This paper presents a comprehensive test of the principal tasks in document image analysis (DIA), starting with binarization, text line segmentation, and isolated character/glyph recognition, and continuing on to word recognition and transliteration for a new and challenging collection of palm leaf manuscripts from Southeast Asia. This research presents and is performed on a complete dataset collection of Southeast Asian palm leaf manuscripts. It contains three different scripts: Khmer script from Cambodia, and Balinese script and Sundanese script from Indonesia. The binarization task is evaluated on many methods up to the latest in some binarization competitions. The seam carving method is evaluated for the text line segmentation task, compared to a recently new text line segmentation method for palm leaf manuscripts. For the isolated character/glyph recognition task, the evaluation is reported from the handcrafted feature extraction method, the neural network with unsupervised learning feature, and the Convolutional Neural Network (CNN) based method. Finally, the Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) based method is used to analyze the word recognition and transliteration task for the palm leaf manuscripts. The results from all experiments provide the latest findings and a quantitative benchmark for palm leaf manuscripts analysis for researchers in the DIA community.

In order to preserve the Sundanese palm leaf manuscripts, some digitization campaigns have been done recently. Then, for further access in education and research, the handwritten Sundanese palm leaf manuscript dataset called Lontar Sunda dataset has been created. The dataset was constructed from 66 pages of 27 collections of Sundanese palm leaf manuscripts from the 15th century. The dataset has been carried out with manuscripts from Garut, West Java, Indonesia. This paper presents the Sundanese dataset which is publicly available for scientific use. The groundtruth includes binarized images, annotations at word level and annotations at character level. The Sundanese dataset provides useful data to test word spotting, character/symbol recognition and binarization methods, and will facilitate the evaluation of developed methods.

Indonesia is a developing country that began to utilize information technology in education. A form of its implementation is the use of e-learning. However, in practice there are still some obstacles, such as learning resources are not evenly distributed, limited access to services provided, qualified educators resources are concentrated in specific areas. This led to the emergence of disparities educational process, and technology gap due to differences in ICT infrastructure owned by any educational institution. Therefore this study propose an architecture of cloud-based open learning to solve these problems. The term open learning is used in order to encouraging the development of the concept of Indonesia Open Educational Resources (IOER) and as well as the adoption of concept of cloud computing. This research through several phases of research including analysis, design, implementation, testing and evaluation. The design of the proposed architecture consists of six layers: (1) Infrastructure, (2) Platform, (3) Application, (4) Service, (5) Access, (6) User. As a results of the implementation from this architecture is a prototype of Indonesia - Virtual Open Learning System (iVOLS). In experiment, personalization e-learning runs as a service that need large storage and other shared facilities to conduct the program so the system can delivered different learning materials to different learners. The personalization e-learning in cloud environment successed when the learners got the best performance on learning and it shown by their evaluation score. Based on the test results and evaluation showed that the availability on Cloud-Based Open Learning further meet user needs. This is indicated by the presence of a simple infrastructure services, application services with just one stage and the availability of a wider range of data and the resource sharing. In accessibility, Cloud-Based Open Learning provides easy access to the user. By economically, the result of evaluation showed that Cloud-Based Open Learning has an investment of 35.61% efficiency, increase return on investment (ROI) of 60.95% and an increase in benefits (NPV) of 81.97% from the user's perspective. While from the provider's perspective, Cloud-Based Open Learning has an investment of 200% efficiency, increase return on investment (Rol) of 220.4% and an increase in benefits (NPV) of 109.55%.

Cognitive load (CL), the mental effort required to process information, plays a pivotal role in user performance and experience in various domains, particularly within computer science (CS) and information systems (IS). As technology becomes more interactive and complex, understanding and measuring CL has become increasingly important for the design of adaptive and user-centered systems. This study aims to investigate trends in CL measurement techniques within CS and IS research from 2017 to 2024, with a focus on identifying emerging tools, methods, and their applications. A systematic literature review (SLR) was conducted to provide a comprehensive overview of CL’s role in CS and IS, the methods used to detect it, and how it is analyzed across different tasks and environments. The motivation behind this research stems from the growing need to optimize user experiences and system efficiency through better CL management. Findings reveal a significant shift towards multimodal CL measurement methods, which integrate subjective, performance-based, behavioral, and physiological data. These approaches are increasingly analyzed using machine learning techniques, particularly in areas such as human-computer interaction, education, and immersive technologies like virtual reality. This research highlights the importance of accurate CL measurement and suggests future directions for enhancing adaptive system design through the integration of CL metrics.

Sleep apnea is a sleep disorder that causes decreasing or even stopping of breathing during sleep. One way to detect whether a person has the disorder or not, then it can be done by conducting a sleep test (polysomnogram). Polysomnogram provides overall body activity during sleep. Polysomnogram records every process of breath changes, muscle tension, brain waves, eye movements that occur in sleep from awake to the patient has dreams and finally wakes up. Once polysomnogram is obtained, then the doctor will check it. One of the targets of the analysis conducted is sleep stage classification. It takes a long time if done manually. Therefore, it needs an application that automatically to make classification efficiently. It is the main reason for this research that must be done. Specifically, this research applies Multi-Layer Perceptron (MLP) to classify the sleep stage. The results show that MLP has a higher performance than Naïve Bayes, Bayesian Networks, K-Nearest Neighbours, and Decision Tree.

EVALUASI APLIKASI SEMI-IMMERSIVE VIRTUAL REALITY PADA BIDANG PENDIDIKAN MENURUT ASPEK HEURISTIK DAN PEMBELAJARAN