JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
An insight into the Application of AI in maritime and Logistics toward Sustainable Transportation
Get PDFThis review article looks at the developing field of artificial intelligence and machine learning in maritime and marine environment management. The marine industry is increasingly interested in applying advanced AI and ML technologies to solve sustainability, efficiency, and regulatory compliance issues. This paper examines maritime and marine AI and ML applications using a deep literature review and case study analysis. Modeling ship fuel consumption, which impacts the environment and operating expenses, is a top responsibility. The study demonstrates that ML approaches such as Random Forest and Tweedie models can estimate ship fuel use. Statistical analysis demonstrates that the Random Forest model beats the Tweedie model regarding accuracy and consistency. For the training and testing datasets, the Random Forest model has high R2 values of 0.9997 and 0.9926, indicating a solid match. Low Root Mean Square Error (RMSE) and average absolute relative deviation (AARD) suggest that the model accurately reflects fuel use variability. While still performing well, the Tweedie model has lower R2 values and higher RMSE and AARD values, suggesting reduced accuracy and precision in fuel consumption prediction. These findings provide light on the potential applications of artificial intelligence and machine learning in maritime and marine environment management. Advanced analytics enables decision-makers to analyze fuel consumption patterns better, increase operational efficiency, and decrease environmental impact, thus improving maritime sustainability
A Comparative Analysis of Combination of CNN-Based Models with Ensemble Learning on Imbalanced Data
Get PDFThis study investigates the usefulness of the Synthetic Minority Oversampling Technique (SMOTE) in conjunction with convolutional neural network (CNN) models, which include both single and ensemble classifiers. The objective of this research is to handle the difficulty of multi-class imbalanced image classification. The application of SMOTE in imbalanced picture datasets is still underexplored, even though CNNs have been shown to be successful in image classification and that ensemble learning approaches have improved their performance. To investigate whether or not SMOTE can increase classification accuracy and other performance measures when combined with CNN-based classifiers, our research makes use of a CIFAR-10 dataset that has been artificially step-imbalanced and has varying imbalanced ratios. We conducted experiments using five distinct models, namely AdaBoost, XGBoost, standalone CNN, CNN-AdaBoost, and CNN-XGBoost, on datasets that were either imbalanced or SMOTE-balanced. Metrics such as accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC) were included in the evaluation process. The findings indicate that SMOTE dramatically improves the accuracy of minority classes, and that the combination of ensemble classifiers with CNNs and oversampling techniques significantly improves overall classification performance, particularly in situations when there is a high-class imbalance. When it comes to enhancing imbalanced classification tasks, this study demonstrates the potential of merging oversampling techniques with CNN-based ensemble classifiers to minimize the impacts of class imbalance in picture datasets. This suggests a promising direction for future research in this area
Creation of Cultural Local Wisdom-Based Picture-Science Stories Application for the Introduction of Scientific Literacy for Early Childhood
Get PDFThis article aims to explain the design, development, implementation, and evaluation of the Picture Science Story (CSB) application integrated with local wisdom based on an Android application for early childhood. This application can be used with a touch screen. The aim of making this application is to introduce the science process skills and local wisdom to the children. The research method used was R and D. The initial stage of developing the CSB prototype model was to conduct the needs analysis, child characteristics, and curriculum analysis. Then, the design, development, implementation, and evaluation of the CSB application were carried out. The application used a layered platform. Many experts from different fields were involved in the design process: graphic design experts to create images, multimedia experts to create applications, and teachers for the science material. The CSB prototype design was validated by material, media, and user experts, namely Al-Huffaz Kindergarten teachers and children. The participants in this research were 13 Alhufazh Kindergarten students. A questionnaire was given to get a response from the teachers, consisting of aspects of understanding multimedia, function, and configuration. The average score of the teachers’ responses was 92%. Meanwhile, the average score of children's responses was 95%. Based on the results of validation and trials, it was found that the CSB application integrated with local wisdom based on an Android application was valid, effective, and practical for early childhood. The suggestions from users require multidisciplinary knowledge in designing picture-science stories based on Android applications. Then, the feedback addressed the importance of using the Science Story Creation prototype and integration of the Local Wisdom of Minangkabau Culture to introduce Early Childhood Science Literacy
A Convolutional Neural Network-based Intelligence System for the Identification of Copra Maturity Levels
Get PDFThe North Sulawesi Province, widely recognized as the Coconut Waving Province owing to its substantial coconut tree population, primarily depends on copra production. This research presents a novel methodology for determining copra maturity levels by utilizing a Convolutional Neural Network (CNN) on digital photographs, classifying them into three distinct stages: raw, half-ripe, and ripe. By employing a rigorous 10-fold cross-validation technique, our models demonstrated remarkable performance. Notably, even the model with the lowest performance achieved a commendable accuracy of 87.78% during the training and validation phases. The model that exhibited the highest level of performance achieved a perfect accuracy rate of 100%. Moreover, when subjected to real-world testing situations using novel data, the model with the lowest performance exhibited a noteworthy accuracy of 83.34%. In contrast, the highest-performing model achieved a flawless accuracy of 100%. Based on the findings above, an online system has been built that leverages the most optimal model, facilitating the assessment of copra maturity in real-time. The prospects encompass the integration of this methodology into copra sorting machinery, thereby yielding advantages for both agricultural producers and industrial sectors. This research enhances copra quality control processes and promotes sustainability in the copra industry. Further research could explore refining the CNN model to accommodate a broader range of copra variations and investigating automation possibilities in copra production processes. These endeavors would advance the efficacy and applicability of copra maturity classification methods, fostering continued innovation in the industry
Modified Alexnet Architecture for Classification of Cassava Based on Leaf Images
Get PDFThe objective of this study is to address the drawbacks of conventional classification approaches through the implementation of deep learning, specifically a modified AlexNet. The primary aim of this study is to precisely categorize the four distinct varieties of cassava, namely Manggu, Gajah, Beracun, and Kapok. The cassava dataset was obtained from farmers in Lamongan, Indonesia, and was used as a source of information. Data collection on cassava leaves was carried out with agricultural research specialists. A total of 1,400 images are included in the dataset, with 350 images corresponding to each variety of cassava produced. The central focus of this research lies in a comprehensive evaluation of the modified AlexNet architecture's performance compared to the original AlexNet architecture for cassava classification. Multiple scenarios were examined, involving diverse combinations of learning rates and epochs, to thoroughly assess the robustness and adaptability of the proposed approach. Among the evaluation criteria that were rigorously examined were accuracy, recall, F1 score, and precision. These metrics were used to determine the predictive capabilities of the model as well as its potential utilization in the actual world. The results show that the modified AlexNet design has better performance than the original AlexNet for recall, accuracy, precision, and F-1 score, all achieving a rate of 87%. In situations where a learning rate of 0.0001 and an epoch count of 150 are utilized, the performance of the approach stands out significantly, displaying an excellent level of competency. Nevertheless, it is crucial to recognize that distinct fluctuations in performance were noted within particular contexts and with diverse learning rates
Lightweight Image Encryption Based on A Hybrid Approach
Get PDFA secure image could be achieved by encryption, a technique for securing images over different media transmission lines with privacy and keeping them safe for the receiver. This paper proposes an image encryption approach to achieve excellent security by combining a lightweight encryption algorithm with the chaotic Peter De Jong map. The Lilliput algorithm, lightweight encryption, uses the Peter De-Jones map to produce keys. The suggested approach achieved a suitable level of complexity that matched the historical demands for transmission images. Two methods were used to conduct the tests on a standard image collection: an encrypted image and a generated key. Standard metrics find the similarity between the input and output images to achieve an accurate proposal performance. The encrypted image's entropy was assessed and discovered that it matched the original image values exactly. The results were satisfactory regarding obtaining a precise correlation rate between the original and encrypted photos. The decryption and reconstruction of the image were completed quickly and steadily, with a high success rate and excellent outcomes. The proposed approach was evaluated on a dataset of well-known test photos with unique features, including varying degrees of lightness and shade to create the perfect test
Performance Comparison of GLCM Features and Preprocessing Effect on Batik Image Retrieval
Get PDFThe use of the Grey-Level Co-occurrence Matrix (GLCM) for feature extraction in image retrieval with complex motifs, such as batik images, has been widely used. Some features often extracted include energy, entropy, correlation, and contrast. Other than these four features, the addition of dissimilarity and homogeneity features to the GLCM method is proposed in this study. Preprocessing methods such as Histogram Equalization (HE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are also used to see whether the two methods can increase the precision value of the retrieval results. This study used the Batik 300 dataset, which consists of 50 classes. Batik was chosen because this type of image has complex patterns and motifs so that it will maximize the role of the GLCM method itself. In addition, Batik is also a world heritage art, so its sustainability needs to be maintained. The test results show that adding dissimilarity and homogeneity features and using the CLAHE method in the preprocessing step can improve model performance. Combining these two methods has produced higher precision values than not using either. Batik, a globally recognized art form, holds the status of a world heritage, necessitating the preservation of its sustainability. Test results have demonstrated that incorporating dissimilarity and homogeneity features, alongside using the CLAHE method during the preprocessing stage, leads to enhanced model performance. The amalgamation of these two methods has yielded precision values that surpass those achieved when either method is used in isolation
Comparative Analysis of the Implementation of Technology Trends, Pedagogy Trends and Education Trends of Science and Non-Science Program Students in Sulawesi
No full textAs a result of their increased exposure to technology, today's students are skilled users of a wide range of digital gadgets in their daily lives. To solve difficulties, they can freely access knowledge across a variety of digital platforms; this ability has to be included into contemporary learning principles. The purpose of this study is to investigate how lecturers might modify innovative teaching methods to better suit the needs of their students. 125 people participated in the survey that we did; 59 of them were from scientific programs and 66 were from non-science programs. The study used observation sheets, interview guides, and questionnaires. The questionnaire was split into two sections: one measured students' opinion of the technology and pedagogical innovations used by lecturers, and the other their reactions to the classroom and educational system. Before any data was collected, the validity and reliability of the instruments were confirmed. The findings showed that students had preferences for different types of technology. Students in scientific programs liked interactive platforms like Edmodo and Google Classroom, while students in other programs liked webinars and video conferences. Additionally, the study found a relationship between the educational trends that lecturers apply, pedagogical innovation, and the learning environment. The results of this study are anticipated to improve instructional practices in digital learning settings and provide a basis for policymaking in continuing education.
Network Attack Detection Using NeuroEvolution of Augmenting Topologies (NEAT) Algorithm
Get PDFThe imperfection of existing intrusion detection methods and the changing nature of malicious actions on the attacker's part led to the Internet of Things (IoT) network interaction in an unsafe state. The actual problem of improving the technology of the IOT is counteracting malicious network impacts. In this regard, research and development aimed at creating effective tools for solving applied problems within the framework of this problem are becoming increasingly important. This study seeks to develop tools for detecting anomalous network conditions resulting from malicious attacks. In particular, the accuracy of the identification of DoS and DDoS attacks is sufficient for operational use. This study analyzes various multi-level architectures, relevant communication protocols, and different types of network attacks. The presented research was conducted on open datasets TON_IOT DATASETS, which include multiple data sources collected from IoT sensors. The modified HyperNEAT algorithm was used as the basis for the development. The NEAT methodology used in the study allows you to combine various network nodes. Results of the study: a neuro-evolutionary algorithm for identifying DoS and DDoS attacks was implemented, integrated, and real-tested based on a multi-level analysis of network traffic combined with various adaptive modules. The accuracy of identifying DoS and DDoS attacks is 0.9242 in the Accuracy metric. The study implies that the proposed approach can be recommended for network intrusion detection, ensuring security when interacting with the IoT
Rainfall-Runoff Modeling Using Artificial Neural Network for Batu Pahat River Basin
Get PDFThis research delves into the effectiveness of Artificial Neural Networks with Multilayer Perceptron (ANN-MLP) and Nonlinear AutoRegressive with eXogenous inputs (NARX) models in predicting short-term rainfall-runoff patterns in the Batu Pahat River Basin. This study aims to predict river water levels using historical rainfall and river level data for future intervals of 1, 3, and 6 hours. Data preprocessing techniques, including the management of missing values, identification of outliers, and reduction of noise, were applied to enhance the accuracy and dependability of the models. This study assessed the performance of the models for ANN-MLP and NARX by comparing their effectiveness across various forecast timeframes and evaluating their performance in different scenarios. The findings of the study revealed that the ANN-MLP model showed robust performance in short-term prediction. On the contrary, the NARX model exhibited higher accuracy, particularly in capturing intricate temporal relationships and external impacts on river behavior. The ANN-MLP produces 99% accuracy for 1-hour prediction, and NARX yields 98% accuracy with 0.3245 Root Mean Squared Error and 0.1967 Mean Absolute Error. This study makes a valuable contribution to hydrological forecasting by presenting a rigorous and precise modeling methodology