Sadashiva V. Chakrasali
@msrit.edu
Assistant Professor, Electronics and Communication
m s ramaiah institute of technology
EDUCATION
M.Tech, PhD
RESEARCH, TEACHING, or OTHER INTERESTS
Electrical and Electronic Engineering, Computer Vision and Pattern Recognition
Scopus Publications
Scopus Publications
A. Divya, S. Ramesh, Sadashiva V. Chakrasali, Meriga Kiran Kumar, Mohammad Taj, Rajendra Kumar Ganiya, J. Nageswara Rao, Balasubramanian K, and Shamimul Qamar
Elsevier BV
V. Dankan Gowda, Sadashiva V. Chakrasali, Pullela SVVSR Kumar, Sampada Abhijit Dhole, Jayamala Kumar Patil, and Shivoham Singh
Taru Publications
Federated Learning (FL) has turned out to be one of the most useful techniques for enabling distributed machine learning while protecting the data. Thirdly, because FL is distributed, the introduced feature is susceptible to several attacks associated with security. The current paper develops a new cryptographic solution that can enhance the security of FL frameworks. Thus, applying the cryptographic technologies, the employ of the proposed method ensures reliable data protection against the losses and illicit interventions. Experimental evaluations for this strategy are numerous and illustrate how, at the same time, our approach defends FL operations on the practical level while providing performance. It should also be noted how the results can provide a clear depiction to prove how beneficial our cryptographic solution will be in the context of improving the security of federated learning and paving the way for safer and more reliable FL implementations.
M. Nagabushanam, Sadashiva Chakrasali, S. L. Gangadharaiah, Sampath H. Patel, Gurumurthy Ramaiah, and Raju Basak
Springer Science and Business Media LLC
V. Dankan Gowda, Sadashiva V. Chakrasali, Ved Srinivas, K.D.V. Prasad, and Saptarshi Mukherjee
Wiley
V. Dankan Gowda, Y. N. Sunitha, Sadashiva V. Chakrasali, K. D. V. Prasad, Parismita Sarma, and Mirzanur Rahman
Taru Publications
Accurate diagnosis and well-informed treatment choices are only possible with the help of sophisticated medical imaging technology. The introduction of digital imaging methods has led to a dramatic rise in the volume of data associated with medical images, which in turn has led to difficulties in their storage, transmission, and administration. It is crucial to utilize effective image compression techniques to address these challenges without compromising the diagnostic integrity of the pictures. The wavelet transform has matured into a potent method for striking a good compromise between picture quality and file size reduction while compressing. The safe and efficient transfer of medical image data is a major concern in today’s healthcare settings. In this academic investigation, we investigate how wavelet transform-based techniques may be used to enhance medical picture compression. The proposed techniques optimize compression ratios while maintaining diagnostic picture quality by making use of the wavelet transform’s multi-resolution and frequency localization features. To address the unique challenges given by medical image collections, various iterations of the wavelet transform and compression techniques are investigated. Through a series of detailed tests involving several medical picture modalities, the effectiveness of these technologies is thoroughly evaluated, demonstrating their effectiveness in achieving significant data reduction without sacrificing clinical information.
Rajendra Prasad P, Sadashiva V Chakrasali, M. Nagabushanam, V Nuthan Prasad, and Shashank H N
IEEE
Delta sigma modulation (DSM) is a prominent technique in both analog-to-digital conversion (ADC) and digital-to-analog conversion (DAC), known for its ability to achieve high resolution and dynamic range while maintaining low power consumption. This paper introduces a novel implementation of delta sigma ADC and DAC converters aimed at enhancing high-resolution analog signal processing applications. Leveraging advanced delta sigma modulation techniques, the design and implementation of the converters are outlined, emphasizing oversampling, noise shaping, and decimation strategies to achieve superior performance. The ADC stage employs delta sigma modulation to encode analog signals into high-resolution digital format while mitigating quantization noise through noise shaping techniques. Following the ADC stage, the paper explores the reconstruction process in the DAC stage, focusing on inverse delta sigma modulation techniques to faithfully reconstruct the analog signal from digital data. Design considerations such as digital filter design, quantization error compensation, and signal-to-noise ratio optimization are addressed to ensure accurate signal reconstruction. Results highlight significant improvements in signal fidelity and noise reduction compared to conventional ADC-DAC systems. This work represents significant advancements in high-resolution analog signal processing systems, promising enhanced performance and reliability in various real-world applications including telecommunications, audio processing, and sensor interfaces.
Avinash Sharma, K.D.V. Prasad, Sadashiva V. Chakrasali, Dankan Gowda V, Chanakya Kumar, Abhay Chaturvedi, and A. Azhagu Jaisudhan Pazhani
Elsevier BV
Sadashiva Veerappa Chakrasali, Krishnappa Indira, Sunitha Yariyur Narasimhaiah, and Shadaksharaiah Chandraiah
Institute of Advanced Engineering and Science
Text <span lang="EN-US">to speech (TTS) is a system that generates artificial speech from text input. The prosodic models used improve the quality of the synthesized speech especially naturalness and intelligibility. The prosody involves intonation, intonation refers to the variations in the pitch frequency (F0) with respect to time in an utterance. This work mainly concentrates on building feedback neural network model to predict F0 contour in the utterances using Fujisaki intonation model parameters as the input features to the network since the Fujisaki intonation model is data driven and not a rule based one. In this work we have built 4-layer feedback neural network in the festival framework. Finally, the synthetically generated Kannada speech using the neural network model, is compared for its performance with the classification and regression tree (CART) model and Tilt model. Database of simple declarative Kannada sentences created by Carnegie Mellon University have been deployed in this work. From the study it is very clear that F0 contours can be accurately predicted using CART and neural network models, whereas naturalness and intelligibility is high in CART model rather than neural network model.</span>
Satish Tunga, Sadashiva V. Chakrasali, N. Shylashree, Latha B. N., and Mamatha A. S.
Institute of Advanced Engineering and Science
A new algorithm is described for determining the optimal round-trip paths for two moving sinks in a wireless sensor network. The algorithm uses binary integer programming to select two non-overlapping shortest paths except having a common junction node to cover all the sensor nodes. The two paths are balanced as nearly equal as possible. That is the sensor nodes along each path are equal or differ by just one depending on whether the total number of sensor nodes excluding the junction node is even or odd. In this method, both the path lengths are made equal or very nearly equal while the total length is minimized. This integrated approach is a novel and unique solution to solve the dual moving sink path problem in a wireless sensor network.
Sadashiva V Chakrasali*, , K Indira, Shashank B Sharma, Srinivas N M, Varun S S, , , , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
The process which involves generation of human like voice by a machine is called speech synthe- sis. The developments in the fteld of speech synthesis is vast in international languages, but it is limited in Indian languages like Kannada. This work aims at de- velopment of such a system for Kannada language using Festival and Festvox. It is based on parametric analysis and models of speech features, particular to a language and speaker. The system is memoryless and dynamic, wherein only extracted features are stored but not recorded audio. The training process involves speech data acquisition, pre-processing, labelling using Baum- Welch Iteration, whereas testing process involves text analysis, text segmentation, speech synthesis and qual- ity enhancement using acoustic HMM model develop- ment. The quality of synthesis is 3.52 dB to 5.02 dB as measured by Mel-Cepstral Distortion (MCD) score.
Sadashiva Chakrasali, Umesh Bilembagi, and K. Indira
IEEE
Acoustic phonetics is the study of the physical properties of sounds and provides means to distinguish one sound from another in quality and quantity. A study of acoustic characteristics of Kannada begins with the phonemic analysis of the language. Phonetic analysis of Kannada vowels is presented in this paper. The analysis of speech signal based on formant space provides a method of assessing the influence of each formant on a phoneme across gender and different age groups. PRAAT software is used for the purpose of analysis of speech signals. In this work Kannada vowels speech signals were recorded from different age groups of both male and female. Formant frequencies of corresponding vowels were computed. The analysis is carried out separately for male and female speakers. The preliminary analysis of formants of vowels show significant variations across gender and age groups. In the similar way using the Linear Predictive coding (LPC) analysis is done to get in depth understanding of formants by considering different filter orders. Then order of the LPC filter is typically estimated by using information about the formants obtained using PRAAT tool.
Somaraddi H Gondi, Aditya Kumar, and Sadashiva V Chakrasali
IEEE
The vehicles are increasing day by day, due to which emission of nitrogen oxide gases are consequently increasing which is leading to the various adverse effects to the life of humankind. NOx gases will cause smog, acid rain and formation of fine particles (PM) which are hazardous to health. NOx gases produced from the reaction of nitrogen and oxygen gases during combustion, especially at high temperatures. In areas of high motor vehicle traffic, such as in large cities, the amount of nitrogen oxides emitted into the atmosphere as air pollution can be significant. The exhaust gas gets treatment before releasing into atmosphere before tail pipe with Adblue liquid (32.5% of urea in water). This liquid reacts with exhaust gas and converts nitrogen oxides into nitrogen and water but the problem is to maintain Adblue liquid to desired temperature mainly in European countries (cold regions). BOSCH has developed heater control unit for passenger cars using Freescale microcontroller, which have only two heater elements i.e. there is no flexibility in current design to add & drive extra heater element. Therefore, this project aims at developing a new RCV-PC, with flexibility on number of heater elements (maximum up to 4) along with more Flash Size for additional feature implementation, less power consumption and low cost compared to the existing RCV-PC. For development, IAR Embedded Workbench for Renesas RL78 (version 1.40.5) is used.
Sadashiva V Chakrasali and Sanmati Kuthale
IEEE
This paper gives the hardware implementation of face detection on FPGA using Haar features. The design consisting of integral image generation which is used to compute the Haar features at a faster rate, has been illustrated. The classifiers are built using the AdaBoost algorithm which selects a minimum number of critical Haar features from a very large set. Also, parallel processing classifiers increase the speed of the face detection system by rejecting non-faces quickly. The described detection architecture has been designed using Verilog HDL and implemented on Xilinx vertex-5 FPGA which shows optimization in terms of area and speed.
Sadashiva Chakrasali, Y. N. Sunitha, and Y. N. Sharathkumar
IEEE
It is important to characterize the noise accurately before including its structure in the formulations of algorithms. The distribution suggested in this paper is suitable for the ambient noise having kurtosis between 2.30 and 3. The ambient noise having low kurtosis is mainly dominated by shipping traffic which is having low frequency range.