Pub Date : 2023-03-05DOI: 10.35842/icostec.v2i1.30
Fazli Nugraha Tambunan, Rika Rosnelly, Z. Situmorang
Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20- fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.
{"title":"Transfer Learning for Feral Cat Classification Using Logistic Regression","authors":"Fazli Nugraha Tambunan, Rika Rosnelly, Z. Situmorang","doi":"10.35842/icostec.v2i1.30","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.30","url":null,"abstract":"Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20- fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"634 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115110864","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.33
Doughlas Pardede, W. Wanayumini, Rika Rosnelly
Differences in human facial structures, especially those recorded in a digital image, can be used as an automatic gender comparison tool. This research utilizes machine learning using the support vector machine (SVM) algorithm to perform gender identification based on human facial images. The transfer learning technique using the Inception-v3 model is combined with the SVM algorithm to produce six models that implement polynomial, radial basis function (RBF), and sigmoid kernel functions. The results obtained are models with excellent performance, as seen from the lowest values of accuracy = 0.852, precision = 0.856, recall = 0.852, and the highest values of 0.957, 0.957, and 0.957. This combination also produces a model with excellent reliability, where the probability of overfitting or underfitting obtained is below 1%.
{"title":"A Combination Of Support Vector Machine And Inception-V3 In Face-Based Gender Classification","authors":"Doughlas Pardede, W. Wanayumini, Rika Rosnelly","doi":"10.35842/icostec.v2i1.33","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.33","url":null,"abstract":"Differences in human facial structures, especially those recorded in a digital image, can be used as an automatic gender comparison tool. This research utilizes machine learning using the support vector machine (SVM) algorithm to perform gender identification based on human facial images. The transfer learning technique using the Inception-v3 model is combined with the SVM algorithm to produce six models that implement polynomial, radial basis function (RBF), and sigmoid kernel functions. The results obtained are models with excellent performance, as seen from the lowest values of accuracy = 0.852, precision = 0.856, recall = 0.852, and the highest values of 0.957, 0.957, and 0.957. This combination also produces a model with excellent reliability, where the probability of overfitting or underfitting obtained is below 1%.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134120836","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.48
S. Indirawati, Pauzi Ibrahim Nainggolan, U. Salmah, Dhany Syahputra Bukit, Indra Chahaya
The number of dengue cases in Tebing Tinggi, North Sumatra province has fluctuated. The number of DHF cases in 2021 was 87 cases, then it was increase in 2022 to 175 cases. This number is still relatively high considering that the indicator for DHF morbidity is 20/100,000 population. Efforts to control the DHF vector have been carried out but have not been maximal in reducing cases. One House One The Larvae Observer Movement as the effort to optimizing Mosquito Nest Eradication (MNE) and 3M Plus in the Community has been carried out but determining the larvae free index (LFI) and larval density using a house survey requires time and The Larvae Observer's accuracy in seeing the type and presence of mosquitoes. Utilization of technology with digital images can address this imbalance in The Larvae Observer's tasks. LFI data can be directly reported along with a map of the location of the house with positive larvae so that time is more efficient and the presentation of information is more accurate. This study aims to determine the zoning of potential DHF areas using digital images technology in monitoring the presence of larvae. This type of research was an analytic survey with a cross-sectional design. The population of this study were all houses located in endemic areas, a sample of 500 houses representing 5 districts was taken by purposive sampling. Data collection uses the kobotoolbox which contains questions about the condition of the house, TPA and its type. Larvae application with digital image to identify the presence of larvae and map positive larvae houses. Spatial analysis was used to map the zoning for the presence of Aedes aegypti larvae and larvae free index (LFI), HI, CI and BI. The results showed that the maps of 5 sub-districts representing 5 sub-districts in the city of Tebing Tinggi, all of them have potential risks because LFI <95%, HI 13-35%, Ci 6.5 -13.4%, BI 20-50%, LFI 65-87% .
北苏门答腊省特炳丁吉的登革热病例数有所波动。2021年登革出血热病例数为87例，2022年增加到175例。考虑到登革出血热发病率指标为20/10万人，这一数字仍然相对较高。已开展控制登革出血热病媒的努力，但未能最大限度地减少病例。作为优化社区灭蚊(MNE)和3M Plus的努力，已开展了幼虫观察者运动，但使用房屋调查确定无幼虫指数(LFI)和幼虫密度需要时间和幼虫观察者观察蚊子类型和存在的准确性。利用数字图像技术可以解决幼虫观察者任务中的这种不平衡。LFI数据可以直接连同带有阳性幼虫的房屋位置地图一起报告，这样时间更有效率，信息呈现更准确。本研究旨在利用数字图像技术监测幼虫的存在，确定潜在的DHF区域的分区。这种类型的研究是一个分析调查与横断面设计。本研究的人口均为位于流行地区的房屋，采用有目的抽样的方法，抽取了代表5个区500所房屋的样本。数据收集使用kobotoolbox，其中包含有关房屋状况，TPA及其类型的问题。幼虫应用数码图像识别幼虫的存在，并绘制阳性幼虫的巢穴。采用空间分析方法绘制埃及伊蚊幼虫分布分区、幼虫游离指数(LFI)、HI、CI和BI。结果表明:特滨市5个街道的5个街道地图均存在潜在风险，LFI <95%， HI 13-35%， Ci 6.5 -13.4%， BI 20-50%， LFI 65-87%。
{"title":"The Larvae Project Application as a Digital Image for monitoring the Larvae Free Index in DHF endemic areas in Tebing Tinggi city","authors":"S. Indirawati, Pauzi Ibrahim Nainggolan, U. Salmah, Dhany Syahputra Bukit, Indra Chahaya","doi":"10.35842/icostec.v2i1.48","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.48","url":null,"abstract":"The number of dengue cases in Tebing Tinggi, North Sumatra province has fluctuated. The number of DHF cases in 2021 was 87 cases, then it was increase in 2022 to 175 cases. This number is still relatively high considering that the indicator for DHF morbidity is 20/100,000 population. Efforts to control the DHF vector have been carried out but have not been maximal in reducing cases. One House One The Larvae Observer Movement as the effort to optimizing Mosquito Nest Eradication (MNE) and 3M Plus in the Community has been carried out but determining the larvae free index (LFI) and larval density using a house survey requires time and The Larvae Observer's accuracy in seeing the type and presence of mosquitoes. Utilization of technology with digital images can address this imbalance in The Larvae Observer's tasks. LFI data can be directly reported along with a map of the location of the house with positive larvae so that time is more efficient and the presentation of information is more accurate. This study aims to determine the zoning of potential DHF areas using digital images technology in monitoring the presence of larvae. This type of research was an analytic survey with a cross-sectional design. The population of this study were all houses located in endemic areas, a sample of 500 houses representing 5 districts was taken by purposive sampling. Data collection uses the kobotoolbox which contains questions about the condition of the house, TPA and its type. Larvae application with digital image to identify the presence of larvae and map positive larvae houses. Spatial analysis was used to map the zoning for the presence of Aedes aegypti larvae and larvae free index (LFI), HI, CI and BI. The results showed that the maps of 5 sub-districts representing 5 sub-districts in the city of Tebing Tinggi, all of them have potential risks because LFI <95%, HI 13-35%, Ci 6.5 -13.4%, BI 20-50%, LFI 65-87% .","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131510311","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.55
Yossi Naomi Magdalena, T. Raharjo, D. I. Sensuse
In developing the e-commerce business in Indonesia, e-commerce companies must maintain customer satisfaction. In the e-commerce company, customer satisfaction can see from the ratings given by consumers. This research aims to find factors influencing consumers in providing ratings to improve services. The company’s current condition does not know the indicators when consumers give ratings. The current situation is decreasing order because the number of bad rating is higher and impact to profit company. This research uses several methods, such as the Unified Theory of Acceptance and Use of Technology (UTAUT), the Technology Acceptance Model (TAM), and product quality that influences ratings. The target respondents are consumers who have given bad ratings and have never been given a rating, with 326 respondents. The statistical analysis processing used was Partial Least Square (PLS) with SmartPLS v.4 tools. The results of the research concluded that the factors that influence bad rating respondents in giving ratings with significant positive results are the factors of perceived ease of use, social influence, and customer satisfaction, with an r-square rating value of 0.354 (moderate). From moderation, the variable with the most significant positive effect is the female gender. Meanwhile, respondents who have never been given a rating that has a significant positive impact are performance expectancy, social influence, and customer satisfaction, with an r-square value for ratings of 0.823 (strong). The results of this research concluded that there are several improvements to improve service, namely improving application algorithms, developing operational teams, and several strategies to overcome the impact of the covid pandemic.
{"title":"The Factors that Affect Customer Ratings in E-Commerce Company","authors":"Yossi Naomi Magdalena, T. Raharjo, D. I. Sensuse","doi":"10.35842/icostec.v2i1.55","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.55","url":null,"abstract":"In developing the e-commerce business in Indonesia, e-commerce companies must maintain customer satisfaction. In the e-commerce company, customer satisfaction can see from the ratings given by consumers. This research aims to find factors influencing consumers in providing ratings to improve services. The company’s current condition does not know the indicators when consumers give ratings. The current situation is decreasing order because the number of bad rating is higher and impact to profit company. This research uses several methods, such as the Unified Theory of Acceptance and Use of Technology (UTAUT), the Technology Acceptance Model (TAM), and product quality that influences ratings. The target respondents are consumers who have given bad ratings and have never been given a rating, with 326 respondents. The statistical analysis processing used was Partial Least Square (PLS) with SmartPLS v.4 tools. The results of the research concluded that the factors that influence bad rating respondents in giving ratings with significant positive results are the factors of perceived ease of use, social influence, and customer satisfaction, with an r-square rating value of 0.354 (moderate). From moderation, the variable with the most significant positive effect is the female gender. Meanwhile, respondents who have never been given a rating that has a significant positive impact are performance expectancy, social influence, and customer satisfaction, with an r-square value for ratings of 0.823 (strong). The results of this research concluded that there are several improvements to improve service, namely improving application algorithms, developing operational teams, and several strategies to overcome the impact of the covid pandemic.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130824680","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.56
Yuni Franciska br Tarigan, T. Gunawan, B. Hayadi
Javanese script is one of Indonesia's cultural heritages that are increasingly rarely used today. The difficulty of recognizing the shapes of letters, let alone writing them, is the main obstacle in using the Hanacaraka script. This research offers an alternative to Hanacaraka script recognition using a combination of image feature extraction and machine learning, where we utilize a pre-trained SquzeeNet model and Multilayer Backpropagation algorithm. Of the 18 models built using ReLu, Sigmoid, and Tanh activation functions, we found that the Tanh activation function, using the combination of 50-50-100 neuron configuration and 25 epochs, was the most optimal function used to classify the training data with accuracy, precision, and recall values of 93.8%. Meanwhile, the Tanh activation function, using the 50-100-50 neuron configuration and 50 epochs, is the most optimal function to classify the testing data, with accuracy, precision, and recall values of 89.1%, 89.5%, and 89.5%. All built models show a training and testing performance ratio below 10%. From this result, we conclude that all models have good reliability in the training and testing classification process.
{"title":"Combination Of SqueezeNet And Multilayer Backpropagation Algorithm In Hanacaraka Script Recognition","authors":"Yuni Franciska br Tarigan, T. Gunawan, B. Hayadi","doi":"10.35842/icostec.v2i1.56","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.56","url":null,"abstract":"Javanese script is one of Indonesia's cultural heritages that are increasingly rarely used today. The difficulty of recognizing the shapes of letters, let alone writing them, is the main obstacle in using the Hanacaraka script. This research offers an alternative to Hanacaraka script recognition using a combination of image feature extraction and machine learning, where we utilize a pre-trained SquzeeNet model and Multilayer Backpropagation algorithm. Of the 18 models built using ReLu, Sigmoid, and Tanh activation functions, we found that the Tanh activation function, using the combination of 50-50-100 neuron configuration and 25 epochs, was the most optimal function used to classify the training data with accuracy, precision, and recall values of 93.8%. Meanwhile, the Tanh activation function, using the 50-100-50 neuron configuration and 50 epochs, is the most optimal function to classify the testing data, with accuracy, precision, and recall values of 89.1%, 89.5%, and 89.5%. All built models show a training and testing performance ratio below 10%. From this result, we conclude that all models have good reliability in the training and testing classification process.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133308595","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.59
S. Riyadi, H. Hartono, W. Wanayumini
A person's talent is closely related to intelligence, hobbies, and interests. These factors are the best features to be used in a dataset to predict a children's talent, such as in an academy, arts, or sports. This research uses the C4.5 and random forest algorithms in 8 different models to predict a children's talent based on a dataset gained from a survey involving 1601 parents. Each model contains four training-testing data ratios, such as 50:50, 60:40, 70:30, and 80:20. We calculate each model prediction performance using 10-fold and 20-fold cross validation, with the accuracy, f-score, precision, and recall values as a comparison. The best result for the training evaluation we get is 91.5% for each comparison value from the random forest model (70:30 ratio) using a 20-fold cross-validation. For the testing evaluation, we get 92.7%, 92.8%, 92.8%, and 92.7% from the random forest model (50:50 ratio). The worst testing evaluation we get is 81.7% for each comparison value from the C4.5 model (50:50 ratio) using a 20-fold cross-validation. For the testing evaluation, we get 89.2%, 89.2%, 89.3%, and 89.2% from the C4.5 model (50:50 ratio).
{"title":"Predicting Children's Talent Based On Hobby Using C4.5 Algorithm And Random Forest","authors":"S. Riyadi, H. Hartono, W. Wanayumini","doi":"10.35842/icostec.v2i1.59","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.59","url":null,"abstract":"A person's talent is closely related to intelligence, hobbies, and interests. These factors are the best features to be used in a dataset to predict a children's talent, such as in an academy, arts, or sports. This research uses the C4.5 and random forest algorithms in 8 different models to predict a children's talent based on a dataset gained from a survey involving 1601 parents. Each model contains four training-testing data ratios, such as 50:50, 60:40, 70:30, and 80:20. We calculate each model prediction performance using 10-fold and 20-fold cross validation, with the accuracy, f-score, precision, and recall values as a comparison. The best result for the training evaluation we get is 91.5% for each comparison value from the random forest model (70:30 ratio) using a 20-fold cross-validation. For the testing evaluation, we get 92.7%, 92.8%, 92.8%, and 92.7% from the random forest model (50:50 ratio). The worst testing evaluation we get is 81.7% for each comparison value from the C4.5 model (50:50 ratio) using a 20-fold cross-validation. For the testing evaluation, we get 89.2%, 89.2%, 89.3%, and 89.2% from the C4.5 model (50:50 ratio).","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115461346","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.47
U. Salmah, S. Indirawati, Risanti FR Situmorang, Pauzi Ibrahim Nainggolan
A large number of accidents begins with the number of near misses and the magnitude of work risks experienced by workers, so control efforts are needed as early as possible. This study uses quantitative research using the SIRISKA smart online application (Occupational Risk Mapping System) involving sections clerks and oil palm harvesters as respondents. There were 3 cases of work accidents, and there was a near-miss hazard at each stage of oil palm harvesting. The near-miss hazards that can occur are being cut by an sickle or an axe, falling by an sickle, being crushed by a frond, being hit by a fibre, or being pierced by a palm thorn which must be recorded and reported. By optimizing the reporting system using the SIRISKA smart online application, it is hoped that zero accidents can be achieved at PTPN IV Adolina Garden.
大量的事故都是从险些事故的数量和工人所经历的工作风险的大小开始的，所以需要尽早采取控制措施。本研究使用SIRISKA智能在线应用程序(职业风险测绘系统)进行定量研究，涉及部门文员和油棕采收者作为调查对象。工作事故共发生3起，油棕采收各阶段均有一次险情发生。可能发生的险情包括被镰刀或斧头割伤、被镰刀砍倒、被叶子压碎、被纤维击中或被棕榈刺穿，这些都必须记录和报告。通过使用SIRISKA智能在线应用程序优化报告系统，希望PTPN IV Adolina花园能够实现零事故。
{"title":"Optimization of the Near Miss Reporting System in Achieving Zero Accidents at PTPN IV ADOLINA Garden (SIRISKA Online Smart Application)","authors":"U. Salmah, S. Indirawati, Risanti FR Situmorang, Pauzi Ibrahim Nainggolan","doi":"10.35842/icostec.v2i1.47","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.47","url":null,"abstract":"A large number of accidents begins with the number of near misses and the magnitude of work risks experienced by workers, so control efforts are needed as early as possible. This study uses quantitative research using the SIRISKA smart online application (Occupational Risk Mapping System) involving sections clerks and oil palm harvesters as respondents. There were 3 cases of work accidents, and there was a near-miss hazard at each stage of oil palm harvesting. The near-miss hazards that can occur are being cut by an sickle or an axe, falling by an sickle, being crushed by a frond, being hit by a fibre, or being pierced by a palm thorn which must be recorded and reported. By optimizing the reporting system using the SIRISKA smart online application, it is hoped that zero accidents can be achieved at PTPN IV Adolina Garden.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130592855","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.50
Hari Anna Lastya, Y. Away, T. Tarmizi, I. D. Sara, M. Ikhsan, Ulya Zikra, Nikmal Maula Mirda
Solar energy is optimally obtained by solar cells when the solar cells are perpendicular to the sun's position, so a sun tracker is needed to track the sun precisely. This research compares the electrical power used in two system dual-axis sun trackers with a tetrahedron geometry that uses an LDR sensor with a phototransistor sensor. The two sun trackers are built identically and the experimental data with the servo movement and the solar cell load are carried out side by side. The servo motor controls with Proportional Integral Derivative (PID) algorithm controls the movement of the dual-axis sun tracker. Data were obtained by recording the voltage and current received by the solar cells installed on the two sun trackers and comparing the results. The results showed that the phototransistor sensor performs better than the LDR sensor. This can be seen from the amount of power generated by the phototransistor sensor which is more than the power generated by the LDR sensor on the solar cell. The solar energy received by sun tracker uses a phototransistor sensor average 40% more than sun tracker uses an LDR sensor.
{"title":"Performance Comparison Between LDR and Phototransistor Sensor for Dual-Axis Sun Tracker Sensor Based on Tetrahedron Geometry","authors":"Hari Anna Lastya, Y. Away, T. Tarmizi, I. D. Sara, M. Ikhsan, Ulya Zikra, Nikmal Maula Mirda","doi":"10.35842/icostec.v2i1.50","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.50","url":null,"abstract":"Solar energy is optimally obtained by solar cells when the solar cells are perpendicular to the sun's position, so a sun tracker is needed to track the sun precisely. This research compares the electrical power used in two system dual-axis sun trackers with a tetrahedron geometry that uses an LDR sensor with a phototransistor sensor. The two sun trackers are built identically and the experimental data with the servo movement and the solar cell load are carried out side by side. The servo motor controls with Proportional Integral Derivative (PID) algorithm controls the movement of the dual-axis sun tracker. Data were obtained by recording the voltage and current received by the solar cells installed on the two sun trackers and comparing the results. The results showed that the phototransistor sensor performs better than the LDR sensor. This can be seen from the amount of power generated by the phototransistor sensor which is more than the power generated by the LDR sensor on the solar cell. The solar energy received by sun tracker uses a phototransistor sensor average 40% more than sun tracker uses an LDR sensor.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127646956","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.39
Khairul fadhli Fadhli Margolang, Muhammad Zarlis, H. Hartono
As one the most famous world-class motorcycle racing competition, MotoGP is an event broadcast live on television with millions of viewers on each race. Indonesia, especially the Pertamina Mandalika Circuit, will hold this prestigious racing event in the 19th series of 2022. This event sparks Indonesian netizens' reactions on social media, especially on Twitter. This research aims to analyze the public sentiment and emotional value regarding this event, with the data collected from Twitter social media. With the features of sentiment and emotion values extracted from the contents of this tweet, we use K-means clustering to generate sentiment clusters as targets for the classification using the Random Forest (RF) algorithm. From the evaluation using the 5-fold and 10-fold cross-validation, we get the highest accuracy of 0.99, the highest precision of 0.990175, and the highest recall of 0.99 from the RF model with ten trees configuration. We also get the lowest accuracy, precision, and recall values of 0.96, 0.960934, and 0.96 from the RF models with 15 and 20 trees configuration, with the 10-fold evaluation.
{"title":"Sentiment Classification on Mandalika MotoGP Event Using K-Means Clustering and Random Forest","authors":"Khairul fadhli Fadhli Margolang, Muhammad Zarlis, H. Hartono","doi":"10.35842/icostec.v2i1.39","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.39","url":null,"abstract":"As one the most famous world-class motorcycle racing competition, MotoGP is an event broadcast live on television with millions of viewers on each race. Indonesia, especially the Pertamina Mandalika Circuit, will hold this prestigious racing event in the 19th series of 2022. This event sparks Indonesian netizens' reactions on social media, especially on Twitter. This research aims to analyze the public sentiment and emotional value regarding this event, with the data collected from Twitter social media. With the features of sentiment and emotion values extracted from the contents of this tweet, we use K-means clustering to generate sentiment clusters as targets for the classification using the Random Forest (RF) algorithm. From the evaluation using the 5-fold and 10-fold cross-validation, we get the highest accuracy of 0.99, the highest precision of 0.990175, and the highest recall of 0.99 from the RF model with ten trees configuration. We also get the lowest accuracy, precision, and recall values of 0.96, 0.960934, and 0.96 from the RF models with 15 and 20 trees configuration, with the 10-fold evaluation.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122285983","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 : 2023-03-05DOI: 10.35842/icostec.v2i1.52
Radhika Sreedharan
IoT (Internet of Things) is related to design of a lot of iinter-related “contrived" gadgets having finite capacities with regard to memory and processing power and design is like an Internet. These are frequently battery-driven, raises requirement for adopting environment-friendly techniques. Between the noteworthy ultimatum that establishing interrelated smart objects accompanies are uniformity and coordination. Many smart objects are presumed to develop and addresses of IPv4 are normally utilized. IPv6 is recognized as a possibility for smartobject transmission. Internet of Things (IoT) is a global network of physical and virtual ‘things’ connected to the internet. All objects have unique IDs that are utilized for identification. IoT is the emerging technology which can change the way we communicate with devices. Hereafter almost every electronic device will be a smart device that will be able to compute and communicate with handheld and other infrastructure gadgets. The Internet of Things utilization builds a lot of security problems, which arises from • Smart objects essence: utilization of cryptographic algorithms which are delicate, with regard to requirements of processing and memory. • Quality protocols utilization and the requirement to reduce the data quantity swapped among nodes. An IoT usage which accumulates or handles consumer distinctive data like bank particulars require a foremost rank of security, while a sensor linked to a station area will have a low rank. It need not be costly to carry out fundamental security steps; but it is significant to determine a security strategy and incorporate recuperation measures in the security problems incidents. The main aim of this topic is to describe mechanisms which can help to deal with IoT security issues.
物联网(Internet of Things, Internet of Things)是指设计大量相互关联的“人造”设备，这些设备在内存和处理能力方面的容量有限，而设计就像互联网一样。它们通常是电池驱动的，这就提出了采用环保技术的要求。在建立相互关联的智能对象的值得注意的最后通牒之间伴随着统一和协调。假定有许多智能对象被开发，并且IPv4地址通常被使用。IPv6被认为是智能对象传输的一种可能性。物联网(IoT)是连接到互联网的物理和虚拟“事物”的全球网络。所有对象都有惟一的id，用于标识。物联网是一种新兴技术，它可以改变我们与设备的通信方式。此后，几乎所有电子设备都将是智能设备，能够与手持设备和其他基础设施设备进行计算和通信。物联网的使用构建了许多安全问题，这些问题源于智能对象的本质:加密算法的使用是微妙的，在处理和内存的要求方面。•高质量协议利用率和减少节点间交换数据量的要求。积累或处理消费者独特数据(如银行信息)的物联网应用需要最高级别的安全性，而连接到车站区域的传感器则需要低级别的安全性。实施基本的安全措施不一定代价高昂;但在安全问题事件中，确定安全策略并纳入恢复措施具有重要意义。本主题的主要目的是描述有助于处理物联网安全问题的机制。
{"title":"Dealing With Security Issues In IoT","authors":"Radhika Sreedharan","doi":"10.35842/icostec.v2i1.52","DOIUrl":"https://doi.org/10.35842/icostec.v2i1.52","url":null,"abstract":"IoT (Internet of Things) is related to design of a lot of iinter-related “contrived\" gadgets having finite capacities with regard to memory and processing power and design is like an Internet. These are frequently battery-driven, raises requirement for adopting environment-friendly techniques. Between the noteworthy ultimatum that establishing interrelated smart objects accompanies are uniformity and coordination. Many smart objects are presumed to develop and addresses of IPv4 are normally utilized. IPv6 is recognized as a possibility for smartobject transmission. Internet of Things (IoT) is a global network of physical and virtual ‘things’ connected to the internet. All objects have unique IDs that are utilized for identification. IoT is the emerging technology which can change the way we communicate with devices. Hereafter almost every electronic device will be a smart device that will be able to compute and communicate with handheld and other infrastructure gadgets. The Internet of Things utilization builds a lot of security problems, which arises from • Smart objects essence: utilization of cryptographic algorithms which are delicate, with regard to requirements of processing and memory. • Quality protocols utilization and the requirement to reduce the data quantity swapped among nodes. An IoT usage which accumulates or handles consumer distinctive data like bank particulars require a foremost rank of security, while a sensor linked to a station area will have a low rank. It need not be costly to carry out fundamental security steps; but it is significant to determine a security strategy and incorporate recuperation measures in the security problems incidents. The main aim of this topic is to describe mechanisms which can help to deal with IoT security issues.","PeriodicalId":241682,"journal":{"name":"International Conference on Information Science and Technology Innovation (ICoSTEC)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132115925","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：