Prefacedoi: 10.1088/1757-899X/1074/1/011001pmid: N/A
The Department of CSE, Jawaharlal Nehru Technological University Kakinada (JNTUK), Kakinada, Andhra Pradesh has organized an International Conference on Computer Vision, High Performance Computing, Smart Devices and Networks (CHSN-2020) during 28th-29th December 2020. Principal focus of the conference is to encourage the enthusiasm among researchers, academicians and the scientists of premier research laboratories across the globe to submit and present the basic and applied work in various specialized fields like Communication Engineering, Information Theory, Signal, Image and Speech Processing, Wireless and Mobile Communication, Internet-of-Things and Cyber Security etc.The main objective of the conference is to bring researchers together on to a common platform to acquire the knowledge, discuss and share the emerging trends which help in achieving the best results. Hence, we solemnly invite all to join and get acquainted with recent advances and trends in the fields of Computer Vision, High Performance Computing, Smart Devices and Networks.List of Chief Patron, Patrons, Honorary Chair, General Chair, Program Chair, Convener, Organizing Secretary are available in this Pdf.
Peer review declarationdoi: 10.1088/1757-899X/1074/1/011002pmid: N/A
All papers published in this volume of IOP Conference Series: Materials Science and Engineering have been peer reviewed through processes administered by the Editors. Reviews were conducted by expert referees to the professional and scientific standards expected of a proceedings journal published by IOP Publishing.• Type of peer review: Double blind• Conference submission management system: Easy Chair• Number of submissions received: 144• Number of submissions sent for review: 144• Number of submissions accepted: 55• Acceptance Rate (Number of Submissions Accepted / Number of Submissions Received X 100): 38.19%• Average number of reviews per paper: 2• Total number of reviewers involved: 48• Any additional info on review process: Reviewers from premier organizations such as IITs, NITs, Central Universities and State Universities.• Contact person for queries: Dr.D.Haritha, Convenor, CHSN-2020 ([email protected])PEER REVIEW POLICY Adopted by CHSN-2020Reviewers were asked to consider the following key points related to scientific content, quality and presentation.Technical Criteria• Formal Structure of the review• Language• Scientific merit: Originality and Topicality, Materials and Methods• Clarity of expression; communication of ideas; readability and discussion• ReferencesQuality Criteria• Originality: Novelty of the proposed approaches/methods• Results: Clarity of the illustration• Repetition: Have significant parts of the manuscript already been published?• Length: Is the content of the work of sufficient scientific interest to justify its length?Presentation Criteria• Title: Is it adequate and appropriate for the content of the article?• Abstract: Does it contain the essential information of the article? Is it complete? Is it suitable for inclusion by itself in an abstracting service?• Diagrams, figures, tables and captions: Are they essential and clear?• Text and mathematics: Are they brief but still clear? If you recommend shortening, please suggest what should be omitted.• Conclusion: Does the paper contain a carefully written conclusion, summarizing what has been learned and why it is interesting and useful?The conference coordinators reviewed the submitted papers relevance to the conference topics and checked whether the papers meet the IOP format requirements. The independent reviewers evaluated the submitted papers according to the following criteria as the relevance to meet the study, novelty of work, quality and scientific knowledge, paper structure for IOP format and adequate references etc. Based on the reviewers report, the authors are suggested to revise the submitted manuscript for further reviews.
HYBRID SHUFFLED FROG LEAPING ALGORITHM WITH PROBABILITY DISPERSAL METHOD FOR TUMOR DETECTION IN 3D MRI BRAINTUMOR IMAGESSirisha, P.G.K.; Haritha, D.
doi: 10.1088/1757-899X/1074/1/012001pmid: N/A
In the medical image study, the brain tumor classification using MRIs is difficult due to the brain’s complicated structure and the high variance in tumor tissues’ position. So, the requirement for useful and specific tumor identification methods is developing for medical recognition and regular medical applications. The conventional brain tumor identification performs anatomical knowledge of irregular tissues in the brain, helping the doctor design approach. The research proposes several techniques for brain tumor identification. This work aims to present brain tumor identification methods based on evolutional intelligence and segmentation. Unusual areas in the brain are identified by using the Expectation-Maximization (EM) algorithm. For segmenting the 3D brain MRI data, this work presents a novel hybrid optimization meta-heuristic called the Shuffled Frog Leaping Algorithm (SFLA) with probability dispersal (i.e., SFLA - Stochastic Diffusion Search (SDS)). The efficacy of the suggested 3D SFLA probability dispersal EM in enhancing the performance of the 3D SFLA tabu EM has been proven by empirical outcomes.
A Review on Detection of Land Use and Land Cover from an Optical Remote Sensing Image.Kavitha, A.V.; Srikrishna, A.; Satyanarayana, Ch.
doi: 10.1088/1757-899X/1074/1/012002pmid: N/A
Detection of land use and land cover from an optical remote sensing image is an essential research area from the inception of a remote sensing image. Land use land cover maps have numerous applications in agriculture, environment monitoring, urban planning, etc, along with managing various catastrophic events like floods, tsunamis, forest fires, etc. This paper reviewed major techniques for detection of land use and land cover from an optical remote sensing image. Many techniques based on only spectral information, spatio-contextual information and knowledge based methods have been discussed, finally arguing the importance of the techniques based on spatio-contextual information and Mathematical Morphology.
CBCA: Consignment based communal authentication and encryption scheme for Internet of things using Digital Signature AlgorithmM, Arun.; S, PraveenKumar.; S, Rajakumar.P.; P, Thamizhikkavi.
doi: 10.1088/1757-899X/1074/1/012003pmid: N/A
IoT (Internet of things) gives a dream that communicate the extent of web by incorporating physical articles to distinguish themselves among the participating people. This contemporary observation encourages physical objects to represent them in the advanced world. There are heaps of hypotheses and future conjecture about different physical substances associated with the web, programs, Most of the devices needs security features from the wide range of attacks that are present in the environment. The computationally complex and asset expending methods have a restricted support over these installed physical objects and miniature sensor hubs. In this paper we propose a CBCA (Consignment based communal authentication) conspire for real objects that are moderately associated with the IoT condition. Client server correspondence model is used by present reality substances to communicate with each other. In our proposed framework we use lightweight features of CoAP(Constrained Application Protocol) to screen servers, regardless of whether the assets from the server are empowered on client in a vitality proficient way. Digital signature algorithm (DSA) with a key length of 512 bits is used to set up a protected meeting for the resource assessment. Our plan is assessed for real world situation utilizing NetDuino Plus 2 sheets. Our proposed framework gives an overwhelming obstruction against various attacks and its computationally proficient, get less association overhead simultaneously.
Cancer Classification using Ensemble Feature Selection and Random Forest ClassifierKoul, Nimrita; Manvi, Sunilkumar S
doi: 10.1088/1757-899X/1074/1/012004pmid: N/A
High volumes of genomic data made available by high through put gene expression sequencing technologies like next generation sequencing, microarray gene expression data have made it possible to develop models to computationally analyse this data and infer meaningful insights like presence of a disease, nature of disease, place of localization of the tumour in cancers etc. Since gene expression data is very high dimensional, each gene stands for one dimension, and has very small number of observations, it is imperative to apply feature selection on the data before using it for classification task. In this paper, we have proposed a method for classification of human cancer types by analysis of microarray gene expression data. We have used an ensemble feature selection algorithm for selecting subsets of 5, 10, 20 and 30 genes and applied random forest classifiers to obtain the classification accuracy and other performance parameters for comparison with existing solutions. We have been able to obtain 100% classification accuracy with just 5 genes on colon cancer data set with our algorithm.
Advanced Convolutional Neural Network Classification for Automatic Seizure Epilepsy Detection in EEG SignalMancha, Venkata Ramana; Reddy E, Srinivasa; Ch, Satyanarayana
doi: 10.1088/1757-899X/1074/1/012005pmid: N/A
Epilepsy is one of the irregular electro-physiological disorder appeared in human brain, which is characterized by tonic recurrent seizures, Electroencephalogram (EEG) is a sufficient test measure to maintain records with respects to electrical activity of brain and it is widely used in analysis and detection of electro epileptic seizures. Manual inspection of EEG signal extraction will take more time to process and it puts heavy complex on neurologists affects their performance. It is often difficult in identification of brain subtle but emergency changes in EEG wave forms by visual inspection based on research area for bio- engineers implement different types of methodologies for identification of such type of subtle. But all these algorithms/methodologies don’t perform efficient accuracy in classification of normal, ictal class instances. So that in this paper, we propose a novel system based on machine learning, which is single dimensional pyramidal ensemble convolutional neural network (1D-PECNN). Here ensemble means different parts of the signal are assigned to different models for efficient analysis of data. We also propose mathematical augmented approach for learning features. In 1D-PECNN model, system consist high amount of desirable and learnable parameters, in all cases proposed approach 1D-PECNN gives maximum accuracy (Approximately from 92%-99%) when compare to state-of-the methods.
An Effective Analytics using Machine Learning Integrated Approaches for Diagnosis, Severity Estimation andPrediction of Heart DiseaseSatyanandam, N; Satyanarayana, Ch
doi: 10.1088/1757-899X/1074/1/012006pmid: N/A
Heart Disease is one of the precarious issues in the medial domain whereby the number of cases is huge in the global scenario. The instances of heart transplants increase a lot every year even in the developed countries. Heart disorder identifies a number of heart disease disorders with the cardiac disorders including illnesses of the blood stream, coronary artery disease, cardiovascular rhythms and related cardiac defects. Cardiovascular diseasing commonly implies disorders requiring restricted or blocked blood pathways that can lead to cardiac attack, chest pressure (angina) or a stroke. Some cardiac disorders including key causes of heart disease are often regarded as influencing the cardiac muscle, valves and rhythms. Many cases of cardiac illness can be reversed or managed with a safe lifestyle. Heart Failure (HF) is not a disorder but a complex health illness. The rise in costs in health care, the increasing occurrence, the decreased quality of life, frequent hospitalizations and early mortality have turned HF into a global and Indian crisis and have emphasized the need to diagnose HF and determine its magnitude and efficacy. The principal goal of this research manuscript is to find a machine-based learning approach to diagnoses, intensity predictions and heart disease prediction. In this manuscript, we present the regression as well as ensemble learning based analysis on the benchmark dataset of Cleveland from UCI repository for the estimation of cardiac diseases. A further aspect is that 303 records are scheduled for this review. The knowledge from Cleveland consists of approximately 13 features and we have intended to group it in five groups in this report. The presented outcomes on the assorted algorithmic approaches are quite effective and ensemble-based approach is quite performance aware.
Sentiment Analysis using Neural Network and LSTMSrinivas, Akana Chandra Mouli Venkata; Satyanarayana, Ch.; Divakar, Ch.; Sirisha, Katikireddy Phani
doi: 10.1088/1757-899X/1074/1/012007pmid: N/A
People put their opinions or views on various events happening in the society or world. Twitter is one of the best social networking sites where a huge amount of data generates on the daily basis. These data can be used to classify their tweets based on various sentiments attached to them. Numerous technologies are applied to analyse the sentiments of users. Sentiment analysis needs a very efficient method to manage long arrangement data and their drawn-out dependencies. In this paper, we have applied a deep learning technique to perform Twitter sentiment analysis. Simple Neural Network, Long Short-Term Memory (LSTM), and Convolutional Neural Network (CNN) methods are applied for the sentiment analysis and their performances are evaluated. The LSTM is the best among all proposed techniques with the highest accuracy of 87%. We have collected a Twitter dataset from Kaggle to perform our experiment. The future improvement of the proposed research should include REST APIs and web crawling-based solutions to get live tweets to perform real-time analytics. We have analysed 1.6 million tweets in our research work.
Classification of Breast Cancer using Histology images: Handcrafted and Pre-Trained Features Based ApproachKundale, Jyoti; Dhage, Sudhir
doi: 10.1088/1757-899X/1074/1/012008pmid: N/A
Breast cancer has become a critical disease in women. The number of patients with breast cancer is quite high in India. It is of paramount importance to detect the disease in advance. Digital histopathology is one of the most advanced techniques for detection using machine learning. Artificial intelligence is going to be like a sunrise in the field of medicine. Deep neural networks have been successfully applied to the problem under consideration in the past. As, we know the feature extraction is one of the essential and crucial steps in case of classification. In this paper, we compare two approaches, first is feature extraction using traditional Handcrafted based and other is Transfer Learning based model (Pre-trained) for multiclass classification of Breast Cancer using Convolutional Neural Network (CNN) as a classifier. The models are trained using handcrafted features like Seeped Up Robust Features (SURF) and Dense Scale Invariant Feature Transform (DSIFT) techniques, later these extracted features are encoded by Locality Constrained Linear Coding method (LLC). In pre-trained model we have used VGG16, VGG19, ResNet50, GoogLeNet for feature extraction. The maximum accuracy for “SURF+CNN” is 92.88% for Handcrafted feature and in case of Pre-trained “GoogLeNet+ CNN” model gives 94%, both for 400X magnification factor.