RHRimuljo Hendradi

Rimuljo Hendradi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Rimuljo Hendradi has a total of 72 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Automatic Skill Extraction across Job Postings, Course Learning Outcomes, and Skills Framework for the Information Age for Pre-Competency Mapping Process

    by Badrus Zaman, Windarto Windarto, Rimuljo Hendradi

    Background: The increasing demand for Information Technology (IT) professionals is often not aligned with the unstructured representation of competencies across various document sources, including industry documents such as job postings and educational documents such as Course Learning Outcomes (CLOs) and the Skills Framework for the Information Age (SFIA). Differences in linguistic characteristics among these sources create challenges for automatic skill extraction. Objective: This study aims to compare the performance of four Natural Language Processing (NLP)-based skill extraction methods, namely skill-specific NER (SkillNER), Rapid Automatic Keyword Extraction (RAKE), Yet Another Keyword Extractor (YAKE!), and KeyBERT, across three domains namely job postings, CLOs, and SFIA Framework. Methods: This study used 60 documents consisting of 20 job postings, 20 CLOs, and 20 SFIA Framework. The methods used consist of ground truth annotation using Cohen's Kappa, document extraction, skill extraction and evaluation using precision, recall, and F1-score. Results: SkillNER consistently outperformed all comparison methods across all data sources, achieving F1-Scores of 0.613 for job postings, 0.896 for SFIA, and 0.818 for CLOs. RAKE and YAKE! produced F1-Scores ranging from 0.101 to 0.263, while KeyBERT demonstrated the lowest performance. Conclusion: NER-based approaches trained on skill taxonomies are more effective than general keyword extraction methods. Future studies should integrate query expansion mechanisms, apply transformer model fine-tuning on skill-domain datasets, and expand data coverage to improve result generalizability. Keywords: Course Learning Outcomes, SkillNER, Job Posting, Skill Extraction, Skill Framework for the Information Age

  • Open Access

    Integrating CLAHE and H-MHI with CNN for prompt recognition in children with a diagnosis of autism

    by Indah Werdiningsih, Ira Puspitasari, Rimuljo Hendradi

    Individualized therapeutic prompts such as physical, gestural, or verbal cues are necessary to enable children diagnosed with autism to become independent in daily activities. However, the automated detection of the prompts in naturalistic conditions is difficult. The solutions currently proposed also have difficulty with unstructured video data obtained from real-world therapeutic settings with different camera angles, uneven lighting, and random movement of children. Therefore, this study aims to introduce a new model that combines contrast limited adaptive histogram equalization (CLAHE) along with hybrid motion history image (H-MHI) to extract motion-based features with convolutional neural networks (CNNs) to classify features and provide timely responses in the context of autism therapy. The H-MHI method was based on the regular MHI with the addition of Otsu thresholding and Canny edge detector. These features were subsequently categorized with the CNN architectures in the form of VGG19 and MobileNetV2. The suggested algorithm was tested on 1,083 video samples and the results showed the ability of H-MHI to enhance accuracy by 2-3% at less computing time than the conventional MHI. The trend reflected the suggested method’s effectiveness in enhancing recognition performance without compromising the computational efficiency.

  • Early postoperative seizure after extracranial–intracranial revascularization for moyamoya disease and moyamoya syndrome: single centre post-revascularization moyamoya cohort study in Indonesia

    by Muhammad Kusdiansah, Bryan Gervais de Liyis, Abdi Marang Gusti Alhaq, Abrar Arham, Nakao Ota, Rokuya Tanikawa, Rimuljo Hendradi, Asra Al Fauzi

    Early postoperative seizure after revascularization for moyamoya vasculopathy remains incompletely characterized, particularly in Indonesia. This study described the incidence and exploratory clinical and hemodynamic patterns associated with early postoperative seizure after extracranial-intracranial bypass in an Indonesian single center cohort. This single center retrospective cohort included moyamoya disease (MMD) or moyamoya syndrome (MMS) patients who underwent extracranial-intracranial revascularization. Early postoperative seizure was defined as a clinically documented new onset epileptic event occurring intraoperatively after bypass completion or within 14 days. Clinical and computed tomography perfusion (CTP) variables were compared between MMD and MMS and, within MMS, between seizure and non-seizure groups using descriptive exploratory analyses. Forty patients were analyzed, including 19 with MMD and 21 with MMS. Early postoperative seizure occurred exclusively in the MMS group (6/21, 29%) and was not observed in MMD (0/19; p = 0.021). Compared with MMS, MMD demonstrated larger pre-bypass infarct volume (14.48 ± 8.54 vs. 5.06 ± 5.52 mL; p = 0.005) and hypoperfusion volume (54.39 ± 33.07 vs. 27.26 ± 25.76 mL; p = 0.028). In paired CTP analysis, hypoperfusion volume decreased from 41.48 ± 27.78 to 26.06 ± 21.51 mL (p = 0.023), and infarct volume decreased from 10.27 ± 7.89 to 5.48 ± 4.16 mL (p = 0.040). Within MMS, patients with postoperative seizure were older (52.00 [41.75 to 55.00] vs. 35.00 [26.00 to 42.00] years; p = 0.014), more frequently presented with dysarthria (67% vs. 20%; p = 0.040) and monoparesis (50% vs. 0%; p = 0.015), and were more commonly classified as having suspected atherosclerotic vasculopathy (100% vs. 33.3%; p = 0.012). Follow up CTP demonstrated lower relative post-bypass CBV in the seizure group (0.31 [0.14 to 0.48] vs. 1.16 [0.68 to 1.22]; p = 0.026), although this finding was interpreted cautiously because postoperative imaging was not temporally aligned with seizure onset. In this exploratory Indonesian moyamoya cohort, early postoperative seizures were observed only in the MMS subgroup. Older age, baseline focal neurological deficits, and MMS related etiologic heterogeneity may be relevant to postoperative seizure susceptibility.

  • Clinical and CT perfusion outcomes after direct STA–MCA bypass in moyamoya and non-moyamoya steno-occlusive disease: an Indonesian single-center cohort

    by Muhammad Kusdiansah, Bryan Gervais de Liyis, Syifa Aulia Suryani, Aisha Lathifa Zahra, Abrar Arham, Nakao Ota, Rokuya Tanikawa, Rimuljo Hendradi, Asra Al Fauzi


  • Open Access

    Advanced inferential statistics and data mining for chlorophyll distribution clustering

    by Felix Reba, Toha Saifudin, Rimuljo Hendradi

    This study proposes an integrated statistical framework to analyze chlorophyll distribution in marine environments by combining probability distribution modeling, goodness-of-fit (GoF) evaluation, and machine learning-based clustering. Eight probability distribution models—half normal, inverse Gaussian, Rician, Birnbaum–Saunders, Nakagami, extreme value, t location-scale, and stable—were evaluated using observational chlorophyll-a data from the Copernicus Marine Service. Model performance was assessed through the Kolmogorov–Smirnov (KS) and Anderson Darling (AD) GoF tests, along with five statistical information criteria. The results indicate that the inverse Gaussian and extreme value distributions consistently offered the best statistical fit and ecological relevance across varying sample sizes. Clustering analysis, performed using the k-means algorithm and validated via the silhouette index, further confirmed the robustness of these two models in forming stable and well-separated clusters. In contrast, the half-normal distribution showed poor performance and instability, especially with smaller sample sizes. The proposed taxonomy and spatial visualizations enable empirical classification of model behavior and support integration into real-time marine decision support systems (DSS) for ecosystem monitoring. Overall, the study contributes to the development of accurate, data-driven analytical tools that aid sustainable marine resource management, aligned with sustainable development goal (SDG) 14 on marine ecosystem protection.

  • Open Access

    ChatGPT and Its Impact on Students Assessment Practices in the Higher Educational Sector: A Systematic Review

    by Lizzy Oluwatoyin Ofusori, Rimuljo Hendradi

    Background: The proliferation of Artificial Intelligence (AI) tools such as ChatGPT is growing at a rapid pace, sparing no sector. One of the AI tools that has grown in it use across the sectors is the use of ChatGPT, a tool that mimics human like capabilities of producing ideas. However, there have been many concerns about how ChatGPT will change the higher education institutions. More worrisome is how it poses risks that compromise the integrity of academic outputs if left unregulated Objective: This study examines the influence of ChatGPT on students’ assessment practices in the higher educational sector Methods: The study carried out a systematic literature review by gathering data from peer reviewed academic papers. Initially, 140 research papers were identified. Thereafter, these papers went through further filtering, and 35 usable papers were selected and included in the study Results: This study highlighted the importance of using AI tools such as ChatGPT in the higher education sector, underscoring its advantages and the threats that it poses to the sector if the use remains unregulated. The study has recommended institutional policies about the use of AI tools that must be put in place to guide academic staff, researchers and learners in the responsible use of ChatGPT for academic work. Conclusion: “While the widespread adoption of ChatGPT is undeniable, there is an urgent need for a well-balanced regulation regarding its use within Higher Education Institutions (HEIs). Thus, future research should focus on examining the existing policies and practices related to ChatGPT ethics, privacy, and security in education and identify gaps and areas for improvement. Keywords: ChatGPT, Artificial Intelligence, Chatbot, OpenAI, Higher Education


  • Open Access

    Recognizing Daily Activities of Children with Autism Spectrum Disorder Using Convolutional Neural Network Based on Image Enhancement

    by Indah Werdiningsih, Ira Puspitasari, Rimuljo Hendradi

    Independence for individuals with disabilities, Children with Autism Spectrum Disorder (ASD), need skills to perform daily activities. This study focuses on recognizing the daily activities of children with ASD using a Convolutional Neural Network (CNN) based on augmented images. The CNN architectures employed are Visual Geometry Group 19 (VGG19) and MobileNetV2, while image improvement techniques include Histogram Equalization, Contrast Stretching, and Contrast Limited Adaptive Histogram Equalization (CLAHE). The data consists of eating (606 videos) and drinking (477 videos) activities recorded by therapists or parents. CLAHE proved the most effective, achieving an SSIM of 0.998 and a PSNR of 38.466 for the eating activities, an SSIM of 0.998, and a PSNR of 38.296 for the drinking activities. Experimental results using CLAHE and VGG19 showed a recognition model accuracy of 85%, while VGG19 without image enhancement achieved an accuracy of 83%. CNN with image enhancement achieves slightly better accuracy, though the difference is insignificant.


  • Open Access

    Input-Output Based Relations T-Way Test Suite Generation Strategy Based on Ant Colony Optimization Algorithm (iTTSGA)

    by Nuraminah Ramli, Rozmie Razif Othman, Rimuljo Hendradi, Hasneeza Liza Zakaria, Iszaidy Ismail, Nurul Ain Mohd Zaki, Nik Afiqah N. Ahmad Yani

    Input-output based relations (IOR) testing is one of the important support interactions in t-way testing (t is referring to the interaction strength). For the past 20 years, a number of IOR test suite generation strategies have been put forth in the literature (e.g., Density, ParaOrder, ReqOrder, UNION, Greedy, ITTDG, and AURA). Although these strategies can produce a sizable IOR test suite, very little of them use the metaheuristic search technique. According to the literature, compared to other search techniques, most metaheuristic-based t-way strategies can produce smaller test suite sizes for uniform and variable strength interactions. Because the T-way test suite generation problem is NP-hard, no strategy can guarantee that it can produce the ideal test suite size for every possible system configuration. Motivated by these challenges, this paper presents an IOR test suite generation strategy based on a metaheuristic algorithm, Ant Colony Optimization (ACO) called iTTSGA. The results of two benchmark experiments for IOR uniform and non-uniform configurations were compared with those of other IOR strategies that have been published. The performance of iTTSGA has been statistically analyzed using the Friedman test and Wilcoxon Sum test. Results show that, with the exception of |R| = 10 and the top ranking in the Friedman Test, iTTSGA outperforms other strategies in the majority of uniform configurations. In addition, the iTTSGA performs exceptionally well in non-uniform configuration for |R| = 30 and 60 and ranks second in the Friedman test. It demonstrates that iTTSGA can produce test suites with a smaller file size for IOR t-way testing.


  • Open Access

    PENERAPAN METODE RULE BASED PADA QUESTION ANSWERING SYSTEM TERJEMAH AL-QURAN BERTEMA SAINS

    by Ade Vita Aulia, Badrus Zaman, Rimuljo Hendradi

    PENERAPAN METODE RULE BASED PADA QUESTION ANSWERING SYSTEM TERJEMAH AL-QURAN BERTEMA SAINS