JOIV : International Journal on Informatics Visualization
Not a member yet
786 research outputs found
Sort by
A Comprehensive Review of Cyber Hygiene Practices in the Workplace for Enhanced Digital Security
Full text linkIn today's digital age, cybercrime is increasing at an alarming rate, and it has become more critical than ever for organizations to prioritize adopting best practices in cyber hygiene to safeguard their personnel and resources from cyberattacks. As personal hygiene keeps one clean and healthy, cyber hygiene combines behaviors to enhance data privacy. This paper aims to explore the common cyber-attacks currently faced by organizations and how the different practices associated with good cyber hygiene can be used to mitigate those attacks. This paper also emphasizes the need for organizations to adopt good cyber hygiene techniques and, therefore, provides the top 10 effective cyber hygiene measures for organizations seeking to enhance their cybersecurity posture. To better evaluate the cyber hygiene techniques, a systematic literature approach was used, assessing the different models of cyber hygiene, thus distinguishing between good and bad cyber hygiene techniques and what are the cyber-attacks associated with bad cyber hygiene that can eventually affect any organization. Based on the case study and surveys done by the researchers, it has been deduced that good cyber hygiene techniques bring positive behavior among employees, thus contributing to a more secure organization. More importantly, it is the responsibility of both the organization and the employees to practice good cyber hygiene techniques. Suppose organizations fail to enforce good cyber hygiene techniques, such as a lack of security awareness programs. In that case, employees may have the misconception that it is not their responsibility to contribute to their security and that of the organization, which consequently opens doors to various cyber-attacks. There have not been many research papers on cyber hygiene, particularly when it comes to its application in the workplace, which is a fundamental aspect of our everyday life. This paper focuses on the cyber hygiene techniques that any small to larger organization should consider. It also highlights the existing challenges associated with the implementation of good cyber hygiene techniques and offers potential solutions to address them
An Improved Hybrid GRU and CNN Models for News Text Classification
Full text link Due to the continuous growth and advancement of technology, an enormous volume of text data is generated daily across various sources including social media platforms, websites, search engines, healthcare records, and news articles. Extracting meaningful patterns from text data, such as viewpoints, related theories, journal distribution, facts, and the development of online news text, is a challenging task due to the varying lengths of the texts. One issue arises from the length of the text data itself, and another challenge lies in extracting valuable features, especially in news articles. In the deep learning models, the convolutional neural networks (CNNs) are capable of capturing local features in text data, but unable to capture the structural information or semantic relationships between words. Consequently, a sole CNN network often yields poor performance in text classification tasks, whereas the Gated Recurrent Unit (GRU) is adept at effectively extracting semantic information and understanding the global structural relationships present in textual data. This paper presents a solution to the problem by introducing a new text classification that integrates the strengths of CNN and GRU. The proposed hybrid models incorporate word vectorization and word dispersion in parallel. Initially, the model trains word vectors using the Word2vec model and then leverages the GRU model to capture semantic information from text sentences. Subsequently, the CNN method is employed to capture crucial semantic features, leading to classification using the SoftMax layer. Experimental findings demonstrated that the proposed hybrid GRU_CNN model outperformed and achieved accuracy 97.73% as compared to individual CNN, LSTM, and GRU models in terms of classification effectiveness and accuracy
Security System for Door Locks Using YOLO-Based Face Recognition
Full text linkDi era kemajuan teknologi dan algoritma canggih yang memudahkan hidup manusia, kunci pintar pengenalan wajah merupakan sistem yang menggunakan salah satu algoritma tersebut dan mengatasi masalah keamanan dalam teknologi rumah pintar. Kunci pintar ini dapat dipasang di dekat pintu untuk memantau rumah, perusahaan, dan universitas. Masalah dengan solusi kunci pintar pengenalan wajah saat ini adalah bahwa kunci pintar tersebut kurang cepat dan tepat. Pintu merupakan salah satu komponen bangunan yang perlu diperhatikan keamanannya untuk mencegah upaya pencurian. Bangunan yang memiliki banyak ruang harus memiliki pintu dengan sistem keamanan yang kuat, salah satunya adalah hotel. Alat yang sering digunakan untuk mengakses kamar hotel adalah RFID. Mobil RFID memiliki banyak kekurangan, antara lain tamu sering meninggalkan kartu RFID mereka di kamar sehingga mereka tidak dapat lagi memasuki kamar dan harus melapor ke resepsionis terlebih dahulu, kartu RFID juga mudah hilang sehingga tamu yang kehilangan kartu RFID akan didenda sebagai biaya penggantian kartu. Oleh karena itu, dibuatlah sistem keamanan pintu menggunakan pengenalan wajah dengan algoritma YOLO. Algoritma YOLO digunakan untuk mendeteksi wajah siapa saja yang ingin mengakses pintu. Hasil pengujiannya adalah sistem dapat mendeteksi wajah dengan tingkat akurasi 94,4%
Design and Development of a System for Monitoring Student Attention and Concentration during Learning using CNN Model and Face Landmark Detection
Full text linkMobile learning media has been wide and provides a tendency for lecturers to identify students' concentration levels in online classes. To bring the class into active learning, efforts are needed from lecturers and educational institutions to return students' concentration to the ongoing learning process. In this paper, a monitoring and alarm system is designed to increase student concentration and combines two elements of statistical analysis to validate CNN models that recognize face emotions in real time while learning. The research was carried out by recording face data using a camera, extracting digital features, and analyzing facial features. The results of the analysis are used as data input for the decision-making system regarding the level of concentration. The concentration level will be used to activate alarms and send them via chat so that students can focus on learning.The system is created by merging facial expression recognition (FER) and decision-making with a convolutional neural network. The system using a face landmark via camera V2 and a Raspberry Pi 4 performed with the Haar-Cascade classifier, extracting facial features. Face detection via camera is performed using the Haar-Cascade classifier, which extracts facial features. The results of CNN model face detection with landmark features showed good results, with weighted average performance of precision, recall, and F1-score close to 0.99. According to the implementation results, the average number of facial expressions identified in drowsy and neutral states. The device can alert lecturers to how frequently drowsy detects students within a 10-minute interval
Automatic Feature Extraction of Marble Fleck in Digital Beef Images to Support Decision Preferences
Full text linkBeef is one of the essential food ingredients to meet human nutritional needs. These nutrients are fundamental to the growth and development of the human body. The primary nutrient found in beef is protein. The nutritional value of protein in beef can be observed by the quality of the beef itself. An indicator of the protein level is the amount of marbling or white streaks in the meat. Marbling is characterized by a marble-like pattern in the meat layers. This study aims to process beef images to automatically identify marbling. The data processed is secondary data obtained from Kaggle.com, consisting of 60 images with a resolution of 800 by 800 pixels. This study develops a highly subjective method to produce fast and accurate classification. The processing stages used are pre-processing, segmentation, and extraction. The automatic stage is in the extraction, by developing a filtering algorithm. The results of this study can identify the marbling fleck ratio of each beef image very well, where each beef image has marbling flecks. The area of marbling flecks varies greatly depending on the quality of the meat, with the lowest quality having a ratio of 1.0% and the highest being 71.39%. This ratio level becomes an indicator in determining the quality of the meat, which is the primary preference in making accurate decisions in selecting meat quality. Thus, this study can serve as an indicator in determining the appropriate meat preference choice
Comparison of Classification Algorithms in Bamboo Distribution Mapping for Identification of Industrial Supporting Raw Materials
Full text linkThis study aims to address the challenges in the widespread supply of bamboo raw materials and the lack of coordination between bamboo-producing regions, as well as to conduct a comprehensive inventory and mapping of bamboo resources. In addition, this study also explores the factors that influence the distribution and growth characteristics of bamboo, such as soil type, altitude, and rainfall. The main problems faced in the bamboo industry are the uneven distribution of raw materials and the lack of coordination between regions, which hinder the development of a strong and sustainable bamboo industry value chain. The lack of in-depth information on the ecological factors that influence bamboo growth also exacerbates this situation. The method used in this study involves mapping bamboo potential through aerial photography data collection, which is then analyzed using machine learning technology. The three algorithms used in the classification process are K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest. The study was conducted in an area rich in bamboo vegetation, especially Bojongmangu District in Bekasi, West Java, Indonesia. From the analysis results, the SVM algorithm showed the best performance with a classification accuracy ranging from 80% to 90%. These results indicate that this method is very effective in mapping bamboo vegetation areas with high precision. This study also identified other variables, such as soil type and altitude, that play a role in bamboo distribution. With this more holistic approach, the study is expected to provide deeper insights into bamboo ecology and improve sustainable bamboo resource management
Comparative Analysis of Homomorphic and Morphological Filters Using Inception V3 for Thermal Facial Image Classification of Autistic Children
Full text linkAutism Spectrum Disorder (ASD) is a neuro-developmental disorder characterized by varying degrees of difficulty in social interaction and communication and repetitive behaviors. Early confirmation of the diagnosis of ASD leads to early appropriate treatment. However, confirming ASD diagnosis is challenging due to its wide spectrum and challenging behavior assessment. This research proposes a technology-based ASD diagnosis on children utilizing thermal facial analysis. This is conducted subject to the uniqueness of facial expression that is typically applied to children with ASD. A modified Inception V3 architecture did the intended thermal facial analysis for ASD diagnosis. Homomorphic filters and morphological filters are applied to the data pre-processing to improve the classification ability. The proposed identification method shows better sensitivity to the false-positive aspect. It is indicated by better performance in terms of precision, with a rate of 90% to 91%. This research is expected to support medical experts in confirming early diagnosis in children with ASD
Enhanced BatikGAN SL Model for High-Quality Batik Pattern Generation
Full text linkBatik represents one of the most prominent traditional cultural forms in Indonesia, serving not only as an art form but also as a symbol of cultural identity and heritage. The creation of intricate and unique Batik patterns is a highly skilled craft that has been passed down through generations. Still, modern efforts to innovate and enhance Batik designs face significant challenges. Specifically, there is a growing demand for high-quality Batik patterns that maintain the aesthetic and cultural value of traditional motifs while incorporating modern design elements. This study aims to address these challenges by introducing an enhanced BatikGAN SL model that leverages local features. The model's performance was rigorously evaluated using the Batik Nitik dataset, which consists of 126 Batik motifs collected from artisans in Yogyakarta, a region renowned for its rich Batik traditions. This dataset allowed for a robust testing ground, representing a diverse array of motifs and styles. In comparative evaluations, the enhanced BatikGAN SL model outperformed not only its predecessor but also models utilizing histogram-equalized datasets, which are often employed to improve image contrast. Key metrics, including the Fréchet Inception Distance (FID) score of 20.087, Peak Signal-to-Noise Ratio (PSNR) of 25.665, and Structural Similarity Index Measure (SSIM) of 0.918, demonstrated significant improvements in both the visual and technical quality of the generated Batik patterns. These metrics indicate that the proposed model excels in producing patterns with more precise details, better contrast, and higher overall image fidelity when compared to previous approaches
Analysis of Stakeholder Collaboration in Local Rice Seed Governance in West Sumatra: Fuzzy Delphi Approach to Improve Food Security and Sustainable Agriculture
Full text linkLocal rice seeds are crucial to Indonesia's food security and agricultural sustainability, especially in West Sumatra. Seed management has yet to achieve seed independence, hindering the development of breeders and seed users. Overcoming this requires collaboration between stakeholders because locals can take collective responsibility and build trust in the Government through collaborative seed governance. This study introduces the concept of assessing the level of collaboration between stakeholders to analyze the stages of cooperation currently occurring in the governance of local rice seeds in West Sumatra. This study employs a mixed-methods approach, combining quantitative and qualitative methods. The study involved interviews with experts and a literature review, identifying 14 indicators influencing collaboration in seed governance. After validation by 5 (five) Experts, 13 (thirteen) indicators were obtained for further analysis using the Fuzzy Delphi, which was applied through a questionnaire distributed to 30 (thirty) informants representing stakeholders in five Regencies/Cities selected purposively in West Sumatra Province. The results were analyzed using a Likert scale and converted to fuzzy logic. These indicators are categorized into 5 (five) characteristics of collaboration. This study found that the level of collaboration between stakeholders is at the "cooperation" stage, which shows a significant lack of effectiveness in the interaction between stakeholders. This study offers valuable insights for stakeholders to enhance the collaborative process of local rice seed management, thereby achieving food security and sustainable agriculture
Investigating the Role of Gamification in Motivating Students Learning
Full text linkThis study investigates the role of gamification in enhancing student motivation within higher education, specifically targeting bachelor’s degree students in Klang Valley, Malaysia. The objective is to examine how the ARCS-R model by integrating the ARCS motivational framework (Attention, Relevance, Confidence, Satisfaction) with the Relatedness component of Self-Determination Theory (SDT) influences student motivation. A quantitative approach was employed, involving 208 business students who engaged in gamified learning activities via the Socrative platform. Participants completed competitive and collaborative tasks, followed by a survey measuring motivational constructs. Partial Least Squares Structural Equation Modelling (PLS-SEM) was utilized for data analysis. The results indicated that Relevance, Confidence, Satisfaction, and Relatedness had significant positive effects on student motivation, while Attention did not show a significant impact. The findings suggest that although gamified environments can enhance motivation, some elements, such as Attention, may be less effective without dynamic game design features. The study underscores the importance of integrating more interactive and adaptive game mechanics to sustain learner engagement. This research contributes to the understanding of motivation theories in gamified learning, offering empirical support for combining ARCS and SDT models. Future research should explore longitudinal effects and the role of personalized gamification strategies to optimize motivational outcomes across diverse student populations