@pvpsiddhartha.ac.in
Associate Professor
PVP siddhartha institute of technology
IoT data science and wsn
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Ravuri Daniel, Bode Prasad, Abhay Chaturvedi, Chinthaguntla Balaswamy, Dorababu Sudarsa, Nallathambi Vinodhkumar, Ramakrishna Reddy Eamani, Ambarapu Sudhakar, and Bodapati Venkata Rajanna
Institute of Advanced Engineering and Science
<p>The increasing demand for faster, robust, and efficient device development of enabling technology to mass production of industrial research in circuit design deals with challenges like size, efficiency, power, and scalability. This paper, presents a design and analysis of low power high speed full adder using negative capacitance field effecting transistors. A comprehensive study is performed with adiabatic logic and reversable logic. The performance of full adder is studied with metal oxide field effect transistor (MOSFET) and negative capacitance field effecting (NCFET). The NCFET based full adder offers a low power and high speed compared with conventional MOSFET. The complete design and analysis are performed using cadence virtuoso. The adiabatic logic offering low delay of 0.023 ns and reversable logic is offering low power of 7.19 mw.</p>
Ravuri Daniel, Bode Prasad, Pasam Prudhvi Kiran, Dorababu Sudarsa, Ambarapu Sudhakar, and Bodapati Venkata Rajanna
Institute of Advanced Engineering and Science
<span lang="EN-US">The recognition of handwritten digits holds a significant place in the field of information processing. Recognizing such characters accurately from images is a complex task because of the vast differences in people's writing styles. Furthermore, the presence of various image artifacts such as blurring, intensity variations, and noise adds to the complexity of this process. The existing algorithm, convolution neural network (CNN) is one of the prominent algorithms in deep learning to handle the above problems. But there is a difficulty in handling input data that differs significantly from the training data, leading to decreased accuracy and performance. In this work, a method is proposed to overcome the aforementioned limitations by incorporating a quantum convolutional neural network algorithm (QCNN). QCNN is capable of performing more complex operations than classical CNNs. It can achieve higher levels of accuracy than classical CNNs, especially when working with noisy or incomplete data. It has the potential to scale more efficiently and effectively than classical CNNs, making them better suited for large-scale applications. The effectiveness of the proposed model is demonstrated on the modified national institute of standards and technology (MNIST) dataset and achieved an average accuracy of 91.08%.</span>
Sudhakar Ambarapu, Ravuri Daniel, Sreekanth Puli, Satyanarayana Mummana, Nitalaksheswara Rao Kolukula, and Bodapati Venkata Rajanna
Institute of Advanced Engineering and Science
<p><span>In this study, multiple intelligent control systems for direct torque-controlled Synchronous motors are implemented and compared. Using a lookup table to pick a vector through the inverter voltage space, the direct torque control (DTC) system can be obtained. To replicate the state selector in relation to the look-up table, intelligent controllers are deployed. Intelligent logic controllers like fuzzy and neural are used to regulate the performance of permanent magnet synchronous motors (PMSM). In steady-state applications, neural and fuzzy controllers reduce the torque ripple and stator current harmonic distortion. These outcomes are compared with those obtained when the synchronous motor was put under the basic direct torque control method using a proportional integral (PI) controller. The accuracy and effectiveness of the suggested control topologies have been verified using computer simulation software like MATLAB/Simulink.</span></p>
Ravuri Daniel, T. Satyanarayana Murthy, Ch. D. V. P. Kumari, E. Laxmi Lydia, Mohamad Khairi Ishak, Myriam Hadjouni, and Samih M. Mostafa
Institute of Electrical and Electronics Engineers (IEEE)
Online social network (OSN) plays a crucial role to facilitate social connections; but, this social networking media increases antisocial behaviors, like trolling, cyberbullying, and hate speech. Cyberbullying has often resulted in serious physical and mental distress, especially for children and women, and even sometimes forces them to commit suicide. Conventional techniques for detecting cyberbullying, such as relying on users to report the instance of bullying, are not always effective. Deep learning (DL) and Machine learning (ML) techniques are trained to automatically recognize and flag potential cyberbullying content, along with identifying behavior patterns that are indicative of cyberbullying. Therefore, this study concentrates on the design and development of ensemble deep learning with tournament-selected glowworm swarm optimization (EDL-TSGSO) algorithm for cyberbullying detection and classification on Twitter data. The goal of the study is to examine social media data through the use of natural language processing (NLP) and ensemble learning process. This EDL-TSGSO technique preprocesses the raw tweets and then employs the Glove word embedding technique. In addition, the presented EDL-TSGSO technique utilizes ensemble long short-term memory with Adaboost (ELSTM-AB) model for effective cyberbullying detection and classification. The ensemble ELSTM-AB classifier integrates the prediction of LSTM and Adaboost models to enhance the overall classification performance. To further develop the cyberbullying detection performance of the EDL-TSGSO algorithm, the TSGSO algorithm is applied as a hyperparameter optimizer. The experimental validation of the EDL-TSGSO algorithm on the Twitter dataset demonstrates its promising performance over other state of art approaches in terms of different measures.
Ganga Rama Koteswara Rao, Jeevana Jyothi Pujari, Ravuri Daniel, Sunkari Venkata Rama Krishna, and Chindu Hema
IEEE
Transformer design, which recently emerged as the most promising solution for Natural Language Processing (NLP) tasks, is now state-of-the-art for these tasks. However, since sentences are composed of words and words are stored as vectors in NLP tasks, every problem involving multidimensional vector sequences should theoretically be able to be solved using a transformer model. In this article, the author will clearly explain the issues that motivated the research on transformers as well as the specifics of their architecture. He will also conduct a data analysis on a specific dataset and demonstrate a model that, by applying transformers to a series of multidimensional tabular data, can predict which should be used next.
Saud Yonbawi, Sultan Alahmari, T. Satyanarayana murthy, Ravuri Daniel, E. Laxmi Lydia, Mohamad Khairi Ishak, Hend Khalid Alkahtani, Ayman Aljarbouh, and Samih M. Mostafa
Computers, Materials and Continua (Tech Science Press)
Praveen Tumuluru, Ravuri Daniel, Gundabathula Mahesh, Kalavala Deekshitha Lakshmi, Pakalapati Mahidhar, and Muttum Vinay Kumar
IEEE
Class imbalance is a significant problem in many real-time domains dealing with healthcare data, which leads to poor classification performance and may have severe consequences. This work addresses the class imbalance problem in healthcare data, which often leads to poor classification performance and potentially serious consequences. This study proposes a hybrid PNM model that integrates the Near-Miss sampling technique and Principal Component Analysis to overcome this challenge. This study aims to investigate the effectiveness of the PNM model in improving classifier performance and compare it with several baseline classifiers. Further, the experiments are conducted on a real-world healthcare dataset containing various healthcare records. The results showed that the PNM model outperformed the baseline classifiers regarding the precision, recall, F1 score, and area under the curve (AUC). Specifically, the PNM model achieved a precision of - 0.85, recall of - 0.82, F1 score - 0.83, and AUC - 0.91, while the best-performing baseline classifier achieved a precision of 0.72, recall of 0.64, F1 score of 0.68, and AUC of 0.83. Our study demonstrates that the PNM model offers a promising approach to addressing the class imbalance in healthcare data and improving classifier performance. Integrating the Near-Miss sampling technique and Principal Component Analysis enables the model to achieve a better balance among the majority and minority classes, resulting in more accurate classification. The PNM model has the potential to be applied to various healthcare domains, such as disease diagnosis, patient risk stratification, and treatment prediction.
Laila Almutairi, Ravuri Daniel, Shaik Khasimbee, E. Laxmi Lydia, Srijana Acharya, and Hyun-Il Kim
Institute of Electrical and Electronics Engineers (IEEE)
T. Sathyanarayana Murthy, N. Mohan Krishna Varma, Daniel Ravuri, D. Kishore Babu, and Shaik Nazeer
Springer Nature Singapore
E. Laxmi Lydia, Jose Moses Gummadi, Sharmili Nukapeyi, Sumalatha Lingamgunta, A. Krishna Mohan, and Ravuri Daniel
Springer Singapore
E. Laxmi Lydia, Jose Moses Gummadi, Chinmaya Ranjan Pattanaik, B. Prasad, CH. Usha Kumari, and Ravuri Daniel
Springer Singapore
E. Laxmi Lydia, Jose Moses Gummadi, Chinmaya Ranjan Pattanaik, A. Krishna Mohan, G. Jaya Suma, and Ravuri Daniel
Springer Singapore
E. Laxmi Lydia, Jose Moses Gummadi, Chinmaya Ranjan Pattanaik, G. Jaya Suma, A. Krishna Mohan, and Ravuri Daniel
Springer Singapore
R. Daniel and K. N. Rao
Korean Society for Internet Information (KSII)
Melaku Tamene, Kuda Nageswara, and Ravuri Daniel
Springer International Publishing
Many cluster based routing protocols have been developed in order to enhance the network lifetime, but the potency of clustering in energy management highly relies on the optimality of clusters. Optimal cluster formation is the chief source of challenges in clustering protocols. In this paper, new approach has been introduced to formulate the optimization problem in the partition of networks into optimal organization of clusters. The optimization problem consists of finding optimal configuration of clusters such that the distance of cluster heads from the pre-computed cluster centers, communication cost of nodes to transport data and the expected energy dissipation of the network per the residual energy of cluster heads are minimized. The solution to the devised nonlinear clustering problem is found using the genetic algorithm. The genetic algorithm toolbox is developed in C++ and integrated with OMNeT++ simulation platform to implement the protocol. The experimental results verify that the proposed protocol extends the network lifetime compared to the prominent LEACH, LEACH-C and CHEF protocols.
R. Daniel and K. N. Rao
Korean Society for Internet Information (KSII)
Ravuri Daniel and Kuda Nageswara Rao
IEEE
Wireless Sensor Networks have found thousands of applications duo to new era of technologies like Internet of Things and Cloud to simplify the management of complex problems. Energy conservation in wireless sensor nodes is important concern to most of its applications. Duo to inherent issue of power limitation of sensor nodes, enhancing the specified network life time is the prime requirement. Therefore, an efficient routing protocol is needed to construct any real time applications of wireless sensor networks. The proposed, Fuzzy Verdict Mechanism Cluster Protocol (FVMCP) is used to construct knowledge based system effectively for the eligibility of the sensor node to be elected as a Cluster Header(CH). The eligibility of CH nodes based on their respective sensor nodes has important characteristics like duty cycle, energy level, geographical position, and number of hops. The simulation of FVMCP algorithm carried out in Mat Lab which shows enhancement of the performance accuracy up to 17 to 21 % in compassion with hard clustering methods.