Department of Electrical Engineering
Permanent URI for this collection
Browse
Browsing Department of Electrical Engineering by Author "Cherukuri, Aswani Kumar"
Now showing 1 - 12 of 12
Results Per Page
Sort Options
Item A Secure Peer-to-Peer Image Sharing Using Rubik's Cube Algorithm and Key Distribution Centre(Sciendo, 2023-09-01) Cherukuri, Aswani Kumar; Sannuthi, Shria; Elagandula, Neha; Gadamsetty, Rishita; Singh, Neha; Jain, Arnav; Sumaiya Thaseen I.; Priya V.; Jonnalagadda, Annapurna; Kamalov, FiruzIn this work, we build upon an implementation of a peer-to-peer image encryption algorithm: "Rubik's cube algorithm". The algorithm utilizes pixel-level scrambling and XOR-based diffusion, facilitated through the symmetric key. Empirical analysis has proven this algorithm to have the advantage of large key space, high-level security, high obscurity level, and high speed, aiding in secure image transmission over insecure channels. However, the base approach has drawbacks of key generation being handled client-side (at nodes) and the process is time-consuming due to dynamically generating keys. Our work solves these issues by introducing a Key Distribution Center (KDC) to distribute symmetric keys for transmission, increasing confidentiality, and reducing key-generation overhead on nodes. Three approaches utilizing the KDC are presented, communicating the dimensions with KDC to generate keys, standardizing any image to fixed dimensions to standardize key-generation, and lastly, using a single session key which is cyclically iterated over, emulating different dimensions. © 2023 Aswani Kumar Cherukuri et al., published by Sciendo.Item Comparative analysis of activation functions in neural networks(Institute of Electrical and Electronics Engineers Inc., 2021) Kamalov, Firuz; Nazir, Amril; Safaraliev, Murodbek; Cherukuri, Aswani Kumar; Zgheib, RitaAlthough the impact of activations on the accuracy of neural networks has been covered in the literature, there is little discussion about the relationship between the activations and the geometry of neural network model. In this paper, we examine the effects of various activation functions on the geometry of the model within the feature space. In particular, we investigate the relationship between the activations in the hidden and output layers, the geometry of the trained neural network model, and the model performance. We present visualizations of the trained neural network models to help researchers better understand and intuit the effects of activation functions on the models. © 2021 IEEE.Item Deep learning for Covid-19 forecasting: State-of-the-art review(Elsevier B.V., 2022-10-28) Kamalov, Firuz; Rajab, Khairan; Cherukuri, Aswani Kumar; Elnagar, Ashraf; Safaraliev, MurodbekThe Covid-19 pandemic has galvanized scientists to apply machine learning methods to help combat the crisis. Despite the significant amount of research there exists no comprehensive survey devoted specifically to examining deep learning methods for Covid-19 forecasting. In this paper, we fill the gap in the literature by reviewing and analyzing the current studies that use deep learning for Covid-19 forecasting. In our review, all published papers and preprints, discoverable through Google Scholar, for the period from Apr 1, 2020 to Feb 20, 2022 which describe deep learning approaches to forecasting Covid-19 were considered. Our search identified 152 studies, of which 53 passed the initial quality screening and were included in our survey. We propose a model-based taxonomy to categorize the literature. We describe each model and highlight its performance. Finally, the deficiencies of the existing approaches are identified and the necessary improvements for future research are elucidated. The study provides a gateway for researchers who are interested in forecasting Covid-19 using deep learning. © 2022 Elsevier B.V.Item Digital twin technology: Security implications and issues(Nova Science Publishers, Inc., 2023) Nikhil, C.; Rahul, K.; Cherukuri, Aswani Kumar; Kamalov, Firuz; Srinivasan, KathiravanItem Forecasting COVID-19: Vector Autoregression-Based Model(Springer Science and Business Media Deutschland GmbH, 2022-06) Rajab, Khairan; Kamalov, Firuz; Cherukuri, Aswani KumarItem Keep it simple: random oversampling for imbalanced data(Institute of Electrical and Electronics Engineers Inc., 2023) Kamalov, Firuz; Leung, Ho-Hon; Cherukuri, Aswani KumarItem Machine learning and blockchain integration for security applications(River Publishers, 2022-11-11) Bhandari, Aradhita; Cherukuri, Aswani Kumar; Kamalov, FiruzItem Machine learning applications for COVID-19: a state-of-the-art review(Elsevier, 2022-01-01) Kamalov, Firuz; Cherukuri, Aswani Kumar; Sulieman, Hana; Thabtah, FadiItem Machine learning applications to COVID-19: a state-of-the-art survey(Institute of Electrical and Electronics Engineers Inc., 2022) Kamalov, Firuz; Cherukuri, Aswani Kumar; Thabtah, FadiThere exists a large and rapidly growing body of literature related to applications of machine learning to Covid-19. Given the substantial volume of research, there is a need to organize and categorize the literature. In this paper, we provide the most up-to-date review as of the beginning of 2022. We propose an application-based taxonomy to group the existing literature and provide an analysis of the research in each category. We discuss the progress as well as the pitfalls of the existing research, and propose keys for improvement. © 2022 IEEE.Item Proactive AI Enhanced Consensus Algorithm with Fraud Detection in Blockchain(Springer, 2023) Das, Vinamra; Cherukuri, Aswani Kumar; Hu, Qin; Kamalov, Firuz; Jonnalagadda, AnnapurnaThe security and transparency provided to the data in blockchain are unmatchable, with the least instances of system hack or failure reported. With a number of consensus algorithms used in the past and the presence of leader nodes in many of them, it is important to check the leader node’s activities. As the system is large, the usage of artificial intelligence and deep learning methodologies seems the right choice to monitor the leader node’s activities. Hence in this chapter, an algorithm is proposed as to how should the consensus algorithm be modified while adding deep learning techniques to keep track of the leader node’s selection behaviors. It also explains how the system detects and moves back to stability once such a scenario is encountered. Hence in this work, the artificial neural network is used to learn the node selection behavior of the leader node by taking in 5 input parameters: sender ID, receiver ID, transaction amount, sender’s balance, and receiver’s balance. Output is either 0 (not selected into the chain) or 1 (selected into the chain) once trained neurons (each input parameter) are tested for it’s sensitivity to the selection. If it exceeds a threshold value, it is assumed to be biased upon that parameter/s, and further consensus occurs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Synthetic Data for Feature Selection(Springer Science and Business Media Deutschland GmbH, 2023) Kamalov, Firuz; Sulieman, Hana; Cherukuri, Aswani KumarFeature selection is an important and active field of research in machine learning and data science. Our goal in this paper is to propose a collection of synthetic datasets that can be used as a common reference point for feature selection algorithms. Synthetic datasets allow for precise evaluation of selected features and control of the data parameters for comprehensive assessment. The proposed datasets are based on applications from electronics in order to mimic real life scenarios. To illustrate the utility of the proposed data we employ one of the datasets to test several popular feature selection algorithms. The datasets are made publicly available on GitHub and can be used by researchers to evaluate feature selection algorithms. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item XyGen: Synthetic data generator for feature selection[Formula presented](Elsevier B.V., 2023-03) Kamalov, Firuz; Elnaffar, Said; Sulieman, Hana; Cherukuri, Aswani KumarGiven the large number of feature selection algorithms, it has become imperative to have a uniform procedure for evaluating the performance of the algorithms. We propose a library of synthetic datasets designed specifically to test the effectiveness of feature selection algorithms. The datasets are inspired by applications in the field of electronics and have a range of characteristics to provide a variety of test scenarios. The software comes in the form of a Python library with standard interface for loading and generating datasets. Each dataset is implemented as a function that allows control of various parameters of the data. © 2023 The Author(s)