Smart Techno (Smart Technology, Informatics and Technopreneurship)

Design Overview Of User Interface Design For Medical Record Filling System At Dharma Yadnya General Hospital

Made Wahyu Aditya — 2025-02-14

The manual recording of borrowing and returning medical record documents using expedition books leads to several challenges, such as incomplete data on borrowing and returning medical record documents beyond 24 hours, as well as delays in returning medical record documents. Additionally, manual expedition book usage is less effective and efficient. The purpose of this research is to understand the overview of designing the user interface for filling system medical record documents. The research method used is descriptive qualitative with the waterfall design method.. The research results indicate that the user acceptance level of the user interface design falls within the acceptable category. This indicates that the user interface design for the electronic expedition system of inpatient medical records has a good level of usability. With an average score of 90, there is no need for further improvements in the user interface design, which can be considered as a recommendation to Dharma Yadnya General Hospital.

The Implementation of Copilot-Based Artificial Intelligence (AI) Through Collage Techniques in Illustration Design

Dharma Prasetya Irawan — 2025-02-21

The development of artificial intelligence (AI)-based illustrations, specifically using Copilot, in the creative industry has had a significant impact, opening new opportunities for designers to create visual works more efficiently and innovatively. The advantage of AI in analyzing and generating images makes the creative process faster and more varied. As this technology evolves, I am interested in developing a collaboration between AI-based collage techniques and illustration design. This research uses a descriptive analysis approach that combines observation, interviews/questionnaires, documentation, and literature study. Observations are made on the AI processes that I have created. Additionally, questionnaires are distributed to students from the Visual Communication Design department at Universitas Primakara to assess the importance and benefits of this technique in completing their assignments. The results of this research are expected to provide insights into whether this technique can help enhance creativity and efficiency in creating illustration designs, as well as contribute to the development of a more innovative creative industry.

Development of a Community Complaint Information System to Support the Realization of a Smart Village in Sibetan

I Gede Juliana Eka Putra — 2025-03-04

A computerized (digital) village is one of the key initiatives introduced by public authorities to support the sustainable development of rural areas across the Republic of Indonesia. One of the primary objectives of a Digital Village is to disseminate information rapidly, accurately, and efficiently to local communities while promoting transparency and public participation. Sibetan Village is among those committed to becoming a digital village through the integration of information and communication technologies into its governance systems. However, in developing a local complaints website, the testing process must strictly adhere to the village’s expected quality standards to ensure usability, reliability, and effectiveness. Villages are widely encouraged to leverage data-driven innovations to enhance administrative processes, improve public service delivery, and foster inclusive community engagement. In Sibetan, one such initiative is the development of a web-based Regional Complaints Information System, designed to facilitate the submission of inquiries and complaints from the public, enabling faster responses by village authorities. The system was designed using the Waterfall method to accommodate user requirements. The outcome of this research is the user interface design of the Sibetan Village community complaints website.

Improving MRI Classification through Layered Convolutional Neural Networks Configuration

Paul Michael Custodio — 2025-04-25

Timely and accurate classification of brain tumors using Magnetic Resonance Imaging (MRI) is critical for effective treatment planning. This study proposes a layered Convolutional Neural Network (CNN) configuration to enhance the classification of brain tumors, addressing the limitations of traditional machine learning approaches that rely heavily on manual feature extraction. Utilizing a dataset sourced from Kaggle, comprising 7023 MRI images categorized into glioma, meningioma, no tumor, and pituitary tumor classes, the research implements data augmentation techniques such as rotation and flipping to increase the dataset size by 20%. Images were standardized to 128x128 pixels and normalized for model compatibility. The core model architecture was built using 2D CNNs with configurations ranging from one to three layers. The models were trained and tested using TensorFlow and Keras on Google Collaboratory, and evaluated based on accuracy, loss, and computational efficiency. The findings revealed that among all the configurations tested, the three-layered CNN model delivered the best performance. It achieved an accuracy value of 89.79% with a corresponding loss of 0.469. In terms of processing time, the model completed training in 59.8894 seconds and performed inference in 5.1099 seconds, highlighting its suitability for real-time diagnostic applications despite the longer training duration.

Convolutional Neural Network-Based Human Stress Detection Using Multivariate Sensor Data and Cross-Validation

Asma' Abu Samah — 2025-04-25

Early identification of human stress levels plays a crucial role in promoting mental well-being and preventing related health issues. However, conventional stress assessment methods often involve multi-step procedures or subjective evaluations, making them inefficient and impractical for continuous monitoring. This study introduces a Convolutional Neural Network (CNN)-based approach to automatically detect human stress using multivariate sensor data, such as heart rate, oxygen saturation, body temperature, and movement signals. Unlike traditional machine learning methods that rely on handcrafted features and shallow classifiers, the proposed deep learning model leverages raw sensor data to learn hierarchical representations of physiological patterns associated with various stress levels. The dataset utilized in this research is the SaYoPillow dataset obtained from Kaggle, which includes labeled physiological signals based on subjective stress assessments. Input features are normalized and reshaped into one-dimensional sequences compatible with the CNN architecture. A stratified 5-fold cross-validation strategy is used to ensure robust and generalizable model performance. The proposed CNN model achieved an outstanding accuracy of 0.999, with a precision of 0.998, recall of 0.991, and F1 score of 0.994, outperforming baseline models such as Decision Tree with accuracy of 0.987 and Random Forest with accuracy of 0.981. These results highlight the CNN model’s strong potential for real-time, reliable stress monitoring using wearable sensors, making it a promising solution for digital health and well-being applications.