Jurnal Online Informatika
Not a member yet
276 research outputs found
Sort by
Comparison of EfficientNetB0 and EfficientNetB7 Models in Classifying Malaria Based on Blood Cells
Full text linkMalaria is a disease caused by the bite of malaria mosquitoes, which spreads through blood. Malaria mosquitoes will spread the Plasmodium parasite through their bites. Early malaria identification is essential so the disease can be prevented immediately. Through data science, which utilizes the CNN model, the classification of blood infected with parasites can be predicted accurately. This research uses data obtained from Kaggle website with 27,558 image samples. The data is divided into two classes, parasite-infected and uninfected, which are then divided again into two types. The first class is training data divided into 80% of the total data and the other 20% as validation data. This research used two test scenarios to obtain a more effective classification model. The first scenario uses Hyperparameter Tuning and the EfficientNetB0 model with classification results of 95%. Meanwhile, the classification achievement for scenario two was 99% by utilizing EfficientNetB7
Evaluating Readiness and Acceptance of Artificial Intelligence Adoption Among Elementary School Teachers
Full text linkArtificial Intelligence (AI) is a computer system that mimics the human brain\u27s ability to process information and make decisions. AI technology is used to learn patterns in data and make predictions or decisions based on that learning. Despite the potential benefits of AI in education, elementary school teachers face significant challenges in adopting AI technology due to limited training, lack of resources, and resistance to change. This research aims to identify the factors influencing the adoption of AI technology among primary school teachers in West Java, Indonesia. The study involved 384 participants and employed a quantitative approach. Specific factors influencing AI adoption were identified by developing a model for AI-based teaching and learning and assessing readiness factors. The results identified optimism, innovativeness, insecurity, discomfort, perceived validity, trust, usefulness, and ease of use as critical factors for successful AI adoption among primary school teachers in West Java. The customized adoption model provides a practical roadmap for integrating AI into teaching and learning processes, addressing regional specificities while remaining relevant to similar educational challenges worldwide. The assessment of readiness factors offers actionable insights for fostering a supportive environment for technology integration. The study concludes with recommendations for future research and implications for educators, administrators, and policymakers
Machine Learning Monitoring Model for Fertilization and Irrigation to Support Sustainable Cassava Production: Systematic Literature Review
Full text linkThe manual and time-consuming nature of current agronomic technology monitoring of fertilizer and irrigation requirements, the possibility of overusing fertilizer and water, the size of cassava plantations, and the scarcity of human resources are among its drawbacks. Efforts to increase the yield of cassava plants > 40 tons per ha include monitoring fertilization approach or treatment, as well as water stress or drought using UAVs and deep learning. The novel aspect of this research is the creation of a monitoring model for the irrigation and fertilizer to support sustainable cassava production. This study emphasizes the use of Unnamed Aerial Vehicle (UAV) imagery for evaluating the irrigation and fertilization status of cassava crops. The UAV is processed by building an orthomosaic, labeling, extracting features, and Convolutional Neural Network (CNN) modeling. The outcomes are then analyzed to determine the requirements for air pressure and fertilization. Important new information on the application of UAV technology, multispectral imaging, thermal imaging, among the vegetation indices are the Soil-Adjusted Vegetation Index (SAVI), Leaf Color Index (LCI), Leaf Area Index (LAI), Normalized Difference Water Index (NDWI), Normalized Difference Red Edge Index (NDRE), and Green Normalized Difference Vegetation Index (GNDVI)
Identification of Inpari HDB 32 Superior Rice Seeds based on Android in Realtime with Artificial Neural Network
Full text linkRice is a staple food for humans living in East Asia. Rice is a crystal fruit. The Latin name for rice is Oryza Sativa. Rice plants are 110-120 days old. The selection of quality rice seeds by farmers is seen from the bright yellow color of the rice without black/brown spots, its large size and rounder. Rice seeds that are not of good quality are dark brown in color, have black/brown spots, and are flat in shape. The absence of superior rice recognition technology that is not Android-based in real time is the main reason for this research. The focus of this research is to identify superior and non-superior rice in Inpari HDB 32 rice with a high recognition accuracy rate of more than 70 percent with a viewing angle of 0-180 degrees using the real-time ANN method. The training data used in this research was 1000 datasets consisting of 350 superior rice datasets and 650 non-superior datasets. The smart model for classifying rice seeds that has been built in this research is generally able to run well where the classification accuracy obtained is quite good. The classification accuracy of the ANN model during training of the neural network model was able to classify rice seeds with an accuracy of 70-100% with the confidence value of the real-time classification results ranging from 65-98%. Real-time classification of rice grains with maximum accuracy of 96% and many grains 73%
A Comparison of Ryu and Pox Controllers: A Parallel Implementation
Full text linkSoftware Defined Network (SDN) network controllers have limitations in handling large volumes of data generated by switches, which can slow down their performance. Using parallel programming methods such as threading, multiprocessing, and MPI aims to improve the performance of the controller in handling a large number of switches. By considering factors such as memory usage, CPU consumption, and execution time. The test results show that although RYU outperforms POX in terms of faster execution time and lower CPU utilization rate, POX shows its prowess by exhibiting less memory usage despite higher CPU utilization rate than RYU. The use of the parallel approach proves advantageous as both controllers exhibit enhanced efficiency levels. Ultimately, RYU\u27s impressive speed and superior resource optimization capabilities may prove to be more strategic than POX over time. Taking into account the specific needs and prerequisites of a given system, this research provides insights in selecting the most suitable controller to handle large-scale switches with optimal efficiency
Realizing the Promise of Artificial Intelligence in Hepatocellular Carcinoma through Opportunities and Recommendations for Responsible Translation
Full text linkThis study aims to provide an overview of the current state-of-the-art applications of artificial intelligence (AI) and machine learning in the management of hepatocellular carcinoma (HCC), and to explore future directions for continued progress in this emerging field. This study is a comprehensive literature review that synthesizes recent findings and advancements in the application of AI and machine learning techniques across various aspects of HCC care, including screening and early detection, diagnosis and staging, prognostic modeling, treatment planning, interventional guidance, and monitoring of treatment response. The review draws upon a wide range of published research studies, focusing on the integration of AI and machine learning with diverse data sources, such as medical imaging, clinical data, genomics, and other multimodal information. The results demonstrate that AI-based systems have shown promise in improving the accuracy and efficiency of HCC screening, diagnosis, and tumor characterization compared to traditional methods. Machine learning models integrating clinical, imaging, and genomic data have outperformed conventional staging systems in predicting survival and recurrence risk. AI-based recommendation systems have the potential to optimize personalized therapy selection, while augmented reality techniques can guide interventional procedures in real-time. Moreover, longitudinal application of AI may enhance the assessment of treatment response and recurrence monitoring. Despite these promising findings, the review highlights the need for rigorous multicenter prospective validation studies, standardized multimodal datasets, and thoughtful consideration of ethical implications before widespread clinical implementation of AI technologies in HCC management
AI-Powered Real-time Accessibility Enhancement: A Solution for Web Content Accessibility Issues
Full text linkThe web accessibility landscape is a significant challenge, with 96.3% of home pages displaying issues with Web Content Accessibility Guidelines (WCAG). This paper addresses the primary accessibility issues, such as missing Accessible Rich Internet Applications (ARIA) landmarks, ill-formed headings, low contrast text, and inadequate form labeling. The dynamic nature of modern web and cloud applications presents challenges, such as developers\u27 limited awareness of accessibility implications, potential code bugs, and API failures. To address these issues, an AI-enabled system is proposed to dynamically enhance web accessibility. The system uses machine learning algorithms to identify and rectify accessibility issues in real-time, integrating with existing development workflows. Empirical evaluation and case studies demonstrate the efficacy of this solution in improving web accessibility across diverse scenarios
Wave Downscaling Approach with TCN model, Case Study in Bengkulu, Indonesia
Full text linkWhen conducting marine operations that rely on wave conditions, such as maritime trade, the fishing industry, and ocean energy, accurate wave downscaling is important, especially in coastal locations with complicated geometries. Traditional approaches for wave downscaling are usually obtained by performing nested simulations on a high-resolution local grid from global grid information. However, this approach requires high computation resources. In this paper, to downscale global wave height data into a high-resolution local wave height with less computation resources, we propose a machine learning-based approach to downscaling using the Temporal Convolutional Network (TCN) model. To train the model, we obtain the wave dataset using the SWAN model in a local domain. The global datasets are taken from the ECMWF Reanalysis (ERA-5) and used to train the model. We choose the coastal area of Bengkulu, Indonesia, as a case study. The results of TCN are also compared with other models such as LSTM and Transformers. It showed that TCN demonstrated superior performance with a CC of 0.984, RMSE of 0.077, and MAPE of 4.638, outperforming the other models in terms of accuracy and computational efficiency. It proves that our TCN model can be alternative model to downscale in Bengkulu’s coastal area
Analysis of Data and Feature Processing on Stroke Prediction using Wide Range Machine Learning Model
Full text linkStroke is a disease which cause the death of brain cells, so that the part of the body controlled by the brain loses its function. If not treated immediately, this disease can cause long-term disability, brain damage, and death. In this research, stroke prediction was carried out on the Stroke dataset acquired from the Kaggle dataset using various machine learning models. Then, data sampling techniques are used to handle data imbalance problems in the stroke dataset, which include Random Undersampling, Random Oversampling, and SMOTE techniques. Pearson Correlation and Principal Component Analysis are also used for dimensional reduction and analyzing the important features that are most influential in predicting stroke. Pearson Correlation produces five attributes that have the highest Pearson coefficient, namely age, hypertension, heart disease, blood sugar level, and marital status. Experimental results have demonstrated that the utilization of RUS, ROS, and SMOTE sampling techniques can significantly boost the F1-Score testing by an impressive 43.44%, 34.44%, and 35.55% respectively, as compared to experiments conducted without implementing any data sampling techniques. The highest F1-Score testing was achieved using the Support Vector Machine and Gaussian Naïve Bayes models, namely 0.83
Data Balancing Techniques Using the PCA-KMeans and ADASYN for Possible Stroke Disease Cases
Full text linkImbalanced data happens when the distribution of classes is not equal between positive and negative classes. In healthcare, the majority class typically consists of healthy patient data, while the minority class contains sick patient data. This condition can cause the minority class prediction to be wrong because the model tends to predict the majority class. In this study, we use a deep neural network algorithm with focal loss that can deal with class imbalance during training. To balance the data, we use the PCA-KMeans combination model to shrink the dataset and the ADASYN model to give the minority class more samples than it needs. In this study, the research problem is how well the two techniques can improve model performance, especially in minority case classification. The mild model is the best without data balancing, resulting in an accuracy value of 84%. The class 0 F1-score has a value of 86%, whereas the class 1 F1-score has a value of 82%. The moderate model is the best model in the case study of PCA-KMeans balancing data, resulting in an accuracy value of 89%; the class 0 F1-score is 91%; and the class 1 F1-score is 85%. The extreme model is the best model in the ADASYN data balancing case study, resulting in an accuracy value of 95%; the value in class 0 gets a F1-score of 96%, while the value in class 1 gets a F1-score of 96%. Of the three test models, the best model is obtained using ADASYN extreme data balancing with an accuracy value of 95%, the value in class 0 with a F1- score of 93%