Muhammad Hevny Rizky, M. Faisal, Irwan Budiman, D. Kartini, Friska Abadi
The field of information technology requires software, which has significant issues. Quality and reliability improvement needs damage prediction. Tree-based algorithms like Random Forest, Deep Forest, and Decision Tree offer potential in this domain. However, proper hyperparameter configuration is crucial for optimal outcomes. This study demonstrates the use of Random Search Hyperparameter Setting Technique to predict software defects, improving damage estimation accuracy. Using ReLink datasets, we found effective algorithm parameters for predicting software damage. Decision Tree, Random Forest, and Deep Forest achieved an average AUC of 0.73 with Random Search. Random Search outperformed other tree-based algorithms. The main contribution is the innovative Random Search hyperparameter tuning, particularly for Random Forest. Random Search has distinct advantages over other tree-based algorithms
{"title":"Effect of Hyperparameter Tuning Using Random Search on Tree-Based Classification Algorithm for Software Defect Prediction","authors":"Muhammad Hevny Rizky, M. Faisal, Irwan Budiman, D. Kartini, Friska Abadi","doi":"10.22146/ijccs.90437","DOIUrl":"https://doi.org/10.22146/ijccs.90437","url":null,"abstract":"The field of information technology requires software, which has significant issues. Quality and reliability improvement needs damage prediction. Tree-based algorithms like Random Forest, Deep Forest, and Decision Tree offer potential in this domain. However, proper hyperparameter configuration is crucial for optimal outcomes. This study demonstrates the use of Random Search Hyperparameter Setting Technique to predict software defects, improving damage estimation accuracy. Using ReLink datasets, we found effective algorithm parameters for predicting software damage. Decision Tree, Random Forest, and Deep Forest achieved an average AUC of 0.73 with Random Search. Random Search outperformed other tree-based algorithms. The main contribution is the innovative Random Search hyperparameter tuning, particularly for Random Forest. Random Search has distinct advantages over other tree-based algorithms","PeriodicalId":518542,"journal":{"name":"IJCCS (Indonesian Journal of Computing and Cybernetics Systems)","volume":"15 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529310","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}
Indonesia is a country with a unique geography. The confluence of three tectonic plates located in the country results in frequent natural disasters, from earthquakes to volcanic activity. BMKG is a monitoring agency tasked with providing information related to these natural disasters. However, one type of natural disaster data, the SIGMET data (Significant Meteorological Information) used to provide information on volcanic ash, has a complicated format that is difficult for ordinary people to understand. Therefore, this research seeks to make finding information related to volcanic ash and volcanic eruptions in Indonesia easier in terms of access and comprehension. In this research, an application design will be carried out that can search SIGMET data by implementing natural language processing with a production rule base. The research results have an accuracy rate of 84% using 25 test sample sentences that combine sentences and words contained in the important words section.
{"title":"Rule-Based Natural Language Processing in Volcanic Ash Data Searching System","authors":"Rangga Kusuma Priandana, Indra Indra","doi":"10.22146/ijccs.88081","DOIUrl":"https://doi.org/10.22146/ijccs.88081","url":null,"abstract":"Indonesia is a country with a unique geography. The confluence of three tectonic plates located in the country results in frequent natural disasters, from earthquakes to volcanic activity. BMKG is a monitoring agency tasked with providing information related to these natural disasters. However, one type of natural disaster data, the SIGMET data (Significant Meteorological Information) used to provide information on volcanic ash, has a complicated format that is difficult for ordinary people to understand. Therefore, this research seeks to make finding information related to volcanic ash and volcanic eruptions in Indonesia easier in terms of access and comprehension. In this research, an application design will be carried out that can search SIGMET data by implementing natural language processing with a production rule base. The research results have an accuracy rate of 84% using 25 test sample sentences that combine sentences and words contained in the important words section.","PeriodicalId":518542,"journal":{"name":"IJCCS (Indonesian Journal of Computing and Cybernetics Systems)","volume":"59 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529275","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}
Buses are one of the most widely chosen transportation methods to support the mobility of the Indonesian people. Mobility that is often found in addition to public transportation, is also often found in the mobility of tourism tour activities for a travel group. The number of tourist destinations to which passengers go up and down makes the assistant bus driver or group leader work hard to ensure that the number of passengers boarding the bus matches the number of groups. It often takes a long time to ensure the accuracy of the number of passengers before departure to the next destination. This conventional method results in the delay of the tourism tour schedule. In this research, the author designs a webcam-based bus passenger face detection system using the Single Shot Detector (SSD) method that can provide real-time information to bus drivers, assistant bus drivers or group leaders. The results obtained by the system obtained an achievement of 95% of the total system creation along with testing the detection of bus passenger faces in actual conditions resulted in an average accuracy of 77.5%.
{"title":"Webcam-Based Bus Passenger Detection System Using Single Shot Detector Method","authors":"Sigit Wasista","doi":"10.22146/ijccs.87393","DOIUrl":"https://doi.org/10.22146/ijccs.87393","url":null,"abstract":"Buses are one of the most widely chosen transportation methods to support the mobility of the Indonesian people. Mobility that is often found in addition to public transportation, is also often found in the mobility of tourism tour activities for a travel group. The number of tourist destinations to which passengers go up and down makes the assistant bus driver or group leader work hard to ensure that the number of passengers boarding the bus matches the number of groups. It often takes a long time to ensure the accuracy of the number of passengers before departure to the next destination. This conventional method results in the delay of the tourism tour schedule. In this research, the author designs a webcam-based bus passenger face detection system using the Single Shot Detector (SSD) method that can provide real-time information to bus drivers, assistant bus drivers or group leaders. The results obtained by the system obtained an achievement of 95% of the total system creation along with testing the detection of bus passenger faces in actual conditions resulted in an average accuracy of 77.5%.","PeriodicalId":518542,"journal":{"name":"IJCCS (Indonesian Journal of Computing and Cybernetics Systems)","volume":"109 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529178","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}
BPJS Kesehatan plays a crucial role in providing affordable access to healthcare services and reducing individual financial burdens. However, deficit issues can disrupt the sustainability of the program, making anomaly detection highly important to conduct. Previous research on unsupervised anomaly detection in BPJS Kesehatan revealed a limitation with Simple Linear Regression (SLR), which only accommodates linear relationships among independent variables and the target variable of BPJS Kesehatan claim values. Minister of Health Regulation No. 52 of 2016 identified eight influential non-linear independent variables, leading to the proposal of Support Vector Regression (SVR) to address SLR's shortcomings.Research findings demonstrate SVR's superior anomaly detection performance over SLR. Interestingly, the SVR model excels in anomaly detection but lacks in prediction. Optimal tuning of SVR hyperparameters (C=9, epsilon=90, gamma=0.009, residual anomaly definition > 0.5*RMSE for both datasets) yields impressive metrics: Accuracy=0.97, Precision=0.84, Recall=0.97, and F1-Score=0.90. The anomaly detection results are expected to greatly support the sustainability of the BPJS Kesehatan program in Indonesia.
{"title":"Anomaly Detection of Hospital Claim Using Support Vector Regression","authors":"Luthfia Nurma Hapsari, Nur Rokhman","doi":"10.22146/ijccs.91857","DOIUrl":"https://doi.org/10.22146/ijccs.91857","url":null,"abstract":"BPJS Kesehatan plays a crucial role in providing affordable access to healthcare services and reducing individual financial burdens. However, deficit issues can disrupt the sustainability of the program, making anomaly detection highly important to conduct. Previous research on unsupervised anomaly detection in BPJS Kesehatan revealed a limitation with Simple Linear Regression (SLR), which only accommodates linear relationships among independent variables and the target variable of BPJS Kesehatan claim values. Minister of Health Regulation No. 52 of 2016 identified eight influential non-linear independent variables, leading to the proposal of Support Vector Regression (SVR) to address SLR's shortcomings.Research findings demonstrate SVR's superior anomaly detection performance over SLR. Interestingly, the SVR model excels in anomaly detection but lacks in prediction. Optimal tuning of SVR hyperparameters (C=9, epsilon=90, gamma=0.009, residual anomaly definition > 0.5*RMSE for both datasets) yields impressive metrics: Accuracy=0.97, Precision=0.84, Recall=0.97, and F1-Score=0.90. The anomaly detection results are expected to greatly support the sustainability of the BPJS Kesehatan program in Indonesia.","PeriodicalId":518542,"journal":{"name":"IJCCS (Indonesian Journal of Computing and Cybernetics Systems)","volume":"22 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529116","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}
Q. Aini, Danny Manongga, Eko Sediyono, Sri Yulianto Joko Prasetyo, U. Rahardja, N. Santoso
There are many aspects of readiness that must be considered when implementing technological breakthroughs, the business sector is still relatively slow in adopting blockchain technology. However, considering that blockchain technology is still in its early stages of development and has many potential applications, it is necessary to conduct empirical studies on the factors influencing its application in the industry. The problem of this study is to develop an appropriate framework based on how well its features match the needs of the business sector. This research method uses data collection using online questionnaires to obtain information from 86 respondents. The current study also utilizes the Smart PLS 4 model to produce a structural hypothetical model. The results of this study find a significant influence on Revolutionary Innovation by enriching the literature on the relationship between Blockchain, Big Data and the Business Sector, which is expanded by adding new variables. The novelty of this research identifies potential utilization, analyzes internal and external factors, and identifies how blockchain disrupts the business sector. The purpose of this study is to assess how blockchain technology is currently used in the business sector for data provision as a theoretical information technology innovation
{"title":"The Adoption of Blockchain Technology the Business Using Structural Equation Modelling","authors":"Q. Aini, Danny Manongga, Eko Sediyono, Sri Yulianto Joko Prasetyo, U. Rahardja, N. Santoso","doi":"10.22146/ijccs.82107","DOIUrl":"https://doi.org/10.22146/ijccs.82107","url":null,"abstract":"There are many aspects of readiness that must be considered when implementing technological breakthroughs, the business sector is still relatively slow in adopting blockchain technology. However, considering that blockchain technology is still in its early stages of development and has many potential applications, it is necessary to conduct empirical studies on the factors influencing its application in the industry. The problem of this study is to develop an appropriate framework based on how well its features match the needs of the business sector. This research method uses data collection using online questionnaires to obtain information from 86 respondents. The current study also utilizes the Smart PLS 4 model to produce a structural hypothetical model. The results of this study find a significant influence on Revolutionary Innovation by enriching the literature on the relationship between Blockchain, Big Data and the Business Sector, which is expanded by adding new variables. The novelty of this research identifies potential utilization, analyzes internal and external factors, and identifies how blockchain disrupts the business sector. The purpose of this study is to assess how blockchain technology is currently used in the business sector for data provision as a theoretical information technology innovation","PeriodicalId":518542,"journal":{"name":"IJCCS (Indonesian Journal of Computing and Cybernetics Systems)","volume":"56 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529443","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：