Claim Missing Document
Check
Articles

Found 5 Documents
Search

Room occupancy classification using multilayer perceptron Wijaya, Dandi Indra; Aulia, Muhammad Kahfi; Jumanto, Jumanto; Hakim, M. Faris Al
Journal of Soft Computing Exploration Vol. 2 No. 2 (2021): September 2021
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v2i2.53

Abstract

A room that should be comfortable for humans can create a sense of absence and appear diseases and other health problems. These rooms can be from boarding rooms, hotels, office rooms, even hospital rooms. Room occupancy prediction is expected to help humans in choosing the right room. Occupancy prediction has been evaluted with various statistical classification models such as Linier Discriminat Analysis LDA, Classification And Regresion Trees (CART), and Random Forest (RF). This study proposed learning approach to classification of room occupancy with multi layer perceptron (MLP). The result shows that a proper MLP tuning paramaters was able estimate the occupancy with 88.2% of accuracy
Model Prediksi Risiko Kesehatan Perkotaan Berbasis Lingkungan dengan XGBoost Prihatin, Nanang; Aulia, Muhammad Kahfi; Utaminingsih, Eka
Computer Science (CO-SCIENCE) Vol. 5 No. 2 (2025): Juli 2025
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/coscience.v5i2.9109

Abstract

Poor urban air quality is a major public health concern, especially in highly urbanized areas. This study aims to predict health risks associated with air pollution using machine learning techniques based on environmental variables. The dataset used, Urban Air Quality and Health Impact, contains 1,000 rows and 46 columns, including temperature, humidity, wind speed, dew point, ultraviolet (UV) index, and health risk scores from major U.S. cities. As an improvement over previous studies using linear regression and Random Forest (R-squared 0.89; Mean Squared Error/MSE 0.65), this research implements an optimized Extreme Gradient Boosting (XGBoost) model. The model was fine-tuned using Randomized Search on key hyperparameters and evaluated with an 80:20 data split. It achieved an R-squared of 0.9692 and MSE of 0.0122. Dew point and wind speed were identified as the most influential features. Although synthetic, the dataset reflects environmental patterns similar to Indonesian urban areas. This study does not adopt a text mining framework but instead uses a supervised regression approach based on environmental features. Its main novelty lies in the first application of an optimized XGBoost model using complex variables such as feels-like temperature to estimate urban health risk. Limitations include the absence of real-world validation with Indonesian data and the lack of analysis on interactions between variables
Eka Learning Center (ELC) Tutoring Assistance thru the Development of SOPs and a Transparent Bookkeeping System Based on Excel Software Anora, Ayu; Multazam, Muhammad; Mardhiah, Ainol; Muktarullah, Millatina; Ningsih, Eka Utami; Yusnidar; Aulia, Muhammad Kahfi
Unram Journal of Community Service Vol. 6 No. 3 (2025): September
Publisher : Pascasarjana Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/ujcs.v6i3.1128

Abstract

Non-formal educational institutions such as tutoring centers play a vital role in enhancing the quality of education within communities. However, many of these institutions face challenges in management governance, particularly in establishing standardized operational procedures and financial accountability systems. This community engagement program aimed to strengthen the management capacity of the Eka Learning Center (ELC) by developing Standard Operating Procedures (SOPs) and an accountable, transparent bookkeeping system using Microsoft Excel. The method adopted was a participatory approach, consisting of socialization sessions, technical training, simulation practices, and intensive mentoring for ELC administrators. The outcomes demonstrated a significant improvement in the partners’ understanding and skills in preparing applicable SOP documents and recording financial transactions systematically through customized Excel templates. Furthermore, the partners showed enhanced capacity in generating basic financial reports that are internally and externally accountable. This program contributed positively to increasing operational efficiency and institutional transparency. The success of this activity is expected to serve as a model for similar educational institutions and support the achievement of Sustainable Development Goals (SDGs), particularly in the areas of quality education and good institutional governance.
CLASSIFICATION OF MIGRAINE TYPES BASED ON SYMPTOMS USING ARTIFICIAL NEURAL NETWORKS Aulia, Muhammad Kahfi; Prihatin, Nanang
Multidiciplinary Output Research For Actual and International Issue (MORFAI) Vol. 6 No. 2 (2026): Multidiciplinary Output Research For Actual and International Issue
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.18811901

Abstract

Migraine is a complex neurological disorder with heterogeneous clinical manifestations, making accurate subtype classification difficult using conventional diagnostic approaches. Diagnostic inaccuracies may result in inappropriate treatment and suboptimal patient outcomes. This study proposes an Artificial Neural Network (ANN) model to classify migraine subtypes based on patient-reported symptoms and clinical characteristics. A publicly available dataset containing 400 instances and 24 features—including demographic data, aura symptoms, neurological and autonomic indicators, genetic history, and disease burden—was utilized. Data preprocessing involved feature standardization, label encoding, and one-hot encoding, followed by an 80:20 split for training and testing. The ANN architecture comprised an input layer with 23 neurons, two hidden layers with 64 and 32 neurons using ReLU activation, and a seven-neuron output layer with softmax activation. The model was trained using the Adam optimizer and categorical cross-entropy loss for 50 epochs. Experimental results showed that the proposed model achieved a training accuracy of 91.56% and a testing accuracy of 93.00%, demonstrating strong generalization performance and effective learning of complex, non-linear symptom patterns. These results indicate that ANN-based classification has significant potential as a clinical decision-support tool for improving migraine subtype diagnosis and enabling more personalized treatment strategies.
PRESERVING PROVERBS IN THE DIGITAL AGE: A QUALITATIVE STUDY ON STAKEHOLDER PERCEPTIONS OF ARTIFICIAL INTELLIGENCE FOR ACEHNESE LANGUAGE HERITAGE Hajar, Ibnu; Husna, Asmaul; Aulia, Muhammad Kahfi; Muntazar, T.
Journal Informatic, Education and Management (JIEM) Vol 8 No 1 (2026): FEBRUARY
Publisher : STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61992/jiem.v8i1.306

Abstract

This qualitative study investigates the perceived opportunities and challenges of developing an artificial intelligence (AI) application for preserving Acehnese proverbs (Hadih Maja), a critical yet endangered component of cultural heritage. Conducted as a multi-stakeholder feasibility study, it engages academics (linguists, anthropologists, AI/data scientists) and cultural custodians (tokoh adat) in North Aceh and Lhokseumawe, Indonesia. Through reflexive thematic analysis of in-depth interviews, the research reveals a dualistic landscape. Stakeholders recognize AI’s transformative potential as a bridge for intergenerational engagement, enabling interactive, mobile-based learning for youth. However, this promise is counterbalanced by formidable socio-technical hurdles. Key challenges include the fundamental "low-resource" paradox—where data scarcity severely limits natural language processing capabilities—and profound ethical risks of cultural decontextualization, trivialization, and the erosion of community sovereignty over knowledge. The findings underscore that the primary impediments are not merely technical but deeply socio-technical, necessitating an approach that makes community governance and cultural integrity foundational. The study concludes that a successful initiative must be reconceptualized from an "AI development project" to a "community-led cultural revitalization project enabled by AI," prioritizing participatory co-design, ethical data governance guided by the CARE principles, and the creation of a culturally-grounded multimodal corpus before any substantial technical development. This research offers a critical framework for ethically and effectively leveraging AI in endangered language contexts globally.