The enthusiasm of students to join online tuition centers is rising from time to time. It affects the number of tutors who have the important roles as the instructors. In the meantime, the students usually get information regarding the tuition centers from their colleagues or relatives. This affects the number of the students which is still minor. This indicates that the information about the existence of online tuition centers among societies has not been spread out widely. Mirroring on the lack, there is an idea appears. It is necessary to design a specific website for the online tuition centers. Besides its function as the promotion media, the website also provides access to learning materials. The learning materials which will be offered include theories, academic data manager and tabulation, and exercises with the tricks of how to finish them easily. This aims to help the students improve their achievements at school. The design of the application of these online tuition centers was constructed by the language program of PHP, MySQL basis data, and the methodology of waterfall. All stages of waterfall were started from analysis systems with business process, system design with DFD which includes diagram context, DFD Level 1, and DFD Level 2, ERD, and Data Dictionary. The process of managing and tabulating data which are in the system includes administrators, instructors, applicants and parents, where everyone has the access to the specific features. Through the Blackbox testing, it is concluded that all the features ran well, so they met the plan
{"title":"PERANCANGAN APLIKASI BIMBINGAN BELAJAR ONLINE","authors":"Jadiaman Parhusip, Widiatry Widiatry, Indes Permatahati Parhusip","doi":"10.47111/jti.v7i2.5604","DOIUrl":"https://doi.org/10.47111/jti.v7i2.5604","url":null,"abstract":"The enthusiasm of students to join online tuition centers is rising from time to time. It affects the number of tutors who have the important roles as the instructors. In the meantime, the students usually get information regarding the tuition centers from their colleagues or relatives. This affects the number of the students which is still minor. This indicates that the information about the existence of online tuition centers among societies has not been spread out widely. Mirroring on the lack, there is an idea appears. It is necessary to design a specific website for the online tuition centers. Besides its function as the promotion media, the website also provides access to learning materials. The learning materials which will be offered include theories, academic data manager and tabulation, and exercises with the tricks of how to finish them easily. This aims to help the students improve their achievements at school. The design of the application of these online tuition centers was constructed by the language program of PHP, MySQL basis data, and the methodology of waterfall. All stages of waterfall were started from analysis systems with business process, system design with DFD which includes diagram context, DFD Level 1, and DFD Level 2, ERD, and Data Dictionary. The process of managing and tabulating data which are in the system includes administrators, instructors, applicants and parents, where everyone has the access to the specific features. Through the Blackbox testing, it is concluded that all the features ran well, so they met the plan","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117134008","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 rapid growth of the palm oil industry has made it increasingly important to develop applications that can detect the maturity level of oil palm fruit. This paper presents the design and development of an application for detecting the maturity level of oil palm fruit based on color composition using the K-NN algorithm. The K-NN algorithm is used to classify the oil palm fruit based on the color composition that is related to its maturity level. The application uses image processing technology to measure the qualitative and quantitative parameters of various maturity indicators, such as color, size, and texture. Different color compositions of the oil palm fruit indicate different maturity levels, and using the K-NN algorithm, the fruit can be classified based on its maturity level. The application helps reduce production costs and losses caused by errors in harvesting the fruit. The application is designed to be user-friendly and accessible to farmers and plantation managers. The user interface is simple and intuitive, allowing users to easily input the image of the oil palm fruit and get a quick analysis of its maturity level. The results are displayed in a clear and understandable way, making it easy for users to make informed decisions about when to harvest the fruit. In conclusion, the application for detecting the maturity level of oil palm fruit based on color composition using the K-NN algorithm is a useful tool in the palm oil industry. It helps farmers and plantation managers determine the optimal time for harvesting the fruit, reducing production costs and increasing productivity. The user-friendly interface makes it accessible to a wider range of users and facilitates informed decision-makin
{"title":"RANCANG BANGUN SISTEM DETEKSI KEMATANGAN BUAH KELAPA SAWIT BERDASARKAN DETEKSI WARNA MENGGUNAKAN ALGORITMA K-NN","authors":"A. Saputra, Enny Dwi Oktaviyani","doi":"10.47111/jti.v7i2.9232","DOIUrl":"https://doi.org/10.47111/jti.v7i2.9232","url":null,"abstract":"The rapid growth of the palm oil industry has made it increasingly important to develop applications that can detect the maturity level of oil palm fruit. This paper presents the design and development of an application for detecting the maturity level of oil palm fruit based on color composition using the K-NN algorithm. The K-NN algorithm is used to classify the oil palm fruit based on the color composition that is related to its maturity level. \u0000 \u0000The application uses image processing technology to measure the qualitative and quantitative parameters of various maturity indicators, such as color, size, and texture. Different color compositions of the oil palm fruit indicate different maturity levels, and using the K-NN algorithm, the fruit can be classified based on its maturity level. The application helps reduce production costs and losses caused by errors in harvesting the fruit. \u0000 \u0000The application is designed to be user-friendly and accessible to farmers and plantation managers. The user interface is simple and intuitive, allowing users to easily input the image of the oil palm fruit and get a quick analysis of its maturity level. The results are displayed in a clear and understandable way, making it easy for users to make informed decisions about when to harvest the fruit. \u0000 \u0000In conclusion, the application for detecting the maturity level of oil palm fruit based on color composition using the K-NN algorithm is a useful tool in the palm oil industry. It helps farmers and plantation managers determine the optimal time for harvesting the fruit, reducing production costs and increasing productivity. The user-friendly interface makes it accessible to a wider range of users and facilitates informed decision-makin","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122450270","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}
At the time of the development of industry 4.0, freight forwarding services urgently needed increased online buying and selling services supported by e-commerce. Problems with delivery services are usually caused by the sender himself. For example, such as damage and loss of goods sent, high shipping costs and erratic delivery times. To overcome the above problems, the researcher created a design in the form of a package receiving box using a linear sequential method such as analysis, design, coding and testing where this box can later be used when the box owner is not at the box's house. The box that is made has a camera that is used to monitor the whereabouts of the person in front of the box, if someone is in front of the box, the box will send a notification to the telegram so that later the owner can control the box to open so that packages can be put into the box. The final result of this research is a package receiving box that can be controlled and provides notification via telegram, where this tool uses a camera as a person detector and ultrasonic to detect items in the box, which will later provide notifications to the telegram bot so that the package owner knows if there is a courier or not in front of the package receiving box, and also telegram can control the servo to unlock the package receiving box itself.
{"title":"SMARTBOX PENERIMA PAKET BELANJA ONLINE","authors":"Deddy Ronaldo, Nahumi Nugrahaningsih, Edy Pratamajaya","doi":"10.47111/jti.v7i2.8782","DOIUrl":"https://doi.org/10.47111/jti.v7i2.8782","url":null,"abstract":"\u0000 \u0000 \u0000 \u0000At the time of the development of industry 4.0, freight forwarding services urgently needed increased online buying and selling services supported by e-commerce. Problems with delivery services are usually caused by the sender himself. For example, such as damage and loss of goods sent, high shipping costs and erratic delivery times. To overcome the above problems, the researcher created a design in the form of a package receiving box using a linear sequential method such as analysis, design, coding and testing where this box can later be used when the box owner is not at the box's house. The box that is made has a camera that is used to monitor the whereabouts of the person in front of the box, if someone is in front of the box, the box will send a notification to the telegram so that later the owner can control the box to open so that packages can be put into the box. The final result of this research is a package receiving box that can be controlled and provides notification via telegram, where this tool uses a camera as a person detector and ultrasonic to detect items in the box, which will later provide notifications to the telegram bot so that the package owner knows if there is a courier or not in front of the package receiving box, and also telegram can control the servo to unlock the package receiving box itself. \u0000 \u0000 \u0000 \u0000","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130063316","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}
Tokopedia is one of the leading e-commerce platforms in Indonesia. The use of e-commerce platforms has increased rapidly in recent years. This is due to technological advances, increased internet access, and consumer behavior that prefers to shop online. In today's digital era, user reviews have an increasingly important role in shaping consumer perceptions of a product or service. The purpose of this research is to conduct sentiment analysis on application performance based on user reviews of the Tokopedia application. Researchers made the decision to use sentiment analysis because it is the most suitable method for processing data sets. From 1019 Tokopedia user reviews on the Play Store that were collected, 176 positive reviews and 843 negative reviews were obtained. Then, the data is classified using the Naive Bayes and K-Nearest Neighbor algorithms, then optimized using Particle Swarm Optimization. The results of the research conducted obtained an accuracy of 76.30% for the Naive Bayes accuracy value without feature selection, 74.09% for Naive Bayes results using feature selection. Then the accuracy value obtained for K-Nearest Neighbor without feature selection is 83.10%, and with feature selection is 83.53%. From the results obtained, the effect of using Particle Swarm Optimization selection features on the two algorithms does not have a big impact, there is an insignificant change in accuracy and AUC values which in the Naïve Bayes algorithm actually decreases
{"title":"KOMPARASI ALGORITMA NAIVE BAYES DAN K-NEAREST NEIGHBOR PADA ANALISIS SENTIMEN TERHADAP ULASAN PENGGUNA APLIKASI TOKOPEDIA","authors":"Ryfan Maulana, Muhammad Raihan, Imam Santoso","doi":"10.47111/jti.v7i2.10071","DOIUrl":"https://doi.org/10.47111/jti.v7i2.10071","url":null,"abstract":"Tokopedia is one of the leading e-commerce platforms in Indonesia. The use of e-commerce platforms has increased rapidly in recent years. This is due to technological advances, increased internet access, and consumer behavior that prefers to shop online. In today's digital era, user reviews have an increasingly important role in shaping consumer perceptions of a product or service. The purpose of this research is to conduct sentiment analysis on application performance based on user reviews of the Tokopedia application. Researchers made the decision to use sentiment analysis because it is the most suitable method for processing data sets. From 1019 Tokopedia user reviews on the Play Store that were collected, 176 positive reviews and 843 negative reviews were obtained. Then, the data is classified using the Naive Bayes and K-Nearest Neighbor algorithms, then optimized using Particle Swarm Optimization. The results of the research conducted obtained an accuracy of 76.30% for the Naive Bayes accuracy value without feature selection, 74.09% for Naive Bayes results using feature selection. Then the accuracy value obtained for K-Nearest Neighbor without feature selection is 83.10%, and with feature selection is 83.53%. From the results obtained, the effect of using Particle Swarm Optimization selection features on the two algorithms does not have a big impact, there is an insignificant change in accuracy and AUC values which in the Naïve Bayes algorithm actually decreases \u0000 ","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121507082","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}
Local language is a representation of cultural identity. Apart of being used as communication tools, local language also contains valuable values and local language. Central Kalimantan has a lot of undocumented local language, etiher conventially, let alone digitally. The purposes of this research is to provide a digital vocabulaty of Dayak Lawangan in Central Kalimantan. The stages in Rapid Application Develoment (RAD) method was adopted to build the application. The method was chosen because it is suitable for the lack of development time but it still can provide a precise and complies with the stages of making an application. With this applicatioin, it is hoped that the existence of local language of Dayak Lawangan community can be well documented in order to maintain the diversity.
{"title":"PERANCANGAN APLIKASI KAMUS DIGITAL BAHASA LAWANGAN – BAHASA INDONESIA","authors":"A. Lestari, Nahumi Nugrahaningsih, D. Septiana","doi":"10.47111/jti.v7i2.9095","DOIUrl":"https://doi.org/10.47111/jti.v7i2.9095","url":null,"abstract":"Local language is a representation of cultural identity. Apart of being used as communication tools, local language also contains valuable values and local language. Central Kalimantan has a lot of undocumented local language, etiher conventially, let alone digitally. The purposes of this research is to provide a digital vocabulaty of Dayak Lawangan in Central Kalimantan. The stages in Rapid Application Develoment (RAD) method was adopted to build the application. The method was chosen because it is suitable for the lack of development time but it still can provide a precise and complies with the stages of making an application. With this applicatioin, it is hoped that the existence of local language of Dayak Lawangan community can be well documented in order to maintain the diversity.","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130320755","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}
Technological developments are developing very quickly, so in this digital era, the use of technology as an effort to improve the delivery of information and promotional media at Perjuangan University uses Virtual Reality technology. Because not all students know or even have never visited the library. This study aims to produce a library layout information application based on Virtual Reality. An Android-based application that can provide information about the layout and usability of the library in a virtual form as if it were in a location using the VR Box tool as the media. The tests were carried out using ISO 25010 quality standards, namely the parameters of functional suitability, portability, and usability using a Likert scale measurement. The results of this study obtained a score of 84% in the "Good" category based on user satisfaction when using the application.
{"title":"RANCANG BANGUN APLIKASI INFORMASI TATA LETAK PERPUSTAKAAN BERBASIS VIRTUAL REALITY","authors":"Kania Aulia, Missi Hikmatyar, Ruuhwan","doi":"10.47111/jti.v7i2.10456","DOIUrl":"https://doi.org/10.47111/jti.v7i2.10456","url":null,"abstract":"Technological developments are developing very quickly, so in this digital era, the use of technology as an effort to improve the delivery of information and promotional media at Perjuangan University uses Virtual Reality technology. Because not all students know or even have never visited the library. This study aims to produce a library layout information application based on Virtual Reality. An Android-based application that can provide information about the layout and usability of the library in a virtual form as if it were in a location using the VR Box tool as the media. The tests were carried out using ISO 25010 quality standards, namely the parameters of functional suitability, portability, and usability using a Likert scale measurement. The results of this study obtained a score of 84% in the \"Good\" category based on user satisfaction when using the application.","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114760778","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 Immaculata Credit Cooperative is a cooperative organization whose mission is to advance the Immaculata Credit Cooperative as a reliable, independent and professional microfinance empowerment institution. One of the cooperative sectors is the credit sector because credit is a source of financing for cooperatives. Lending at the Immaculata Credit Cooperative is currently still subject to manual analysis by the credit committee, so that an inaccurate determination of credit granting can increase the number of bad or default loans. Therefore the researcher proposes to build a decision support system using the electre method where the output of the electre method calculation is in the form of ranking so that it can determine recommended prospective customers by looking at 5 assessment criteria including income, length of time to return, occupation, age, and collateral. The results of this study are in the form of desktop-based applications that can make it easier for cooperatives, especially credit committees, to determine which customers to recommend.
{"title":"SISTEM PENDUKUNG KEPUTUSAN PEMBERIAN KREDIT MENGGUNAKAN METODE ELECTRE (Studi Kasus : Koperasi Kredit Immaculata)","authors":"Mayela Wete, Yoseph P.K Kelen, Siprianus S. Manek","doi":"10.47111/jti.v7i2.10347","DOIUrl":"https://doi.org/10.47111/jti.v7i2.10347","url":null,"abstract":"The Immaculata Credit Cooperative is a cooperative organization whose mission is to advance the Immaculata Credit Cooperative as a reliable, independent and professional microfinance empowerment institution. One of the cooperative sectors is the credit sector because credit is a source of financing for cooperatives. Lending at the Immaculata Credit Cooperative is currently still subject to manual analysis by the credit committee, so that an inaccurate determination of credit granting can increase the number of bad or default loans. Therefore the researcher proposes to build a decision support system using the electre method where the output of the electre method calculation is in the form of ranking so that it can determine recommended prospective customers by looking at 5 assessment criteria including income, length of time to return, occupation, age, and collateral. The results of this study are in the form of desktop-based applications that can make it easier for cooperatives, especially credit committees, to determine which customers to recommend.","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128565476","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}
One of the development orientations in Indonesia is to improve the welfare of society. Therefore, it is important to identify and understand the characteristics of community welfare in each province in order to determine effective and targeted development strategies. Cluster analysis is one of the analyses that can be used to group provinces in Indonesia that have homogeneous characteristics within a cluster. The partition method is the simplest and fundamental approach to cluster analysis, but it can only find clusters with spherical-shaped forms. On the other hand, DBSCAN is a density-based clustering algorithm that can be used to find clusters with arbitrary shapes. In this study, the performance of the K-Means, K-Medoids, and DBSCAN algorithms was compared using data that had been dimensionally reduced using the t-SNE method. The data used was the indicator data of community welfare in the year 2022. The evaluation results of clustering based on the highest Silhouette coefficient (0.917) and the lowest Davies-Bouldin index (0.089) indicate that the best clustering methods are K-Means and DBSCAN with parameters perplexity = 1, minPts = 2, and epsilon = 9. Both methods produce the same result, which is the formation of eight clusters.
{"title":"PERBANDINGAN PERFORMA ALGORITMA K-MEANS, K-MEDOIDS, DAN DBSCAN DALAM PENGGEROMBOLAN PROVINSI DI INDONESIA BERDASARKAN INDIKATOR KESEJAHTERAAN MASYARAKAT","authors":"Ferista Wahyu Saputri, Dede Brahma Arianto","doi":"10.47111/jti.v7i2.9558","DOIUrl":"https://doi.org/10.47111/jti.v7i2.9558","url":null,"abstract":"One of the development orientations in Indonesia is to improve the welfare of society. Therefore, it is important to identify and understand the characteristics of community welfare in each province in order to determine effective and targeted development strategies. Cluster analysis is one of the analyses that can be used to group provinces in Indonesia that have homogeneous characteristics within a cluster. The partition method is the simplest and fundamental approach to cluster analysis, but it can only find clusters with spherical-shaped forms. On the other hand, DBSCAN is a density-based clustering algorithm that can be used to find clusters with arbitrary shapes. In this study, the performance of the K-Means, K-Medoids, and DBSCAN algorithms was compared using data that had been dimensionally reduced using the t-SNE method. The data used was the indicator data of community welfare in the year 2022. The evaluation results of clustering based on the highest Silhouette coefficient (0.917) and the lowest Davies-Bouldin index (0.089) indicate that the best clustering methods are K-Means and DBSCAN with parameters perplexity = 1, minPts = 2, and epsilon = 9. Both methods produce the same result, which is the formation of eight clusters. ","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123198590","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}
Deep Belief Networks are deep learning models that utilize stacks of Restricted Boltzmann Machines (RBM) or sometimes Autoencoders. Autoencoder is a neural network model that has the same input and output. The autoencoder learns the input data and attempts to reconstruct the input data. The solution in this study can provide several tests on DBN such as detecting recall accuracy and better classification precision. By using this algorithm, it is hoped that we as users can overcome problems that occur quite often such as brute force attacks in our accounts and within the company. And the results obtained from this DBN experiment are with an accuracy value of 90.27%, recall 90.27%, precession 91.67%, F1-score 90.51%. The results of this study are the data values of accuracy, recall, precession, and f1-score data used to detect brute force attacks are quite efficient using the deep model of the deep belief network.
{"title":"MODEL DETEKSI SERANGAN SSH-BRUTE FORCE BERDASARKAN DEEP BELIEF NETWORK","authors":"Constantin menteng, A. Setyanto, H. Fatta","doi":"10.47111/jti.v7i2.8151","DOIUrl":"https://doi.org/10.47111/jti.v7i2.8151","url":null,"abstract":"\u0000 \u0000 \u0000 \u0000Deep Belief Networks are deep learning models that utilize stacks of Restricted Boltzmann Machines (RBM) or sometimes Autoencoders. Autoencoder is a neural network model that has the same input and output. The autoencoder learns the input data and attempts to reconstruct the input data. The solution in this study can provide several tests on DBN such as detecting recall accuracy and better classification precision. By using this algorithm, it is hoped that we as users can overcome problems that occur quite often such as brute force attacks in our accounts and within the company. And the results obtained from this DBN experiment are with an accuracy value of 90.27%, recall 90.27%, precession 91.67%, F1-score 90.51%. The results of this study are the data values of accuracy, recall, precession, and f1-score data used to detect brute force attacks are quite efficient using the deep model of the deep belief network. \u0000 \u0000 \u0000 \u0000","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131569969","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}
Putu Atika, A. S. Sahay, Nahumi Nugrahaningsih, A. Lestari, Felicia Sylviana
An expert system is an application program that tries to imitate the reasoning of an expert in solving a problem. Students at the Faculty of Engineering who are taking a thesis must have experienced stress when working on a thesis, this is obtained from internal and external factors, stress is divided into 4, namely normal, mild, moderate, and severe stress. To find out what level of stress they are experiencing while working on the thesis. Therefore, in this thesis research, we will discuss how to design and build an Expert System application for Stress Levels for Website-Based Thesis Students (Case Study: Faculty of Engineering, University of Palangka Raya) aims to create an expert system using the forward chaining method and certainty factor, by making an application. In this way, students can find out the level of stress that is being experienced when working on a thesis and be given solutions according to the level of stress. The result is an expert system application that can replace the presence of experts to diagnose stress levels. Students make independent diagnoses by answering the symptoms they are experiencing. This study uses 10 student data from the Department of Civil Engineering 3, Architecture 2, Informatics Engineering 3, and Mining Engineering 2. The results can be concluded that the dominant students experience severe stress levels when working on theses. There is a recapitulation to see the percentage of students who experience stress levels at stress levels and periods.
{"title":"SISTEM PAKAR TINGKAT STRES PADA MAHASISWA SKRIPSI BERBASIS WEBSITE (STUDI KASUS: FAKULTAS TEKNIK UNIVERSITAS PALANGKA RAYA)","authors":"Putu Atika, A. S. Sahay, Nahumi Nugrahaningsih, A. Lestari, Felicia Sylviana","doi":"10.47111/jti.v17i1.8241","DOIUrl":"https://doi.org/10.47111/jti.v17i1.8241","url":null,"abstract":"An expert system is an application program that tries to imitate the reasoning of an expert in solving a problem. Students at the Faculty of Engineering who are taking a thesis must have experienced stress when working on a thesis, this is obtained from internal and external factors, stress is divided into 4, namely normal, mild, moderate, and severe stress. To find out what level of stress they are experiencing while working on the thesis. \u0000Therefore, in this thesis research, we will discuss how to design and build an Expert System application for Stress Levels for Website-Based Thesis Students (Case Study: Faculty of Engineering, University of Palangka Raya) aims to create an expert system using the forward chaining method and certainty factor, by making an application. In this way, students can find out the level of stress that is being experienced when working on a thesis and be given solutions according to the level of stress. \u0000The result is an expert system application that can replace the presence of experts to diagnose stress levels. Students make independent diagnoses by answering the symptoms they are experiencing. This study uses 10 student data from the Department of Civil Engineering 3, Architecture 2, Informatics Engineering 3, and Mining Engineering 2. The results can be concluded that the dominant students experience severe stress levels when working on theses. There is a recapitulation to see the percentage of students who experience stress levels at stress levels and periods.","PeriodicalId":214711,"journal":{"name":"Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130095117","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：