RESEARCH OUTPUT
Publications
38 publications and patents in optimization, machine learning, cloud computing, IoT and intelligent systems.
2026
-
Predictive workload forecasting models for energy-efficient resource provisioning in cloud data centres
Next research., vol. 11, pp. 102001, 2026
-
The Efficient Utilization of Energy in Cloud Computing Data Centers
Lecture notes in electrical engineering, pp. 127–141, 2026
2024
-
A Review of Lightweight Security and Privacy for Resource-Constrained IoT Devices
Computers, Materials and Continua, vol. 78(1), pp. 31–63, 2024
-
A comprehensive review on detection and classification of dementia using neuroimaging and machine learning
Multimedia Tools and Applications, vol. 83(17), pp. 52365–52403, 2024
-
Optimized transfer learning approach for leaf disease classification in smart agriculture
Multimedia Tools and Applications, vol. 83(20), pp. 58103–58123, 2024
-
Performance enhancement of kernelized SVM with deep learning features for tea leaf disease prediction
Multimedia Tools and Applications, vol. 83(13), pp. 39117–39134, 2024
-
Real-Time Application Layer Protocols to support lightweight mechanism in Internet of Things for e-Healthcare systems
5th International Conference on Recent Trends in Computer Science and Technology, ICRTCST 2024 - Proceedings, pp. 676–694, 2024
-
SHC: 8-bit Compact and Efficient S-Box Structure for Lightweight Cryptography
IEEE Access, vol. 12, pp. 39430–39449, 2024
DOI Link BibTeX Cited by 39Abstract
The AES (Advance Encryption Standard) has made the development of new block ciphers unnecessary; it is now the de facto standard for most uses of block ciphers. However, the AES is still not well-suited for very limited contexts like RFID (Radio-Frequency Identification) tags and WSN(Wireless Sensor Networks), despite recent implementation advancements. In this study, we present SHC (Simple Hybrid Cipher), a new block cipher that uses a 64-bit block length and a 128-bit key length. It offers a hardware implementation that efficiently uses limited resources, making it ideal for use as a sensor in a WSN or an RFID tag. The core function of SHC depends on S-Box-based, composite field arithmetic technology, as it consumes relatively low cost on hardware implementation while still providing sufficient security as a solid encryption algorithm. The hardware implementation of SHC-64 requires 949 LUTs; it generates a maximum operating frequency of 515.995 MHz on the Xilinx-powered Artix-7 Field Programmable Gate Array (FPGA) development board. At the same time, the National Institute of Standards and Technology (NIST) recommended standard algorithm AES consumes 3645 LUTs and generates a maximum operating frequency of 277.369 MHz. The SHC-64 cipher also shows resistance against known cryptanalytics attacks.
-
Self-adaptive search optimization-based vehicle path prediction and traffic light controller in vehicular ad hoc network
International Journal of Communication Systems, vol. 37(1), 2024
DOI Link BibTeX Cited by 3Abstract
Summary In recent days, VANET is considered as the main hopeful equipment in the system of transportation since traffic congestion arises regularly and thus occurred road accidents very easily. Besides, the network traffic is increasing due to the huge quantity of information generated in region of urban. Therefore, one of the primary challenges faced by Intelligent Transportation System (ITS) is ensuring the accurate transmission of information in both vehicle‐to‐vehicle (V2V) and vehicle‐to‐road (V2R) sensing unit communications. So, here, an adaptive routing controller (ARC) is utilized to improve the data transmission between vehicle and road sensing unit (RSU) and to minimize the traffic density in VANET, and the self‐adaptive search optimization is developed in VANET clustering to prioritize vehicles in the lane, in which the multi‐objective function is intended depending on the energy of the node, acceleration, jitter, priority, velocity, and trust factors. The traffic light control is done to facilitate the effective communication in the network. Thus, the proposed technique is calculated in terms of throughput, jitter, quadratic mean of acceleration (QMA), and spatially distributed travel time (SDTT), which acquired the values of 0.53 s, 36.07 kmph, 3.472 s, and 43.572%, respectively, while using 50 vehicles at 50 s.
2023
-
Bell pepper leaf disease classification with LBP and VGG-16 based fused features and RF classifier
International Journal of Information Technology (Singapore), vol. 15(1), pp. 465–475, 2023
-
Efficient feature selection using BoWs and SURF method for leaf disease identification
Multimedia Tools and Applications, vol. 82(18), pp. 28187–28211, 2023
-
Human brain tumor classification and segmentation using CNN
Multimedia Tools and Applications, vol. 82(5), pp. 7599–7620, 2023
-
Hybrid Methods for Increasing Security of IoT and Cloud Data
Lecture Notes in Electrical Engineering, pp. 571–586, 2023
-
Mode Search Optimization Algorithm for Traffic Prediction and Signal Controlling Using Bellman–Ford with TPFN Path Discovery Model Based on Deep LSTM Classifier
SN Computer Science, vol. 4(5), 2023
-
Performance and security analysis using B-128 modified blowfish algorithm
Multimedia Tools and Applications, vol. 82(17), pp. 26661–26678, 2023
-
Performance evaluation of PCA based reduced features of leaf images extracted by DWT using random Forest and XGBoost classifier
Multimedia Tools and Applications, vol. 82(17), pp. 26225–26254, 2023
-
Securing of Cloud Storage Data Using Hybrid AES-ECC Cryptographic Approach
Journal of Mobile Multimedia, 2023
DOI Link BibTeX Cited by 12Abstract
Internet has revolutionized the world in a way no one could have ever imagined. It paved the way for various different technologies, that have transformed the world exceptionally. Internet enabled cloud technology which provides cost-effective, scalable, on-demand computing resources with little to no downtime. Cloud storage allows its users to store and access private data from anywhere in the world without needing any high-end computing system. Cloud storage isn’t always secure, but that doesn’t imply it isn’t. The security of a data depends on the security policies followed by the provider along with the security of the communication channel via which the data is being sent. Encryption is used to obfuscate the data so that it can only be viewed when correct credentials, known as encryption keys, are provided. Following study proposes an encryption technique using ECC (Elliptic Curve Cryptography) along with AES (Advance Encryption Standard) to provide data confidentiality in an efficient way for securing data on cloud and hence, protect the personal information of user from any adversary. This new method is more effective, and the results are superior as a consequence.
-
Stability analysis of mathematical model for spread of pest in tea plant by RKM-4 and ABM-2
Journal of Difference Equations and Applications, vol. 29(2), pp. 121–142, 2023
-
Traffic Prediction and Signal Controlling Using Mode-search Optimization Based Deep Long Short Term Memory Classifier
International Journal on Artificial Intelligence Tools, vol. 32(06), 2023
DOI Link BibTeXAbstract
Aim: The research aims at developing a traffic prediction and signal controlling model based on deep learning technique in order to provide congestion-free transportation in Intelligent Transport System (ITS). Need for the Research: Recent technical advancements in the ITS, industrialization, and urbanization increase traffic congestion, which leads to high fuel consumption and health issues. This signifies the need for a dynamic traffic management system to handle the traffic congestion issues that negatively affect the transportation service. Methods: For promoting congestion-free transportation in the ITS, this research aims to devise a traffic prediction and control system based on deep learning techniques that effectively controls the traffic during peak hours. The proposed mode-search optimization effectively clusters the vehicles based on the necessity. In addition, the mode-search optimization tunes the optimal hyperparameters of the deep Long Short Term Memory classifier, which minimizes the training loss. Further, the traffic signal control system is developed through the mode-search-based deep LSTM classifier for predicting the path of the vehicles by analyzing the attributes, such as velocity, acceleration, jitter, and priority of the vehicles. Result: The experimental results evaluate the efficacy of the traffic prediction model in terms of quadratic mean of acceleration (QMA), jitter, standard deviation of travel time (SDTT), and throughput, for which the values are found to be 37.43, 0.23, 8.75, and 100 respectively. Achievements: The proposed method attains the performance improvement of 5% to 42% when compared with the conventional methods.
2022
-
A comprehensive survey on leaf disease identification & classification
Multimedia Tools and Applications, vol. 81(23), pp. 33897–33925, 2022
-
An Automatic Lung Nodule Classification System Based on Hybrid Transfer Learning Approach
SN Computer Science, vol. 3(4), 2022
2021
-
A Survey of Lightweight Cryptography for Power-Constrained IoT Devices: Security Challenges and Issues
CRC Press eBooks, pp. 293–313, 2021
DOI Link BibTeX Cited by 6Abstract
As the Internet of Things (IoT) is growing exponentially, the number of data shared between IoT devices is increasing at an exponential rate. Almost all IoT devices are battery concerned devices in which power is very low, and these devices are interconnected and communicated to perform certain tasks, and also to transmit confidential and sensitive data over a communication channel. The IoT now enables power-restricted systems for communication, processing, and communication decisions. In stratified IoT networks, there are many problems and challenges, including protection, cheap power usage in computers, restricted battery size, memory space, high efficiency, and minimal communication network latency. We address in this paper a state-of-the-art lightweight cryptographic algorithm that includes lightweight block ciphers, hash functions, stream ciphers, high-performance systems, and low power-constrained devices and IoT network tools in detail. The lightweight cryptography algorithms are evaluated based on key size, block size, round size, and structure. We also explore the security framework, challenges, and key solutions for the power-constrained device of the IoT system.
-
Application of Internet of Things in Digital Pedagogy
Intelligent Systems Reference Library, pp. 219–234, 2021
-
Magnetic Resonance Imaging Classification Methods: A Review
Nanoelectronics, Circuits and Communication Systems, pp. 417–427, 2021
BibTeX Cited by 2Abstract
Magnetic resonance imaging (MRI) is one of the most important medical diagnosis methods in the field of computer-aided detection of medical images. The MRI images help to find the presence of abnormal cells or tissues, referred as tumors. Prior to classification, preprocessing of MRI images is performed. These preprocessing operations help to reduce undesired distortions and select only relevant features for further analysis, making the classification technique more accurate and efficient. In this paper, we present various image classification techniques used over MRI images and their performance.
-
TPA Auditing to Enhance the Privacy and Security in Cloud Systems
Journal of Cyber Security and Mobility, 2021
DOI Link BibTeX Cited by 36Abstract
Over the last decade, many enterprises around the world migrating from traditional infrastructure to cloud resources in order to cut down operational and capital expenditure. With cloud computing, huge amount of data transactions is communicated between cloud consumers and cloud service providers. However, this cloud computing enables surplus security challenges associated to unauthorized access and data breaches. We proposed in this paper a trusted third-party auditor (TPA) model which uses lightweight cryptographic system and lightweight hashing technique to ensure data security and data integrity to audit the cloud users outsourced data from cloud service providers. With our proposed system, we solve the concern of data reliability using data correctness and verification analysis and error recovery analysis. The time complexity of our proposed system is less as compared with other TPA model. Our proposed system also shows resistance against various known cryptanalytic attacks, the performance and extensive compression technique of our proposed system are probably secure and highly proficient.
2020
-
A Review on Medical Image Data Compression Techniques
2nd International Conference on Data, Engineering and Applications, IDEA 2020, pp. 1–6, 2020
DOI Link BibTeX Cited by 20Abstract
In most of the telemedicine applications, the role of image compression techniques is important to deal with the medical images. This will be used for storage and transfer of data over a low bandwidth channel like the Internet by pathologist to a doctor for diagnosis problems of patient.If a medical image is compressed using methods of lossy compression, the doctor will not be able to perceive any deterioration in quality with respect to the original input image. One of the main disadvantage of the lossy compression algorithms that are commonly used for multimedia applications not for medical image, while the overall quality of the image can be controlled to some extent, in these cases, it is necessary to use lossless compression algorithms, because the compression and decompression of an image is identical to the original image since the information is preserved during the decompression process after image compression the reconstructed image is exact replica of the original image means no information is lost in the coding process. The aim of this paper is to provide a review on various image compression techniques, which is used in medical image compression, performance analysis and compared existing research on medical image compression.
-
Bell pepper leaf disease classification using CNN
2nd International Conference on Data, Engineering and Applications, IDEA 2020, pp. 1–5, 2020
-
Comparative Analysis and Performance Evaluation of Medical Image Compression Method for Telemedicine
2nd International Conference on Data, Engineering and Applications, IDEA 2020, vol. 22, pp. 1–5, 2020
DOI Link BibTeX Cited by 3Abstract
In most of the telemedicine applications, the role of image compression techniques is important to deal with the medical images. This will be used for storage and transfer of data over a low bandwidth channel. One of the main drawbacks of the lossy compression algorithms is that it is not applicable for multimedia application while the overall quality of the image can be controlled to some extent. Due to the multiple properties of the Wavelet Transform over DCT, the wavelet based techniques (JPEG 2000) have produced better results compared to DCT based techniques (JPEG). Results of the above-noted techniques were compared and different parameters for medical images such as compression, MSE, SNR, PSNR analysis were carried out.
-
Plant leaf disease classification using grid search based SVM
2nd International Conference on Data, Engineering and Applications, IDEA 2020, pp. 1–6, 2020
-
Rapid and Efficient Medical Image Segmentation Using Thresholding and CLAHE with 3-Level FCM Clustering
SSRN Electronic Journal, 2020
2019
-
Gameplay using Reinforcement Learning
Devices for Integrated Circuit (DevIC), vol. 529, pp. 177–180, 2019
-
Role of Internet of Things (IoT) in Smart Farming: A Brief Survey
Proceedings of 3rd International Conference on 2019 Devices for Integrated Circuit, DevIC 2019, pp. 141–145, 2019
-
Ubiquitous and Emerging Concepts of Sensors
Proceedings of 3rd International Conference on 2019 Devices for Integrated Circuit, DevIC 2019, pp. 341–347, 2019
2017
-
Bi-objective virtual machine placement using hybrid of genetic algorithm and particle swarm optimization in cloud data center
International Journal of Applied Engineering Research, 2017
-
Multi-objective virtual machine placement using improved teaching learning based optimization in cloud data centers
International Journal of Applied Engineering Research, 2017
2016
-
Greedy approaches for deadline based task consolidation in cloud computing
International Conference on Computing, Communication and Automation, vol. 3, pp. 1271–1276, 2016
DOI Link BibTeX Cited by 2Abstract
In cloud infrastructure, an active users can demand for various of services to the cloud infrastructure simultaneously. So it must be a provision that all resources are made available to the user in efficient manner to satisfy the need. Effective utilization of a resource is analogous to lesser cost of utilization of that resource. Under Visualization, VMs are resources used to map incoming users request/tasks before the task is executed on the physical machine. This article shows an analysis of Greedy approach algorithms to efficiently map tasks to VMs and reduce the cost of utilization of VMs.
2015
-
Heuristic task consolidation techniques for energy efficient cloud computing
Web-Based Services: Concepts, Methodologies, Tools, and Applications, 2015
-
Performance analysis of greedy load balancing algorithms in heterogeneous distributed computing system
2014 International Conference on High Performance Computing and Applications, ICHPCA 2014, pp. 1–7, 2015