Kiran Mai Cherukuri

@vnrvjiet.in

Professor, Computer Science and engineering Department
Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology

Kiran Mai Cherukuri


               Download Compact PDF  
https://researchid.co/kiranmai

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science
13

Scopus Publications

Scopus Publications

  • Retraction Notice: Object Detection with Audio Feedback (E3S Web of Conferences (2024) 540 (14004) DOI: 10.1051/e3sconf/202454014004)
    Abbi Sandhya Rani, C. Kiran Mai
    E3s Web of Conferences, 2024
    We take a zero tolerance to any situation where fraudulent research is published in our journals. As a result, this article has been retracted by the Publisher because it is suspected to be a nonsensical computer-generated publication with a number of tortured phrases and irrelevant references. Additional measures have been implemented to prevent these issues from reoccurring. EDP Sciences is extremely grateful to anonymous whistleblowers and the Problematic Paper Screener [1] for bringing this case to our attention for further investigations.
  • Object Detection with Audio Feedback
    Abbi Sandhya Rani, C. Kiran Mai
    E3s Web of Conferences, 2024
    We take a zero tolerance to any situation where fraudulent research is published in our journals. As a result, this article has been retracted by the Publisher because it is suspected to be a nonsensical computer-generated publication with a number of tortured phrases and irrelevant references. Additional measures have been implemented to prevent these issues from reoccurring. EDP Sciences is extremely grateful to anonymous whistleblowers and the Problematic Paper Screener [1] for bringing this case to our attention for further investigations.
  • Analytical Framework to Understand Electric Vehicle Adoption by Leveraging Sentiment Analysis
    Madhu Bala Myneni, Haritha Akkineni, Cherukuri Kiran Mai, Sisira Boppana
    Journal of Mobile Multimedia, 2024
    Electric vehicles (EVs) are gaining eminence as a sustainable alternative to conventional vehicles. Even though EV’s are more expensive than conventional vehicles, people are excited about this green initiative. Hence, understanding public sentiment towards them becomes crucial for industry stakeholders and policymakers. This paper proposes a Twitter-based analytical framework to develop the application of sentiment analysis to understand public perceptions and concerns toward EVs. The opinions are tagged with three categories: constructive(positive), adverse(negative), and unbiased(neutral) from the overall public perception of electric mobility. It has been implemented in two phased manner as descriptive and predictive analytics on Twitter data. The study provides insights into the public’s support, concerns, and potential barriers to EV adoption. A sentiment model was evaluated with various machine-learning algorithms. The results ascertained that the SVM is performing well among all other models with 89% accuracy. Findings highlight critical factors influencing perception and offer recommendations for addressing public concerns to encourage broader acceptance of electric vehicles.
  • Applicant Credentials Tracker for Employment Using Blockchain Technology
    International Journal of Intelligent Systems and Applications in Engineering, 2024
  • Analyzing the Behavioral Artifacts for Malicious Software Detection Using Machine Learning Algorithms
    Nikkam Chandini, C. Kiran Mai
    Proceedings 2022 4th International Conference on Advances in Computing Communication Control and Networking Icac3n 2022, 2022
    Malicious software intentionally affects your computer system. Malware is analyzed using static or dynamic analysis techniques. These techniques are used to classify and predict unique patterns for correctly identifying malware. Over the last decade, many malware detection techniques have been proposed using a variety of techniques. In most cases, network-based attacks such as DDoS attacks are known network security risks. These causes usually cause network devices to overflow with more requests than they can handle, preventing the server from responding to legitimate requests. The biggest security risk is related to software. Software attacks can exploit the entire system, steal information, modify data, deny services, and endanger or damage devices. In particular, I am interested in dynamic analysis for developing malware detection systems that utilize machine learning techniques. This document proposes behavior-based malware detection techniques. To develop this model, we arrange a dynamic analysis approach and run malware samples using classifiers. To extracted for the malware detection system. To develop this technique, we create a dynamic analysis approach and run malware using classification algorithms. Computer programs connected to Internet are increasingly needed to analyze and prevent malware. The software exploits system vulnerabilities to unknowingly steal sensitive information and secretly send it to an attacker-controlled remote server. This approach uses the ML classifier to detect malware and identify the type of malware attacked in the dataset.
  • Emotion and Stress Recognition Through Speech Using Machine Learning Models
    Druva Manasa, C. Kiran Mai
    Learning and Analytics in Intelligent Systems, 2021
  • Classification of land cover images using modified water wave Optimization-based hybrid classifier
    Malige Gangappa, C. Kiran Mai, P. Sammulal
    International Journal of Computers and Applications, 2021
    The inadequate land cover data have predominantly limited the significance and impacts of land cover. Even though remote sensing or satellite imaging has been deployed in mapping several temporal and spatial scales, but its full effort was not yet recognized. Hence, this paper intends to implement a novel land cover classification model through optimal deep learning architecture. Here, it includes three main phases namely, (i) Segmentation (ii) Feature Extraction and (iii) Classification. Initially, the land cover image is segmented, and subjected for feature extraction process. For feature extraction, Vegetation Indexes (VI), such as Simple Ratio (SR), Normalized Difference Vegetation Index (NDVI) and Kauth–Thomas Tasseled Cap, are extracted. Furthermore, these features are classified using Neural Network (NN) and Convolutional Neural Network (CNN). In both the classifiers, the number of hidden neuron is optimized by modified Water wave Optimization (WWO) called Modified Propagation Update based WWO (MPU-WWO). The optimization of hidden neurons is done in such a way that the classification accuracy should be high, which is taken as the main objective.
  • Preface
    Learning and Analytics in Intelligent Systems, 2021
  • Predictive data analysis to identify heart anomalies
    , Sabha samreen, Dr.Kiran Mai Cherukuri, , Dommati Venkatsai Goud, and
    International Journal of Recent Technology and Engineering, 2019
    Heart disease is a usually used word to describe diseases related to heart, when heart is not efficiently performing at is best, most of this disease is acquired because of unhealthy lifestyle and unhealthy food. Heart diseases need regular care to improve the patient’s quality of life. We can analyze cardiac disabilities of a individual by factors like historical health data and risk factors .The fusion of algorithms with clinical data can forecast the results of any disease so, incorporating these two things for Predicting and diagnosis of the heart functionality using the computational algorithms where the user interface in developed in R studio. Foremost objective of the system is for majorly predicting the heart anomalies collected using the real time clinical data .The proposed method uses the performance comparison of the algorithms and as well as the datasets like random forest and logistic regression to calculate which gives highest accuracy rate performance and this study also involves use of two different datasets, one which is available in the existing dataset for heart disease and another which was collected from the hospital in real time, so this can help in making an efficient system that can be utilized to predict the probability of heart diseases of any individual. Thus this can form a foundation for any therapy or treatment to be given this would increase the efficiency as well as help the medical staff and doctors to predict heart disease and more accurately. Computer diagnosis and prediction of a disease can solve many medical problems by predicting it beforehand.
  • New machine learning based approach for predictive modeling on spatial data
    M. Gangappa, C. Kiran Mai, P. Sammulal
    2017 International Conference on Advances in Computing Communications and Informatics Icacci 2017, 2017
    Image classification domain has been an area which has attracted a lot of researchers over past years. Many classification methodologies for spatial image datasets has been developed. Artificial intelligence based approaches are getting popular now a days for getting the image classification task done in more efficient and correct way. The prime goal is to develop a classification mechanism which can handle the uncertainity in more efficient manner. This paper presents a novel approach for classification based predictive modeling technique for spatial data sets. Advanced machine learning concepts like RST are employed in our algorithmic procedure, which gives a major advantage of reduction in dimensionality of data in efficient way. Experiments are performed on Bhuvan NRSC geospatial repository datasets and simulation results are given.
  • Analysis of advanced data mining prototypes in spatial data analysis
    Journal of Engineering and Applied Sciences, 2017
  • On-board wireless data acquisition system and telemetry
    Proceedings of the International Telemetering Conference, 2013
  • A Comparative study on manual and automated system for wireless networks
    Journal of Theoretical and Applied Information Technology, 2010