Pub Date : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034671
Yunifa Miftachul Arif, S. M. S. Nugroho, M. Hariadi
Many tourist cities in developing countries, especially in Indonesia, have exciting tourism destinations. However, some of them do not use a good management concept, for example, to develop tourism destinations. Early process in the development of the destination is making priority selection appropriately. They should consider the success level of tourism destinations. This paper discusses implementations of the 6AsTD framework and TOPSIS method as a combination concept to select destinations priority that recommended to do development. 6AsTD has six components that reflect successful tourism destinations. All components used in the process of the TOPSIS method as input criteria. This research used 11 tourism destinations data bundles in Batu City. The result is a tourism destination with the highest priority has a score of 0.88, and the lowest priority has a score of 0.19.
{"title":"Selection of Tourism Destinations Priority using 6AsTD Framework and TOPSIS","authors":"Yunifa Miftachul Arif, S. M. S. Nugroho, M. Hariadi","doi":"10.1109/ISRITI48646.2019.9034671","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034671","url":null,"abstract":"Many tourist cities in developing countries, especially in Indonesia, have exciting tourism destinations. However, some of them do not use a good management concept, for example, to develop tourism destinations. Early process in the development of the destination is making priority selection appropriately. They should consider the success level of tourism destinations. This paper discusses implementations of the 6AsTD framework and TOPSIS method as a combination concept to select destinations priority that recommended to do development. 6AsTD has six components that reflect successful tourism destinations. All components used in the process of the TOPSIS method as input criteria. This research used 11 tourism destinations data bundles in Batu City. The result is a tourism destination with the highest priority has a score of 0.88, and the lowest priority has a score of 0.19.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126005156","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034569
Kevin Alamsyah Yuwono, Irma Safitri, Iwan Iwut Tritoasmoro
Face recognition system is a crucial issue these days. This research builds an Android-based facial recognition system in real time using the Gabor filter and artificial neural network (ANN) methods. The system can be implemented properly. The test results show that for testing in scenario 1, the largest accuracy is 90% in hidden layer 4 and 5. The smallest computation time is 0.46872 seconds for layer 2 and the biggest time is 0.63778 seconds for hidden layer 5. While the test results for scenario 2 shows the lowest accuracy is the trainrp training function for 76%, while the highest accuracy of 94% is in the traincgp training function.
{"title":"Artificial Neural Networks Android-Based Interface Facial Recognition Systems","authors":"Kevin Alamsyah Yuwono, Irma Safitri, Iwan Iwut Tritoasmoro","doi":"10.1109/ISRITI48646.2019.9034569","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034569","url":null,"abstract":"Face recognition system is a crucial issue these days. This research builds an Android-based facial recognition system in real time using the Gabor filter and artificial neural network (ANN) methods. The system can be implemented properly. The test results show that for testing in scenario 1, the largest accuracy is 90% in hidden layer 4 and 5. The smallest computation time is 0.46872 seconds for layer 2 and the biggest time is 0.63778 seconds for hidden layer 5. While the test results for scenario 2 shows the lowest accuracy is the trainrp training function for 76%, while the highest accuracy of 94% is in the traincgp training function.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128879429","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034596
Edy Winarno, Imam Husni Al Amin, Herny Februariyanti, P. Adi, W. Hadikurniawati, M. T. Anwar
One of the developments in computer vision is the research on human face recognition. One of the implementations of the human face recognition system is used as an attendance system. The attendance system uses faces as objects to be detected and recognized as a person's identity and then stored as a face database. The process of matching face image data captured by the camera with face images that have been stored in the face database will result in face identification of the object faces captured by the camera. The face recognition-based attendance system in this study uses a hybrid feature extraction method using CNN-PCA (Convolutional Neural Network - Principal Component Analysis). This combination of methods is intended to produce a more accurate feature extraction method. The face recognition-based attendance system using this camera is very effective and efficient to further improve the accuracy of user data. This face recognition-based attendance system using this camera has very accurate data processing and high accuracy so that it can produce a system that is reliable and powerful to identify human faces in real-time.
{"title":"Attendance System Based on Face Recognition System Using CNN-PCA Method and Real-time Camera","authors":"Edy Winarno, Imam Husni Al Amin, Herny Februariyanti, P. Adi, W. Hadikurniawati, M. T. Anwar","doi":"10.1109/ISRITI48646.2019.9034596","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034596","url":null,"abstract":"One of the developments in computer vision is the research on human face recognition. One of the implementations of the human face recognition system is used as an attendance system. The attendance system uses faces as objects to be detected and recognized as a person's identity and then stored as a face database. The process of matching face image data captured by the camera with face images that have been stored in the face database will result in face identification of the object faces captured by the camera. The face recognition-based attendance system in this study uses a hybrid feature extraction method using CNN-PCA (Convolutional Neural Network - Principal Component Analysis). This combination of methods is intended to produce a more accurate feature extraction method. The face recognition-based attendance system using this camera is very effective and efficient to further improve the accuracy of user data. This face recognition-based attendance system using this camera has very accurate data processing and high accuracy so that it can produce a system that is reliable and powerful to identify human faces in real-time.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128985526","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034634
W. S. M. Sanjaya, Akhmad Roziqin, A. Kusumorini, D. Anggraeni, F. I. Nurrahman, W. G. Kresnadjaja, D. Maulana
One of the mandatory requirements of performing Sholat or other various worship for Muslim’s is faces to Qibla direction (the direction toward Kaaba in Mecca). Muslims around the world who far away from Kabaa motivate the beginning Muslims scientist (one of them is al-Biruni (973 - 1050 CE)) to develop various method to determine the Qibla direction. This study describes al-Biruni’s Third method from the manuscript Kitab Tahdid Nihayat al-Amakin for determining the Qibla direction of a Location computed in Python 2.7. The computation result presents that al-Biruni’s Third method equivalent to the modern spherical trigonometry method. Hence, al-Biruni’s method can still be used to determine the Qibla direction of a location in the present. Then, the algorithm of al-Biruni’s Third has been implemented to construct Q-Bot Ver. 3 based on Arduino board MCU, GPS module, and digital compass so that can determine the Qibla direction in a Location automatically and in real-time.
{"title":"The Third al-Biruni’s Method for The Determination of Qibla Direction from Kitab Tahdid Nihayat al-Amakin with The Implementation Based on Arduino Board MCU, GPS Module, and Digital Compass","authors":"W. S. M. Sanjaya, Akhmad Roziqin, A. Kusumorini, D. Anggraeni, F. I. Nurrahman, W. G. Kresnadjaja, D. Maulana","doi":"10.1109/ISRITI48646.2019.9034634","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034634","url":null,"abstract":"One of the mandatory requirements of performing Sholat or other various worship for Muslim’s is faces to Qibla direction (the direction toward Kaaba in Mecca). Muslims around the world who far away from Kabaa motivate the beginning Muslims scientist (one of them is al-Biruni (973 - 1050 CE)) to develop various method to determine the Qibla direction. This study describes al-Biruni’s Third method from the manuscript Kitab Tahdid Nihayat al-Amakin for determining the Qibla direction of a Location computed in Python 2.7. The computation result presents that al-Biruni’s Third method equivalent to the modern spherical trigonometry method. Hence, al-Biruni’s method can still be used to determine the Qibla direction of a location in the present. Then, the algorithm of al-Biruni’s Third has been implemented to construct Q-Bot Ver. 3 based on Arduino board MCU, GPS module, and digital compass so that can determine the Qibla direction in a Location automatically and in real-time.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121839644","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034600
Shofyan Arsyad Widhiono, Muhammad Ary Murti, C. Setianingsih
In this modern age, electricity has become essential things in every aspect of living. To ensure its proper use, a program created to help regulate electricity usage based on user defined priority. In this study Priority Queue Algorithm is used to measure how long every can stay active so it will not drain user’s monthly electricity target usage. The calculation process is done on android device then the execution order to turn the devices on or off are sent to database MySQL The result obtained from this research that priority queue algorithm is able to regulate electricity usage based on rule testing and fast response time to control and retrieve data from the database, 0.006s average time on manual control system, 0.005s average time on automatic control system, and 0.004s average time on retrieving data.
{"title":"Electronic Loads Control and Management Using Priority Queue Algorithm on Android Based Smartphone","authors":"Shofyan Arsyad Widhiono, Muhammad Ary Murti, C. Setianingsih","doi":"10.1109/ISRITI48646.2019.9034600","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034600","url":null,"abstract":"In this modern age, electricity has become essential things in every aspect of living. To ensure its proper use, a program created to help regulate electricity usage based on user defined priority. In this study Priority Queue Algorithm is used to measure how long every can stay active so it will not drain user’s monthly electricity target usage. The calculation process is done on android device then the execution order to turn the devices on or off are sent to database MySQL The result obtained from this research that priority queue algorithm is able to regulate electricity usage based on rule testing and fast response time to control and retrieve data from the database, 0.006s average time on manual control system, 0.005s average time on automatic control system, and 0.004s average time on retrieving data.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133899615","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034608
Carensy Donabela, M. A. Ulin Nuha, Rini Wisnu Wardhani, Mohamad Syahral, Dion Ogi, Dedy Septono Catur Putranto
Polarization Automation based on EDU-QCRY 1 is a system designed to facilitate the use of EDU-QCRY 1 devices in simulation of sending Quantum Bit (Qubit). Polarization automation utilizes quantum mechanical properties on the EDU QCRY 1 device, which will produce bits through polarization automation on the EDU-QCRY 1 quantum polarizator device. Polarization rotation will be done automatically and randomly using an ultrasonic piezomotor device that receives random voltage input on the Arduino Uno microcontroller. The random voltage input is based on a random source from the accelerometer sensor. The measurement results of the accelerometer sensor will be processed and converted into voltage as input to perform automatic and random polarization rotations on the EDU QCRY polariator device. Furthermore, the automatic polarization results will produce a series of numbers that run on the principle of anti-cloning and quantum mechanical properties.
{"title":"Design of Automated Polarization based on EDU-QCRY 1","authors":"Carensy Donabela, M. A. Ulin Nuha, Rini Wisnu Wardhani, Mohamad Syahral, Dion Ogi, Dedy Septono Catur Putranto","doi":"10.1109/ISRITI48646.2019.9034608","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034608","url":null,"abstract":"Polarization Automation based on EDU-QCRY 1 is a system designed to facilitate the use of EDU-QCRY 1 devices in simulation of sending Quantum Bit (Qubit). Polarization automation utilizes quantum mechanical properties on the EDU QCRY 1 device, which will produce bits through polarization automation on the EDU-QCRY 1 quantum polarizator device. Polarization rotation will be done automatically and randomly using an ultrasonic piezomotor device that receives random voltage input on the Arduino Uno microcontroller. The random voltage input is based on a random source from the accelerometer sensor. The measurement results of the accelerometer sensor will be processed and converted into voltage as input to perform automatic and random polarization rotations on the EDU QCRY polariator device. Furthermore, the automatic polarization results will produce a series of numbers that run on the principle of anti-cloning and quantum mechanical properties.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134306798","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034572
Thusitha Shaleendra, Buddhi Tharuka Wishvamali, N. Gunarathne, S. Hareendran, P. Abeygunawardhana
With the vast growth of the population, increased production of agricultural products is necessary. Although the amount of land available for agriculture is limited, the demand for food products based on agriculture is expanding. The Organic food supply is scarce in the current food market; hence, their retail prices are higher than the other agricultural products which were produced with the use of pesticides. In this context, Greenhouse production is widely used all over the world with minimal pesticides and weedicides including Sri Lanka. Automated Greenhouses can be used to increase production with a minimum amount of human labor. With less use of human hours, it will produce more harvest than conventional Greenhouses which need constant human attention and care. The installation of automated Greenhouses is costly although their long-term benefits are higher than a conventional one. For this reason, introducing the concept to cultivators would be difficult, as they are reluctant to invest their money on unfamiliar technology. There is a hesitance to embrace technology since they don’t have the first-hand experience in operating an automated Greenhouse. Therefore, in this paper, we present a simulated model of automated Greenhouse using Augmented reality, through which a client can visually experience the workings of IoT Greenhouse based on theoretical models beforehand to make an informed decision to invest in automated Greenhouses.
{"title":"Simulation of the Influence of environmental factors related to Greenhouses using Augmented Reality","authors":"Thusitha Shaleendra, Buddhi Tharuka Wishvamali, N. Gunarathne, S. Hareendran, P. Abeygunawardhana","doi":"10.1109/ISRITI48646.2019.9034572","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034572","url":null,"abstract":"With the vast growth of the population, increased production of agricultural products is necessary. Although the amount of land available for agriculture is limited, the demand for food products based on agriculture is expanding. The Organic food supply is scarce in the current food market; hence, their retail prices are higher than the other agricultural products which were produced with the use of pesticides. In this context, Greenhouse production is widely used all over the world with minimal pesticides and weedicides including Sri Lanka. Automated Greenhouses can be used to increase production with a minimum amount of human labor. With less use of human hours, it will produce more harvest than conventional Greenhouses which need constant human attention and care. The installation of automated Greenhouses is costly although their long-term benefits are higher than a conventional one. For this reason, introducing the concept to cultivators would be difficult, as they are reluctant to invest their money on unfamiliar technology. There is a hesitance to embrace technology since they don’t have the first-hand experience in operating an automated Greenhouse. Therefore, in this paper, we present a simulated model of automated Greenhouse using Augmented reality, through which a client can visually experience the workings of IoT Greenhouse based on theoretical models beforehand to make an informed decision to invest in automated Greenhouses.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133192367","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034579
Aulia Pasca Sahida, B. Surarso, R. Gernowo
The selection of the right vendor is crucial for the success and competitiveness of manufacturing organizations. Vendor selection decision making has a wide scope and a high level of complexity, which is due to the involvement of various decision makers who have their own preferences. The involvement of various decision makers with their respective preferences, also causes differences in priority over the criteria used. In this paper, it is proposed to use the concept of Group Decision Support System (GDSS) to determine the best vendor based on the aggregation of the preferences of each decision maker. The proposed GDSS concept is to combine the Multi-Objective Optimization method on the basis of Ratio Analysis (MOORA) with the Copeland Score method. The MOORA method is used as a ranking method based on the criteria and weight ratio of each decision maker. The results of ranking using the MOORA method each decision maker is then aggregated using the Copeland Score method, to get the final vendor ranking. The results show that Alternative 5 (Yogatama) has the highest score, so it is ranked first and shows as the best alternative. Sensitivity analysis showed that the proposed GDSS concept was solid, with a low percentage of change.
选择合适的供应商对制造企业的成功和竞争力至关重要。供应商选择决策具有广泛的范围和高度的复杂性，这是由于各种决策者的参与，他们有自己的偏好。不同的决策者以他们各自的偏好参与其中，也造成了对所使用标准的优先次序的差异。本文提出了利用群体决策支持系统(Group Decision Support System, GDSS)的概念，通过汇总各决策者的偏好来确定最佳供应商。本文提出的GDSS概念是将基于Ratio Analysis (MOORA)的多目标优化方法与Copeland Score方法相结合。采用MOORA法根据各决策者的标准和权重比进行排序。使用MOORA方法进行排名的结果，然后使用Copeland Score方法对每个决策者进行汇总，以获得最终的供应商排名。结果显示，选择5 (Yogatama)得分最高，因此排名第一，显示为最佳选择。敏感性分析表明，提出的GDSS概念是可靠的，具有低百分比的变化。
{"title":"The combination of the MOORA method and the Copeland Score method as a Group Decision Support System (GDSS) Vendor Selection","authors":"Aulia Pasca Sahida, B. Surarso, R. Gernowo","doi":"10.1109/ISRITI48646.2019.9034579","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034579","url":null,"abstract":"The selection of the right vendor is crucial for the success and competitiveness of manufacturing organizations. Vendor selection decision making has a wide scope and a high level of complexity, which is due to the involvement of various decision makers who have their own preferences. The involvement of various decision makers with their respective preferences, also causes differences in priority over the criteria used. In this paper, it is proposed to use the concept of Group Decision Support System (GDSS) to determine the best vendor based on the aggregation of the preferences of each decision maker. The proposed GDSS concept is to combine the Multi-Objective Optimization method on the basis of Ratio Analysis (MOORA) with the Copeland Score method. The MOORA method is used as a ranking method based on the criteria and weight ratio of each decision maker. The results of ranking using the MOORA method each decision maker is then aggregated using the Copeland Score method, to get the final vendor ranking. The results show that Alternative 5 (Yogatama) has the highest score, so it is ranked first and shows as the best alternative. Sensitivity analysis showed that the proposed GDSS concept was solid, with a low percentage of change.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116475982","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034580
Ranny Ranny, D. Lestari, Tati Latifah Erawati Rajab, I. Suwardi
One of the most common problems in sound recognition is the overlapping sound. This phenomena requires sound separation beforehand in order to be recognized. Most studies related to sound separation used artificial data in their research, i.e. using experiment sound data from a controlled environment which is augmented with one or more sound types, and achieve good results. However, when it is implemented in the real condition, it’s performance has dropped dramatically. Thus, in this research we use overlapping data recorded in real environments. The purpose of this research is to separate the speech and non-speech, and noise by using the Non-negative Matrix Factorization (NMF). Our experimental results show that the NMF works well when separating sound and non-sound, and has helped the performance of sound recognition.
{"title":"Separation of Overlapping Sound using Nonnegative Matrix Factorization","authors":"Ranny Ranny, D. Lestari, Tati Latifah Erawati Rajab, I. Suwardi","doi":"10.1109/ISRITI48646.2019.9034580","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034580","url":null,"abstract":"One of the most common problems in sound recognition is the overlapping sound. This phenomena requires sound separation beforehand in order to be recognized. Most studies related to sound separation used artificial data in their research, i.e. using experiment sound data from a controlled environment which is augmented with one or more sound types, and achieve good results. However, when it is implemented in the real condition, it’s performance has dropped dramatically. Thus, in this research we use overlapping data recorded in real environments. The purpose of this research is to separate the speech and non-speech, and noise by using the Non-negative Matrix Factorization (NMF). Our experimental results show that the NMF works well when separating sound and non-sound, and has helped the performance of sound recognition.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121250513","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 : 2019-12-01DOI: 10.1109/ISRITI48646.2019.9034653
Ekasari Nugraheni
The 2019 Presidential Election in Indonesia causes sharp political polarization. The battle of discourse between two massive camps took place on social media. Various aspects of public opinion showing how people think and act can be found easily. Twitter as the most popular microblogging platform, offers a place to express a variety of thoughts and opinions. This makes Twitter as a source of opinion mining that can be used to detect people's emotional feelings about an event. This paper explores the pre-processing stages of text classification for the emotion recognition based on Twitter conversations that correlate with the debate of Indonesian presidential candidates. Data pre-processing is an important step in sentiment analysis because the results of the analysis are strongly affected by the quality of the data provided. A combination of data processing has been carried out using Indonesian Twitter datasets. The accuracy of the analysis was tested using a deep learning model MLP and LSTM. The results show that the use of appropriate pre-processing techniques can improve accuracy.
{"title":"Indonesian Twitter Data Pre-processing for the Emotion Recognition","authors":"Ekasari Nugraheni","doi":"10.1109/ISRITI48646.2019.9034653","DOIUrl":"https://doi.org/10.1109/ISRITI48646.2019.9034653","url":null,"abstract":"The 2019 Presidential Election in Indonesia causes sharp political polarization. The battle of discourse between two massive camps took place on social media. Various aspects of public opinion showing how people think and act can be found easily. Twitter as the most popular microblogging platform, offers a place to express a variety of thoughts and opinions. This makes Twitter as a source of opinion mining that can be used to detect people's emotional feelings about an event. This paper explores the pre-processing stages of text classification for the emotion recognition based on Twitter conversations that correlate with the debate of Indonesian presidential candidates. Data pre-processing is an important step in sentiment analysis because the results of the analysis are strongly affected by the quality of the data provided. A combination of data processing has been carried out using Indonesian Twitter datasets. The accuracy of the analysis was tested using a deep learning model MLP and LSTM. The results show that the use of appropriate pre-processing techniques can improve accuracy.","PeriodicalId":367363,"journal":{"name":"2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126570730","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：