Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234210
Dwi Intan Af’idah, R. Kusumaningrum, B. Surarso
Large amount of text has been created on the Internet which requires assessment to convert this data into useful information. Deep learning can address this challenge by delivering improved performance in sentiment analysis compared to classic machine learning that utilises the statistical technique. LSTM (Long short-term memory), CNN (Convolutional neural network), their combined model, and developments in their architecture have shown excellent performance for assessment of sentiment in English corpus. However, there have been limited research works on deep learning that utilizes a blend of the two models for the Indonesian body of languages. In this research, we present the LSTM-CNN combined model and the Word2Vec framework for assessment of sentiment in the Indonesian language with respect to the reviews of tourist regions. The dataset comprises 10000 touristic destination reviews in the Indonesian language (5000 positive and 5000 negative reviews). The parameters for LSTM-CNN and Word2Vec which were put to test in the study are dropout, pooling layer, learning level, convolutional activation, Word2Vec architecture, Word2Vec evaluation approach, and Word2Vec dimension. The outcomes indicate that the precision of the LSTM-CNN model is higher compared to LSTM; the precision of LSTM-CNN is 97.17% as against 90.82% for LSTM. Going forward, our results could be utilised by the government or the tourism sector as a material basis for fostering tourism, and by the public as a platform for selecting travel destination.
{"title":"Long Short Term Memory Convolutional Neural Network for Indonesian Sentiment Analysis towards Touristic Destination Reviews","authors":"Dwi Intan Af’idah, R. Kusumaningrum, B. Surarso","doi":"10.1109/iSemantic50169.2020.9234210","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234210","url":null,"abstract":"Large amount of text has been created on the Internet which requires assessment to convert this data into useful information. Deep learning can address this challenge by delivering improved performance in sentiment analysis compared to classic machine learning that utilises the statistical technique. LSTM (Long short-term memory), CNN (Convolutional neural network), their combined model, and developments in their architecture have shown excellent performance for assessment of sentiment in English corpus. However, there have been limited research works on deep learning that utilizes a blend of the two models for the Indonesian body of languages. In this research, we present the LSTM-CNN combined model and the Word2Vec framework for assessment of sentiment in the Indonesian language with respect to the reviews of tourist regions. The dataset comprises 10000 touristic destination reviews in the Indonesian language (5000 positive and 5000 negative reviews). The parameters for LSTM-CNN and Word2Vec which were put to test in the study are dropout, pooling layer, learning level, convolutional activation, Word2Vec architecture, Word2Vec evaluation approach, and Word2Vec dimension. The outcomes indicate that the precision of the LSTM-CNN model is higher compared to LSTM; the precision of LSTM-CNN is 97.17% as against 90.82% for LSTM. Going forward, our results could be utilised by the government or the tourism sector as a material basis for fostering tourism, and by the public as a platform for selecting travel destination.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121326910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234248
L. Gumilar, D. E. Cahyani, Mokhammad Sholeh
Battery Charging Station (BCS) is needed by Electrical Vehicle (EV) to refill electrical energy. BCS obtains electricity supply from the electric power system. However, the existence of BCS can cause the bus voltage to become unstable. This paper discusses how to maintain the stability of the bus voltage by interconnecting the wind power plant (WPP). The method is use four types of WPP. WPP first type is Fixed-speed conventional induction generators (FSCIG). WPP second type is Variable slip induction generators (VSIG). WPP third type is Variable doubly fed induction generators with rotor-side converters (DFIG). WPP fourth type is Variable speed with full induction generators (FCIIG) interface converter. In addition to using the four types of WPP, it also uses a combination of WPP first type with third type, second type with fourth type, and a combination of all types of WPP. Voltage analysis uses the P-V curve to show the sensitivity of active power changes to bus voltage change. Q-V curve to show the sensitivity of reactive power changes to bus voltage change. This paper focuses on stable margin areas on the P-V and Q-V curves. Based on the results of all the interconnection conditions of the types of WPP and BCS, the reference is at the widest margin of the stable voltage area. FCIIG and BCS interconnections on bus number 14 are capable of producing the widest stable margin area. The highest active power operating range is from 1.15 MW to 1.95 MW. As for the operating range of reactive power from 0.671 MVAR to 1.22 MVAR. Operation of the two power ranges keeps the voltage in a stable area.
{"title":"P-V and Q-V Curve Analysis of Four Types Wind Power Plants at Battery Charging Station","authors":"L. Gumilar, D. E. Cahyani, Mokhammad Sholeh","doi":"10.1109/iSemantic50169.2020.9234248","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234248","url":null,"abstract":"Battery Charging Station (BCS) is needed by Electrical Vehicle (EV) to refill electrical energy. BCS obtains electricity supply from the electric power system. However, the existence of BCS can cause the bus voltage to become unstable. This paper discusses how to maintain the stability of the bus voltage by interconnecting the wind power plant (WPP). The method is use four types of WPP. WPP first type is Fixed-speed conventional induction generators (FSCIG). WPP second type is Variable slip induction generators (VSIG). WPP third type is Variable doubly fed induction generators with rotor-side converters (DFIG). WPP fourth type is Variable speed with full induction generators (FCIIG) interface converter. In addition to using the four types of WPP, it also uses a combination of WPP first type with third type, second type with fourth type, and a combination of all types of WPP. Voltage analysis uses the P-V curve to show the sensitivity of active power changes to bus voltage change. Q-V curve to show the sensitivity of reactive power changes to bus voltage change. This paper focuses on stable margin areas on the P-V and Q-V curves. Based on the results of all the interconnection conditions of the types of WPP and BCS, the reference is at the widest margin of the stable voltage area. FCIIG and BCS interconnections on bus number 14 are capable of producing the widest stable margin area. The highest active power operating range is from 1.15 MW to 1.95 MW. As for the operating range of reactive power from 0.671 MVAR to 1.22 MVAR. Operation of the two power ranges keeps the voltage in a stable area.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133492471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234234
Whilly Harsono, R. Sarno, S. Sabilla
Many studies have used an electronic nose (E-nose) to detect several types of coffee. To the best of our knowledge, none of the studies have tried to detect odors from a mixture of several types of coffee. Therefore, this research proposes E-nose which can be used to recognize original Arabica civet coffee. The mixture of Arabica civet coffee and Robusta coffee (non-civet coffee) is used as the object of this research. Nine combinations of mixture are prepared in this study. Those combinations are referred to as classes. After collecting the data, a statistical calculation would be determined to obtain parameter statistics. Moreover, the classification method used in this study is to recognize original Arabica civet coffee and original Robusta coffee. Several classifications had been compared, namely Logistic Regression (LR), Linear Discriminant Analysis (LDA), and K-Nearest Neighbors (KNN). The best result is the KNN method with an accuracy value of 97.7% for nine classes.
{"title":"Recognition of Original Arabica Civet Coffee based on Odor using Electronic Nose and Machine Learning","authors":"Whilly Harsono, R. Sarno, S. Sabilla","doi":"10.1109/iSemantic50169.2020.9234234","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234234","url":null,"abstract":"Many studies have used an electronic nose (E-nose) to detect several types of coffee. To the best of our knowledge, none of the studies have tried to detect odors from a mixture of several types of coffee. Therefore, this research proposes E-nose which can be used to recognize original Arabica civet coffee. The mixture of Arabica civet coffee and Robusta coffee (non-civet coffee) is used as the object of this research. Nine combinations of mixture are prepared in this study. Those combinations are referred to as classes. After collecting the data, a statistical calculation would be determined to obtain parameter statistics. Moreover, the classification method used in this study is to recognize original Arabica civet coffee and original Robusta coffee. Several classifications had been compared, namely Logistic Regression (LR), Linear Discriminant Analysis (LDA), and K-Nearest Neighbors (KNN). The best result is the KNN method with an accuracy value of 97.7% for nine classes.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132510600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234219
Irawan Dwi Wahyono, Khoirudin Asfani, Mohd Murtadha Mohamad, Djoko Saryono, H. Putranto, W. Wibisono
This research develops a smart course to study network security. This smart courser uses computational intelligence (CI) to classify the user's capabilities in the network security learning module. The use of other computational intelligence is used in this smart course to provide suggestions on network security modules that students can work on based on previously acquired abilities. The algorithm computational intelligence used in this study is k-Nearest Neighbor and Bayesian Network (BN). The k-NN algorithm to classify the user's capabilities based on the pre-test of each module on the smart course. The Bayesian Network algorithm is used to provide further modules to the user by the wishes and abilities of the user. The k-NN and Bayesian Network test results on this smart course have an average accuracy of 85%.
{"title":"Smart Courses Learning for Network Security using Computational Intelligence","authors":"Irawan Dwi Wahyono, Khoirudin Asfani, Mohd Murtadha Mohamad, Djoko Saryono, H. Putranto, W. Wibisono","doi":"10.1109/iSemantic50169.2020.9234219","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234219","url":null,"abstract":"This research develops a smart course to study network security. This smart courser uses computational intelligence (CI) to classify the user's capabilities in the network security learning module. The use of other computational intelligence is used in this smart course to provide suggestions on network security modules that students can work on based on previously acquired abilities. The algorithm computational intelligence used in this study is k-Nearest Neighbor and Bayesian Network (BN). The k-NN algorithm to classify the user's capabilities based on the pre-test of each module on the smart course. The Bayesian Network algorithm is used to provide further modules to the user by the wishes and abilities of the user. The k-NN and Bayesian Network test results on this smart course have an average accuracy of 85%.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116251480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234259
Frismanda, Agustinus Bimo Gumelar, Derry Pramono Adi, Eman Setiawan, Agung Widodo, M. T. Sulistyono
The recent advancement of Machine Learning (ML) has brought us to many implementations. Online payday loan scam is a phenomenon which interestingly containing toxic speech in conversation. Toxic speech means implying threat toxic speech, offensive language, and hate speech. toxic speech would ultimately trigger such responses, namely loss of work ethic, alienation from the social, even suicidal thought. Despite the unnerving impact of toxic speech, there is still little known research regarding toxic speech, one of them is how to classify toxic speech. This research aims to make a comparison of various ML techniques with the means of classifying toxic speech found in the online payday loan scam phenomenon. For this experiment, we employed Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Random Forest (RF), and k-Nearest Neighbour (k-NN). All data were taken, filtered, and normalized manually from YouTube. Many reported the incident of online payday loan scam via YouTube in the form of two-way call communication. In total, there are 79 fraud report records converted into *.wav files, followed by the feature extraction process using openSMILE, and are classified using machine learning. We get the MLP result which has an acquisition value of 97.9%, below that received SVM 97.2%.
{"title":"Machine Learning Performance Comparison for Toxic Speech Classification : Online Payday Loan Scams in Indonesia","authors":"Frismanda, Agustinus Bimo Gumelar, Derry Pramono Adi, Eman Setiawan, Agung Widodo, M. T. Sulistyono","doi":"10.1109/iSemantic50169.2020.9234259","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234259","url":null,"abstract":"The recent advancement of Machine Learning (ML) has brought us to many implementations. Online payday loan scam is a phenomenon which interestingly containing toxic speech in conversation. Toxic speech means implying threat toxic speech, offensive language, and hate speech. toxic speech would ultimately trigger such responses, namely loss of work ethic, alienation from the social, even suicidal thought. Despite the unnerving impact of toxic speech, there is still little known research regarding toxic speech, one of them is how to classify toxic speech. This research aims to make a comparison of various ML techniques with the means of classifying toxic speech found in the online payday loan scam phenomenon. For this experiment, we employed Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Random Forest (RF), and k-Nearest Neighbour (k-NN). All data were taken, filtered, and normalized manually from YouTube. Many reported the incident of online payday loan scam via YouTube in the form of two-way call communication. In total, there are 79 fraud report records converted into *.wav files, followed by the feature extraction process using openSMILE, and are classified using machine learning. We get the MLP result which has an acquisition value of 97.9%, below that received SVM 97.2%.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133656992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234249
Y. Yamasari, A. Qoiriah, H. P. Tjahyaningtijas, R. E. Putra, A. Prihanto, Asmunin
the quality of students' performance clusters relates to the accuracy of students being in groups based on their performance. However, the resulting quality sometimes needs to be improved because the clustering process involves features that are not dominant. Furthermore, in the previous works, measurement of the quality of the clusters in unsupervised evaluation often only uses one measure. Therefore, this paper focuses to enhance the quality of clusters by eliminating features that are irrelevant by applying the feature selection method called the Gini Index. Meanwhile, in this paper, the clustering method applied is K-means for the mining process. Then, we propose the evaluation process measured by three metrics, namely: silhouette coefficient, ANOVA, and t-test. The experimental results show that the Gini Index can improve the quality of clusters based on the three proposed metrics.
{"title":"Improving the Quality of the Clustering Process on Students’ Performance using Feature Selection","authors":"Y. Yamasari, A. Qoiriah, H. P. Tjahyaningtijas, R. E. Putra, A. Prihanto, Asmunin","doi":"10.1109/iSemantic50169.2020.9234249","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234249","url":null,"abstract":"the quality of students' performance clusters relates to the accuracy of students being in groups based on their performance. However, the resulting quality sometimes needs to be improved because the clustering process involves features that are not dominant. Furthermore, in the previous works, measurement of the quality of the clusters in unsupervised evaluation often only uses one measure. Therefore, this paper focuses to enhance the quality of clusters by eliminating features that are irrelevant by applying the feature selection method called the Gini Index. Meanwhile, in this paper, the clustering method applied is K-means for the mining process. Then, we propose the evaluation process measured by three metrics, namely: silhouette coefficient, ANOVA, and t-test. The experimental results show that the Gini Index can improve the quality of clusters based on the three proposed metrics.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132981068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234200
Mahmud Zain Abdullah, I. Sudiharto, Rachma Prilian Eviningsih
Solar energy is environmentally friendly energy and it has an unlimited source in nature. To be able to get electrical energy from the sun, photovoltaic is needed that will convert sunlight energy into electrical energy. A photovoltaic has a non-linear output and cannot generate maximum power automatically because it is influenced by solar radiation, temperature, and shadow. Photovoltaic require a tracking system to produce maximum power. The fuzzy logic controller (FLC) is proposed in this paper as a Maximum Power Point Tracking (MPPT) system to get maximum power from photovoltaic with changes in irradiation and temperature. MPPT system will be connected to the zeta converter. Zeta converter is the development of a buck-boost converter with a low ripple and the same polarity as the input voltage polarity on the converter. The results of the simulation show that with changes in irradiance and temperature, the MPPT system using the fuzzy logic controller can find the Maximum Power Point. The average efficiency obtained from the simulation results when the irradiation change is 96.64% and the temperature change is 99.40%.
{"title":"Photovoltaic System MPPT using Fuzzy Logic Controller","authors":"Mahmud Zain Abdullah, I. Sudiharto, Rachma Prilian Eviningsih","doi":"10.1109/iSemantic50169.2020.9234200","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234200","url":null,"abstract":"Solar energy is environmentally friendly energy and it has an unlimited source in nature. To be able to get electrical energy from the sun, photovoltaic is needed that will convert sunlight energy into electrical energy. A photovoltaic has a non-linear output and cannot generate maximum power automatically because it is influenced by solar radiation, temperature, and shadow. Photovoltaic require a tracking system to produce maximum power. The fuzzy logic controller (FLC) is proposed in this paper as a Maximum Power Point Tracking (MPPT) system to get maximum power from photovoltaic with changes in irradiation and temperature. MPPT system will be connected to the zeta converter. Zeta converter is the development of a buck-boost converter with a low ripple and the same polarity as the input voltage polarity on the converter. The results of the simulation show that with changes in irradiance and temperature, the MPPT system using the fuzzy logic controller can find the Maximum Power Point. The average efficiency obtained from the simulation results when the irradiation change is 96.64% and the temperature change is 99.40%.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116614752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234277
Z. Arifin, Eki Yuni Madya Mukti, Aries Jehan Tamamy, M. Ary Heryanto
Indonesia is an exporter of natural rubber. One type of processed rubber used as export material is a sheet of smoked rubber or Ribbed Smoked Sheets (RSS) rubber. The quality of Ribbed Smoked Sheets greatly affects the increase in rubber exports. The quality of Ribbed Smoked Sheets has been stipulated in SNI 06-001-1987 and the International Standards of Quality and Packing for Natural Rubber Grades (The Green Book). The process of determining the quality of Ribbed Smoked Sheets is also called the sorting process. However, in some rubber plantations, the process of sorting is still done manually by observing the presence or absence of mold on the surface of the Ribbed Smoked Sheets in plain sight so as to produce inaccurate and subjective qualities. Therefore, this study is intended to carry out a classification process based on the presence of mold on the Ribbed Smoked Sheets automatically. This research uses image processing with rubber sheet image as input and classification results as output. The classification process of Ribbed Smoked Sheets uses the Neural Network Perceptron method with two classifications, namely moldy Ribbed Smoked Sheets and non-moldy Ribbed Smoked Sheets. This study uses 1000 pieces of Ribbed Smoked Sheets images as training data and 50 images of smoke rubber sheet as test data, each test has 100 pieces with an accuracy value of 96% with the best epoch value on the 4th epoch
{"title":"Classification of RSS (Ribbed Smoke Sheet) Based on Presence or Absence of Fungus using the NN (Neural Network) Perceptron Method","authors":"Z. Arifin, Eki Yuni Madya Mukti, Aries Jehan Tamamy, M. Ary Heryanto","doi":"10.1109/iSemantic50169.2020.9234277","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234277","url":null,"abstract":"Indonesia is an exporter of natural rubber. One type of processed rubber used as export material is a sheet of smoked rubber or Ribbed Smoked Sheets (RSS) rubber. The quality of Ribbed Smoked Sheets greatly affects the increase in rubber exports. The quality of Ribbed Smoked Sheets has been stipulated in SNI 06-001-1987 and the International Standards of Quality and Packing for Natural Rubber Grades (The Green Book). The process of determining the quality of Ribbed Smoked Sheets is also called the sorting process. However, in some rubber plantations, the process of sorting is still done manually by observing the presence or absence of mold on the surface of the Ribbed Smoked Sheets in plain sight so as to produce inaccurate and subjective qualities. Therefore, this study is intended to carry out a classification process based on the presence of mold on the Ribbed Smoked Sheets automatically. This research uses image processing with rubber sheet image as input and classification results as output. The classification process of Ribbed Smoked Sheets uses the Neural Network Perceptron method with two classifications, namely moldy Ribbed Smoked Sheets and non-moldy Ribbed Smoked Sheets. This study uses 1000 pieces of Ribbed Smoked Sheets images as training data and 50 images of smoke rubber sheet as test data, each test has 100 pieces with an accuracy value of 96% with the best epoch value on the 4th epoch","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"18 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125735850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234298
R. Yusianto, Marimin Marimin, Suprihatin, H. Hardjomidjojo
The most important risk in potatoes farming is the Potato Cyst Nematode (PCN) attacks. The attacks were marked by a decrease in production of up to 70%. This means it has dropped to 11.89 tons/ha from Indonesia's average production of 16.99 tons/ha. The objective of this study was identifying PCN attacks using the Fuzzy Mamdani method. The contribution of this study was that we used spatial analysis to identify abiotic factors that affect the PCN attacks level, namely altitude, slope, temperature, and rainfall. To balance sensitivity we arranged in random grid-based sampling points. We took 5-10 stabs/ha in Kejajar, Indonesia. The sampling pattern used a combination of military standard 105B with a random grid. We used 4 stages to get the output, namely the fuzzy sets formation, the implications function with the minimum method, the rules composition with the maximum method and defuzzification. The fuzzy model was designed with 81 rules to obtain 3 types of PCN attack level intensity. The results showed that the accuracy rate of this method was 98.3%. This means that to support decision making in identifying PCN attacks, this spatial analysis method can be used. For further research, this method can be implemented for other potato disease types.
{"title":"Spatial Analysis on Potato Cyst Nematode (Globodera rostochiensis) Attacks Identification using the Fuzzy Mamdani Method","authors":"R. Yusianto, Marimin Marimin, Suprihatin, H. Hardjomidjojo","doi":"10.1109/iSemantic50169.2020.9234298","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234298","url":null,"abstract":"The most important risk in potatoes farming is the Potato Cyst Nematode (PCN) attacks. The attacks were marked by a decrease in production of up to 70%. This means it has dropped to 11.89 tons/ha from Indonesia's average production of 16.99 tons/ha. The objective of this study was identifying PCN attacks using the Fuzzy Mamdani method. The contribution of this study was that we used spatial analysis to identify abiotic factors that affect the PCN attacks level, namely altitude, slope, temperature, and rainfall. To balance sensitivity we arranged in random grid-based sampling points. We took 5-10 stabs/ha in Kejajar, Indonesia. The sampling pattern used a combination of military standard 105B with a random grid. We used 4 stages to get the output, namely the fuzzy sets formation, the implications function with the minimum method, the rules composition with the maximum method and defuzzification. The fuzzy model was designed with 81 rules to obtain 3 types of PCN attack level intensity. The results showed that the accuracy rate of this method was 98.3%. This means that to support decision making in identifying PCN attacks, this spatial analysis method can be used. For further research, this method can be implemented for other potato disease types.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123598515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-19DOI: 10.1109/iSemantic50169.2020.9234193
Soedibyo, Avian Lukman Setya Budi, M. Ashari, Hilman Ridho, F. Pamuji
Photovoltaic, wind turbine, and fuel cell can produce electrical energy by utilizing renewable energy. The energy is clean and unlimited. Photovoltaic (PV), wind turbine, and fuel cell hybrid system has high reliability and can produce more energy than the standalone PV system. MPPT (Maximum Power Point Tracking) is needed to maximize the input power by placing the input current and voltage at the maximum point on both voltage and current, so the power produced is also at the maximum point. But there is a problem of integrating method of the power generator since the constraint of the parallel generator operation should be have the same voltage level. In this paper, will be discussed about the P&O method, that can be used for various characteristics of PV and does not require information of wind turbine characteristics. As the results, Perturb and Observe (P&O) algorithm on multi-input DC/DC converter can maximize the output power up to 125,87% more power. Hopefully with this research, it can help the advancement of the renewable energy electricity generation research in the future.
光伏、风力涡轮机和燃料电池可以利用可再生能源产生电能。能源是清洁和无限的。光伏(PV)、风力涡轮机和燃料电池混合系统具有高可靠性，并且可以比独立的光伏系统产生更多的能量。需要MPPT(最大功率点跟踪)，通过将输入电流和电压置于电压和电流的最大点，使输入功率最大化，因此产生的功率也处于最大点。但由于并联发电机的运行约束必须具有相同的电压水平，因此存在发电机积分方法的问题。本文将讨论P&O方法，该方法可用于光伏的各种特性，并且不需要风力机特性的信息。结果表明，在多输入DC/DC变换器上采用P&O (Perturb and Observe)算法可使输出功率最大提高12.7%。希望通过本研究对未来可再生能源发电研究的推进有所帮助。
{"title":"Implementation Of Maximum Power Point Tracking Based On Perturb and Observe Algorithm For Photovoltaic, Wind Turbine, and Fuel Cell Hybrid System","authors":"Soedibyo, Avian Lukman Setya Budi, M. Ashari, Hilman Ridho, F. Pamuji","doi":"10.1109/iSemantic50169.2020.9234193","DOIUrl":"https://doi.org/10.1109/iSemantic50169.2020.9234193","url":null,"abstract":"Photovoltaic, wind turbine, and fuel cell can produce electrical energy by utilizing renewable energy. The energy is clean and unlimited. Photovoltaic (PV), wind turbine, and fuel cell hybrid system has high reliability and can produce more energy than the standalone PV system. MPPT (Maximum Power Point Tracking) is needed to maximize the input power by placing the input current and voltage at the maximum point on both voltage and current, so the power produced is also at the maximum point. But there is a problem of integrating method of the power generator since the constraint of the parallel generator operation should be have the same voltage level. In this paper, will be discussed about the P&O method, that can be used for various characteristics of PV and does not require information of wind turbine characteristics. As the results, Perturb and Observe (P&O) algorithm on multi-input DC/DC converter can maximize the output power up to 125,87% more power. Hopefully with this research, it can help the advancement of the renewable energy electricity generation research in the future.","PeriodicalId":345558,"journal":{"name":"2020 International Seminar on Application for Technology of Information and Communication (iSemantic)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125458533","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：