Pub Date : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878514
Arief Bramanto Wicaksono Putra, A. F. O. Gaffar
Density-based clustering is related to the value space surrounding non-data points with data points. This algorithm uses a multi-resolution grid data structure and uses grid density to form clusters. The density-based clustering algorithm starts by determining the size or threshold of cluster density. In this study, density-based clustering is used to group the electrical power usage dataset into three density clusters (low, medium, and high density). The electrical power usage dataset has two attributes: the actual use and ideal use. The generation of the ideal use data for both UOL (Usage Off-peak Load) and UPL (Usage Peak Load) is using two scenarios: worst and best scenario. The application of these two scenarios is expected to provide a significant difference in performance. The cluster density threshold is determined based on the selection of the extreme distance range between data points (min and max). The purpose of the use of this clustering technique is to obtain the pattern of electrical power usage per month represented by the density level of each cluster. All the members of the high-density cluster are then used to measure its performance. The results of the study showed that the average performance of −17.48% (over kWh). The total performance of the usage load between the worst and best scenario was not so significantly different (25.15% of the best scenario) compared to the generation results of the ideal use data for both scenarios (682% of the best scenario). This result can be an indication of other factors contributing to these conditions which need to be analyzed in more depth, perhaps one of which is the aspect of the feasibility of existing electrical installations.
{"title":"Measurement of Electrical Power Usage Performance using Density Based Clustering Approach","authors":"Arief Bramanto Wicaksono Putra, A. F. O. Gaffar","doi":"10.1109/EIConCIT.2018.8878514","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878514","url":null,"abstract":"Density-based clustering is related to the value space surrounding non-data points with data points. This algorithm uses a multi-resolution grid data structure and uses grid density to form clusters. The density-based clustering algorithm starts by determining the size or threshold of cluster density. In this study, density-based clustering is used to group the electrical power usage dataset into three density clusters (low, medium, and high density). The electrical power usage dataset has two attributes: the actual use and ideal use. The generation of the ideal use data for both UOL (Usage Off-peak Load) and UPL (Usage Peak Load) is using two scenarios: worst and best scenario. The application of these two scenarios is expected to provide a significant difference in performance. The cluster density threshold is determined based on the selection of the extreme distance range between data points (min and max). The purpose of the use of this clustering technique is to obtain the pattern of electrical power usage per month represented by the density level of each cluster. All the members of the high-density cluster are then used to measure its performance. The results of the study showed that the average performance of −17.48% (over kWh). The total performance of the usage load between the worst and best scenario was not so significantly different (25.15% of the best scenario) compared to the generation results of the ideal use data for both scenarios (682% of the best scenario). This result can be an indication of other factors contributing to these conditions which need to be analyzed in more depth, perhaps one of which is the aspect of the feasibility of existing electrical installations.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124987056","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878511
U. Pujianto, Nur A’yuni Ramadhani, A. Wibawa
Chronic kidney disease is a kidney disease in which there is a function loss of kidney and it is occurred overtimes and years. This disease is perceptible until the kidney losses 25% of its function. Chronic kidney disease requires a correct and appropriate diagnostic process in order to provide relevant and proper treatment which is in accordance with the diagnosis. Using current developed technology, the diagnosis process can be easily conducted. The diagnosis can be carried out by employing data mining techniques such as clustering and classification. This study seeks to explore the implementation of the K-Means algorithm as a clustering algorithm and Support Vector Machine algorithm as a classification algorithm. Clustering process is used to determine data on the pure cluster then the data will be classified using the Support Vector Machine algorithm. In the classification process with the Support Vector Machine algorithm, various non-linear kernels such as polynomial kernels, RBF kernels, and sigmoid kernels are used. Based on the research results, the highest accuracy is obtained from the classification process with two clusters, which is 100% in all kernel functions. As for the highest accuracy in the classification with three clusters, four clusters, and five clusters are generated by the classification process using the RBF kernel.
{"title":"Support Vector Machine with Purified K-Means Clusters for Chronic Kidney Disease Detection","authors":"U. Pujianto, Nur A’yuni Ramadhani, A. Wibawa","doi":"10.1109/EIConCIT.2018.8878511","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878511","url":null,"abstract":"Chronic kidney disease is a kidney disease in which there is a function loss of kidney and it is occurred overtimes and years. This disease is perceptible until the kidney losses 25% of its function. Chronic kidney disease requires a correct and appropriate diagnostic process in order to provide relevant and proper treatment which is in accordance with the diagnosis. Using current developed technology, the diagnosis process can be easily conducted. The diagnosis can be carried out by employing data mining techniques such as clustering and classification. This study seeks to explore the implementation of the K-Means algorithm as a clustering algorithm and Support Vector Machine algorithm as a classification algorithm. Clustering process is used to determine data on the pure cluster then the data will be classified using the Support Vector Machine algorithm. In the classification process with the Support Vector Machine algorithm, various non-linear kernels such as polynomial kernels, RBF kernels, and sigmoid kernels are used. Based on the research results, the highest accuracy is obtained from the classification process with two clusters, which is 100% in all kernel functions. As for the highest accuracy in the classification with three clusters, four clusters, and five clusters are generated by the classification process using the RBF kernel.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128285207","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 : 2018-11-01DOI: 10.1109/eiconcit.2018.8878561
{"title":"EIConCIT 2018 Call for Paper","authors":"","doi":"10.1109/eiconcit.2018.8878561","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878561","url":null,"abstract":"","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124497578","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878575
Muhammad Faisal, Rahman, Fadly Shabir, Ida
Indonesia’s plantation sector contributes significantly to gross domestic product (GDP). Not only local, plantation products such as oil palm, cocoa, rubber, coffee and pepper have become international trade commodities, and place Indonesia as one of the main countries in the trading of these commodities. Ironically, farmers as the initial source of the trade chain often do not get maximum benefits, due to price fluctuations as a result of the instability of the rupiah exchange rate. This instability is an opportunity for fraudulent traders to play prices at the farmer level. The government as a price regulator and guarantor of economic justice, is responsible for socializing prices as a form of prolonged protection for farmers. The problem is that the plantation area and the farmer’s dwellings are scattered to remote areas, making it difficult for the government to socialize prices at any time. Therefore, the presence of an information system on the spread of agricultural commodity prices based on SMS auto-reply, can be an information sharing solution. The application and testing of the message delivery system was 100% successful, without failure to send messages at each level. The test is carried out with 3 system condition scenarios, first: the server condition is dead, second: the smartphone is dead and third: the cellular phone is out of network coverage. Each scenario uses 3 smartphones for 3 groups of SMS senders, with each of 10 different cell phones. The test results show this system can be an alternative distribution of commodity price information with the support of cellular communication infrastructure that functions well into remote areas.
{"title":"Design and Implementation of Plantation Commodities Price Information Broadcaster via Autoreply Short Message Service on Smartphone","authors":"Muhammad Faisal, Rahman, Fadly Shabir, Ida","doi":"10.1109/EIConCIT.2018.8878575","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878575","url":null,"abstract":"Indonesia’s plantation sector contributes significantly to gross domestic product (GDP). Not only local, plantation products such as oil palm, cocoa, rubber, coffee and pepper have become international trade commodities, and place Indonesia as one of the main countries in the trading of these commodities. Ironically, farmers as the initial source of the trade chain often do not get maximum benefits, due to price fluctuations as a result of the instability of the rupiah exchange rate. This instability is an opportunity for fraudulent traders to play prices at the farmer level. The government as a price regulator and guarantor of economic justice, is responsible for socializing prices as a form of prolonged protection for farmers. The problem is that the plantation area and the farmer’s dwellings are scattered to remote areas, making it difficult for the government to socialize prices at any time. Therefore, the presence of an information system on the spread of agricultural commodity prices based on SMS auto-reply, can be an information sharing solution. The application and testing of the message delivery system was 100% successful, without failure to send messages at each level. The test is carried out with 3 system condition scenarios, first: the server condition is dead, second: the smartphone is dead and third: the cellular phone is out of network coverage. Each scenario uses 3 smartphones for 3 groups of SMS senders, with each of 10 different cell phones. The test results show this system can be an alternative distribution of commodity price information with the support of cellular communication infrastructure that functions well into remote areas.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"321 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124545259","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878519
Veronica Ernita Kristianti, E. P. Wibowo, Atit Pertiwi, Hamzah Afandi, Busono Soerowirdjo
The data security or information of any kind is essential to maintain its confidentiality. For that reason, we need a system that can maintain the security of such information. DES (Data Encryption Standard) becomes one of the algorithms that can be used in data and information security system. In this paper, we propose to get the best DES algorithm to apply on System on Chip (SoC). The analysis was performed by comparing between the 16-round pipelines DES algorithms which is the general DES algorithm with the 8-round pipeline DES algorithm which is the result of efficiency. The analysis was done with VHDL (Verilog High Definition Language) design language model and synthesized using XC3ES500E Field Programmable Gate Array (FPGA). The result of the average analysis of the overall resources required by each of the DES algorithms compared is that the 16-round DES requires an average of 21.2% of the resources, while the 8-round DES requires an average of only 9.7%. This shows that the 8-round DES pipeline algorithm is the best and efficient DES algorithm to apply on SoC as a data and information security system.
任何类型的数据安全或信息对于保持其机密性至关重要。因此，我们需要一个能够维护这些信息安全的系统。DES (Data Encryption Standard，数据加密标准)成为数据和信息安全系统中可以使用的算法之一。在本文中，我们提出了最好的DES算法应用于片上系统(SoC)。将16轮管道DES算法(一般DES算法)与8轮管道DES算法(效率结果)进行比较分析。采用VHDL (Verilog High Definition Language)设计语言模型进行分析，并利用XC3ES500E现场可编程门阵列(FPGA)进行综合。对每一种DES算法所需要的总体资源进行平均分析比较的结果是，16轮DES平均需要21.2%的资源，而8轮DES平均只需要9.7%的资源。这表明8轮DES流水线算法是最适合应用于SoC数据和信息安全系统的高效DES算法。
{"title":"Finding an Efficient FPGA Implementation of the DES Algorithm to Support the Processor Chip on Smartcard","authors":"Veronica Ernita Kristianti, E. P. Wibowo, Atit Pertiwi, Hamzah Afandi, Busono Soerowirdjo","doi":"10.1109/EIConCIT.2018.8878519","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878519","url":null,"abstract":"The data security or information of any kind is essential to maintain its confidentiality. For that reason, we need a system that can maintain the security of such information. DES (Data Encryption Standard) becomes one of the algorithms that can be used in data and information security system. In this paper, we propose to get the best DES algorithm to apply on System on Chip (SoC). The analysis was performed by comparing between the 16-round pipelines DES algorithms which is the general DES algorithm with the 8-round pipeline DES algorithm which is the result of efficiency. The analysis was done with VHDL (Verilog High Definition Language) design language model and synthesized using XC3ES500E Field Programmable Gate Array (FPGA). The result of the average analysis of the overall resources required by each of the DES algorithms compared is that the 16-round DES requires an average of 21.2% of the resources, while the 8-round DES requires an average of only 9.7%. This shows that the 8-round DES pipeline algorithm is the best and efficient DES algorithm to apply on SoC as a data and information security system.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"25 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125893440","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878629
Salma, R. F. Olanrewaju, K. Abdullah, Rusmala, Herdianti Darwis
Cloud computing is an IT model that offers a large number of storage space, unbelievable computing power and inconceivable speed of calculations. There are a number of costumers like corporate components, social media programs and individual customers are all moving towards to the vast area of cloud computing. The importance of cloud computing comes out with the security of data accessibility, reliability and reliability of information. The verification and permission is more necessary to access information as “cloud” is only assortment of actual super computer speed through the world. There are many research has been done on security of file encryption with AES algorithm. There is no any successful attack yet against AES but because of a higher increasing of cybercrime it could be possible attack on it like brute force attack and algebraic attack. Hence, in this research has been proposed a hybrid structure of Dynamic AES (DAES) and Blowfish algorithms. This procedure specifies the security of uploaded file on the cloud with a strong encryption method and also the privacy and reliability of submitted information of a user with considering performance of speed.
{"title":"Enhancing Cloud Data Security Using Hybrid of Advanced Encryption Standard and Blowfish Encryption Algorithms","authors":"Salma, R. F. Olanrewaju, K. Abdullah, Rusmala, Herdianti Darwis","doi":"10.1109/EIConCIT.2018.8878629","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878629","url":null,"abstract":"Cloud computing is an IT model that offers a large number of storage space, unbelievable computing power and inconceivable speed of calculations. There are a number of costumers like corporate components, social media programs and individual customers are all moving towards to the vast area of cloud computing. The importance of cloud computing comes out with the security of data accessibility, reliability and reliability of information. The verification and permission is more necessary to access information as “cloud” is only assortment of actual super computer speed through the world. There are many research has been done on security of file encryption with AES algorithm. There is no any successful attack yet against AES but because of a higher increasing of cybercrime it could be possible attack on it like brute force attack and algebraic attack. Hence, in this research has been proposed a hybrid structure of Dynamic AES (DAES) and Blowfish algorithms. This procedure specifies the security of uploaded file on the cloud with a strong encryption method and also the privacy and reliability of submitted information of a user with considering performance of speed.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130555796","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878591
Muladi, Sherly Allsa Siregar, A. Wibawa
One of the most used method for forecasting is Artificial Neural Network (ANN). The success of ANN to solve the problem depends on the input data. Improving data quality can be done by smoothing the input data. In this study, smoothing data will be done using Exponential Smoothing (ES) approach. We use exchange rate of Indonesia Rupiah (IDR) against US Dollar (USD) from January 2016 to December 2017 for the data research. This research the forecasting using ANN with smoothing process in the data input using Double Exponential Smoothing (DES) will compared with the forecasting using ANN with original data input and forecasting using ANN with smoothing process in the data input using Single Exponential Smoothing (SES) as a model. The model’s performance will have measured using error value and execution time. This research concludes that Double Exponential Smoothing (DES) method can improve the performance of ANN on IDR/USD exchange rate forecasting, it produces 0.530% of MAPE values and takes 561s for time execution, and also, we conclude that DES is better than SES to improve ANN performance for exchange rate forecasting.
{"title":"Double Exponential-Smoothing Neural Network for Foreign Exchange Rate Forecasting","authors":"Muladi, Sherly Allsa Siregar, A. Wibawa","doi":"10.1109/EIConCIT.2018.8878591","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878591","url":null,"abstract":"One of the most used method for forecasting is Artificial Neural Network (ANN). The success of ANN to solve the problem depends on the input data. Improving data quality can be done by smoothing the input data. In this study, smoothing data will be done using Exponential Smoothing (ES) approach. We use exchange rate of Indonesia Rupiah (IDR) against US Dollar (USD) from January 2016 to December 2017 for the data research. This research the forecasting using ANN with smoothing process in the data input using Double Exponential Smoothing (DES) will compared with the forecasting using ANN with original data input and forecasting using ANN with smoothing process in the data input using Single Exponential Smoothing (SES) as a model. The model’s performance will have measured using error value and execution time. This research concludes that Double Exponential Smoothing (DES) method can improve the performance of ANN on IDR/USD exchange rate forecasting, it produces 0.530% of MAPE values and takes 561s for time execution, and also, we conclude that DES is better than SES to improve ANN performance for exchange rate forecasting.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134604418","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878593
A. Lawi, F. Aziz
ASD sufferers face difficulties in early development compared to normal humans. Various tools, clinical, and non-clinical approaches have been implemented but take a long time to produce a complete diagnosis. the solution by adopting machine learning. This study proposes the application of cross-validation techniques in the Decision Tree method, Linear Discriminant Analysis, Logistic Regression, SVM, and KNN and determines the best k value in each classification method because the shift of datasets when using cross-validation techniques in the classification method is one factor that can cause the estimate to be inaccurate. The results show that the decision tree provides an accuracy of 100% in each of the k values that have been determined previously. 96.9% on Linear Discriminant Analysis with $k=7, k=9$, and $k =10$. 99.7% in Logistic Regression with values of $k=2$ and $k= 3$. 99.9% in Support Vector Machine with values of $k=9$ and $k =1theta$ and 94.2% for K-Nearest Neighbors with a value of $k=8$.
{"title":"Comparison of Classification Algorithms of the Autism Spectrum Disorder Diagnosis","authors":"A. Lawi, F. Aziz","doi":"10.1109/EIConCIT.2018.8878593","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878593","url":null,"abstract":"ASD sufferers face difficulties in early development compared to normal humans. Various tools, clinical, and non-clinical approaches have been implemented but take a long time to produce a complete diagnosis. the solution by adopting machine learning. This study proposes the application of cross-validation techniques in the Decision Tree method, Linear Discriminant Analysis, Logistic Regression, SVM, and KNN and determines the best k value in each classification method because the shift of datasets when using cross-validation techniques in the classification method is one factor that can cause the estimate to be inaccurate. The results show that the decision tree provides an accuracy of 100% in each of the k values that have been determined previously. 96.9% on Linear Discriminant Analysis with $k=7, k=9$, and $k =10$. 99.7% in Logistic Regression with values of $k=2$ and $k= 3$. 99.9% in Support Vector Machine with values of $k=9$ and $k =1theta$ and 94.2% for K-Nearest Neighbors with a value of $k=8$.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134241494","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}
Color blindness or color vision deficiency (CVD) is a physical disorder causing patients hardly to recognize or to distinguish certain colors. It might make some tasks on daily basis more challenging particularly in dealing with certain jobs requiring high visual acuity. In this research, augmented reality (AR), text-to-speech (TTS) system, and midpoint algorithm as color pixel detector were implemented in developing an application to support people with CVD. The application provides a convenient way to recognize colors using an Android smartphone camera. Four experiments were designed to measure how the application works; a drinking bottle was used as the first experiment object, the second and third experiments were designed to perceive the result of the same object but different contrasts, the fourth is a testing on printed colors. This research has figured out that the algorithm works well to recognize the color pixel and so does the TTS system because the average result of the detection rate was 85% with normal lighting level and 80% of response time of TTS system.
{"title":"Implementation of Augmented Reality, TTS, and Midpoint Algorithm in Supporting People with Color Vision Deficiency","authors":"Irawati, Ahyar Muawwal, Herdianti Darwis, Harlinda Lahuddin, Sugiarti, Lilis Nur Hayati","doi":"10.1109/EIConCIT.2018.8878518","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878518","url":null,"abstract":"Color blindness or color vision deficiency (CVD) is a physical disorder causing patients hardly to recognize or to distinguish certain colors. It might make some tasks on daily basis more challenging particularly in dealing with certain jobs requiring high visual acuity. In this research, augmented reality (AR), text-to-speech (TTS) system, and midpoint algorithm as color pixel detector were implemented in developing an application to support people with CVD. The application provides a convenient way to recognize colors using an Android smartphone camera. Four experiments were designed to measure how the application works; a drinking bottle was used as the first experiment object, the second and third experiments were designed to perceive the result of the same object but different contrasts, the fourth is a testing on printed colors. This research has figured out that the algorithm works well to recognize the color pixel and so does the TTS system because the average result of the detection rate was 85% with normal lighting level and 80% of response time of TTS system.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115238282","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 : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878640
Eki Nugraha, Alifia Chinka Rizal Muhammad, L. Riza, Haviluddin
Sundanese characters are one of the original Sundanese historical relics that have existed since the 5th century and have become the writing language at that time. Classification of handwriting characters is a challenge because the results of handwriting are very diverse, including the characters of handwritten characters. The number of feature extraction methods that can be used in the classification process, but not all feature extraction methods are in accordance with the characteristics of the Sundanese characters. Therefore, the focus of this research is to find the optimal feature extraction method to classify the character of Sundanese characters, in order to get better accuracy by running some experiments. Feature extraction methods proposed in this research are zoning, histograms and structural approaches. Then, some following classifier methods are used for constructing models and prediction over new data: Random Forest (RF), K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Based on the experiments, we can state that RF provided the best results (i.e., 89.84% in average) while the optimal feature-constructing method is by using the structural approach.
{"title":"Experimental Study on Zoning, Histogram, and Structural Methods to Classify Sundanese Characters from Handwriting","authors":"Eki Nugraha, Alifia Chinka Rizal Muhammad, L. Riza, Haviluddin","doi":"10.1109/EIConCIT.2018.8878640","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878640","url":null,"abstract":"Sundanese characters are one of the original Sundanese historical relics that have existed since the 5th century and have become the writing language at that time. Classification of handwriting characters is a challenge because the results of handwriting are very diverse, including the characters of handwritten characters. The number of feature extraction methods that can be used in the classification process, but not all feature extraction methods are in accordance with the characteristics of the Sundanese characters. Therefore, the focus of this research is to find the optimal feature extraction method to classify the character of Sundanese characters, in order to get better accuracy by running some experiments. Feature extraction methods proposed in this research are zoning, histograms and structural approaches. Then, some following classifier methods are used for constructing models and prediction over new data: Random Forest (RF), K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Based on the experiments, we can state that RF provided the best results (i.e., 89.84% in average) while the optimal feature-constructing method is by using the structural approach.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"48 19","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113936997","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：