@vnrvjiet.ac.in
Senior Assistant Professor, Department of CSE (AIML & IoT)
Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology
Career Profile:
A highly dedicated, professional, and accomplished Computer Science Lecturer and Researcher with extensive knowledge of teaching and research in Computer Science. To work for an organization that will bring the best of my talent and utilizes my research and teaching skills to the fullest helps me achieve my and the organization's desired goals.
Research Experience:
Total research experience is 12 Years. Did the research on a new framework for brain tumor detection and classification in MRI images. A computer-assisted tool to automate the detection of a tumor area in MRI brain image(s). The automated approach should have the capability of localizing and segmenting the tumor area followed by the classification process, even in the low contrast MRI brain im
Diploma In CSE
B.Tech in CSE
M.Tech in CSE
Ph.D in CSE
Image Processing, Machine Learning, and Deep Learning
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
J.C. Sekhar, Ch Rajyalakshmi, S. Nagaraj, S. Sankar, Rajesh Saturi, and A. Harshavardhan
Elsevier BV
Awari Harshavardhan, Sreevardhan Cheerla, Anbusubramanian Parkavi, Saleth Angel Latha Mary, Kashif Qureshi, and Harshada Rangnath Mhaske
SPIE-Intl Soc Optical Eng
Bura Vijay Kumar, Khaja Mannan, Mothe Rajesh, D. Kothandaraman, A. Harshavardhan, and P. Kumaraswamy
Springer Nature Singapore
A. Harshavardhan, N. Uma Maheswari, M. Prakash, and Naresh Sammeta
IEEE
Brain tumor classification is beneficial for identifying and diagnosing the tumor’s specific location. According to the medical imaging system, early diagnosis and categorization of a tumor extend a person’s life. Clinical specialists rely heavily on magnetic resonance imaging (MRI) among numerous imaging modalities since it provides contrast information on brain malignancies. The primary purpose of this project is to use a competent automated approach that improves tumour identification accuracy. Several segmentation strategies have been developed throughout the years to achieve and improve the categorization precision of brain tumours. Brain picture segmentation has long been recognised as a difficult and time-consuming aspect of medical image processing. This method for detecting brain tumors Brain pictures are classified using the Full Resolution Convolutional Network (FRCN) classification architecture after pre-processing and segmentation. This study presents a Full Resolution Convolutional Network (FRCN) with Support Vector Machine (SVM) approach for detecting tumors on MRI scans. The procedure is broken down into four steps. In the first phase, the anisotropic filter is utilized to pre-process raw MRI images, followed by segmentation using the Support vector machine (SVM) and skull classification. The singular value decomposition and primary component analysis operations are performed in the third step. Tumors are then detected and classified using the Full Resolution Convolutional Network (FRCN) approach. Simultaneously, the Support Vector Machine (SVM) technique is employed to improve the classification precision of the study model. The experimental results showed an amazing accuracy rate of nearly 100% in detecting both normal and diseased tissues from brain MR images, confirming the efficacy of the suggested technique.
S. Raghavendra, A. Harshavardhan, S. Neelakandan, R. Partheepan, Ranjan Walia, and V. Chandra Shekhar Rao
World Scientific Pub Co Pte Ltd
One of the deadliest diseases in the world is brain cancer. Children and adults are also susceptible to this malignancy. It also has the poorest rate of survival and comes in a variety of shapes, textures, and sizes, depending on where it is found. Bad things will happen if the tumour brain is misclassified. As a reason, early detection of the right kind and grade of tumour is critical in determining the best treatment strategy. Brain tumours may be identified by looking at magnetic resonance imaging (MRI) pictures of the patient’s brain. The manual method becomes time-consuming and may lead to human mistakes due to the huge quantities of data and the different kinds of brain tumours. As a result, a computer-assisted diagnostic (CAD) system is needed. Image categorization methods have advanced significantly in recent years, particularly deep learning networks, which have achieved success in this field. In this case, we used a multilayer stacked probabilistic belief network to accurately classify brain tumors. Here the MRI brain images are Pre-processed using the Hybrid Butter worth Anisotropic filter and contrast Blow up Histogram Equalization. Followed by pre-processing, the denoised image can be segmented by using the bounding box U-NET segmentation methodology. Then after segmenting the target, the specialized features regarding the tumor can be extracted using the In-depth atom embedding method. Then they obtained can reduce feature dimensionality by using the Backward feature eliminating green wing optimization. The extracted features can be given as input for the classification process. A Multilayer stacked probabilistic belief network is then used to classify the tumour as malignant or benign. The suggested system’s efficacy was tested on the BraTS dataset, which yielded a high level of accuracy. Subjective comparison study is also performed out among the suggested technique and certain state-of-the-art methods, according to the work presented. Experiments show that the proposed system outperforms current methods in terms of assisting radiologists in identifying the size, shape, and location of tumors in the human brain.
B. Vijay Kumar, A. Harshavardhan, Khaja Mannan, P. Kumaraswamy, K. Sangameshwar, D. Kothandaraman, and Y. Chanti
AIP Publishing
Harshavardhan Awari, Neelakandan Subramani, Avanija Janagaraj, Geetha Balasubramaniapillai Thanammal, Jackulin Thangarasu, and Rachna Kohar
Wiley
S. Parthiban, A. Harshavardhan, S. Neelakandan, Vempaty Prashanthi, Abdul-Rasheed Akeji Alhassan Alolo, and S. Velmurugan
Hindawi Limited
The amount of energy required by Cloud Data Centers (CDCs) has increased significantly in this digital age, and as a result, there is a pressing need to reduce CDC energy ingesting. Consolidation of virtual machines (VMs) and effective virtual machine placement (VMP) techniques are commonly employed in large data middles to reduce energy consumption. The VMP is an NP-hard subject with infeasible optimum explanations even for tiny data middles, and it is dealt with using the Metaheuristic Optimization Algorithm, which is an experiential approach to optimization. With this in mind, this study introduces a novel energy-aware VMP technique for CDCs that is founded on the Disordered Salp Swarm Optimization Algorithm (EAVMP-CSSA) and is enhanced for energy efficiency (EAVMP-CSSA). The EAVMP-CSSA technique attempts to reduce CDC energy ingesting by dropping the quantity of active servers supporting virtual machines. The recommended EAVMP-CSSA strategy also aims to balance the resource operation of active servers (i.e., CPU, RAM, and Bandwidth), hence reducing waste and increasing efficiency. Furthermore, by combining the ideas of chaotic maps with the standard Salp Swarm Optimization Algorithm (SSA), the CSSA is intended to improve overall performance and reduce computational costs (SSA). A comprehensive range of experimental analyses are performed to ensure that the EAVMP-CSSA technique performs better, and the findings are compared to current VMP techniques. The EAVMP-CSSA approach achieves an effective outcome with a maximum service rate of 98.12%, whereas the Random, FFD, ACO, and AP-ACO procedures achieve a minimum service rate of 74.40%, 78.80%, 90.70%, and 96.31%, respectively. The experimental results demonstrate that the EAVMP-CSSA approach outperforms other assessment metrics.
R. Gopi, S. Veena, S. Balasubramanian, D. Ramya, P. Ilanchezhian, A. Harshavardhan, and Zatin Gupta
Computers, Materials and Continua (Tech Science Press)
A. Harshavardhan, Prasanthi Boyapati, S. Neelakandan, Alhassan Alolo Abdul-Rasheed Akeji, Aditya Kumar Singh Pundir, and Ranjan Walia
Hindawi Limited
Several studies aimed at improving healthcare management have shown that the importance of healthcare has grown in recent years. In the healthcare industry, effective decision-making requires multicriteria group decision-making. Simultaneously, big data analytics could be used to help with disease detection and healthcare delivery. Only a few previous studies on large-scale group decision-making (LSDGM) in the big data-driven healthcare Industry 4.0 have focused on this topic. The goal of this work is to improve healthcare management decision-making by developing a new MapReduce-based LSDGM model (MR-LSDGM) for the healthcare Industry 4.0 context. Clustering decision-makers (DM), modelling DM preferences, and classification are the three stages of the MR-LSDGM technique. Furthermore, the DMs are subdivided using a novel biogeography-based optimization (BBO) technique combined with fuzzy C-means (FCM). The subgroup preferences are then modelled using the two-tuple fuzzy linguistic representation (2TFLR) technique. The final classification method also includes a feature extractor based on long short-term memory (LSTM) and a classifier based on an ideal extreme learning machine (ELM). MapReduce is a data management platform used to handle massive amounts of data. A thorough set of experimental analyses is carried out, and the results are analysed using a variety of metrics.
C Pretty Diana Cyril, J Rene Beulah, Neelakandan Subramani, Prakash Mohan, A Harshavardhan, and D Sivabalaselvamani
SAGE Publications
The modern society runs over the social media for their most time of every day. The web users spend their most time in social media and they share many details with their friends. Such information obtained from their chat has been used in several applications. The sentiment analysis is the one which has been applied with Twitter data set toward identifying the emotion of any user and based on those different problems can be solved. Primarily, the data as of the Twitter database is preprocessed. In this step, tokenization, stemming, stop word removal, and number removal are done. The proposed automated learning with CA-SVM based sentiment analysis model reads the Twitter data set. After that they have been processed to extract the features which yield set of terms. Using the terms, the tweets are clustered using TGS-K means clustering which measures Euclidean distance according to different features like semantic sentiment score (SSS), gazetteer and symbolic sentiment support (GSSS), and topical sentiment score (TSS). Further, the method classifies the tweets according to support vector machine (CA-SVM) which classifies the tweet according to the support value which is measured based on the above two measures. The attained results are validated utilizing k-fold cross-validation methodology. Then, the classification is performed by utilizing the Balanced CA-SVM (Deep Learning Modified Neural Network). The results are evaluated and compared with the existing works. The Proposed model achieved 92.48 % accuracy and 92.05% sentiment score contrasted with the existing works.
A. Harshavardhan, Sushma Jaiswal, K.K. Arun, and V.R. Navaneeth
Elsevier BV
Kothandaraman D., A. Harshavardhan, V. Manoj Kumar, D. Sunitha, and Seena Naik Korra
Elsevier BV
Vempaty Prashanthi, Srinivas Kanakala, V. Akila, and A Harshavardhan
IEEE
Music genre prediction is a difficult job in the field in Retrieval of Musical Data. Music group categorization is essential for the music recommending systems, since genre has a high weight in such systems and their recommendations. A machine learning model is designed which automatically classifies the genre of a music clip. Here, we are going to extract acoustic music features with the help of digital signal processing and then classification of music is done with the help of machine learning methods. Librosa, is a tool we will be using for audio feature extraction, which offers a full-featured work-flow situation for low and high-level audio features. In this paper, we are going to utilize k-Nearest Neighbours method for the reason that in many research it is shown that this method gives good outcomes in such scenario. We will be using music dataset GTZAN Genre Collection (1010 clips).
Sallauddin Mohmmad, Ramesh Dadi, Syed Nawaz Pasha, Mruthyunjaya Mendu, A Harshavardhan, and Shabana
IOP Publishing
Abstract Fog Computing become an emerging technology and majorly adapted to IoT networks. In the IoT network Fog nodes interact directly with edge devices and create easy communication with reliable data transmission to store in cloud data centers. In this paper we proposed a Cost Function for Delay(CFD) in transmission of data from end devices to cloud data centers by passing through fog devices and other network devices in a multi hop based network. The total data transmission time included with many parameters including delay which occupies small amount of time in total data transmission time. The CFD evaluated for every local device on reach by each hop and at fog device where task offload dynamically. In our proposal we considered the greedy heuristic based approach to derive the solution effectively.
E Sudarshan, Seena Naik Korra, KM Prof. Rajasekharaiah, S Venkatesulu, and A Harshavardhan
IOP Publishing
Bonthala Prabhanjan Yadav, Sukhaveerji Ghate, A Harshavardhan, G Jhansi, Komuravelly Sudheer Kumar, and E Sudarshan
IOP Publishing
A Balasundaram, S Ashokkumar, D Kothandaraman, SeenaNaik kora, E Sudarshan, and A Harshaverdhan
IOP Publishing
Syed Nawaz Pasha, Dadi Ramesh, Sallauddin Mohmmad, A. Harshavardhan, and Shabana
IOP Publishing
Abstract Cardiovascular Disease or coronary illness is one of the significant dangerous infections in India as well as in the entire world. It is estimated that 28.1 % of deaths occur due to heart diseases. It is also the major cause for significant number of deaths which as more than 17.6 million in the year 2016. So proper and timely diagnosis, treatment of such diseases require a system that can predict with precise accuracy and reliability. Intensive research is carried out by various researchers using diverse machine learning algorithms to forecast the heart disease taking different datasets which consists of different attributes that result in heart attack. In this paper we analyzed the dataset collected from kaggle which consists of attributes related to heart disease such as age, gender, blood pressure, cholesterol and so on. We have also investigated the accuracy levels of various machine learning techniques such as Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Decision Trees (DT). The performance and accuracy of above algorithms is not so well when executed using large dataset, so here we tried to improving the prediction accuracy using Artificial Neural Network(ANN), Tensor Flow Keras.
Yerrolla Chanti, Seena Naik Korra, Bandi Bhaskar, A. Harshavardhan, and V Srinivas
IOP Publishing
Ramesh Dadi, Syed Nawaz Pasha, Mohammad Sallauddin, Chintoju Sidhardha, and A. Harshavardhan
IOP Publishing
Abstract Assessment is considered to play an essential function inside the Educational System. The interest of using automatic tools by human beings has been increased. So in the same way student response evaluation in education system with automatic assessment systems has grown exponentially in the last couple of years. Due to the increasing number of students and the use of online MOOC courses and lack of time and lack of consistency, assessment is shifted to automatic assessment. In this regard many of the researchers worked on it to make the assessment process easy. And they succeeded in assessment objective-type questions: i.e. multiple choices. Now here comes an interesting part is to assess the essays with automated tools. In this area, more number of researches worked and invented some tools for grading the essays but not up to the mark. Most of the assessment tools were assigning grades based on the style that is the number of sentences, the number of words, parts of speech, length of an essay, and grammar but not on the content of the essay. But few of the tools grading the essays based on the content by using traditional methods, and very few tools are using natural language processing methods.
A. Harshavardhan, D. Ramesh, P. Kumaraswamy, Mahesh Akarapu, Bhavana Jamalpur, and YerrollaChanti
IOP Publishing
Abstract Teaching Software engineering is very difficult because it includes theory and practical approach. Applying the theoretical knowledge is very complex. At the same time theory can’t be understood without applying. In this paper, we present an innovative teaching practice on the course “Software Engineering Practical” by which students will have a practical knowledge. We use different teaching steps and software tools to build an interactive lab atmosphere for the students to learn, recognize and understand the concepts of software engineering.
A Harshavardhan, D Ramesh, Syed Nawaz Pasha, S Shwetha, Sallauddin Mohmmad, and D Kothandaraman
IOP Publishing
Abstract He impaired are denied of all open doors for social and monetary turn of events. They have an absence of essential offices like wellbeing, instruction, and business. One of the crippled classifications is individuals who don’t have appendages. Limbless individuals face numerous issues like moving starting with one spot then onto the next, climbing steps, taking things from the rack or racks, and so forth. Our task intention is to answer the limbless individuals who are confronting issues in taking the things from the racks at the most extreme stature. We met our locale accomplice concerning this task talked about the issues looked by them. Because they collaborated with their issues, we thought of the most ideal arrangement which comforts and fulfills the client needs. Our item serves the genuinely impeded individuals in the general public in the most effective way.