Article Per Year (5 Year)
p-Index From 2021 - 2026
2.049
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal ICT : Information Communication & Technology JURNAL MUTIARA NERS Jurnal Kejaora (Kesehatan Jasmani dan Olahraga) Gladi : Jurnal Ilmu Keolahragaan Journal of Physical Education and Sports Journal of Physical Education Health and Sport "Indonesian Journal for Physical Education and Sport "
Rumini
Unknown Affiliation
Humanities Computer Science & IT Education Engineering Nursing Physics Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Applying a Deep Learning Pedagogical Model in Physical Education and Health Learning Rahmadani, Amalia Rizki; Rumini
Gladi : Jurnal Ilmu Keolahragaan Vol. 17 No. 01 (2026): Gladi : Jurnal Ilmu Keolahragaan
Publisher : Universitas Negeri Jakarta Postgraduate of Physical Education Departments

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/GJIK.171.02

Abstract

This study examines the implementation of the Deep Learning model in Physical Education, Sports, and Health (PJOK) learning at YSKI Christian High School, Semarang. Deep learning emphasizes meaningful, reflective, and contextual learning experiences that foster students’ higher-order thinking and real-life application of physical activity. A descriptive qualitative approach was employed involving PJOK teachers and Grade XI students. Data were collected through interviews, observations, documentation, and student questionnaires and analyzed using triangulation of sources, methods, and time. The findings indicate that the Deep Learning model is implemented through three core principles: Meaningful Learning, Mindful Learning, and Joyful Learning. These principles enhance students’ cognitive engagement, understanding of learning purposes, and ability to apply physical activities in daily life. Institutional support, technological readiness of teachers and students, and a supportive learning environment emerged as key facilitating factors. However, limited instructional time and variations in students’ digital literacy remain challenges. The use of digital platforms such as Kahoot, Quizizz, and SiSKY significantly increases learning interactivity and motivation. Overall, the Deep Learning model contributes positively to improving PJOK instructional quality and students’ critical, collaborative, and reflective skills.
Physical Condition Analysis of Junior High School Volleyball Players: A Study on the Extracurricular of Junior High School 3 Semarang Ahmad Kholik Husain; Rumini
Journal of Physical Education Health and Sport Vol. 12 No. 2 (2025)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/jpehs.v12i2.37940

Abstract

Physical conditioning is an essential of volleyball play, involving strenght, speed, endurance, agility coordination and flexibility. But the gym program of schools extracuricular is crushed in a below priority with respect to technical training. This research aimed to describe the reality of physical fitness in general on volleyball extracuricular participants at Junior High School 3 Semarang objectively, considering gender category. The purpose of this study was to determine the global physical fitness profile of students who participated in extracurricular volleyball and contrast athletic performance between male and female participants. This research was quantitative in nature with 62 students selected through total sampling technique. Physical accomplishment was measured in muscle strength, endurance, power, speed,flexibility,agility, coordination and balance. The raw scores of each subscale were transformed into T-scores and classified into five skill levels based on predefined normative criteria. The findings indicate that subjects had low physical fitness levels. For the women, 40% achieved a moderate level and 24% an inferior level; 20 and 8% reached the high and very high level respectively and only 8% were found to be at the very poor level. The trends for men were along the same line, as 34.2% reached to poor and 31.5% hit moderate weight classes. In contrast, 26.4% of them accomplished the High level while at the Very high level 7.9% and nobody attained to Very poor level. Extracuricular participants physical conditioning status is between fair to poor, suggest a more structured, comprehensive training program focusing on both physical and technical development in order to excel in maximal performance of vollyball.
Implementasi Deep Learning Algoritma Convolutional Neural Network untuk Klasifikasi Kesegaran Buah dan Sayur Latifa, Annisa; Hikmah, Nor; Kurniawan, Hendra; Rohmat Hidayat, Kardilah; Larasati, Niken; Rumini
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 2: April 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2026131

Abstract

Buah dan sayur merupakan sumber utama vitamin, mineral, dan serat yang sangat penting untuk menjaga kesehatan tubuh. WHO merekomendasikan konsumsi sebesar 400 gram per hari untuk gizi seimbang. Namun, kualitas dan kesegaran buah dan sayur sering kali sulit diidentifikasikan secara manual, terutama dalam skala besar, karena metode tradisional memiliki keterbatasan akurasi dan rentan terhadap kesalahan manusia. Kemajuan kecerdasan buatan, khususnya deep learning, memberikan solusi inovatif dalam klasifikasi citra. Convolutional Neural Network (CNN), telah terbukti efektif dalam pengenalan dan klasifikasi gambar. Penelitian ini menerapkan CNN dengan arsitektur Inception V3 dalam mengklasifikasikan kesegaran buah dan sayuran menjadi dua kategori utama, yaitu segar dan busuk. Model dikembangkan menggunakan dataset yang terdiri dari 11. 441 citra yang gambar, yang dibagi ke dalam tiga subset utama, yaitu data latih (±44.38%), data validasi (±11.07%), dan data uji (±44.55%). Dengan data kelas terbagi 14 kelas. Hasil penelitian  dengan menggunakan confusion matric  nilai accuracy sebesar 95%  dan hasil evaluasi validation accuracy  sebesar 100% pada epoch ke-4, dengan val_loss terendah sebesar 0.0260  serta nilai MAE  0.26, yang artinya model memiliki kinerja yang sangat baik  dalam mendekteksi kesegaran  buah dan sayur. Penelitian lanjutan disarankan untuk meningkatkan generalisasi model dengan menggunakan dataset yang lebih beragam, dan mengintegrasikan komputasi tepi (edge computing) untuk inspeksi kualitas langsung di Lokasi.   Abstract Fruits and vegetables are primary sources of vitamins, minerals, and fiber, which are essential for maintaining a healthy body. The World Health Organization (WHO) recommends a daily intake of 400 grams for a balanced diet. However, the quality and freshness of fruits and vegetables are often difficult to identify manually, especially at large scale, as traditional methods have limitations in accuracy and are prone to human error. Advances in artificial intelligence, particularly deep learning, offer innovative solutions in image classification. Convolutional Neural Networks (CNNs) have proven effective in image recognition and classification tasks. This study implements a CNN using the Inception V3 architecture to classify the freshness of fruits and vegetables into two main categories: fresh and rotten. The model was developed using a dataset consisting of 11,441 images, divided into three main subsets: training data (approximately 44.38%), validation data (approximately 11.07%), and test data (approximately 44.55%), with 14 distinct classes. The results of the study, based on the confusion matrix, show an accuracy of 95%, and a validation accuracy of 100% at the 4th epoch, with the lowest validation loss recorded at 0.0260 and a MAE of 0.26. These results indicate that the model performs very well in detecting the freshness of fruits and vegetables. Further research is recommended to improve model generalization using more diverse datasets and to integrate edge computing for on-site quality inspection.
Co-Authors Agus Widodo Suripto Ahmad Kholik Husain Alfian Agung Putranto Annisa Latifa Ardana, Dimas Setiya Cahyo Yuwono Hadi Arifin Hendra Kurniawan Hermawan Pamot Raharjo Hikmah, Nor HINGIS MOUDINA ENGGAR SUKMA Justina Purwarini, Justina Laeli Prastiwi, Catur Anggara Muhammad Zidane Nuralif Niken Larasati Norhikmah Norhikmah Rachudu, Arna Ridho Rahmadani, Amalia Rizki Rohmat Hidayat, Kardilah Santi Wijayanti, Dwi Gansar Tandiyo Rahayu Vidaliya Rizki Apriliana