Yalabaka Srikanth
@sru.edu.in
ASSISTANT PROFESSOR DEPARTMENT OF ECE
SR UNIVERSITY
RESEARCH, TEACHING, or OTHER INTERESTS
Engineering, Electrical and Electronic Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
V. Malathy, N. Shilpa, S. M. Kamali, M. Anand, S. Vimala, G. Shiva, and Y. Srikanth
AIP Publishing
N. Shilpa, V. Malathy, S. M. Kamali, M. Anand, S. Vimala, G. Shiva, and Y. Srikanth
AIP Publishing
Y. Srikanth, Ch. Rajendra Prasad, S. Srinvas, Sreedhar Kollem, and Rajesh Thota
AIP Publishing
Ch. Rajendra Prasad, Srikanth Yalabaka, Sreedhar Kollem, Srinivas Samala, and P. Ramchandar Rao
AIP Publishing
Srinivas Samala, Ch. Rajendra Prasad, Sreedhar Kollem, Srikanth Yalabaka, and P. Ramchandar Rao
AIP Publishing
Srikanth Yalabaka, Aravelli Tejaswi, Acha Nethaji, Ch. Rajendra Prasad, Konne Vamshi, and Naveen Kumar
AIP Publishing
Srikanth Yalabaka, B. Sneha, Ch.Rajendra Prasad, B. Vineetha, S. Srinith, and N. Revanth
IEEE
Epilepsy is a health condition that affects many individuals, potentially causing significant harm to the brain. Seizures, a common symptom of epilepsy, can result in severe injuries. Early detection of seizures is crucial to minimizing the impact of these injuries. A seizure prediction system aims to recognize when a seizure is likely to occur, facilitating timely intervention for individuals with epilepsy. In order to predict epileptic seizures, we used machine learning (ML) and deep learning (DL) models in this work. The machine learning methods used are SVM, Random Forest, Decision Tree, KNN, and Logistic Regression. Conventional neural networks, artificial neural networks, convolutional neural networks, recurrent neural networks, and long short-term memory are the DL algorithms used. Of these models, the Long Short-Term Memory deep learning model outperforms in terms of accuracy.
K. Sagar, B. Sathwika, M. Maniteja, I. Navaneeth Reddy, Ch. Rajendra Prasad, and Srikanth Yalabaka
IEEE
Skin-related illnesses are a significant worldwide health concern, and early detection is crucial to successful treatment. Traditional methods of diagnosing skin disorders rely on the expertise of dermatologists, which can be expensive and time-consuming. Moreover, in countries where dermatologists are in short supply, access to timely and accurate diagnosis may be restricted. This paper proposes a classification of skin diseases based on machine learning algorithms. The five machine learning approaches used for classification are k-nearest neighbours, random forests, decision trees, Naïve Bayes, and support vector machines. The dataset utilized in this investigation was provided by the dermatology department of Peking Union Medical College Hospital in China. The support vector machine is by far the most accurate of these models, with 91.94% accuracy.
Srikanth Yalabaka, Vanthadpula Harshini, Ch.Rajendra Prasad, Vipul Keerthi, Janagani Avinash, and Kasanaboina Muneeshwar
IEEE
The majority of women are affected by breast cancer. Considering that the majority of them are unaware that they have breast cancer. Improving breast cancer survival rates requires early detection and treatment. Statistical models, expert knowledge and judgment, modelling and simulation, historical comparisons and analogies, and expert knowledge and judgment can all be used to forecast breast cancer. Identifying the drawbacks and limitations of non-ML predictions; developing artistic or literary interpretations of predictions; and developing hybrid approaches that combine various prediction techniques, human judgment, creative thinking, and other non-quantitative factors in making predictions are some of its limitations. Using models for machine learning Python-based application of decision tree, random forest, logistic regression, and KNN algorithms for the prediction of breast cancer. The algorithms obtain good accuracy, precision, recall, and F1-score when tested on a widely used dataset on breast cancer.
Ch. Rajendra Prasad, Shayaan Hussain, B. Srinivas, Srinivas Samala, Ravichander Janapati, and Srikanth Yalabaka
IEEE
A brain tumor is characterized as an aggregation of abnormal cells within the brain. These tumors can be classified into two categories: malignant and benign. Malignant is cancerous whereas benign is not. Both tumors are very hazardous as they grow rapidly and attack different parts of the cerebrum. Even after extensive research, the cause of the brain tumor is unknown. In this paper, a VGG-19 and an Inception-Resnet V2 model are presented for detecting brain tumor by employing images of MRI scans. The dataset is gathered from Kaggle and preprocessed using Keras Image Data Generator. The VGG-19 model provided an accuracy of 99.71% and the Inception-Resnet V2 provided an accuracy of 99.28%. The proposed models performed well to achieve the task.
Ch. Rajendra Prasad, Sami Mohammed, P.Ramchander Rao, Sreedhar Kollem, Srinivas Samala, and Srikanth Yalabaka
IEEE
A brain tumour is a dangerous form of cancer that happens when cells divide in an abnormal way. Recent advances in deep learning have helped the medical imaging sector in the diagnosis of numerous diseases. This paper presents Multiclass MRI Brain Tumour Classification with Deep Transfer Learning. In the proposed model, VGG-16 is employed as a deep transfer learning model. The dataset is collected from the Kaggle brain tumour MRI dataset, which is a combination of three popular brain tumour datasets such as figshare, SARTAJ, and Br35H datasets. The data are prepossessed by rescaling and random brightness and/or contrast by ±20% before applying to the modified VGG-16 model. The proposed model employs minimum computational resources and achieves better results in accuracy, precision, recall, and F1 score.
K. Rajkumar, Ravi Teja Sri Ramoju, Tharun Balelly, Sravan Ashadapu, Ch.Rajendra Prasad, and Yalabaka Srikanth
IEEE
This study presents two types of Kidney cancer detection one is with the help of images and another one is with the help of blood test samples value. Kidney disease is condition caused either by renal disease of the kidneys. In the present study, Kidney cancer is one of the critical diseases for patient's diagnosis and classification. Early detection and good treatment can avoid or decrease the growth of cancer disease into the final stage where dialysis or renal transplantation is the only way of saving the life of the patient. And another way is with machine learning models with this model the disease at an early stage can be detected, is one of the important tasks in today's world. This research proposed kidney images detection through deep learning models like Convolutional Neural Networks (CNNs), and blood samples dataset values through Artificial Neural Network (ANN) models that can be helpful for the early diagnosis of cancer. The existing studies have mainly used only simple CNN models and have done another classification of kidney images. This research consists of CNN with more convolution layers for classifying images of cancer kidneys and normal kidneys and ANN is used for kidney cancer prediction using dataset values. This research will be helpful for early and accurate diagnosis of kidney cancer to save the lives of many patients. Lastly, there is an application page that contains a code in the backend that predicts whether a person is suffering from a kidney cancer or not.
Yalabaka Srikanth, Meghana Daddanala, Manchala Sushrith, Pranith Akula, Ch. Rajendra Prasad, and Dasari Sindhu Sri
IEEE
Agriculture is regarded as one of the most crucial occupation in India and the backbone of the country's economy, because agriculture employs and sustains 70% of the Indian people. Soil quality and climatic conditions are two significant elements that influence agriculture. Choosing a crop that does not suit the soil or climatic conditions not only reduces the crop's quality but also its quantity. To address this issue, this research study has developed a system to evaluate the soil quality and also provide crop recommendations. It also anticipates the fertilizer needed for the crop and even the market place using machine learning algorithms to maintain the suggestions as precise as possible based on soil characteristics like as soil nutrients, moisture, and rainfall, and then deploying of the proposed model.
Srinivas Samala, Nakka Bhavith, Raghav Bang, Durshanapally Kondal Rao, Ch. Rajendra Prasad, and Srikanth Yalabaka
IEEE
Tomatoes are the most widely grown vegetable, used in a wide variety of dishes around the world. After potatoes and sweet potatoes, it is the third most extensively cultivated crop in the world. However, due to several diseases, both the quality and quantity of tomato harvests dedine. To maximize tomato yields, it is important to identify and eradicate the many diseases that harm the crop as early as possible. In this paper, we investigate the potential of deep learning techniques for diagnosing diseases on tomato leaves. The use of automatic methods for tomato leaf disease detection is helpful because it reduces the amount of monitoring needed in large-scale crop farms and does so at a very early stage when the signs of the disease identified on plant leaves are still easy to cure. The Kaggle dataset for tomato leaf disease was used for the study. A technique based on convolutional neural networks is used for disease identification and classification. Deep learning models, such as Inception V3 are used in this work. This proposed system obtained an accuracy of 99.60% suggesting that the neural network approach is effective even under difficult situations.
Ch.Rajendra Prasad, Banothu Arun, Soma Amulya, Preethi Abboju, Sreedhar Kollem, and Srikanth Yalabaka
IEEE
Breast cancer is the deadliest and most common cancer in the world. Early treatment of this cancer can help to nip it in the bud. In present medical setting, this cancer is identified by manual clinical procedures, which can lead to human errors and further delay the treatment procedure. So, we propose a Convolutional Neural Network (CNN) model employed with transfer learning approach with RESNET50, VGG19 and InceptionV3 algorithms. The histopathological image dataset is used to detect cancer cells in the tissues of the breast. We examine the performance of different models based on their accuracy, by varying different optimizers (Adam, SGDM and RMSProp) for each transfer learning model. The results show that the Inception-V3 model with Adam optimizer outperforms VGG19 and RESNET-50 in terms of accuracy.
Y. Srikanth, Ch. Rajendra Prasad, P. Ramchandar Rao, and G. Sunil
AIP Publishing
Ch. Rajendra Prasad, P. Ramchandar Rao, Y. Srikanth, and A. Chakradhar
AIP Publishing
Y. Srikanth, Ch. Rajendra Prasad, P. Ramchandar Rao, and G. Sunil
AIP Publishing
Ch. Rajendra Prasad, Y. Srikanth, P. Ramchandar Rao, and Kollem Sreedhar
AIP Publishing
Ch. Rajendra Prasad, Sreedhar Kollem, Srinivas Samala, P. Ramchandar Rao, Srikanth Yalabaka, and A. Chakradhar
IEEE
Digitization of ancient scripts is more important to make available for future generations. Devanagari script is the most popular ancient Indian literature of India. Over the last decade the researcher focusing on Devanagari script digit classification. This paper presents Devanagari script digit classification using modified AlexNet with transfer learning. The pre-trained AlexNet 23rd and 25th layers modified for the requirement of Devanagari script digit data. The proposed model employs a dataset from the Kaggle and Stochastic Gradient Descent with a momentum optimizer employed for training. The proposed model shows impressive results in terms of accuracy of 93.64%.
Srinivas Samala, Ch. Rajendra Prasad, Sreedhar Kollem, P. Ramchandar Rao, Srikanth Yalabaka, and Ramu Moola
IEEE
Due to remarkable performance, deep neural networks have gained popularity in computer vision and machine learning applications such as regression, segmentation, classification, detection, and pattern recognition over the past few years. This paper examines the categorization of handwritten telugu vowel characters using a modified 25-layer AlexNET and transfer learning approach. The six-class Handwritten Telugu vowel dataset from Kaggle is utilized in this experiment. To accommodate the required amount of vowel dataset classes, the 23rd and 25th layers of pre-trained AlexNET are adjusted. Training makes advantage of stochastic gradient descent using momentum optimizer. The proposed model accurately classified handwritten telugu vowel characters with a remarkable 99.72 % accuracy.
Srikanth Yalabaka, Ch. Rajendra Prasad, P. Sanjana, B. Lokesh, T. Shradha, and Srinivas Samala
IEEE
Deep learning techniques provide solutions to various real-world problems and have given rise to many innovations. One such innovation is autonomous vehicles; the key parameter of autonomous vehicles is providing the correct path which is nothing but detecting the road lanes. We primarily focused on detecting the path using an image dataset. The dataset consists of images of roads taken during morning, night and in various weather conditions. The dataset contains around 5000+ images. The deep learning algorithm that we used is a convolution neural network. Convolution neural network mimics the human brain and it is the most used algorithm for image processing. We built a CNN model that takes an image as input and processes it through different layers and extracts the necessary features. The features extracted are used for identifying the path from the testing images with utmost accuracy. The deep learning model that can effectively detect the path is built using google colab.
Ch Rajendra Prasad, Sandeep Kumar V, P Ramchandar Rao, Sreedhar Kollem, Srikanth Yalabaka, and Srinivas Samala
IEEE
Internet of Things (IoT) enables the development of several applications to create a “smart city” with enhanced safety, comfort, and, ultimately, quality of life. IoT possessing heavy data and need storage capacity due to implementation of heavy data applications processing. The affects cloud cause to unreliable latency and lack of storage support and also location awareness problems. Cloud is a distributing computing platform where cloud users connecting and accessing information anytime and from anywhere. As per load on cloud, the users delay in accessing web page loading from internet. Because of complexity of latency when accessing the internet. There are three reasons at first, cloud centers are situated far away from cloud users and second, latency occurs heavy workload by distributed access by cloud users. Third, cloud is executing on various virtual machines for heterogeneous work load. The introduction of Fog computing reduces the time it takes to access apps and reduces cloud latency. As a result, IoT apps can better respond to requests and provide better services. This study proposes a Survey on Task offloading of Fog Computing to reduce latency, maximize computation, storage capacity, and network bandwidth by utilizing nature inspired computing (NIC) methods. The objective this paper is effectively balancing of IoT applications load over fog nodes to minimize response time, minimize communication cost by applying NIC algorithms. This research intends to give a thorough literature assessment on offloading activities in IoT applications for smart city of fog computing using NIC methods.
Matta Preethi Reddy, MD.Farhan Mohiuddin, Shruthi Budde, Gajula Jayanth, Ch.Rajendra Prasad, and Srikanth Yalabaka
IEEE
In today's world, the accident rate due to negligence of observing traffic signs and not obeying traffic rules has been increasing drastically. By utilization of synthesized training data, which are created from road traffic sign images allows us to overcome the problems of traffic sign detection databases, which vary for countries and regions. This method is used for the generation of a database which consists of synthesized pictures to detect traffic signs under different view-light conditions. With this data set and a perfect Convolutional Neural Network (CNN), we can develop a data driven, traffic sign recognition and detection system which has high detection accuracy and also has high performance ability in training and recognition processes. This ensures less occurrence of accidents and also helps the driver to concentrate on driving rather than observing each and every traffic sign.
Sabiha Tanveez, MD. Amer, C. Vamshika, A. Sangeeth Reddy, Ch.Rajendra Prasad, and Srikanth Yalabaka
IEEE
Nowadays laptops are imaginative and prescient is growing rapidly. Face detection and recognition are turning into the profitable application of image evaluation and understanding based on the algorithm. First of all, emotion detection is a very necessary challenge for many companies reacting to the products launched with the aid of them. Also, it helps them to comprehend whether their employees are satisfied with the facilities given to them. Also, it can discover the temper of a character via a camera. Due to this computer image processing and understanding, the utility used will enable the person to analyze a person's facial expressions. This software will be developed using Python in the Google Colab.