Publication Search

Sign language recognition is one of the areas of image recognition and image processing technology that is developing rapidly in human-computer interaction. This technology really helps the deaf and speech impaired in communicating with non-disabled people. This research aims to examine the optimization of an object tracking system in sign language using the Gaussian Mixture Model (GMM) and Kalman Filter by including the Region of Interest (ROI). The proposed system consists of three main components, namely hand detection, object extraction, and classification. Hand detection is done using the Kalman Filter to track hand movements accurately. Next, Region of Interest (ROI) features, such as shape, direction and movement features, are extracted from the detected part of the hand. These features are fed into a Gaussian Mixture Model (GMM) classifier, which can recognize sign language based on the extracted features. With the combination of GMM and Kalman Filter in this research, it can increase accuracy in object tracking, reduce interference from the background, and ensure the tracking focus remains on important objects. The dataset used is in the form os SIBI alphabet symbols, namely A-Z with the amount of data for each class, namely 620 images. Based on the research result, model testing using GMM, Kalman Filter and ROI produces higher accuracy of 99%, while model testing using GMM and ROI produces accuracy of 90%.

Gesture  recognition  technology  is  used  to  detect  movements  through  image processing,   enabling  computers  or digital devices to understand and interpret human  body  movements  as  input  or  commands.   This  technology  has  great potential  to bridge communication between the deaf community and individuals without   hearing   impairments,    enhancing  interaction  and  enriching  mutual understanding between the two.  However,  the accuracy ofgesture recognition is often  affected  by variations in the distance between hand landmarks.  Based on this problem,  this research proposes a methodfor stabilizing the measurement of distances between landmark points  in gesture recognition through a polynomial regression  approach.   Specifically,   the  distance  between  hand  landmarks  is calculated and stabilized using polynomial  regression to improve the accuracy of gesture recognition.  This method is implemented using the MediaPipeframework to detect and track hands in real-time,  and the OpenCV library to manage video. The  research  results  show  that  this  approach  can  significantly  improve  the stability  and accuracy  of gesture detection.   The developed system successfully detects gestures for  letters A  through F with a high accuracy  rate,  averaging above 98,3%.  The use ofpolynomial regression helps enhance detection accuracy by reducing noise in the landmark data.

For every child to receive an equal education, inclusive education at the early childhood education (PAUD) level is a strategic step. The purpose of this study is to thoroughly study the basic concepts of inclusive education in early childhood, identify various types of specific challenges for Children with Special Needs (ABK) in regular classes, and evaluate how effective the use of inclusive learning methods is in optimizing child development. This study uses a literature review with a descriptive qualitative approach. Secondary data were analyzed using content analysis. According to the study, teachers in regular classes face multidimensional characteristics of ABK. These obstacles include visual impairment, deafness, mental retardation, physical disability, emotional retardation/ADHD, autism, and exceptional intelligence. To overcome these problems, it has been proven that the use of assistive technology, a more flexible curriculum, individualized learning programs (IPC) based on initial assessment, varied teaching methods, and a friendly environment can be helpful. This study shows that teachers are not the only key to the success of inclusive education. This requires strong multi-stakeholder collaboration between the government, schools, special education teachers (GPK), professionals, and parents to address facility challenges and eliminate existing stigma in the field.

Communication is an essential human right, yet a significant communication gap persists between individuals with sensory disabilities, specifically the deaf and speech-impaired, and the general public. While many technological solutions have been proposed to translate sign language, existing models primarily rely on heavy deep learning architectures such as Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN/LSTM). These models often demand high computational power, leading to latency and limiting real-time application on standard devices. This study proposes a lightweight, fast, and highly responsive sign language translation system specifically designed to recognize static alphabets (A-Z) and single-character air writing. The system utilizes MediaPipe for hand tracking, where feature extraction is intelligently processed by calculating the relative spatial coordinates of fingertips to the wrist, reducing dependency on raw camera coordinates. Classification is performed using a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel, prioritizing computational efficiency without sacrificing accuracy. To enhance user experience, the system introduces three key novelties: smart relative feature extraction, an anti-duplication hold system with a 1-second timer to prevent input spamming, and a non-blocking multithreaded audio execution (Daemon Thread) utilizing Google Text-to-Speech (gTTS), ensuring the webcam feed remains fluid during audio playback. Additionally, an alternative air-writing mode is integrated, utilizing geometric heuristics and PyTesseract OCR to read single drawn letters in the air. The results indicate that the proposed system operates swiftly and efficiently, bridging the communication barrier with a hardware-friendly approach.

Background: Diffable children have a higher risk of developing caries compared to normal children. Objective: This study aims to determine the prevalence of caries in deaf children aged 12-18 years in Denpasar City. Method: This study design was cross-sectional analytic and the target population was deaf children in Denpasar City. The variables studied were sociodemographic characteristics, knowledge, and behavior of maintaining oral health and caries prevalence. Data were collected through interviews using questionnaires and intra-oral examinations. The collected data were analyzed using the chi-square test. Result: The prevalence of caries in deaf children is 81.7%. There was a tendency for boys, age group 12-14 years, poor knowledge and poor behavior to experience dental caries. However, from the results of the analytical test, only gender showed a significant relationship with caries (boys had a risk of 1.3 times (CI95%=1.125-1.741) having caries compared to girls). Conclusion: The prevalence of dental caries in deaf children is quite high, especially boys are more at risk than girls. Efforts are needed to increase knowledge and monitor the oral health behaviour of deaf children, especially boys, and to promote early detection of dental caries with support of parents, teachers, health services and the health office.

This study examines the effectiveness of Assemblr Augmented Reality (AR) in improving English vocabulary mastery among deaf students in an inclusive classroom setting. The research was conducted at SD N 2 Bengkala using a quantitative pre-experimental design with a one-group pre-test and post-test approach. The participants were Grade 5 deaf students selected through purposive sampling. Data were collected using a researcher-developed vocabulary test consisting of 15 items, which was validated through expert judgment and demonstrated high reliability (Cronbach’s Alpha = 0.815). Descriptive statistical analysis revealed a substantial improvement in students’ vocabulary scores, with the mean increasing from 45.00 in the pre-test to 76.50 in the post-test. The minimum score improved from 40 to 73, and the maximum score increased from 50 to 80. Inferential analysis using the Wilcoxon Signed-Rank Test showed a significance value of 0.180, indicating no statistical significance due to the small sample size. However, the observed improvement indicates strong practical significance. The findings suggest that Assemblr AR enhances vocabulary learning by providing visual and interactive learning experiences that support deaf students’ cognitive processing. This study highlights the potential of AR technology as an effective instructional medium in inclusive education environments.  

This study aims to identify the learning needs of deaf students in internship programs, examine the challenges they face, develop appropriate solutions, and design as well as evaluate a visual module-based learning model to improve their work skills. The study used a Research and Development (R&D) approach with a 4D model: Define, Design, Develop, and Disseminate. The participants included deaf students from special needs high schools (SMALB) involved in vocational internships, mentor teachers, and industry supervisors. Data were collected through observation, interviews, questionnaires, documentation, and focus group discussions, and analyzed using qualitative techniques supported by descriptive analysis. The findings indicate that deaf students require visual, structured, and easily understandable work instructions supported by symbols, color codes, and guidance materials. Major challenges include limited verbal communication, difficulty understanding instructions, and risks of procedural errors. To address these issues, a systematic and communicative visual module-based learning model was developed, incorporating collaborative support from schools and industry. The resulting model integrates planning, implementation, mentoring, and evaluation stages, and has proven feasible and effective in enhancing students’ independence, technical competence, and overall work readiness.

Indonesia represents one of the world's most complex and dynamic linguistic ecosystems, harboring over 700 regional languages alongside the national language (Bahasa Indonesia) and Indonesian Sign Language (BISINDO). This synthesis study provides comprehensive analysis of the Indonesian linguistic landscape, integrating findings from five complementary large-scale investigations conducted 2020–2024: code-switching patterns in digital communication; typological uniqueness of Indonesia's tenseless temporal system; linguistic complexity of BISINDO and barriers to deaf inclusion; sociolinguistic stratification through first-person pronoun variation; and critical endangerment of regional languages. The synthesis employed integrative methodology encompassing 3,550 total participants, 20,000+ linguistic tokens, 18 months of ethnographic fieldwork, and analysis of 150 languages and 25 revitalization programs. Synthesis reveals five interconnected dynamics: (1) centripetal standardization through education, urbanization, and media; (2) centrifugal diversification through identity construction and social stratification; (3) typological persistence maintaining Indonesian distinctiveness despite contact; (4) parallel endangerment affecting regional languages and BISINDO; and (5) ideology-driven change linking language choice to modernity and prestige. These dynamics produce dynamic tension between homogenization and diversification. Indonesia's linguistic future depends on whether policies can balance national unity through Indonesian and linguistic diversity through regional language and BISINDO protection. 

Indonesian Sign Language (Bahasa Isyarat Indonesia, BISINDO) is often misunderstood as merely a gestural or simplified form of communication, undermining its linguistic sophistication and contributing to barriers to deaf inclusion in Indonesia. Approximately 2.6 million deaf individuals in the country rely on BISINDO as their primary language. This study explores the linguistic complexity of BISINDO, documenting its phonological, morphological, syntactic, and semantic systems. Using a mixed-methods approach, we analyzed 150 hours of BISINDO conversations from 80 deaf signers, conducted experimental studies on phonological distinctions and syntactic complexity, and performed ethnographic fieldwork in deaf communities and schools. Comparative analysis with American Sign Language (ASL) was also conducted. Our findings demonstrate that BISINDO is a fully developed natural language, with 45 handshapes, 18 locations, 23 movements, and 4 orientations in its phonological system. It shows productive morphological processes, flexible word order, and rich semantics, including idioms and metaphors. However, there are significant barriers to inclusion: 68% of deaf students lack qualified BISINDO teachers, and 84% of public services lack sign language interpreters. Furthermore, 72% of hearing Indonesians still do not recognize BISINDO as a legitimate language. Deaf community organizations, however, report BISINDO as central to their identity. The study highlights the need for policy reforms, including BISINDO recognition as an official language, qualified interpreters, bilingual deaf education, and public awareness campaigns to combat misconceptions.    

Students with deaf disabilities often have difficulty understanding verbal instruction, but have significant advantages in visual and motor aspects. This service activity aims to apply multisensory methods through Suminagashi craft art training (cloth marbling) to improve students' fine motor skills and creativity at SLB B Yakut Purwokerto. The implementation method uses a descriptive qualitative approach with a "see-learn-do" strategy involving 20 high school students. The learning process integrates visual stimulation through structured demonstrations and tactile stimulation through the exploration of material textures. The results of the activity showed that the multisensory approach was effective in bridging the barriers of deaf students with disabilities in communicating due to hearing limitations. Students demonstrate a high level of visual focus and are able to replicate marble motif making techniques with precision without relying on complex verbal explanations. The combination of cue instructions and direct touch experiences has been proven to minimize miscommunication and improve understanding of abstract concepts of the material. This activity recommends the use of visual-tactile strategies as an adaptive inclusive learning method to support the vocational independence of deaf people.          

Communication is a fundamental aspect of human life. However, individuals with hearing and speech impairments often face barriers in communicating with the general public. The Indonesian Sign System (SIBI) serves as a communication solution for the deaf and speech-impaired community in Indonesia, yet public understanding of SIBI remains limited. To address this issue, this study aims to develop an automatic translation model from SIBI sign language into Indonesian text by utilizing Deep Learning technology, specifically the Convolutional Neural Network (CNN) algorithm. CNN was chosen for its ability to effectively recognize visual patterns, making it suitable for processing hand gesture images in sign language. This research involved collecting and classifying a dataset of hand images based on the alphabet or words in SIBI, which were then used to train the CNN model. The designed CNN model was built to accurately classify hand signs and translate them into Indonesian text. The results of this study have the potential to serve as a supportive solution for inclusive communication between the deaf community and the wider public, and can be further developed for contextual sentence translation. Keywords: Indonesian Sign System (SIBI), CNN, Deep Learning, Automatic Translation, Inclusive Communication