Abstract:Abstract: The literacy and numeracy achievements of elementary school students in Indonesia still face various challenges, despite showing an upward trend based on the results of the National Assessment. One cause is the…
implementation of conventional and less interactive learning models. This community service activity aims to develop and train the use of the interactive Learning Management System (LMS) kelaspetualang.com integrated with Scratch-based educational games to support literacy and numeracy learning at SD Negeri 067240 Medan. The implementation method used an interactive workshop based on practice-based learning that included needs analysis, material development, training, implementation, mentoring, and evaluation. The activity participants consisted of 20 teachers. The evaluation was conducted using a 1–5 Likert scale questionnaire to measure understanding, interest, and effectiveness of the activity. The results of the activity showed that 18 teachers successfully developed and uploaded game-based teaching materials to the LMS, while two teachers experienced technical difficulties with the device. The evaluation results showed a very good level of understanding and enthusiasm, especially regarding interest in developing game-based learning media, although further mentoring is still needed on technical aspects. This activity has been proven to improve teachers' digital competence and literacy and has the potential to enrich literacy and numeracy learning in an innovative way.
Keywords: educational; games; scratch; literacy; numeracy
Abstrak: Capaian literasi dan numerasi siswa sekolah dasar di Indonesia masih menghadapi berbagai tantangan, meskipun menunjukkan tren peningkatan berdasarkan hasil Asesmen Nasional. Salah satu penyebabnya adalah penerapan model pembelajaran yang masih konvensional dan kurang interaktif. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk mengembangkan dan melatih pemanfaatan Learning Management System (LMS) interaktif kelaspetualang.com yang terintegrasi dengan game edukatif berbasis Scratch guna mendukung pembelajaran literasi dan numerasi di SD Negeri 067240 Medan. Metode pelaksanaan menggunakan workshop interaktif berbasis practice-based learning yang meliputi analisis kebutuhan, pengembangan materi, pelatihan, implementasi, pendampingan, dan evaluasi. Peserta kegiatan terdiri atas 20 guru. Evaluasi dilakukan menggunakan kuesioner skala Likert 1–5 untuk mengukur pemahaman, minat, dan efektivitas kegiatan. Hasil kegiatan menunjukkan bahwa 18 guru berhasil mengembangkan dan mengunggah materi ajar berbasis game ke dalam LMS, sementara dua guru mengalami kendala teknis perangkat. Hasil evaluasi menunjukkan tingkat pemahaman dan antusiasme yang sangat baik, terutama pada minat pengembangan media pembelajaran berbasis game, meskipun masih diperlukan pendampingan lanjutan pada aspek teknis. Kegiatan ini terbukti meningkatkan kompetensi dan literasi digital guru serta berpotensi memperkaya pembelajaran literasi dan numerasi secara inovatif.
Kata kunci: pendidikan; permainan; Scratch; literasi; numerasi.
Abstract:Abstract: Digitalization 5.0 has opened wide opportunities for students to build digital-based startups. However, many student startups face challenges in financial management, developing a Minimum Viable Product (MVP),…
and ensuring business sustainability. This program aims to implement Digital Business Incubation as a strategy for developing student digital startups. The methods used include observation, tenant selection, interviews, and intensive mentoring for incubation program participants. As a result of the selection process, 14 businesses were chosen to be incubated, consisting of service-based and product-based ventures. The program is designed to provide entrepreneurship training, financial management workshops, business legality assistance, investor networking opportunities, and technological support. The outcomes of the program indicate that through digital incubation, average 77,91% of the participating students were able to enhance their digital entrepreneurship skills, strengthen their business models, and optimize the potential for business sustainability. Therefore, Digital Business Incubation has proven to be an effective mechanism for fostering the growth of student digital startups that are adaptive, innovative, and competitive in the digital economy era.
Keywords: bussiness digital, enterprise, student, service
Abstrak: Digitalisasi 5.0 telah membuka peluang luas bagi mahasiswa untuk membangun usaha rintisan (startup) berbasis digital. Namun, banyak startup mahasiswa menghadapi tantangan dalam hal pengelolaan keuangan, Minimum Viable Product, dan keberlanjutan usaha. Program ini bertujuan untuk mengimplementasikan program Digital Business Incubation sebagai strategi pengembangan startup digital mahasiswa. Metode yang digunakan meliputi observasi, seleksi tenant, wawancara, serta pendampingan intensif terhadap peserta program inkubasi. Dari hasil seleksi terpilih 14 usaha yang akan diinkubasi yang terdiri dari usaha yang bergerak dibidang jasa dan produk. Program ini dirancang untuk memberikan pembinaan kewirausahaan, pelatihan keuangan, pendampingan legalitas usaha, akses bersama investor, serta dukungan teknologi. Hasil program ini menunjukkan bahwa melalui inkubasi digital, rata rata 77,91% mahasiswa mampu meningkatkan keterampilan wirausaha digital, memperkuat model bisnis, serta mengoptimalkan potensi keberlanjutan usaha. Dengan demikian, Inkubasi bisnis digital terbukti menjadi mekanisme efektif dalam mendorong lahirnya startup digital mahasiswa yang adaptif, inovatif, dan berdaya saing di era ekonomi digital.
Kata kunci: bisnis, mahasiswa, jasa, startup digital
Abstract:Abstract: The development of artificial intelligence (AI) technology presents new opportunities in education, particularly in lesson planning. However, most vocational high school teachers in Palembang City, including those…
ose at SMK PGRI 2, still have limited knowledge and skills in utilizing AI. This problem is the background to the implementation of community service activities (PkM) with the aim of improving teacher competency in using Large Language Models (LLM) such as Gemini and ChatGPT to develop Lesson Implementation Plans (RPP). The methods used included needs surveys, interactive workshops, hands-on practice, and evaluation through post-tests and participant feedback. The results of the activity showed a significant increase, where teacher knowledge increased from 20% to 80% and the application of AI in lesson plans increased from 10% to 65%. The contribution of this activity lies in improving teachers' ability to utilize AI to develop lesson plans more effectively and providing a scientific basis for the application of LLM in lesson planning in vocational education.
Keywords: artificial intelligence, lesson planning, vocational school teachers
Abstrak: Perkembangan teknologi kecerdasan buatan (Artificial Intelligence) menghadirkan peluang baru dalam dunia pendidikan, khususnya dalam perencanaan pembelajaran. Namun, sebagian besar guru SMK di Kota Palembang, termasuk di SMK PGRI 2, masih memiliki keterbatasan dalam pengetahuan dan keterampilan pemanfaatan AI. Permasalahan ini melatarbelakangi dilaksanakannya kegiatan pengabdian kepada masyarakat (PkM) dengan tujuan meningkatkan kompetensi guru dalam menggunakan Large Language Models (LLM) seperti Gemini dan ChatGPT untuk menyusun Rencana Pelaksanaan Pembelajaran (RPP). Metode yang digunakan meliputi survei kebutuhan, workshop interaktif, praktik langsung, serta evaluasi melalui post-test dan umpan balik peserta. Hasil kegiatan menunjukkan adanya peningkatan signifikan, di mana pengetahuan guru meningkat dari 20% menjadi 80% dan penerapan AI dalam RPP naik dari 10% menjadi 65%. Kontribusi kegiatan ini terletak pada peningkatan kemampuan guru dalam memanfaatkan AI untuk menyusun RPP secara lebih efektif serta penyediaan dasar ilmiah bagi penerapan LLM dalam perencanaan pembelajaran di pendidikan vokasi.
Kata kunci: artificial intelligence, guru SMK, perencanaan pembelajaran
Abstract:Abstract: Monotonous learning in elementary schools, teachers do not use a learning model to improve numeracy literacy in elementary schools. To overcome this problem, namely by using a cooperative learning model. Cooperative…
ative learning model is a learning model in which students learn and work in small groups collaboratively with 4-5 members with heterogeneous group structures. This service aims to find out how to improve the application of cooperative learning models based on local wisdom in elementary schools in order to increase numeracy literacy. This method is a participatory action study, namely the implementation of the method by considering the existence of a problem study stage by involving students in elementary schools, as well as looking for the most appropriate alternative solution in overcoming the problem. The result of this service is students' understanding of the cooperative learning model which can be seen from discussions and questions and answers. In addition, the results of this service increase students' ability to work together to improve numeracy literacy.
Keywords: cooperative learning; local wisdom; numerical literacy
Abstrak: Pembelajaran di Sekolah Dasar yang monoton, guru tidak menggunakan sebuah model pembelajaran untuk meningkatkan literasi numerasi di Sekolah Dasar. Untuk mengatasi masalah tersebut yakni dengan menggunakan model cooperative learning. Model cooperative learning adalah suatu model pembelajaran dimana siswa belajar dan bekerja dalam kelompok kecil secara kolaboratif yang anggotanya 4–5 orang dengan struktur kelompok heterogen. Pengabdian ini bertujuan untuk mengetahui bagaimana meningkatkan penerapan model pembelajaran kooperatif berbasis kearifan lokal di sekolah dasar dalam rangka peningkatan literasi numerasi. Metode ini yaitu kaji tindak partisipatif yaitu pengimplementasian metode dengan mempertimbangkan adanya tahap kajian masalah dengan melibatkan siswa di Sekolah Dasar, serta mencari alternatif solusi yang paling tepat dalam mengatasi permasalahan. Hasil dari pengabdian ini adalah pemahaman siswa mengenai model pembelajaran Cooperative Learning yang dapat dilihat dari diskusi dan tanya jawab. Selain itu hasil dari pengabdian ini menambah kemampuan siswa dalam bekerja sama untuk meningkatkan literasi numerasi.
Kata Kunci : cooperative learning; kearifan lokal; literasi numerasi
Abstract:Abstract: Along development process of teaching activities in classroom has many challenges and demands. The increasing number information channels that can be accessed by students so that teacher often lags far behind the…
he updated information that has been received. Therefore teacher is forced to compensate by looking for various additional information. One of the learning strategies that has not been widely applied today is the e-learning strategy. Edmodo is a paid e-learning website that can be utilized teachers implementing learning strategies. But there are still many teachers who do not know and utilize it to fullest helping learning process in the classroom. The method used this training is lecture, discussion and direct practice. The lecture method and discussion are used to convey information relating the theories and benefits of applying edmodo. With direct practice, teachers will be more understanding in applying edmodo. It is expected that after this training, teachers are able compile learning materials in e-learning online so that teachers are not only fixated on conventional learning models. After that, the teacher can implement e-learning in the class he is teaching. Starting from listening material, making assignments given through assignments and online quizzes for the subjects they teach.
Keywords: Learning Strategy, e-Learning, Edmodo
Abstrak: Seiring perkembangan zaman proses kegiatan mengajar di kelas memiliki banyak tantangan dan tuntutan. Semakin banyaknya jalur informasi yang dapat diakses oleh siswa sehingga tidak jarang guru tertinggal jauh dari updatenya informasi yang sudah diterima oleh siswa. Oleh karena itu guru dipaksa harus mengimbanginya dengan mencari berbagai informasi tambahan. Salah satu strategi belajar yang belum banyak diterapkan saat ini adalah strategi belajar e-learning. Edmodo merupakan website e-learning tidak berbayar yang dapat dimanfaatkan oleh guru dalam menerapkan strategi belajar e-learning. Namun masih banyak guru yang belum mengetahui dan memanfaatkannya secara maksimal dalam membantu proses belajar mengajar di kelas. Metode yang digunakan dalam pelatihan ini yaitu ceramah, diskusi dan praktek langsung. Metode ceramah dan diskusi digunakan untuk menyampaikan informasi yang berkaitan dengan teori-teori dan manfaat menerapkan edmodo. Dengan praktek langsung, guru-guru akan lebih memahami dalam menerapkan edmodo. Diharapkan setelah diadakan pelatihan ini, guru-guru SMA IT Plus Bazma Brilliant mampu menyusun materi pembelajaran secara e-learning online sehingga guru tidak hanya terpaku pada model pembelajaran konvensional saja. Setelah itu, guru dapat mengimplementasikan pembelajaran e-learning di dalam kelas yang diampunya. Mulai dari menguploud materi, membuat tugas yang diberikan melalui fitur assignment dan kuis online untuk mata pelajaran yang diajarnya.
Kata kunci: Strategi Belajar, e-Learning, Edmodo
Abstract:Some housewives in Batam City do not work, relying solely on income from their husbands. During this time, housewives use their free time to socialize and have a good time with their neighbors without producing anything…
useful, so it's time to take advantage of these habits in order to produce something to support their family's economy. In order for income housewives to have new knowledge and abilities, crafting activities are carried out by using patchwork. This training is carried out to use patchwork to have more selling value such as hijab accessories. This training was carried out twice, which was given the understanding of housewives about the use of patchwork and then given the practice of learning by doing. In the implementation of the service carried out by practicing directly how to make a brooch with several models of patchwork. Aside from the guidance of making brooches from patchwork, researchers also provide assistance in managing financial management, so that in the future it can be used as a home business that can help support the family's economy. From the results of the evaluation at the service of the mothers, thousands of households have been able to make patchwork brooches with several variations and models
Abstract:Abstract: Student graduation is an urgent matter that is an indicator of the success of a university in producing its learning output. Several factors influence student graduation such as GPA, attendance, late taking credits,…
dits, and lack of student involvement in academic activities. The urgency of this research, universities need a method that is able to predict student graduation early so that it can provide academic intervention to students who have the potential to experience delays or fail to graduate. However, limited access to real academic data is often an obstacle in the development of predictive models, Therefore, this study aims to implement the XGBoost algorithm to predict student graduation based on several academic variables, namely the Cumulative Grade Point Average (GPA), the number of credits taken, the percentage of attendance, and the average grade of students. Model training using the XGBoost algorithm using a simulation dataset of 500 students who are labeled as graduating into two classes, namely passed and failed. The results of the study showed that the classification performance was very good with an accuracy value of 99.6%, Precision 99.7%, recall 99.4%.
Keywords: xgboost algorithm; data mining; student graduation
Abstrak: Kelulusan mahasiswa merupakan hal urgensi yang menjadi indikator keberhasilan sebuah perguruan tinggi dalam menghasilkan output pembelajarannya. Beberapa Faktor yang mempengaruhi kelulusan mahasiswa seperti IPK, kehadiran, keterlambatan pengambilan SKS, serta kurangnya keterlibatan mahasiswa dalam aktifitas akademik. Yang menjadi urgensi penelitian ini, Perguruan tinggi memerlukan suatu metode yang mampu memprediksi kelulusan mahasiswa secara dini sehingga dapat memberikan intervensi akademik kepada mahasiswa yang berpotensi mengalami keterlambatan atau tidak lulus. Namun, keterbatasan akses terhadap data akademik riil sering menjadi kendala dalam pengembangan model prediksi, Oleh karena itu, penelitian ini bertujuan mengimplementasikan algoritma XGBoost untuk memprediksi kelulusan mahasiswa berdasarkan beberapa variabel akademik, yaitu Indeks Prestasi Kumulatif (IPK), jumlah SKS yang ditempuh, persentase kehadiran, dan nilai rata-rata mahasiswa. Pelatihan model menggunakan algoritma XGBoost dengan menggunakan dataset simulasi 500 mahasiswa yang diberi label kelulusan menjadi dua kelas yaitu lulus dan tidak lulus. Hasil penelitian menunjukan bahwa performance klasifikasi yang sangat baik dengan nilai accurasi sebesar 99,6%, Precision 99,7%, recall 99,4%.
Kata kunci: algoritma xgbosst; kelulusan mahasiswa; penambangan data
Abstract:Abstract: Manual meeting documentation risks losing important information due to cognitive fatigue. Although automated summarization models have evolved, integrated end-to-end systems for Indonesian spoken language remain…
n highly limited. This study aims to design and evaluate an end-to-end automated meeting summarization architecture that directly integrates Automatic Speech Recognition (ASR) via OpenAI Whisper for transcription and the IndoT5 language model for abstractive summarization. IndoT5 was fine-tuned using a dataset of 486 Indonesian spoken language transcript pairs. Testing was conducted on a CPU infrastructure using MP4, MP3, and WAV formats. Results show the optimal fine-tuning configuration significantly improved accuracy, achieving ROUGE-1 (0.4167), ROUGE-2 (0.1973), and ROUGE-L (0.2701) scores. Computationally, the system achieved a Real-Time Factor below 1, processing data faster than the actual recording duration. Conclusively, integrating Whisper and IndoT5 shows potential in producing coherent meeting summaries with lightweight computational overhead, making it viable for local infrastructure implementation to ensure data privacy.
Keywords: abstractive summarization; ASR; end-to-end pipeline; IndoT5; real-time factor
Abstrak: Dokumentasi rapat manual rentan menghilangkan informasi penting akibat keterbatasan kognitif. Meskipun model peringkas otomatis telah berkembang, implementasi sistem terintegrasi (end-to-end) khusus percakapan lisan berbahasa Indonesia masih sangat terbatas. Penelitian ini bertujuan merancang dan mengevaluasi arsitektur peringkas rapat otomatis end-to-end yang mengintegrasikan langsung Automatic Speech Recognition (ASR) melalui OpenAI Whisper untuk transkripsi dan model bahasa IndoT5 untuk peringkasan abstraktif. Adaptasi domain dilakukan melalui fine-tuning IndoT5 menggunakan 486 pasang dataset transkrip lisan berbahasa Indonesia. Pengujian pada infrastruktur CPU menggunakan format MP4, MP3, dan WAV. Hasil pengujian menunjukkan konfigurasi fine-tuning optimal berhasil meningkatkan akurasi, dengan skor ROUGE-1 (0,4167), ROUGE-2 (0,1973), dan ROUGE-L (0,2701). Sistem mendemonstrasikan efisiensi komputasi dengan nilai Real-Time Factor di bawah 1, mengindikasikan waktu pemrosesan lebih cepat dari durasi rekaman asli. Kesimpulannya, integrasi Whisper dan IndoT5 menunjukkan potensi dalam menghasilkan ringkasan yang koheren dengan beban komputasi ringan, sehingga layak diimplementasikan pada infrastruktur lokal organisasi untuk menjaga privasi data.
Kata kunci: ASR; end-to-end pipeline; IndoT5; peringkasan abstraktif; real-time factor
Abstract:Abstract: The growing intensity of cyber attacks, marked by rapid, large-scale, automated, and adaptive execution, requires analytical methods that represent the diversity of network environments, including variations in…
target platforms such as IoT, traditional networks, and hybrid infrastructures. This study compares machine learning models for cyber attack classification under heterogeneous environmental conditions and formulates a conceptual optimization framework based on model performance. Four publicly available benchmark datasets were used, namely UNB CIC IoT 2023, UNB CIC IDS-2018, UNSW-NB15, and a Kaggle cyber security attacks dataset, comprising approximately 40,000 to over 3.6 million records and 25 to 80 features across IoT, conventional, and mixed network environments. Random Forest, XGBoost, Multilayer Perceptron, and Transformer were implemented within a unified pipeline involving preprocessing, feature selection, and Bayesian Optimization-based hyperparameter tuning. All models achieved F1-score and Cohen's Kappa above 96%, with XGBoost performing best (97.80%, 97.26%), followed by Random Forest (97.78%, 96.96%) and Transformer (97.44%, 96.82%), while MLP scored lowest (96.74%, 96.00%), a gap below one percentage point. Confusion matrix analysis revealed persistent misclassification in minority and overlapping attack classes, informing a proposed adaptive cyber attack simulation optimization framework.
Keywords: cyber attacks; optimization; machine learning; environmental variability.
Abstrak: Meningkatnya intensitas serangan siber yang berlangsung cepat, masif, otomatis, dan adaptif menuntut pendekatan analitis yang merepresentasikan keragaman lingkungan jaringan, termasuk perbedaan karakteristik platform sasaran seperti Internet of Things (IoT), jaringan konvensional, dan infrastruktur hibrida. Penelitian ini membandingkan model machine learning untuk klasifikasi serangan siber pada kondisi lingkungan heterogen, sekaligus menyusun kerangka optimasi konseptual berdasarkan performa model. Empat dataset benchmark publik digunakan, yaitu UNB CIC IoT 2023, UNB CIC IDS-2018, UNSW-NB15, serta dataset Kaggle cyber security attacks, dengan jumlah data berkisar 40.000 hingga lebih dari 3,6 juta rekaman dan 25 sampai 80 fitur, mewakili lingkungan IoT, konvensional, dan campuran. Random Forest, XGBoost, Multilayer Perceptron, dan Transformer diimplementasikan melalui pipeline terpadu mencakup pra-pemrosesan, seleksi fitur, dan optimasi hyperparameter berbasis Bayesian Optimization. Seluruh model mencapai F1-score dan Cohen's Kappa di atas 96%, dengan XGBoost menunjukkan performa terbaik (97,80%, 97,26%), diikuti Random Forest (97,78%, 96,96%) dan Transformer (97,44%, 96,82%), sementara MLP mencatat skor terendah (96,74%, 96,00%), dengan selisih kurang dari satu poin persentase. Analisis confusion matrix mengungkap misklasifikasi yang konsisten pada kelas minoritas dan serangan dengan karakteristik serupa, yang menjadi dasar kerangka optimasi simulasi serangan siber adaptif yang diusulkan.
Kata kunci: serangan siber; optimasi; machine learning; variabilitas lingkungan
Abstract:Abstract: Accurate bone age estimation is essential for monitoring pediatric growth, diagnosing endocrine disorders, and supporting clinical decision-making. Although deep learning has improved prediction accuracy, limited…
ed studies have systematically examined how increasing model depth affects performance and reliability. This study evaluates the effectiveness of progressively deeper convolutional neural networks, specifically EfficientNet variants B0 to B5, for bone age estimation from hand radiographs. Experiments were conducted using 12,611 hand X-ray images from the RSNA Pediatric Bone Age Challenge dataset on Kaggle. To ensure fair comparison, all models were trained using a unified and consistent training pipeline. Model performance was evaluated using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), and Pearson correlation coefficient. The results show a consistent improvement in prediction accuracy as model depth increases. Among the evaluated models, EfficientNet-B5 achieved the best performance, with an MAE of 21.5 months, MAPE of 6.23%, CCC of 0.9148, and Pearson’s r of 0.9203. These findings confirm that model scaling plays a critical role in enhancing prediction robustness and clinical reliability. Future work should emphasize external validation across diverse populations and incorporate interpretability techniques, such as Grad-CAM, to improve clinical transparency and trust.
Keywords: bone age prediction; deep learning; model evaluation; clinical validation
Abstrak: Estimasi usia tulang yang akurat sangat penting untuk memantau pertumbuhan anak, mendiagnosis gangguan endokrin, dan mendukung pengambilan keputusan klinis. Meskipun pembelajaran mendalam telah meningkatkan akurasi prediksi, studi yang secara sistematis meneliti bagaimana peningkatan kedalaman model memengaruhi kinerja dan keandalan masih terbatas. Studi ini mengevaluasi efektivitas jaringan saraf konvolusional yang semakin dalam, khususnya varian EfficientNet B0 hingga B5, untuk estimasi usia tulang dari radiografi tangan. Eksperimen dilakukan menggunakan 12.611 gambar sinar-X tangan dari dataset RSNA Pediatric Bone Age Challenge di Kaggle. Untuk memastikan perbandingan yang adil, semua model dilatih menggunakan alur pelatihan yang terpadu dan konsisten. Kinerja model dievaluasi menggunakan Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), dan koefisien korelasi Pearson. Hasil menunjukkan peningkatan yang konsisten dalam akurasi prediksi seiring dengan peningkatan kedalaman model. Di antara model yang dievaluasi, EfficientNet-B5 mencapai kinerja terbaik, dengan MAE sebesar 21,5 bulan, MAPE sebesar 6,23%, CCC sebesar 0,9148, dan Pearson’s r sebesar 0,9203. Temuan ini menegaskan bahwa penskalaan model memainkan peran penting dalam meningkatkan optimasi prediksi dan keandalan klinis. Penelitian selanjutnya dapat menekankan validasi eksternal di berbagai populasi dan menggabungkan teknik interpretasi, seperti Grad-CAM, untuk meningkatkan transparansi dan kepercayaan klinis.
Kata kunci: prediksi usia tulang; deep learning; evaluasi model; validasi klinis