Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288601
B. Krishnamurthy, S. Subramanian
We observe the impact of using category averaged feature vectors as intermediaries in predicting object categories from fMRI(Functional Magnetic Resonance Imaging) voxel activations. The validation accuracy of state-of-art prediction methods falls drastically when multiple classes are used at the same time, pointing towards the overlapping nature of representations in the voxel activations. To overcome this disadvantage, we map these overlapping representation to a more separable representation. The equivalent of these representations in the field of Computer Vision is a Convolutional Neural Network(CNN) feature vector. After taking into consideration the structural trade-offs the Ventral Temporal Cortex possesses to achieve efficient categorization, we designed a model whose architecture tries to mimic these functional nuances. There are two parts to the implementation - Estimation of feature vectors and efficient category prediction from the estimated feature vectors. We inspected the perceptual similarity of the estimated feature vectors by the use of Annoy tree. We found that Deep ReLU-MLP(Rectified Linear Unit-Multilayer Perceptron) performs better at decoding fMRI voxel activations compared to Sparse Linear Regressor. While inspecting the perceptual neighborhood of the decoded feature vector, we found a significantly higher percentage of the feature vectors predicted from visual perception experiments mapped to the correct neighborhood than in the case of visual imagery experiment.
{"title":"Mapping fMRI voxel activations to CNN feature space for ease of categorization","authors":"B. Krishnamurthy, S. Subramanian","doi":"10.1109/ICIC50835.2020.9288601","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288601","url":null,"abstract":"We observe the impact of using category averaged feature vectors as intermediaries in predicting object categories from fMRI(Functional Magnetic Resonance Imaging) voxel activations. The validation accuracy of state-of-art prediction methods falls drastically when multiple classes are used at the same time, pointing towards the overlapping nature of representations in the voxel activations. To overcome this disadvantage, we map these overlapping representation to a more separable representation. The equivalent of these representations in the field of Computer Vision is a Convolutional Neural Network(CNN) feature vector. After taking into consideration the structural trade-offs the Ventral Temporal Cortex possesses to achieve efficient categorization, we designed a model whose architecture tries to mimic these functional nuances. There are two parts to the implementation - Estimation of feature vectors and efficient category prediction from the estimated feature vectors. We inspected the perceptual similarity of the estimated feature vectors by the use of Annoy tree. We found that Deep ReLU-MLP(Rectified Linear Unit-Multilayer Perceptron) performs better at decoding fMRI voxel activations compared to Sparse Linear Regressor. While inspecting the perceptual neighborhood of the decoded feature vector, we found a significantly higher percentage of the feature vectors predicted from visual perception experiments mapped to the correct neighborhood than in the case of visual imagery experiment.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133778315","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288623
B. Haryanto, Arfive Gandhi, Yudho Giri Sucahyo
Electronic signature should accelerate and protect the electronic transactions in government agencies and non-governmental organizations, but its adoption is slow. Until the beginning of 2020, the number of organizations that utilize electronic signature is still very small compared to the number of organizations that have online service. This study aims to identify factors that determine employees in the organization to continue or are interested in utilizing electronic signature. The electronic signature referred to in this study is a certified electronic signature or digital signature. The survey was conducted on users and prospective users in government agencies and non-government organizations. The research uses an integrated framework Technology Acceptance Model (TAM) and Technology-Organization-Environment (TOE) in the information systems discipline. Based on 192 responses, the research framework is validated. Seven driving factors were successfully identified. The seven driving factors are security protection, internal need, training and education, government policy, vendor support, perceived ease of use, and perceived usefulness. The results of this study expand research on the adoption of electronic signature, and broaden research on technology acceptance models, specifically the TAM-TOE integration model. The findings of this study can be input for the government, electronic signature vendors, and organizations to increase the utilization of electronic signature.
{"title":"The Determinant Factors in Utilizing Electronic Signature Using the TAM and TOE Framework","authors":"B. Haryanto, Arfive Gandhi, Yudho Giri Sucahyo","doi":"10.1109/ICIC50835.2020.9288623","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288623","url":null,"abstract":"Electronic signature should accelerate and protect the electronic transactions in government agencies and non-governmental organizations, but its adoption is slow. Until the beginning of 2020, the number of organizations that utilize electronic signature is still very small compared to the number of organizations that have online service. This study aims to identify factors that determine employees in the organization to continue or are interested in utilizing electronic signature. The electronic signature referred to in this study is a certified electronic signature or digital signature. The survey was conducted on users and prospective users in government agencies and non-government organizations. The research uses an integrated framework Technology Acceptance Model (TAM) and Technology-Organization-Environment (TOE) in the information systems discipline. Based on 192 responses, the research framework is validated. Seven driving factors were successfully identified. The seven driving factors are security protection, internal need, training and education, government policy, vendor support, perceived ease of use, and perceived usefulness. The results of this study expand research on the adoption of electronic signature, and broaden research on technology acceptance models, specifically the TAM-TOE integration model. The findings of this study can be input for the government, electronic signature vendors, and organizations to increase the utilization of electronic signature.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131453312","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288534
Rianto, Achmad Benny Mutiara, Eri Prasetyo Wibowo, P. Insap Santosa
In verbal communication, people use sentences that can be classified into two categories, namely formal and non- formal. The former meets the grammatical standard as prescribed by linguistic rules of the language, while the latter deviates it. In daily communication, however, non-formal sentences are more intensively used because they are more practical and easier to understand. With this deviation, nonformal sentences cause problems in linguistic computation because most linguistic computations use formal languages that already have standard rules. This research aims to develop an Indonesian closed corpus related to airline ticket reservations. The data used to develop the corpus are taken from conversations between customer service staff and consumers in airline ticket reservations. This is a preliminary study to propose and develop a chatbot in airline ticket reservations. The result of this study is the Indonesian closed corpus related to airline ticket reservations to determine the right response for consumers.
{"title":"The Crowdsourcing Method to Normalize “Bahasa Alay”, a Case of Indonesian Corpus","authors":"Rianto, Achmad Benny Mutiara, Eri Prasetyo Wibowo, P. Insap Santosa","doi":"10.1109/ICIC50835.2020.9288534","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288534","url":null,"abstract":"In verbal communication, people use sentences that can be classified into two categories, namely formal and non- formal. The former meets the grammatical standard as prescribed by linguistic rules of the language, while the latter deviates it. In daily communication, however, non-formal sentences are more intensively used because they are more practical and easier to understand. With this deviation, nonformal sentences cause problems in linguistic computation because most linguistic computations use formal languages that already have standard rules. This research aims to develop an Indonesian closed corpus related to airline ticket reservations. The data used to develop the corpus are taken from conversations between customer service staff and consumers in airline ticket reservations. This is a preliminary study to propose and develop a chatbot in airline ticket reservations. The result of this study is the Indonesian closed corpus related to airline ticket reservations to determine the right response for consumers.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133287430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288597
Fx. Hendra Prasetya, Bernardinus Harnadi, Albertus Dwiyoga Widiantoro, A. Hidayanto, Agustinus Nugroho
This paper aims to investigate the influence of System and Service Quality on Customer Loyalty in their acceptance of e-marketplaces. The e-marketplaces are Tokopedia, Bukalapak, Lazada, Shopee, and others. Several variables from previous related studies on expectation-confirmation model (ECM) and TAM are employed on a proposed model to explore the customers' satisfaction and their impact on the acceptance of the e-marketplace. The model expresses the effect of System Quality, Service Quality on Confirmation and Satisfaction; Confirmation on Perceived Usefulness and Perceived Ease of Use; Perceived ease of use on Perceived Usefulness; Perceived Usefulness, and Confirmation on Satisfaction; and Perceived Usefulness and Satisfaction on Continuance Intension to use. The model was examined using 210 respondent data and Correlation Analysis was done after the validity and reliability check to reveal the correlation of variables. The analysis of the causal effects of variables is tested using Structural Equation Modelling (SEM) using Partial Least Square (PLS). The result reveals that the Satisfaction of customer of e-marketplace platforms was more affected by System Quality, Service Quality, and Confirmation than Perceived Usefulness. Whereas, the continued intention to use e-marketplace platform was determined by Perceived Usefulness and Satisfaction. The results have a contribution to e-marketplace players and developers who have a concern on customer loyalty to attract their continued intention in using the platform.
{"title":"Investigating the Impact of System and Service Qualities on Customer Loyalty in Acceptance of E-Marketplace","authors":"Fx. Hendra Prasetya, Bernardinus Harnadi, Albertus Dwiyoga Widiantoro, A. Hidayanto, Agustinus Nugroho","doi":"10.1109/ICIC50835.2020.9288597","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288597","url":null,"abstract":"This paper aims to investigate the influence of System and Service Quality on Customer Loyalty in their acceptance of e-marketplaces. The e-marketplaces are Tokopedia, Bukalapak, Lazada, Shopee, and others. Several variables from previous related studies on expectation-confirmation model (ECM) and TAM are employed on a proposed model to explore the customers' satisfaction and their impact on the acceptance of the e-marketplace. The model expresses the effect of System Quality, Service Quality on Confirmation and Satisfaction; Confirmation on Perceived Usefulness and Perceived Ease of Use; Perceived ease of use on Perceived Usefulness; Perceived Usefulness, and Confirmation on Satisfaction; and Perceived Usefulness and Satisfaction on Continuance Intension to use. The model was examined using 210 respondent data and Correlation Analysis was done after the validity and reliability check to reveal the correlation of variables. The analysis of the causal effects of variables is tested using Structural Equation Modelling (SEM) using Partial Least Square (PLS). The result reveals that the Satisfaction of customer of e-marketplace platforms was more affected by System Quality, Service Quality, and Confirmation than Perceived Usefulness. Whereas, the continued intention to use e-marketplace platform was determined by Perceived Usefulness and Satisfaction. The results have a contribution to e-marketplace players and developers who have a concern on customer loyalty to attract their continued intention in using the platform.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131470555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288554
I. Yudha Pratama, A. Wahab, M. Alaydrus
The hydroponic system is a development of traditional farming that substitute soil as a medium plant due to land limitation. Lettuce is the most popular hydroponic vegetable product in the market. However, during harvesting, there are huge challenges to ensure product quality especially for mass production has a better quality. In this research, we utilized Deep Learning as objection detection to recognize the disease in Hydroponic vegetables by using Faster R-CNN with Inception V2 algorithm and compare the performance by divided the ratio of training and validation dataset into 3 categories i.e. 78/9, 70/17, and 61/26 with the standard testing ratio for all categories is 13%. From this study we obtain a result that ratio 78/9 have a better performance with Accuracy 70%; Precision 97%; Recall 68% and F1 Score 80% however, ratio 61/26 has the lowest performance with Accuracy 40%; Precision 24%; Recall 100% and F1 Score 38,5% from 412 images dataset with 53 testing images with default learning rate setting 0.0002. As the result shown that the testing and validation ratio was affected by the deep learning model performances.
{"title":"Deep Learning for Assessing Unhealthy Lettuce Hydroponic Using Convolutional Neural Network based on Faster R-CNN with Inception V2","authors":"I. Yudha Pratama, A. Wahab, M. Alaydrus","doi":"10.1109/ICIC50835.2020.9288554","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288554","url":null,"abstract":"The hydroponic system is a development of traditional farming that substitute soil as a medium plant due to land limitation. Lettuce is the most popular hydroponic vegetable product in the market. However, during harvesting, there are huge challenges to ensure product quality especially for mass production has a better quality. In this research, we utilized Deep Learning as objection detection to recognize the disease in Hydroponic vegetables by using Faster R-CNN with Inception V2 algorithm and compare the performance by divided the ratio of training and validation dataset into 3 categories i.e. 78/9, 70/17, and 61/26 with the standard testing ratio for all categories is 13%. From this study we obtain a result that ratio 78/9 have a better performance with Accuracy 70%; Precision 97%; Recall 68% and F1 Score 80% however, ratio 61/26 has the lowest performance with Accuracy 40%; Precision 24%; Recall 100% and F1 Score 38,5% from 412 images dataset with 53 testing images with default learning rate setting 0.0002. As the result shown that the testing and validation ratio was affected by the deep learning model performances.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128601675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288651
S. Widiyanto, Jhordy Wong Abuhasan
Psychotest or psychological tests at this time are often applied in the process of selection of human resources aimed at measuring the potential of intelligence, recognizing personality, predicting work performance, mapping potential, and level of productivity. The Draw-A-Person test has been long applied to measure personality and to know the individual's creative experience. This test is widely used by psychologist institution in Psychotest because the implementation of test is quite simple that only use a pencil as well as paper. In practice, a psychologist takes quite a long time to assess the result of the Draw-A-Person test. To accelerated the required time and facilitate the work of a psychologist, a model is needed to recognize and classify the results of a Draw-A-Person test. This model is able to recognize and study the Draw-A-Person test result based on the head-size drawings on paper. Deep learning with a convolutional neural network method is applied to recognize and study the Draw-A-Person test result. To improve the usability of CNN method, the data is in the form of a digital image. The data is collected using a smartphone camera and labeled in Microsoft Excel one by one according to the criteria on the image. Data that has been labeled will be used to train the model. The trained model will be tested for new data. In this research, the data train achieves 99.48% accuracy and 1.74% loss. In the new data, the model achieved 66.7% accuracy
{"title":"Implementation The Convolutional Neural Network Method For Classification The Draw-A-Person Test","authors":"S. Widiyanto, Jhordy Wong Abuhasan","doi":"10.1109/ICIC50835.2020.9288651","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288651","url":null,"abstract":"Psychotest or psychological tests at this time are often applied in the process of selection of human resources aimed at measuring the potential of intelligence, recognizing personality, predicting work performance, mapping potential, and level of productivity. The Draw-A-Person test has been long applied to measure personality and to know the individual's creative experience. This test is widely used by psychologist institution in Psychotest because the implementation of test is quite simple that only use a pencil as well as paper. In practice, a psychologist takes quite a long time to assess the result of the Draw-A-Person test. To accelerated the required time and facilitate the work of a psychologist, a model is needed to recognize and classify the results of a Draw-A-Person test. This model is able to recognize and study the Draw-A-Person test result based on the head-size drawings on paper. Deep learning with a convolutional neural network method is applied to recognize and study the Draw-A-Person test result. To improve the usability of CNN method, the data is in the form of a digital image. The data is collected using a smartphone camera and labeled in Microsoft Excel one by one according to the criteria on the image. Data that has been labeled will be used to train the model. The trained model will be tested for new data. In this research, the data train achieves 99.48% accuracy and 1.74% loss. In the new data, the model achieved 66.7% accuracy","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128684730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288515
Sandy Kurniawan, I. Budi
In recent years, hate speech found in social media is increasing. The increase in the number of hate speech is caused by the increasing number of social media active users around the world. A lot of hate speech is aimed at governments or certain individuals. Hate speech is very harmful because it may affect the target negatively, whether the target is individuals or groups. Identification of targets in hate speech is crucial as it can be used to prevent the impact of hate speech such as exclusion, discrimination, and violence directed to the target in the hate speech. In this paper, we present our study in hate speech target classification in Indonesian Twitter. We studied hate speech target classification on Indonesian Twitter by comparing the classification performance based on the algorithms and feature representations used. Word n-grams were used as the feature representation combine with Bag-of-Words and Term Frequency - Inverse Document Frequency (TF-IDF). The classification was performed using Naive Bayes, Support Vector Machine (SVM), and Random Forest Decision Tree (RFDT). The best result achieved F1-score of 0.84772 when using TF-IDF with word unigram features combine with SVM classifier.
{"title":"Indonesian Tweets Hate Speech Target Classification using Machine Learning","authors":"Sandy Kurniawan, I. Budi","doi":"10.1109/ICIC50835.2020.9288515","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288515","url":null,"abstract":"In recent years, hate speech found in social media is increasing. The increase in the number of hate speech is caused by the increasing number of social media active users around the world. A lot of hate speech is aimed at governments or certain individuals. Hate speech is very harmful because it may affect the target negatively, whether the target is individuals or groups. Identification of targets in hate speech is crucial as it can be used to prevent the impact of hate speech such as exclusion, discrimination, and violence directed to the target in the hate speech. In this paper, we present our study in hate speech target classification in Indonesian Twitter. We studied hate speech target classification on Indonesian Twitter by comparing the classification performance based on the algorithms and feature representations used. Word n-grams were used as the feature representation combine with Bag-of-Words and Term Frequency - Inverse Document Frequency (TF-IDF). The classification was performed using Naive Bayes, Support Vector Machine (SVM), and Random Forest Decision Tree (RFDT). The best result achieved F1-score of 0.84772 when using TF-IDF with word unigram features combine with SVM classifier.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125527284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288545
Kevin Chantona, Ronsen Purba, Arwin Halim
Every trader in trading aspires to make the best decisions in buying and selling transactions and maximize the profits they get. The reinforcement learning method is a growing and popular method for making predictions in financial markets. After the AlphaGo defeated the strongest Go Contemporary board game player named Lee Sedol in 2016, this method creates a system capable of learning trading from itself. In a systematic review conducted by Terry Lingze Meng, all the latest articles related to stock and forex predictions that use reinforcement learning as the primary method only use past technical data as their state. In this study, the authors propose the implementation of word2vec and Recurrent Convolution Neural Network to provide the agent with the ability to read and process fundamental factors through the provided news headlines. The action augmentation technique reduces random exploration by the agent. The simulation will run on historical price changes for the seven most frequently traded currency pairs. This implementation demonstrates the impact of adding news headlines to improve risk management and lower the maximum withdrawal point value on almost all tested currency pairs with the highest increase of up to 57.9% on GBPUSD from 7.9% to 3.32%.
{"title":"News Sentiment Analysis in Forex Trading Using R-CNN on Deep Recurrent Q-Network","authors":"Kevin Chantona, Ronsen Purba, Arwin Halim","doi":"10.1109/ICIC50835.2020.9288545","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288545","url":null,"abstract":"Every trader in trading aspires to make the best decisions in buying and selling transactions and maximize the profits they get. The reinforcement learning method is a growing and popular method for making predictions in financial markets. After the AlphaGo defeated the strongest Go Contemporary board game player named Lee Sedol in 2016, this method creates a system capable of learning trading from itself. In a systematic review conducted by Terry Lingze Meng, all the latest articles related to stock and forex predictions that use reinforcement learning as the primary method only use past technical data as their state. In this study, the authors propose the implementation of word2vec and Recurrent Convolution Neural Network to provide the agent with the ability to read and process fundamental factors through the provided news headlines. The action augmentation technique reduces random exploration by the agent. The simulation will run on historical price changes for the seven most frequently traded currency pairs. This implementation demonstrates the impact of adding news headlines to improve risk management and lower the maximum withdrawal point value on almost all tested currency pairs with the highest increase of up to 57.9% on GBPUSD from 7.9% to 3.32%.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123196197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288563
G. Indrawan, Gede Rasben Dantes, Kadek Yota Ernanda Aryanto, I. Ketut Paramarta
This study is aimed at analyzing the handling of mathematical expression on the Latin-to-Balinese Script transliteration method since there has not been studied yet. It is one of the ways to preserve the endangered local culture knowledge through the collaboration between Computer Science and Language discipline. Moreover, this study was conducted on mobile computing that supports ubiquitous learning. There are three aspects related, i.e.; 1) Balinese Language uses verbal mathematical expression rather than mathematical expression using the notation in its Balinese writing; 2) In transliteration case, the Latin text of mathematical expression using notation should be preserved to avoid complexity related to various verbal mathematical expressions (which they have the same meaning); and 3) The second aspect was limitedly handled by the supporting computer font, which in this case is Bali Simbar Dwijendra (SD) font, and special algorithm needed to be applied on them. This research added a certain perspective and strengthened the transliteration knowledge, as part of Balinese Language ubiquitous learning that supports Balinese Language education, which is a mandatory local subject from basic to high school in Bali Province. This analysis was conducted on pioneering Aksara Bali SD mobile application that receives Latin text input and outputs Balinese Script based on Bali SD font. Through the experiment, it's handling of mathematical expression gave good transliteration results since a special rule-based algorithm was applied.
本研究旨在分析目前尚未研究的拉丁-巴厘文字转写法对数学表达式的处理。计算机科学与语言学科的合作是保护濒危地方文化知识的途径之一。此外，本研究是在支持泛在学习的移动计算上进行的。有三个方面是相关的，即;1)巴厘语在其巴厘文字中使用口头数学表达，而不是使用符号的数学表达;2)在音译的情况下，应保留使用表示法的数学表达式的拉丁文文本，以避免与各种口头数学表达式(它们具有相同的含义)相关的复杂性;3)第二方面的处理受限于支持的计算机字体，本例中使用的是Bali Simbar Dwijendra (SD)字体，需要对其应用特殊的算法。本研究增加了一定的视角，强化了音译知识，作为支持巴厘语教育的巴厘语泛在学习的一部分，巴厘语教育是巴厘省从基础到高中的地方必修科目。本分析是针对Aksara Bali SD手机应用程序进行的，该应用程序接收拉丁文本输入，并基于Bali SD字体输出Bali Script。通过实验，由于采用了一种特殊的基于规则的算法，它对数学表达式的处理取得了很好的音译效果。
{"title":"Handling of Mathematical Expression on Latin-to-Balinese Script Transliteration Method on Mobile Computing","authors":"G. Indrawan, Gede Rasben Dantes, Kadek Yota Ernanda Aryanto, I. Ketut Paramarta","doi":"10.1109/ICIC50835.2020.9288563","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288563","url":null,"abstract":"This study is aimed at analyzing the handling of mathematical expression on the Latin-to-Balinese Script transliteration method since there has not been studied yet. It is one of the ways to preserve the endangered local culture knowledge through the collaboration between Computer Science and Language discipline. Moreover, this study was conducted on mobile computing that supports ubiquitous learning. There are three aspects related, i.e.; 1) Balinese Language uses verbal mathematical expression rather than mathematical expression using the notation in its Balinese writing; 2) In transliteration case, the Latin text of mathematical expression using notation should be preserved to avoid complexity related to various verbal mathematical expressions (which they have the same meaning); and 3) The second aspect was limitedly handled by the supporting computer font, which in this case is Bali Simbar Dwijendra (SD) font, and special algorithm needed to be applied on them. This research added a certain perspective and strengthened the transliteration knowledge, as part of Balinese Language ubiquitous learning that supports Balinese Language education, which is a mandatory local subject from basic to high school in Bali Province. This analysis was conducted on pioneering Aksara Bali SD mobile application that receives Latin text input and outputs Balinese Script based on Bali SD font. Through the experiment, it's handling of mathematical expression gave good transliteration results since a special rule-based algorithm was applied.","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"171 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121925679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-03DOI: 10.1109/ICIC50835.2020.9288560
Lutfiah Zahara, Purnawarman Musa, Eri Prasetyo Wibowo, Irwan Karim, Saiful Bahri Musa
One of the ways humans communicate is by using facial expressions. Research on technology development in artificial intelligence uses deep learning methods in human and computer interactions as an effective system application process. One example, if someone does show and tries to recognize facial expressions when communicating. The prediction of the expression or emotion of some people who see it sometimes does not understand. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. This research proposes the design of a system that can predict and recognize the classification of facial emotions based on feature extraction using the Convolution Neural Network (CNN) algorithm in real-time with the OpenCV library, namely: TensorFlow and Keras. The research design implemented in the Raspberry Pi consists of three main processes, namely: face detection, facial feature extraction, and facial emotion classification. The prediction results of facial expressions in research with the Convolutional Neural Network (CNN) method using Facial Emotion Recognition (FER-2013) were 65.97% (sixty-five point ninety-seven percent)
{"title":"The Facial Emotion Recognition (FER-2013) Dataset for Prediction System of Micro-Expressions Face Using the Convolutional Neural Network (CNN) Algorithm based Raspberry Pi","authors":"Lutfiah Zahara, Purnawarman Musa, Eri Prasetyo Wibowo, Irwan Karim, Saiful Bahri Musa","doi":"10.1109/ICIC50835.2020.9288560","DOIUrl":"https://doi.org/10.1109/ICIC50835.2020.9288560","url":null,"abstract":"One of the ways humans communicate is by using facial expressions. Research on technology development in artificial intelligence uses deep learning methods in human and computer interactions as an effective system application process. One example, if someone does show and tries to recognize facial expressions when communicating. The prediction of the expression or emotion of some people who see it sometimes does not understand. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. This research proposes the design of a system that can predict and recognize the classification of facial emotions based on feature extraction using the Convolution Neural Network (CNN) algorithm in real-time with the OpenCV library, namely: TensorFlow and Keras. The research design implemented in the Raspberry Pi consists of three main processes, namely: face detection, facial feature extraction, and facial emotion classification. The prediction results of facial expressions in research with the Convolutional Neural Network (CNN) method using Facial Emotion Recognition (FER-2013) were 65.97% (sixty-five point ninety-seven percent)","PeriodicalId":413610,"journal":{"name":"2020 Fifth International Conference on Informatics and Computing (ICIC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115783975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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：