Pub Date : 2023-04-07DOI: 10.33096/ilkom.v15i1.839.201-214
Apriade Voutama, Adhi Rizal
The housing loan application system, which is usually managed by banks, is currently very much needed by many people, especially for customers who are already working and want to own a house. One of the efforts is to create an Expert System that can facilitate internal parties in controlling the provision of home loans to customers so that bad credit does not occur and customers do not wait too long for approval of a home loan application. Expert System is one part of Artificial Intelligence that is able to adopt a human mindset by solving problems like an expert. The method applied is Forward Chaining for KPR internal control. The Forward Chaining method is used by creating rules through a collection of facts and data as requirements for KPR then compiled into a decision tree, namely conclusions based on the rules. This process results in several decisions whether or not a customer is eligible to apply for a home loan, if accepted by the customer, it will be adjusted based on the level of the solution according to the customer's requirements. These results are implemented into an Expert System so that the Bank will easily control the provision of credit to customers and can anticipate bad credit.
{"title":"[Retraction] Penerapan Forward Chaining Pada Sistem Pakar Pengendalian Internal Bank Pemberian Kredit Pemilikan Rumah","authors":"Apriade Voutama, Adhi Rizal","doi":"10.33096/ilkom.v15i1.839.201-214","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.839.201-214","url":null,"abstract":"The housing loan application system, which is usually managed by banks, is currently very much needed by many people, especially for customers who are already working and want to own a house. One of the efforts is to create an Expert System that can facilitate internal parties in controlling the provision of home loans to customers so that bad credit does not occur and customers do not wait too long for approval of a home loan application. Expert System is one part of Artificial Intelligence that is able to adopt a human mindset by solving problems like an expert. The method applied is Forward Chaining for KPR internal control. The Forward Chaining method is used by creating rules through a collection of facts and data as requirements for KPR then compiled into a decision tree, namely conclusions based on the rules. This process results in several decisions whether or not a customer is eligible to apply for a home loan, if accepted by the customer, it will be adjusted based on the level of the solution according to the customer's requirements. These results are implemented into an Expert System so that the Bank will easily control the provision of credit to customers and can anticipate bad credit.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43197713","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1483.101-106
Nastiti Susetyo Fanany Putri, A. Wibawa, Harits Ar Rasyid, A. N. Handayani, A. Nafalski, Edinar Valiant Hawali, J. Hammad
In scientific research, journals are among the primary sources of information. There are quartiles or categories of quality in journals which are Q1, Q2, Q3, and Q4. These quartiles represent the assessment of journal. A classification machine learning algorithm is developed as a means in the categorization of journals. The process of classifying data to estimate an item class with an unknown label is called classification. Various classification algorithms, such as K-Nearest Neighbor (KNN), Naïve Bayes, and Support Vector Machine (SVM) are employed in this study, with several situations for exchanging training and testing data. Cross-validation with Confusion Matrix values of accuracy, precision, recall, and error classification is used to analyzed classification performance. The classifier with the finest accuracy rate is KNN with average accuracy of 70%, Naïve Bayes at 60% and SVM at 40%. This research suggests assumption that algorithms used in this article can approach SJR classification system.
{"title":"Classification of Engineering Journals Quartile using Various Supervised Learning Models","authors":"Nastiti Susetyo Fanany Putri, A. Wibawa, Harits Ar Rasyid, A. N. Handayani, A. Nafalski, Edinar Valiant Hawali, J. Hammad","doi":"10.33096/ilkom.v15i1.1483.101-106","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1483.101-106","url":null,"abstract":"In scientific research, journals are among the primary sources of information. There are quartiles or categories of quality in journals which are Q1, Q2, Q3, and Q4. These quartiles represent the assessment of journal. A classification machine learning algorithm is developed as a means in the categorization of journals. The process of classifying data to estimate an item class with an unknown label is called classification. Various classification algorithms, such as K-Nearest Neighbor (KNN), Naïve Bayes, and Support Vector Machine (SVM) are employed in this study, with several situations for exchanging training and testing data. Cross-validation with Confusion Matrix values of accuracy, precision, recall, and error classification is used to analyzed classification performance. The classifier with the finest accuracy rate is KNN with average accuracy of 70%, Naïve Bayes at 60% and SVM at 40%. This research suggests assumption that algorithms used in this article can approach SJR classification system.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48674867","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1546.11-20
A. Yudhana, I. Riadi, M. R. Djou
To maximize and get population document services closer to the community, the Disdukcapil district of Alor provides mobile services by visiting people in remote villages which difficult-to-reach service centres in the city. Due to a large number of villages and limited time and costs, not all villages can be served, so the kNN algorithm is needed to determine which villages are eligible to be served. The criteria used in this determination are village distance, difficulty level, and document ownership (Birth Certificate, KIA, family card, and KTPel). The classes that will be determined are "Very eligible", "Eligible", and "Not eligible". By applying Z-Score normalization with the value of K=5, the classification gets 94.12% accuracy, while non-normalized only gets 88.24% accuracy. Thus, applying normalization to training data can improve the kNN algorithm's accuracy in determining eligible villages for "ball pick-up" or mobile services.
{"title":"Determining Eligible Villages for Mobile Services using K-NN Algorithm","authors":"A. Yudhana, I. Riadi, M. R. Djou","doi":"10.33096/ilkom.v15i1.1546.11-20","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1546.11-20","url":null,"abstract":"To maximize and get population document services closer to the community, the Disdukcapil district of Alor provides mobile services by visiting people in remote villages which difficult-to-reach service centres in the city. Due to a large number of villages and limited time and costs, not all villages can be served, so the kNN algorithm is needed to determine which villages are eligible to be served. The criteria used in this determination are village distance, difficulty level, and document ownership (Birth Certificate, KIA, family card, and KTPel). The classes that will be determined are \"Very eligible\", \"Eligible\", and \"Not eligible\". By applying Z-Score normalization with the value of K=5, the classification gets 94.12% accuracy, while non-normalized only gets 88.24% accuracy. Thus, applying normalization to training data can improve the kNN algorithm's accuracy in determining eligible villages for \"ball pick-up\" or mobile services.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45970595","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1040.193-200
Fitriyani Umar, Herdianti Darwis, P. Purnawansyah
Hal yang kritis dalam proses pengenalan pola adalah ekstraksi fitur. Merupakan suatu metode untuk mendapatkan ciri-ciri suatu citra (image) sehingga dapat dikenali satu sama lain. Pada penelitian ini, metode deskriptor Fourier digunakan untuk mengekstraksi pola aksara Lontara yang terdiri dari 23 huruf. Deskriptor Fourier adalah metode yang digunakan dalam pengenalan objek dan pemrosesan citra untuk merepresentasikan bentuk batas segmen citra. Pengenalan karakter dilakukan dengan menggunakan jarak Euclidean dan Manhattan. Hasil pengujian menunjukkan bahwa tingkat pengenalan tertinggi mencapai akurasi 91,30% dengan menggunakan koefisien Fourier sebesar 50. Pengenalan huruf menggunakan Manhattan dan Euclidean cenderung sama atau menghasilkan akurasi yang cenderung serupa. Akurasi tertinggi dicapai saat menggunakan Manhattan sebesar 91,30%.
{"title":"Fourier Descriptor on Lontara Scripts Handwriting Recognition","authors":"Fitriyani Umar, Herdianti Darwis, P. Purnawansyah","doi":"10.33096/ilkom.v15i1.1040.193-200","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1040.193-200","url":null,"abstract":"Hal yang kritis dalam proses pengenalan pola adalah ekstraksi fitur. Merupakan suatu metode untuk mendapatkan ciri-ciri suatu citra (image) sehingga dapat dikenali satu sama lain. Pada penelitian ini, metode deskriptor Fourier digunakan untuk mengekstraksi pola aksara Lontara yang terdiri dari 23 huruf. Deskriptor Fourier adalah metode yang digunakan dalam pengenalan objek dan pemrosesan citra untuk merepresentasikan bentuk batas segmen citra. Pengenalan karakter dilakukan dengan menggunakan jarak Euclidean dan Manhattan. Hasil pengujian menunjukkan bahwa tingkat pengenalan tertinggi mencapai akurasi 91,30% dengan menggunakan koefisien Fourier sebesar 50. Pengenalan huruf menggunakan Manhattan dan Euclidean cenderung sama atau menghasilkan akurasi yang cenderung serupa. Akurasi tertinggi dicapai saat menggunakan Manhattan sebesar 91,30%.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48025763","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1272.82-100
S. Sumiati, S. Suherman, Raden Muhamad Firzatullah, Agung Triayudi, Agung Rahmad Fadjar
Heart disease is the main cause of death which can be diagnosed using an electrocardiogram. This study aims to classify heart defects using the Fuzzy C Means technique. The advantage of using Fuzzy C Means is that it is unsupervised and can reach a convergent cluster center under certain conditions. It is a clustering model that has the value of the objective function, number of iterations and completed time. In an unsupervised learning, the focus is more on exploring data such as looking for patterns in the data. Clustering itself aims to identify patterns of similar data to be grouped. It can be a solution to overcome the process of determining the risk of heart disease. The results showed that there were 10 data grouped into cluster 1 and 10 data into cluster 2. The first group (Cluster 1) consisted of patients with serial numbers 3,5,8,9,11,12,16,17,19,20, while the second group (Cluster 2) consisted of patients with serial numbers 1,2,4,6,7,10,13,14,15 and 18. Accuracy testing results in a success rate of 60%.
{"title":"Application of the Fuzzy C-Means Method in Grouping Heart Abnormalities Based on Electrocardiogram Medical Records","authors":"S. Sumiati, S. Suherman, Raden Muhamad Firzatullah, Agung Triayudi, Agung Rahmad Fadjar","doi":"10.33096/ilkom.v15i1.1272.82-100","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1272.82-100","url":null,"abstract":"Heart disease is the main cause of death which can be diagnosed using an electrocardiogram. This study aims to classify heart defects using the Fuzzy C Means technique. The advantage of using Fuzzy C Means is that it is unsupervised and can reach a convergent cluster center under certain conditions. It is a clustering model that has the value of the objective function, number of iterations and completed time. In an unsupervised learning, the focus is more on exploring data such as looking for patterns in the data. Clustering itself aims to identify patterns of similar data to be grouped. It can be a solution to overcome the process of determining the risk of heart disease. The results showed that there were 10 data grouped into cluster 1 and 10 data into cluster 2. The first group (Cluster 1) consisted of patients with serial numbers 3,5,8,9,11,12,16,17,19,20, while the second group (Cluster 2) consisted of patients with serial numbers 1,2,4,6,7,10,13,14,15 and 18. Accuracy testing results in a success rate of 60%.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47713322","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1284.144-152
Dodi Al Vayed, Ulung Pribadi, R. Fatriani
The purpose of this study was to prove the researcher's hypothesis, which was related to the satisfaction level analysis of the SIKOJA application’s users in Jambi City during the COVID-19 pandemic. Discussing the use of applications in the era of the COVID-19 pandemic. Optimal use of Information and Communication Technology resources allows the government to implement new ways of running information services to the fullest. This study used quantitative methods with data sources from questionnaires via google form with 93 respondents. Data management was carried out using SEM-pls. This study used the PICIES Framework theory to determine the factors that influenced people in using SIKOJA sensitive applications. The measured variables were performance, efficiency, information, service, and control. The results of this study indicated that the value of R square was .738, the satisfaction level of using the application was 73.8%, which the R-square identified was in the medium category. Variables that influenced users of the Jambi City SIKOJA application were performance, efficiency, information, service, and control.
{"title":"The Satisfaction Level Analysis of the SIKOJA Application’s Users in Jambi City during the COVID-19 Pandemic","authors":"Dodi Al Vayed, Ulung Pribadi, R. Fatriani","doi":"10.33096/ilkom.v15i1.1284.144-152","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1284.144-152","url":null,"abstract":"The purpose of this study was to prove the researcher's hypothesis, which was related to the satisfaction level analysis of the SIKOJA application’s users in Jambi City during the COVID-19 pandemic. Discussing the use of applications in the era of the COVID-19 pandemic. Optimal use of Information and Communication Technology resources allows the government to implement new ways of running information services to the fullest. This study used quantitative methods with data sources from questionnaires via google form with 93 respondents. Data management was carried out using SEM-pls. This study used the PICIES Framework theory to determine the factors that influenced people in using SIKOJA sensitive applications. The measured variables were performance, efficiency, information, service, and control. The results of this study indicated that the value of R square was .738, the satisfaction level of using the application was 73.8%, which the R-square identified was in the medium category. Variables that influenced users of the Jambi City SIKOJA application were performance, efficiency, information, service, and control.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42092946","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1531.132-143
Aang Anwarudin, A. Fadlil, A. Yudhana
Currently, the academic information system (AIS) at universities processes academic data to facilitate student’s activities. AIS was developed to provide maximum service to students. To optimize the use of information technology and to ensure the appropriateness of the provided AIS services, it is necessary to examine the level of service provided to improve quality. This study aimed to analyze the level of AIS service quality based on user perceptions and expectations. Dissemination of online questionnaires using Google Forms with a total of 100 students as respondents. This study used the modified Webqual 4.0 method as an indicator in the preparation of the questionnaire and the importance-performance analysis (IPA) method as an analysis method. The results of data were classified based on the percentage of user’s satisfaction with AIS services with three classifications, namely good, moderate, and poor. The results of the IPA analysis showed that the AIS had good quality. The results obtained from the analysis of the quality of the AIS system had a conformity level of 90.90%, where respondents perceived close to satisfaction with AIS services. The gap level was -0.3281 which was the result of the perception/performance of the AIS that was not in line with the expectations of the user. The results of this study contribute to Universitas Muhammadiyah Gombong as reference material and evaluation of AIS system services in the future.
{"title":"User’s Satisfaction Analysis of the Academic Information Systems Quality using the Modified Webqual 4.0 Method and Importance-Performance Analysis","authors":"Aang Anwarudin, A. Fadlil, A. Yudhana","doi":"10.33096/ilkom.v15i1.1531.132-143","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1531.132-143","url":null,"abstract":"Currently, the academic information system (AIS) at universities processes academic data to facilitate student’s activities. AIS was developed to provide maximum service to students. To optimize the use of information technology and to ensure the appropriateness of the provided AIS services, it is necessary to examine the level of service provided to improve quality. This study aimed to analyze the level of AIS service quality based on user perceptions and expectations. Dissemination of online questionnaires using Google Forms with a total of 100 students as respondents. This study used the modified Webqual 4.0 method as an indicator in the preparation of the questionnaire and the importance-performance analysis (IPA) method as an analysis method. The results of data were classified based on the percentage of user’s satisfaction with AIS services with three classifications, namely good, moderate, and poor. The results of the IPA analysis showed that the AIS had good quality. The results obtained from the analysis of the quality of the AIS system had a conformity level of 90.90%, where respondents perceived close to satisfaction with AIS services. The gap level was -0.3281 which was the result of the perception/performance of the AIS that was not in line with the expectations of the user. The results of this study contribute to Universitas Muhammadiyah Gombong as reference material and evaluation of AIS system services in the future.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46835099","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1455.1-10
Brigitha Valensia Angela, Tina Tri Wulansari, Riyayatsyah Riyayatsyah, Yuli Fitrianto, Abdul Rahim
User criticism on the Play Store revealed some flaws in the Kejar Mimpi App review. Observations were made on research that discussed the Kejar Mimpi Application, and it discovered that no prior research on User Experience and User Interface had been conducted. Interviews will be conducted to collect additional data, and the initial questionnaire will be distributed on May 6, 2022. Developers and designers use User-Centered Design (UCD) design methodologies to ensure that the product or system meets the users' needs. This study used the System Usability Scale (SUS) and User Experience Questionnaire (UEQ) methods or techniques to assess user interface and user experience. This research has produced as many as 24 design recommendations and a style guide. The final evaluation results measured using the SUS questionnaire increased the average value by 14,9% from a value of 67 (adjective rating Ok category, grade scale D, High Marginal category) to 77 (adjective rating Good, grade scale C, Acceptable category). The results of the UEQ also have gained an average increase in the ratio, where previously most were in below-average positions, now in good positions. Research on the user interfaces analysis and user experience of the Kejar Mimpi Application has the potential to be developed further. Therefore, the author has several suggestions that can be used for further research so that prototype part can be developed again to be more responsive and use different methods for evaluation of design results, such as Eye Tracking, Cognitive Walkthrough, and Heuristic Evaluation.
{"title":"User Interface and User Experience Analysis of Kejar Mimpi Mobile Application using the User-Centered Design Method","authors":"Brigitha Valensia Angela, Tina Tri Wulansari, Riyayatsyah Riyayatsyah, Yuli Fitrianto, Abdul Rahim","doi":"10.33096/ilkom.v15i1.1455.1-10","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1455.1-10","url":null,"abstract":"User criticism on the Play Store revealed some flaws in the Kejar Mimpi App review. Observations were made on research that discussed the Kejar Mimpi Application, and it discovered that no prior research on User Experience and User Interface had been conducted. Interviews will be conducted to collect additional data, and the initial questionnaire will be distributed on May 6, 2022. Developers and designers use User-Centered Design (UCD) design methodologies to ensure that the product or system meets the users' needs. This study used the System Usability Scale (SUS) and User Experience Questionnaire (UEQ) methods or techniques to assess user interface and user experience. This research has produced as many as 24 design recommendations and a style guide. The final evaluation results measured using the SUS questionnaire increased the average value by 14,9% from a value of 67 (adjective rating Ok category, grade scale D, High Marginal category) to 77 (adjective rating Good, grade scale C, Acceptable category). The results of the UEQ also have gained an average increase in the ratio, where previously most were in below-average positions, now in good positions. Research on the user interfaces analysis and user experience of the Kejar Mimpi Application has the potential to be developed further. Therefore, the author has several suggestions that can be used for further research so that prototype part can be developed again to be more responsive and use different methods for evaluation of design results, such as Eye Tracking, Cognitive Walkthrough, and Heuristic Evaluation.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48629191","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1270.107-117
S. L. Wungo, Mardewi Mardewi, F. Aziz, Pertiwi Ishak, Hechmi Shili
Human Activity Recognition is technology introduced to recognize human activities. Several technologies that have been applied are Accelerometer sensors, Gyroscope sensors, Cameras, and GPS. The selection of the Support Vector Machine algorithm is due to its capabilities to minimize errors in training data sets and the Curse of dimensionality which can estimate parameters as well as its ability to find the best hyperplane that separates two classes. The SVM algorithm was originally developed for the classification of two classes. Problem raised if there are more than two classes. In addition, the performance will not optimal for the large-scale data. Therefore, modification the current design is needed. An ensemble technique can be used to combine the Support Vector Machine algorithm with the bagging algorithm. This study proposes the application of an ensemble SVM algorithm to classify human activities based on accelerometers and gyroscope sensors on smartphones. The total data is 13725 records with 4575 representatives of each class. From the results of the overall data partition carried out in the calcification process using the ensemble SVM algorithm, the best performance was generated when comparing datasets with 80% training data and 20% test data from a total of 13725 records because it succeeded in increasing accuracy, precision, and sensitivity.
{"title":"Classification of Multiclass Ensemble SVM for Human Activities based on Sensor Accelerometer and Gyroscope","authors":"S. L. Wungo, Mardewi Mardewi, F. Aziz, Pertiwi Ishak, Hechmi Shili","doi":"10.33096/ilkom.v15i1.1270.107-117","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1270.107-117","url":null,"abstract":"Human Activity Recognition is technology introduced to recognize human activities. Several technologies that have been applied are Accelerometer sensors, Gyroscope sensors, Cameras, and GPS. The selection of the Support Vector Machine algorithm is due to its capabilities to minimize errors in training data sets and the Curse of dimensionality which can estimate parameters as well as its ability to find the best hyperplane that separates two classes. The SVM algorithm was originally developed for the classification of two classes. Problem raised if there are more than two classes. In addition, the performance will not optimal for the large-scale data. Therefore, modification the current design is needed. An ensemble technique can be used to combine the Support Vector Machine algorithm with the bagging algorithm. This study proposes the application of an ensemble SVM algorithm to classify human activities based on accelerometers and gyroscope sensors on smartphones. The total data is 13725 records with 4575 representatives of each class. From the results of the overall data partition carried out in the calcification process using the ensemble SVM algorithm, the best performance was generated when comparing datasets with 80% training data and 20% test data from a total of 13725 records because it succeeded in increasing accuracy, precision, and sensitivity.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42809794","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 : 2023-04-07DOI: 10.33096/ilkom.v15i1.1512.72-81
S. J. Sumarauw
Short-term Load Forecast (STLF) is a load forecasting that is very important to study because it determines the operating pattern of the electrical system. Forecasting errors, both positive and negative, result in considerable losses because operating costs increase and ultimately lead to waste. STLF research in Indonesia, especially the State Electricity Company (PLN Sulselrabar), has yet to be widely used. Methods mainly used are manual and conventional methods because they are considered adequate. In addition, Indonesia's geographical conditions are extensive and diverse, and the electricity system is complex. As a result, the factors affecting each country's electricity demand are different, so unique forecasting methods are needed. Artificial Neural Network (ANN) is one of the Artificial Intelligent (AI) methods widely used for STLF because it can model complex and non-linear relationships from networks. This paper aims to build an STLF forecasting model that is suitable for Indonesia's geographical conditions using several ANN models tested. Based on several ANN forecasting models, the test results obtained the best model is Model-6 with ANN architecture (9-20-1). This model has one hidden layer, 20 neurons in the hidden layer, a sigmoid logistic activation function (binary sigmoid), and a linear function. Forecasting performance values obtained mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of 430.48 MW2, 15.07 MW, and 2.81%, respectively.
{"title":"Short-Term Load Forecasting using Artificial Neural Network in Indonesia","authors":"S. J. Sumarauw","doi":"10.33096/ilkom.v15i1.1512.72-81","DOIUrl":"https://doi.org/10.33096/ilkom.v15i1.1512.72-81","url":null,"abstract":"Short-term Load Forecast (STLF) is a load forecasting that is very important to study because it determines the operating pattern of the electrical system. Forecasting errors, both positive and negative, result in considerable losses because operating costs increase and ultimately lead to waste. STLF research in Indonesia, especially the State Electricity Company (PLN Sulselrabar), has yet to be widely used. Methods mainly used are manual and conventional methods because they are considered adequate. In addition, Indonesia's geographical conditions are extensive and diverse, and the electricity system is complex. As a result, the factors affecting each country's electricity demand are different, so unique forecasting methods are needed. Artificial Neural Network (ANN) is one of the Artificial Intelligent (AI) methods widely used for STLF because it can model complex and non-linear relationships from networks. This paper aims to build an STLF forecasting model that is suitable for Indonesia's geographical conditions using several ANN models tested. Based on several ANN forecasting models, the test results obtained the best model is Model-6 with ANN architecture (9-20-1). This model has one hidden layer, 20 neurons in the hidden layer, a sigmoid logistic activation function (binary sigmoid), and a linear function. Forecasting performance values obtained mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of 430.48 MW2, 15.07 MW, and 2.81%, respectively.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45542935","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：