Pub Date : 2018-11-01DOI: 10.1109/EIConCIT.2018.8878550
Achmad Maududie, Windi Eka Yulia Retnani, Muhamat Abdul Rohim
The high growth of news document emerging a new problem when the news website does not provide downloading service. This paper describes an approach of providing title, publication date, author, clean text article, and URL address of news article from HTML page of three news web-sites, i.e., Detik, Tribunnews, and Liputan6 without manually copy and paste process. This approach consists of three steps, i.e.: analyzing news website structure, constructing pattern of Regex and implementing the patterns as a set of rule in web scraping. Based on the experiment, each news web site used their own pattern for article link, article title, article author, and publication date of article. Special for extracting a clean text of news article phase, there were two kinds of pattern i.e.: content pattern (for extracting original text article of news) and filter pattern (for eliminating non-news elements). In these three-news website, the non-news elements consist of text advertisement, video advertisement, link, image, and script with different pattern for every website. After generated all necessary patterns and implemented these patterns as a set of rules, the web scraping module produced very good results of news article extraction on Detik and Tribunnews that was presented by recall = 1, precision = 1 and F-Measure =100% while Liputan6 had a little bit lower i.e., recall =0.95, precision =0.95, and F-Measure =95%. It is found that this approach is a simple and strait forward way to extract news article which consists of title, publication date, author, news article, and the URL address of news article.
{"title":"An Approach of Web Scraping on News Website based on Regular Expression","authors":"Achmad Maududie, Windi Eka Yulia Retnani, Muhamat Abdul Rohim","doi":"10.1109/EIConCIT.2018.8878550","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878550","url":null,"abstract":"The high growth of news document emerging a new problem when the news website does not provide downloading service. This paper describes an approach of providing title, publication date, author, clean text article, and URL address of news article from HTML page of three news web-sites, i.e., Detik, Tribunnews, and Liputan6 without manually copy and paste process. This approach consists of three steps, i.e.: analyzing news website structure, constructing pattern of Regex and implementing the patterns as a set of rule in web scraping. Based on the experiment, each news web site used their own pattern for article link, article title, article author, and publication date of article. Special for extracting a clean text of news article phase, there were two kinds of pattern i.e.: content pattern (for extracting original text article of news) and filter pattern (for eliminating non-news elements). In these three-news website, the non-news elements consist of text advertisement, video advertisement, link, image, and script with different pattern for every website. After generated all necessary patterns and implemented these patterns as a set of rules, the web scraping module produced very good results of news article extraction on Detik and Tribunnews that was presented by recall = 1, precision = 1 and F-Measure =100% while Liputan6 had a little bit lower i.e., recall =0.95, precision =0.95, and F-Measure =95%. It is found that this approach is a simple and strait forward way to extract news article which consists of title, publication date, author, news article, and the URL address of news article.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"47 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":"121276140","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.2018.8878564
Andi Tejawati, H. S. Pakpahan, Wahyu Susantini
To find out the level of drug addicts, a system that can process predetermined criteria is needed. The system is a decision support system using the SMART method. The purpose of this study is to create a decision support system to help drug addicts to know that someone is classified as a mild, moderate or severe addict with several criteria that must be chosen by addicts, before choosing criteria for an addict to do the screening process first. Collecting data in this study uses literature study techniques, interviews, and observations in data collection. The system development uses the waterfall method. Analysis and design modeling use Laravel framework with PHP programming language and MySQL database server. The test method uses black-box testing, testing calculations and testing the comparison of real data with data that has been applied to the SMART method with a success of 75.37%. The results of this study are a decision support system for diagnosing drug addicts so that a drug addict can find out the level of addicts and solutions and descriptions of the results of the diagnosis.
{"title":"Drugs Diagnose Level using Simple Multi-Attribute Rating Technique (SMART)","authors":"Andi Tejawati, H. S. Pakpahan, Wahyu Susantini","doi":"10.1109/EIConCIT.2018.8878564","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878564","url":null,"abstract":"To find out the level of drug addicts, a system that can process predetermined criteria is needed. The system is a decision support system using the SMART method. The purpose of this study is to create a decision support system to help drug addicts to know that someone is classified as a mild, moderate or severe addict with several criteria that must be chosen by addicts, before choosing criteria for an addict to do the screening process first. Collecting data in this study uses literature study techniques, interviews, and observations in data collection. The system development uses the waterfall method. Analysis and design modeling use Laravel framework with PHP programming language and MySQL database server. The test method uses black-box testing, testing calculations and testing the comparison of real data with data that has been applied to the SMART method with a success of 75.37%. The results of this study are a decision support system for diagnosing drug addicts so that a drug addict can find out the level of addicts and solutions and descriptions of the results of the diagnosis.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"179 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":"114829526","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}
In the digital era like now almost all transactions are done in online. However, information on the results of transactions sent through digital communication channels are very vulnerable to counterfeiting attacks. Therefore, it is made to ensure that the received message information is still intact and genuine. A MAC is a cryptographic algorithm that is suitable and widely used as a solution for such problems even though there are still many tricks that can be used by attackers to find fake messages for deceive other parties. The secure Ok-MAC algorithm developed in this paper is that enhanced MAC uses a message digest based on a hybrid of two existing message digests using just one key. The test results show that for the small-sized message the MAC algorithm Ok-MAC is slightly slower (26.53 ms) than the HMAC-SHA-1 (24.94 ms) and Ok-MAC is expected to validate the integrity and authenticity of the sort message well.
{"title":"Enhanced MAC based on Hybrid-MD Algorithm","authors":"Muslim Muslim, Suarga Suarga, As’ad Djamalilleil, Fitriyani Umar, Mardiyyah Hasnawi, Syahrul Mubarak","doi":"10.1109/EIConCIT.2018.8878523","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878523","url":null,"abstract":"In the digital era like now almost all transactions are done in online. However, information on the results of transactions sent through digital communication channels are very vulnerable to counterfeiting attacks. Therefore, it is made to ensure that the received message information is still intact and genuine. A MAC is a cryptographic algorithm that is suitable and widely used as a solution for such problems even though there are still many tricks that can be used by attackers to find fake messages for deceive other parties. The secure Ok-MAC algorithm developed in this paper is that enhanced MAC uses a message digest based on a hybrid of two existing message digests using just one key. The test results show that for the small-sized message the MAC algorithm Ok-MAC is slightly slower (26.53 ms) than the HMAC-SHA-1 (24.94 ms) and Ok-MAC is expected to validate the integrity and authenticity of the sort message well.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"15 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":"122605136","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.2018.8878535
Toni Wijanarko Adi Putra, Joko Minardi, A. F. O. Gaffar, B. Suprapty, R. Malani, Supriadi
Face recognition system is the development of basic methods of authentication systems by using the natural characteristics of the human face as a basis. The process of recognizing the facial image through several stages of the training phase and testing phase. This study has used datasets in the form of facial image samples obtained with various light intensities, distances, and positions toward the acquisition devices. This study has implemented the Centroid method and Canny edge detection to get image patterns from preprocessed image samples. Image features were obtained from image patterns using Gray Level Co-occurrence Matrix (GLCM). PNN has used as a classification of image patterns. The results of this study showed that the combination of the Centroid and GLCM methods (accuracy of 93.33%) is better than the combination of Canny edge detection and the GLCM method (accuracy of 66.43%). The results of this study also showed that the farther the spatial distance to build the GLCM features, the lower the accuracy.
{"title":"Comparison of Canny and Centroid on Face Recognition Process using Gray Level Cooccurrence Matrix and Probabilistic Neural Network","authors":"Toni Wijanarko Adi Putra, Joko Minardi, A. F. O. Gaffar, B. Suprapty, R. Malani, Supriadi","doi":"10.1109/EIConCIT.2018.8878535","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878535","url":null,"abstract":"Face recognition system is the development of basic methods of authentication systems by using the natural characteristics of the human face as a basis. The process of recognizing the facial image through several stages of the training phase and testing phase. This study has used datasets in the form of facial image samples obtained with various light intensities, distances, and positions toward the acquisition devices. This study has implemented the Centroid method and Canny edge detection to get image patterns from preprocessed image samples. Image features were obtained from image patterns using Gray Level Co-occurrence Matrix (GLCM). PNN has used as a classification of image patterns. The results of this study showed that the combination of the Centroid and GLCM methods (accuracy of 93.33%) is better than the combination of Canny edge detection and the GLCM method (accuracy of 66.43%). The results of this study also showed that the farther the spatial distance to build the GLCM features, the lower the accuracy.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"32 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":"133522370","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.2018.8878618
Rosmasari, N. Puspitasari, Vinda Nur Vadilla, U. Hairah, Huzain Azis, Haviluddin, M. Wati, E. Budiman
Usability is a key factor that determines the success of a management software or interactive system, like student academic portal. The increasing usage of a portal requires usability evaluation method that is more accurate and effective to found usability problem, so it can be used for management service improvement in the academic process. The study aims to analyze the feasibility level of using a student academic portal. There are two methods that we using to find problems of convenience, i.e. Think Aloud Evaluation (TA), and Heuristic Evaluation. The study has resulted in the main factors affect the service capabilities of a student academic portal, revealing all the strengths and weaknesses of the portal based on the user’s perceptions of the system.
{"title":"Usability Study of Student Academic Portal from a User’s Perspective","authors":"Rosmasari, N. Puspitasari, Vinda Nur Vadilla, U. Hairah, Huzain Azis, Haviluddin, M. Wati, E. Budiman","doi":"10.1109/EIConCIT.2018.8878618","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878618","url":null,"abstract":"Usability is a key factor that determines the success of a management software or interactive system, like student academic portal. The increasing usage of a portal requires usability evaluation method that is more accurate and effective to found usability problem, so it can be used for management service improvement in the academic process. The study aims to analyze the feasibility level of using a student academic portal. There are two methods that we using to find problems of convenience, i.e. Think Aloud Evaluation (TA), and Heuristic Evaluation. The study has resulted in the main factors affect the service capabilities of a student academic portal, revealing all the strengths and weaknesses of the portal based on the user’s perceptions of the system.","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":"130510325","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.2018.8878630
F. Zulkifli
The population growth based from Beecham Research Institute, the world population is expected to reach 9.6 billion people. Food production must be increased to support this condition which can be provided by implementation of technology in agriculture sector. Implementing the concept of Internet of Thing (IoT) can be expressed as smart connectivity through internet which every device exchange information with each other.Star fruit is a native fruit of Indonesia, with total production reaching 3000 tons each year in Depok region. However, most of these farmers are uneducated farmers who have not applied technology in their agricultural activities. Meanwhile for optimum growth of the star fruit, pH balance and soil moisture plays an important role. With IoT technology, a monitoring system that focus on pH and soil moisture of the star fruit can be implemented to inform the farmers of their fruit condition. If they maintain the optimum balance, optimum growth of the fruit is expected and therefore an increase of production.
{"title":"Keynote Speech 3 Internet of Things (IoT) Technology For Star Fruit Plantation","authors":"F. Zulkifli","doi":"10.1109/eiconcit.2018.8878630","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878630","url":null,"abstract":"The population growth based from Beecham Research Institute, the world population is expected to reach 9.6 billion people. Food production must be increased to support this condition which can be provided by implementation of technology in agriculture sector. Implementing the concept of Internet of Thing (IoT) can be expressed as smart connectivity through internet which every device exchange information with each other.Star fruit is a native fruit of Indonesia, with total production reaching 3000 tons each year in Depok region. However, most of these farmers are uneducated farmers who have not applied technology in their agricultural activities. Meanwhile for optimum growth of the star fruit, pH balance and soil moisture plays an important role. With IoT technology, a monitoring system that focus on pH and soil moisture of the star fruit can be implemented to inform the farmers of their fruit condition. If they maintain the optimum balance, optimum growth of the fruit is expected and therefore an increase of production.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"221 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":"114398582","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.2018.8878516
Eel Susilowati, S. Madenda, Sunny Arief Sudiro, Lussiana Etp
Research on plantation products has now turned to non-destructive research, this is because the quality of plantation products still uses the manual method of relying on sight or hand size to distinguish which is good, damaged, ripe, raw, large or small. Of course, the results are inconsistent, due to differences in perceptions of sight and the size of the hand between farmers with each other. Now the researcher conduct research based on the analysis of image processing. Where color extraction features (other than shape and texture) which is the stage of extracting the information contained in an object in a digital image. This information is used to distinguish between one object and another object at the stage of grouping/identification analysis based on color. In this case, the author extracts color features based on the minimum and maximum values for each component of the values R, G, B, H, S, V, H, C and L using the RGB, HSV and HCL methods. Thus, it can be seen the differences in the results of color extraction that characterize the object: Medan oranges of the three methods. The conclusion resulted from this research can't be used as a basis for determining specific the characteristics of each oranges class, because there is any overlap minimum-maximum value
{"title":"Color Features Extraction Based on Min-Max Value from RGB, HSV, and HCL on Medan Oranges Image","authors":"Eel Susilowati, S. Madenda, Sunny Arief Sudiro, Lussiana Etp","doi":"10.1109/EIConCIT.2018.8878516","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878516","url":null,"abstract":"Research on plantation products has now turned to non-destructive research, this is because the quality of plantation products still uses the manual method of relying on sight or hand size to distinguish which is good, damaged, ripe, raw, large or small. Of course, the results are inconsistent, due to differences in perceptions of sight and the size of the hand between farmers with each other. Now the researcher conduct research based on the analysis of image processing. Where color extraction features (other than shape and texture) which is the stage of extracting the information contained in an object in a digital image. This information is used to distinguish between one object and another object at the stage of grouping/identification analysis based on color. In this case, the author extracts color features based on the minimum and maximum values for each component of the values R, G, B, H, S, V, H, C and L using the RGB, HSV and HCL methods. Thus, it can be seen the differences in the results of color extraction that characterize the object: Medan oranges of the three methods. The conclusion resulted from this research can't be used as a basis for determining specific the characteristics of each oranges class, because there is any overlap minimum-maximum value","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"25 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":"116738934","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.2018.8878664
H. S. Pakpahan, Haviluddin, M. Wati
Geothermal utilization in Indonesia is mostly for electricity generation. Electricity consumption has increased while geothermal production has not increased, so it is necessary to develop geothermal wells. One of the efforts is the prediction of well behavior so that the well performance can be known which a need for well development is. To predict the behavior of geothermal wells temperature prediction (T) and pressure (P) with location parameters (x and y), well depth (z) injection flow rate (qinj) and injection temperature (Tinj) using the Artificial Neural Network (ANN) method. The first is the generation of well production models, M-1, M-2 and M-3, each model has 6 wells. Data is generated during one year of production and data separation is carried out, i.e. data for 11 months is used as ANN training data and data for the last 1 month is used as test data. The results of the prediction with ANN will be compared with the test data. Calculation of errors between the predicted results and the test data on M-1 is 0.0251 for temperature (T) and 0.0303 for pressure (P), while the MSE value is 0.00378. At M-2 is 0.0283 for temperature (T) and 0.0468 for pressure (P), while the MSE value is 0.000795. At M-3 is 0.0445 for temperature (T) and 0.0566 for pressure (P), while the MSE value is 0.0121. Based on the results obtained the error value and MSE are relatively small, so ANN can be used to predict the behavior of geothermal wells. Then the variation in the number of hidden layers is done. H-15 has the best error value and MSE, while h-50 has the best regression value (R).
{"title":"Identification of Geothermal Reservoir Determination using Artificial Neural Network (ANN)","authors":"H. S. Pakpahan, Haviluddin, M. Wati","doi":"10.1109/EIConCIT.2018.8878664","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878664","url":null,"abstract":"Geothermal utilization in Indonesia is mostly for electricity generation. Electricity consumption has increased while geothermal production has not increased, so it is necessary to develop geothermal wells. One of the efforts is the prediction of well behavior so that the well performance can be known which a need for well development is. To predict the behavior of geothermal wells temperature prediction (T) and pressure (P) with location parameters (x and y), well depth (z) injection flow rate (qinj) and injection temperature (Tinj) using the Artificial Neural Network (ANN) method. The first is the generation of well production models, M-1, M-2 and M-3, each model has 6 wells. Data is generated during one year of production and data separation is carried out, i.e. data for 11 months is used as ANN training data and data for the last 1 month is used as test data. The results of the prediction with ANN will be compared with the test data. Calculation of errors between the predicted results and the test data on M-1 is 0.0251 for temperature (T) and 0.0303 for pressure (P), while the MSE value is 0.00378. At M-2 is 0.0283 for temperature (T) and 0.0468 for pressure (P), while the MSE value is 0.000795. At M-3 is 0.0445 for temperature (T) and 0.0566 for pressure (P), while the MSE value is 0.0121. Based on the results obtained the error value and MSE are relatively small, so ANN can be used to predict the behavior of geothermal wells. Then the variation in the number of hidden layers is done. H-15 has the best error value and MSE, while h-50 has the best regression value (R).","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"215 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":"116172331","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.2018.8878546
Advendio Desandros, A. H. Saputro
Transmittance and reflectance modes are the two most common technique used for investigating liquid psychochemical properties based on optical spectra. In the case of honey characterization, this research performed to show a comparison between both modes to measure honey’s Total Soluble Solids and pH based on the Vis-NIR hyperspectral imaging system. The system consists of Specim FX10 hyperspectral camera with 448 bands (400-1000nm), three 200 W halogen lamps, a light diffuser, a motor slider, and a PC. Then, a Partial Least Square Regression (PLSR) algorithm applied to predict measured values based on the acquired transmittance and reflectance spectrum. Performance of each technique tested by tenfold Cross Validation, which randomly grouping the dataset into ten partitions. Samples is prepared from 28 different honey types with varied colors, placed in 5 cm diameter Petri dishes at 10 ml volume. Performance of each technique measured by R2 and a Root Mean Square Percentage Error (RMSPE) score. Transmittance mode results in R2 of 0.93 and 0.80, RMSPE of 1.06% and 5.36% for total soluble solid content and pH measurement. For similar measured properties, reflectance mode results in R2 of 0.94 and 0.82, RMSPE of1.01% and 5.23%. In this research, reflectance mode performs slightly better than transmittance mode in the measurement of Total Soluble Solids and pH in honey samples.
{"title":"Comparative Study of Hyperspectral Aquisition Technique in Total Soluble Content and pH Measurement in Honey","authors":"Advendio Desandros, A. H. Saputro","doi":"10.1109/EIConCIT.2018.8878546","DOIUrl":"https://doi.org/10.1109/EIConCIT.2018.8878546","url":null,"abstract":"Transmittance and reflectance modes are the two most common technique used for investigating liquid psychochemical properties based on optical spectra. In the case of honey characterization, this research performed to show a comparison between both modes to measure honey’s Total Soluble Solids and pH based on the Vis-NIR hyperspectral imaging system. The system consists of Specim FX10 hyperspectral camera with 448 bands (400-1000nm), three 200 W halogen lamps, a light diffuser, a motor slider, and a PC. Then, a Partial Least Square Regression (PLSR) algorithm applied to predict measured values based on the acquired transmittance and reflectance spectrum. Performance of each technique tested by tenfold Cross Validation, which randomly grouping the dataset into ten partitions. Samples is prepared from 28 different honey types with varied colors, placed in 5 cm diameter Petri dishes at 10 ml volume. Performance of each technique measured by R2 and a Root Mean Square Percentage Error (RMSPE) score. Transmittance mode results in R2 of 0.93 and 0.80, RMSPE of 1.06% and 5.36% for total soluble solid content and pH measurement. For similar measured properties, reflectance mode results in R2 of 0.94 and 0.82, RMSPE of1.01% and 5.23%. In this research, reflectance mode performs slightly better than transmittance mode in the measurement of Total Soluble Solids and pH in honey samples.","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"2 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":"120898820","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.2018.8878585
{"title":"[EIConCIT 2018 Cover Page]","authors":"","doi":"10.1109/eiconcit.2018.8878585","DOIUrl":"https://doi.org/10.1109/eiconcit.2018.8878585","url":null,"abstract":"","PeriodicalId":424909,"journal":{"name":"2018 2nd East Indonesia Conference on Computer and Information Technology (EIConCIT)","volume":"23 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114099159","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：