{"title":"Text-Based Emotion Recognition in Indonesian Tweet using BERT","authors":"Kuncahyo Setyo Nugroho, F. A. Bachtiar","doi":"10.1109/ISRITI54043.2021.9702838","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702838","url":null,"abstract":"Human uses social media platform such as Twitter to express feelings and opinions through text about the surrounding issues. Understanding emotions at the subtle level of expressed feelings are essential for better human and computer interactions. The previous emotion recognition approach required many training data and lexical databases. Unfortunately, the availability of very little labeled training data is a limitation and challenge to achieving high model performance. Therefore, we investigate the BERT language model for emotion recognition in Indonesian-language Tweets in this study. We choose to use fine-tuning instead of pre-training, which requires extensive data and resources. Two pre-trained models were used to determine the effectiveness and performance of the proposed model. Experiments show that the proposed model outperforms all existing baseline models, with the highest accuracy is 77%. Another advantage that we analyze is that BERT requires a relatively short computation time. In addition, BERT has a better context representation.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133429388","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}
{"title":"Interline Feeder of Shunt Passive Harmonic Filter and Detuned Reactor to Reduce Harmonic Distortion","authors":"L. Gumilar, Mokhammad Sholeh, Wahyu Sapto Nugroho","doi":"10.1109/ISRITI54043.2021.9702777","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702777","url":null,"abstract":"Power electronics devices are increasingly needed today. Every human activity always uses power electronic equipment such as motor drive power supply, charger, inverter, control system, etc. The principle of switching work on these equipment can cause harmonics so that they are considered as nonlinear loads. The large number of power electronic devices in the electric power system causes high harmonic distortion. THD and IHD are the measuring parameters for harmonics. High THD cannot be reduced by a shunt harmonic passive filter alone. Therefore, it is necessary to add additional devices such as a detuned reactor as additional equipment to increase the performance of the harmonic power filter. Combination of detuned reactor and shunt harmonic passive filter are placed on interline feeder bus. This interline method is done to save on adding harmonic filters to each feeder. Generally, each feeder is connected to a nonlinear load, so a harmonic filter is needed on each feeder. Several scenarios were made to compare the ability of the shunt harmonic passive filter (SHPF) when without a detuned reactor and when combined with it. All of these scenarios were carried out in the condition of the interline feeder of the electric power system. Each scenario show an increase in the ability of the SHPF after being combined with a detuned reactor. In the first scenario, the THD-I value is 18.16% in feeder number 1 and 15.86% in feeder number 2. THD-V value is 26.9% in feeder number 1 and 23.58% in feeder number 2. In the second scenario, the THD-I value is 9.57% in feeder number 1 and 10.96% in feeder number 2. THD-V value is 8.87% in feeder number 1 and 8.87% in feeder number 2. In the third scenario, the THD-I value is 3.95% in feeder number 1 and 4.53% in feeder number 2. THD-V value is 2.17% in feeder number 1 and 2.17% in feeder number 2.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"38 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131491519","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}
{"title":"NFR Classification using Keyword Extraction and CNN on App Reviews","authors":"Taufik Hidayat, S. Rochimah","doi":"10.1109/ISRITI54043.2021.9702793","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702793","url":null,"abstract":"Documentation and fulfillment of software requirement are important aspects in measuring the success of a team in developing software. In the field of requirement engineering, there are two types of requirements namely functional requirements (FR) and non-functional requirements (NFR). Nowadays, requirements may also be found in app reviews, so this study conducted to classify non-functional requirements collected from app reviews. We classify keywords into 2 categories, namely project specific (PS) and non-project specific (NPS) and we propose an automatic method to extract them from app reviews and app description. We classify app reviews plus keyword extracted using convolutional neural network (CNN) and word2vec vectorization into several category of NFRs. Our proposed method managed to extract several keywords and improve the performance of the classification algorithm used. Our proposed method has an average accuracy of 80%, precision of 71%, and recall of 63%. The result show that our proposed method performed better than basic CNN and any classification algorithm.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124949024","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}
{"title":"Semantic Inpainting of Images using Deep Learning","authors":"S. G, U. M","doi":"10.1109/ISRITI54043.2021.9702794","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702794","url":null,"abstract":"Computer Vision enables computers to retrieve information from digital images and use the inferred data to perform the required task. Image inpainting, a computer vision technique, helps to reconstruct damaged images by refilling the missing pixels, called holes, using the relevant and known pixels, so that repaired image looks very natural and realistic. Traditional inpainting methods generally fill the holes by matching the most similar pixels in the surrounding known regions, focusing to reconstruct the exact ground truth image, leaving behind the texture and quality. Currently, many deep learning methods produced drastic improvements in visual quality and texture and also look for the semantic context of the image. However, achieving success on high resolution images with complex structures remains challenging. This paper imparts an intensive vision of the existing Inpainting methods by providing a comprehensive description of the methods used, datasets and evaluation metrics for all the analyzed techniques.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122038566","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}
Y. Siregar, Hendra Zulkarnain, Rony Firdaus Ginting
{"title":"Analysis of Resistivity, Dielectric Strength and Tensibility of Insulator Materials of A Mixture of Epoxy Resin, Silicone Rubber, and Coal Ash","authors":"Y. Siregar, Hendra Zulkarnain, Rony Firdaus Ginting","doi":"10.1109/ISRITI54043.2021.9702856","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702856","url":null,"abstract":"Coal ash is a coal combustion waste whose amount increases with the use of coal as fuel. The reuse of coal waste has been carried out in civil construction such as the cement industry. Coal ash is utilized in the manufacture of polymer insulating materials with the main ingredients of epoxy resin and silicone rubber. The feasibility of epoxy resin insulators, silicone rubber, and coal ash was tested by testing resistivity, dielectric strength, and tensile strength. The insulator material test was carried out according to ASTM standards and was carried out for 12 different types of samples. The addition of coal ash filler affects the dielectric strength of the test sample. The stability of the test value can be seen in sample S7, with the composition of the sample consisting of 30% resin A, 30% resin B, 20% silicone rubber, and 20% coal fly ash. The test results of the sample code S7 have a resistivity value of 42.793 $MOmega m$, a dielectric strength value of 154.133 kV/cm, a tensile stress value of 7.53 MPa, and a strain percentage of 16.75%. Calculation of the stability of the research results is from the scoring of the overall composition.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116219614","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}
{"title":"Solving the Capacitated Vehicle Routing Problem (CVRP) with Guided Local Search and Simulated Annealing for Optimizing the Distribution of Fishing Vessels","authors":"Hozairi, Syariful Alim, M. Tukan","doi":"10.1109/ISRITI54043.2021.9702877","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702877","url":null,"abstract":"This paper discusses the completion of the distribution route of fishing vessels in twenty-six Fish Landing Bases (FLB) to the National Fisheries Port (NFP), this research includes the Capacitated Vehicle Routing Problem (CVRP) model with several constraints, namely, distance, number of ships, ship capacity, fish catches, travel time and ship operating costs, thus requiring optimization of the route of fishing vessels to each FLB. The method used to solve the problem is Guided Local Search (GLS) and Simulated Annealing (SA) using Google OR-Tools which are proven to be efficient in solving heuristic problems. The results showed that the application of the GLS and SA methods showed different results, for the simulation of two and three fishing vessels the same distance optimization results were obtained, namely 290 miles and 355 miles, but for four fishing vessels the GLS method resulted in 464 miles while the SA method yields 439 miles, meaning that the more fishing vessels, the SA method has a better performance than the GLS method, for a case study of the distribution of fishing vessels in Maluku, the SA method is capable of 6% efficiency in distance while being able to save time and ship operational costs. The results of this study contribute to saving the company's operational costs and improving the quality of fish exports abroad.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116333782","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}
Maria Susan Anggreainy, Ajeng Wulandari, Abdullah M. Illyasu
{"title":"Pneumonia Detection using Dense Convolutional Network (DenseNet) Architecture","authors":"Maria Susan Anggreainy, Ajeng Wulandari, Abdullah M. Illyasu","doi":"10.1109/ISRITI54043.2021.9702803","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702803","url":null,"abstract":"Pneumonia is a dangerous disease that attacks the respiratory system, causing pain in the chest when breathing. The disease killed more than two million people in one year in 2017. Photo the resulting chest X-ray will be checked manually and require proper lighting by a doctor to get the type of pneumonia. Therefore, we need a method to automatically classify pneumonia of the Chest X-ray image. Pneumonia classification systems have been developed but still, produce low accuracy. This research developed a classification system using DenseNet and compared its accuracy with previous studies using ResNet. The results show a 9% performance using DenseNet is better than using ResNet.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114965588","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}
H. Studiawan, T. Ahmad, A. M. Shiddiqi, B. J. Santoso, B. Pratomo
{"title":"Forensic Event Reconstruction for Drones","authors":"H. Studiawan, T. Ahmad, A. M. Shiddiqi, B. J. Santoso, B. Pratomo","doi":"10.1109/ISRITI54043.2021.9702864","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702864","url":null,"abstract":"Event reconstruction is one of the forensic processes used to determine and reconstruct event sequences of cyberse-curity attacks or incidents. In drone forensics, existing research focuses on artifact extraction and analysis. Therefore, in this paper, we propose an event reconstruction method for drones using a directed graph representation. The sentiment analysis technique is used to investigate any events of interest that have been represented as graph vertices. Experimental results on drone public datasets indicate that the proposed method can reconstruct events and show the suspicious activities of a drone to assist in an investigation.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128833318","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}
{"title":"Sponsored","authors":"Rabindra Kumar Behera","doi":"10.1109/isriti54043.2021.9702815","DOIUrl":"https://doi.org/10.1109/isriti54043.2021.9702815","url":null,"abstract":"","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121488560","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}
L. Gumilar, Mokhammad Sholeh, Rachmat Triharto, S. N. Rumokoy, Dezetty Monika, Achmad Fahrul Aji
{"title":"Influence of Wind Turbine Pitch Angle on DFIG Output Stability under Load Changes","authors":"L. Gumilar, Mokhammad Sholeh, Rachmat Triharto, S. N. Rumokoy, Dezetty Monika, Achmad Fahrul Aji","doi":"10.1109/ISRITI54043.2021.9702760","DOIUrl":"https://doi.org/10.1109/ISRITI54043.2021.9702760","url":null,"abstract":"Wind power plants have several advantages compared to other types of renewable energy generation, such as wind energy sources that can be available during the day and night, the power that can be produced by wind power plants is greater. These advantages make many countries prefer to use wind power plants as the main electricity generation compared to other renewable energies. However, it is also necessary to know how the wind power plant can respond to changes in load. The load always changes every hour according to the consumption of electricity by consumers. Therefore, this paper aims to analyze the stability of the wind power plant against changes in load. The type of wind power plant used in this paper is the Double Fed Induction Generator (DFIG). The parameter that is used as input to maintain the stability of the wind power plant is the pitch angle of the wind turbine. The pitch angles used are 0, 10, 20, and 30 degrees. Furthermore, to determine the stability response of the wind power plant parameter output, it is necessary to test it with changes in load. The change in load in question is the addition of a load when the wind power plant is operating. The wind power plant output parameters analyzed include current, active power, induction generator rotation speed, and voltage. The simulation results on the output voltage side, the greater the pitch angle, the greater the peak voltage increase, and vice versa. On the side of current, active power and rotor rotation speed, the smaller the pitch angle, the less wave disturbance fluctuations and the faster the DFIG reach its stable condition for the output parameters, and vice versa. From these relationships, it can be concluded that a pitch angle of ° degrees has a more stable output and can make DFIG more responsive to reach its normal condition when there is a disturbance that enters the electric power system.","PeriodicalId":156265,"journal":{"name":"2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)","volume":"169 4299 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115037738","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}