Claim Missing Document
Check
Articles

Found 25 Documents
Search

Pendampingan Pengembangan Soft Skills Ibu-Ibu Mekar di Era Society 5.0 di Kota Semarang Fidyah Yuli Ernawati; Hendrayanti, Silvia; Junaidi, Achmad; Sukarsono Sukarsono
Inovasi Sosial : Jurnal Pengabdian Masyarakat Vol. 2 No. 4 (2025): November : Inovasi Sosial : Jurnal Pengabdian Masyarakat
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/inovasisosial.v2i4.2521

Abstract

This community service activity aims to improve the soft skills capacity of the Ibu-Ibu Mekar community in Semarang City to face the demands of the Society 5.0 era. The program was implemented through four stages: needs assessment, participatory planning, training, and mentoring. The methods used included interactive lectures, group discussions, role-play, and contextual practice. The results of the activity showed significant improvements in participants' communication, creativity, collaboration, and problem-solving skills. In addition, several participants began to demonstrate informal leadership roles and greater involvement in community activities. These findings indicate that the experience-based participatory mentoring approach is effective in strengthening women's empowerment and preparing communities for socio-technological change. The program also helped participants develop adaptability to change, increased self-confidence, and facilitated the formation of broader social networks in their communities. Empowering women through soft skills development is expected to create a more resilient community in facing the challenges posed by digital transformation in the Society 5.0 era. This program emphasizes the importance of sustainable soft skills development as a foundation for community resilience in the Society 5.0 era.
Konstruksi Pengetahuan dalam Relasi Kuasa di Pondok Pesantren Juhairiyah; Maimun; Sa’dud Darain, A.; Fitriyah, Eliyatul; Junaidi, Achmad
Kartika: Jurnal Studi Keislaman Vol. 6 No. 1 (2026): Kartika: Jurnal Studi Keislaman (Februari)
Publisher : Lembaga Pendidikan Tinggi Nahdlatul Ulama (LPT NU) PCNU Kabupaten Nganjuk

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59240/kjsk.v6i1.451

Abstract

This study aims to examine how knowledge is constructed within the dynamics of power relations at Subulus Salam Islamic Boarding School. Using a qualitative method with a case study design, this research explores the interaction between formal and cultural authority structures and their influence on teaching practices and epistemological processes. Data were collected through in-depth interviews, participant observation, and documentation analysis, and were analyzed using an interactive model. The findings reveal that power relations in the pesantren are predominantly shaped by the central role of the kiai, whose authority determines educational policies, the selection of legitimate knowledge, and the direction of students’ intellectual development. This authoritative structure creates a learning environment in which students tend to adopt a passive stance and have limited opportunities for critical engagement. However, the study also identifies emerging initiatives within the institution to encourage intellectual participation, promote dialogical learning, and strengthen students’ critical thinking skills. These efforts indicate a shift toward more transformative and participatory educational practices. Overall, this research demonstrates that balancing traditional authority with inclusive learning strategies is essential for enhancing the quality of Islamic education in pesantren while maintaining their cultural identity.
Face Detection Based on Anti-Spoofing with FaceNet Method for Filtering Contract Cheating in Online Exam Ujianto, Erik Iman Heri; Diyasa, I Gede Susrama Mas; Junaidi, Achmad; Fatullah, Ryan Reynickha; Permanasari, Wahyu Melinda; Sari, Allan Ruhui Fatmah
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1167

Abstract

This study develops a reliable face-based verification system for online examinations by integrating a face recognition model with a blink detection mechanism to minimize the risk of identity fraud, also known as "contract cheating," and static image manipulation. "Contract cheating" refers to the practice where students hire others to complete their exams or assignments, compromising academic integrity. The growing reliance on online exams has raised concerns about the credibility of facial verification, as conventional methods are often vulnerable to spoofing attempts. To address this issue, the proposed system combines FaceNet, a deep learning model for identity recognition, with Dlib’s eye blink detection to provide a stronger layer of protection. The system was evaluated using 5-fold and 10-fold K-fold cross-validation, and additional testing assessed the impact of different video frame rates on performance. The results show that the system performs effectively in identifying legitimate users and detecting spoofing. FaceNet achieved an accuracy of 96.67 percent, outperforming DeepFace, which showed poorer results in precision, recall, and F1 score for some participants. Both models were evaluated on the same dataset, consisting of 150 images. The preprocessing pipeline, including face detection using MTCNN, cropping, and resizing, was applied consistently to both models to ensure a fair comparison of their performance. The system also demonstrated adaptability, achieving correct classifications at both 15 and 30 frames per second. Anti-spoofing tests based on the eye blink detection system detected all real faces, while static images were classified as spoofing. These results confirm that combining face recognition with liveness detection enhances the security of online examination platforms. The findings demonstrate the system's potential to reduce contract cheating and impersonation fraud, making online examinations more credible. Future work may focus on implementing adaptive thresholding for blink detection and integrating multimodal verification techniques to improve robustness across diverse real-world environments.
Model Hibrida Deret Waktu Adaptif untuk Peramalan Dinamis Permintaan Penumpang Kereta Api Menggunakan Kalman Filter Isworo, Muhamad Raihan Ramadhani; Tri Anggraeny, Fetty; Junaidi, Achmad
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 13 No 1: Februari 2026
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

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

Abstract

Peramalan permintaan penumpang kereta api yang akurat sangat penting untuk optimasi operasional dan perencanaan layanan transportasi PT KAI. Model peramalan konvensional sering menghadapi tantangan dalam menangani dinamika permintaan yang kompleks, terutama saat terjadi perubahan pola mendadak dan kejadian khusus seperti hari libur atau kejadian luar biasa. Penelitian ini mengusulkan model hibrida adaptif yang menggabungkan SARIMAX dan Prophet dengan optimasi bobot menggunakan Kalman Filter. Data yang digunakan adalah jumlah penumpang bulanan PT KAI DAOP 8 periode 2016-2023 yang mencakup fluktuasi musiman dan kejadian khusus yang mempengaruhi permintaan penumpang. Hasil menunjukkan bahwa model hibrida adaptif mencapai MAPE 4.32%, lebih baik dibandingkan dengan SARIMAX (7.72%) dan Prophet (6.06%). Kalman Filter berhasil mengoptimalkan bobot secara dinamis, meningkatkan kemampuan adaptasi model terhadap perubahan pola permintaan. Model ini menunjukkan performa akurasi dan stabilitas yang tinggi, serta dapat digunakan untuk meramalkan permintaan penumpang di masa depan dan memberikan rekomendasi untuk perencanaan kapasitas PT KAI yang lebih efektif.   Abstract Accurate forecasting of rail passenger demand is essential for operational optimization and planning of transportation services. Conventional forecasting models often face challenges in handling complex demand dynamics, especially when sudden pattern changes and special events occur. This study proposes an adaptive hybrid model combining SARIMAX and Prophet with weight optimization using the Kalman Filter. The data used is the monthly passenger number of PT KAI DAOP 8 from 2016 to 2023, which includes seasonal fluctuations and special events affecting passenger demand. The results show that the adaptive hybrid model achieved a MAPE of 4.32%, better than SARIMAX (7.72%) and Prophet (6.06%). The Kalman Filter successfully optimized the weights dynamically, improving the model's adaptability to changing demand patterns. This model demonstrates high accuracy and stability, and can be used to forecast future passenger demand and provide recommendations for more effective capacity planning for PT KAI.
Costs of Stroke Treatment Under National Health Insurance at Dr. Mohammad Hoesin General Hospital Ramadhoni, Pinto Desti; Junaidi, Achmad; Octavinawaty, Lenny; Apriyono, Apriyono; Oktaviandi, Ardy
Journal of Neurointervention and Stroke Vol. 1 No. 1: MAY 2025
Publisher : Neurointervention Working Group of Indonesian Neurological Association

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63937/jnevis-2025.11.1

Abstract

Highlight: Discrepancy in costs hospitalization Prevalence and risk factors ABSTRACT Introduction: Indonesia’s National Health Insurance/Jaminan Kesehatan Nasional (JKN) consider stroke a catastrophic disease due to its high treatment costs and healthcare system burden. Stroke patients need extended hospitalization, advanced procedures, and long-term rehabilitation, making it financially and socially burdensome. Endovascular procedures like mechanical thrombectomy and coiling improve clinical outcomes but are expensive. Objective: To outline the characteristics and hospitalization costs of stroke patients—both ischemic and hemorrhagic—covered by JKN at Dr. Mohammad Hoesin General Hospital, focusing on cost differences among conservative therapy, thrombolysis, mechanical thrombectomy, and coiling.  Method: A descriptive study with retrospective data collection was performed at a Type A hospital in South Sumatra, using patient records from January to April 2024. Result: Ischemic stroke was the most common type, with most patients aged 46-65 and male. Most patients stayed less than ten days on second-class wards. Conservative therapy was the most frequently used treatment. Hypertension and kidney disorders were the biggest risk factors and comorbidities. Hospital charges for mechanical thrombectomy and coiling exceeded INA-CBG (Indonesian Case Based Groups) reimbursement rates, highlighting a substantial gap between actual hospital costs and insurance coverage. For both stroke types, medication costs dominated total expenses. Conclusion: The significant gap actual hospital costs and INA-CBG reimbursement  rates for stroke treatments, especially for mechanical thrombectomy and coiling, may affect hospital policies on these interventions. To ensure long-term stroke management, revisions to reimbursement schemes should take into account the high costs associated with endovascular therapy.