Pub Date : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127743
Muhammad Zulfikar Fauzi, R. Sarno, S. Hidayati
In this study, a sign language-to-speech system was developed to recognize and convert BISINDO's sign language into speech using a machine learning approach. The speech output will make it easier for the user to communicate with the other person and will make it easier for the other person to understand sign language and will improve the quality of communication. Using the dataset produced in this study and Mediapipe for feature extraction, the model accuracy was able to obtain a score of 98% using the Support Vector Machine method. However, the accuracy score of the model decreased drastically reaching 78% in trials conducted directly on users because the testing exceeded the system effective range. The results of the implementation of Sign Language-to-Speech succeeded in producing an output in form of audio speech without using an internet connection. The system was able to detect both dynamic and static gesture from the user in real-time.
{"title":"Recognition of Real-Time BISINDO Sign Language-to-Speech using Machine Learning Methods","authors":"Muhammad Zulfikar Fauzi, R. Sarno, S. Hidayati","doi":"10.1109/ICCoSITE57641.2023.10127743","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127743","url":null,"abstract":"In this study, a sign language-to-speech system was developed to recognize and convert BISINDO's sign language into speech using a machine learning approach. The speech output will make it easier for the user to communicate with the other person and will make it easier for the other person to understand sign language and will improve the quality of communication. Using the dataset produced in this study and Mediapipe for feature extraction, the model accuracy was able to obtain a score of 98% using the Support Vector Machine method. However, the accuracy score of the model decreased drastically reaching 78% in trials conducted directly on users because the testing exceeded the system effective range. The results of the implementation of Sign Language-to-Speech succeeded in producing an output in form of audio speech without using an internet connection. The system was able to detect both dynamic and static gesture from the user in real-time.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122316055","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127799
A. Firmansyah, T. F. Kusumasari, E. N. Alam
Face recognition is one of the biometric-based authentication methods known for its reliability. In addition, face recognition is also currently very concerning, especially with the growing use and available technology. Many frameworks can be used for the face recognition process, one of which is DeepFace. DeepFace has many models and detectors that can be used for face recognition with an accuracy above 93%. However, the accuracy obtained needs to be tested, especially when faced with a dataset of Indonesian faces. This research will discuss the accuracy comparison of the Facenet model, Facenet512, from ArcFace, available in the DeepFace framework. From the comparison results, it is obtained that Facenet512 has a high value in accuracy calculation which is 0.974 or 97.4%, compared to Facenet, which has an accuracy of 0.921 or 92.1%, and ArcFace, which has an accuracy of 0.878 or 87.8%. The benefit of this research is to test how high the accuracy of the existing model in DeepFace is if tested with the Indonesian dataset. In this test, Facenet512 is the model that has the highest accuracy when compared to ArcFace and Facenet. This research is expected to help DeepFace users determine the best model to use and provide references to DeepFace developers for future development.
{"title":"Comparison of Face Recognition Accuracy of ArcFace, Facenet and Facenet512 Models on Deepface Framework","authors":"A. Firmansyah, T. F. Kusumasari, E. N. Alam","doi":"10.1109/ICCoSITE57641.2023.10127799","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127799","url":null,"abstract":"Face recognition is one of the biometric-based authentication methods known for its reliability. In addition, face recognition is also currently very concerning, especially with the growing use and available technology. Many frameworks can be used for the face recognition process, one of which is DeepFace. DeepFace has many models and detectors that can be used for face recognition with an accuracy above 93%. However, the accuracy obtained needs to be tested, especially when faced with a dataset of Indonesian faces. This research will discuss the accuracy comparison of the Facenet model, Facenet512, from ArcFace, available in the DeepFace framework. From the comparison results, it is obtained that Facenet512 has a high value in accuracy calculation which is 0.974 or 97.4%, compared to Facenet, which has an accuracy of 0.921 or 92.1%, and ArcFace, which has an accuracy of 0.878 or 87.8%. The benefit of this research is to test how high the accuracy of the existing model in DeepFace is if tested with the Indonesian dataset. In this test, Facenet512 is the model that has the highest accuracy when compared to ArcFace and Facenet. This research is expected to help DeepFace users determine the best model to use and provide references to DeepFace developers for future development.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116498131","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127774
D. Purwitasari, D. A. Navastara, Y. Findawati, Kresna Adhi Pramana, Agus Budi Raharjo
Dangerous speech is a strong hate speech that causes negative impacts, such as violence, crime, social pressure, trauma, and despair, and can lead to conflicts between groups. Raw data of Twitter texts need the necessary preprocess to obtain the proper training datasets for hate speech or even dangerous one. One reason is how to express hate speech related to mentions or hashtags. Because of the variants of context messages in raw Twitter posts which could be hate speech or not, the problem here is hierarchical and multi-label classification with three label types of hate speech status, issues, and dangerous levels. The issues in this work are about religion, ethnicity, and others. After handling preprocess, the word embedding includes data under-sampling because the dataset is not balanced. Additional stop-word dictionaries to overcome language-related vocabularies are also incorporated. To observe the preprocess effects in the classification problem, some methods of machine learning and deep learning, such as SVM, Bi-LSTM, and BERT are explored. Then we examined after hyper-parameter settings with performance indicators of subset accuracy and Hamming lost for imbalanced, in addition to F1 scores of micro and macro averages.
{"title":"Feature Extraction in Hierarchical Multi-Label Classification for Dangerous Speech Identification on Twitter Texts","authors":"D. Purwitasari, D. A. Navastara, Y. Findawati, Kresna Adhi Pramana, Agus Budi Raharjo","doi":"10.1109/ICCoSITE57641.2023.10127774","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127774","url":null,"abstract":"Dangerous speech is a strong hate speech that causes negative impacts, such as violence, crime, social pressure, trauma, and despair, and can lead to conflicts between groups. Raw data of Twitter texts need the necessary preprocess to obtain the proper training datasets for hate speech or even dangerous one. One reason is how to express hate speech related to mentions or hashtags. Because of the variants of context messages in raw Twitter posts which could be hate speech or not, the problem here is hierarchical and multi-label classification with three label types of hate speech status, issues, and dangerous levels. The issues in this work are about religion, ethnicity, and others. After handling preprocess, the word embedding includes data under-sampling because the dataset is not balanced. Additional stop-word dictionaries to overcome language-related vocabularies are also incorporated. To observe the preprocess effects in the classification problem, some methods of machine learning and deep learning, such as SVM, Bi-LSTM, and BERT are explored. Then we examined after hyper-parameter settings with performance indicators of subset accuracy and Hamming lost for imbalanced, in addition to F1 scores of micro and macro averages.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115326834","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127829
Ni Wayan Parwati Septiani, Hendy Agung Setiawan, Mei Lestari, Irwan Agus, Rayung Wulan, A. Irawan, Sutrisno
In Indonesia, batik was not popular among all socio-economic groups until the 20th century. Recently, batik has been considered an essential part of Indonesian culture and heritage. Geometric batik patterns are recognized by their symmetry, horizontal repetition, and vertical and diagonal angles between shapes. Sade is one village located south of Lombok island. Woven fabrics typical of Sade Village have distinctive motifs that differ from those of Sukarara Village, Central Lombok. Sade's batik mostly has geometric patterns that are almost similar. There are 5 motifs in Sade, namely Selolot, kembang komak, tapok kamalo, ragi genep and batang empat. The Sade village’s economy, which mostly relied on the sales of its fabric production, has been placed under an enormous burden by the COVID-19 pandemic. There must be a new and creative way in order to sustain its market penetration. One possible approach is by linking the community of Sade village fabric producers to the nationwide established marketplace. We propose an ML-based mobile web application that is supposed to be used by ordinary users, not only the tourists who visited Sade village. This mobile web main feature is to do the image classification of the aforementioned motifs and to provide a list of Sade village fabric sellers on the marketplace so that interested users may purchase the product. Models were created using the CNN algorithm to classify batik-sade images. CNN is one frequently used deep learning algorithm for image classification. Image datasets consist of training, testing, and validation datasets. The training datasets contain 2398 photos, while the testing and validation datasets each have 480 data. Ten epochs of experimental data revealed that the suggested CNN model has a training loss of 0.0560 and a training accuracy of 0.9805.
在印度尼西亚，直到20世纪，蜡染才在所有社会经济群体中流行起来。最近，蜡染被认为是印尼文化和遗产的重要组成部分。几何蜡染图案是通过它们的对称、水平重复以及形状之间的垂直和对角角来识别的。萨德是位于龙目岛南部的一个村庄。Sade村典型的梭织织物具有与龙目岛中部Sukarara村不同的独特图案。萨德的蜡染大多有几乎相似的几何图案。沙德有5个主题，分别是Selolot, kembang komak, tapok kamalo, ragi genep和batang empat。萨德村的经济主要依赖于面料的销售，新冠肺炎疫情给该村庄带来了巨大的负担。必须有一个新的和创造性的方式来维持它的市场渗透。一种可能的方法是将Sade村的织物生产商社区与全国范围内建立的市场联系起来。我们提出了一个基于ml的移动web应用程序，它应该被普通用户使用，而不仅仅是访问Sade村的游客。这个移动网站的主要功能是对上述图案进行图像分类，并提供市场上萨德村面料卖家的列表，以便感兴趣的用户可以购买产品。使用CNN算法创建模型对蜡染色图像进行分类。CNN是一种常用的深度学习图像分类算法。图像数据集包括训练、测试和验证数据集。训练数据集包含2398张照片，而测试和验证数据集各有480张照片。10个epoch的实验数据表明，本文提出的CNN模型的训练损失为0.0560，训练精度为0.9805。
{"title":"Convolutional Neural Network (CNN) Algorithm for Geometrical Batik Sade’ Motifs","authors":"Ni Wayan Parwati Septiani, Hendy Agung Setiawan, Mei Lestari, Irwan Agus, Rayung Wulan, A. Irawan, Sutrisno","doi":"10.1109/ICCoSITE57641.2023.10127829","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127829","url":null,"abstract":"In Indonesia, batik was not popular among all socio-economic groups until the 20th century. Recently, batik has been considered an essential part of Indonesian culture and heritage. Geometric batik patterns are recognized by their symmetry, horizontal repetition, and vertical and diagonal angles between shapes. Sade is one village located south of Lombok island. Woven fabrics typical of Sade Village have distinctive motifs that differ from those of Sukarara Village, Central Lombok. Sade's batik mostly has geometric patterns that are almost similar. There are 5 motifs in Sade, namely Selolot, kembang komak, tapok kamalo, ragi genep and batang empat. The Sade village’s economy, which mostly relied on the sales of its fabric production, has been placed under an enormous burden by the COVID-19 pandemic. There must be a new and creative way in order to sustain its market penetration. One possible approach is by linking the community of Sade village fabric producers to the nationwide established marketplace. We propose an ML-based mobile web application that is supposed to be used by ordinary users, not only the tourists who visited Sade village. This mobile web main feature is to do the image classification of the aforementioned motifs and to provide a list of Sade village fabric sellers on the marketplace so that interested users may purchase the product. Models were created using the CNN algorithm to classify batik-sade images. CNN is one frequently used deep learning algorithm for image classification. Image datasets consist of training, testing, and validation datasets. The training datasets contain 2398 photos, while the testing and validation datasets each have 480 data. Ten epochs of experimental data revealed that the suggested CNN model has a training loss of 0.0560 and a training accuracy of 0.9805.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123335197","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127838
Ghadeer Ismail Khalil, Hafsa Mohammad Sajjad, Manal Sohail, Zahra Ishfaq
Machines can learn through experience, adapt to new input information, and carry out the necessary human-like duties thanks to artificial intelligence (AI). AI adaptation in the education industry has become more significant. This research aimed to determine the role of Artificial Intelligence (AI) on education in the Kingdom of Bahrain from a student-teacher perspective and examine its factors by adapting Technology Acceptance Model (TAM). To fulfil the objectives of this research, efficiency and convenience of implementing AI within education has been examined to further investigate the challenges faced by students and educators. A quantitative and qualitative approach was used to gather data from the universities in Bahrain, with a sample size of 383 determined by the Stratified Sampling method and Purposive Sampling. The analysis of the responses to the conducted survey resulted in a total of 501 responses. The results analysis revealed that both students and instructors believe security and privacy issues to be the most prevalent obstacle to the use of AI in education. Although AI tools and applications cover most of the ethical aspects, data privacy and security issues remain to be important concerns for users. Furthermore, both students and instructors agree that AI supports self- dependent learning, but it might be complex to use without a set of skills and some experience. In addition, the main limitation was the time consumed in collecting data. The research suggests methods to improve the results and overcome future challenges.
{"title":"Role of AI in the Education Sector in the Kingdom of Bahrain","authors":"Ghadeer Ismail Khalil, Hafsa Mohammad Sajjad, Manal Sohail, Zahra Ishfaq","doi":"10.1109/ICCoSITE57641.2023.10127838","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127838","url":null,"abstract":"Machines can learn through experience, adapt to new input information, and carry out the necessary human-like duties thanks to artificial intelligence (AI). AI adaptation in the education industry has become more significant. This research aimed to determine the role of Artificial Intelligence (AI) on education in the Kingdom of Bahrain from a student-teacher perspective and examine its factors by adapting Technology Acceptance Model (TAM). To fulfil the objectives of this research, efficiency and convenience of implementing AI within education has been examined to further investigate the challenges faced by students and educators. A quantitative and qualitative approach was used to gather data from the universities in Bahrain, with a sample size of 383 determined by the Stratified Sampling method and Purposive Sampling. The analysis of the responses to the conducted survey resulted in a total of 501 responses. The results analysis revealed that both students and instructors believe security and privacy issues to be the most prevalent obstacle to the use of AI in education. Although AI tools and applications cover most of the ethical aspects, data privacy and security issues remain to be important concerns for users. Furthermore, both students and instructors agree that AI supports self- dependent learning, but it might be complex to use without a set of skills and some experience. In addition, the main limitation was the time consumed in collecting data. The research suggests methods to improve the results and overcome future challenges.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"40 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123737592","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127706
Farrel Rasyad, Hardi Andry Kongguasa, Nicholas Christandy Onggususilo, Anderies, Afdhal Kurniawan, A. A. Gunawan
Humans have studied calligraphy and calculated programs to foster creativity for years. Image generation technology using artificial intelligence and Generative Adversarial Networks is currently reaching the peak of its performance. While there are newer and newer algorithms to improve the image generation system, the output of the images is still suitable at best and only excels in their category. While it is true that some of the images generated are good enough to be used, it is still unclear whether the capabilities of AI image generation can outperform their creative human counterparts. Therefore, this literature study aims to explore the basics of AI image generation, how they work, and what factors contribute to creating art such as simple pictures. Previous studies from several years ago show that most generated images are not good enough for creative usage because they only replicate traces of their dataset. The most significant factor contributing to this is the algorithm used and how it is used to create new images. In general, the concluded that while current AI-generated images are improving, they are still not creative enough to replace human creativity.
{"title":"A Systematic Literature Review of Generative Adversarial Network Potential In AI Artwork","authors":"Farrel Rasyad, Hardi Andry Kongguasa, Nicholas Christandy Onggususilo, Anderies, Afdhal Kurniawan, A. A. Gunawan","doi":"10.1109/ICCoSITE57641.2023.10127706","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127706","url":null,"abstract":"Humans have studied calligraphy and calculated programs to foster creativity for years. Image generation technology using artificial intelligence and Generative Adversarial Networks is currently reaching the peak of its performance. While there are newer and newer algorithms to improve the image generation system, the output of the images is still suitable at best and only excels in their category. While it is true that some of the images generated are good enough to be used, it is still unclear whether the capabilities of AI image generation can outperform their creative human counterparts. Therefore, this literature study aims to explore the basics of AI image generation, how they work, and what factors contribute to creating art such as simple pictures. Previous studies from several years ago show that most generated images are not good enough for creative usage because they only replicate traces of their dataset. The most significant factor contributing to this is the algorithm used and how it is used to create new images. In general, the concluded that while current AI-generated images are improving, they are still not creative enough to replace human creativity.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128393549","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127853
A. T. Santoso, M. R. Rosa, Edwar
This paper proposes the Model Reference Adaptive Control (MRAC) design for the CubeSat 1U prototype with a magnetorquer to control the yaw angle. In practice, the system dynamics parameters of the CubeSat 1U, such as the moment inertia and mass, are unknown. To handle the uncertainties of the parameters, the authors propose MRAC to control the yaw angle of the CubeSat 1U. The controller is designed and deployed using MATLAB, which is connected via Bluetooth to the CubeSat 1U. In the experiment, the communication delay occurs and causes deteriorated output response of standard MRAC. The modified MRAC and redesigned reference signal are used to reduce the time delay effect for the proposed controller. The numerical simulation and experiment are used to show the effectiveness of the proposed controller design. It is shown by modifying the standard MRAC and the reference signal, the system error can be reduced from +110-20 degrees to +10-10 degrees.
{"title":"Model Reference Adaptive Control Design for CubeSat with Magnetorquer","authors":"A. T. Santoso, M. R. Rosa, Edwar","doi":"10.1109/ICCoSITE57641.2023.10127853","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127853","url":null,"abstract":"This paper proposes the Model Reference Adaptive Control (MRAC) design for the CubeSat 1U prototype with a magnetorquer to control the yaw angle. In practice, the system dynamics parameters of the CubeSat 1U, such as the moment inertia and mass, are unknown. To handle the uncertainties of the parameters, the authors propose MRAC to control the yaw angle of the CubeSat 1U. The controller is designed and deployed using MATLAB, which is connected via Bluetooth to the CubeSat 1U. In the experiment, the communication delay occurs and causes deteriorated output response of standard MRAC. The modified MRAC and redesigned reference signal are used to reduce the time delay effect for the proposed controller. The numerical simulation and experiment are used to show the effectiveness of the proposed controller design. It is shown by modifying the standard MRAC and the reference signal, the system error can be reduced from +110-20 degrees to +10-10 degrees.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130951397","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127851
Gerry Samhari Ramadhan, Budhi Irawan, C. Setianingsih, Figo Plambudi Dwigantara
A song is a unity of sound that contains a tone and lyrics. A song can contain a variety of emotions. Emotions in the song can arise because of the combination of lyrics and tones that create a beautiful sound and harmony. This research is about the emotional content of the song lyrics. This research began with collecting datasets in the form of song lyrics from kapanlagi.com, liriklaguindonesia.net, and liriklaguanak.com as a provider of song lyrics. Then preprocessing data consists of case folding, tokenizing, stop removal, and stemming. After that, the part of speech (POS) tagging process automatically labels the word in the text according to the word class. Labeling a word, whether it's a verb, adjective, or description, to be able to determine the song's emotional lyrics according to what we listen to takes the right method. The method used is the Naive Bayes Classifier and Particle Swarm Optimization methods, as methods used in performing text classification. In some studies, it was mentioned that the Naive Bayes Classifier method shows good results in the case of the classification of Indonesian text information, with an accuracy of 90%–96% using an inertia weight score of 1.0.
{"title":"Classification of Emotions on Song Lyrics using Naïve Bayes Algorithm and Particle Swarm Optimization","authors":"Gerry Samhari Ramadhan, Budhi Irawan, C. Setianingsih, Figo Plambudi Dwigantara","doi":"10.1109/ICCoSITE57641.2023.10127851","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127851","url":null,"abstract":"A song is a unity of sound that contains a tone and lyrics. A song can contain a variety of emotions. Emotions in the song can arise because of the combination of lyrics and tones that create a beautiful sound and harmony. This research is about the emotional content of the song lyrics. This research began with collecting datasets in the form of song lyrics from kapanlagi.com, liriklaguindonesia.net, and liriklaguanak.com as a provider of song lyrics. Then preprocessing data consists of case folding, tokenizing, stop removal, and stemming. After that, the part of speech (POS) tagging process automatically labels the word in the text according to the word class. Labeling a word, whether it's a verb, adjective, or description, to be able to determine the song's emotional lyrics according to what we listen to takes the right method. The method used is the Naive Bayes Classifier and Particle Swarm Optimization methods, as methods used in performing text classification. In some studies, it was mentioned that the Naive Bayes Classifier method shows good results in the case of the classification of Indonesian text information, with an accuracy of 90%–96% using an inertia weight score of 1.0.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124890137","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}
Despite the popularity of online dating Application, there are increasing security issues and challenges with them, such as the creation of fake accounts and phishing, which are commonly called romance scams, one of which is fake user data or even completely fake profiles. This research will discuss the profile verification technology that has been developed in several online dating applications to verify the authenticity of user profiles using an algorithm capable of detecting fake profiles. This study used Sequential Equation Modeling (SEM) method and SMART PLS as a statistical tool. A total of 561 data from online dating application users in Indonesia were collected in October 2022. The purpose of this study was to determine the impact of Attitude, Trust, and Subjective Norm to intention to use profile verification in Dating Application in Indonesia. Attitude, Trust, and Subjective Norms will be special variables that affect the user's intention to use Profile Verification on Dating Applications in Indonesia. The results of the study found that all research hypotheses had a significant effect on each variable relationship in the research model.
{"title":"Analysis of Attitude, Trust, and Subjective Norm Impact on Intention to Use Profile Verification in Dating Applications in Indonesia","authors":"Kenny Prasetyo, Xenia Dharmawan, Erwin Ardianto Halim, Marylise Hebrard","doi":"10.1109/ICCoSITE57641.2023.10127777","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127777","url":null,"abstract":"Despite the popularity of online dating Application, there are increasing security issues and challenges with them, such as the creation of fake accounts and phishing, which are commonly called romance scams, one of which is fake user data or even completely fake profiles. This research will discuss the profile verification technology that has been developed in several online dating applications to verify the authenticity of user profiles using an algorithm capable of detecting fake profiles. This study used Sequential Equation Modeling (SEM) method and SMART PLS as a statistical tool. A total of 561 data from online dating application users in Indonesia were collected in October 2022. The purpose of this study was to determine the impact of Attitude, Trust, and Subjective Norm to intention to use profile verification in Dating Application in Indonesia. Attitude, Trust, and Subjective Norms will be special variables that affect the user's intention to use Profile Verification on Dating Applications in Indonesia. The results of the study found that all research hypotheses had a significant effect on each variable relationship in the research model.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126367225","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 : 2023-02-16DOI: 10.1109/ICCoSITE57641.2023.10127814
Muhammad Yusuf Firdaus, Septi Andryana
Employee ranking is an activity carried out by companies to rank employees based on the results of criteria that have been assessed. This is done to give an idea to the company how the value results from the criteria that have been obtained by employees. Related to this research, a Decision Support System is needed to rank the best employees, which uses a combination of 2 methods, namely the Analytical Hierarchy Process (AHP) method is used to weight each criterion and to test the consistency between criteria and Višekriterijumsko Kompromisno Rangiranje (VIKOR) is used to solve complex multi-criteria system problems that focus on ranking and selection of an alternative and determining the ideal solution. The criteria used in this research are Work Behavior Value (C1), SKP value (C2) and Work Performance Value (C3). For alternative data, employee data is used. The results of this study indicate that the employee with the highest rank is Hanung Harimba (KR1) with a value of Q = 0 and the employee with the lowest rank is Christina Thiveny (KR8) with a value of Q = 1.
{"title":"Employee Ranking Based On Work Performance Using AHP and VIKOR Methods","authors":"Muhammad Yusuf Firdaus, Septi Andryana","doi":"10.1109/ICCoSITE57641.2023.10127814","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127814","url":null,"abstract":"Employee ranking is an activity carried out by companies to rank employees based on the results of criteria that have been assessed. This is done to give an idea to the company how the value results from the criteria that have been obtained by employees. Related to this research, a Decision Support System is needed to rank the best employees, which uses a combination of 2 methods, namely the Analytical Hierarchy Process (AHP) method is used to weight each criterion and to test the consistency between criteria and Višekriterijumsko Kompromisno Rangiranje (VIKOR) is used to solve complex multi-criteria system problems that focus on ranking and selection of an alternative and determining the ideal solution. The criteria used in this research are Work Behavior Value (C1), SKP value (C2) and Work Performance Value (C3). For alternative data, employee data is used. The results of this study indicate that the employee with the highest rank is Hanung Harimba (KR1) with a value of Q = 0 and the employee with the lowest rank is Christina Thiveny (KR8) with a value of Q = 1.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114317360","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：