Ch V Raghavendran
@acet.ac.in
Professor, Department of Information Technology
Aditya College of Engineering & Technology
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Science, Computer Science Applications, Computer Science
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Ganduri Srikanth, Ch V. Raghavendran, M. Ramkumar Prabhu, Marepalli Radha, N. V. Siva Kumari, and Sabitha Kumari Francis
Springer Science and Business Media LLC
Ch V Raghavendran, A S A Siddhardha, Md Sameeunnisa, S Jahnavi Sai Lakshmi, and M J V Surya
IEEE
The agricultural industry is crucial for providing high-quality food and significantly contributes to the growth of both economies and populations. However, plant diseases can lead to substantial losses in food production and reduce species diversity. By utilizing precise and automated recognition methods, timely diagnosis of plant diseases can increase food production quality and decrease economic losses. Recently, deep learning has greatly advanced the accuracy of image classification and object detection systems, enhancing their effectiveness. Agriculture is the backbone of any country’s economy and is vital for the people’s survival. To ensure high crop production efficiency, it is essential to prevent plant diseases. For this study we considered a dataset with total of 15 classes which includes both healthy and diseases classes of leaves of total 6 categories i.e Apple healthy, Apple cedar rust, Apple scab, Potato early blight, Potato late blight, Tomato Early blight, Tomato Late blight, Grape healthy, Grape black rot, Corn (maize) rust, Corn (maize) healthy, Cherry healthy, Cherry powdery mildew. The Dense Convolutional Neural Network (DCNN) is employed for classification. In this paper, a pre-trained neural network model, DenseNet-121 is applied on the dataset. The dataset is trained by freezing layers in the DenseNet architecture to increase the time complexity. The proposal aims to optimize resource information to improve outcomes without added complexity. This results a model with 99.2% accuracy and 0.3% loss. Fine-tuning layers were added to the DenseNet-121 model for achievement of enhanced and higher results.
Kathi Chandra Mouli, Ch. V. Raghavendran, V. Y. Bharadwaj, G. Y. Vybhavi, C. Sravani, Khristina Maksudovna Vafaeva, Rajesh Deorari, and Laith Hussein
Informa UK Limited
Kathi Chandra Mouli, Ch. V. Raghavendran, Ch. Mallikarjuna Rao, D. Ushasree, B. Indupriya, Nikolai Ivanovich Vatin, and Anup Singh Negi
Informa UK Limited
T. PrabhakaraRao, Satishkumar Patnala, Ch.V. Raghavendran, E. Laxmi Lydia, Yeonwoo Lee, Srijana Acharya, and Jae-Yong Hwang
Institute of Electrical and Electronics Engineers (IEEE)
K. Chandra Mouli, B. Indupriya, D. Ushasree, Ch.V. Raghavendran, Babita Rawat, and Bhukya Madhu
EDP Sciences
Network intrusion detection is a vital element of cybersecurity, focusing on identification of malicious activities within computer networks. With the increasing complexity of cyber-attacks and the vast volume of network data being spawned, traditional intrusion detection methods are becoming less effective. In response, machine learning has emerged as a promising solution to enhance the accuracy and efficiency of intrusion detection. This abstract provides an overview of proper utilization of machine learning techniques in intrusion detection and its associated benefits. The base paper explores various machine learning algorithms employed for intrusion detection and evaluates their performance. Findings indicate that machine learning algorithms exhibit a significant improvement in intrusion detection accuracy compared to traditional methods, achieving an accuracy rate of approximately 90 percent. It is worth noting that the previous work experienced computational challenges due to the time-consuming nature of the utilized algorithm when processing datasets. In this paper, we propose the exertion of more efficient algorithms to compute datasets, resulting in reduced processing time and increased precision compared to other algorithms to provide sustainability. This approach proves particularly when computational resources are limited or when the relationship between features and target variables is relatively straightforward.
C.N. Ravi, Ch. V. Raghavendran, G. Naga Satish, Kumbam Venkat Reddy, G Kasi Reddy, and Chinnala Balakrishna
Auricle Technologies, Pvt., Ltd.
Moringa Stenopetala is a plant species that is endemic to the southern region of Ethiopia. It is primarily cultivated for its nutritional value and is considered an important food source. The present research aimed to analyse the physicochemical properties of Moringa Stenopetala seed oil (MSO) obtained through solvent extraction method utilising hexane as the solvent. The collection of seeds was conducted in Adama, which is situated in the East Shawa zone of Oromia, Ethiopia. Prior to the extraction procedure, the seeds' average moisture content, crude ash, fibre, protein, and oil content were analysed and found to be 6.27%, 7.8%, 2.7%, 26.5%, and 43.2%, respectively. Using the Response Surface Method (RSM) and Artificial Neural Network (ANN), the extraction process was modeled. The study utilised numerical solutions to determine the optimal process parameters for maximising oil yield during extraction. The results indicated that a particle size of 0.85mm, a temperature of 85°C, and an extraction time of 4.75 hours were the most effective parameters. Furthermore, an investigation was conducted on the physical and chemical properties of the oil obtained under optimised conditions.
R.V.S. Lalitha, Divya Lalitha Sri Jalligampala, Kayiram Kavitha, and Ch.V. Raghavendran
IOS Press
The detection and tracking of objects in autonomous vehicles is essential for operation safety. There are several approaches for computing the distance between static objects. Conventional machine learning methods are using distance metrics to calculate the distance between the objects like Manhattan distance, hamming distance and Euclidean distance based on p-norm measure. But coming to the field of moving objects the focal length is the point of concern. In this paper, the object detection and also tracking of the object is worked out from the moving camera. The detection is performed based on You Only Look Once (YOLO) algorithms and the distance is calculated by finding the focal length between the object and camera. The methods tailored gave accurate results in assessing the spatial distance between the camera and the moving object.
Ch.V. Raghavendran, RVVN Bheema Rao, SK Mahaboob Basha, and T.R. Mani Chigurupati
IOS Press
This paper is intended to explore the research done on identifying the diseased plants and crops using Machine Learning (ML) and Deep Learning (DL) techniques during last 10 years using bibliometric methods. In this study, we used Scopus database to analyze on “Plant disease” or “Crop disease” using “Machine Learning” or “Deep Learning” or “Neural Networks”. This paper focuses on the importance of ML and DL techniques in identifying plant or crop diseases. The database collected from the Scopus is analyzed using VOSviewer software of version 1.6.16. The study is limited to publications from conferences, journals with subject areas are limited to Computer Science, Engineering and languages limited to English and Chinese. Scopus search outputs 824 articles on Plant or Crop diseases with ML, DL and Neural Networks covering conference papers and journal articles. Statistics showed that more articles were published during the last five years and major contributions were from India. By analyzing database on Authors, Subject area, Keywords, Affiliation, Source type it is evident that there is plenty of research scope in this area. Network analysis on diverse parameters specifies that there is a good scope to do research in this topic using advanced deep learning techniques.
Ch V Raghavendran, S K Mahaboob Basha, T. R. Mani Chigurupati, and R V S Lalitha
IEEE
Machine Learning (ML) algorithms can be used to forecast the production of bore oil volume. Different ML algorithms were applied to train the model over number of features. The public dataset for daily production was used for this study. The proposed model underwent various preprocessing stages before applying the algorithms. The data is purified by filling the null values with imputing methods like iterative imputer, KNN imputer. Accuracy of an algorithm is much influenced by the right feature and so, feature selection methods play a vital role. Random feature elimination with cross validation techniques like – linear regression, decision tree regression and random forest regression are used to identify prominent features that influence the dependent feature. Conventional regression algorithms like linear regression, polynomial regression are applied along with ensemble algorithms like Decision Tree Regressor, AdaBoost Regressor, Random Forest Regressor, Gradient Boost Regressor and XGBoost Regressor are applied on dataset. The metrics used to analyze the performance of these regression models includes Mean Square Error (MSE), Root Mean Square Error (RMSE), R2 Score. The traditional regressor algorithms are good at train data, they are failed to perform well on test data. Among the ensemble algorithms, XGBoost has performed will comparing with the remaining algorithms on both train and test dataset.
Vempati Krishna, Y. David Solomon Raju, Ch. V. Raghavendran, P. Naresh, and Adepu Rajesh
IEEE
Image Processing (IP) and Machine Learning (ML) are used to identify nutritional deficiencies in crops. Crops require an appropriate quantity of vitamins and minerals to finish and maintain a balanced lifetime. A adequate number of six key vitamins and minerals, such as nitrogen, calcium, phosphorus, potash, sulphur, and magnesium (mg), are highly critical for regular and robust crop development. Nutritional deficiencies or deficiency causes difficulty in performing out everyday crop operations and, as a result, reduces production. As a result, having a rapid assessment for nutritional intake is critical. Crops frequently have a noticeable shortage on their leaflets, with distinct configurations for every ingredient. The goal of our planned effort is to create an autonomous and dependable inexpensive alternative for nutritional deficit detection. The datasets for insufficient and healthier branches are constructed utilizing IP techniques such as RGB colour feature extractor, real-time texture recognition, edge recognition, and so on. This produced database will be used as a training images for supervised ML to discover and identify specific nutritional deficiencies and healthier seedlings in order to take precautionary actions to optimize production.
B. Narsimha, Ch V Raghavendran, Pannangi Rajyalakshmi, G Kasi Reddy, M. Bhargavi, and P. Naresh
FOREX Publication
Cyber security comes with a combination of various security policies, AI techniques, network technologies that work together to protect various computing resources like computing networks, intelligent programs, and sensitive data from attacks. Nowadays, the shift to digital freedom had led to opened many new challenges for financial services. Cybercriminals have found the ability to leverage e- currency exchanges and other financial transactions to perform their fraudulent activities. The unregulated channel makes it essential for banks and financial institutions to deploy advanced AI & ML (DL) techniques to fight cybercrime. This can be implemented by deploying AI & ML (DL) techniques. Customers are experiencing an increase in the fraud-hit rate in financial banking operations. It is difficult to defend against dynamic cyber-attacks using conventional non- dynamic algorithms. Therefore, AI with machine learning techniques has been set up with cyber security to build intelligent models for malware categorization & intelligently sensing the fraught with danger. This paper introduces the cyber security defense mechanism by using artificial intelligence (AI), machine learning (ML)) techniques with the current Feedzai security model to identifying fraudulent banking transaction. We have given a preface to the popular ML & AI model with random forest algorithm and Feedzai’s Open ML fraud detection software tool, which provides automatic fraud-recognition to the current intelligent framework for solving Financial Fraud Detection.
Ch. V. Raghavendran, G. Naga Satish, N. S. L. Kumar Kurumeti, and Shaik Mahaboob Basha
Springer Nature Singapore
R. V. Satya Lalitha, Rayudu Srinivas, Ch.V. Raghavendran, K. Kavitha, Pullela S. V. V. S. R. Kumar, and P. S. L. Sravanthi
Springer Singapore
T. Rama Reddy, P. V. G. D. Prasad Reddy, Rayudu Srinivas, Ch. V. Raghavendran, R. V. S. Lalitha, and B. Annapurna
Springer Science and Business Media LLC
AbstractEducation acts as a soul in the overall societal development, in one way or the other. Aspirants, who gain their degrees genuinely, will help society with their knowledge and skills. But, on the other side of the coin, the problem of fake certificates is alarming and worrying. It has been prevalent in different forms from paper-based dummy certificates to replicas backed with database tampering and has increased to astronomic levels in this digital era. In this regard, an overlay mechanism using blockchain technology is proposed to store the genuine certificates in digital form and verify them firmly whenever needed without delay. The proposed system makes sure that the certificates, once verified, can be present online in an immutable form for further reference and provides a tamper-proof concealment to the existing certification system. To confirm the credibility of the proposed method, a prototype of blockchain-based credential securing and verification system is developed in ethereum test network. The implementation and test results show that it is a secure and feasible solution to online credential management system.
K Prathyusha, K Helini, Ch V Raghavendran, and NSL Kumar Kurumeti
IEEE
The new virus named COVID-19 identified in Wuhan, China causes a severe impact on the respiratory system of the human. In considering its effect and spread in the community, the Government of India has imposed World’s biggest Lockdown from 25th March 2020. Later on, it was extended in another three phases as Lockdown 2.0, 3.0, and 4.0 with some relaxations in each Lockdown. In this paper, we have studied the COVID-19 patients’ data of Confirmed cases, Recovered cases, and Deaths based on before, after, and during lockdowns. The data analysis is done basing on the daily growth rate of confirmed cases, recovery rate, and fatality rate. We have applied Regression techniques viz., Linear Regression, Polynomial Regression of Machine Learning (ML) to predict the future spread of this virus in India. The Polynomial Regression has given accurate predictions comparing with the Linear Regression.
G. Naga Satish, Ch. V. Raghavendran, and R. S. Murali Nath
Springer Singapore
B. Annapurna, T Rama Reddy, Ch. V. Raghavendran, Raushan Kumar Singh, and Vedurai Veera Prasad
IOP Publishing
Abstract Biometric systems are the most advanced access technology developed so far in the 21st century. It does not even require to carry key cards or passwords in mind. Today most of the commercial and private entries are protected by biometric recognition systems like fingerprint scans facial recognition, retina scans, voice matching, etc. Even our phones, laptops, and daily access devices are equipped with biometric systems. In banks, the PCs are secured by the combination of passwords and fingerprint scans. Biometric scans are considered the most secure access technology so far. Our paper is to examine whether they are secure? Should we rely on them with our hard-earned money and social identity? Is there any way we can use these services without actually compromising our data and security? Our observation is on our digital identity. Promoting digitization in every department brings our topic in the picture. All our information is saved in our phones, our daily routine, whom we talk, what we purchase, whom we chat, where we travel, etc. Almost every smartphone has biometric fingerprint locks which means our phones have our fingerprint scans in database and with internet blend it’s tethered worldwide. Our fingerprints are connected to our bank accounts, PAN Cards, Passport, and SIM Cards using Aadhar Cards. If someone has our fingerprint they can easily reach our Aadhar Card and through that to all our personal information. Most of the phone companies are Chinese, Korean, German, and American. As per their country policies, they must share their data with the governing authorities. We aim to create a security system without actually using the biometric scans. The system is an advancement of the biometric system but with better accuracy and intelligence. We interface image acquisition tools to live track the red color things. The web camera or inbuilt system lens can be used as the acquisition system. When the red color object is moved in front of the lens it shows the corresponding coordinate of the object shown. We use these x and y coordinate of the objects as the authentication points. If the correct value grant access is 120 ⩽ x ⩽ 122 means the system grants permission only if the value of x=120,121 or 122 is obtained. Now, this is tricky. Even if you know the correct value also, it is very difficult to bring the correct point. Think about if you don’t know the point and it is also possible to make it much difficult by adding y coordinate so if the desired point is x=10, y=12 (10, 12) it is way more difficult. Each point is a possible password candidate and the screen of any device have megapixels where 1 Megapixel=106 pixels. Each pixel is a possible key or password entry. It can keep all our information safe and secure. We use a microcontroller and motor driver connected gate to demonstrate the result.
B. Lakshmi Sucharitha, Ch. V. Raghavendran, and B. Venkataramana
Springer Singapore
Ch. V. Raghavendran, G. Naga Satish, and P. Suresh Varma
Springer International Publishing