Platform metabase GIS data analysis based on the cloud that has been successfully developed is an alternative solution for spatial-text data analysis. The output of this cloud-based platform not only provides accurate textual information but also precise location representation of the objects. This research examines the quality of the developed platform based on ISO 9126, which consists of six main indicators: functionality, reliability, feasibility, efficiency, maintainability, and portability. Each indicator has different sub-indicators, totaling 22 sub-indicators. The quality assessment results indicate that the platform for metabase GIS data analysis based on the cloud exhibits excellent quality, with an average test result based on the ISO 9126 indicators reaching 93%.
已成功开发的基于云的元数据库 GIS 数据分析平台是空间文本数据分析的另一种解决方案。该云平台的输出不仅能提供准确的文本信息，还能提供对象的精确位置表示。本研究根据 ISO 9126 标准对所开发平台的质量进行了检验，该标准包括六大指标：功能性、可靠性、可行性、效率、可维护性和可移植性。每个指标都有不同的子指标，共计 22 个子指标。质量评估结果表明，基于云的元数据库 GIS 数据分析平台质量优异，基于 ISO 9126 指标的平均测试结果达到 93%。
{"title":"Cloud-based Metabase GIS Data Analysis Platform Quality Management According to ISO 9126 Indicators","authors":"Rani Purbaningtyas, Moh Munih Dian Widianta, Mochammad Rifki Ulil Albaab","doi":"10.20895/infotel.v16i1.1041","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1041","url":null,"abstract":"Platform metabase GIS data analysis based on the cloud that has been successfully developed is an alternative solution for spatial-text data analysis. The output of this cloud-based platform not only provides accurate textual information but also precise location representation of the objects. This research examines the quality of the developed platform based on ISO 9126, which consists of six main indicators: functionality, reliability, feasibility, efficiency, maintainability, and portability. Each indicator has different sub-indicators, totaling 22 sub-indicators. The quality assessment results indicate that the platform for metabase GIS data analysis based on the cloud exhibits excellent quality, with an average test result based on the ISO 9126 indicators reaching 93%.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"14 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140443131","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 : 2024-02-21DOI: 10.20895/infotel.v16i1.1075
Sulistyo Widodo, Erfiana Wahyuningsih, Y. G. Adhiyoga
Indonesia will become a net importer if it runs out of oil and gas reserves within the next 11 to 12 years if no alternative energy sources are developed. Therefore, there is a need to utilize alternative energy that is not dependent on oil or gas. One alternative energy is using solar light energy. This research designed a device that can convert the energy of sunlight into electrical energy and automatically store electrical energy in a battery with PWM (Pulse Width Modulation) so that it can be used as alternative energy, and help reduce the consumption of electricity from PLN. The battery used 12V 80Ah and a solar panel module 50W for energy storage and system resources. The research results show that systems can automatically charge energy using sunlight and turn the lights to 7W. Using the charging system automatically uses PWM to reduce the risk of damage to the battery because, in the charging process, battery conditions will be monitored. The maximum power generated from solar panel modules used is 35.57 W.
{"title":"Solar Panel Power Generator with Automatic Charging using PWM System based on Microcontroller","authors":"Sulistyo Widodo, Erfiana Wahyuningsih, Y. G. Adhiyoga","doi":"10.20895/infotel.v16i1.1075","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1075","url":null,"abstract":"Indonesia will become a net importer if it runs out of oil and gas reserves within the next 11 to 12 years if no alternative energy sources are developed. Therefore, there is a need to utilize alternative energy that is not dependent on oil or gas. One alternative energy is using solar light energy. This research designed a device that can convert the energy of sunlight into electrical energy and automatically store electrical energy in a battery with PWM (Pulse Width Modulation) so that it can be used as alternative energy, and help reduce the consumption of electricity from PLN. The battery used 12V 80Ah and a solar panel module 50W for energy storage and system resources. The research results show that systems can automatically charge energy using sunlight and turn the lights to 7W. Using the charging system automatically uses PWM to reduce the risk of damage to the battery because, in the charging process, battery conditions will be monitored. The maximum power generated from solar panel modules used is 35.57 W.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"37 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140444389","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 : 2024-02-21DOI: 10.20895/infotel.v16i1.1103
A. A. Gozali, Fat’hah Noor Prawita, Ihshan Gumilar, Haidar Rashid Ramdana Putra, Muhammad Arief Fauzan
Navigational challenges in large buildings with multiple rooms, such as museums, often result in inefficient visitor experiences. Traditional signage and direction plans, while common, do not always effectively convey the necessary information. This paper introduces an innovative solution leveraging Augmented Reality (AR) technology to enhance navigation in such complex environments. We developed a mobile application utilizing the Immersal Software Development Kit (SDK) to facilitate interaction with the surroundings in the Bandung Geological Museum. The application serves as a digital guide, providing clear directions and route information to various rooms within the museum. Our study's findings reveal that the application not only facilitated easier navigation through its accurate room identification and route suggestions but also enhanced the overall visitor experience by making it more interactive and immersive. Furthermore, the user engagement and experience survey, encompassing a broad demographic range, highlighted a significant increase in visitor satisfaction and interaction. The application's intuitive and user-friendly interface played a key role in this enhanced engagement. The survey results reflect the application's success in meeting its main objectives, demonstrating usability, and offering an effective user interface.
{"title":"Geo-Navigation in Museums: Augmented Reality Application in the Geological Museum Indonesia","authors":"A. A. Gozali, Fat’hah Noor Prawita, Ihshan Gumilar, Haidar Rashid Ramdana Putra, Muhammad Arief Fauzan","doi":"10.20895/infotel.v16i1.1103","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1103","url":null,"abstract":"Navigational challenges in large buildings with multiple rooms, such as museums, often result in inefficient visitor experiences. Traditional signage and direction plans, while common, do not always effectively convey the necessary information. This paper introduces an innovative solution leveraging Augmented Reality (AR) technology to enhance navigation in such complex environments. We developed a mobile application utilizing the Immersal Software Development Kit (SDK) to facilitate interaction with the surroundings in the Bandung Geological Museum. The application serves as a digital guide, providing clear directions and route information to various rooms within the museum. Our study's findings reveal that the application not only facilitated easier navigation through its accurate room identification and route suggestions but also enhanced the overall visitor experience by making it more interactive and immersive. Furthermore, the user engagement and experience survey, encompassing a broad demographic range, highlighted a significant increase in visitor satisfaction and interaction. The application's intuitive and user-friendly interface played a key role in this enhanced engagement. The survey results reflect the application's success in meeting its main objectives, demonstrating usability, and offering an effective user interface.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"14 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140441906","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 : 2024-02-19DOI: 10.20895/infotel.v16i1.999
Anita Desiani, Rifkie Primartha, Herlina Hanum, Siti Rusdiana Puspa Dewi, Muhammad Gibran Al-Filambany, Muhammad Suedarmin, B. Suprihatin
Diabetic Retinopathy (DR) is a diabetes disease that attacks the retina of the eye and can be recognized through retinal images. The process of assisting retinal images can be done by applying deep learning-based methods, one of which is the Convolutional Neural Network (CNN). CNN has many architectures that can perform image classification processes, namely ResNet-50, MobileNet, and EfficientNet. Weaknesses of each architecture can be overcome through ensemble learning methods that can add up the performance results of each classification method. The study applies the ensemble learning method to improve the performance of the ResNet-50, MobileNet, and EfficientNet architectures in paying for DR disease on the retina by weighted voting. The data used are the APTOS and EyePACS datasets. The method in this research is data collection, training, testing, and evaluation of each architecture and ensemble learning. The results of the superior ensemble learning performance in the value of accuracy, F1-Score, and Cohens Kappa were obtained respectively 93.3%, 93.42%, and 0.866. The best specificity value was obtained by Resnet-50 at 99.78% and the highest sensitivity value was obtained by EfficientNet at 96.2%. Based on the classification results of each architectural and ensemble learning, it can be interpreted that the proposed ensemble learning method is excellent to perform image classification for Diabetic Retinopathy.
{"title":"Weighted Voting Ensemble Learning of CNN Architectures for Diabetic Retinopathy Classification","authors":"Anita Desiani, Rifkie Primartha, Herlina Hanum, Siti Rusdiana Puspa Dewi, Muhammad Gibran Al-Filambany, Muhammad Suedarmin, B. Suprihatin","doi":"10.20895/infotel.v16i1.999","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.999","url":null,"abstract":"Diabetic Retinopathy (DR) is a diabetes disease that attacks the retina of the eye and can be recognized through retinal images. The process of assisting retinal images can be done by applying deep learning-based methods, one of which is the Convolutional Neural Network (CNN). CNN has many architectures that can perform image classification processes, namely ResNet-50, MobileNet, and EfficientNet. Weaknesses of each architecture can be overcome through ensemble learning methods that can add up the performance results of each classification method. The study applies the ensemble learning method to improve the performance of the ResNet-50, MobileNet, and EfficientNet architectures in paying for DR disease on the retina by weighted voting. The data used are the APTOS and EyePACS datasets. The method in this research is data collection, training, testing, and evaluation of each architecture and ensemble learning. The results of the superior ensemble learning performance in the value of accuracy, F1-Score, and Cohens Kappa were obtained respectively 93.3%, 93.42%, and 0.866. The best specificity value was obtained by Resnet-50 at 99.78% and the highest sensitivity value was obtained by EfficientNet at 96.2%. Based on the classification results of each architectural and ensemble learning, it can be interpreted that the proposed ensemble learning method is excellent to perform image classification for Diabetic Retinopathy.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"30 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140450943","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 : 2024-02-16DOI: 10.20895/infotel.v16i1.1057
Tamsir Ariyadi, I. Irham, Eko Fajar Cahyadi
Advances in information and communication technology continue to grow over time. This causes significant changes in social, economic, and political conditions. One company that requires strong network security is PT PLN (Perusahaan Listrik Negara) Persero, which is a leading energy company in Indonesia. In this case, the need to evaluate network security at PT PLN is very important. This evaluation will help identify vulnerabilities and security gaps that exist in PT PLN's network infrastructure. This network security evaluation using the Penetration Testing Execution Standards (PTES) method can provide an overview of the vulnerabilities or weaknesses of the network system at PT PLN UP2D S2JB which has quite a lot of gaps to exploit. This is evidenced by the results of fifteen tests conducted, only two of which failed, namely in the type of attack The Rogue Access Point. The results of Penetration Testing are very necessary and important as feedback for system managers in fixing existing vulnerability gaps.
{"title":"An Evaluation of Wireless Network Security with Penetration Testing Method at PT PLN UP2D S2JB","authors":"Tamsir Ariyadi, I. Irham, Eko Fajar Cahyadi","doi":"10.20895/infotel.v16i1.1057","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1057","url":null,"abstract":"Advances in information and communication technology continue to grow over time. This causes significant changes in social, economic, and political conditions. One company that requires strong network security is PT PLN (Perusahaan Listrik Negara) Persero, which is a leading energy company in Indonesia. In this case, the need to evaluate network security at PT PLN is very important. This evaluation will help identify vulnerabilities and security gaps that exist in PT PLN's network infrastructure. This network security evaluation using the Penetration Testing Execution Standards (PTES) method can provide an overview of the vulnerabilities or weaknesses of the network system at PT PLN UP2D S2JB which has quite a lot of gaps to exploit. This is evidenced by the results of fifteen tests conducted, only two of which failed, namely in the type of attack The Rogue Access Point. The results of Penetration Testing are very necessary and important as feedback for system managers in fixing existing vulnerability gaps.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"197 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140454547","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 : 2024-02-13DOI: 10.20895/infotel.v16i1.1025
Aji Gautama Putrada, M. Abdurohman, Doan Perdana, Hilal Hudan Nuha
Several previous studies have proposed a temporal sequential-artificial neural network (TS-ANN) to convert PIR Sensor movement data into presence data and improve the performance of smart lighting control. However, such a temporal-sequential forecasting concept has a curse of dimensionality problem. This study aims to proposes the application of principal component analysis with TS-ANN (PCA-TS-ANN) as an intelligent method for controlling smart lighting with low dimensions. We have primary data directly from a smart lighting implementation that utilizes PIR sensors. We apply cross-correlation to the original dataset to find the optimum time step. Then we discover the optimum TS-ANN based on selected tuning parameter values through PCC. We then design and compare scenarios involving the combination of TS-ANN and PCA. Finally, we evaluate these scenarios using the metrics Accuracy, Precision, Recall, F1− Score, and Delay. The results of this study are the PCA-TS-ANN model with Accuracy, Precision, Recall, and F1−Score value of 0.9993, 0.9997, 0.9994, and 0.9996 respectively. The PCA method reduces the TS-ANN features from 1200 features to 36 features. The model size has also decreased from 3534kB to 807kB. Our model has a simpler complexity with TS-ANN that the µ ± σ Delay is 0.27±0.06 ms versus 0.34±0.11 ms.
{"title":"Temporal Sequential-Artificial Neural Network Enhancements for Improved Smart Lighting Control","authors":"Aji Gautama Putrada, M. Abdurohman, Doan Perdana, Hilal Hudan Nuha","doi":"10.20895/infotel.v16i1.1025","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1025","url":null,"abstract":"Several previous studies have proposed a temporal sequential-artificial neural network (TS-ANN) to convert PIR Sensor movement data into presence data and improve the performance of smart lighting control. However, such a temporal-sequential forecasting concept has a curse of dimensionality problem. This study aims to proposes the application of principal component analysis with TS-ANN (PCA-TS-ANN) as an intelligent method for controlling smart lighting with low dimensions. We have primary data directly from a smart lighting implementation that utilizes PIR sensors. We apply cross-correlation to the original dataset to find the optimum time step. Then we discover the optimum TS-ANN based on selected tuning parameter values through PCC. We then design and compare scenarios involving the combination of TS-ANN and PCA. Finally, we evaluate these scenarios using the metrics Accuracy, Precision, Recall, F1− Score, and Delay. The results of this study are the PCA-TS-ANN model with Accuracy, Precision, Recall, and F1−Score value of 0.9993, 0.9997, 0.9994, and 0.9996 respectively. The PCA method reduces the TS-ANN features from 1200 features to 36 features. The model size has also decreased from 3534kB to 807kB. Our model has a simpler complexity with TS-ANN that the µ ± σ Delay is 0.27±0.06 ms versus 0.34±0.11 ms.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"24 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139964273","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 : 2024-02-05DOI: 10.20895/infotel.v16i1.974
S. Sutikno
Heart failure is a dangerous condition in which the heart cannot pump blood effectively and can lead to death. To improve this treatment, it needs methods to predict patient survival. This paper proposed combining wrapping features, namely Binary particle swarm optimization (BPSO) and a multilayer perceptron (MLP) classifier called BPSO-MLP. BPSO is used to determine the most relevant feature subset, and MLP is used to calculate its fitness. The experiment used a public dataset containing the medical records of 299 heart failure patients. This dataset comprises 13 features: age, anemia, high blood pressure, creatinine phosphokinase (CPK), diabetes, ejection fraction, platelets, gender, serum creatinine, serum sodium, smoking, time, and death events. The experiment results showed that the proposed method could produce an accuracy of up to 91.11%. The proposed method can increase accuracy by 8.89% compared to MLP (without BPSO). The addition of this wrapping feature has a significant influence on the accuracy results.
{"title":"Combination of Binary Particle Swarm Optimization (BPSO) and Multilayer Perceptron (MLP) for Survival Prediction of Heart Failure Patients","authors":"S. Sutikno","doi":"10.20895/infotel.v16i1.974","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.974","url":null,"abstract":"Heart failure is a dangerous condition in which the heart cannot pump blood effectively and can lead to death. To improve this treatment, it needs methods to predict patient survival. This paper proposed combining wrapping features, namely Binary particle swarm optimization (BPSO) and a multilayer perceptron (MLP) classifier called BPSO-MLP. BPSO is used to determine the most relevant feature subset, and MLP is used to calculate its fitness. The experiment used a public dataset containing the medical records of 299 heart failure patients. This dataset comprises 13 features: age, anemia, high blood pressure, creatinine phosphokinase (CPK), diabetes, ejection fraction, platelets, gender, serum creatinine, serum sodium, smoking, time, and death events. The experiment results showed that the proposed method could produce an accuracy of up to 91.11%. The proposed method can increase accuracy by 8.89% compared to MLP (without BPSO). The addition of this wrapping feature has a significant influence on the accuracy results.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"56 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139965403","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 : 2024-02-04DOI: 10.20895/infotel.v16i1.1074
Umar Ali Ahmad, Ikbal Ramdani, Fath Muhammad Isham, R. R. Dwiputra S, Yusup Diva Pratama, Rifdo Shah Alam, Fauzi Sofyan, Reza Rendian Septiawan, Ratna Astuti Nugraheni, A. Rusdinar, Ashri Dinimaharawati, M. A. Abdurahman
PAMDES is a drinking water company managed by local villagers. The water meter data are read and recorded manually without any technology, which is ineffective and inefficient. Digital image processing can be implemented to read and record the water meter data automatically. When implemented in the water meter, it can help PAMDES officers to read the data without the internet, without changing the conventional water meter device, and the water meter data can be read and recorded effectively and efficiently. This research used the agile method, one of the methods used in the Software Development Life Cycle (SDLC). The method is done repetitively within a short period of time. The output of this research is an application with a digital image processing model that can read water meter data up to 82% in normal conditions and still can be improved. This research aims to make the water meter data reading and recording more effective and efficient and to contribute to the transformation of Sindangsari village into a digitalized village.
{"title":"Water Meter Reading Application System Development using Image Processing A Case Study from Sindangsari Village Water Services","authors":"Umar Ali Ahmad, Ikbal Ramdani, Fath Muhammad Isham, R. R. Dwiputra S, Yusup Diva Pratama, Rifdo Shah Alam, Fauzi Sofyan, Reza Rendian Septiawan, Ratna Astuti Nugraheni, A. Rusdinar, Ashri Dinimaharawati, M. A. Abdurahman","doi":"10.20895/infotel.v16i1.1074","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1074","url":null,"abstract":"PAMDES is a drinking water company managed by local villagers. The water meter data are read and recorded manually without any technology, which is ineffective and inefficient. Digital image processing can be implemented to read and record the water meter data automatically. When implemented in the water meter, it can help PAMDES officers to read the data without the internet, without changing the conventional water meter device, and the water meter data can be read and recorded effectively and efficiently. This research used the agile method, one of the methods used in the Software Development Life Cycle (SDLC). The method is done repetitively within a short period of time. The output of this research is an application with a digital image processing model that can read water meter data up to 82% in normal conditions and still can be improved. This research aims to make the water meter data reading and recording more effective and efficient and to contribute to the transformation of Sindangsari village into a digitalized village.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"17 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140461744","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 : 2024-02-04DOI: 10.20895/infotel.v16i1.1004
Ainin Maftukhah, Abdul Fadlil, Sunardi Sunardi
Kurangnya pengetahuan tentang kupu-kupu dapat menimbulkan masalah karena kupu-kupu berperan penting dalam ekosistem. Urgensi dalam penelitian ini terkait dengan bidang biologi yaitu klasifikasi citra kupu-kupu dapat membantu dalam memahami pola migrasi, pola kawin, dan pola perilaku kupu-kupu dalam interaksinya dengan lingkungan sekitarnya. Tujuan dari penelitian ini adalah untuk mengklasifikasikan spesies kupu-kupu. Dataset yang digunakan adalah dataset citra kupu-kupu sebanyak 5.499 dengan total 50 spesies. Metode yang diterapkan adalah convolution neural network (CNN) dengan arsitektur AlexNet. Proses pelatihan menggunakan arsitektur AlexNet diawali dengan input dataset citra, dataset akan diproses terlebih dahulu seperti resizing dan RGB to grayscale.Kemudian lakukan filter atau kernel. Output dari kernel digunakan untuk melakukan pooled convolution. Konvolusi dan pooling dilakukan sebanyak lima kali. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan pre
{"title":"Butterfly Image Classification using Convolution Neural Network with AlexNet Architecture","authors":"Ainin Maftukhah, Abdul Fadlil, Sunardi Sunardi","doi":"10.20895/infotel.v16i1.1004","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.1004","url":null,"abstract":"Kurangnya pengetahuan tentang kupu-kupu dapat menimbulkan masalah karena kupu-kupu berperan penting dalam ekosistem. Urgensi dalam penelitian ini terkait dengan bidang biologi yaitu klasifikasi citra kupu-kupu dapat membantu dalam memahami pola migrasi, pola kawin, dan pola perilaku kupu-kupu dalam interaksinya dengan lingkungan sekitarnya. Tujuan dari penelitian ini adalah untuk mengklasifikasikan spesies kupu-kupu. Dataset yang digunakan adalah dataset citra kupu-kupu sebanyak 5.499 dengan total 50 spesies. Metode yang diterapkan adalah convolution neural network (CNN) dengan arsitektur AlexNet. Proses pelatihan menggunakan arsitektur AlexNet diawali dengan input dataset citra, dataset akan diproses terlebih dahulu seperti resizing dan RGB to grayscale.Kemudian lakukan filter atau kernel. Output dari kernel digunakan untuk melakukan pooled convolution. Konvolusi dan pooling dilakukan sebanyak lima kali. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Setiap hasil max pooling terakhir diratakan tiga kali untuk mengubah gambar berbentuk matriks menjadi tiga dimensi. Setelah itu, terhubung sepenuhnya. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan preprocessing dataset seperti resizing dan RGB to grayscale. Kemudian dataset diklasifikasikan dengan arsitektur AlexNet CNN. Setelah itu dilakukan evaluasi model, dan terakhir adalah hasil klasifikasi citra kupu-kupu.Hasil klasifikasi diperoleh akurasi sebesar 80% dengan resize 100x100, 82% dengan resize 150x150, dan 82% dengan resize 200x200. Tahap terakhir adalah citra dapat diklasifikasikan. Proses pengujian menggunakan arsitektur AlexNet diawali dengan input dataset citra, dilakukan pre","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"17 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140462054","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 : 2024-02-04DOI: 10.20895/infotel.v16i1.984
Prabowo Adi Perwira, Nelly Indriani Widiastuti
Sentiment analysis was commonly used to determine the polarity of the review text. However, there is a problem if some reviews have more than one aspect with different polarities, so the reviews have more than one polarity. That has happened in some reviews on the game Genshin Impact. Not merely that, the number of sentiments contained in a review is not always the same as other reviews will cause imbalanced data. So, this study will handle imbalance data with Random Under-Sampling and Random Over-Sampling on aspect-based-sentiment-analysis of Genshin Impact Review with Multinomial Naïve-Bayes, so that the classification prediction does not ignore the minority class due to the dominance of the majority class. The classification process used K-Fold Cross Validation (k=10) validation method and the Laplace smoothing technique on Multinomial Naïve Bayes. As a result, the conclusion is that Random Oversampling had better accuracy than Random Undersampling in handling imbalanced data on aspect-based sentiment analysis of Genshin Impact game Review in Indonesian with Naïve Bayes Multinomial, with the highest accuracy of 85.55%.
{"title":"Imbalance Dataset in Aspect-Based Sentiment Analysis on Game Genshin Impact Review","authors":"Prabowo Adi Perwira, Nelly Indriani Widiastuti","doi":"10.20895/infotel.v16i1.984","DOIUrl":"https://doi.org/10.20895/infotel.v16i1.984","url":null,"abstract":"Sentiment analysis was commonly used to determine the polarity of the review text. However, there is a problem if some reviews have more than one aspect with different polarities, so the reviews have more than one polarity. That has happened in some reviews on the game Genshin Impact. Not merely that, the number of sentiments contained in a review is not always the same as other reviews will cause imbalanced data. So, this study will handle imbalance data with Random Under-Sampling and Random Over-Sampling on aspect-based-sentiment-analysis of Genshin Impact Review with Multinomial Naïve-Bayes, so that the classification prediction does not ignore the minority class due to the dominance of the majority class. The classification process used K-Fold Cross Validation (k=10) validation method and the Laplace smoothing technique on Multinomial Naïve Bayes. As a result, the conclusion is that Random Oversampling had better accuracy than Random Undersampling in handling imbalanced data on aspect-based sentiment analysis of Genshin Impact game Review in Indonesian with Naïve Bayes Multinomial, with the highest accuracy of 85.55%.","PeriodicalId":30672,"journal":{"name":"Jurnal Infotel","volume":"24 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140461924","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：