chetana prakash
@bietdvg.edu
Professor, CSE Department
Bapuji Institute of Engineering & Technology
EDUCATION
B.E. (Computer Science & Engineering)
M.S (BITS Pilani)
Ph.D (IIIT Hyderabad)
RESEARCH INTERESTS
Speech Signal, Fuzzy Technique, Web Data Mining, Data Mining, Image Processing, Computer Networks, IoT, ML, DL
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Shashirekha Hanumanthappa and Chetana Prakash
Institute of Advanced Engineering and Science
Recently, significant growth in using online-based learning stream (i.e., elearning systems) have been seen due to pandemic such as COVID-19. Forecasting student performance has become a major task as an institution is focusing on improving the quality of education and students' performance. Data mining (DM) employing machine learning (ML) techniques have been employed in the e-learning platform for analyzing student session streams and predicting academic performance with good effects. A recent, study shows ML-based methodologies exhibit when data is imbalanced. In addressing ensemble learning by combining multiple ML algorithms for choosing the best model according to data. However, the existing ensemblebased model does not incorporate feature importance into the student performance prediction model. Thus, exhibits poor performance, especially for multi-label classification. In addressing this, this paper presents an improved ensemble learning mechanism by modifying the XGBoost algorithm, namely modified XGBoost (MXGB). The MXGB incorporates an effective cross-validation scheme that learns correlation among features more efficiently. The experiment outcome shows the proposed MXGBabased student performance prediction model achieves much better prediction accuracy contrary to the state-of-art ensemble-based student performance prediction model.
Manu Y. M., Chetana Prakash, S. Santhosh, Shaik Shafi, and K. Shruthi
Springer International Publishing
Azizkhan F Pathan and Chetana Prakash
Elsevier BV
Azizkhan F Pathan and Chetana Prakash
Elsevier BV
Aditya Sarin, Deveshi Thanawala, Saurav Verma, and Chetana Prakash
IEEE
The diversity of the internet can be fascinating with our everyday devices getting automated. However, such technology of connecting everything to the internet can actually be daunting. This data could easily be attacked by malicious users and hence hangs the usage of such technologies in a precarious condition. To prevent such attacks, we have used AES algorithm to secure data bits and also designed a two-stage encryption and decryption algorithm. This algorithm was successfully tested by transmitting data bits through a channel between two wireless sensor nodes for five test cases. The model is tested in such a way that it can be universally applicable to all IoT networks.
Kavitha G. and Chetana Prakash
IEEE
Medical imaging has become a very important non-invasive diagnosis tool for various diseases. During image acquisition, they get acquainted with noise because of modality and/or because of body conditions such as patient’s position or body fat. Most common noise in ultrasound is speckle, CT and MRI are motion and electrical noises. And other additional noise can also be present such as salt and pepper, Gaussian, Poisson. These noises degrade image quality. The only expert radiologist can make an appropriate diagnosis. Hence it is very important to perform de-noising. Many techniques are present for de-noising which are basically dependent on noise type. Here an attempt is made to remove speckle noise using multilevel hybrid filters. Ultrasound images of the common carotid artery are degraded by speckle noise and then de-noised using the median, wiener, NLM, Homorphic, Bilateral and hybrid filter are applied. Performance of these algorithms is measured using PSNR, MSE, SSIM and ROC curve is drawn. Results show that the Median filter With Bilateral filter has better performance.
Saurav Verma, Rahul Gala, S. Madhavan, Sanchit Burkule, Swapnil Chauhan, and Chetana Prakash
IEEE
Agriculture is one major and important sector for the growth of economy for any country. As per the current scenarios, various problems are present in agriculture like techniques which are used currently are not efficient, requirement of larger manpower and appropriate time for irrigation and spreading of fertilizer to yield. Internet of Things (IoT) is latest technology for smart farming to enhance efficiency, productivity and resolve various issues present in agriculture. IoT network consist of various sensor node which is used to monitor soil acidity level, temperature, and other variables. In this paper, the steps involved for agriculture are discussed and mainly focus on use of IoT in agriculture i.e. in proposed architecture which leads to growth of agriculture exponentially and the economy.
Shivangi Vashi, Jyotsnamayee Ram, Janit Modi, Saurav Verma, and Chetana Prakash
IEEE
The Internet of Things is an emerging technology across the world, which helps to connect sensors, vehicles, hospitals, industries and consumers through internet connectivity. This type of architecture leads to Smart Cities, Smart home, Smart agriculture and Smart World. Architecture of IoT is very complex because of the large number of devices, link layer technology and services that are involved in this system. However, security in IoT is the most important parameter. In this paper, we give an overview of the architecture of IoT with the help of Smart World. In the second phase of this paper, we discuss the security challenges in IoT followed by the security measures in IoT. Finally, these challenges, which are discussed in the paper, could be research direction for future work in security for IoT.
H. Shashi Rekha, Chetana Prakash, and G. Kavitha
IEEE
Chetana Prakash, Dhananjaya N. Gowda, and Suryakanth V. Gangashetty
Springer Science and Business Media LLC
In this paper, we propose an approach for the analysis and detection of acoustic events in speech signals using the Bessel series expansion. The acoustic events analyzed are the voice onset time (VOT) and the glottal closure instants (GCIs). The hypothesis is that the Bessel functions with their damped sinusoid-like basis functions are better suited for representing the speech signals than the sinusoidal basis functions used in the conventional Fourier representation. The speech signal is band-pass filtered by choosing the appropriate range of Bessel coefficients to obtain a narrow-band signal, which is decomposed further into amplitude modulated (AM) and frequency modulated (FM) components. The discrete energy separation algorithm (DESA) is used to compute the amplitude envelope (AE) of the narrow-band AM-FM signal. Events such as the consonant and vowel beginnings in an unvoiced stop consonant vowel (SCV) and the GCIs are derived by processing the AE of the signal. The proposed approach for the detection of the VOT using the Bessel expansion is shown to perform better than the conventional Fourier representation. The performance of the proposed GCI detection method using the Bessel series expansion is compared against some of the existing methods for various noise environments and signal-to-noise ratios.
Chetana Prakash and Suryakanth V. Gangashetty
IEEE
In this paper we propose Fourier-Bessel cepstral coefficients (FBCC) features for robust speech recognition. The Fourier-Bessel representation of the speech signal is obtained using Bessel function as a basis set. The FBCC are extracted from zeroth order Bessel coefficients taking into account of the perceptual characteristics of human auditory system. Recognition accuracy is measured using the CMU SPHINX-III speech recognition system using the DARPA Resource Management (RM) speech corpus for training and testing. We evaluate the FBCC in a common experimental set up and compare their performance against traditional technique such as the Mel-frequency cepstral coefficients (MFCC) for various noise conditions. The recognition accuracy is found to be better using FBCC features in comparison with MFCC features under noisy condition data.
C. Prakash, Balamanohar Paluri, S. Nalin Pradeep, and Hitesh Shah
Springer Berlin Heidelberg
The paper proposes a parametric approach for color based tracking. The method fragments a multimodal color object into multiple homogeneous, unimodal, fragments. The fragmentation process consists of multi level thresholding of the object color space followed by an assembling. Each homogeneous region is then modelled using a single parametric distribution and the tracking is achieved by fusing the results of the multiple parametric distributions. The advantage of the method lies in tracking complex objects with partial occlusions and various deformations like non-rigid, orientation and scale changes. We evaluate the performance of the proposed approach on standard and challenging real world datasets.
Balamanohar Paluri, S. Nalin Pradeep, Hitesh Shah, and C. Prakash
Springer Berlin Heidelberg
The paper proposes a novel approach for classification of sports images based on the geometric information encoded in the image of a sport's field. The proposed approach uses invariant nature of a crossratio under projective transformation to develop a robust classifier. For a given image, cross-ratios are computed for the points obtained from the intersection of lines detected using Hough transform. These cross-ratios are represented by a histogram which forms a feature vector for the image. An SVM classifier trained on aprior model histograms of crossratios for sports fields is used to decide the most likely sport's field in the image. Experimental validation shows robust classification using the proposed approach for images of Tennis, Football, Badminton, Basketball taken from dissimilar view points.
Mayur D Jain, S Nalin Pradeep, C Prakash, and Balasubramanian Raman
IEEE
Fingerprint matching algorithm is a key step in fingerprint recognition system. Though there are many existing matching algorithms, there has been inability to match fingerprints in linear time. In this paper we present a novel biometric approach to match fingerprints that run in linear time. We match the minutiae in the fingerprint by constructing a nearest neighbor vector (NNV) considering its k-nearest neighbors. The consolidation of these matched minutiae points is done by incorporating them in binary tree that propagates simultaneously in both fingerprints. This helps our algorithm to run in O(n) time in contrast to many existing algorithms when reference core point is available. We analyze the resulting improvement in computational complexity and present experimental evaluation over FVC2002 database.
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
Publications
1. A Comparative study of Median, ANW, NLM and proposed Hybrid Filtering Technique using Median and ANW Filter for Medical Images, (IPASJ International
Journal of Computer Science (IIJCS))
2. Implementation of New Approach to Secure IoT Networks with Encryption and Decryption Techniques, IEEE 49239
3. A Framework for Hierarchical Big Image Data , IJIRSET
4. Advancement in infotainment system in automotive sector with vehicular cloud network and current state of art (IJECE)
5. An Internet of things (IoT) architecture for Smart Agriculture ( 978-1-5386-5257-2/18/$31.00 ©2018 IEEE)
6. Big Data Mining from Social Networking Services using Spectral Clustering Algorithm (IJIRCCE)
7. Privacy Preserving Mechanism for Mobile Healthcare Emergency (IJARSET)
8. Internet of Things (IoT) A vision, Architectural Elements and Security Issues" , IEEE International Conference on I-SMAC
( IoT in Social, Mobile, Analytics & Cloud) (I-SMAC-2017)
9. Survey on Infotainment System for Vehicular Adhoc Networks" 3rd National Conference on Recent Trends in Electronics & Communication – 2017
(NCRTEC-2017)
10. Comparative study of Median, ANW, NLM and proposed Hybrid Filtering Technique using , Median and ANW Filter for Medical Images", IPASJ, International Journal of Computer Science
11. Privacy Preserving Mechanism for Mobile Healthcare Emergency" , International Journal of Advanced Research in Science , Engineering Technology
12.An Internet of things (IoT) architecture for smart Agricu