Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288515
Sandy Kurniawan, I. Budi
In recent years, hate speech found in social media is increasing. The increase in the number of hate speech is caused by the increasing number of social media active users around the world. A lot of hate speech is aimed at governments or certain individuals. Hate speech is very harmful because it may affect the target negatively, whether the target is individuals or groups. Identification of targets in hate speech is crucial as it can be used to prevent the impact of hate speech such as exclusion, discrimination, and violence directed to the target in the hate speech. In this paper, we present our study in hate speech target classification in Indonesian Twitter. We studied hate speech target classification on Indonesian Twitter by comparing the classification performance based on the algorithms and feature representations used. Word n-grams were used as the feature representation combine with Bag-of-Words and Term Frequency - Inverse Document Frequency (TF-IDF). The classification was performed using Naive Bayes, Support Vector Machine (SVM), and Random Forest Decision Tree (RFDT). The best result achieved F1-score of 0.84772 when using TF-IDF with word unigram features combine with SVM classifier.
{"title":"Indonesian Tweets Hate Speech Target Classification using Machine Learning","authors":"Sandy Kurniawan, I. Budi","doi":"10.1109/ICIC50835.2020.9288515","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288515","url":null,"abstract":"In recent years, hate speech found in social media is increasing. The increase in the number of hate speech is caused by the increasing number of social media active users around the world. A lot of hate speech is aimed at governments or certain individuals. Hate speech is very harmful because it may affect the target negatively, whether the target is individuals or groups. Identification of targets in hate speech is crucial as it can be used to prevent the impact of hate speech such as exclusion, discrimination, and violence directed to the target in the hate speech. In this paper, we present our study in hate speech target classification in Indonesian Twitter. We studied hate speech target classification on Indonesian Twitter by comparing the classification performance based on the algorithms and feature representations used. Word n-grams were used as the feature representation combine with Bag-of-Words and Term Frequency - Inverse Document Frequency (TF-IDF). The classification was performed using Naive Bayes, Support Vector Machine (SVM), and Random Forest Decision Tree (RFDT). The best result achieved F1-score of 0.84772 when using TF-IDF with word unigram features combine with SVM classifier.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125527284","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288562
Peter Liuwandy, Suryasari, Wella
Earthquake is one of the natural disasters that often occurs in Indonesia. Recorded data from 1779 to 2010, earthquakes that occurred in Indonesia were more than 48,000 with strength greater than four on the Richter Scale. Therefore, earthquake simulations are carried out in offices such as schools, offices, and so on. This research focuses on using virtual reality as an earthquake simulation drill to give a better experience to the user. This research also tries to reach as many people as possible so that it's built on Android and doesn't need any additional tools, just VR glasses, with the help of Google VR prefab. The results show that the earthquake simulation drill through virtual reality is more familiar and save time than the traditional earthquake simulation drill used by the comprehensive institution.
{"title":"Affordable Mobile Virtual Reality Earthquake Simulation","authors":"Peter Liuwandy, Suryasari, Wella","doi":"10.1109/ICIC50835.2020.9288562","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288562","url":null,"abstract":"Earthquake is one of the natural disasters that often occurs in Indonesia. Recorded data from 1779 to 2010, earthquakes that occurred in Indonesia were more than 48,000 with strength greater than four on the Richter Scale. Therefore, earthquake simulations are carried out in offices such as schools, offices, and so on. This research focuses on using virtual reality as an earthquake simulation drill to give a better experience to the user. This research also tries to reach as many people as possible so that it's built on Android and doesn't need any additional tools, just VR glasses, with the help of Google VR prefab. The results show that the earthquake simulation drill through virtual reality is more familiar and save time than the traditional earthquake simulation drill used by the comprehensive institution.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"310 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132703356","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288560
Lutfiah Zahara, Purnawarman Musa, Eri Prasetyo Wibowo, Irwan Karim, Saiful Bahri Musa
One of the ways humans communicate is by using facial expressions. Research on technology development in artificial intelligence uses deep learning methods in human and computer interactions as an effective system application process. One example, if someone does show and tries to recognize facial expressions when communicating. The prediction of the expression or emotion of some people who see it sometimes does not understand. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. This research proposes the design of a system that can predict and recognize the classification of facial emotions based on feature extraction using the Convolution Neural Network (CNN) algorithm in real-time with the OpenCV library, namely: TensorFlow and Keras. The research design implemented in the Raspberry Pi consists of three main processes, namely: face detection, facial feature extraction, and facial emotion classification. The prediction results of facial expressions in research with the Convolutional Neural Network (CNN) method using Facial Emotion Recognition (FER-2013) were 65.97% (sixty-five point ninety-seven percent)
{"title":"The Facial Emotion Recognition (FER-2013) Dataset for Prediction System of Micro-Expressions Face Using the Convolutional Neural Network (CNN) Algorithm based Raspberry Pi","authors":"Lutfiah Zahara, Purnawarman Musa, Eri Prasetyo Wibowo, Irwan Karim, Saiful Bahri Musa","doi":"10.1109/ICIC50835.2020.9288560","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288560","url":null,"abstract":"One of the ways humans communicate is by using facial expressions. Research on technology development in artificial intelligence uses deep learning methods in human and computer interactions as an effective system application process. One example, if someone does show and tries to recognize facial expressions when communicating. The prediction of the expression or emotion of some people who see it sometimes does not understand. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. This research proposes the design of a system that can predict and recognize the classification of facial emotions based on feature extraction using the Convolution Neural Network (CNN) algorithm in real-time with the OpenCV library, namely: TensorFlow and Keras. The research design implemented in the Raspberry Pi consists of three main processes, namely: face detection, facial feature extraction, and facial emotion classification. The prediction results of facial expressions in research with the Convolutional Neural Network (CNN) method using Facial Emotion Recognition (FER-2013) were 65.97% (sixty-five point ninety-seven percent)","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115783975","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288607
Herlawati Herlawati, Rahmadya Trias Handayanto, Inna Ekawati, K. Meutia, J. Asian, Umar Aditiawarman
Social media (Facebook, Instagram, Twitter, etc.) have been widely used. They have many advantages, especially for business. However, such media sometimes invite negative effects, e.g. decreasing employee performance, conflict in a relationship, crime, etc. Therefore, this study proposes a method to scrap one of the social media, i.e. Twitter for profiling. Gephi application is used for network analysis after scrapping the network using Twecoll, a Python-based scrapping application. A web-based application is also created including the Apache-based server and Python-based script. The result shows that the scrapped account has several groups/communities including the weight of each connection. In addition, the result can be used for group profiling and additional analysis to complete the sentiment analysis based on tweets.
{"title":"Twitter Scrapping for Profiling Education Staff","authors":"Herlawati Herlawati, Rahmadya Trias Handayanto, Inna Ekawati, K. Meutia, J. Asian, Umar Aditiawarman","doi":"10.1109/ICIC50835.2020.9288607","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288607","url":null,"abstract":"Social media (Facebook, Instagram, Twitter, etc.) have been widely used. They have many advantages, especially for business. However, such media sometimes invite negative effects, e.g. decreasing employee performance, conflict in a relationship, crime, etc. Therefore, this study proposes a method to scrap one of the social media, i.e. Twitter for profiling. Gephi application is used for network analysis after scrapping the network using Twecoll, a Python-based scrapping application. A web-based application is also created including the Apache-based server and Python-based script. The result shows that the scrapped account has several groups/communities including the weight of each connection. In addition, the result can be used for group profiling and additional analysis to complete the sentiment analysis based on tweets.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130427248","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288548
Adyanissa Farsya Kirana, F. Azzahro, Putu Wuri Handayani, Widia Resti Fitriani
As the most generous country, Indonesia embedded altruism as their lifestyle. However, the donation that is often made conventionally now has been shifted to online donation. Online donation platform such as Kitabisa.com has significant users growths in recent years. Along with the increasing number of online donations, many fraud cases occurred which harm users' trust in online donation platforms. Thus, this study aims to examine the institutional mechanism and information systems success factors that influence trust and distrust in the online donation platform and how it influences attitude and online donation intention. We collected 865 data using an online survey and then analyzed it using Partial Least Square - Structural Equation Modeling (PLS-SEM). The result of this study indicates that quality aspects such as system quality, information quality, and institutional mechanism aspects such as perceived platform rules and perceived monitoring influence trust and distrust in online donation platforms. Additionally, trust and distrust in online donation platforms influence attitude towards donation and online donation intention significantly.
{"title":"Trust and Distrust: The Antecedents of Intention to Donate in Digital Donation Platform","authors":"Adyanissa Farsya Kirana, F. Azzahro, Putu Wuri Handayani, Widia Resti Fitriani","doi":"10.1109/ICIC50835.2020.9288548","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288548","url":null,"abstract":"As the most generous country, Indonesia embedded altruism as their lifestyle. However, the donation that is often made conventionally now has been shifted to online donation. Online donation platform such as Kitabisa.com has significant users growths in recent years. Along with the increasing number of online donations, many fraud cases occurred which harm users' trust in online donation platforms. Thus, this study aims to examine the institutional mechanism and information systems success factors that influence trust and distrust in the online donation platform and how it influences attitude and online donation intention. We collected 865 data using an online survey and then analyzed it using Partial Least Square - Structural Equation Modeling (PLS-SEM). The result of this study indicates that quality aspects such as system quality, information quality, and institutional mechanism aspects such as perceived platform rules and perceived monitoring influence trust and distrust in online donation platforms. Additionally, trust and distrust in online donation platforms influence attitude towards donation and online donation intention significantly.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775155","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288565
Zen Munawar, N. Suryana, Zurina Binti Sa'aya, Yudi Herdiana
This research is a framework with an approach to the user as an evaluation for the recommendation system. Prediction algorithm can provide accuracy to the recommendation system. The recommendation system strongly influences user experience in the recommendation system. The relationship between objective system aspects and user behavior is carried out with a framework based on a collection of perceptions and evaluations with various aspects of subjective experience through personal and situational characteristics of user experiences. This research is also supported by related literature in mapping the framework. In this way, the framework can be validated. Analysis of Field trials and experiments with structural equation modeling. The results showed that the subjective system aspects and user experience could provide an explanation of why and how the user experience emerges from the recommendation system. Perceived quality and variation of recommendations are important mediators in predicting objective system aspects of user experience components such as perceived processes or difficulties, systems in the form of perceived system effectiveness, results in the form of choice of satisfaction. This study also found that there was a correlation of behavior from subjective aspects such as a lack of search results, this shows the results of the effectiveness of the system. There is a relationship between aspects of the system with personal and situational characteristics indicated by the number of feedback preferences from users in exchange for system usability and user privacy.
{"title":"Framework With An Approach To The User As An Evaluation For The Recommender Systems","authors":"Zen Munawar, N. Suryana, Zurina Binti Sa'aya, Yudi Herdiana","doi":"10.1109/ICIC50835.2020.9288565","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288565","url":null,"abstract":"This research is a framework with an approach to the user as an evaluation for the recommendation system. Prediction algorithm can provide accuracy to the recommendation system. The recommendation system strongly influences user experience in the recommendation system. The relationship between objective system aspects and user behavior is carried out with a framework based on a collection of perceptions and evaluations with various aspects of subjective experience through personal and situational characteristics of user experiences. This research is also supported by related literature in mapping the framework. In this way, the framework can be validated. Analysis of Field trials and experiments with structural equation modeling. The results showed that the subjective system aspects and user experience could provide an explanation of why and how the user experience emerges from the recommendation system. Perceived quality and variation of recommendations are important mediators in predicting objective system aspects of user experience components such as perceived processes or difficulties, systems in the form of perceived system effectiveness, results in the form of choice of satisfaction. This study also found that there was a correlation of behavior from subjective aspects such as a lack of search results, this shows the results of the effectiveness of the system. There is a relationship between aspects of the system with personal and situational characteristics indicated by the number of feedback preferences from users in exchange for system usability and user privacy.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127693047","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288558
Ni Made Satvika Iswari, E. K. Budiardjo, Z. Hasibuan
Software Product Line Engineering (SPLE) allows developers to build product family software that comes from the same platform. The advantage of this technique is to reduce construction time, effort, costs, and difficulties. So, to build variations of software products, developers do not need to build entirely from scratch and can take advantage of general models that have been prepared previously. The software product line consists of common features and variability features. Common features are found on all product lines produced. While the variability features are determined by the requirements of each user. There are several approaches to implement these variability features, including using patterns, framework, polymorphism or configuration and build tools with compile-time variables. In this study, variability features implementation is carried out using the Aspect-Oriented Programming approach that allows explicit expression and modularization of the variability on a model, code, and generator levels. The proposed approach was implemented in an online store website. Based on the implementation that has been done, an online store website can be built with different features according to user requirements.
{"title":"Aspect Oriented Programming Approach for Variability Feature Implementation in Software Product Line Engineering","authors":"Ni Made Satvika Iswari, E. K. Budiardjo, Z. Hasibuan","doi":"10.1109/ICIC50835.2020.9288558","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288558","url":null,"abstract":"Software Product Line Engineering (SPLE) allows developers to build product family software that comes from the same platform. The advantage of this technique is to reduce construction time, effort, costs, and difficulties. So, to build variations of software products, developers do not need to build entirely from scratch and can take advantage of general models that have been prepared previously. The software product line consists of common features and variability features. Common features are found on all product lines produced. While the variability features are determined by the requirements of each user. There are several approaches to implement these variability features, including using patterns, framework, polymorphism or configuration and build tools with compile-time variables. In this study, variability features implementation is carried out using the Aspect-Oriented Programming approach that allows explicit expression and modularization of the variability on a model, code, and generator levels. The proposed approach was implemented in an online store website. Based on the implementation that has been done, an online store website can be built with different features according to user requirements.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133145951","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288657
G. Karya, W. Sunindyo, B. Sitohang, Saiful Akbar, Adi Mulyanto
The use of big-data analysis in elections in Indonesia has been started since the Governor Election of DKI-Jakarta in 2012 until the Presidential Election in 2019. However, its use is limited to using analytical sentiment to map support and predict election results using social-media data. We see that there is a great opportunity to use big data for a broader election, which is to facilitate the fulfillment of the information and analysis needs of all election stakeholders. But the main problem in using big-data is the integration of big data from various sources with a variety of different formats and large volumes, in addition to the issues of analysis and visualization. For this reason, in this paper, we propose a big-data integration design to meet the needs of elections in Indonesia. This big-data integration design was developed based on election regulations in Indonesia, knowledge of big-data, and the use of a NoSQL database to store unstructured data. The election big-data integration design that we propose includes (1) the information needs of each election stakeholder; (2) the potential for big-data in fulfilling the information needs of every election stakeholder; (3) big-data analysis architecture for elections; (4) big-data integration architecture for elections; (5) crawler architecture; and (5) technology architecture that can implement big-data integration design for elections. Currently, the implementation of this design is in progress in the P3MI-ITB research project.
{"title":"Big Data Integration Design for General Election in Indonesia","authors":"G. Karya, W. Sunindyo, B. Sitohang, Saiful Akbar, Adi Mulyanto","doi":"10.1109/ICIC50835.2020.9288657","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288657","url":null,"abstract":"The use of big-data analysis in elections in Indonesia has been started since the Governor Election of DKI-Jakarta in 2012 until the Presidential Election in 2019. However, its use is limited to using analytical sentiment to map support and predict election results using social-media data. We see that there is a great opportunity to use big data for a broader election, which is to facilitate the fulfillment of the information and analysis needs of all election stakeholders. But the main problem in using big-data is the integration of big data from various sources with a variety of different formats and large volumes, in addition to the issues of analysis and visualization. For this reason, in this paper, we propose a big-data integration design to meet the needs of elections in Indonesia. This big-data integration design was developed based on election regulations in Indonesia, knowledge of big-data, and the use of a NoSQL database to store unstructured data. The election big-data integration design that we propose includes (1) the information needs of each election stakeholder; (2) the potential for big-data in fulfilling the information needs of every election stakeholder; (3) big-data analysis architecture for elections; (4) big-data integration architecture for elections; (5) crawler architecture; and (5) technology architecture that can implement big-data integration design for elections. Currently, the implementation of this design is in progress in the P3MI-ITB research project.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114554557","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288599
C. Tania, Wella, Y. Soelistio
Gabor filter as a prominent filter approach ever done in a digital audio signal to find cultural diffusion patterns in Indonesia by analyzing folk songs. The topic is interesting and rarely discussed, but unfortunately, several weaknesses still exist in the research, which are the folk songs used is biased, one of the primary theoretical basis is invalid, and the most unfortunate is the sourcebook of the dataset does not have International Standard Book Number, which means the book is unregistered. Therefore, by using identical methods (Gabor filtration), the present research would perform some development from the lack of prior research to get better results. This research specified the testing area to improve focus - which is only used provinces in Java Island folk songs, used a valid dataset source, and added several different spectrogram sizes to improve accuracy. Compared to previous, recent research hit better results since it has more significant features and directly proportional relations than before.
{"title":"Gabor Filter Methods to Analyze the Influence of Geographic Distance and Folk Song in Java Indonesia","authors":"C. Tania, Wella, Y. Soelistio","doi":"10.1109/ICIC50835.2020.9288599","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288599","url":null,"abstract":"Gabor filter as a prominent filter approach ever done in a digital audio signal to find cultural diffusion patterns in Indonesia by analyzing folk songs. The topic is interesting and rarely discussed, but unfortunately, several weaknesses still exist in the research, which are the folk songs used is biased, one of the primary theoretical basis is invalid, and the most unfortunate is the sourcebook of the dataset does not have International Standard Book Number, which means the book is unregistered. Therefore, by using identical methods (Gabor filtration), the present research would perform some development from the lack of prior research to get better results. This research specified the testing area to improve focus - which is only used provinces in Java Island folk songs, used a valid dataset source, and added several different spectrogram sizes to improve accuracy. Compared to previous, recent research hit better results since it has more significant features and directly proportional relations than before.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124280121","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 : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288648
S. Saifullah
Image segmentation is often used in the process of detecting separated objects. In this study, the application of image segmentation in the detection of egg fertility. The fertility of eggs in hatching is checked between the seventh day to separate eggs that have embryos (fertile). Application of technology, one of which is image processing, requires a preprocessing process to detect the presence of embryos in eggs. In this research, the preprocessing process can help divide the color image of chicken eggs using K-means Algorithm. K-means used are based on a matrix of color images (three color components, red, green, and blue) with a value of k = 50. The result is a segmented color image. The K-means segmentation image is converted to a grayscale image and processed with image enhancement. The final process is the result of image enhancement morphological processes (dilated with string size six) and converted to black and white images to clarify the segmentation process occurs. Based on experiments, the process can run well, with the value of MSSIM = 0.9995 (Mean of the SSIM), which means that the image information is under the original image. Besides, the processed object gives a clear picture of the embryo in the egg, which shows that k-means segmentation can help the process of detecting the presence or absence of embryos in the egg.
{"title":"Segmentation for embryonated Egg Images Detection using the K-Means Algorithm in Image Processing","authors":"S. Saifullah","doi":"10.1109/ICIC50835.2020.9288648","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288648","url":null,"abstract":"Image segmentation is often used in the process of detecting separated objects. In this study, the application of image segmentation in the detection of egg fertility. The fertility of eggs in hatching is checked between the seventh day to separate eggs that have embryos (fertile). Application of technology, one of which is image processing, requires a preprocessing process to detect the presence of embryos in eggs. In this research, the preprocessing process can help divide the color image of chicken eggs using K-means Algorithm. K-means used are based on a matrix of color images (three color components, red, green, and blue) with a value of k = 50. The result is a segmented color image. The K-means segmentation image is converted to a grayscale image and processed with image enhancement. The final process is the result of image enhancement morphological processes (dilated with string size six) and converted to black and white images to clarify the segmentation process occurs. Based on experiments, the process can run well, with the value of MSSIM = 0.9995 (Mean of the SSIM), which means that the image information is under the original image. Besides, the processed object gives a clear picture of the embryo in the egg, which shows that k-means segmentation can help the process of detecting the presence or absence of embryos in the egg.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125200954","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：