Pub Date : 2023-11-08DOI: 10.32736/sisfokom.v12i3.1717
Andi Christian, Ariansyah Ariansyah, Anggie Sri Wahyuni
In every educational institution, especially universities, there are lots of scholarships offered to students. Likewise with the Prabumulih College of Engineering (STIT Prabumulih) which has a scholarship program for its students by applying predetermined rules or criteria, for example, parents' income, parents' dependents, student achievement index scores, etc. Due to this, not all scholarship recipients who apply for scholarships will receive a scholarship. The problem faced by the campus today is in the process of winning scholarships. therefore a decision support system is needed that can assist in providing scholarship recipient recommendations. In this study the authors used the AHP method and the Expert Choice application. From the calculation results obtained by the specified criteria, the GPA of 0.389 is the highest priority weight compared to other criteria. Then, from the results of calculating student data or all alternatives, the total value of each student is obtained. It can be concluded that the one who can be recommended to get a UKT scholarship is Student A because it has the highest score, namely 16.6% of the total calculated.
{"title":"Determining Scholarship Recipients at STIT Prabumulih Using the AHP Method","authors":"Andi Christian, Ariansyah Ariansyah, Anggie Sri Wahyuni","doi":"10.32736/sisfokom.v12i3.1717","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1717","url":null,"abstract":"In every educational institution, especially universities, there are lots of scholarships offered to students. Likewise with the Prabumulih College of Engineering (STIT Prabumulih) which has a scholarship program for its students by applying predetermined rules or criteria, for example, parents' income, parents' dependents, student achievement index scores, etc. Due to this, not all scholarship recipients who apply for scholarships will receive a scholarship. The problem faced by the campus today is in the process of winning scholarships. therefore a decision support system is needed that can assist in providing scholarship recipient recommendations. In this study the authors used the AHP method and the Expert Choice application. From the calculation results obtained by the specified criteria, the GPA of 0.389 is the highest priority weight compared to other criteria. Then, from the results of calculating student data or all alternatives, the total value of each student is obtained. It can be concluded that the one who can be recommended to get a UKT scholarship is Student A because it has the highest score, namely 16.6% of the total calculated.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135430784","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 : 2023-11-08DOI: 10.32736/sisfokom.v12i3.1730
Indah Werdiningsih, Endah Purwanti, Gede Rangga Wira Aditya, Auliya Rakhman Hidayat, R. Sulthan Rafi Athallah, Virda Adisty Sahar, Tio Satrio Wibisono, Darren Febriand Nura Somba
The use of credit cards is increasing in today's digital era. This increase has resulted in many cases of fraud which have had a negative impact on credit card owners. To overcome this, many financial institutions have developed credit card fraud detection systems that can identify suspicious transactions. This study uses a classification method, namely random forest and decision tree to identify illegal transactions using a credit card, which then compares the results and attempts to create a model that can be useful for detecting fraud using a credit card that is more accurate and effective. The result of this study is that the accuracy provided by the Decision Tree Classifier is 0.98, while the accuracy provided by the Random Forest Classification is also 0.975. The conclusion obtained that the decision tree has a higher level of accuracy compared to the Random Forest Classification Algorithm, which is 98%. On the other hand, the Random Forest classification algorithm has a slightly lower level of accuracy compared to the Decision Tree classification algorithm, with an accuracy rate of 97.5%
{"title":"Identifying Credit Card Fraud in Illegal Transactions Using Random Forest and Decision Tree Algorithms","authors":"Indah Werdiningsih, Endah Purwanti, Gede Rangga Wira Aditya, Auliya Rakhman Hidayat, R. Sulthan Rafi Athallah, Virda Adisty Sahar, Tio Satrio Wibisono, Darren Febriand Nura Somba","doi":"10.32736/sisfokom.v12i3.1730","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1730","url":null,"abstract":"The use of credit cards is increasing in today's digital era. This increase has resulted in many cases of fraud which have had a negative impact on credit card owners. To overcome this, many financial institutions have developed credit card fraud detection systems that can identify suspicious transactions. This study uses a classification method, namely random forest and decision tree to identify illegal transactions using a credit card, which then compares the results and attempts to create a model that can be useful for detecting fraud using a credit card that is more accurate and effective. The result of this study is that the accuracy provided by the Decision Tree Classifier is 0.98, while the accuracy provided by the Random Forest Classification is also 0.975. The conclusion obtained that the decision tree has a higher level of accuracy compared to the Random Forest Classification Algorithm, which is 98%. On the other hand, the Random Forest classification algorithm has a slightly lower level of accuracy compared to the Decision Tree classification algorithm, with an accuracy rate of 97.5%","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135429847","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1976
Tommy Saputra, Siti Nurmaini, Muhammad Taufik Roseno, Hadi Syaputra
Cardiomegaly is a disease in which sufferers show no symptoms and have symptoms such as shortness of breath, abnormal heartbeat and edema. Cardiomegaly will cause the sufferer's heart to pump harder than usual. Early diagnosis of cardiomegaly can help make decisions about whether the heart is abnormal or normal. In addition, due to the problem that manual examination takes time and requires human interpretation and experience, tools are needed to automatically develop and identify normal and abnormal hearts. Therefore, this study proposes cardiac chamber segmentation using 2D (two-dimensional) ultrasound convolutional neural networks for rapid cardiomegaly screening in clinical applications based on heart ultrasound examination. The proposed approach uses a CNN with a U-Net architecture model with abnormal and normal heart data. The research results obtained used the pixel matrix evaluation Avg_accuracy of 99.50%, Val_accuracy of 97.98% and Mean_IoU of 90.01%.
{"title":"Heart Chamber Segmentation in Cardiomegaly Conditions Using the CNN Method with U-Net Architecture","authors":"Tommy Saputra, Siti Nurmaini, Muhammad Taufik Roseno, Hadi Syaputra","doi":"10.32736/sisfokom.v12i3.1976","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1976","url":null,"abstract":"Cardiomegaly is a disease in which sufferers show no symptoms and have symptoms such as shortness of breath, abnormal heartbeat and edema. Cardiomegaly will cause the sufferer's heart to pump harder than usual. Early diagnosis of cardiomegaly can help make decisions about whether the heart is abnormal or normal. In addition, due to the problem that manual examination takes time and requires human interpretation and experience, tools are needed to automatically develop and identify normal and abnormal hearts. Therefore, this study proposes cardiac chamber segmentation using 2D (two-dimensional) ultrasound convolutional neural networks for rapid cardiomegaly screening in clinical applications based on heart ultrasound examination. The proposed approach uses a CNN with a U-Net architecture model with abnormal and normal heart data. The research results obtained used the pixel matrix evaluation Avg_accuracy of 99.50%, Val_accuracy of 97.98% and Mean_IoU of 90.01%.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545453","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1819
Wahyu Irwan Putra, Muchtar Ali Setyo Yudono, Alun Sujjada
The importance of digital security in today's technological era requires various innovations in creating a reliable security system for humans. Biometrics is an authentication method and the most effective system for performing personal recognition because biometrics have unique characteristics. Dorsal hand vein become biometrics for the individual recognition process in this study using feature extraction of gabor filters and neural network backpropagation to classify recognition into five classes of human individuals, which are expected to be able to provide a higher accuracy value when compared to research on the introduction of dorsal hand vein. This classification process has several stages, namely input image, image pre-processing, segmentation, feature extraction, and image classification. The test results show that the percentage of success based on the five test scenarios has an average value of 75%. In this study, the results of the greatest test accuracy in the fourth scenario were 91%.
{"title":"Comparison of Gabor Filter Parameter Characteristics for Dorsal Hand Vein Authentication Using Artificial Neural Networks","authors":"Wahyu Irwan Putra, Muchtar Ali Setyo Yudono, Alun Sujjada","doi":"10.32736/sisfokom.v12i3.1819","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1819","url":null,"abstract":"The importance of digital security in today's technological era requires various innovations in creating a reliable security system for humans. Biometrics is an authentication method and the most effective system for performing personal recognition because biometrics have unique characteristics. Dorsal hand vein become biometrics for the individual recognition process in this study using feature extraction of gabor filters and neural network backpropagation to classify recognition into five classes of human individuals, which are expected to be able to provide a higher accuracy value when compared to research on the introduction of dorsal hand vein. This classification process has several stages, namely input image, image pre-processing, segmentation, feature extraction, and image classification. The test results show that the percentage of success based on the five test scenarios has an average value of 75%. In this study, the results of the greatest test accuracy in the fourth scenario were 91%.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545457","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1787
Putu Widyantara Artanta Wibawa, Cokorda Pramartha
Emotions are a person's response to an event. Emotions can be expressed verbally or nonverbally. Over time people can express their emotions through social media. Considering that emotion is a reflection of society's response, it is important to classify emotions in society to find out the community's response as information for consideration in decision-making. This study is aimed to identify and analyze the datasets, methods, and evaluation metrics that are being used in the classification of emotional texts in textual data from research data from 2013 to 2022. Based on the inclusion and exclusion design in selecting literature, a total of 50 kinds of literature were used in extracting and synthesizing data. Analysis of the data shows that out of 50 pieces of literature, there are 36 works of literature that use public datasets while 14 kinds of literature use private datasets. In the method of developing models for classifying, the SVM and Naive Bayes models are the most popular among the other models. In evaluating the model, the F-measure or F1-score metric is the most widely used metric compared to other metrics. There are three main contributions identified in this study, namely methods, models, and evaluation
{"title":"Systematic Literature Review: Machine Learning Methods in Emotion Classification in Textual Data","authors":"Putu Widyantara Artanta Wibawa, Cokorda Pramartha","doi":"10.32736/sisfokom.v12i3.1787","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1787","url":null,"abstract":"Emotions are a person's response to an event. Emotions can be expressed verbally or nonverbally. Over time people can express their emotions through social media. Considering that emotion is a reflection of society's response, it is important to classify emotions in society to find out the community's response as information for consideration in decision-making. This study is aimed to identify and analyze the datasets, methods, and evaluation metrics that are being used in the classification of emotional texts in textual data from research data from 2013 to 2022. Based on the inclusion and exclusion design in selecting literature, a total of 50 kinds of literature were used in extracting and synthesizing data. Analysis of the data shows that out of 50 pieces of literature, there are 36 works of literature that use public datasets while 14 kinds of literature use private datasets. In the method of developing models for classifying, the SVM and Naive Bayes models are the most popular among the other models. In evaluating the model, the F-measure or F1-score metric is the most widely used metric compared to other metrics. There are three main contributions identified in this study, namely methods, models, and evaluation","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545450","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1904
Samsinar Samsinar, Dwi Astuti
Data analysis and processing is very important to support business development. One example is The Javanese Café which requires analysis and processing to determine promotional menu package recommendations. To carry out data analysis and processing, of course you need technology to make these activities easier. The technology that can be used to overcome this problem is data mining. Data mining has an association rule method which functions to form association patterns. Researchers also use the FP-Growth algorithm to speed up the data processing process. The sales transaction data processing resulted in 14 association patterns with the highest confidence values and 9 menu items with the lowest support values. Then the results were analyzed again and produced 4 recommendations for promotional menu packages that could be used to support product marketing strategies.
{"title":"Determining Promotional Package Recommendations Using the Frequent Pattern Growth Algorithm at The Java Cafe","authors":"Samsinar Samsinar, Dwi Astuti","doi":"10.32736/sisfokom.v12i3.1904","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1904","url":null,"abstract":"Data analysis and processing is very important to support business development. One example is The Javanese Café which requires analysis and processing to determine promotional menu package recommendations. To carry out data analysis and processing, of course you need technology to make these activities easier. The technology that can be used to overcome this problem is data mining. Data mining has an association rule method which functions to form association patterns. Researchers also use the FP-Growth algorithm to speed up the data processing process. The sales transaction data processing resulted in 14 association patterns with the highest confidence values and 9 menu items with the lowest support values. Then the results were analyzed again and produced 4 recommendations for promotional menu packages that could be used to support product marketing strategies.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545446","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1808
Rezky Yuranda, Tata Sutabri, Delpiah Wahyuningsih
In the current digital era, information availability is abundant, and news serves as a primary source of up-to-date and reliable information for the public. However, with the increasing volume of information, a robust evaluation method is necessary to ensure accurate and dependable news labeling. This research employs a machine learning approach, utilizing three common classification algorithms: Naive Bayes, SVM, and Random Forest, to evaluate news labels based on their titles. The dataset utilized in this study is obtained from Jakarta AI Research and consists of 10,000 samples covering various news topics. Evaluation is conducted using accuracy, precision, recall, and F1-Score metrics to gain a comprehensive understanding of the classification algorithm's performance. The results of this research demonstrate that the SVM algorithm exhibits the best performance, achieving an accuracy rate of 92.92%. Random Forest follows with an accuracy rate of 91.21%, and Naive Bayes with an accuracy rate of 89.61%. These findings provide deep insights into the effectiveness of the machine learning approach in evaluating news labels based on their titles. Furthermore, the study highlights the importance of considering other evaluation metrics such as precision, recall, and F1-Score to obtain a more holistic understanding of the algorithm's performance. Further research is encouraged to involve additional classification algorithms and more diverse and extensive datasets to enhance the comprehension of news label evaluation comprehensively. Such endeavors can significantly contribute to the development of automated systems for classifying news with higher accuracy and reliability in the future
{"title":"Macine Learning Approach in Evaluating News Labels Based on Titles: Online Media Case Study","authors":"Rezky Yuranda, Tata Sutabri, Delpiah Wahyuningsih","doi":"10.32736/sisfokom.v12i3.1808","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1808","url":null,"abstract":"In the current digital era, information availability is abundant, and news serves as a primary source of up-to-date and reliable information for the public. However, with the increasing volume of information, a robust evaluation method is necessary to ensure accurate and dependable news labeling. This research employs a machine learning approach, utilizing three common classification algorithms: Naive Bayes, SVM, and Random Forest, to evaluate news labels based on their titles. The dataset utilized in this study is obtained from Jakarta AI Research and consists of 10,000 samples covering various news topics. Evaluation is conducted using accuracy, precision, recall, and F1-Score metrics to gain a comprehensive understanding of the classification algorithm's performance. The results of this research demonstrate that the SVM algorithm exhibits the best performance, achieving an accuracy rate of 92.92%. Random Forest follows with an accuracy rate of 91.21%, and Naive Bayes with an accuracy rate of 89.61%. These findings provide deep insights into the effectiveness of the machine learning approach in evaluating news labels based on their titles. Furthermore, the study highlights the importance of considering other evaluation metrics such as precision, recall, and F1-Score to obtain a more holistic understanding of the algorithm's performance. Further research is encouraged to involve additional classification algorithms and more diverse and extensive datasets to enhance the comprehension of news label evaluation comprehensively. Such endeavors can significantly contribute to the development of automated systems for classifying news with higher accuracy and reliability in the future","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545458","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 : 2023-11-07DOI: 10.32736/sisfokom.v12i3.1978
Hendri Donan, Edi Surya Negara Surya Negara, Tata Sutabri, Firdaus Firdaus
The utilization of Information Technology (IT) in higher education setting aims to enhance the quality of education, and this initiative is realized through the implementation of Information Technology at the Institute of Health Sciences and Technology Muhammadiyah Palembang (IKesT MP) in the form of an Academic Information System (SIMAKAD). SIMAKAD is a vital role as a tool to manage internal data and serves as an information hub for students. This research is conducted to evaluate the acceptance level of the UTAUT2 model and the impact of both the main and target variables within the UTAUT2 model. This research utilizes a quantitative method with 150 respondents, analyzed using SMART PLS 3.0 software." software. The research findings indicate that the acceptance level of the UTAUT2 model reaches 74%, signifying a high adoption rate. Variables like Perceived Value (p-Value: 0.019) and Habit (p-Value: 0.009) significantly influence Behavioral Intention, with a p-Value 0.05, indicating that their hypotheses are accepted. On the other hand, variables such as Performance Expectancy (p-Value: 0.660), Effort Expectancy (p-Value: 0.417), Social Influence (p-Value: 0.652), and Facilitating Conditions (p-Value: 0.292) There is no substantial influence on Behavioral Intention as a result of using Information Technology (IT), indicating that their hypotheses have not been endorsed.. Additionally, the variable Hedonic Motivation (p-Value: 0.978) also does not can significantly impact one's inclination toward a behavior Intention. However, variables Facilitating Conditions (p-Value: 0.000) and Behavioral Intention (p-Value: 0.000) have a positive impact on Use Behavior, indicating that their hypotheses are accepted. Conversely, the variable Habit (p-Value: 0.915) Does not exert a significant impact on Uss Behavior, resulting in the rejection of its hypothesis.
{"title":"Analysis of Behavioral Use of Academic Information Systems with the Implementation of UTAUT 2 Integration at the Muhammadi-Palembang Institute of Health Science and Technology","authors":"Hendri Donan, Edi Surya Negara Surya Negara, Tata Sutabri, Firdaus Firdaus","doi":"10.32736/sisfokom.v12i3.1978","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1978","url":null,"abstract":"The utilization of Information Technology (IT) in higher education setting aims to enhance the quality of education, and this initiative is realized through the implementation of Information Technology at the Institute of Health Sciences and Technology Muhammadiyah Palembang (IKesT MP) in the form of an Academic Information System (SIMAKAD). SIMAKAD is a vital role as a tool to manage internal data and serves as an information hub for students. This research is conducted to evaluate the acceptance level of the UTAUT2 model and the impact of both the main and target variables within the UTAUT2 model. This research utilizes a quantitative method with 150 respondents, analyzed using SMART PLS 3.0 software.\" software. The research findings indicate that the acceptance level of the UTAUT2 model reaches 74%, signifying a high adoption rate. Variables like Perceived Value (p-Value: 0.019) and Habit (p-Value: 0.009) significantly influence Behavioral Intention, with a p-Value 0.05, indicating that their hypotheses are accepted. On the other hand, variables such as Performance Expectancy (p-Value: 0.660), Effort Expectancy (p-Value: 0.417), Social Influence (p-Value: 0.652), and Facilitating Conditions (p-Value: 0.292) There is no substantial influence on Behavioral Intention as a result of using Information Technology (IT), indicating that their hypotheses have not been endorsed.. Additionally, the variable Hedonic Motivation (p-Value: 0.978) also does not can significantly impact one's inclination toward a behavior Intention. However, variables Facilitating Conditions (p-Value: 0.000) and Behavioral Intention (p-Value: 0.000) have a positive impact on Use Behavior, indicating that their hypotheses are accepted. Conversely, the variable Habit (p-Value: 0.915) Does not exert a significant impact on Uss Behavior, resulting in the rejection of its hypothesis.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135545749","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 : 2023-11-06DOI: 10.32736/sisfokom.v12i3.1742
Syefrida Yulina, Heni Rachmawati
Facial Expression Recognition (FER) is currently widely explored by researchers in the field of Computer Vision. The application of Machine Learning and Deep Learning methods is useful in developing an intelligent system that is accurate in recognizing facial expressions such as emotions. This is inseparable from the type of dataset and classification method used which certainly affects the desired results. To choose the right method, it is necessary to compare the performance of these methods. This study focuses on comparing the performance results of four classification methods namely, Convolutional Neural Network (CNN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes Classifier (NBC) on a multiclass dataset for seven classes of facial emotion labels based on Eigenface feature selection uses the Personal Component Analysis (PCA) algorithm. The test parameters used to perform method comparisons are accuracy, recall, precision, f1-score, as well as the Receiving Operating Characteristic (ROC) and Area Under Curve (AUC) curves. The results of the analysis state that the SVM method has the highest accuracy value, while other methods show varying performance based on recall, precision, f1-score, and ROC and AUC analysis. This research was conducted on the FER 2013 dataset which showed that the classification method tested had quite good performance according to the test parameters.
{"title":"Performance Analysis of Classification Models in Multiclass Facial Expression Recognition Based on Eigenface Features","authors":"Syefrida Yulina, Heni Rachmawati","doi":"10.32736/sisfokom.v12i3.1742","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1742","url":null,"abstract":"Facial Expression Recognition (FER) is currently widely explored by researchers in the field of Computer Vision. The application of Machine Learning and Deep Learning methods is useful in developing an intelligent system that is accurate in recognizing facial expressions such as emotions. This is inseparable from the type of dataset and classification method used which certainly affects the desired results. To choose the right method, it is necessary to compare the performance of these methods. This study focuses on comparing the performance results of four classification methods namely, Convolutional Neural Network (CNN), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Naïve Bayes Classifier (NBC) on a multiclass dataset for seven classes of facial emotion labels based on Eigenface feature selection uses the Personal Component Analysis (PCA) algorithm. The test parameters used to perform method comparisons are accuracy, recall, precision, f1-score, as well as the Receiving Operating Characteristic (ROC) and Area Under Curve (AUC) curves. The results of the analysis state that the SVM method has the highest accuracy value, while other methods show varying performance based on recall, precision, f1-score, and ROC and AUC analysis. This research was conducted on the FER 2013 dataset which showed that the classification method tested had quite good performance according to the test parameters.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135723748","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 : 2023-11-06DOI: 10.32736/sisfokom.v12i3.1756
Yosefina Finsensia Riti, Jonathan Steven Iskandar, Hendra Hendra
The Sumba region, Indonesia, is known for its extraordinary natural beauty and unique cultural richness. There are 19 interesting tourist attractions spread throughout the area, but tourists often face difficulties in planning efficient visiting routes. From this case, it can be solved by applying graph theory in terms of searching for the shortest distance which is completed using the shortest path search algorithm. Then these 19 tourist objects are used to build a weighted graph, where the nodes represent the tourist objects and the edges of the graph describe the distance or travel time between these objects. Therefore, this research aims to compare the shortest path search algorithm with parameters to compare the shortest distance results, algorithm complexity and execution time for tourism in the Sumba area. The results of this research involve a comparison of several shortest path search algorithms, with the aim of finding the shortest distance results, algorithm complexity, and execution time for tourism in the Sumba area. Based on the test results of the five algorithms with the parameters that have been prepared, and the findings show that each algorithm has its own characteristics, the results are as follows: Dijkstra's algorithm can be used to calculate the shortest route for single-source and single-destination types. This resembles the Bellman-Ford algorithm, only the Bellman-Ford algorithm can be used simultaneously on graphs that have negative weight values. Meanwhile, the Floyd-Warshall algorithm is suitable for use on the all-pairs type. Then, the Johnson Algorithm can be used to determine the shortest path from all pairs of paths where the destination node is located in the graph. Finally, the Ant Colony algorithm to compute from a node to each pair of destination nodes.
{"title":"Comparison Analysis of Graph Theory Algorithms for Shortest Path Problem","authors":"Yosefina Finsensia Riti, Jonathan Steven Iskandar, Hendra Hendra","doi":"10.32736/sisfokom.v12i3.1756","DOIUrl":"https://doi.org/10.32736/sisfokom.v12i3.1756","url":null,"abstract":"The Sumba region, Indonesia, is known for its extraordinary natural beauty and unique cultural richness. There are 19 interesting tourist attractions spread throughout the area, but tourists often face difficulties in planning efficient visiting routes. From this case, it can be solved by applying graph theory in terms of searching for the shortest distance which is completed using the shortest path search algorithm. Then these 19 tourist objects are used to build a weighted graph, where the nodes represent the tourist objects and the edges of the graph describe the distance or travel time between these objects. Therefore, this research aims to compare the shortest path search algorithm with parameters to compare the shortest distance results, algorithm complexity and execution time for tourism in the Sumba area. The results of this research involve a comparison of several shortest path search algorithms, with the aim of finding the shortest distance results, algorithm complexity, and execution time for tourism in the Sumba area. Based on the test results of the five algorithms with the parameters that have been prepared, and the findings show that each algorithm has its own characteristics, the results are as follows: Dijkstra's algorithm can be used to calculate the shortest route for single-source and single-destination types. This resembles the Bellman-Ford algorithm, only the Bellman-Ford algorithm can be used simultaneously on graphs that have negative weight values. Meanwhile, the Floyd-Warshall algorithm is suitable for use on the all-pairs type. Then, the Johnson Algorithm can be used to determine the shortest path from all pairs of paths where the destination node is located in the graph. Finally, the Ant Colony algorithm to compute from a node to each pair of destination nodes.","PeriodicalId":34309,"journal":{"name":"Jurnal Sisfokom","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135723762","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：