2022 IEEE International Conference on Data Science and Information System (ICDSIS)最新文献

{"title":"SDNet: Integrated Unsupervised Learning with DLCNN for Shrimp Disease Detection and Classification","authors":"Gadhiraju Tej Varma, A. S. Krishna","doi":"10.1109/ICDSIS55133.2022.9915812","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915812","url":null,"abstract":"Shrimp is a main international food item with a significant economic value, as well as one of the most vital animal protein sources. However, the production of shrimps is directly affected by the different types of shrimp diseases. Thus, it is necessary to identify the shrimp diseases in primary stage to avoid the losses. Therefore, this article is implemented the shrimp disease network (SDNet) using deep learning architectures. Initially, K-means clustering (KMC) is applied on the test images to localize the region of disease or virus location. Then, machine learning based iterative random forest algorithm (IRFA) is utilized to extract the features from segmented images and it also develops the optimal features. Finally, deep learning convolution neural network (DLCNN) is used to perform the multi class classification of shrimp diseases by training the optimal features. The proposed SDNet method resulted in superior performance as compared to state of art approaches with respect to both subjective and objective metrics in terms of classification metrics such as sensitivity, specificity, accuracy, precision, recall, and F1-socre.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114441463","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":"Dormitory Regulatory System Using Artificial Intelligence and IoT","authors":"B. Kumar, Janhavi Soni, N. Gayathri","doi":"10.1109/ICDSIS55133.2022.9915946","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915946","url":null,"abstract":"There’s an unprecedented increase in the no. of educational institutions found throughout the planet, particularly during the last decade. the expansion has taken education to people’s doorstep. As a result, literacy levels for the entire human population have risen drastically within some centuries. As the reports suggest in 1820 when only 12% of the population could read and write, today the stats are completely changed or reversed their course: The reports suggest, from 1820 to 2016 the literacy level has risen by 72%. If the rate of increment is considered, it’s around 4% increment every 5 years – from 42% in 1960 to 86% in 2015. Increasing education has helped within the formation of well-educated citizens who can easily accept rules and make rules for a developed society making it more civilized and making a meaningful contribution thereto. However, the majority of newly established educational institutions still use the old traditional methods to manage their belonging/properties, particularly hostel facilities. In recent times, after the internet boom, tremendous development in smart devices and services is noticeable. The internet is moreover becoming less expensive nowadays as well as the increasing internet speed has made it reach to newer horizons. It can be easily stated that the internet age has become a part of today’s civilization. This transition of human beings from citizens to netizens has expanded the interest for an ever-increasing number of gadgets to be associated on the internet. Smart homes and other IoT-based systems are getting famous now a days. Many problems nowadays are often being solved using the Internet as a medium. We’ve lived inside the hostels for five years as of now and with the help of the survey and our observation, we have come up with a plethora of important issues which are common for all. Also, as a part of tech study, we’ve conceptualized a robust & smart conceptual framework, which assures to solve these problems using cutting-edge technologies especially, AI (Artificial Intelligence) and IOT (Internet of Things), with proper shreds of evidence and proofs we’ve specifically discussed the problems faced in hostels and proposed solutions for those problems in an oriented and detailed manner from both technological and social perspective. The created structure assures overcoming the drawbacks of normal hostel management methods; with access control systems, more user-friendly UI, graphical-user-oriented designs, robust, efficient, and safe access and usage especially for students.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116431743","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":"QoE Aware Video Adaptation For Video Streaming in 5G Networks","authors":"Aditi Hegde, Mookambeswaran Vijayalakshmi, G. Jayalaxmi","doi":"10.1109/ICDSIS55133.2022.9915912","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915912","url":null,"abstract":"The popularity of video streaming has skyrocketed as an outcome of the increased demand for use of wireless devices such as smartphones and tablets etc. As a result, perplexing video applications like remote surgery, mobile broadcasting, real-time demand, delivery of Ultra High Quality, and Augmented Reality are predicted to control the traffic of mobile networks in the future generation (5G). This is because video applications currently account for more than 70% of IP-based internet traffic, and by 2021, they are expected to account for more than 80%. In addition, mobile device traffic is expected to increase by 10%. As the demand for mobile video consumption grows, 5G networks will require larger bandwidths, improved dependability, and reduced end-to-end delay. Despite considerable improvements in QoS, network operators will continue to face significant issues as 5G video traffic grows in volume. As a result, the focus of network quality has shifted in recent days from network provider QoS to Quality of Experience (QoE), culminating in the QoE predictive model. The assumption for 5G networks is that they shall be capable of delivering Ultra Hd video streaming and the QoE-aware techniques shall be able to match the user’s anticipated quality standard. The purpose of this research is to study, give a broad overview of the many QoE aware adaptive video streaming systems available today, as well as their current trends, and implement an adaptive video streaming system that could enhance the QoE and user perception using a SDN platform.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126082759","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":"VDS: A Variant of Δ-stepping Algorithm for Parallel SSSP Problem","authors":"Praveen Kumar, A. Singh","doi":"10.1109/ICDSIS55133.2022.9915894","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915894","url":null,"abstract":"Δ-stepping is a famous parallel algorithm for the single-source shortest path problem. It requires a tuning parameter (delta) to achieve a good trade-off between parallelism and work efficiency. The performance of Δ-stepping changes drastically with the changing value of delta. A poor choice of delta leads to an inefficient Δ-stepping algorithm. For large graphs, finding the best-performing value of delta is difficult. This paper proposes a variant of the Δ-stepping algorithm (VDS). We have evaluated the proposed algorithm on graph500 data sets. Our results show that the proposed algorithm is equally work-efficient and scalable compared to Δ-stepping, and its performance remains almost stable with the changing value of delta. Against the best performing value of delta, VDS’s performance on different deltas varies up to 136%, whereas Δ-stepping’s performance varies up to 430%. For the best performing value of delta, the proposed algorithm is competitive or slightly efficient compared to the Δ-stepping. And, for the most inefficient delta, the proposed algorithm is 2.8–3.6x faster than the Δ-stepping.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125112851","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 Retrospective Study on Obesity to Evaluate Omnipotence of Physical Condition Feature Set","authors":"Diganta Sengupta, Subhash Mondal, Susanta Banerjee, H. Navin","doi":"10.1109/ICDSIS55133.2022.9915821","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915821","url":null,"abstract":"One of the growing medical concerns globally is obesity. The age old popular notion for the disease lies in physical conditions (PC), and eating habits (EH), leading to much observed debate for the root cause of obesity. This study establishes the omnipotence of PC over EH as a leading cause of obesity. The dataset used for the study comprised of 16 features which were divided into two feature subsets (FSS); one FSS containing 9 PC features, and the other FSS containing features related to EH. Initially obesity was classified using the complete feature dataset, followed by classification using the PC and EH FSSs respectively. Eight Machine Learning (ML) algorithms were used for the study. Regular performance metrics were used to evaluate the results. It was observed that the PC features unanimously contributed to obesity in contrast to EH features. Moreover, boosting was done using six algorithms, and results reflected that all the boosting algorithms enhanced the results. Of all the boosting algorithms, Hist-Gradient Boost generated the best results. The prime focus of the study is to analyze the major features for obesity using ML algorithms including boosting. This study computationally concludes that physical conditions have a greater impact on obesity with respect to eating habit conditions.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126473100","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":"IoT and Solar Energy Based Multipurpose Agricultural Robot for Smart Farming","authors":"Ashok G Meti, Kirangouda S Biradar, G. H. Manoj, Pramod N Rayangoudra, Vishal Kumar, B. T. V. Murthy","doi":"10.1109/ICDSIS55133.2022.9915810","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915810","url":null,"abstract":"In India, nearly 70% of people depend on agriculture. In the agricultural field, various operations such as seed sowing, grass cutting, pesticide spraying, ploughing are carried out. Automation of agricultural operations is a current demand to increase productivity through the use of tools and technology. At the moment seed sowing, pesticide spraying, and grass cutting are all difficult tasks. The equipment needed for the aforementioned actions is both expensive and inconvenient to use. As a result, India’s agricultural system should be advanced through the development of a system that reduces reliance on human labour and time. The proposed agricultural robot is a user-friendly, Internet of Things (IoT)-based system that can be used in any type of soil. Users can use a web page to monitor the crop’s condition as well as perform some specific operations. The objective of this project is to design, develop, and build a robot that can sow seeds, cut grass, spray pesticides, pluck fruit, and detect soil nutrition levels and irrigation. Solar energy is used to power the entire system. By connecting through wireless modules. the designed model can be controlled via a web page. The web page is used to control the robot’s required mechanism and movement. This improves the efficiency of seed sowing, pesticide spraying, grass cutting, fruit plucking, soil nutrition level detection, and irrigation, as well as reducing the need for manual planting.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129065033","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":"Rank Based Adaptive Algorithm for Route Generation in Multi Source Energy Harvesting Wireless Sensor Network","authors":"Somnath Sinha, V. Lakshmipriya","doi":"10.1109/ICDSIS55133.2022.9915913","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915913","url":null,"abstract":"WSNs are suitable for a variety of technical applications, including monitoring, control, and surveillance of electrical plants, to name a few. Sensors will connect, conspire, contribution, and onward data without the need for a central controller in a multi-hop method. The route optimization technique is used to address the long networking problem and give the quickest path between communication nodes in order to obtain essential data. Short distances are generated as a result of the optimization, which decreases the requirement for route floods. As a result, the shortest path requirement is undesirable for WSN, as it may result in many nodes losing power and high signaling and processing expenses owing to network rebuilding. The rank is completely based on capacity of each node and energy flow route of each node. The architecture of a multi-hop wireless sensor network is viewed as a distributed computer infrastructure in this study, and a route setting method based on it is offered.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129134777","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":"Kannada Handwritten Character Recognition and Classification Through OCR Using Hybrid Machine Learning Techniques","authors":"Deekshitha Gowda, V. Kanchana","doi":"10.1109/ICDSIS55133.2022.9915906","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915906","url":null,"abstract":"In many workplaces in Karnataka the documents are in regional language and it is handwritten. Consequently, there is a requirement for a PC based framework to beat the gap among machines and people. There is a lot of challenges faced when converting these handwritten documents to computer editable format. One of the challenges faced is in classifying confounding characters which are many in Kannada which may recognize wrongly due to the way the characters are written. The scanned handwritten document was pre-processed then segmented into line, word and character ouring Edge based segmentation. The feature extracted mostly based on the curviness of the characters using Convolutional Neural Networks. The segmented and feature extracted characters are further classified using Support Vector Machines, K Nearest Neighbors and Random Forest algorithms. The accuracy rates obtained based on 2000 handwritten documents where Random Forest-95%, Support Vector Machine - 96%, K Nearest Neighbors-92%.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132284414","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":"Mango Leaf Disease Detection Using Ultrasonic Sensor","authors":"G. Gurumita Naidu, G. Ramesh","doi":"10.1109/ICDSIS55133.2022.9916015","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9916015","url":null,"abstract":"Mango Plant Diseases wreak havoc on fruit production and cause growers to lose money. This dilemma prompted the development of a new technology for detecting and diagnosing mango plant illnesses. In agriculture, keeping an eye on the health and illness of crops is critical for the booming output of crops in the cultivation industry. A multilayer convolutional neural network (MCNN) is constructed for the classification of Mango leaves disease, which is a classic and cost-effective solution to the above problem. Canonical correlation analysis (CCA)-based fusion is used to extract and fuse the features. The use of an ultrasonic sensor to detect bacterial canker and phomba blight disease is proposed in this research. The ultrasonic sensor that produces a pulse reflected signal from mango leaves uses the echo pin. Microsoft Excel is used to record the pulse data. A threshold frequency for disease detection is calculated using these values. The proposed approach has a 90% accuracy rate.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116623535","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":"Optimization of Traffic Congestion in Smart Cities Using Residual Convolutional Neural Network","authors":"Karthick Rajan, K. Sampath Kumar","doi":"10.1109/ICDSIS55133.2022.9915860","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915860","url":null,"abstract":"With increasing density of vehicle in smart cities, the traffic gets worsen day by day, therefore it is necessary to optimize the traffic signals for smooth flow of traffic. In this paper, we develop a real-time solution on traffic signal control for the reduction of traffic congestion. The study develops a ResNet approach using Internet of Things (IoT) that controls the traffic congestion in smaller congestion area. The real-time analysis generates the traffic simulation environment in a simulator using the real time data i.e., finding number of vehicles getting congested from the images captured via IoT image acquisition module. The simulation generation using ResNet generates the control signal to real-time environment to quickly clear the congestion in that area. The experimental results with the support of simulator shows that the proposed ResNet is efficient to control the traffic congestion in smart cities.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116846830","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}