Control of electronic equipment can be done with a smart home application that controls web-based household electronic equipment and can be controlled remotely. This smart home application can make it easier for users to control household electronic equipment such as lights, air conditioners and so that it can reduce the wastage of electricity when users forget to turn off household electronic equipment when outside the home or wherever the user is. This application uses NodeMCU which functions as a server that will connect hardware and software controlled via the web as an interface used by users to enter input and produce output. From the results of the tests that have been carried out, this system can be controlled remotely using button commands and can function as originally intended for this research.
{"title":"Rancang Bangun Rumah Pintar (Smart Home) Berbasis Internet Of Things (IoT)","authors":"Malik Ibrahim, B. Sugiarto","doi":"10.29408/jit.v6i1.5365","DOIUrl":"https://doi.org/10.29408/jit.v6i1.5365","url":null,"abstract":"Control of electronic equipment can be done with a smart home application that controls web-based household electronic equipment and can be controlled remotely. This smart home application can make it easier for users to control household electronic equipment such as lights, air conditioners and so that it can reduce the wastage of electricity when users forget to turn off household electronic equipment when outside the home or wherever the user is. This application uses NodeMCU which functions as a server that will connect hardware and software controlled via the web as an interface used by users to enter input and produce output. From the results of the tests that have been carried out, this system can be controlled remotely using button commands and can function as originally intended for this research.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79490443","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}
The development of the E-learning application is part of the solution for convenience in carrying out teaching and learning activities, the process of receiving and sending a digital document in the form of learning videos and ebooks is the most important part so that information can be accessed quickly and easily. Special methods are needed to build e-learning applications more quickly and according to needs. Requirements Planning plays a very important role in the software development process, project management in software development and one of the processes is to estimate that the software produced is according to a predetermined schedule and cost. The Rapid Application Development Method is a life cycle strategy aimed at To provide development that is much faster and get results with better quality, UML (Unified Modeling Language) is a language that has become a decent standard in designing, visualizing and documenting software.
{"title":"Pengembangan Aplikasi E-learning dengan Metode Rapid Application Development","authors":"Ahmad Fauzi, Ginabila Ginabila, M. A. Azis","doi":"10.29408/jit.v6i1.7414","DOIUrl":"https://doi.org/10.29408/jit.v6i1.7414","url":null,"abstract":"The development of the E-learning application is part of the solution for convenience in carrying out teaching and learning activities, the process of receiving and sending a digital document in the form of learning videos and ebooks is the most important part so that information can be accessed quickly and easily. Special methods are needed to build e-learning applications more quickly and according to needs. Requirements Planning plays a very important role in the software development process, project management in software development and one of the processes is to estimate that the software produced is according to a predetermined schedule and cost. The Rapid Application Development Method is a life cycle strategy aimed at To provide development that is much faster and get results with better quality, UML (Unified Modeling Language) is a language that has become a decent standard in designing, visualizing and documenting software.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"73 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85934232","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}
Internet-based technology has become a primary need. Based on the survey results from the Central Statistics Agency in collaboration with APJII, email sending and receiving activities have outperformed social media positions by reaching 95.75%. Very intense use of email can have both positive and negative effects. Because apart from being a communication tool, in reality not everyone uses email well and there are even so many misuses of email that have the potential to harm others. This misused email is commonly known as spam or junkmail (junk email) which contains advertisements, scams and even viruses. In this study, data processing from gmail emails with text mining was carried out and then tested with several data mining classification methods including the Naïve Bayes Algorithm, SVM, Random Forest and combined with Partical Swarm Optimization in predicting spam emails with the aim that the selected algorithm is the most accurate. From the test results by measuring the performance of the four algorithms using Confusion Matrix and ROC, it is known that the Naïve Bayes algorithm with Partical Swarm Optimization (PSO) has the highest accuracy value, namely 81.40% and AUC 0.78
{"title":"Deteksi Spam Email dengan Metode Naive Bayes dan Particle Swarm Optimization (PSO)","authors":"Muhamad Abdul Ghani, Hamdun Sulaiman","doi":"10.29408/jit.v6i1.7049","DOIUrl":"https://doi.org/10.29408/jit.v6i1.7049","url":null,"abstract":"Internet-based technology has become a primary need. Based on the survey results from the Central Statistics Agency in collaboration with APJII, email sending and receiving activities have outperformed social media positions by reaching 95.75%. Very intense use of email can have both positive and negative effects. Because apart from being a communication tool, in reality not everyone uses email well and there are even so many misuses of email that have the potential to harm others. This misused email is commonly known as spam or junkmail (junk email) which contains advertisements, scams and even viruses. In this study, data processing from gmail emails with text mining was carried out and then tested with several data mining classification methods including the Naïve Bayes Algorithm, SVM, Random Forest and combined with Partical Swarm Optimization in predicting spam emails with the aim that the selected algorithm is the most accurate. From the test results by measuring the performance of the four algorithms using Confusion Matrix and ROC, it is known that the Naïve Bayes algorithm with Partical Swarm Optimization (PSO) has the highest accuracy value, namely 81.40% and AUC 0.78","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86541496","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}
E. Susilo, Rahmat Rizal Andhi, Diantyastuti Ramadhani
The current website of Informatics Programme at Riau University is being redesign. This process need to be done because the past design had a few shortcomings, such as not being responsive and less attactive to user, in term of UI. To figure out weather the new design meets the UX aspects, it is necessary to make an evaluation. This research does that evaluation about current website User Interface (UI) using UEQ. UEQ,as for today, is consider a fast and simple tools to test UX aspects of certain website. The UEQ will be distributed to 50 respondents which is Informatics Programme’s student. This respondent consist of 25 men and 25 women. Respondent data was analyzed using UEQ Data Analysis Tools. The result was 4 aspects which is consider good, such as attractiveness, efficiency, dependability and stimulation. There was 1 aspect which score above average, namely perspicuity. One last aspect was score below average, which is novelty. From this research result, in general the UI design and UX aspects of this website is consider good. However, to reach maximum performance some adjustment need to be done. Especially from the perspicuity ascpect. The developer need to clarify the way to use this website. The approach can be taken from general web design principal. As for novelty aspects, improvement need to be done to its content with creative and inovatif idea. This will bring unique value for informatics programme website compare to another sites.
{"title":"Evaluasi User Interface Website Prodi Teknik Informatika UNRI Menggunakan User Experience Questionnaire (UEQ)","authors":"E. Susilo, Rahmat Rizal Andhi, Diantyastuti Ramadhani","doi":"10.29408/jit.v5i2.5939","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5939","url":null,"abstract":"The current website of Informatics Programme at Riau University is being redesign. This process need to be done because the past design had a few shortcomings, such as not being responsive and less attactive to user, in term of UI. To figure out weather the new design meets the UX aspects, it is necessary to make an evaluation. This research does that evaluation about current website User Interface (UI) using UEQ. UEQ,as for today, is consider a fast and simple tools to test UX aspects of certain website. The UEQ will be distributed to 50 respondents which is Informatics Programme’s student. This respondent consist of 25 men and 25 women. Respondent data was analyzed using UEQ Data Analysis Tools. The result was 4 aspects which is consider good, such as attractiveness, efficiency, dependability and stimulation. There was 1 aspect which score above average, namely perspicuity. One last aspect was score below average, which is novelty. From this research result, in general the UI design and UX aspects of this website is consider good. However, to reach maximum performance some adjustment need to be done. Especially from the perspicuity ascpect. The developer need to clarify the way to use this website. The approach can be taken from general web design principal. As for novelty aspects, improvement need to be done to its content with creative and inovatif idea. This will bring unique value for informatics programme website compare to another sites.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"49 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83981287","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}
The field of digital image processing, such as segmentation, has become a widely discussed topic. Segmentation aims to divide the image into parts or regions so that there is no overlap with similar characteristics, such as color, shape, texture, and intensity. The segmentation process is generally divided into three groups of segmentation, including segmentation based on classification (classification based segmentation), segmentation based on edges (edge based segmentation), and segmentation based on region (region based segmentation). Edge detection is a systematic process used to detect pixels in digital images that are not fixed or always changing their brightness level in a line or curve. The purpose of this study is to compare edge detection methods using image objects. This research was conducted using the method of Robert, Prewitt, Sobel and Canny to detect the number of white pixels in each image. The tool used in this research is Simulink Matlab, where the parameters of each algorithm will be compared. Then the total number of white pixels is calculated from each edge detection method.
数字图像处理领域，如分割，已经成为一个广泛讨论的话题。分割的目的是将图像分割成多个部分或区域，使其不存在具有相似特征的重叠，如颜色、形状、纹理、强度等。分割过程一般分为三类分割，包括基于分类的分割(classification based segmentation)、基于边缘的分割(edge based segmentation)和基于区域的分割(region based segmentation)。边缘检测是一种系统的过程，用于检测数字图像中不固定或总是在直线或曲线中改变其亮度水平的像素。本研究的目的是比较使用图像对象的边缘检测方法。本研究采用Robert, Prewitt, Sobel和Canny的方法检测每张图像中的白色像素数。本研究使用的工具是Simulink Matlab，将对各算法的参数进行比较。然后从每种边缘检测方法中计算出白色像素的总数。
{"title":"Implementasi Perbandingan Deteksi Tepi Pada Citra Digital Menggunakan Metode Roberst, Sobel, Prewitt dan Canny","authors":"Kukuh Panggalih, Wawan Kurniawan, Windu Gata","doi":"10.29408/jit.v5i2.5923","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5923","url":null,"abstract":"The field of digital image processing, such as segmentation, has become a widely discussed topic. Segmentation aims to divide the image into parts or regions so that there is no overlap with similar characteristics, such as color, shape, texture, and intensity. The segmentation process is generally divided into three groups of segmentation, including segmentation based on classification (classification based segmentation), segmentation based on edges (edge based segmentation), and segmentation based on region (region based segmentation). Edge detection is a systematic process used to detect pixels in digital images that are not fixed or always changing their brightness level in a line or curve. The purpose of this study is to compare edge detection methods using image objects. This research was conducted using the method of Robert, Prewitt, Sobel and Canny to detect the number of white pixels in each image. The tool used in this research is Simulink Matlab, where the parameters of each algorithm will be compared. Then the total number of white pixels is calculated from each edge detection method.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75407269","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}
The use of information technology to support administrative activities in the neighborhood makes it easier for administrators to provide administrative services for community members. The service of making rt cover letters and paying residents' mandatory contributions at RT08 / RW10 Perum Ambar Cibinong Residence Bogor still uses conventional methods, namely by recording manually. This process is considered inefficient in the process of waiting for the process of checking and making letters. And for the payment process that is still carried out by paying directly to the public relations and then handed over to the Treasurer of the RT. For this reason, an information system is needed that can facilitate these problems. The service of requesting a letter of introduction and payment of mandatory dues can be facilitated through the SI-Warga application. The creation of a SI-Warga application using a prototype model, where the flow and stages used include identifying users and developing prototypes. With this web-based application, it is hoped that the documentation of the cover letter archive and reports on the payment of mandatory contributions for residents will be more organized and well stored and can be accessed anywhere when needed with an internet connection.
{"title":"Prototype Aplikasi SI-Warga Sebagai Penunjang Administrasi Surat Pengantar dan Iuran Warga pada Rukun Tetangga","authors":"A. Sari, Ishak Kholil","doi":"10.29408/jit.v5i2.5897","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5897","url":null,"abstract":"The use of information technology to support administrative activities in the neighborhood makes it easier for administrators to provide administrative services for community members. The service of making rt cover letters and paying residents' mandatory contributions at RT08 / RW10 Perum Ambar Cibinong Residence Bogor still uses conventional methods, namely by recording manually. This process is considered inefficient in the process of waiting for the process of checking and making letters. And for the payment process that is still carried out by paying directly to the public relations and then handed over to the Treasurer of the RT. For this reason, an information system is needed that can facilitate these problems. The service of requesting a letter of introduction and payment of mandatory dues can be facilitated through the SI-Warga application. The creation of a SI-Warga application using a prototype model, where the flow and stages used include identifying users and developing prototypes. With this web-based application, it is hoped that the documentation of the cover letter archive and reports on the payment of mandatory contributions for residents will be more organized and well stored and can be accessed anywhere when needed with an internet connection.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87860688","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}
Coding or computer programming for children is now increasingly popular. According to various studies, children who learn coding at a very young age will benefit from learning to critically assess situations, explore different perspectives, build creative solutions, and even develop cognitive abilities. But of course the difficulty of the learning process itself is another level, and again, we need to see the fact that children nowadays are more into video games than learning makes this kind of situation become more complex. Therefore, this research was carried out which aims to design and create an Android-based coding introduction educational game called Funcode. Game development is assisted by the Construct 2 game engine and using the waterfall method from the SDLC or System Development Life Cycle. The game is in the form of a module equipped with a quiz by introducing HTML and CSS programming languages, as well as applying a little Computational Thinking material. Based on the blackbox test results, this mobile game called Funcode is successfully runs without any errors on various types of smartphones that have been tested
{"title":"Perancangan Game Edukasi Pengenalan Bahasa Pemrograman Menggunakan Construct 2","authors":"Iedam Fardian Anshori, Salsabila Ayuni Kaffah, Nahdayanti Supa, Rizal Rizal Setiawan Mail","doi":"10.29408/jit.v5i2.5803","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5803","url":null,"abstract":"Coding or computer programming for children is now increasingly popular. According to various studies, children who learn coding at a very young age will benefit from learning to critically assess situations, explore different perspectives, build creative solutions, and even develop cognitive abilities. But of course the difficulty of the learning process itself is another level, and again, we need to see the fact that children nowadays are more into video games than learning makes this kind of situation become more complex. Therefore, this research was carried out which aims to design and create an Android-based coding introduction educational game called Funcode. Game development is assisted by the Construct 2 game engine and using the waterfall method from the SDLC or System Development Life Cycle. The game is in the form of a module equipped with a quiz by introducing HTML and CSS programming languages, as well as applying a little Computational Thinking material. Based on the blackbox test results, this mobile game called Funcode is successfully runs without any errors on various types of smartphones that have been tested","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88638039","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}
Measuring the level of student satisfaction with academic and student services really needs to be done by measuring the level of student satisfaction with academic and student services that can be used as a benchmark for the quality of services that have been provided. By knowing the level of student satisfaction, the university can improve the service if it is not good and further improve the service if the satisfaction level is good. The method used in this research is to use the Data Mining Decission Tree classification method C4.5 algorithm where the data source used uses questionnaire technique through a google form filled out by students in the Prof. University environment. Dr. Hazairin, SH. The variables used are service quality, information quality, system quality, and performance expectations. From the analysis process, it can be seen that the level of service quality, namely service speed and staff consistency in providing services is the most dominant in determining the level of student satisfaction at the University Prof. Dr. Hazairin, SH. It is hoped that the results of this research can be used for the purposes of evaluating higher education policies in improving the quality of services in the academic and student fields
{"title":"Penerapan Data Mining Decission Tree Algoritma C4.5 Untuk Mengetahui Tingkat Kepuasan Mahasiswa Terhadap Layanan Akademik Dan Kemahasiswaan (Studi Kasus Universitas.Prof.Dr. Hazairin,SH)","authors":"Reni Kurniah, Dadang Yunika Surya Putra, Elviza Diana","doi":"10.29408/jit.v5i2.5910","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5910","url":null,"abstract":"Measuring the level of student satisfaction with academic and student services really needs to be done by measuring the level of student satisfaction with academic and student services that can be used as a benchmark for the quality of services that have been provided. By knowing the level of student satisfaction, the university can improve the service if it is not good and further improve the service if the satisfaction level is good. The method used in this research is to use the Data Mining Decission Tree classification method C4.5 algorithm where the data source used uses questionnaire technique through a google form filled out by students in the Prof. University environment. Dr. Hazairin, SH. The variables used are service quality, information quality, system quality, and performance expectations. From the analysis process, it can be seen that the level of service quality, namely service speed and staff consistency in providing services is the most dominant in determining the level of student satisfaction at the University Prof. Dr. Hazairin, SH. It is hoped that the results of this research can be used for the purposes of evaluating higher education policies in improving the quality of services in the academic and student fields","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82696086","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}
This study aims to observe, understand, design and build an information system for reporting drug abuse in the city of Kediri. This study uses the Waterfall method. The research subject is a system that can report drug abuse itself. The theoretical basis of the research used by the author uses Geographic Information Systems. GIS is a computer-based system that aims to store, manipulate, and analyze geographic information. In this research the author uses the Java programming language and the MYSQL database system as user data storage. Username using the primary key Employee Identification Number (NIP). For location mapping that has been carried out by the RPE Action, users who have created an account will be able to access the camera on a smartphone. Later the photos taken by the user will show the location of Latitude and Longitude. The research modeling uses DFD (Data Flow Diagram) modeling which contains DFD level 0 and level 1, ERD (Entity Realionship Diagram) and Flowchart. This study contains interface design, login interface design, main menu design, abuse reporting menu design, service menu design, socialization request menu design, rehabilitation request menu design, P4GN menu design, counseling request menu design, user menu design, mentoring menu design abuse, abuse report table design, edit profile menu design. Interface design is an important part of the application, because the first thing you see running is the application interface
{"title":"Rancang Bangun Pelaporan Penyalahgunaan Narkoba Badan Narkotika Nasional (BNN) Kota Kediri Berbasis Android","authors":"L. Nuryanto, D. Santoso","doi":"10.29408/jit.v5i2.5912","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5912","url":null,"abstract":"This study aims to observe, understand, design and build an information system for reporting drug abuse in the city of Kediri. This study uses the Waterfall method. The research subject is a system that can report drug abuse itself. The theoretical basis of the research used by the author uses Geographic Information Systems. GIS is a computer-based system that aims to store, manipulate, and analyze geographic information. In this research the author uses the Java programming language and the MYSQL database system as user data storage. Username using the primary key Employee Identification Number (NIP). For location mapping that has been carried out by the RPE Action, users who have created an account will be able to access the camera on a smartphone. Later the photos taken by the user will show the location of Latitude and Longitude. The research modeling uses DFD (Data Flow Diagram) modeling which contains DFD level 0 and level 1, ERD (Entity Realionship Diagram) and Flowchart. This study contains interface design, login interface design, main menu design, abuse reporting menu design, service menu design, socialization request menu design, rehabilitation request menu design, P4GN menu design, counseling request menu design, user menu design, mentoring menu design abuse, abuse report table design, edit profile menu design. Interface design is an important part of the application, because the first thing you see running is the application interface","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"70 2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80308598","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}
Heart failure is a global health problem that not only causes physical problems, other impacts such as psychological, social, and economic, as well as depression, which affects treatment, worsens functional status, and increases hospitalization rates to death. According to the World Health Organization (WHO), nearly 17.5 million people die from cardiovascular disease, which represents 31% of deaths in the world. Using machine learning to predict the survival of patients with heart failure so that they can take precautions from the start. The stages of the research carried out include the business understanding stage, the data understanding stage, the data preparation stage, the modeling stage, and the evaluation stage. In this study, using feature selection using best-first resulted in 4 very influential features, namely age, injection_fraction, serum_creatinene and time, and handling imbalance class using the class balancer model. Random forest algorithm with 80% percentage split method which produces 91.45% accuracy, mean absolute error 0.1874, incorrectly classified instances 8.55%, precision 0.915, recall 0.914, AUC 0.953.
{"title":"Algoritma Random Forest Untuk Prediksi Kelangsungan Hidup Pasien Gagal Jantung Menggunakan Seleksi Fitur Bestfirst","authors":"Yuri Yuliani","doi":"10.29408/jit.v5i2.5896","DOIUrl":"https://doi.org/10.29408/jit.v5i2.5896","url":null,"abstract":"Heart failure is a global health problem that not only causes physical problems, other impacts such as psychological, social, and economic, as well as depression, which affects treatment, worsens functional status, and increases hospitalization rates to death. According to the World Health Organization (WHO), nearly 17.5 million people die from cardiovascular disease, which represents 31% of deaths in the world. Using machine learning to predict the survival of patients with heart failure so that they can take precautions from the start. The stages of the research carried out include the business understanding stage, the data understanding stage, the data preparation stage, the modeling stage, and the evaluation stage. In this study, using feature selection using best-first resulted in 4 very influential features, namely age, injection_fraction, serum_creatinene and time, and handling imbalance class using the class balancer model. Random forest algorithm with 80% percentage split method which produces 91.45% accuracy, mean absolute error 0.1874, incorrectly classified instances 8.55%, precision 0.915, recall 0.914, AUC 0.953.","PeriodicalId":13567,"journal":{"name":"Infotek : Jurnal Informatika dan Teknologi","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89399106","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：