Pub Date : 2024-07-01DOI: 10.21107/kursor.v12i3.376
Jasman Pardede, Fandi Ahmad
Image captioning is a task in image processing that involves creating text descriptions that can describe the image content. The formation of the image captioning system model is influenced by image interpretation related to the given image caption. Image interpretation is influenced by the feature extraction used. This research proposes feature extraction with Xception and Inception-V3 by generating an image captioning model using Transformer. Model performance is measured based on BLUE and METEOR values. Based on the results of research conducted on the Flickr8k Dataset, it shows that the best model performance is using Xception feature extraction and batch_size = 256. The image captioning performance of Xception feature extraction for BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR when compared with Inception-V3 achieves increasing of 13.15%, 18.03%, 18.71%, 27.27%, and 15.43% respectively. The performance for Xception feature extraction with batch_size = 256 compared with batch_size = 128, increasing BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR namely 19.81%, 41.84%, 52.23%, 53.14%, and 31.56% respectively.
{"title":"IMAGE CAPTIONING USING TRANSFORMER WITH IMAGE FEATURE EXTRACTION BY XCEPTION AND INCEPTION-V3","authors":"Jasman Pardede, Fandi Ahmad","doi":"10.21107/kursor.v12i3.376","DOIUrl":"https://doi.org/10.21107/kursor.v12i3.376","url":null,"abstract":"Image captioning is a task in image processing that involves creating text descriptions that can describe the image content. The formation of the image captioning system model is influenced by image interpretation related to the given image caption. Image interpretation is influenced by the feature extraction used. This research proposes feature extraction with Xception and Inception-V3 by generating an image captioning model using Transformer. Model performance is measured based on BLUE and METEOR values. Based on the results of research conducted on the Flickr8k Dataset, it shows that the best model performance is using Xception feature extraction and batch_size = 256. The image captioning performance of Xception feature extraction for BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR when compared with Inception-V3 achieves increasing of 13.15%, 18.03%, 18.71%, 27.27%, and 15.43% respectively. The performance for Xception feature extraction with batch_size = 256 compared with batch_size = 128, increasing BLUE-1, BLUE-2, BLUE-3, BLUE-4, and METEOR namely 19.81%, 41.84%, 52.23%, 53.14%, and 31.56% respectively.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"7 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141704263","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 : 2023-12-10DOI: 10.21107/kursor.v12i2.348
Ismit Mado, Achmad Budiman, Aris Triwiyatno
Electrical power requirements at load centers tend to change over time, so the State Electricity Company (PLN) as a provider of electrical energy must be able to predict electrical load requirements every day. The city of Tarakan as a reference center in the northern region of Indonesia is developing rapidly. Along with this growth, the need for electric power is of course also increasing, so we must be able to provide an economical and reliable electric power supply system. This research aims to predict the electricity load at PT. PLN (Persero) Tarakan City. The author will carry out short-term forecasting using time series data in the form of daily electrical power usage data using the Autoregressive Integrated Moving Average (ARIMA) method. The ARIMA method or often called the Box-Jenkins technique shows that this method is suitable for predicting a number of variables quickly, simply and cheaply because it only requires variable data to be predicted. Analysis based on the Box-Jenkins time series taking into account the influence of seasonal patterns. The prediction results show that the data contains seasonal elements with the best model being SARIMA with a MAPE of 3 percent.
{"title":"SHORT-TERM FORECASTING DAILY ELECTRICITY LOADS USING SEASONAL ARIMA PATTERNS OF GENERATION UNITS AT PT. PLN (PERSERO) TARAKAN CITY","authors":"Ismit Mado, Achmad Budiman, Aris Triwiyatno","doi":"10.21107/kursor.v12i2.348","DOIUrl":"https://doi.org/10.21107/kursor.v12i2.348","url":null,"abstract":"Electrical power requirements at load centers tend to change over time, so the State Electricity Company (PLN) as a provider of electrical energy must be able to predict electrical load requirements every day. The city of Tarakan as a reference center in the northern region of Indonesia is developing rapidly. Along with this growth, the need for electric power is of course also increasing, so we must be able to provide an economical and reliable electric power supply system. This research aims to predict the electricity load at PT. PLN (Persero) Tarakan City. The author will carry out short-term forecasting using time series data in the form of daily electrical power usage data using the Autoregressive Integrated Moving Average (ARIMA) method. The ARIMA method or often called the Box-Jenkins technique shows that this method is suitable for predicting a number of variables quickly, simply and cheaply because it only requires variable data to be predicted. Analysis based on the Box-Jenkins time series taking into account the influence of seasonal patterns. The prediction results show that the data contains seasonal elements with the best model being SARIMA with a MAPE of 3 percent.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"21 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184418","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 : 2023-12-10DOI: 10.21107/kursor.v12i2.347
A. G. Sooai, S. D. B. Mau, Yovinia Carmeneja Hoar Siki, D. J. Manehat, Shine Crossifixio Sianturi, Alicia Herlin Mondolang
As an invasive and poisonous plant, Lantana has become a pest in the agricultural world. Still, on the other hand, it becomes an ornamental plant with different positive potentials. Lantana flower datasets are not yet widely available for open image classification research, given that the research needs are still broad in remote sensing. This study aims to provide a model with classifier accuracy that outperforms similar studies and Lantana datasets for classification needs using several algorithms that can be run on small source computers. This study used five types of lantana colors, red, white, yellow, purple, and orange, as the primary dataset, which had 411 instances. VGG16 assisted feature extraction in preparing datasets for the data training using three classifiers: decision tree, AdaBoost, and k-NN. 2-fold cross-validation, 5-fold cross-validation, and a self-organizing map are used to help validate each process. The experiment to measure the classifier's performance resulted in a good figure of 99.8% accuracy for 2-fold cross-validation, 100% for 5-fold cross-validation, and a primary dataset of lantana interest that can be accessed freely on the IEEE Data port. This study outperformed other related studies in terms of classifier accuracy.
{"title":"OPTIMIZING LANTANA CLASSIFICATION: HIGH-ACCURACY MODEL UTILIZING FEATURE EXTRACTION","authors":"A. G. Sooai, S. D. B. Mau, Yovinia Carmeneja Hoar Siki, D. J. Manehat, Shine Crossifixio Sianturi, Alicia Herlin Mondolang","doi":"10.21107/kursor.v12i2.347","DOIUrl":"https://doi.org/10.21107/kursor.v12i2.347","url":null,"abstract":"As an invasive and poisonous plant, Lantana has become a pest in the agricultural world. Still, on the other hand, it becomes an ornamental plant with different positive potentials. Lantana flower datasets are not yet widely available for open image classification research, given that the research needs are still broad in remote sensing. This study aims to provide a model with classifier accuracy that outperforms similar studies and Lantana datasets for classification needs using several algorithms that can be run on small source computers. This study used five types of lantana colors, red, white, yellow, purple, and orange, as the primary dataset, which had 411 instances. VGG16 assisted feature extraction in preparing datasets for the data training using three classifiers: decision tree, AdaBoost, and k-NN. 2-fold cross-validation, 5-fold cross-validation, and a self-organizing map are used to help validate each process. The experiment to measure the classifier's performance resulted in a good figure of 99.8% accuracy for 2-fold cross-validation, 100% for 5-fold cross-validation, and a primary dataset of lantana interest that can be accessed freely on the IEEE Data port. This study outperformed other related studies in terms of classifier accuracy.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"43 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184462","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 : 2023-12-10DOI: 10.21107/kursor.v12i2.343
Dwi Fitria Al Husaeni, Eka Fitrajaya Rahman, Erna Piantari
This study aims to evaluate the effectiveness of using and developing problem-based learning multimedia with find and sort QR code games to improve students' computational thinking (CT) skills in learning object-oriented programming using a web-based digital platform. The Research and Development (R&D) method and One-Group Pretest-Posttest design was used in this study. The subjects of this study were 35 students of SMK Negeri 1 Cimahi, Indonesia. There are three stages in conducting research 1) analysis of problems, 2) learning multimedia development, and 3) evaluation. The findings show there is an increase in students' CT skills after implementing the find and sort QR Code Game problem-based learning multimedia during the learning process. Student learning outcomes have increased from 45.71 (pretest) to 89.50 (posttest). The average increase in student learning outcomes occurred significantly based on the results of the t-test. In addition, the students' CT average score increased from 65.43 (pretest) to 85.29 (posttest). The order of increasing the CT component based on the n-gain value is 1) abstraction (0.66); 2) pattern recognition (0.63); 3) decomposition (0.48); and 4) algorithm design (0.39). Student responses to multimedia learning in this study were obtained very well with a score of 84.95%.
本研究旨在评估使用和开发基于问题的学习多媒体与查找和分类二维码游戏的效果，以提高学生在使用基于网络的数字平台学习面向对象程序设计时的计算思维（CT）技能。本研究采用了研究与开发（R&D）方法和单组前测后测设计。研究对象是印度尼西亚SMK Negeri 1 Cimahi的35名学生。研究分为三个阶段：1）问题分析；2）学习多媒体开发；3）评估。研究结果表明，在学习过程中实施查找和分类 QR 码游戏问题式学习多媒体后，学生的 CT 技能有所提高。学生的学习成绩从 45.71（前测）提高到 89.50（后测）。根据 t 检验结果，学生的平均学习成绩有了显著提高。此外，学生的 CT 平均分从 65.43（前测）提高到 85.29（后测）。根据 n 增益值，CT 部分的增加顺序为：1）抽象（0.66）；2）模式识别（0.63）；3）分解（0.48）；4）算法设计（0.39）。在本研究中，学生对多媒体学习的反应非常好，得分率为 84.95%。
{"title":"IMPLEMENTATION OF PROBLEM-BASED LEARNING MULTIMEDIA WITH FIND AND SORT QR CODE GAMES TO IMPROVE STUDENT'S COMPUTATIONAL THINKING SKILLS","authors":"Dwi Fitria Al Husaeni, Eka Fitrajaya Rahman, Erna Piantari","doi":"10.21107/kursor.v12i2.343","DOIUrl":"https://doi.org/10.21107/kursor.v12i2.343","url":null,"abstract":"This study aims to evaluate the effectiveness of using and developing problem-based learning multimedia with find and sort QR code games to improve students' computational thinking (CT) skills in learning object-oriented programming using a web-based digital platform. The Research and Development (R&D) method and One-Group Pretest-Posttest design was used in this study. The subjects of this study were 35 students of SMK Negeri 1 Cimahi, Indonesia. There are three stages in conducting research 1) analysis of problems, 2) learning multimedia development, and 3) evaluation. The findings show there is an increase in students' CT skills after implementing the find and sort QR Code Game problem-based learning multimedia during the learning process. Student learning outcomes have increased from 45.71 (pretest) to 89.50 (posttest). The average increase in student learning outcomes occurred significantly based on the results of the t-test. In addition, the students' CT average score increased from 65.43 (pretest) to 85.29 (posttest). The order of increasing the CT component based on the n-gain value is 1) abstraction (0.66); 2) pattern recognition (0.63); 3) decomposition (0.48); and 4) algorithm design (0.39). Student responses to multimedia learning in this study were obtained very well with a score of 84.95%.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"18 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184517","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 : 2023-12-10DOI: 10.21107/kursor.v12i2.351
Galih Restu Baihaqi, Mulaab
The reason fishermen lose control is wave height and wind speed. The impact is also felt by all users of the marine sector. This research uses the Long Short Term Memory (LSTM) method because this method has accurate values in the forecasting process with a lot of historical data and uses the Prophet method to detect outliers with Newton interpolation to replace the detected outlier data. The total number of data was 2074 obtained from BMKG Perak Surabaya from January 2020 to November 2022 at four research points, namely north, northeast, east and south points. The test results provide varying error values with MAPE as the model evaluation value. The error value for sea wave height at the north, northeast, east and south points is 13.32 respectively; 13.32; 9.32 and 8.85 with data without interpolation. Meanwhile, the error value in the wind speed data is 14.74; 14.85; 15.14 and 14.52 with a 3rd order Newton interpolation process at the northeast and east points. MAPE values below 20% prove that the LSTM model is good for predicting wave height and wind speed data at four points in Sumenep Regency. The system implementation is made into a web-based application.
{"title":"LONG SHORT-TERM MEMORY FOR PREDICTION OF WAVE HEIGHT AND WIND SPEED USING PROPHET FOR OUTLIERS","authors":"Galih Restu Baihaqi, Mulaab","doi":"10.21107/kursor.v12i2.351","DOIUrl":"https://doi.org/10.21107/kursor.v12i2.351","url":null,"abstract":"The reason fishermen lose control is wave height and wind speed. The impact is also felt by all users of the marine sector. This research uses the Long Short Term Memory (LSTM) method because this method has accurate values in the forecasting process with a lot of historical data and uses the Prophet method to detect outliers with Newton interpolation to replace the detected outlier data. The total number of data was 2074 obtained from BMKG Perak Surabaya from January 2020 to November 2022 at four research points, namely north, northeast, east and south points. The test results provide varying error values with MAPE as the model evaluation value. The error value for sea wave height at the north, northeast, east and south points is 13.32 respectively; 13.32; 9.32 and 8.85 with data without interpolation. Meanwhile, the error value in the wind speed data is 14.74; 14.85; 15.14 and 14.52 with a 3rd order Newton interpolation process at the northeast and east points. MAPE values below 20% prove that the LSTM model is good for predicting wave height and wind speed data at four points in Sumenep Regency. The system implementation is made into a web-based application.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"28 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184389","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 : 2023-12-10DOI: 10.21107/kursor.v12i2.349
Fawaidul Badri, M. Taqijuddin Alawiy, Eko Mulyanto Yuniarno
In current technological developments, Deep Learning is one of the most popular studies today, especially in the fields of machine learning and computer vision, GPU Acceration Technology is one of the reasons for the development of Deep Learning. Deep Learning has a very good ability to solve classic problems in the field of computer vision, one of which is in the case of object classification in images. one of the deep learning methods that is often used in image processing is the Convolution Neural Network (CNN) which is a development of the Multi Layer Perceptron method. This study uses the CNN architecture which consists of a convolution layer, as well as a fully connected layer, and will also determine the appropriate Optimizer and Loss function for CNN. The implementation of this method uses Google Colab (Tensorflow and Keras) with the Python programming language. In the training process using CNN, setting the number of epochs is done to improve accuracy in image classification, in the first scenario using epoch 20 produces an average accuracy of 99.45 with a loss value of 1.66. In the second scenario using epoch 15 produces an average accuracy value of 99.00 with a loss value of 2.92. then in the third scenario with a number of epochs 10 it produces an average accuracy value of 95.55 with a loss value of 95.55, while in the last scenario with a number of epochs 5 it produces an average accuracy value of 73.6 with a loss value of 51.92. From the 4 trial scenarios using the CNN method gives effective results and produces a fairly good accuracy value with an average accuracy and loss value of 99.99%. As well as the results of an average loss of 4.
{"title":"DEEP LEARNING ARCHITECTURE BASED ON CONVOLUTIONAL NEURAL NETWORK (CNN) IN IMAGE CLASSIFICATION","authors":"Fawaidul Badri, M. Taqijuddin Alawiy, Eko Mulyanto Yuniarno","doi":"10.21107/kursor.v12i2.349","DOIUrl":"https://doi.org/10.21107/kursor.v12i2.349","url":null,"abstract":"In current technological developments, Deep Learning is one of the most popular studies today, especially in the fields of machine learning and computer vision, GPU Acceration Technology is one of the reasons for the development of Deep Learning. Deep Learning has a very good ability to solve classic problems in the field of computer vision, one of which is in the case of object classification in images. one of the deep learning methods that is often used in image processing is the Convolution Neural Network (CNN) which is a development of the Multi Layer Perceptron method. This study uses the CNN architecture which consists of a convolution layer, as well as a fully connected layer, and will also determine the appropriate Optimizer and Loss function for CNN. The implementation of this method uses Google Colab (Tensorflow and Keras) with the Python programming language. In the training process using CNN, setting the number of epochs is done to improve accuracy in image classification, in the first scenario using epoch 20 produces an average accuracy of 99.45 with a loss value of 1.66. In the second scenario using epoch 15 produces an average accuracy value of 99.00 with a loss value of 2.92. then in the third scenario with a number of epochs 10 it produces an average accuracy value of 95.55 with a loss value of 95.55, while in the last scenario with a number of epochs 5 it produces an average accuracy value of 73.6 with a loss value of 51.92. From the 4 trial scenarios using the CNN method gives effective results and produces a fairly good accuracy value with an average accuracy and loss value of 99.99%. As well as the results of an average loss of 4.","PeriodicalId":504317,"journal":{"name":"Jurnal Ilmiah Kursor","volume":"42 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139184368","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：