Jurnal Online Informatika
Not a member yet
276 research outputs found
Sort by
Developing an AI-Enhanced Enterprise Architecture Model for Strategic Decision-Making in Malaysiaโs Railway Industry
Full text linkMost developing nations, including Malaysia, still lack a model for the decision-making process that is comprehensive enough to account for a wide variety of potential effects and failures. The implementation of this investigation is crucial for Enterprise Architecture (EA) parameters for Railway Industry (RI) supplier performance that emphasize strategic decision-making processes to help the organizations become more competitive. In response to this need, the research integrates Artificial Intelligence (AI) as an enabler within the EA model to support intelligent and data-driven decision-making. This research has implemented a strategic decision-making process in the RI context and conducted it from a developing country perspective. The study identifies several elements of the decision-making process faced and experienced by the RI and the potential gaps for further observations in adopting the EA model. As a result, a fresh conceptual model enhanced with AI-driven analytics and intelligent decision support was created and assessed. By fulfilling the aims of the study, this research makes important contributions to the RI in terms of the use of EA, aligned with the worldwide standard of the four fundamental EA criteria, and explores the transformative potential of AI integration to accelerate EA adoption. The study\u27s findings will impact both theory and practice, providing a pathway for developing nations to harness AI for strategic advantage and digital maturity
Enchancing Lung Disease Classification through K-Means Clustering, Chan-Vese Segmentation, and Canny Edge Detection on X-Ray Segmented Images
Full text linkThe lungs are one of the vital organs in the human body. Not only play a role in the respiratory system, the lungs are also responsible for the human circulatory system. Supporting examinations can also facilitate medical workers in determining the diagnosis. Usually a lung examination is complemented by a chest X-ray examination procedure. This examination aims to see directly and assess the severity of lung conditions. With current technological advances, image analysis can be done easily. Through digital image processing methods, information can be obtained from images that can be used for analysis as a support for diagnoses in the world of health. Image segmentation is a method in which digital images are divided into several segments or subgroups based on the characteristics of the pixels in the image. In this study, clustering with the K-Means method will be carried out on the results of segmentation of x-ray images of lung diseases, namely Covid-19, Tuberculosis, and Pneumonia. The segmentation method that will be implemented is the Chan-Vese Method and the Canny Edge Detection Method. This research shows that the results of the accuracy of applying the K-Means Clustering method to Chan-Vese and Canny Edge-Based Image Segmentation are 80%
Deep Learning Based LSTM Model for Predicting the Number of Passengers for Public Transport Bus Operators
Full text linkThe bus public transportation system has low reliability and ability to predict the number of passengers. The accuracy of predicting the number of passengers by public transport bus operators is still weak, which results in failure to implement solutions by operators. A prediction model with LSTM based on deep learning is proposed to predict passengers for 4 bus public transportation operators (Go Bus, New Zealand Bus, Pavlovich, and Ritchies) which are evaluated by MSLE, MAPE, and SMAPE with variations in epoch, batch size, and neurons. The dataset is a CSV performance report on Auckland Transport (AT) New Zealand metro patronage buses (01/01/2019-07/31/2023). The best prediction model was obtained from the lowest evaluation value and relatively fast time at variations of epoch 60, batch size 16, and neurons 32. The prediction results on training and testing data improved with the suitability of the model tuning. The proposed prediction model performs predictions 12 months later for 4 predictions simultaneously with predicted fluctuations occurring simultaneously. Strong negative correlation on New Zealand Bus-Pavlovich, strong positive correlation on Go Bus with Ritchies and Pavlovich. Predictions that are less closely related and dependent are New Zealand Bus against Go Bus, Pavlovich, and Ritchies. The proposed prediction modeling can be used as a basis for creating operator policies and strategies to deal with passenger fluctuations and for the development of new prediction models
SAER : Comparison of Rule Prediction Algorithms on Constructing a Corpus for Taxation Related Tweet Aspect-Based Sentiment Analysis
Full text linkTwitter is a popular social media in Indonesia, and sentiment analysis on Twitter has an important role in measuring public trust, especially in taxation issues. Aspect extraction is an important task in sentiment analysis. In this research, we propose SAER, a Syntactic Aspect-opinion Extraction and Rule prediction, that used language rule-based approach using syntactic features for aspect and opinion extraction, and we compare several algorithm for rule prediction such as Random Forest Regression, Decision Tree Regression, K-Nearest Neighbor Regression (KNN), Linear Regression, Support Vector Regression (SVR), and Extreme Gradient Boosting Regression (XGBoost) that can generate rules with a tree-based approach. By employing syntactic features and rule prediction, it has been able to explore important features in a sentence. In rule prediction, comparison results show that Support Vector Regression (SVR) was identified as the most effective model for aspects rule prediction, providing the best results with a Mean Squared Error (MSE) of 0.022, Root Mean Squared Error (RMSE) of 0.150, and Mean Absolute Error (MAE) of 0.123. While XGBoost was identified as the most effective model for opinions rule prediction, with MSE of 0.013, RMSE of 0.117, and MAE of 0.075. Since we used syntactic feature-based approaches and rule prediction in this work, it is expected to be implemented for other cases, with other domain datasets
Water Level Time Series Forecasting Using TCN Study Case in Surabaya
Full text linkClimate change is causing water levels to rise, leading to detrimental effects like tidal flooding in coastal areas. Surabaya, the capital of East Java Province in Indonesia, is particularly vulnerable due to its low-lying location. According to the Meteorological, Climatological, and Geophysical Agency (BMKG), tidal flooding occurs annually in Surabaya as a result of rising water levels, highlighting the urgent need for water level forecasting models to mitigate these impacts. In this study, we employ the Temporal Convolutional Network (TCN) machine learning model for water level forecasting using data from a sea level station monitoring facility in Surabaya. We divided the training data into three scenarios: 3, 6, and 8 months to train TCN models for 14-day forecasts. The 8-month training scenario yielded the best results. Subsequently, we used the 8-month training data to forecast 1, 3, 7, and 14 days using TCN, Transformers, and the Recurrent Neural Network (RNN) models. TCN consistently outperformed other models, particularly excelling in 1-day forecasting with coefficient of determination () and RMSE values of 0.9950 and 0.0487, respectively
CatBoost Optimization Using Recursive Feature Elimination
Full text linkCatBoost is a powerful machine learning algorithm capable of classification and regression application. There are many studies focusing on its application but are still lacking on how to enhance its performance, especially when using RFE as a feature selection. This study examines the CatBoost optimization for regression tasks by using Recursive Feature Elimination (RFE) for feature selection in combination with several regression algorithm. Furthermore, an Isolation Forest algorithm is employed at preprocessing to identify and eliminate outliers from the dataset. The experiment is conducted by comparing the CatBoost regression model\u27s performances with and without the use of RFE feature selection. The outcomes of the experiments indicate that CatBoost with RFE, which selects features using Random Forests, performs better than the baseline model without feature selection. CatBoost-RFE outperformed the baseline with notable gains of over 48.6% in training time, 8.2% in RMSE score, and 1.3% in R2 score. Furthermore, compared to AdaBoost, Gradient Boosting, XGBoost, and artificial neural networks (ANN), it demonstrated better prediction accuracy. The CatBoost improvement has a substantial implication for predicting the exhaust temperature in a coal-fired power plant
Development of a Mobile-Based Application for Classifying Caladium Plants Using the CNN Algorithm
Full text linkCaladium is a popular ornamental plant and has business potential. However, difficulties in recognizing the type of Caladium often occur because of the similarities in shape, pattern, and color of the leaves between the different kinds of Caladium. To overcome this problem, research will use machine learning with the Convolutional Neural Network (CNN) algorithm to build a mobile application that can accurately classify four types of Caladiums. The data set used is 1200 data with four classes; each class has 300 data. The best model is found with the parameter epoch 100, learning rate 0.001, and batch size 64. The model is then implemented in a mobile application with two menus, "Take a photo" and "Choose an image," which will display the classification output and confidence values of the four types of Caladiums. Testing with 30 test data per class achieves 0.975 accuracy on both menus. On the โTake a photoโ menu, precision is 0.974, recall is 0.9725, and f1-score is 0.965. Meanwhile, on the โChoose an imageโ menu a precision and recall value is 0.975, and f1-score value of 0.97
Cassava Diseases Classification using EfficientNet Model with Imbalance Data Handling
Full text linkThis research highlights the urgent need for classifying cassava diseases into five classes, such as Cassava Bacterial Blight (CBB), Cassava Brown Streak Disease (CBSD), Cassava Green Mottle (CGM), and Cassava Mosaic Disease (CMD), and Healthy. The study proposes the utilization of the EfficientNet model, a lightweight deep learning architecture, for classifying cassava diseases based on leaf images. However, the datasets available for this classification task are all unbalanced, made it difficult for researchers to perform. To tackle this imbalance issue, the authors compared several imbalance data handling methods commonly used for image classification, including SMOTE (Synthetic Minority Oversampling Technique), basic augmentation, and neural style transfer, to be applied before fed into EfficientNet. Initially, EfficientNet model without addressing dataset imbalances, the F1-Score stands at 78%, with most images misclassified into the majority class. Integration with SMOTE notably boosts the F1-Score to 82%, showcasing the efficacy of oversampling methods in enhancing model performance. Conversely, employing data augmentation, both basic and deep learning-based, lowers the F1-Score to 74% and 65% respectively, yet it results in a more balanced distribution of true positives across disease classes. The findings suggest that SMOTE surpasses the other methods in handling imbalanced data
Predictive Performance Evaluation of ARIMA and Hybrid ARIMA-LSTM Models for Particulate Matter Concentration
Full text linkThis study provides an objective evaluation of prediction performance models for particulate matter policy for industrial stakeholders by comparing the ARIMA and Hybrid ARIMA-LSTM models for predicting air quality data from the industrial environment. In the case of PM 1.0 concentration, we have an RMSE value of 8.29 and an error ratio of 0.45 for the ARIMA model and an RMSE value of 3.54 and an error ratio of 0.22 for the hybrid ARIMA-LSTM model. Meanwhile, for PM 2.5 concentration, we obtain an RMSE value of 6.61, an error ratio of 0.66 for the ARIMA model, an RMSE value of 2.68, and an error ratio of 0.19 for the hybrid ARIMA-LSTM model. According to this study, the ARIMA model, which is found in autoarima and represents the best model, is (2,0,1) for PM1.0 and (1,0,1) for PM2.5. The hybrid ARIMA-LSTM model outperforms the ARIMA model in terms of prediction accuracy, as evidenced by the RMSE and error ratio values, which are improved by approximately 57.30% and 51.11% for PM1.0 and 59.46% and 71.21% for PM2.5, respectively, since the hybrid ARIMA-LSTM model can accommodate variable-length sequences and capture long-term relationships to become noise-resistant, which makes higher prediction accuracy possible
Strengthening the Authentication Mechanism of Blockchain-Based E-Voting System Using Post-Quantum Cryptography
Full text linkElection systems often face severe challenges regarding security and trust. Threats such as vote falsification and lack of transparency in vote counting have shaken the integrity of elections in various countries. The use of blockchain technology in e-voting has been proposed as an attractive solution to overcome this problem. Several studies use blockchain for the security of electronic voting systems. The existing methods are not resistant against impersonation attacks and man-in-the-middle attacks. This research proposes a new scheme to strengthen a blockchain-based e-voting system. The blockchain used in the proposed method is Ethereum. The proposed scheme uses the modified framework and The Goldreich-Goldwasser-Halevi (GGH) signature scheme. Digital signatures generated using Goldreich-Goldwasser-Halevi (GGH) can strengthen the identity of the message sender so that enemies cannot imitate someone. In this research, the Voter\u27s public key and anonymous ID are used by the Voter to maintain the Voter\u27s anonymity. Based on the experimental results, it can be concluded that the proposed scheme is stronger than the previous scheme because the probability of success in impersonating the sender with the proposed scheme using an impersonation attack and man-in-the-middle attack is small