to detect brain cancers. In contrast, MRI is frequently used because to its superior picture quality and the fact that it does not require ionizing radiation. Recently, the subfield of machine learning known as deep learning has shown especially promising results in the areas of classification and segmentation. To identify the various tumor types seen in the brain, we trained a deep residual network using imaging datasets. There will be a tremendous amount of information generated from the MRI images. It is the radiologist's job to look at these imagesMeningiomas, pituitary tumours, and gliomas are the three most prevalent forms of brain tumours. Because of the complexity of brain tumors, a physical inspection might lead to mistakes. Classification methods that use machine learning to automate the process have shown to be superior to human curation every time. Therefore, we developed a CNN-based deep residual network-based detection and classification system.


  • Open Access

    Enhancing Energy Efficiency in Cluster Based WSN using Grey Wolf Optimization

    by Ashok Kumar Rai, Lalit Kumar Tyagi, Anoop Kumar, Swapnita Srivastava, Naushen Fatima

    Wireless sensor networks (WSNs) are typically made up of small, low-power sensor nodes (SNs) equipped with capability for wireless communication, processing, and sensing. These nodes collaborate with each other to form a self-organizing network. They can collect data from their surrounding environment, such as temperature, humidity, light intensity, or motion, and transmit it to a central base station (BS) or gateway for additional processing and analysis. LEACH and TSEP are examples of cluster-based protocols developed for WSNs. These protocols require careful design and optimization of CH selection algorithms, considering factors such as energy consumption, network scalability, data aggregation, load balancing, fault tolerance, and adaptability to dynamic network conditions. Various research efforts have been made to develop efficient CH selection algorithms in WSNs, considering these challenges and trade-offs. In this paper, the Grey Wolf Optimization (GWO) algorithm is employed to address the problem of selecting CHs (CHs) in WSNs. The proposed approach takes into account two parameters: Residual Energy (RE) and the distance of node (DS)s from the BS. By visualizing and analyzing the GWO algorithm under variable parameters in WSNs, this research identifies the most appropriate node from all normal nodes for CH selection. The experimental results demonstrate that the proposed model, utilizing GWO, outperforms other approaches in terms of performance.


  • Open Access

    Leveraging Replacement Algorithm for Improved Cache Management System

    by Swapnita Srivast, P.K. Singh

    Cache memory is now a buzzword of technology arena. The main monology of the cache memory is to be representing the main re-security system of money for getting arrangement with the prototype-based currency. There is the secondary methodology of cache memory by which the visioning of the hardware area will remain same but processing will be continuing with the décor of software. In suppose, software is the forest and the hardware’s are the trees but to deploy the actual model of the security system of cache memory we need to determine the forest with due respect to trees. We need see the real vision of the tree’s for engaging the forest. Cache memory is being to represent the real time computing system of computer science. Cache memory is one of the fastest saving of computer science. It is the bridge between the central processing unit and the random-access memory. It collects the data in a short period and remove the obstacles of the information’s for restoring the data as far the information of the money is being to be collected. This one actually conflicts the frequency of the data and the interactions of information. This research actually based upon the cache management system of the cache memory system.