Pub Date : 2021-10-20DOI: 10.1109/ICTS52701.2021.9609054
Adi Setyo Nugroho, Aizul Faiz Iswafaza, R. Anggraini, R. Sarno
the reviewer's recommendation in accordance with the field of research is crucial where this is directly proportional to the results of the review on the research. In finding suitable reviewers, conflicts of interest (COI) are often found. In this paper, we propose an approach to reviewer recommendations with topic extraction and author extraction to prevent COI. First, we separate the process into 2, namely to do topic extraction using Latent Dirichlet Allocation (LDA), and also to do author extraction using Cosine Similarity. The next step is to combine the two results to rank the 10 recommended authors. The experimental results show that our approach has succeeded in getting 10 recommended reviewers to avoid COI.
{"title":"A Novel Approach on Conducting Reviewer Recommendations Based on Conflict of Interest","authors":"Adi Setyo Nugroho, Aizul Faiz Iswafaza, R. Anggraini, R. Sarno","doi":"10.1109/ICTS52701.2021.9609054","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9609054","url":null,"abstract":"the reviewer's recommendation in accordance with the field of research is crucial where this is directly proportional to the results of the review on the research. In finding suitable reviewers, conflicts of interest (COI) are often found. In this paper, we propose an approach to reviewer recommendations with topic extraction and author extraction to prevent COI. First, we separate the process into 2, namely to do topic extraction using Latent Dirichlet Allocation (LDA), and also to do author extraction using Cosine Similarity. The next step is to combine the two results to rank the 10 recommended authors. The experimental results show that our approach has succeeded in getting 10 recommended reviewers to avoid COI.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"5 1","pages":"195-200"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90199310","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608559
Hanny Haryanto, Aripin, I. Gamayanto
Activity is one of the main elements for shaping the experience in serious game, that could enhance the player understanding on the learning material. However, lack of concept or framework to design the activity could resulted in poor experience. In previous research, Appreciative Learning has been used to design the activities in serious game. In this study, we use Innovation Profiling as a framework to develop activities in Design Stage of Appreciative Learning. Design stage in Appreciative Learning consists of activities to produce innovation. Therefore, the Innovation Profiling could provide the detailed concept for the activities in this stage. Innovation profiling has four types of innovation, that are open innovation, blind innovation, hidden innovation and unknown innovation. It divided into seven important parts: imitating, seeing, understanding, trying, changing, understanding, solution, integration and creative. Realistic visual speech synthesis is used as the player avatar to interact with the game and serve as main education tool of Indonesian pronunciation. Results show that the activity could enhance the player experience and motivation to learn Indonesian pronunciation.
{"title":"Activity Design Using Innovation Profiling in Appreciative Learning Serious Game of Indonesian Pronunciation","authors":"Hanny Haryanto, Aripin, I. Gamayanto","doi":"10.1109/ICTS52701.2021.9608559","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608559","url":null,"abstract":"Activity is one of the main elements for shaping the experience in serious game, that could enhance the player understanding on the learning material. However, lack of concept or framework to design the activity could resulted in poor experience. In previous research, Appreciative Learning has been used to design the activities in serious game. In this study, we use Innovation Profiling as a framework to develop activities in Design Stage of Appreciative Learning. Design stage in Appreciative Learning consists of activities to produce innovation. Therefore, the Innovation Profiling could provide the detailed concept for the activities in this stage. Innovation profiling has four types of innovation, that are open innovation, blind innovation, hidden innovation and unknown innovation. It divided into seven important parts: imitating, seeing, understanding, trying, changing, understanding, solution, integration and creative. Realistic visual speech synthesis is used as the player avatar to interact with the game and serve as main education tool of Indonesian pronunciation. Results show that the activity could enhance the player experience and motivation to learn Indonesian pronunciation.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"278 1","pages":"24-28"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76893346","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608905
D. A. Navastara, Ihdiannaja, A. Arifin
Question answering (QA) system is built to answer asked queries based on an unstructured collection of documents in natural language. The implementation of the QA system makes QA more efficient because the system can answer similar questions automatically. However, similarity queries based on questions or answers alone fail to retrieve documents relevant to the query in some cases because the word choice used in the query is different from the word choice in the QA database even though the context is the same. The same context can be seen from the list of references used by a QA. Therefore, it is necessary to measure the similarity of the query that does not only take into account the question and answer but also the reference. In this paper, we propose to build a bilingual QA system that answers Indonesian questions based on the combination of query similarities among question, answer, and external reference in Arabic using Bidirectional Encoder Representation from Transformers (BERT) and Best Matching (BM25) method. The similarity between query and reference are able to help to recognize a QA that uses reference with similar context. Based on the experimental result, the combination parameter of query-Question followed by query-Answer achieves the highest evaluation score with the Mean Average Precision (MAP) score of 0.988 and the Mean Reciprocal Rank (MRR) score of 1.000.
问答(QA)系统是基于自然语言的非结构化文档集合来回答用户提出的问题。QA系统的实现使得QA更加高效，因为系统可以自动回答类似的问题。然而，在某些情况下，仅基于问题或答案的相似性查询无法检索与查询相关的文档，因为查询中使用的单词选择与QA数据库中的单词选择不同，即使上下文相同。同样的上下文可以从QA使用的引用列表中看到。因此，有必要测量查询的相似度，不仅要考虑问题和答案，还要考虑参考。在本文中，我们提出了一个基于阿拉伯语问题、答案和外部参考之间的查询相似度组合的双语问答系统，该系统采用双向编码器表示(BERT)和最佳匹配(BM25)方法来回答印尼语问题。查询和引用之间的相似性有助于识别使用具有相似上下文的引用的QA。从实验结果来看，query-Question后query-Answer的组合参数评价得分最高，MAP (Mean Average Precision)得分为0.988,MRR (Mean Reciprocal Rank)得分为1.000。
{"title":"Bilingual Question Answering System Using Bidirectional Encoder Representations from Transformers and Best Matching Method","authors":"D. A. Navastara, Ihdiannaja, A. Arifin","doi":"10.1109/ICTS52701.2021.9608905","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608905","url":null,"abstract":"Question answering (QA) system is built to answer asked queries based on an unstructured collection of documents in natural language. The implementation of the QA system makes QA more efficient because the system can answer similar questions automatically. However, similarity queries based on questions or answers alone fail to retrieve documents relevant to the query in some cases because the word choice used in the query is different from the word choice in the QA database even though the context is the same. The same context can be seen from the list of references used by a QA. Therefore, it is necessary to measure the similarity of the query that does not only take into account the question and answer but also the reference. In this paper, we propose to build a bilingual QA system that answers Indonesian questions based on the combination of query similarities among question, answer, and external reference in Arabic using Bidirectional Encoder Representation from Transformers (BERT) and Best Matching (BM25) method. The similarity between query and reference are able to help to recognize a QA that uses reference with similar context. Based on the experimental result, the combination parameter of query-Question followed by query-Answer achieves the highest evaluation score with the Mean Average Precision (MAP) score of 0.988 and the Mean Reciprocal Rank (MRR) score of 1.000.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"114 1","pages":"360-364"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80795589","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9607996
Ayu Mutiara Sari, Nurul Fajrin Ariyani, A. Ahmadiyah
The spread propagation of fake news about COVID-19 can make it distressing to handle the pandemic situation. Identifying the fake and real news on social media needs to be done as quickly as possible to prevent chaos in the community and hampering the handling of COVID-19. In this study, we conducted some experiments to get a model that works well for classifying information into fake or real news using tweet data. We implemented two different ways to represent data to train machine learning classifier models, syntactic-based using Bag-of-Words and TF-IDF, and semantic-based using Word2Vec and FastText. We evaluated each model produced by the training process using two types of testing data. The results show that The Linear Support Vector Machine model using TF-IDF obtained the best F1-Score value in both testing data. The model obtained F1-Score 92.21% in Testing Data 1 and 93.33% in Testing Data 2.
{"title":"Evaluating The Preliminary Models to Identify Fake News on COVID-19 Tweets","authors":"Ayu Mutiara Sari, Nurul Fajrin Ariyani, A. Ahmadiyah","doi":"10.1109/ICTS52701.2021.9607996","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9607996","url":null,"abstract":"The spread propagation of fake news about COVID-19 can make it distressing to handle the pandemic situation. Identifying the fake and real news on social media needs to be done as quickly as possible to prevent chaos in the community and hampering the handling of COVID-19. In this study, we conducted some experiments to get a model that works well for classifying information into fake or real news using tweet data. We implemented two different ways to represent data to train machine learning classifier models, syntactic-based using Bag-of-Words and TF-IDF, and semantic-based using Word2Vec and FastText. We evaluated each model produced by the training process using two types of testing data. The results show that The Linear Support Vector Machine model using TF-IDF obtained the best F1-Score value in both testing data. The model obtained F1-Score 92.21% in Testing Data 1 and 93.33% in Testing Data 2.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"75 1","pages":"336-341"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82025676","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9609016
Ainurrochman, Irfanur Ilham Febriansyah, Umi Laili Yuhana
Nowadays, device control is commonly using the human body feature or voice recognition technology. To expand the functionality of voice recognition, plenty of researchers have developed speech emotion recognition. By recognizing sound emotions, a system can provide better and beneficial decision-making output. This paper describes the development of an application that is able to recognize speech emotions using Extreme Learning Machine (ELM). We use the dataset from Toronto Emotional Speech Set (TESS). The dataset contains 2800 data points (audio files) in total and has high quality audio that focused on female voices to ensure the reliability of the data. The Speech Emotion Recognition application was design as web-based application that used Golang and Python which built with Extreme Learning Machine and Random Forest to recognize speech emotions. As a result, the functionality test shows that the application was able to satisfy 6 out of 6 requirements, and the accuracy test shows an accuracy value of 100% by identifying 70 out of 70 test data.
{"title":"SER: Speech Emotion Recognition Application Based on Extreme Learning Machine","authors":"Ainurrochman, Irfanur Ilham Febriansyah, Umi Laili Yuhana","doi":"10.1109/ICTS52701.2021.9609016","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9609016","url":null,"abstract":"Nowadays, device control is commonly using the human body feature or voice recognition technology. To expand the functionality of voice recognition, plenty of researchers have developed speech emotion recognition. By recognizing sound emotions, a system can provide better and beneficial decision-making output. This paper describes the development of an application that is able to recognize speech emotions using Extreme Learning Machine (ELM). We use the dataset from Toronto Emotional Speech Set (TESS). The dataset contains 2800 data points (audio files) in total and has high quality audio that focused on female voices to ensure the reliability of the data. The Speech Emotion Recognition application was design as web-based application that used Golang and Python which built with Extreme Learning Machine and Random Forest to recognize speech emotions. As a result, the functionality test shows that the application was able to satisfy 6 out of 6 requirements, and the accuracy test shows an accuracy value of 100% by identifying 70 out of 70 test data.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"183 1","pages":"179-183"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91527580","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608188
Muzammil Khan, Pushpendra Kumar
Variational models are more popular approaches in the estimation of optical flow between two image frames and yield the most accurate flow fields. More fidelity terms in the variational model makes the estimation robust. This paper proposed an anisotropic operator which is designed using the greatest integer and an exponential function to estimate average flow velocity. This will help to preserve discontinuity in the optical flow and provides a significant smooth flow over a uniform region. The design of this operator is motivated from an isotropic operator that is based on the intensity differences of the pixels. This is employed in the controlling of flow propagation. The validation of the accuracy and robustness of our algorithm is provided in terms of qualitative and quantitative results on a variety of spectrum datasets.
{"title":"Discontinuity Preserving Optical Flow Based on Anisotropic Operator","authors":"Muzammil Khan, Pushpendra Kumar","doi":"10.1109/ICTS52701.2021.9608188","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608188","url":null,"abstract":"Variational models are more popular approaches in the estimation of optical flow between two image frames and yield the most accurate flow fields. More fidelity terms in the variational model makes the estimation robust. This paper proposed an anisotropic operator which is designed using the greatest integer and an exponential function to estimate average flow velocity. This will help to preserve discontinuity in the optical flow and provides a significant smooth flow over a uniform region. The design of this operator is motivated from an isotropic operator that is based on the intensity differences of the pixels. This is employed in the controlling of flow propagation. The validation of the accuracy and robustness of our algorithm is provided in terms of qualitative and quantitative results on a variety of spectrum datasets.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"51 1","pages":"306-311"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73586430","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608714
Ainurrochman, A. Nugroho, Raditia Wahyuwidayat, Santi Tiodora Sianturi, Muhamad Fauzi, M. Ramadhan, B. Pratomo, A. M. Shiddiqi
With the rapid development of information technology, the network has been everywhere. This technology has brought a lot of convenience to people, but there are also some security problems. To solve these problems, many methods have been proposed, among which is intrusion detection. A lot of research has been done to find the most effective Intrusion Detection Systems. In term of detecting novel attacks, Anomaly-Based Intrusion Detection Systems has better significance than Misuse-Based Intrusion Detection Systems. The research on the datasets being used for training and testing purposes in the detection model is as important as the model. Better dataset quality can improve intrusion detection model results. This research presents the statistical analysis of labeled flow-based CIDDS-002 dataset using ensemble methods classifier. The analysis is done concerning some prominent evaluation metrics used for evaluating Intrusion Detection Systems including Detection Rate, Accuracy, and False Positive Rate. As a result, the accuracy of the Bagging (Decision Tree) is 99.71% and Bagging (Gaussian Naïve Bayes) is 67.57%.
{"title":"Ensemble Methods Classifier Comparison for Anomaly Based Intrusion Detection System on CIDDS-002 Dataset","authors":"Ainurrochman, A. Nugroho, Raditia Wahyuwidayat, Santi Tiodora Sianturi, Muhamad Fauzi, M. Ramadhan, B. Pratomo, A. M. Shiddiqi","doi":"10.1109/ICTS52701.2021.9608714","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608714","url":null,"abstract":"With the rapid development of information technology, the network has been everywhere. This technology has brought a lot of convenience to people, but there are also some security problems. To solve these problems, many methods have been proposed, among which is intrusion detection. A lot of research has been done to find the most effective Intrusion Detection Systems. In term of detecting novel attacks, Anomaly-Based Intrusion Detection Systems has better significance than Misuse-Based Intrusion Detection Systems. The research on the datasets being used for training and testing purposes in the detection model is as important as the model. Better dataset quality can improve intrusion detection model results. This research presents the statistical analysis of labeled flow-based CIDDS-002 dataset using ensemble methods classifier. The analysis is done concerning some prominent evaluation metrics used for evaluating Intrusion Detection Systems including Detection Rate, Accuracy, and False Positive Rate. As a result, the accuracy of the Bagging (Decision Tree) is 99.71% and Bagging (Gaussian Naïve Bayes) is 67.57%.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"1 1","pages":"62-67"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82077470","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608826
Haekal Febriansyah Ramadhan, Fandi Aditya Putra, R. F. Sari
News is a form of information sharing that tells the people about current event that is happening. With the advancement of technologies, the rate of spreading of the news is also increasing. One of the most popular places to read news is through the Internet. However, most of the people that read news from the Internet is not aware about the news sources. This leads to the spread of some fake news in society. In this paper, we suggest a way to verify a news using Ethereum smart contract and IPFS. There are four entities that involved in the system, such as Journalist as the one that provides the news, Validator as the one that will rate the news, Ethereum Smart Contract that will store the data inside the blockchain, and IPFS that will store the news and giving hash code to be stored inside the blockchain. This paper also analyzed the cost required to run the function of the smart contract deployed. The result is that all of the Rating Functions cost the same. However, the News Submit Function is not. The difference is the bigger the news stored in the IPFS, the more expensive the cost required to run the function.
{"title":"News Verification using Ethereum Smart Contract and Inter Planetary File System (IPFS)","authors":"Haekal Febriansyah Ramadhan, Fandi Aditya Putra, R. F. Sari","doi":"10.1109/ICTS52701.2021.9608826","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608826","url":null,"abstract":"News is a form of information sharing that tells the people about current event that is happening. With the advancement of technologies, the rate of spreading of the news is also increasing. One of the most popular places to read news is through the Internet. However, most of the people that read news from the Internet is not aware about the news sources. This leads to the spread of some fake news in society. In this paper, we suggest a way to verify a news using Ethereum smart contract and IPFS. There are four entities that involved in the system, such as Journalist as the one that provides the news, Validator as the one that will rate the news, Ethereum Smart Contract that will store the data inside the blockchain, and IPFS that will store the news and giving hash code to be stored inside the blockchain. This paper also analyzed the cost required to run the function of the smart contract deployed. The result is that all of the Rating Functions cost the same. However, the News Submit Function is not. The difference is the bigger the news stored in the IPFS, the more expensive the cost required to run the function.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"33 1","pages":"96-100"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80020788","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9608120
R. W. Tri Hartono, Nadya Sarah, Regina Nur Shabrina, Evan Lokajaya
The COVID-19 pandemic is a situation that spreads the disease caused by the corona virus. One of the efforts to prevent the spread of the virus from one person to another is by requiring everyone to wear a face mask, especially for those in public areas. There have been several similar previous studies, however, none of them accompanied by follow-up, if someone is found without a face mask. The purpose of this research is to make a detector called e-Detect to detect visitors in public areas such as supermarkets, hospitals, schools and other similar places that without wearing a face mask (non-user face mask) uses the Convolutional Neural Network (CNN) method. If e-Detect detects non-user face mask who will enter through the gate of a public area without wearing face mask, the gate will not open, the buzzer will sound, and the visitor's photo will be sent to the security guard via telegram as a notification. The gate is only open when visitors wear face masks. Experiments have been carried out using 17 types of masks with percentages of: accuracy 94%, precision 100%, sensitivity 94.11%, specificity 100%, and error rate is 5.56%. A trial on e-Detect ability, show in the experiment range detection distance using any type of mask, which is 175 centimeters. All visitors who come to public areas through the gate that has been installed e-Detect can be ensured that the visitor's face will not be more than 175 cm apart, thus all visitors can be ensured to be well supervised. Based on this data, it can be said that e-Detect is feasible to be produced and used as an effort to prevent the spread of COVID-19.
{"title":"e-Detect: Non-User Mask Detection Based on Image Processing Using Convolutional Neural Network Method","authors":"R. W. Tri Hartono, Nadya Sarah, Regina Nur Shabrina, Evan Lokajaya","doi":"10.1109/ICTS52701.2021.9608120","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9608120","url":null,"abstract":"The COVID-19 pandemic is a situation that spreads the disease caused by the corona virus. One of the efforts to prevent the spread of the virus from one person to another is by requiring everyone to wear a face mask, especially for those in public areas. There have been several similar previous studies, however, none of them accompanied by follow-up, if someone is found without a face mask. The purpose of this research is to make a detector called e-Detect to detect visitors in public areas such as supermarkets, hospitals, schools and other similar places that without wearing a face mask (non-user face mask) uses the Convolutional Neural Network (CNN) method. If e-Detect detects non-user face mask who will enter through the gate of a public area without wearing face mask, the gate will not open, the buzzer will sound, and the visitor's photo will be sent to the security guard via telegram as a notification. The gate is only open when visitors wear face masks. Experiments have been carried out using 17 types of masks with percentages of: accuracy 94%, precision 100%, sensitivity 94.11%, specificity 100%, and error rate is 5.56%. A trial on e-Detect ability, show in the experiment range detection distance using any type of mask, which is 175 centimeters. All visitors who come to public areas through the gate that has been installed e-Detect can be ensured that the visitor's face will not be more than 175 cm apart, thus all visitors can be ensured to be well supervised. Based on this data, it can be said that e-Detect is feasible to be produced and used as an effort to prevent the spread of COVID-19.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"61 1","pages":"271-276"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84559968","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 : 2021-10-20DOI: 10.1109/ICTS52701.2021.9607951
Doni Putra Purbawa, Malikhah, Ratih Nur Esti Anggraini, R. Sarno
The rapid development of science and technology in the health sector cannot be separated from the support of health research results. Before the research with human as a subject is conducted, every health research in Indonesia is required to make a health ethics protocol document in Bahasa which must comply with basic ethical principles. To determine whether the health research ethics protocol document has met the ethical principles, the health research ethics protocol document will be reviewed by a competent reviewer. The health research ethics protocol document consists of several parts and has a large number of pages, so to conduct a review, reviewers need a long time to understand and analyze the health research ethics protocol document. To reduce the review time, an automatic text summarization (ATS) is needed. ATS extracts important information in health research ethics protocol documents and presents it to reviewers. This research uses cosine similarity and Maximum Marginal Relevance (MMR) and TextRank to summarize the document. The MMR method is considered to have more stable results than TextRank based on the ROUGE evaluation results. The evaluation of result with the ROUGE Toolkit showed F-score value of 19.92% for document 1 and 10.98% for document 2 using MMR.
{"title":"Automatic Text Summarization using Maximum Marginal Relevance for Health Ethics Protocol Document in Bahasa","authors":"Doni Putra Purbawa, Malikhah, Ratih Nur Esti Anggraini, R. Sarno","doi":"10.1109/ICTS52701.2021.9607951","DOIUrl":"https://doi.org/10.1109/ICTS52701.2021.9607951","url":null,"abstract":"The rapid development of science and technology in the health sector cannot be separated from the support of health research results. Before the research with human as a subject is conducted, every health research in Indonesia is required to make a health ethics protocol document in Bahasa which must comply with basic ethical principles. To determine whether the health research ethics protocol document has met the ethical principles, the health research ethics protocol document will be reviewed by a competent reviewer. The health research ethics protocol document consists of several parts and has a large number of pages, so to conduct a review, reviewers need a long time to understand and analyze the health research ethics protocol document. To reduce the review time, an automatic text summarization (ATS) is needed. ATS extracts important information in health research ethics protocol documents and presents it to reviewers. This research uses cosine similarity and Maximum Marginal Relevance (MMR) and TextRank to summarize the document. The MMR method is considered to have more stable results than TextRank based on the ROUGE evaluation results. The evaluation of result with the ROUGE Toolkit showed F-score value of 19.92% for document 1 and 10.98% for document 2 using MMR.","PeriodicalId":6738,"journal":{"name":"2021 13th International Conference on Information & Communication Technology and System (ICTS)","volume":"31 1","pages":"324-329"},"PeriodicalIF":0.0,"publicationDate":"2021-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79368177","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：