JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
IoT Attack Detection using Machine Learning and Deep Learning in Smart Home
Get PDFThe Internet of Things (IoT) has revolutionized the traditional Internet, pushing past its former boundaries by implementing smart linked gadgets. The IoT is steadily becoming a staple of everyday life, having been implemented into various diverse applications, such as cities, smart homes, and transportation. However, despite the technological advancements that the IoT brings, various new security risks have also been introduced due to the development of new types of attacks. This prevents current intelligent IoT applications from adaptively learning from other intelligent IoT applications, which leaves them in a volatile state. In this paper, we conducted a structured literature review (SLR) on Smart Home's IoT attack detection using machine learning and deep learning. Four journal databases were used to perform this review: IEEE, Science Direct, Association for Computing Machinery (ACM), and SpringerLink. Sixty articles were selected and studied, where we noted the various patterns and techniques present in the framework of the selected research. We also took note of the different machine learning and deep learning methods, the types of attacks, and the Network layers present in Smart Home. By conducting an SLR, we analyzed the numerous techniques of IoT attack detection for smart homes proposed by various theoretical studies. We enhanced the studied literature by proposing a new solution for better IoT attack detection in smart homes
Enhanced U-Net Architecture for Glottis Segmentation with VGG-16
Get PDFLaryngeal endoscopic image analysis with segmentation techniques has great potential in detecting various diseases in the glottic area, which is essential for early diagnosis and proper treatment. This study proposes developing the U-Net architecture by integrating the VGG-16 model, aiming to improve the accuracy in detecting glottic areas. VGG-16 is applied to the encoder and bridge sections so that the model can take advantage of previously learned knowledge. This modification is expected to improve segmentation performance compared to standard U-Net, especially in handling variations in laryngeal image complexity. The dataset used consisted of 1,200 images taken randomly from the BAGLS website, a collection of laryngeal endoscopic image data rich in variation. The training results show that the standard U-Net produces an accuracy of 0.9995, IoU 0.6744, and DSC 0.7814. The improved U-Net showed a significant performance improvement, with an accuracy of 0.9998, an IoU of 0.8223, and a DSC of 0.9153. This improvement confirms that modifying the U-Net architecture using VGG-16 provides superior results in detecting glottic areas precisely. VGG-16 also helps model performance in overcoming the problem of smaller datasets. In addition, both models were tested using relevant evaluation metrics, and the test results showed that the improved U-Net consistently outperformed other CNN-based segmentation methods. These advantages show that the proposed approach improves accuracy and contributes significantly to developing glottic disease detection methods through laryngeal endoscopic image analysis, which can ultimately support clinical practice in detecting abnormalities in glottis more effectively
Identification Critical Success Factors of Geographic Information System Development in Indonesia with AHP Approach
No full textAn Indonesian government agency in the field of research is developing a Geographic Information System (GIS) to distribute remote sensing data to customers. To prevent project failure, it is crucial to understand the success criteria related to project objectives and the critical success factors (CSFs), which drive project success. This research identifies these CSFs, enabling organizations to prioritize project success factors. The Analytic Hierarchy Process (AHP) ranks project success criteria and CSFs. The mixed research methodology incorporates qualitative elements through discussions with the project manager to validate the AHP hierarchy structure and quantitative aspects through questionnaires used to calculate weighted priorities using AHP. Results show stakeholder satisfaction and objective achievement as the top-ranked success criteria. The top 5 CSFs identified are team commitment and participation, clear roles and responsibilities, leadership, knowledge management, appropriate tools, infrastructure, and resources. Based on the success criteria ranking, development should enhance system functionality to maintain user satisfaction and achieve project objectives. Meanwhile, prioritizing human resources and providing adequate resources are crucial based on the identified top 5 CSFs, contributing to increased development success. This outcome aims to assist firms in improving project management and identifying the most critical success elements for GIS development. Furthermore, this research will likely be a learning experience for other government organizations seeking to enhance their information system development efforts
Automatic Cell Planning Method for Radio Network Optimization
Get PDFAs the first step in building a wireless communication network, wireless network optimization is crucial since it determines how the network will be built scientifically. Numerous challenges remain in the way of the Radio Network's deployment in Indonesia, not the least of which is the still-uneven coverage region. The Kiaracondong region in Bandung is one of the numerous areas in Indonesia that are still considered to be "bad spot areas" as a result. Based on the findings of the driving test conducted in the Kiaracondong sub-district, the KPI target was not fulfilled for the RSRP, SINR, and Throughput parameters. Therefore, this study primarily focuses on the physical tuning optimization using the Automatic Cell Planning (ACP) method for the LTE wireless network optimization. To assess the quality of the LTE network before and after optimization, the results of the ACP optimization simulation will be compared with the results of the existing or non-ACP site simulation and the results of the operator's ACP implementation. As a result, Area 1 has an average RSRP of -72.79 dBm, area 2 -73.17 dBm, and area 3 -68.22 dBm. Additionally, the average SINR in areas 1,2 and 3 is 8 dB, 6.58 dB, and 8.17 dB, respectively. The average downlink throughput in area 1 is 42652.66 Kbps, area 2 is 34420.88 Kbps, and area 3 is 43882.92 Kbps. Finally, the average throughput uplink for areas 1 to 3 is 51651.24 Kbps, 47895.99 Kbps, and 49648.84 Kbps, respectively
Enhancing Weather Prediction Models through the Application of Random Forest Method and Chi-Square Feature Selection
Get PDFThis study discovers weather forecast methodologies, concentrating mainly on the climatic issues faced by Indramayu Regency and its considerable impact on agriculture, specifically rice production and national food security. The study emphasizes the crucial need for accurate weather forecasting, especially in the context of ongoing climate change, by highlighting the region's vulnerability to weather anomalies and their possible disruption of crop output. To solve these issues, the study investigates machine learning techniques, particularly ensemble learning methods such as Random Forest in conjunction with Chi-Square feature selection. The article thoroughly outlines the research approach, including data collection from Indonesia's Meteorology, Climatology, and Geophysics Agency (BMKG), data pre-processing, feature selection processes, and data splitting. Notably, the methodology integrates the Synthetic Minority Over-sampling Technique (SMOTE) to adjust imbalanced data and uses key weather attributes for model construction (humidity, wind speed, and direction). The resulting Random Forest model performs well, with an accuracy rate of 87.6% in forecasting different types of rainfall. However, the study indicates potential overfitting in some rainfall classes, implying the need for additional data augmentation or modeling technique refining. In conclusion, this study demonstrates the potential efficacy of ensemble learning techniques in weather prediction, focusing on the Indramayu Regency. It emphasizes the need for exact forecasts in the agricultural and fisheries industries and suggests possibilities for additional investigation, such as research into alternative prediction approaches such as deep learning
The Rewardable Persuasive Model: A Mobile Exergame Conceptual Design Model that Facilitates Youths to Exercise through Mobile Gaming
Get PDFThis study seeks to assess current design models to propose a conceptual design model for a mobile exergame that promotes physical activity among youths. Encouraging youths to engage in physical activity rather than remaining sedentary is essential due to the numerous health benefits associated with regular exercise. Exercise is a subset of physical activity structured for fitness. Exergames have the potential to inspire youths to be active by combining exercise and gaming engagingly and enjoyably. The proliferation of mobile gaming has further broadened the availability and accessibility of exergames. In this study, we conducted four stages of information gathering to assess and propose a mobile exergame conceptual design model: a literature review, a user survey, expert reviews, and in-depth user interviews. Based on the study's findings, we identified appropriate components and their rationale by adapting an existing design model to our conceptual design model for a mobile exergame. This conceptual design model is called the Rewardable Persuasive Model (RPM). This model aims to help youths achieve their weekly physical activity targets using an engaging and functional mobile application (app). The app incentivizes exercise by integrating it as a key element for unlocking gameplay. With the introduction of these components, an exergame can be designed to engage youths and facilitate physical activity effectively. In a future study, youths will use an app to assess the RPM's effectiveness over time. This assessment will ascertain its appropriateness for facilitating exercise during inactivity
Students' Behavior in the Learning Process Using Zoom Meeting Media: Problems and Solutions
Get PDFRecent digital technologies have increased the flexibility of learning. Online learning is now seen as a good alternative, not a force anymore. Among all online learning media that can aid, Zoom is an interactive online learning media mainly used by lecturers to carry out synchronous learning processes when offline lectures cannot be carried out. Using Zoom, lecturers and students can interact synchronously, like face-to-face learning in class. Many studies have been conducted to see the impacts of online learning on students’ learning behaviors using various media, yet studies on how students behave while learning using Zoom have not yet been explored in more detail. This research aims to reveal how students behave in the learning process by using Zoom in English classes through a survey study. Data were collected through a questionnaire delivered online to some 142 English Department students of Universitas Negeri Padang who experienced online learning. They voluntarily took part in this survey. Carrying quantitative analysis, the research showed that most students did not follow the Zoom-mediated learning process as well as they did face-to-face learning, which was carried out offline, for various reasons. Several positive and negative behaviors were found when implementing the learning process using Zoom. Therefore, for the learning process to run well, it is necessary to agree on the ethics of the learning process by using Zoom. The findings of this research can provide a reference for making conventional ethics of online learning using Zoom or other media
Enhancing Land Management through U-Net Deep Learning: A Case Study on Climate-Related Land Degradation in Berembun Forest Reserve in Malaysia
Get PDFIn the face of accelerating climate change, effective management of land resources needs innovative technological approaches. This study, conducted in the Berembun Forest Reserve, Jelebu, Malaysia, leverages advancements in geospatial technology and machine learning to address the pressing issue of land degradation, focusing on forested areas vulnerable to landslides. Utilizing high-resolution Unmanned Aerial Vehicle (UAV) imagery, the U-Net convolutional neural network model is employed for the precise classification and early detection of landslide-induced land degradation. Through a systematic analysis of 15 high-quality UAV images of 5472 x 3647 pixels, segmented into 256 x 256-pixel patches, the U-Net model demonstrated remarkable accuracy, achieving a mean Intersection-over-Union (IoU) of 0.9466. These findings underscore the model's potential to significantly enhance land management practices by providing timely and cost-effective landslide detection. Adopting such deep learning techniques is a pivotal shift towards more sustainable and resilient land management strategies in the era of climate change. This research showcases the practical application of machine learning in environmental monitoring and paves the way for future innovations. Implications for further research include integrating additional spectral bands, addressing environmental variability, and expanding applications across diverse landscapes to improve environmental monitoring, conservation efforts, and resilience strategies. Developing automated frameworks for real-time data processing and model deployment could further revolutionize the field, enabling more responsive and efficient land management practices
Solution for Public Smart Dispenser Using Digital Payment Based on the Fingerprint Minutiae Algorithm
Get PDFTechnological advancements have significantly focused on secure and efficient digital payments. In the context of Public Smart Dispensers (PSDs), using authentication and verification in payment transactions is crucial to address security concerns, enhance transaction efficiency, and provide a better user experience. This study employs minutiae algorithms for the fingerprint identification and verification process. Fingerprint identification utilizes the crossing number method, while fingerprint verification uses a validation score. If the validation score exceeds the threshold of >80, fingerprint verification is considered successful; conversely, verification is deemed unsuccessful if the validation score is <80. Through testing, biometrics as a payment method was conducted 100 times, resulting in an accuracy rate of 94% with an identification response time of approximately two or three seconds. The research findings demonstrate the practicality of implementing fingerprint biometric payment methods with minutiae algorithms on Public Smart Dispenser payment systems in the field of digital payments and technology. This enables fast and efficient transactions, significantly reducing the risk of fund misuse. Consequently, users can easily access water through Public Smart Dispensers, underscoring the real-world applicability and relevance of this solution. Implementing this technology can enhance user comfort and security while expediting the transaction process, which is crucial for public use. Therefore, this research makes a significant contribution to the advancement of fingerprint-based payment technology on public smart dispensers
Identification of Indonesian Traditional Foods Using Machine Learning and Supported by Segmentation Methods
Get PDFTraditional food is essential in preserving cultural heritage and is a vital part of Indonesian cuisine. In this research, we implement a methodology to identify the traditional Indonesian food using machine learning algorithms supported by various segmentation methods. This research aims to provide an efficient and accurate approach to classifying traditional foods, which can contribute to promoting and preserving Indonesia's culinary heritage. To conduct this research, we conducted experiments on 34 types of conventional Indonesian food originating from various provinces in Indonesia. The analysis of food images involved several segmentation algorithms, including Sobel, Prewitt, Robert, Scharr, and Canny filters. After the segmentation process, we proceeded with feature extraction and classification using traditional machine learning algorithms such as the Random Forest algorithm, Decision Tree, and derivatives of the SVM algorithm. These algorithms aimed to recognize the 34 types of traditional food. After conducting several experiments, we found that Random Forest with Robert's segmentation method was the highest-performance algorithm. It produced extraordinarily accurate results on the test dataset, with an accuracy performance of 85.52%, recall of 84.63%, precision of 83.77%, and an f1 score of 82.49%. Additionally, the best-performing algorithms with execution time averaged less than 1 minute. Another experimental result showed that the Random Forest algorithm with the Canny operator achieved an accuracy of 81.51%, recall of 84.97%, precision of 86.8%, and an f1 score of 85.61% on the test dataset. Furthermore, the Random Forest algorithm with the Sobel operator achieved accuracy results of 78.4%, recall of 65.3%, precision of 62.3%, and an f1 score of 63.71%. In the SVM algorithms derivative, the Sigmoid SVM combined with the Scharr operator achieved the highest performance in its category across all classification metrics. In conclusion, this research offers valuable insights into classifying traditional Indonesian dishes using traditional machine learning algorithms. Simultaneously, this research aims to promote the appropriate and effective preservation and recognition of traditional Indonesian food