MEKALA SRINIVASA RAO
@cse.lbrce.ac.in
Professor in CSE department
Mekala Srinivasa Rao
EDUCATION
B.Tech, M.Tech, Ph.D
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Networks and Communications, Artificial Intelligence, Computer Vision and Pattern Recognition, Computer Science Applications
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Srinivasa Rao Mekala, Shaik Nazma, Kumbhagiri Nava Chaitanya, and Thota Ambica
Institute of Advanced Engineering and Science
<p>A major issue facing the quickly evolving technological world is the surge in security concerns, particularly for critical Internet-of-Things (IoT) applications like health care and the military. Early security attack detection is crucial for safeguarding important resources. Our research focuses on developing an anomaly-based intrusion detection system (IDS) using machine learning (ML) models. With the use of voting strategies, Bagging Ensemble, Boosting Ensemble, and Random Forest, we created a robust and long-lasting IDS. The F1 score is a crucial metric for measuring accurate predictions at the class level and serves as the focus of these ML systems. Maintaining a high F1 score in critical applications highlights the constant need for development. Make use of the latest CICIoT2023 data-set employ Hyper-ledger Fabric to create a private channel in order to bolster the security of our IDS through the usage of block-chain technology. We use block-chain's immutable record and cryptographic techniques to establish a decentralized, tamper-proof environment. Consequently, our proposed approach provides an efficient intrusion detection system that significantly enhances resource protection and alerting the user in prior with intruder information incritical regions for Internet of Things security applications.</p>
Erukala Suresh Babu, Mekala Srinivasa Rao, Gandharba Swain, A. Kousar Nikhath, and Rajesh Kaluri
Wiley
AbstractThe technological integration of the Internet of Things (IoT)‐Cloud paradigm has enabled intelligent linkages of things, data, processes, and people for efficient decision making without human intervention. However, it poses various challenges for IoT networks that cannot handle large amounts of operation technology (OT) data due to physical storage shortages, excessive latency, higher transfer costs, a lack of context awareness, impractical resiliency, and so on. As a result, the fog network emerged as a new computing model for providing computing capacity closer to IoT edge devices. The IoT‐Fog‐Cloud network, on the other hand, is more vulnerable to multiple security flaws, such as missing key management problems, inappropriate access control, inadequate software update mechanism, insecure configuration files and default passwords, missing communication security, and secure key exchange algorithms over unsecured channels. Therefore, these networks cannot make good security decisions, which are significantly easier to hack than to defend the fog‐enabled IoT environment. This paper proposes the cooperative flow for securing edge devices in fog‐enabled IoT networks using a permissioned blockchain system (pBCS). The proposed fog‐enabled IoT network provides efficient security solutions for key management issues, communication security, and secure key exchange mechanism using a blockchain system. To secure the fog‐based IoT network, we proposed a mechanism for identification and authentication among fog, gateway, and edge nodes that should register with the blockchain network. The fog nodes maintain the blockchain system and hold a shared smart contract for validating edge devices. The participating fog nodes serve as validators and maintain a distributed ledger/blockchain to authenticate and validate the request of the edge nodes. The network services can only be accessed by nodes that have been authenticated against the blockchain system. We implemented the proposed pBCS network using the private Ethereum 2.0 that enables secure device‐to‐device communication and demonstrated performance metrics such as throughput, transaction delay, block creation response time, communication, and computation overhead using state‐of‐the‐art techniques. Finally, we conducted a security analysis of the communication network to protect the IoT edge devices from unauthorized malicious nodes without data loss.
Mekala Srinivasa Rao, Birudugadda Kalyani, Baswani Vathsalya, Karri Dhanunjay, and Alasandalapalli Lakshmi Narayana
IEEE
This paper presents a strategy for discovering flaws in web applications through Machine Learning (ML). Web-based applications are especially troublesome to examine attributed to their variety and extensive usage of custom development methodologies. As little more than a basis, machine learning is extremely useful in website safety: It just might combine cognitive knowledge of web app terminology with automated software approaches based on verbally reported information. Mitch tool is the foremost machine learning strategy towards black-box investigation for Cross-Site Request Forgery (C.S.R.F) problems, was built using these principles. Mitch-helped us find Thirty-five recently developed cross-site request forgeries (C.S.R. Fs) in twenty wide fields, together with 3 main C.S.R. Fs in industry applications.
Mekala Srinivasa Rao, Sagenela Vijaya Kumar, Rambabu Pemula, and Anil Kumar Prathipati
Institute of Advanced Engineering and Science
<p>Visual change detection functions in X-ray analytics and computer vision attempt to divide X-ray images toward front and backside areas. There are various difficulties in change detection such as weather changes and shadows; real-time processing; intermittent object motion; lighting variation; and diverse object forms. Traditionally, this issue has been addressed via backdrop modeling methods and the creation of custom features. We present a new feature descriptor called pulmonary embolism detection using isomeric cluster (PEDIC), uses the concept of isomerism. The isomeric and cluster isomerism characteristics of the PEDIC are distinguish it from other graphs. At isomeric thetical orientations, the cluster pattern corresponds to consecutive differences in pixel intensity between the two images. Also, the clusters are oppositely orientated, and both clusters conform to a specified isomeric feature. The local area's lines and corner point information are identified and recorded using the PEDIC in several different directions. We introduced multiresolution PEDIC, which incorporates the multiresolution Gaussian filter to achieve increased resilience in the system. We expanded our research to include rotation-invariant characteristics. We also proposed inter-PEDIC and intra-PEDIC to identify motion changes in X-ray sequences, which allowed them to extract spatiotemporal characteristics.</p>
Satyala Narayana, Suresh Babu Chandanapalli, Mekala Srinivasa Rao, and Kalyanapu Srinivas
Oxford University Press (OUP)
Abstract The amount of data generated is increasing day by day due to the development in remote sensors, and thus it needs concern to increase the accuracy in the classification of the big data. Many classification methods are in practice; however, they limit due to many reasons like its nature for data loss, time complexity, efficiency and accuracy. This paper proposes an effective and optimal data classification approach using the proposed Ant Cat Swarm Optimization-enabled Deep Recurrent Neural Network (ACSO-enabled Deep RNN) by Map Reduce framework, which is the incorporation of Ant Lion Optimization approach and the Cat Swarm Optimization technique. To process feature selection and big data classification, Map Reduce framework is used. The feature selection is performed using Pearson correlation-based Black hole entropy fuzzy clustering. The classification in reducer part is performed using Deep RNN that is trained using a developed ACSO scheme. It classifies the big data based on the reduced dimension features to produce a satisfactory result. The proposed ACSO-based Deep RNN showed improved results with maximal specificity of 0.884, highest accuracy of 0.893, maximal sensitivity of 0.900 and the maximum threat score of 0.827 based on the Cleveland dataset.
E. Suresh Babu, M. Srinivasa Rao, Satuluri Naganjaneyulu, M. Srinivasa Sesha Sai, and Rajendra Kumar Ganiya
Inderscience Publishers
Yugandhar Garapati, G.Charles Babu, K. Venkata Murali Mohan, Mekala Srinivasa Rao, and J Kavitha
IEEE
Present Research tells about the intensity of information and communication technology by analytical hierarchy process utilized in a major big data study to convey data abouthow to make framework which will allow expanding and testing a lot of registering gadgets and a centerSoftware. The explanation of this task is to build the investigation framework for the rapid huge information preparing methodology and to get the center Software and standard ability. The explanation of this investigation is to execute the probability examination on this task. This examinationis utilizing the Analytic Hierarchy Process technique. It is built up the exact investigation process andcan quick demonstrate the intensity of the undertaking by manipulative the loads of the appraisalmethod. The result of this investigation, the total score by Analytic Hierarchy Process examination is 0.869. It demonstrates the execution if task is Possible.
C. Srinivasa Kumar, Ranga Swamy Sirisati, M. Srinivasa Rao, M. V. Narayana, and J. Rajeshwar
Springer Singapore
Erukala Suresh Babu, B. K. N. Srinivasarao, Ilaiah Kavati, and Mekala Srinivasa Rao
IGI Global
Fake certificates pose a severe problem in today's world; they vouch for an individual's false skillset and put an organization's reputation at risk. Moreover, the existing verification process is performed in a centralized manner, often too cumbersome and time-consuming to the end-user, lacking transparency in the educational institutions' Issuance of certificates. Of-late, blockchain is a promising technology that provides transparent, secure, and reliable features, which offers solutions to the education sector. This paper provides the solution to the educational certification problem by employing the blockchain network. We proposed a permissioned blockchain network that identifies, authenticates the Issuer, adequate verification, securely shares academic records to the recipients, and stores the certificate credentials in the blockchain in a distributed manner.
Mekala Srinivasa Rao, O. Pavan Kalyan, N. Naresh Kumar, Md. Tasleem Tabassum, and B. Srihari
IEEE
Classifying various music into its genre has a lot of applications in the real world. It plays an important role in several online music streaming services such as Gaana, Spotify etc. Most of the music recommender systems implement such feature. Over the past two decades music coming from various sources has been increasing at a high speed. Several musical communities are emerged based on the music genre. Therefore, in order to satisfy their requirements, the need for an automatic music genre classifier became evident. In the process of determining the genre of a music, accuracy of the prediction must be well maintained. In our project we are automatically classifying an unknown music into its genre with an effective accuracy. We are separating the linguistic content from the noise while extracting features from the set of audio files. This helps in obtaining a good accuracy of prediction. We are implementing various Machine Learning Algorithms to build our project. We considered the GTZAN dataset [4], which contains 1000 music files of 10 different genres with each file having a duration of 30 sec.
P S V Srinivasa Rao, Mekala Srinivasa Rao, P. Gopala Krishna, P. M. Yohan, and Kandru Arun Kumar
IEEE
This research paper presents the importance of cardiologists and their availability to the public by the usage of various smart devices. These new simplified ECGs may be as complex or sophisticated as those that represent the usage of the medical facility however they are accurately able to observe the heart rate to monitor their health. One of the most commonly overlooked problems in the modern world is Arrhythmia. This is a problem related to the rhythm of the heartbeat and it occurs due to the improper coordination between the electrical impulses with your heartbeat. Heartbeat occurs daily in the lives of several people as they aren’t properly focused upon the monitoring of heartbeat. This research paper attempts to focus on the issue of Heart Arrhythmia as well as the creation and classification model which is capable of identifying the type of heart arrhythmia by an individual how may be suffering from heart issues. To successfully create our model, this research work utilizes the convolution neural networks to train the proposed model with existing ECG data and properly identify the heart rate as well as the type of arrhythmia that they have so that it provides the ability to immediately provide the proper medical attention.
P. S. V. Srinivasa Rao, Mekala Srinivasa Rao, and Ranga Swamy Sirisati
Springer Singapore
Mekala Srinivasa Rao, P. S. V. Srinivasa Rao, and S. Ranga Swamy
Springer Singapore
Ranga SwamySirisati, Mekala Srinivasa Rao, and Srinivasulu Thonukunuri
IEEE
Medical Image Processing plays an essential role in human health. Many methods have played an essential role in reducing physician decision-making in diagnosis. Much caution is required and recommended, especially in cases involving the brain. Separation of tumors from normal brain cells belongs to the category of brain tumors. The dissection process can help provide the information needed for diagnosis. This process is risky due to the unusual shapes and manipulations at the border. Determining these tumors at an early stage can help provide the best treatment for patients. Typically, physicians adopt a manual method of dividing patients into patients, which leads to more time. This paper presents a well-functioning Hybrid Fusion-Neural Filter Approach (HFNF)classification system that considers various factors such as accuracy, recovery and accuracy. MRI is one of the most traditional methods for the primary diagnostic tool for brain tumors. If the tumor is malignant for successful treatment, the necessary diagnostic and treatment planning measures must be taken quickly. Physicians can make accurate decisions by applying the following procedures. The necessary treatment can be done effectively. A computer-assisted diagnostic system, MRI, can help reduce the workload of physicians.
Mekala Srinivasa Rao
Institute of Advanced Scientific Research
M. Srinivasa Rao*, , Dr. E. Suresh, P. Sivanagaraju, Ilaiah Kavati, , , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
This paper proposesan efficient monitoring unit for Controlled Environment Agriculture (CEA) system based on hydroponics environment using various IoTsensor nodes, which is mainly useful toanalyse the habitat conditions. This proposed work makes use of data logging mechanism, which provides detailed overview of the climatic conditions periodically to obtain better quality control along with reduced cost and effort. In particular, we analysed the habitat conditions for various seasonal regions of India and has been proved to be more reliable for these conditions of Indian agriculture.
E. Suresh Babu, Satuluri Naganjaneyulu, P. S. V. Srinivasa Rao, and M. Srinivas Rao
Springer Singapore