Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274682
Latifah Alhaura, I. Budi
The rapid growth of social networks indeed triggers an increase in malicious activities, including the spread of false information, the creation of fake accounts, spamming, and malware distribution. However, developing a detection system that can identify accounts precisely becomes quite challenging. In this paper, we present a study related to the detection of malicious accounts on Twitter users from Indonesia. Our study objective is to propose a simple feature set to detect malicious accounts using only a few metadata and the tweet content itself from Twitter. We divided the classification level into three: account level classification, tweet level classification, and combination of account and tweet level classification. To get the classification results, we applied some popular machine learning algorithms such as Random Forest, Decision Tree, AdaBoost Classifier, Neural Network, and Logistic Regression to each classification level. The results show that Random Forest achieved high classification accuracy (AUC >80%) in each classification level using our proposed feature set.
{"title":"Malicious Account Detection on Indonesian Twitter Account","authors":"Latifah Alhaura, I. Budi","doi":"10.1109/IC2IE50715.2020.9274682","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274682","url":null,"abstract":"The rapid growth of social networks indeed triggers an increase in malicious activities, including the spread of false information, the creation of fake accounts, spamming, and malware distribution. However, developing a detection system that can identify accounts precisely becomes quite challenging. In this paper, we present a study related to the detection of malicious accounts on Twitter users from Indonesia. Our study objective is to propose a simple feature set to detect malicious accounts using only a few metadata and the tweet content itself from Twitter. We divided the classification level into three: account level classification, tweet level classification, and combination of account and tweet level classification. To get the classification results, we applied some popular machine learning algorithms such as Random Forest, Decision Tree, AdaBoost Classifier, Neural Network, and Logistic Regression to each classification level. The results show that Random Forest achieved high classification accuracy (AUC >80%) in each classification level using our proposed feature set.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124051362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274675
Adela Khairunnisa Nugraha, A. Agus
This study examines the influence of homophily, expertise, and emotional attachment to the popularity of vloggers and ultimately examines the effect of emotional attachment, vlogger popularity, and expertise on the purchase intention of recommended beauty products by focusing on beauty vlogger Tasya Farasya. Homophily itself is divided into four dimensions including attitude, background, morals, and appearance. This study uses a descriptive research design conducted in a single-cross sectional through the distribution of questionnaires online to respondents. The target respondents of this study were Indonesian women aged 15 years and over and had watched the YouTube video of Tasya Farasya (n = 430). The data obtained processed using the statistical method of Structural Equation Modeling (SEM) using LISREL 8.80 software. The results of this research showed that almost all dimensions of homophily (attitude, values, appearance) are significantly have a positive impact the emotional attachment. On the other hand, all dimensions of homophily does not have a significant positive impact on vloggers’ popularity. Then, emotional attachment and expertise also found have a significant positive impact to vloggers’ popularity. In last, researcher found that emotional attachment and expertise are significantly have a positive impact the purchase intentions of viewers while vloggers’ popularity does not.
{"title":"Analysis of Homophily, Emotional Attachment, and Expertise towards Vloggers’ Popularity and Viewers Purchasing Decisions in Beauty Products Industry","authors":"Adela Khairunnisa Nugraha, A. Agus","doi":"10.1109/IC2IE50715.2020.9274675","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274675","url":null,"abstract":"This study examines the influence of homophily, expertise, and emotional attachment to the popularity of vloggers and ultimately examines the effect of emotional attachment, vlogger popularity, and expertise on the purchase intention of recommended beauty products by focusing on beauty vlogger Tasya Farasya. Homophily itself is divided into four dimensions including attitude, background, morals, and appearance. This study uses a descriptive research design conducted in a single-cross sectional through the distribution of questionnaires online to respondents. The target respondents of this study were Indonesian women aged 15 years and over and had watched the YouTube video of Tasya Farasya (n = 430). The data obtained processed using the statistical method of Structural Equation Modeling (SEM) using LISREL 8.80 software. The results of this research showed that almost all dimensions of homophily (attitude, values, appearance) are significantly have a positive impact the emotional attachment. On the other hand, all dimensions of homophily does not have a significant positive impact on vloggers’ popularity. Then, emotional attachment and expertise also found have a significant positive impact to vloggers’ popularity. In last, researcher found that emotional attachment and expertise are significantly have a positive impact the purchase intentions of viewers while vloggers’ popularity does not.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126871017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/ic2ie50715.2020.9274614
{"title":"[Copyright notice]","authors":"","doi":"10.1109/ic2ie50715.2020.9274614","DOIUrl":"https://doi.org/10.1109/ic2ie50715.2020.9274614","url":null,"abstract":"","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133023837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274679
H. Maulana, Ulfa Mulyantika
Indonesia is one of the largest swallow nest producers, supported by its natural condition as the original habitat of swiftlets. The selling price of unstable products and the lack of information about the prices of products exported to the general public are the problems faced. The absence of a benchmark or source of certain product prices that cause uncertainty in determining product prices. For this reason, the prediction system is created by applying the Holt’s Double Exponential Smoothing (DES) method, because this smoothing method can overcome time series data that has trend patterns. The prediction system provides a graph of the price movements of export products and price predictions for the following month. Based on testing that has been done, the results obtained mean that the Absolute Presentation Error (MAPE) is very good at 0.20%.
{"title":"The Prediction Of Export Product Prices With Holt’s Double Exponential Smoothing Method","authors":"H. Maulana, Ulfa Mulyantika","doi":"10.1109/IC2IE50715.2020.9274679","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274679","url":null,"abstract":"Indonesia is one of the largest swallow nest producers, supported by its natural condition as the original habitat of swiftlets. The selling price of unstable products and the lack of information about the prices of products exported to the general public are the problems faced. The absence of a benchmark or source of certain product prices that cause uncertainty in determining product prices. For this reason, the prediction system is created by applying the Holt’s Double Exponential Smoothing (DES) method, because this smoothing method can overcome time series data that has trend patterns. The prediction system provides a graph of the price movements of export products and price predictions for the following month. Based on testing that has been done, the results obtained mean that the Absolute Presentation Error (MAPE) is very good at 0.20%.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131615422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274686
Intan Vidia Saputri, E. C. Djamal, Fikri Nugraha, Ridwan Ilyas
Wind speed prediction is needed in various sectors, such as in industry. However, the weather conditions change all the time, so it is not easy to predict. The wind that blows is influenced by several climatic weather factors such as humidity and rainfall. Also, wind speed patterns change when there is a global climate change, El Nino. Therefore this research involved the element in predicting wind patterns one week ahead. Recurrent Neural Networks (RNN) and Long-short Term Memory (LSTM) methods are used for sequential data processing, such as climate data. Climate data for ten years used were wind speed, humidity, and rainfall provided by Meteorological, Climatological, and Geophysical Agency (BMKG) of a weather observation station, while Southern Oscillation Index (SOI), was obtained from the Australian Bureau of Meteorology (ABM). Data need to be pre-processed to solve missing data. Moreover, all variables were normalized and segmentation by overlapping to avoid data discontinuity. The results showed that the use of the amount of data, learning rate, epoch, and selection of the right optimization model could give good accuracy. The purpose of the proper configuration has a good performance, with accuracy reaching 88.34%. The results showed that the use of SOI factors improved correctness from 74.75% without SOI. The results also show that the model Adaptive Moment Estimation (Adam) provides better accuracy than the model Stochastic Gradient Descent (SGD), which gives an accuracy of only 71.84%. Meanwhile, the study also examined the effect of the learning rate and composition of training data and test data. The best accuracy is shown for the learning rate of 0.020 and 80:20% of training and test data comparison.
{"title":"Wind Speed Forecasting toward El Nino Factors Using Recurrent Neural Networks","authors":"Intan Vidia Saputri, E. C. Djamal, Fikri Nugraha, Ridwan Ilyas","doi":"10.1109/IC2IE50715.2020.9274686","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274686","url":null,"abstract":"Wind speed prediction is needed in various sectors, such as in industry. However, the weather conditions change all the time, so it is not easy to predict. The wind that blows is influenced by several climatic weather factors such as humidity and rainfall. Also, wind speed patterns change when there is a global climate change, El Nino. Therefore this research involved the element in predicting wind patterns one week ahead. Recurrent Neural Networks (RNN) and Long-short Term Memory (LSTM) methods are used for sequential data processing, such as climate data. Climate data for ten years used were wind speed, humidity, and rainfall provided by Meteorological, Climatological, and Geophysical Agency (BMKG) of a weather observation station, while Southern Oscillation Index (SOI), was obtained from the Australian Bureau of Meteorology (ABM). Data need to be pre-processed to solve missing data. Moreover, all variables were normalized and segmentation by overlapping to avoid data discontinuity. The results showed that the use of the amount of data, learning rate, epoch, and selection of the right optimization model could give good accuracy. The purpose of the proper configuration has a good performance, with accuracy reaching 88.34%. The results showed that the use of SOI factors improved correctness from 74.75% without SOI. The results also show that the model Adaptive Moment Estimation (Adam) provides better accuracy than the model Stochastic Gradient Descent (SGD), which gives an accuracy of only 71.84%. Meanwhile, the study also examined the effect of the learning rate and composition of training data and test data. The best accuracy is shown for the learning rate of 0.020 and 80:20% of training and test data comparison.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114316927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274670
D. I. Sensuse, L. M. Hasani, B. Bagustari
Addressing different learner’s characteristics and needs is a critical issue in the process of learning. The advent of adaptive e-Learning technology has made it possible to tailor learning materials for different learner characteristics including learning styles. Delivering matching learning objects and strategies through an adaptive e-Learning system is believed to have a profound impact on learner’s learning performance. A body of research has offered various personalization strategies including learning object mapping according to learning styles. This paper focused on exploring how the learning objects are mapped to Felder-Silverman learning styles and the effect of implementing such approach. In this paper, 15 relevant publications were reviewed in order to gain some insights into the implementation of learning styles-based personalization. Based on the insights found this study proposed a conceptual learning object mapping and personalization strategies. The findings and recommendations of this study can be utilized as the basis to build an adaptive e-Learning system based on Felder-Silverman Learning Style Model (FSLSM).
{"title":"Personalization Strategies Based on Felder-Silverman Learning Styles and Its Impact on Learning: A Literature Review","authors":"D. I. Sensuse, L. M. Hasani, B. Bagustari","doi":"10.1109/IC2IE50715.2020.9274670","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274670","url":null,"abstract":"Addressing different learner’s characteristics and needs is a critical issue in the process of learning. The advent of adaptive e-Learning technology has made it possible to tailor learning materials for different learner characteristics including learning styles. Delivering matching learning objects and strategies through an adaptive e-Learning system is believed to have a profound impact on learner’s learning performance. A body of research has offered various personalization strategies including learning object mapping according to learning styles. This paper focused on exploring how the learning objects are mapped to Felder-Silverman learning styles and the effect of implementing such approach. In this paper, 15 relevant publications were reviewed in order to gain some insights into the implementation of learning styles-based personalization. Based on the insights found this study proposed a conceptual learning object mapping and personalization strategies. The findings and recommendations of this study can be utilized as the basis to build an adaptive e-Learning system based on Felder-Silverman Learning Style Model (FSLSM).","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123192964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274591
R. Afshari, Rimba Frida Pusparini, Muhammad Helmi Utomo, Favian Dewanta, R. Negara
The trend of internet of things (IoT) makes the cloud less effective because networked control systems need low latency while cloud have high latency for processing data from sensors and devices. In that kind of situation, fog computing is introduced as the complement of cloud computing. However, unlike cloud services, fog services are limited to certain geographical area. As a consequence, fog services handover is needed in order to accommodate user’s mobility. This paper is focusing on microservices handover that follows user’s movement. The microservices installed in the current fog node are sent to another service coverage of a new fog node for continuing the same service to the users. Fog node contains a docker that runs MySQL, python script, and busybox services. When it comes to handover, docker will freeze current session and convert it to a checkpoint file. The file is created by taking a snapshot of the container, which consists of processes in memory, volume or image. The file will be sent by using secure shell (SSH) or file transfer protocol (FTP). At the destination fog node, the file will be processed in order to resume the service. The results show that delay of SSH is always higher than FTP in all experiments, in which the largest delays are 484.026 seconds for SSH protocol and 146.41 seconds for FTP protocols. As for checkpoint and restore process, those delays tend to be similar with respect to both SSH and FTP protocols but they are still affected by the size of snapshot and checkpoint file.
{"title":"A Method for Microservices Handover in A Local Area Network","authors":"R. Afshari, Rimba Frida Pusparini, Muhammad Helmi Utomo, Favian Dewanta, R. Negara","doi":"10.1109/IC2IE50715.2020.9274591","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274591","url":null,"abstract":"The trend of internet of things (IoT) makes the cloud less effective because networked control systems need low latency while cloud have high latency for processing data from sensors and devices. In that kind of situation, fog computing is introduced as the complement of cloud computing. However, unlike cloud services, fog services are limited to certain geographical area. As a consequence, fog services handover is needed in order to accommodate user’s mobility. This paper is focusing on microservices handover that follows user’s movement. The microservices installed in the current fog node are sent to another service coverage of a new fog node for continuing the same service to the users. Fog node contains a docker that runs MySQL, python script, and busybox services. When it comes to handover, docker will freeze current session and convert it to a checkpoint file. The file is created by taking a snapshot of the container, which consists of processes in memory, volume or image. The file will be sent by using secure shell (SSH) or file transfer protocol (FTP). At the destination fog node, the file will be processed in order to resume the service. The results show that delay of SSH is always higher than FTP in all experiments, in which the largest delays are 484.026 seconds for SSH protocol and 146.41 seconds for FTP protocols. As for checkpoint and restore process, those delays tend to be similar with respect to both SSH and FTP protocols but they are still affected by the size of snapshot and checkpoint file.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123704779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274678
Nurul Fatimah, B. Mulyanti, R. Pawinanto, A. B. Pantjawati
The application of microchip technology has the potential to detect early health aspects. The mixing process in the medical laboratory examination with a blood check is important to determine the overall health condition and provide information on the disease suffered and also determine the treatment carried out or the next stage. This paper aims to study the simulation of microfluidic mixer devices based on flattening channels for blood mixing applications. The finite element analysis is used to study the effect of flattening channel geometry related to the microfluidic mixer performance. The results show that the mixing index above 0.98 is obtained which means the fluid was mixed homogenously. As a consequence, rapid and efficient mixing remains a challenging task within the design and development of micromixers. Furthermore, from the Reynolds number variations, it revealed that the mixing index increase when the Reynolds number increase.
{"title":"The Design of Microfluidic Mixer Based on Flattening for Blood Mixing Application","authors":"Nurul Fatimah, B. Mulyanti, R. Pawinanto, A. B. Pantjawati","doi":"10.1109/IC2IE50715.2020.9274678","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274678","url":null,"abstract":"The application of microchip technology has the potential to detect early health aspects. The mixing process in the medical laboratory examination with a blood check is important to determine the overall health condition and provide information on the disease suffered and also determine the treatment carried out or the next stage. This paper aims to study the simulation of microfluidic mixer devices based on flattening channels for blood mixing applications. The finite element analysis is used to study the effect of flattening channel geometry related to the microfluidic mixer performance. The results show that the mixing index above 0.98 is obtained which means the fluid was mixed homogenously. As a consequence, rapid and efficient mixing remains a challenging task within the design and development of micromixers. Furthermore, from the Reynolds number variations, it revealed that the mixing index increase when the Reynolds number increase.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121978498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274635
Richardo Antolis, A. Agus
The rise of online channel has shifted how Indonesian people purchase their product, making them exposed to multiple channel. Millennial mom is one of the most affected segments as they are willing to spend more time to research for products. This study aims to understand the effect of channel characteristic on the channel selection intention of millennial moms following the theory of planned behavior and commitment trust theory. The study uses a quantitative approach with questionnaire as the instrument for data collection. The study included 296 respondent which are divided into three groups based on their preferred purchasing channel. Data is processed using LISREL edition 8.80 software. The result of the study concluded that certain channel characteristic has an effect on channel selection intention of millennial moms.
{"title":"The Effect of Channel Characteristic on Millennial Moms Purchasing Behaviors of Baby Product","authors":"Richardo Antolis, A. Agus","doi":"10.1109/IC2IE50715.2020.9274635","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274635","url":null,"abstract":"The rise of online channel has shifted how Indonesian people purchase their product, making them exposed to multiple channel. Millennial mom is one of the most affected segments as they are willing to spend more time to research for products. This study aims to understand the effect of channel characteristic on the channel selection intention of millennial moms following the theory of planned behavior and commitment trust theory. The study uses a quantitative approach with questionnaire as the instrument for data collection. The study included 296 respondent which are divided into three groups based on their preferred purchasing channel. Data is processed using LISREL edition 8.80 software. The result of the study concluded that certain channel characteristic has an effect on channel selection intention of millennial moms.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114487484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-15DOI: 10.1109/IC2IE50715.2020.9274562
Maxalmina, Satria Kahfi, Kurniawan Nur Ramadhani, A. Arifianto
Lip motion recognition is a technique for interpreting visual data that focuses on the mouth area and aims to recognize lip movement. The development of lip motion recognition is expected to be used to develop communication tools with deaf people and to automate the speech-to-text process visually. In the Indonesian language, the existence of vowel phonemes is needed to produce sounds so that words and sentences in the Indonesian language can be formed. This paper proposes a model that can recognize Indonesian vowel phonemes (/a/, /i/, /u/, /e/, and /o/) in lip movements. We proposed a model that uses 3D Convolutional Neural Networks. The data in this paper were processed by resizing into 112x56 pixel resolution then, proceed to the data augmentation by reversing the data horizontally and add blur to the data. The results of the testing of the vowel phoneme recognition model on lip motion show the highest accuracy rate of 84%.
{"title":"Lip Motion Recognition for Indonesian Vowel Phonemes Using 3D Convolutional Neural Networks","authors":"Maxalmina, Satria Kahfi, Kurniawan Nur Ramadhani, A. Arifianto","doi":"10.1109/IC2IE50715.2020.9274562","DOIUrl":"https://doi.org/10.1109/IC2IE50715.2020.9274562","url":null,"abstract":"Lip motion recognition is a technique for interpreting visual data that focuses on the mouth area and aims to recognize lip movement. The development of lip motion recognition is expected to be used to develop communication tools with deaf people and to automate the speech-to-text process visually. In the Indonesian language, the existence of vowel phonemes is needed to produce sounds so that words and sentences in the Indonesian language can be formed. This paper proposes a model that can recognize Indonesian vowel phonemes (/a/, /i/, /u/, /e/, and /o/) in lip movements. We proposed a model that uses 3D Convolutional Neural Networks. The data in this paper were processed by resizing into 112x56 pixel resolution then, proceed to the data augmentation by reversing the data horizontally and add blur to the data. The results of the testing of the vowel phoneme recognition model on lip motion show the highest accuracy rate of 84%.","PeriodicalId":211983,"journal":{"name":"2020 3rd International Conference on Computer and Informatics Engineering (IC2IE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128579312","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：