Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234227
Renny Sari Dewi, R. Sarno
In the size estimation software, there are many methods that have proven their reliability. One of them is Use Case Points (UCP). UCP has a well-known advantage based on the use case scenario which is a reformation of the user story in the software requirements specification (SRS) document. However, UCP also has several weaknesses, including the use case is a summary of the user story. User stories often do not reveal detailed data. Therefore, the potential ambiguity of the use case must be watched by a business/system analyst. On the other hand, there is an international association called COSMIC, which has developed a global standard for calculating the size of the software namely ISO/IEC 19761. The COSMIC model begins with a user story which is then carried out cascade to sequence diagrams to make an engagement between process/method flow and data. The purpose of this study is to substitute the use case weight of the pure UCP method, to become a COSMIC functional size unit (Cfsu). Then, the estimation results of the two are compared with the actual effort. The case study used as a comparison of the COSMIC and UCP methods is the Hair Salon Online Booking Application. From this study the results obtained are the deviation between the results of the original UCP estimate (keep use case weight) of the actual effort is 76.85 percent. As for software effort estimation using early COSMIC is 92.67 percent against the actual effort.
{"title":"Software Effort Estimation Using Early COSMIC to Substitute Use Case Weight","authors":"Renny Sari Dewi, R. Sarno","doi":"10.1109/iSemantic50169.2020.9234227","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234227","url":null,"abstract":"In the size estimation software, there are many methods that have proven their reliability. One of them is Use Case Points (UCP). UCP has a well-known advantage based on the use case scenario which is a reformation of the user story in the software requirements specification (SRS) document. However, UCP also has several weaknesses, including the use case is a summary of the user story. User stories often do not reveal detailed data. Therefore, the potential ambiguity of the use case must be watched by a business/system analyst. On the other hand, there is an international association called COSMIC, which has developed a global standard for calculating the size of the software namely ISO/IEC 19761. The COSMIC model begins with a user story which is then carried out cascade to sequence diagrams to make an engagement between process/method flow and data. The purpose of this study is to substitute the use case weight of the pure UCP method, to become a COSMIC functional size unit (Cfsu). Then, the estimation results of the two are compared with the actual effort. The case study used as a comparison of the COSMIC and UCP methods is the Hair Salon Online Booking Application. From this study the results obtained are the deviation between the results of the original UCP estimate (keep use case weight) of the actual effort is 76.85 percent. As for software effort estimation using early COSMIC is 92.67 percent against the actual effort.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122122703","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234295
Rhamadina Fitrah Umami, R. Sarno
Breast cancer is a disease that causes excessive fear in women around the world. The number of high death rates by breast cancer can be reduced by early detection. This can make breast cancer a disease that is easy to cure. A collection of datasets about breast cancer is used in the process of early detection. Early detection is carried out to analyze the state of the early stages of breast cancer patients. This research paper proposes machine learning methods, namely Generalized Linear Model, Logistic Regression, and Gradient Boosted Decision Tree to enhance the classification performance of Wisconsin Diagnostic Breast Cancer Data. The diagnosis results in two classes of cancer decisions which are malignant and benign by looking at evaluating the accuracy of the data classification test. The result shows that the Generalized Linear Model achieves the accuracy of 99.4%, which is higher than the accuracies of the previous studies for classifying the Wisconsin Diagnostic Breast Cancer dataset.
乳腺癌是一种让世界各地的女性感到极度恐惧的疾病。乳腺癌的高死亡率可以通过早期发现而减少。这使得乳腺癌成为一种容易治愈的疾病。在早期检测过程中使用了一系列关于乳腺癌的数据集。开展早期检测，分析早期乳腺癌患者的状态。本文提出了机器学习方法，即广义线性模型、逻辑回归和梯度增强决策树来提高威斯康星乳腺癌诊断数据的分类性能。通过评估数据分类测试的准确性，诊断结果为恶性和良性两类癌症决策。结果表明，广义线性模型(Generalized Linear Model)的准确率达到99.4%，高于以往研究对Wisconsin Diagnostic Breast Cancer数据集进行分类的准确率。
{"title":"Analysis of Classification Algorithm for Wisconsin Diagnosis Breast Cancer Data Study","authors":"Rhamadina Fitrah Umami, R. Sarno","doi":"10.1109/iSemantic50169.2020.9234295","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234295","url":null,"abstract":"Breast cancer is a disease that causes excessive fear in women around the world. The number of high death rates by breast cancer can be reduced by early detection. This can make breast cancer a disease that is easy to cure. A collection of datasets about breast cancer is used in the process of early detection. Early detection is carried out to analyze the state of the early stages of breast cancer patients. This research paper proposes machine learning methods, namely Generalized Linear Model, Logistic Regression, and Gradient Boosted Decision Tree to enhance the classification performance of Wisconsin Diagnostic Breast Cancer Data. The diagnosis results in two classes of cancer decisions which are malignant and benign by looking at evaluating the accuracy of the data classification test. The result shows that the Generalized Linear Model achieves the accuracy of 99.4%, which is higher than the accuracies of the previous studies for classifying the Wisconsin Diagnostic Breast Cancer dataset.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123031469","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234285
Brian Pamukti, Fernaldy Arifin, N. Adriansyah
Visible Light Communication (VLC) that utilizes free space optics as a transmission channel has a high-speed data communication capability, which uses Light Emitting Diode (LED) as a transmitter. Problems occurred in this wireless communication is the distance. VLC can only reach relatively short distance if compared to Radio Frequency (RF). There are many ways to reach a better distance performance on VLC and one of them is the error correction. In this paper, a comparison between uncoded and Quasi-Cyclic-Low Density Parity Check (QC-LDPC) codes implementation on VLC has been compared and the number of decoding iterations is simulated to reach better performance. The encoding technique of QC-LDPC codes is using the G-Matrix and Bit Flipping algorithm as the decoding. The result shows that distance increases 7% in case of QC-LDPC codes from the uncoded VLC system and 27.5% energy efficiency are increased. The number of decoding iterations also contributes an impact to Bit Error Rate (BER) performance. The simulation results proof that on VLC system using QC-LDPC codes shows better performance compared to the uncoded system.
{"title":"Low Density Parity Check Code (LDPC) for Enhancement of Visible Light Communication (VLC) Performance","authors":"Brian Pamukti, Fernaldy Arifin, N. Adriansyah","doi":"10.1109/iSemantic50169.2020.9234285","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234285","url":null,"abstract":"Visible Light Communication (VLC) that utilizes free space optics as a transmission channel has a high-speed data communication capability, which uses Light Emitting Diode (LED) as a transmitter. Problems occurred in this wireless communication is the distance. VLC can only reach relatively short distance if compared to Radio Frequency (RF). There are many ways to reach a better distance performance on VLC and one of them is the error correction. In this paper, a comparison between uncoded and Quasi-Cyclic-Low Density Parity Check (QC-LDPC) codes implementation on VLC has been compared and the number of decoding iterations is simulated to reach better performance. The encoding technique of QC-LDPC codes is using the G-Matrix and Bit Flipping algorithm as the decoding. The result shows that distance increases 7% in case of QC-LDPC codes from the uncoded VLC system and 27.5% energy efficiency are increased. The number of decoding iterations also contributes an impact to Bit Error Rate (BER) performance. The simulation results proof that on VLC system using QC-LDPC codes shows better performance compared to the uncoded system.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123455212","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234282
Ema Utami, Mihuandayani Mihuandayani, Suwanto Raharjo, Anggit Dwi Hartanto, Sumarni Adi
Social media is one of the many internet services for users of productive age. Major social media such as Facebook, Instagram, and Twitter are having many users in Indonesia. The existence of these applications creates new impacts on social interaction. The behaviour of social media users possible to reflect the character of the user. Some cases related to a person’s character often occur starting from what their activities do on social media, for example concerning the relationship between employees and where they work. Human resources play an important role in the success of a company, thus improving the quality of human resources is the main thing. One of the processes in this improvement is by recruiting selective prospective employees. The main goal of the research is doing a literature review to see whether it is possible to use social media activities as one of the factors that can be considered for employee recruitment. This research is focused on surveying the recent journal researches about profiling analysis in social media and then looking further on the methodology, objective and variables regarding personality traits. The result of this study is the social media platforms have big opportunity to be used as one of considering parameters in the employee recruitment process.
{"title":"A Review on Social Media Based Profiling Analysis","authors":"Ema Utami, Mihuandayani Mihuandayani, Suwanto Raharjo, Anggit Dwi Hartanto, Sumarni Adi","doi":"10.1109/iSemantic50169.2020.9234282","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234282","url":null,"abstract":"Social media is one of the many internet services for users of productive age. Major social media such as Facebook, Instagram, and Twitter are having many users in Indonesia. The existence of these applications creates new impacts on social interaction. The behaviour of social media users possible to reflect the character of the user. Some cases related to a person’s character often occur starting from what their activities do on social media, for example concerning the relationship between employees and where they work. Human resources play an important role in the success of a company, thus improving the quality of human resources is the main thing. One of the processes in this improvement is by recruiting selective prospective employees. The main goal of the research is doing a literature review to see whether it is possible to use social media activities as one of the factors that can be considered for employee recruitment. This research is focused on surveying the recent journal researches about profiling analysis in social media and then looking further on the methodology, objective and variables regarding personality traits. The result of this study is the social media platforms have big opportunity to be used as one of considering parameters in the employee recruitment process.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123395559","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234230
Yuni Handayani, Alvin Rinaldy Hakim, Muljono
The rapid development in the world of information and communication technology has made social media users increase. By looking at various kinds of social media, it is always filled with a variety of service users such as the use of mobile-based banking applications. In Indonesia, almost all banking services use banking facilities such as BNI. By looking at the phenomena that occur in these problems, a study was conducted on comments related to BNI mobile application-based services that are used to improve and update the quality of BNI services to customers so that they can compete with other banks. Thus the researcher aims at classifying the existing BNI Mobile Banking Application user comments on the Google Play service into positive and negative comment sentiment by applying the Support Vector Machine Media method which aims to improve and renew the BNI Mobile Banking Application service system to provide service satisfaction to users BNI. In research conducted using k-fold cross-validation testing obtained SVM kernel linear accuracy values of 78,19% for 60% data training and 40% data testing, meanwhile for 80% data training and 20% data testing get accuracy 76,94% and SVM kernel linear using K-Fold Cross Validation the highest value of 78,45% at 10 fold Cross-Validation. This algorithm has a lightweight computation as evidenced by a dataset of 580 data which only takes 2.5 seconds. K-Fold Cross Validation is proven to be able to optimize a test that was previously worth 78,19% with K-Fold Cross Validation rising to 78,45%
{"title":"Sentiment Analysis of Bank BNI User Comments Using the Support Vector Machine Method","authors":"Yuni Handayani, Alvin Rinaldy Hakim, Muljono","doi":"10.1109/iSemantic50169.2020.9234230","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234230","url":null,"abstract":"The rapid development in the world of information and communication technology has made social media users increase. By looking at various kinds of social media, it is always filled with a variety of service users such as the use of mobile-based banking applications. In Indonesia, almost all banking services use banking facilities such as BNI. By looking at the phenomena that occur in these problems, a study was conducted on comments related to BNI mobile application-based services that are used to improve and update the quality of BNI services to customers so that they can compete with other banks. Thus the researcher aims at classifying the existing BNI Mobile Banking Application user comments on the Google Play service into positive and negative comment sentiment by applying the Support Vector Machine Media method which aims to improve and renew the BNI Mobile Banking Application service system to provide service satisfaction to users BNI. In research conducted using k-fold cross-validation testing obtained SVM kernel linear accuracy values of 78,19% for 60% data training and 40% data testing, meanwhile for 80% data training and 20% data testing get accuracy 76,94% and SVM kernel linear using K-Fold Cross Validation the highest value of 78,45% at 10 fold Cross-Validation. This algorithm has a lightweight computation as evidenced by a dataset of 580 data which only takes 2.5 seconds. K-Fold Cross Validation is proven to be able to optimize a test that was previously worth 78,19% with K-Fold Cross Validation rising to 78,45%","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123427545","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234267
Novrindah Alvi Hasanah, Luthfi Atikah, D. Herumurti, A. Yunanto
Combining games with learning methods are the most effective way to increase learning motivation, ratification, concentration, and student skills in understanding and solving problems. One of the most popular games is Sudoku. Traditional methods that have used to solve problems in the Sudoku game show a fairly complex solution. So, a good method for solving these problems is needed such as Ant Colony Optimization, which can be used for path searching. This research uses Ant Colony Optimization as a method to find the best path effectively and efficiently to complete the game. Test results used as a benchmark for the Ant Colony Optimization method are better at completing the game by compiling it with traditional methods such as Backtracking. The result of this research shows that Ant Colony Optimization has better performance than Backtracking algorithm. It was proven by 75 trials conducted at three levels of the game resulting in 67 trials (89%) showing Ant Colony Optimization completing the game faster than Backtracking Algorithm.
{"title":"A Comparative Study: Ant Colony Optimization Algorithm and Backtracking Algorithm for Sudoku Game","authors":"Novrindah Alvi Hasanah, Luthfi Atikah, D. Herumurti, A. Yunanto","doi":"10.1109/iSemantic50169.2020.9234267","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234267","url":null,"abstract":"Combining games with learning methods are the most effective way to increase learning motivation, ratification, concentration, and student skills in understanding and solving problems. One of the most popular games is Sudoku. Traditional methods that have used to solve problems in the Sudoku game show a fairly complex solution. So, a good method for solving these problems is needed such as Ant Colony Optimization, which can be used for path searching. This research uses Ant Colony Optimization as a method to find the best path effectively and efficiently to complete the game. Test results used as a benchmark for the Ant Colony Optimization method are better at completing the game by compiling it with traditional methods such as Backtracking. The result of this research shows that Ant Colony Optimization has better performance than Backtracking algorithm. It was proven by 75 trials conducted at three levels of the game resulting in 67 trials (89%) showing Ant Colony Optimization completing the game faster than Backtracking Algorithm.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129862599","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234260
Fakhriyah Prananingrum Pramadi, Christy Atika Sari, E. H. Rachmawanto, De Rosal Ignatius Moses Setiadi
This research proposes a technique to identify flower images based on first order feature extraction and with Multi-Support Vector Machine (Multi-SVM). First-order feature extraction was chosen because it is the extraction of texture features in the macrostructure, which is considered suitable for identifying types of flowers. To perform feature extraction, color space conversion is done from RGB to Grayscale. After all features are extracted, the classification is done by the Multi-SVM classifier. Multi-SVM has the advantage of classifying more than two classes. In this study, five types of flowers were used, namely Calendula, Iris, Leucanthemum maximum, Peony, and Rose. Based on identification testing, the accuracy is 80%.
{"title":"Flowers Identification using First-order Feature Extraction and Multi-SVM Classifier","authors":"Fakhriyah Prananingrum Pramadi, Christy Atika Sari, E. H. Rachmawanto, De Rosal Ignatius Moses Setiadi","doi":"10.1109/iSemantic50169.2020.9234260","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234260","url":null,"abstract":"This research proposes a technique to identify flower images based on first order feature extraction and with Multi-Support Vector Machine (Multi-SVM). First-order feature extraction was chosen because it is the extraction of texture features in the macrostructure, which is considered suitable for identifying types of flowers. To perform feature extraction, color space conversion is done from RGB to Grayscale. After all features are extracted, the classification is done by the Multi-SVM classifier. Multi-SVM has the advantage of classifying more than two classes. In this study, five types of flowers were used, namely Calendula, Iris, Leucanthemum maximum, Peony, and Rose. Based on identification testing, the accuracy is 80%.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120945065","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234198
Suprihadi Suprihadi, Sutarto Wijono, K. Hartomo
Reducing cases The prevalence of tuberculosis (TB) is still a global problem. Indonesia is still in the list of ten countries with high TB burden. This is due to the fact that the management of TB epidemic handling information is still partial, which is managed by each stakeholder, including the ministry of health as a provider of TB patient data, health facilities as a provider of patient care data, and TB non-governmental organizations (NGOs) as providers of accompanying data and information take medicine for patients. In addition, some TB information requires data analysis, while the technology currently used uses Message-Oriented Middleware (MOM) for data and system integration. But MOM cannot meet TB information needs because it depends on the metadata structure. This research tries to offer a new data integration architecture and system as a middleware application that has layers of data analysis from various metadata sources (TB dictionaries). The method used is Service Computing Systems Engineering Life Cycle. The results of this study are a model of data integration architecture and system design called Service-Oriented Middleware (SOM) for managing TB information. The SOM model can also be used as a reference in the integration of data, systems and data analysis modules to provide information services according to the needs of the company's business processes. Thus, each stakeholder involved can obtain complete data and information, as well as patients get a care service system that can help end the TB epidemic.
{"title":"Service Oriented Middleware for Tuberculosis`s Information Services Management","authors":"Suprihadi Suprihadi, Sutarto Wijono, K. Hartomo","doi":"10.1109/iSemantic50169.2020.9234198","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234198","url":null,"abstract":"Reducing cases The prevalence of tuberculosis (TB) is still a global problem. Indonesia is still in the list of ten countries with high TB burden. This is due to the fact that the management of TB epidemic handling information is still partial, which is managed by each stakeholder, including the ministry of health as a provider of TB patient data, health facilities as a provider of patient care data, and TB non-governmental organizations (NGOs) as providers of accompanying data and information take medicine for patients. In addition, some TB information requires data analysis, while the technology currently used uses Message-Oriented Middleware (MOM) for data and system integration. But MOM cannot meet TB information needs because it depends on the metadata structure. This research tries to offer a new data integration architecture and system as a middleware application that has layers of data analysis from various metadata sources (TB dictionaries). The method used is Service Computing Systems Engineering Life Cycle. The results of this study are a model of data integration architecture and system design called Service-Oriented Middleware (SOM) for managing TB information. The SOM model can also be used as a reference in the integration of data, systems and data analysis modules to provide information services according to the needs of the company's business processes. Thus, each stakeholder involved can obtain complete data and information, as well as patients get a care service system that can help end the TB epidemic.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126348483","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234208
Muhammad Fatkhur Rizal, R. Sarno, S. Sabilla
The use of the computer answer sheet media as a medium for writing answers has now become a necessity, this is because the computer answer sheet media is considered to be very easy and fast in the correction process. Some research and implementation applied in solving cases of correction computer answer sheet with various methods, but the use of inappropriate methods will affect the results that are less than the maximum in detecting. Some use the detection of circles which are not precise so that it has the potential to detect answers that should not be detected with clearly. This study propose Canny and Hough circle transformation method for enhanced by calculating the distance between answers to increase accuracy by 95.75%. This can be used as a basic method in making detection devices.
{"title":"Canny Edge and Hough Circle Transformation for Detecting Computer Answer Sheets","authors":"Muhammad Fatkhur Rizal, R. Sarno, S. Sabilla","doi":"10.1109/iSemantic50169.2020.9234208","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234208","url":null,"abstract":"The use of the computer answer sheet media as a medium for writing answers has now become a necessity, this is because the computer answer sheet media is considered to be very easy and fast in the correction process. Some research and implementation applied in solving cases of correction computer answer sheet with various methods, but the use of inappropriate methods will affect the results that are less than the maximum in detecting. Some use the detection of circles which are not precise so that it has the potential to detect answers that should not be detected with clearly. This study propose Canny and Hough circle transformation method for enhanced by calculating the distance between answers to increase accuracy by 95.75%. This can be used as a basic method in making detection devices.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127138031","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 : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234223
Robert Setyawan, Riris Bayu Asrori, Guruh Fajar Shidik, A. Z. Fanani, Ricardus Anggi Premunendar
Brain tumors segmentation has become a popular research topic in the last five years, proved by the emergence of many methods proposed to segment brain tumors accurately. In this study, the authors propose a brain tumor segmentation method based on the FCM method with a modification of the threshold value, which will later be used to convert an MRI image to a binary image with only the tumor area detected. The segmentation process divided into three stages, with steps is preprocessing segmentation and post-processing. In the preprocessing stage, the skull bones from MRI images are removed, then the noise is removed using Wiener filters, then proceed with the segmentation stage using FCM Thresh, and finally applying morphological area selection to select areas from segmentation results. From a total of 100 positive tumor MRI images that we acquire from the BRATS 2015 dataset, we obtained an average similarity of 0.7592. We achieved an improvement of 0.06 in term of SSIM value from the previous method.
{"title":"Brain Tumor Identification using FCM Threshold Method and Morphological Area Selection","authors":"Robert Setyawan, Riris Bayu Asrori, Guruh Fajar Shidik, A. Z. Fanani, Ricardus Anggi Premunendar","doi":"10.1109/iSemantic50169.2020.9234223","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234223","url":null,"abstract":"Brain tumors segmentation has become a popular research topic in the last five years, proved by the emergence of many methods proposed to segment brain tumors accurately. In this study, the authors propose a brain tumor segmentation method based on the FCM method with a modification of the threshold value, which will later be used to convert an MRI image to a binary image with only the tumor area detected. The segmentation process divided into three stages, with steps is preprocessing segmentation and post-processing. In the preprocessing stage, the skull bones from MRI images are removed, then the noise is removed using Wiener filters, then proceed with the segmentation stage using FCM Thresh, and finally applying morphological area selection to select areas from segmentation results. From a total of 100 positive tumor MRI images that we acquire from the BRATS 2015 dataset, we obtained an average similarity of 0.7592. We achieved an improvement of 0.06 in term of SSIM value from the previous method.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126677552","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：