Abstract:ANNs have the ability to learn from data and recognize unstructured patterns. In face detection, ANNs can be used to recognize faces from images or videos. However, selecting the right ANN method is crucial for achieving…
optimal face detection performance. The results of this study are the highest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images with a comparison of the Learning Vector Quantization method is 96.25% (detection error = 0) with a classification architecture of the test data comparison - training data 70: 30, 20,000 iterations, calculation error tolerance 0.00001 and the number of hidden layer neurons = 5 while the lowest classification accuracy value of the backpropagation artificial neural network system in recognizing student facial images based on LVQ features is 85.42% (detection error = 34) with a classification architecture of the test data comparison - training data 70: 30, 10,000 iterations, calculation error tolerance 0.01 and the number of hidden layer neurons = 15
Abstract:The increasing volume of patient visits in primary healthcare facilities (such as community health centers and clinics) demands efficient resource management and scheduling systems. The inability to predict patient arrival…
al patterns often leads to long queues and suboptimal allocation of medical personnel. To overcome these issues, this study proposes the development of an intelligent framework based on Stacking Ensemble Learning to accurately classify and predict patient revisit frequency patterns. The proposed architecture integrates three heterogeneous base classification models (base learners), namely Logistic Regression (LR), Support Vector Machine (SVM) with non-linear Radial Basis Function (RBF) kernel projection, and Random Forest (RF). The probability predictions from these three base models are then combined into a secondary Logistic Regression based meta-learner to optimize the final decision and reduce the predictive bias of single models. Experiments were conducted using a dataset sourced from actual primary healthcare medical records, totaling 499 data entries. Given the highly imbalanced distribution of demographic data, the preprocessing stages were comprehensively designed, encompassing numerical scale feature standardization and the application of the SMOTE (Synthetic Minority Oversampling Technique) class balancing algorithm. Model testing was performed using a 5-fold stratified cross-validation scheme to ensure the robustness of the model's generalization. Comprehensive evaluation results proved that the Stacking Ensemble architecture achieved peak performance with an Accuracy of 88.4%, Precision of 85%, Recall of 90%, and an F1-Score of 0.88. Furthermore, curve analysis revealed an Area Under the Receiver Operating Characteristic (AUC-ROC) score of 0.961 and a Precision-Recall AUC of 0.95, consistently outperforming the capabilities of each individual baseline model. These findings confirm that combining hybrid machine learning models can produce highly stable and reliable predictions while minimizing false negative errors. This architecture holds massive potential for practical implementation as the foundation of a decision support system in managing operational services within primary healthcare facilities.
Abstract:Jambi traditional culinary is part of the region's cultural heritage that has historical value, distinctive flavors, and local identity. However, information about Jambi traditional culinary is still scattered across various…
ious media and has not been presented in a structured digital system, making it difficult for the public to obtain complete and accessible information. This study aims to design and develop a web-based Encyclopedia of Jambi Traditional Culinary as a medium for information, promotion, and cultural preservation. The system was developed using the Waterfall model, consisting of requirements analysis, system design, implementation, and testing. The application was developed using PHP with the CodeIgniter 4 framework and MySQL database. The search feature applies the Fuzzy Matching method using the similar_text() and levenshtein() functions to provide relevant results for inaccurate keywords. Black Box Testing and Fuzzy Matching testing were conducted to evaluate system functionality and search capability. The results show that all main system functions operated according to the specified requirements, with an average similarity score of 86.50% and a processing time of less than 10 milliseconds. The system successfully presents information on Jambi traditional culinary, including names, descriptions, ingredients, cooking procedures, categories, and images. Therefore, the system can facilitate public access to culinary information while supporting the digitalization and preservation of regional cultural heritage.
Abstract:Student mental health disorders have become an increasingly important issue due to their significant impact on academic performance and psychological well-being. Machine learning-based approaches offer a promising alternative…
ative for supporting early detection; however, only a limited number of studies have conducted comprehensive evaluations of various ensemble learning algorithms by simultaneously considering predictive performance, computational efficiency, and statistical significance. This study aims to compare ten classification algorithms, namely Random Forest, Extra Trees, Gradient Boosting, Hist Gradient Boosting, AdaBoost, XGBoost, LightGBM, CatBoost, Logistic Regression, and Stacking Ensemble, using 5-fold Stratified Cross-Validation. Model performance was evaluated using Accuracy, Precision, Recall, F1-Score, Receiver Operating Characteristic–Area Under the Curve (ROC-AUC), training time, inference time, confusion matrix, feature importance, as well as One-Way Analysis of Variance (ANOVA) and post-hoc Tukey’s Honestly Significant Difference (Tukey HSD) tests. The experimental results show that CatBoost achieved the highest classification performance, with an Accuracy of 84.86%, an F1-Score of 87.19%, a Recall of 88.03%, and an ROC-AUC of 0.9220. XGBoost delivered comparable predictive performance with a substantially shorter training time (3.92 seconds), while LightGBM was the most computationally efficient algorithm, requiring an average training time of only 0.85 seconds. In contrast, the Stacking Ensemble required the longest training time (215.41 seconds) without providing a statistically meaningful performance improvement over the boosting-based models. The ANOVA results revealed significant differences in ROC-AUC among the evaluated models (p < 0.001), whereas the Tukey HSD test indicated that most boosting algorithms did not differ significantly from one another. These findings provide practical guidance for selecting classification algorithms by balancing predictive performance and computational efficiency to support early mental health screening systems for university students.
Abstract:TELISIK+ 2026 merupakan program pengabdian kepada masyarakat berbasis komunitas yang dirancang untuk mengatasi ketimpangan akses persiapan Seleksi Nasional Penerimaan Mahasiswa Baru (SNPMB) sekaligus membekali peserta dengan…
ngan kapasitas akademik dan keterampilan masa depan. Program ini mengusung pendekatan high-tech meets high-touch yang memadukan pembelajaran berbantuan kecerdasan buatan dengan pendampingan tutor secara langsung, dan terdiri atas empat program yang saling terhubung: bantuan buku UTBK, kelas daring UTBK, penulisan ilmiah dan publikasi, serta pengembangan website edukasi berbasis AI. Kegiatan dilaksanakan secara daring pada 16 Januari–20 April 2026 menggunakan kerangka planning, organizing, actuating, controlling (POAC) dan dievaluasi secara deskriptif-evaluatif dengan kerangka RE-AIM. Hasil pelaksanaan menunjukkan 36 peserta menerima bantuan buku persiapan UTBK, 36 sesi pembelajaran terselenggara pada tujuh subtes bersama 18 tutor, serta 24 peserta menyelesaikan seluruh subtes tryout dengan rerata skor 616,3 dan reliabilitas instrumen yang tinggi (Cronbach's alpha 0,897). Sebanyak 34 peserta diterima di perguruan tinggi negeri melalui jalur SNBP 2026. Platform digital yang dikembangkan telah mengarsipkan 2.273 butir soal UTBK dan 1.950 butir soal SKD, serta menjangkau 551 pengguna aktif terverifikasi. Temuan ini menunjukkan bahwa integrasi pemerataan sumber belajar, mentoring humanistik, dan teknologi AI dapat membentuk ekosistem pendidikan komunitas yang inklusif, adaptif, dan berkelanjutan.
TELISIK+ 2026 is a community-based educational initiative designed to address inequality in access to preparation for the National Student Admission Selection (SNPMB) while equipping participants with academic capacity and future-oriented skills. The program adopts a high-tech meets high-touch approach that combines AI-supported learning with direct human mentoring, and comprises four interconnected programs: the UTBK Book Assistance Equity Program, the Online UTBK Learning Program, the Scientific Writing, Research, and Publication Program, and the AI-Based Educational Website Development Program. The activities were conducted online from January 16 to April 20, 2026, following the planning, organizing, actuating, and controlling (POAC) framework and evaluated through a descriptive-evaluative approach using the RE-AIM framework. The implementation resulted in 36 participants receiving UTBK preparation books, 36 learning sessions delivered across seven subtests by 18 tutors, and 24 participants completing all subtests of the practice test with a mean score of 616.3 and high instrument reliability (Cronbach's alpha of 0.897). A total of 34 participants were admitted to public higher education institutions through the 2026 SNBP pathway. The developed platform has archived 2,273 UTBK items and 1,950 SKD items, reaching 551 verified active users. These findings indicate that integrating equitable learning resources, human-centered mentoring, and AI technology can form an inclusive, adaptive, and sustainable community-based educational ecosystem.
Abstract:Stunting merupakan permasalahan yang berkaitan dengan pemenuhan kesehatan, gizi, pengasuhan, dan lingkungan yang mendukung tumbuh kembang anak sehingga pencegahannya memerlukan keterlibatan keluarga dan masyarakat. Kegiatan…
tan pengabdian kepada masyarakat ini bertujuan memberdayakan kader PKK melalui GERDARA (Gerakan Ramah Anak dan Perempuan) serta membentuk Pos Sahabat Aman sebagai wadah edukasi, komunikasi, pemberdayaan, dan pendampingan masyarakat dalam mendukung pencegahan stunting di Desa Sukamantri. Kegiatan menggunakan pendekatan pemberdayaan partisipatif yang meliputi identifikasi masalah dan potensi, sosialisasi dan edukasi, penguatan partisipasi kader, pembentukan Pos Sahabat Aman, pendampingan, serta evaluasi dan penyusunan rencana keberlanjutan. Peserta kegiatan terdiri atas 28 kader PKK dari tujuh dusun di Desa Sukamantri, sedangkan evaluasi dilakukan menggunakan lembar observasi keterlaksanaan GERDARA dan checklist capaian pembentukan Pos Sahabat Aman. Berdasarkan simulasi pengisian yang perlu diverifikasi dengan data lapangan, keterlaksanaan GERDARA mencapai 92,50% dengan kategori sangat baik dan capaian pembentukan Pos Sahabat Aman mencapai 90% dengan kategori sangat baik.
Stunting is a problem related to the fulfilment of children’s health, nutritional, caregiving, and supportive environmental needs; therefore, its prevention requires the involvement of families and communities. This community service activity aimed to empower Family Welfare Empowerment (PKK) cadres through GERDARA (Child- and Women-Friendly Movement) and to establish the Pos Sahabat Aman (Safe Friends Post) as a platform for community education, communication, empowerment, and assistance in supporting stunting prevention in Sukamantri Village. The activity employed a participatory empowerment approach comprising problem and potential identification, socialisation and education, strengthening cadre participation, establishment of the Pos Sahabat Aman, mentoring, as well as evaluation and the development of a sustainability plan. The participants consisted of 28 PKK cadres from seven hamlets in Sukamantri Village, while the evaluation was conducted using a GERDARA implementation observation sheet and a checklist of achievements in establishing the Pos Sahabat Aman. Based on a simulated completion that requires verification against field data, GERDARA implementation reached 92.50%, categorised as very good, while the achievement of establishing the Pos Sahabat Aman reached 90%, also categorised as very good.
Abstract:The Level 2 Working at Height (TKBT) training conducted by PT Batamindo Investment Cakrawala produced 22 certified employees across four divisions. However, post-training recommendations from the HRD unit identified the…
absence of a periodic monitoring mechanism for certificate validity periods and personal protective equipment usage, while all record keeping remained paper-based and spreadsheet-driven. This condition creates a compliance risk against Minister of Manpower Regulation Number 9 of 2016, as expired certificates may go undetected before employees are assigned to work at height. This community service program aims to strengthen the partner's occupational safety competency certification governance through the design, implementation, and mentoring of a web-based information system. The implementation method consists of six stages: situation analysis, requirements analysis, system design, construction, socialisation and training, and operational mentoring. The system was developed using a three-tier architecture and comprises four core modules: certificate record management, automated validity notification, divisional recapitulation dashboard, and digital document archiving. Program effectiveness was measured using a pre-test and post-test design with a 20-item instrument covering four knowledge domains, analysed using normalized gain. Functional testing was conducted using the black box method, while user acceptance was measured using the System Usability Scale. The results show that participants' average knowledge score increased from 51.4 in the pre-test to 86.4 in the post-test, with a normalized gain of 0.72 categorised as high. Black box testing achieved a 90 percent success rate and the System Usability Scale score reached 82.5, indicating good user acceptance.
Abstract:Sampah organik rumah tangga di Desa Sukarami, Kecamatan Seluma Selatan, selama ini belum dikelola secara optimal dan sebagian besar hanya dibuang atau dibakar, sementara peternak lokal menghadapi tekanan biaya akibat kenaikan…
aikan harga pakan ternak pabrikan. Kegiatan pengabdian ini bertujuan memberikan sosialisasi dan edukasi kepada warga mengenai budidaya maggot Black Soldier Fly (BSF) sebagai solusi ganda, yaitu mengurangi volume sampah organik sekaligus menyediakan sumber pakan ternak alternatif yang murah dan bergizi. Kegiatan dilaksanakan oleh Tim KKN Kelompok 46 dengan metode presentasi interaktif dan diskusi tanya jawab bersama warga. Materi yang disampaikan mencakup profil biologis maggot BSF (Hermetia illucens), siklus hidup, alur proses budidaya, kandungan gizi, alat dan bahan yang dibutuhkan, serta manfaat budidaya maggot dari aspek lingkungan, ekonomi, peternakan, dan sosial. Hasil kegiatan menunjukkan peningkatan pemahaman dan antusiasme warga terhadap potensi budidaya maggot BSF sebagai peluang usaha rumahan sekaligus solusi pengelolaan sampah yang berkelanjutan. Kegiatan ini diharapkan menjadi langkah awal bagi warga Desa Sukarami untuk mengembangkan budidaya maggot BSF secara mandiri di lingkungan masing-masing.
Household organic waste in Sukarami Village, South Seluma Sub-district, has not been optimally managed and is largely discarded or burned, while local livestock farmers face rising costs of manufactured feed. This community service activity aimed to socialize and educate residents on Black Soldier Fly (BSF) maggot cultivation as a dual solution for reducing organic waste volume while providing an affordable and nutritious alternative livestock feed source. The activity was carried out by KKN Group 46 through lectures, interactive presentations, and discussion sessions with residents. The material covered the biological profile of BSF maggots (Hermetia illucens), their life cycle, the cultivation process flow, nutritional content, required tools and materials, and the environmental, economic, livestock, and social benefits of maggot cultivation. The results showed an increase in residents' understanding and enthusiasm toward the potential of BSF maggot cultivation as a household business opportunity and a sustainable waste management solution. This activity is expected to be an initial step for Sukarami Village residents to independently develop BSF maggot cultivation in their respective environments.
Abstract:Usaha Mikro, Kecil, dan Menengah (UMKM) kuliner di Kota Tebing Tinggi memiliki potensi besar dalam menggerakkan perekonomian lokal. Namun, banyak pelaku usaha masih menghadapi kendala keterbatasan modal untuk mengembangkan…
an usahanya. Salah satu solusi pembiayaan yang sesuai dengan prinsip syariah adalah akad musyarakah, yaitu bentuk kemitraan modal antara dua pihak atau lebih dengan pembagian keuntungan dan risiko berdasarkan kesepakatan bersama. Sayangnya, pemahaman pelaku UMKM kuliner mengenai konsep dan mekanisme akad musyarakah masih rendah, sehingga skema pembiayaan berbasis syariah ini belum dimanfaatkan secara optimal, termasuk peluang kemitraan modal dengan Baitul Maal wat Tamwil (BMT) sebagai lembaga keuangan mikro syariah yang beroperasi di tingkat lokal. Kegiatan pengabdian masyarakat ini bertujuan memberikan penyuluhan kepada pelaku UMKM kuliner di Kota Tebing Tinggi mengenai konsep, prinsip, dan penerapan akad musyarakah sebagai alternatif penguatan kemitraan modal berbasis syariah, sekaligus membuka wawasan mengenai peluang kemitraan dengan BMT setempat. Metode pelaksanaan meliputi survei pendahuluan, penyuluhan dan sosialisasi melalui ceramah interaktif, diskusi tanya jawab, serta pembahasan contoh perjanjian kerja sama akad musyarakah. Hasil kegiatan menunjukkan adanya peningkatan pemahaman peserta terhadap konsep akad musyarakah, manfaat kemitraan modal berbasis syariah, serta mekanisme bagi hasil yang adil dan transparan. Kegiatan ini diharapkan mendorong terbentuknya sinergi antara perguruan tinggi, pelaku UMKM, dan BMT dalam mendukung pertumbuhan ekonomi kuliner yang inklusif, berkeadilan, dan berbasis prinsip syariah.
Culinary Micro, Small, and Medium Enterprises (MSMEs) in Tebing Tinggi City hold significant potential to drive the local economy. However, many business owners still face capital constraints that hinder business expansion. One Sharia-compliant financing solution is the musyarakah contract a form of capital partnership between two or more parties involving profit and risk sharing based on mutual agreement. Unfortunately, culinary MSME owners often lack understanding of the musyarakah concept and its mechanisms; consequently, this Sharia-based financing scheme remains underutilized, including opportunities for capital partnerships with Baitul Maal wat Tamwil (BMT) local Sharia microfinance institutions. This community service initiative aims to educate culinary MSME owners in Tebing Tinggi City on the concepts, principles, and application of musyarakah contracts as an alternative for strengthening Sharia-based capital partnerships, while also raising awareness about partnership opportunities with local BMTs. The implementation method involved a preliminary survey, educational outreach via interactive lectures and Q&A sessions, and a review of sample musyarakah cooperation agreements. The results indicate an improved understanding among participants regarding the musyarakah concept, the benefits of Sharia-based capital partnerships, and fair, transparent profit-sharing mechanisms. This activity is expected to foster synergy among universities, MSME owners, and BMTs, thereby supporting the growth of a culinary economy that is inclusive, equitable, and grounded in Sharia principles.
Abstract:Environmental education in early childhood plays an important role in developing children’s environmental care character through meaningful real-life experiences. This study aims to analyze the implementation of the Eco-Schools…
o-Schools program in fostering environmental care character among young children at POS PAUD Dahlia Mangli Randudongkal, Pemalang Regency. This research employed a descriptive qualitative approach, with data collected through observations, documentation, and field notes. The research subjects involved young children and teachers as facilitators of environment-based learning activities. The findings indicate that the Eco-Schools program was implemented through various concrete activities, including planting and caring for plants, watering plants, feeding animals, maintaining environmental cleanliness, and developing habits of disposing of waste properly. These activities provided children with direct experiences in understanding the relationship between humans and the environment while fostering values of responsibility, discipline, care, cooperation, and empathy toward living organisms. This study demonstrates that Eco-Schools can serve as an effective character-based learning strategy in early childhood education by integrating environmental education into the daily school culture. Sustainable implementation involving teachers, parents, and the community is essential to strengthen environmental awareness and care from an early age.