A comparative study of YOLOv11-Nano, YOLOv11-Small, and YOLOv11-Medium for detecting empty parking spaces using a dataset of 5,725 parking area images. The study evaluates detection performance to identify the most effective YOLOv11 variant for smart parking applications.

A web-based campus shuttle tracking system for Universitas Negeri Semarang that uses smartphone GPS modules to improve shuttle visibility, operational information, and campus mobility services.

A Moodle LMS feature development study that implements an Activity Leaderboard to support gamified learning. The feature is designed to increase student motivation, participation, and visibility of learning activities through points, badges, and ranking mechanisms.

A software infrastructure study that presents the implementation of cron job scheduling, PHP scripting, and Cloud Panel integration to automate data processing and transfer workflows in cloud infrastructure.

An implementation-focused study on scheduled automation for data processing and transfer across cloud-fog computing systems using cron job mechanisms.

A community service publication focused on improving Generative AI literacy and practical usage skills for teachers at SMK Theresiana Bandungan through a participatory training approach.

A community engagement publication that discusses strategies to increase public awareness of illegal cigarettes in Kelurahan Bandungan, Kecamatan Bandungan, Kabupaten Semarang.

The study reviews empirical and conceptual research on the role of Generative Artificial Intelligence (GenAI) in vocational education, with emphasis on learners’ cognitive adaptation and psychological engagement.

Cerebral palsy (CP) is the leading cause of motor disability in children worldwide, yet access to continuous, high-quality physiotherapy remains limited, especially in low- and middle-income settings. This study presents the design and technical validation of a mobile physiotherapy assistant that leverages Google MediaPipe’s BlazePose for real-time human-pose estimation to support home-based rehabilitation for children with CP. The system adopts a client–server architecture with a Flutter front-end, Flask back-end, and MySQL database to deliver low-latency video processing and quantitative feedback. Rule-based algorithms transform 3-D body-landmark data into clinically relevant metrics such as joint angles, postural stability, and transitional movement parameters, enabling six progressive therapy stages inspired by the Gross Motor Function Measure. Internal testing demonstrated accurate kinematic measurements (mean absolute error <5°) and stable real-time performance (average 11–13 fps) across all therapy modules. These findings confirm the feasibility of using commodity devices for asynchronous, family-centered telerehabilitation.