Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00113
Jyoti Madake, Hrishikesh Salway, Chaitanya Sardey, S. Bhatlawande, S. Shilaskar
Authorized traffic control has the highest priority in the case of high-traffic situations. In such situations, it is very important to have a smooth flow of traffic which is the job of ATC. ATCs make use of hand gestures for controlling traffic. It is very important for drivers to understand these gestures in order to follow their instructions otherwise it might lead to accidents, traffic jams, etc. However, most drivers nowadays are unaware of these signals and in the age of autonomous vehicles, it has become of utmost importance that the vehicles have a high level of understanding of these gestures to better assist the drivers. In this study, various approaches to this problem are tested. A detailed comparison of the proposed methods with previous works on this topic is done and the room for further improvement of the performance is discussed.
{"title":"Vision-Based Traffic Hand Sign Recognition for Driver Assistance","authors":"Jyoti Madake, Hrishikesh Salway, Chaitanya Sardey, S. Bhatlawande, S. Shilaskar","doi":"10.1109/OCIT56763.2022.00113","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00113","url":null,"abstract":"Authorized traffic control has the highest priority in the case of high-traffic situations. In such situations, it is very important to have a smooth flow of traffic which is the job of ATC. ATCs make use of hand gestures for controlling traffic. It is very important for drivers to understand these gestures in order to follow their instructions otherwise it might lead to accidents, traffic jams, etc. However, most drivers nowadays are unaware of these signals and in the age of autonomous vehicles, it has become of utmost importance that the vehicles have a high level of understanding of these gestures to better assist the drivers. In this study, various approaches to this problem are tested. A detailed comparison of the proposed methods with previous works on this topic is done and the room for further improvement of the performance is discussed.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132675008","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00016
Sibo Prasad Patro, Neelamadhab Padhy, Rahul Deo Sah
Accurate analysis and prediction for real-time heart disease are highly significant. Many medical diagnosis difficulties have a class imbalance because the number of patients with a certain disease is significantly smaller than the number of healthy people in the population. The purpose of this work is to provide a way for using a feature selection technique to determine the most relevant features of heart disease characteristics. The experiment for this study is performed over the Framingham Heart Study dataset using OneR, GA, and CORR feature selection methods. With the help of the Chi-squared test, six highly correlated features are selected for disease prediction. The experimental results show that CORR has the lowest mean rank of 8.16% and the accuracy for the proposed model using SVM outperformed with an accuracy of 67% on oversampling data.
{"title":"Classification model for heart disease prediction using correlation and feature selection techniques","authors":"Sibo Prasad Patro, Neelamadhab Padhy, Rahul Deo Sah","doi":"10.1109/OCIT56763.2022.00016","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00016","url":null,"abstract":"Accurate analysis and prediction for real-time heart disease are highly significant. Many medical diagnosis difficulties have a class imbalance because the number of patients with a certain disease is significantly smaller than the number of healthy people in the population. The purpose of this work is to provide a way for using a feature selection technique to determine the most relevant features of heart disease characteristics. The experiment for this study is performed over the Framingham Heart Study dataset using OneR, GA, and CORR feature selection methods. With the help of the Chi-squared test, six highly correlated features are selected for disease prediction. The experimental results show that CORR has the lowest mean rank of 8.16% and the accuracy for the proposed model using SVM outperformed with an accuracy of 67% on oversampling data.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122161237","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00116
Abburu Kalyan Srinivas, Deepa Vikram, Suraj Sharma, R. K. Lenka
Every kind of software system needs an update one or the other day. One such update could be a routine software patch, security patch or a total periodical system update. As the field of Internet Of Medical Things (IOMT) is emerging drastically day by day with huge network of devices connected over internet, comes the challenge of software update Over The Air (OTA) to all the connected target nodes of a wireless sensor network without interrupting the services for longer time. Considering crucial applications of Internet Of Things (IOT) like Health Care, Smart Grids or any other sensitive environments where response time of the system is very less, while applying a software patch or security patch to the concerned device has to be done as quickly as possible, which keeps the services uninterrupted, which requires smart patching. Ideally zero downtime is desired in such critical applications, which is still a long way to go. This article presents a way of deploying the software patches to the IOT systems with multiple features which helps to reduce the downtime of the system over Secure Shell (SSH) Communication Protocol.
每一种软件系统总有一天需要更新。一个这样的更新可以是一个常规的软件补丁，安全补丁或一个完整的定期系统更新。随着医疗物联网(IOMT)领域日益蓬勃发展，庞大的设备网络通过互联网连接，对无线传感器网络中所有连接的目标节点进行OTA (over the Air)软件更新而不长时间中断服务的挑战随之而来。考虑到物联网(IOT)的关键应用，如医疗保健，智能电网或任何其他系统响应时间非常短的敏感环境，同时必须尽快对相关设备应用软件补丁或安全补丁，以保持服务不间断，这需要智能补丁。理想情况下，在这样的关键应用程序中需要零停机时间，这仍然有很长的路要走。本文介绍了一种将软件补丁部署到具有多种功能的物联网系统的方法，这有助于通过SSH通信协议减少系统的停机时间。
{"title":"Deployment Automation for Blockchain Enabled IoMT","authors":"Abburu Kalyan Srinivas, Deepa Vikram, Suraj Sharma, R. K. Lenka","doi":"10.1109/OCIT56763.2022.00116","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00116","url":null,"abstract":"Every kind of software system needs an update one or the other day. One such update could be a routine software patch, security patch or a total periodical system update. As the field of Internet Of Medical Things (IOMT) is emerging drastically day by day with huge network of devices connected over internet, comes the challenge of software update Over The Air (OTA) to all the connected target nodes of a wireless sensor network without interrupting the services for longer time. Considering crucial applications of Internet Of Things (IOT) like Health Care, Smart Grids or any other sensitive environments where response time of the system is very less, while applying a software patch or security patch to the concerned device has to be done as quickly as possible, which keeps the services uninterrupted, which requires smart patching. Ideally zero downtime is desired in such critical applications, which is still a long way to go. This article presents a way of deploying the software patches to the IOT systems with multiple features which helps to reduce the downtime of the system over Secure Shell (SSH) Communication Protocol.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129741819","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00074
Sanjib Kumar Mishra, Sasmita Mishra, R. Priyadarshini
By the recent development of digitization in the businesses, the number of financial transactions increases for each business processes. It's very difficult to keep an eye on each and every transaction made in different departments in an organization like, accounts payable and receivable. Business never wants to pay more or less to their vendors, it wants to maintain a proper accounts of each and every transaction. In large-scale organizations having thousands of vendor invoice posted daily, it's very difficult to keep a track of each and every transaction. With the inception of ERPs (Enterprise Resource Planning), the business processes are tightly integrated and all the financial transaction are accounted as per the accounting principles. ERPs also help in automating the repetitive business processes. This helps in avoiding human error. This study will present how SAP (ERP software) automation helps in applying and removing the payment block for the vendor invoices which are accounted in a three-way match process, where the materials procured by Purchase order (PO), received by Goods receipt (GR) and the invoices posted via Invoice receipt (IR). This paper also tries to find the lacuna present in the existing payment block (application or removal of payment block) solution provided by SAP.
{"title":"An Improvised Way To Automate Logistic Payment Block Process: A Case Study on R-Payment Block","authors":"Sanjib Kumar Mishra, Sasmita Mishra, R. Priyadarshini","doi":"10.1109/OCIT56763.2022.00074","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00074","url":null,"abstract":"By the recent development of digitization in the businesses, the number of financial transactions increases for each business processes. It's very difficult to keep an eye on each and every transaction made in different departments in an organization like, accounts payable and receivable. Business never wants to pay more or less to their vendors, it wants to maintain a proper accounts of each and every transaction. In large-scale organizations having thousands of vendor invoice posted daily, it's very difficult to keep a track of each and every transaction. With the inception of ERPs (Enterprise Resource Planning), the business processes are tightly integrated and all the financial transaction are accounted as per the accounting principles. ERPs also help in automating the repetitive business processes. This helps in avoiding human error. This study will present how SAP (ERP software) automation helps in applying and removing the payment block for the vendor invoices which are accounted in a three-way match process, where the materials procured by Purchase order (PO), received by Goods receipt (GR) and the invoices posted via Invoice receipt (IR). This paper also tries to find the lacuna present in the existing payment block (application or removal of payment block) solution provided by SAP.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121205196","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00098
Arti Gupta, V. Chaurasiya
Recent advancement applications have more computation-intensive, and data-intensive tasks are delay-sensitive. In IoT-Cloud-based healthcare architecture, data is aggregated using edge devices and sent to the cloud for processing and analysis. Furthermore, we need to transfer the data information out of the network for each event. Hence it is a delay-sensitive process that is not useful for instant processing and is unacceptable for healthcare applications. To overcome this problem, we have focused on a fog layer between smart devices and the cloud layer. Additionally, we use the Bayesian Belief Network's classification technique in the fog layer for task offloading. This paper focuses on reducing the response time using the BBN classifier after task offloading and increasing the system's stability using fog computing. In the simulation result, we compare the cloud-based and fog-based models in which the fog-based model is dominant over the cloud- based. This fog-based approach is based on real-time data processing at the local network. Hence it is practically possible and acceptable to get an instant result.
{"title":"Efficient Task-Offloading in IoT-Fog Based Health Monitoring System","authors":"Arti Gupta, V. Chaurasiya","doi":"10.1109/OCIT56763.2022.00098","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00098","url":null,"abstract":"Recent advancement applications have more computation-intensive, and data-intensive tasks are delay-sensitive. In IoT-Cloud-based healthcare architecture, data is aggregated using edge devices and sent to the cloud for processing and analysis. Furthermore, we need to transfer the data information out of the network for each event. Hence it is a delay-sensitive process that is not useful for instant processing and is unacceptable for healthcare applications. To overcome this problem, we have focused on a fog layer between smart devices and the cloud layer. Additionally, we use the Bayesian Belief Network's classification technique in the fog layer for task offloading. This paper focuses on reducing the response time using the BBN classifier after task offloading and increasing the system's stability using fog computing. In the simulation result, we compare the cloud-based and fog-based models in which the fog-based model is dominant over the cloud- based. This fog-based approach is based on real-time data processing at the local network. Hence it is practically possible and acceptable to get an instant result.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123241638","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00056
Priyanka Prabhakar, Deepa Gupta, P. Pati
This paper reports the effectiveness of a method using T5 to generate an abstractive summarisation of Indian legal judgments. When a legally qualified person manually performs summarisation, the created summary always depends on the person's expertise in performing the task. So an automatic legal summarization is used to perform this task more accurately. The system generates an abstractive summary of 350 judgments taken from the Honorable Supreme Court of India. The dataset has been created manually with a lawyer's help, and the result evaluation is performed using the ROUGE score, which gave a precision of 0.54955 for Rouge-L.
{"title":"Abstractive Summarization of Indian Legal Judgments","authors":"Priyanka Prabhakar, Deepa Gupta, P. Pati","doi":"10.1109/OCIT56763.2022.00056","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00056","url":null,"abstract":"This paper reports the effectiveness of a method using T5 to generate an abstractive summarisation of Indian legal judgments. When a legally qualified person manually performs summarisation, the created summary always depends on the person's expertise in performing the task. So an automatic legal summarization is used to perform this task more accurately. The system generates an abstractive summary of 350 judgments taken from the Honorable Supreme Court of India. The dataset has been created manually with a lawyer's help, and the result evaluation is performed using the ROUGE score, which gave a precision of 0.54955 for Rouge-L.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115725101","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00021
Nayan Ranjan Paul, Deepak Sahoo, R. Balabantaray
When it comes to classifying tweets about disasters, Deep Neural Network-based models have shown great potential over conventional machine learning models. In particular, Bidirectional Encoder Representations from Transformers(BERT) are effectively used to capture the contextual information present in a tweet. But it is not effectively capturing the global structural information of tweets. A Graph Convolutional Network's(GCN) power lies in its ability to capture global information. In this study, we present a novel hybrid model called VocabGCN-BERT by combining the GCN made from a vocabulary graph of tweets and the pre-trained BERT model. A powerful representation for classifying tweets is created by combining local contextual information acquired from BERT with global structural information acquired from VocabGCN. The results of the experiments demonstrate that the proposed VocabGCN-BERT performs better than the currently available state-of-art models based on GCN on seven publicly available datasets by a margin of +1.66% to +4.79% in weighted average F1 score and +1.45% to +4.34% in accuracy.
{"title":"VocabGCN-BERT: A Hybrid Model to Classify Disaster Related Tweets","authors":"Nayan Ranjan Paul, Deepak Sahoo, R. Balabantaray","doi":"10.1109/OCIT56763.2022.00021","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00021","url":null,"abstract":"When it comes to classifying tweets about disasters, Deep Neural Network-based models have shown great potential over conventional machine learning models. In particular, Bidirectional Encoder Representations from Transformers(BERT) are effectively used to capture the contextual information present in a tweet. But it is not effectively capturing the global structural information of tweets. A Graph Convolutional Network's(GCN) power lies in its ability to capture global information. In this study, we present a novel hybrid model called VocabGCN-BERT by combining the GCN made from a vocabulary graph of tweets and the pre-trained BERT model. A powerful representation for classifying tweets is created by combining local contextual information acquired from BERT with global structural information acquired from VocabGCN. The results of the experiments demonstrate that the proposed VocabGCN-BERT performs better than the currently available state-of-art models based on GCN on seven publicly available datasets by a margin of +1.66% to +4.79% in weighted average F1 score and +1.45% to +4.34% in accuracy.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125316852","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00108
Gaurish Garg, S. Shivani
This paper discusses a low-cost mixed reality application wherein the movement of hands will be captured using the phone's rear camera and replicated to the objects in the virtual world. In this, a client-server communication channel over UDP Sockets will be set up where the Virtual Reality App in the phone will be the client for a Machine Learning server. The client (virtual reality app on the phone) will capture the live feed of the movement of hands which will be sent to the ML Server for processing. The ML Server will process the live feed and detect the position of hands, which will be passed back to the client (virtual reality app on the phone), where this movement of hands will be replicated in the virtual world.
{"title":"Controller free hand interaction in Virtual Reality","authors":"Gaurish Garg, S. Shivani","doi":"10.1109/OCIT56763.2022.00108","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00108","url":null,"abstract":"This paper discusses a low-cost mixed reality application wherein the movement of hands will be captured using the phone's rear camera and replicated to the objects in the virtual world. In this, a client-server communication channel over UDP Sockets will be set up where the Virtual Reality App in the phone will be the client for a Machine Learning server. The client (virtual reality app on the phone) will capture the live feed of the movement of hands which will be sent to the ML Server for processing. The ML Server will process the live feed and detect the position of hands, which will be passed back to the client (virtual reality app on the phone), where this movement of hands will be replicated in the virtual world.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123930966","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00103
P. Ray, Abhilash Asit Kumar Majhi
A techno-economic analysis was carried out for standalone microgrid systems powered entirely by renewable energy. It includes various scenarios like solar energy with battery energy storage, pumped hydro storage, power to hydrogen system, hybrid solar energy, and wind turbine with battery energy storage and pumped hydro storage. Each scenario, as per its configuration, consists of solar PV of 1 kW rated capacity and a wind turbine of 1.5kW. For storage, lead acid batteries of 1 kWh, pumped hydro storage of 245kWh, and hydrogen power is used. The microgrid has a peak annual load of 88.22kW and daily average demand of 800kWh. The energy technologies were designed, modeled and simulated using HOMER Pro, and the energy economics, balance, and environmental emissions were examined and compared among suggested scenarios. The “National Renewable Energy Lab (NREL)” and “National Aeronautics and Space Administration (NASA)” provided meteorological statistics for simulation in HOMER Pro of Burla, Odisha site to assess system performance. A sensitivity analysis was performed to determine design resilience against uncertainties like fuel price and hub height. The simulation results demonstrated that a Pumped Hydro Storage based hybrid renewable energy system has the least net present cost and levelized cost.
{"title":"Techno-Economic Analysis on Solar and Wind Assisted Standalone Microgrid","authors":"P. Ray, Abhilash Asit Kumar Majhi","doi":"10.1109/OCIT56763.2022.00103","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00103","url":null,"abstract":"A techno-economic analysis was carried out for standalone microgrid systems powered entirely by renewable energy. It includes various scenarios like solar energy with battery energy storage, pumped hydro storage, power to hydrogen system, hybrid solar energy, and wind turbine with battery energy storage and pumped hydro storage. Each scenario, as per its configuration, consists of solar PV of 1 kW rated capacity and a wind turbine of 1.5kW. For storage, lead acid batteries of 1 kWh, pumped hydro storage of 245kWh, and hydrogen power is used. The microgrid has a peak annual load of 88.22kW and daily average demand of 800kWh. The energy technologies were designed, modeled and simulated using HOMER Pro, and the energy economics, balance, and environmental emissions were examined and compared among suggested scenarios. The “National Renewable Energy Lab (NREL)” and “National Aeronautics and Space Administration (NASA)” provided meteorological statistics for simulation in HOMER Pro of Burla, Odisha site to assess system performance. A sensitivity analysis was performed to determine design resilience against uncertainties like fuel price and hub height. The simulation results demonstrated that a Pumped Hydro Storage based hybrid renewable energy system has the least net present cost and levelized cost.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115322392","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}
Pub Date : 2022-12-01DOI: 10.1109/OCIT56763.2022.00047
K. Chakravarty, Jagannath Singh
In current world, complexity and volume of software applications are increasing exponentially. Applications are expected to perform without defects as critical real world transactions are being handled through software design and development. Quality of a software can be impacted by software defects and thus leading to unavoidable high cost and customer dissatisfaction. Preventing defects at early stages of development ensures high quality software. Different defect prevention and detection techniques are used to identify the defects before delivery. In the last decade, machine learning models as defect detection techniques have taken a lot of attention from researchers as this concept narrows down the volume of code under inspection. In this research work, six machine learning algorithms are implemented. The prediction results are based on PROMISE public datasets containing more than ten thousand records. Performances of these algorithms have been compared through Confusion Matrix and Area Under the Curve (AUC) of Receiver Characteristic Operator (ROC) which are the most informative indicators of predictive accuracy in software defect prediction. The result analysis shows MLP is the best fit model in both CM and AUC-ROC showing maximum accuracy.
当今世界，软件应用程序的复杂性和数量呈指数级增长。当通过软件设计和开发处理关键的现实世界事务时，期望应用程序没有缺陷地执行。软件质量可能受到软件缺陷的影响，从而导致不可避免的高成本和客户不满。在开发的早期阶段防止缺陷可以确保高质量的软件。不同的缺陷预防和检测技术用于在交付前识别缺陷。在过去的十年中，机器学习模型作为缺陷检测技术已经引起了研究人员的广泛关注，因为这个概念缩小了被检查代码的数量。在本研究工作中，实现了六种机器学习算法。预测结果基于包含一万多条记录的PROMISE公共数据集。通过混淆矩阵(Confusion Matrix)和ROC曲线下面积(Area Under the Curve, AUC)对这些算法的性能进行了比较，这是软件缺陷预测中最具信息量的预测精度指标。结果分析表明，MLP是CM和AUC-ROC的最佳拟合模型，准确率最高。
{"title":"Optimizing Defect Removal Efficiency by Defect Prediction using Machine Learning","authors":"K. Chakravarty, Jagannath Singh","doi":"10.1109/OCIT56763.2022.00047","DOIUrl":"https://doi.org/10.1109/OCIT56763.2022.00047","url":null,"abstract":"In current world, complexity and volume of software applications are increasing exponentially. Applications are expected to perform without defects as critical real world transactions are being handled through software design and development. Quality of a software can be impacted by software defects and thus leading to unavoidable high cost and customer dissatisfaction. Preventing defects at early stages of development ensures high quality software. Different defect prevention and detection techniques are used to identify the defects before delivery. In the last decade, machine learning models as defect detection techniques have taken a lot of attention from researchers as this concept narrows down the volume of code under inspection. In this research work, six machine learning algorithms are implemented. The prediction results are based on PROMISE public datasets containing more than ten thousand records. Performances of these algorithms have been compared through Confusion Matrix and Area Under the Curve (AUC) of Receiver Characteristic Operator (ROC) which are the most informative indicators of predictive accuracy in software defect prediction. The result analysis shows MLP is the best fit model in both CM and AUC-ROC showing maximum accuracy.","PeriodicalId":425541,"journal":{"name":"2022 OITS International Conference on Information Technology (OCIT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121038553","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：