Lili Xu, A. Apon, Flavio Villanustre, R. Dev, Arjuna Chala
{"title":"Massively Scalable Parallel KMeans on the HPCC Systems Platform","authors":"Lili Xu, A. Apon, Flavio Villanustre, R. Dev, Arjuna Chala","doi":"10.1109/CSITSS47250.2019.9031047","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031047","url":null,"abstract":"Clustering algorithms are an important part of unsupervised machine learning. With Big Data, applying clustering algorithms such as KMeans has become a challenge due to the significantly larger volume of data and the computational complexity of the standard approach, Lloyd's algorithm. This work aims to tackle this challenge by transforming the classic clustering KMeans algorithm to be highly scalable and to be able to operate on Big Data. We leverage the distributed computing environment of the HPCC Systems platform. The presented KMeans algorithm adopts a hybrid parallelism method to achieve a massively scalable parallel KMeans. Our approach can save a significant amount of time of researchers and machine learning practitioners who train hundreds of models on a daily basis. The performance is evaluated with different size datasets and clusters and the results show a significant scalabilty of the scalable parallel KMeans algorithm.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128364554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Prakarsh Anand, Sirsha Chatterjee, I. Agarwal, Shantanu, Aman Anupam, Krupa A. Jain
{"title":"Intelligent Clinical Diagnosis System","authors":"Prakarsh Anand, Sirsha Chatterjee, I. Agarwal, Shantanu, Aman Anupam, Krupa A. Jain","doi":"10.1109/CSITSS47250.2019.9031022","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031022","url":null,"abstract":"Medical Diagnosis is a vast field of knowledge and most part of the world relies on the expertise of doctors to lead them to the correct diagnosis and results. The paper represents a software application hosted on Amazon EC2 using AWS. It is designed to deal with clinical diagnosis of a patient in a uniform and robust manner using the expertise built on real life clinical datasets and rules provided to it. Software approaches an expert system using decision tree algorithm and multi-classification neural net model to conclude to a disease diagnosis. The paper emphasizes on Pyrexia of Unknown Origin aka Fever of Unknown Origin (FUO) as initial symptom use case to demonstrate the application and it can be generalized for other initial symptoms as per the requirement.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129170348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CSITSS Proceedings 2020","authors":"","doi":"10.1109/CSITSS47250.2019.9031039","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031039","url":null,"abstract":"CSITSS Proceedings 2020","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"497 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123412491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Comparative Study of Spark Schedulers' Performance","authors":"Ashmita Raju, Ramya Ramanathan, R. Hemavathy","doi":"10.1109/CSITSS47250.2019.9031028","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031028","url":null,"abstract":"Big data applications have become an integral part of many intelligent systems, enabling better business decision making, by extracting useful information from historical data. This involves a large amount of computational tasks and algorithms. In such scenarios, the time taken by the processing become an important concern, and needs to be optimized. Apache Spark is a high speed big data analytics engine, best known for its fast computation speeds, due to the use of in-memory data structures and its efficient schedulers. Further optimization to enhance the speed of Spark jobs will be valuable. In this paper, the efficiencies of the four standard schedulers of Apache Spark i.e., Standalone Scheduler, Mesos, YARN(Yet Another Resource Negotiator) and the recently introduced Kubernetes Scheduler are compared. The speeds of these schedulers are compared for jobs of different sizes, and the best alternative is identified.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125124853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. R. Harsha, A. Damodaran, S. Ranganath, Vaishnav Raut, Shashanka Holla
{"title":"An approach to enable secure and reliable communication on IoT Devices","authors":"B. R. Harsha, A. Damodaran, S. Ranganath, Vaishnav Raut, Shashanka Holla","doi":"10.1109/CSITSS47250.2019.9031034","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031034","url":null,"abstract":"Today IoT is one of the most widely adopted technologies and is constantly evolving with the explosion of devices in various sectors such as Industrial, Consumer and Enterprises. The use cases and benefits to connect various devices are almost endless. However, one of the key aspects to successful enabling of IoT system is to ensure Security of the connected devices as well the networks involved in connecting these devices. Raspberry Pi is a proven low power platform that can be used to create IoT devices. In this paper, a Zonal Architecture is presented to simplify the IoT eco-system. Further, an attempt is made to provide a quick enablement of security features using Bouncy castle library on Raspberry Pi platform and provide a detailed report on the performance of different crypto algorithms for several use cases/operations such as Key generation, Hash generation, encryption/decryption and Signature/verification.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131571226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Indian Food Image Classification with Transfer Learning","authors":"J. Rajayogi, G. Manjunath, G. Shobha","doi":"10.1109/CSITSS47250.2019.9031051","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031051","url":null,"abstract":"Image classification has become easier with deep learning and availability of larger datasets and computational resources. The Convolutional neural network is the most popular and widely used image classification technique in the recent days. In this paper image classification is performed on Indian food dataset using different transfer learning techniques. The food plays important role in human's life as it provides us different nutrients and hence it is necessary for every individual to keep a watch on their eating habits. Therefore, food classification is a quintessential thing for a healthier life style. Unlike the traditional methods of building a model from the scratch, pre trained models are used in this project which saves the computation time and cost and also has given better results. The Indian food dataset of 20 classes with 500 images in each class is used for training and validating. The models used are IncceptionV3, VGG16, VGG19 and ResNet. After experimentation it was found that Google InceptionV3 outperformed other models with an accuracy of 87.9% and loss rate of 0.5893.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132906751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sourabh S Badhya, A. Prasad, Shetty Rohan, Y. Yashwanth, N. Deepamala, G. Shobha
{"title":"Natural Language to Structured Query Language using Elasticsearch for descriptive columns","authors":"Sourabh S Badhya, A. Prasad, Shetty Rohan, Y. Yashwanth, N. Deepamala, G. Shobha","doi":"10.1109/CSITSS47250.2019.9031030","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031030","url":null,"abstract":"In the present day, data is captured in large amounts in the form of numbers, text, images etc. The data captured is either very simple to extract any useful information or it is very complex such that it takes a lot of time to generate information. In addition to this, data is being stored either in relational databases like MySQL, PostgreSQL or in document-oriented databases like MongoDB, Cassandra. The extraction of data from these databases requires some special knowledge of writing queries that are designed for that particular database. Hence there is a need for a system which extracts information from an input natural language query and convert it into a query which can be understood by the database in a fast and an efficient way. This paper proposes a way to create such a system by making use of Elasticsearch which is used for extracting data from descriptive columns. This paper is mainly focused on creating optimized SQL queries from natural language inputs using Elasticsearch where the extraction of data happens by means of searching through keywords present in input query throughout all the descriptive columns.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133597480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reinforcement Learning Based Channel Selection for Design of Routing Protocol in Cognitive Radio Network","authors":"S. Talekar, Sujatha P. Terdal","doi":"10.1109/CSITSS47250.2019.9031024","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031024","url":null,"abstract":"Cognitive Radio Network (CRN) is a next generation of wireless communication technology for efficient spectrum utilization. A cognitive Radio (CR) is able to recognize the idle spectrum. It solves the problem of spectrum scarcity in CRN. Due to intermittent channel usage by Primary Users (PUs), it is difficult to perform routing task in CRN. We are proposing a solution for optimal channel selection and routing in Cognitive Radio Network. Due to uncertainty in the number of active users, Monte Carlo method is performed for probabilistic outcome. During spectrum access process, Reinforcement Learning (RL) is applied to select best frequency band for routing. From the Simulation results, it is observed that the proposed routing protocol outperform in terms of throughput, packet delivery ratio, delay, dropping ratio & jitter compared to the routing protocol without machine learning assisted routing decision.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129364569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of GNSS Test Tool and Automatic Suit","authors":"Neetin Kumar, Deepak Gupta, Sujata D. Badiger","doi":"10.1109/CSITSS47250.2019.9031011","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031011","url":null,"abstract":"In our day-to-day life we all extensively use location based services to find out where we are located on this planet. This can be done with the help of a GPS receiver. There are several top notch companies vying against one another to become Master in a a field of global positioning. A good GPS receiver must be able to obtain quick location fixes. This project proposes a solution to reduce TTFF (Time to First Fix) and obtain quick position fixes. It also provides a platform to ensure proper functioning of the GNSS solution and to perform system level testing. This project involves the development of two tools- a command line application (RVT) and a graphical use interface (RSDT) to ensure that the GNSS(Global Navigation Satellite System) solution provides quick and accurate position fixes. Both tools are developed using Visual Studio 2012 and is coded in C++ language.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124657512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Survey of Popular Image and Text analysis Techniques","authors":"R. Suresh, N. Keshava","doi":"10.1109/CSITSS47250.2019.9031023","DOIUrl":"https://doi.org/10.1109/CSITSS47250.2019.9031023","url":null,"abstract":"Image processing has made huge progress in recent times and has captured the attention of the international research community in recent times. In this survey paper the winning Convolutional Neural Network (CNN) architectures of the popular ImageNet Large Scale Visual Recognition Competition (ILSVRC) competition along with the innovations they introduced are discussed in detail. CNNs to the likes of the ZFNet, Inception V1, V2, V3 and V4 versions, ResNet versions, Inception ResNet versions, VGG versions are all covered. Also object detection is looked at as a preeminent task and popular models like RCNN, Fast RCNN, Faster RCNN and the YOLO versions along with their award winning architectures are discussed. Text classification is another major practice that is followed before making business decisions. In this survey paper section III explains the text classification techniques. preprocessing techniques such as removing stop words, stemming, lemmatization. Two variants of vectorization method such as vectorization-delta, vectorization-center. paper also explains the hyperparameter tuning for optimization of support vector machine(SVM), Logistic regression(LR), random forest(RF) and Boosted Regression Tree (BRT). Explored fine tuning parameter which enhance the performance of machine learning models.","PeriodicalId":236457,"journal":{"name":"2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS)","volume":"10 9","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133227406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}