Hyperparameter selection to obtain optimal accuracy results is an important factor in improving model performance in data science. This study discusses a comparison of two hyperparameter optimization methods, namely Grid Search and Random Search, in the Decision Tree Classifier algorithm using the Breast Cancer Wisconsin (Diagnostic) Dataset from the UCI Machine Learning Repository. The dataset contains 569 samples with 30 numerical features describing the characteristics of breast cancer cells, such as mean radius, texture, perimeter, area, and smoothness, which are classified into two classes, namely malignant and benign. This study uses the CRISP-DM approach, which includes the stages of business understanding, data understanding, data preparation, modeling, and evaluation. In the modeling stage, three testing scenarios were conducted, namely the Decision Tree model without tuning, the model with Grid Search optimization, and the model with Random Search optimization. Performance evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The results showed that hyperparameter optimization had a significant effect on model performance. The Decision Tree model without tuning produced an accuracy of 92.98%, while the model with Grid Search achieved the highest accuracy of 95.61%, and Random Search obtained an accuracy of 97.37%. Thus, it can be concluded that Grid Search provides the most optimal results in finding the best parameter combination, even though it requires longer computation time compared to Random Search.
Kemajuan teknologi informasi yang didukung oleh infrastruktur dan regulasi yang memadai memudahkan UMKM melakukan bisnis berbasis digital. Strategi e-commerce menjadi kunci keberhasilan pengembangan bisnis berbasis digital. Penelitian dilakukan dengan metode deskriptif kualitatif. Tujuan penelitian untuk menganalisis implementasi strategi e-commerce dalam meningkatkan daya saing Usaha Mikro, Kecil, dan Menengah (UMKM) di Indonesia. Sumber data yang dipergunakan adalah data primer dari hasil wawancara dan data sekunder yang bersumber dari Badan Pusat Statistik (BPS) serta artikel ilmiah. Hasil penelitian menunjukkan bahwa pertumbuhan E-commerce menunjukkan angka yang signifikan dan memberikan dampak positif dalam peningkatan daya saing UMKM seperti peningkatan omset penjualan, akses pasar menjadi lebih luas, kemudahan trasaksi, dan efisiensi biaya operasional. Akan tetapi, UMKM menghadapi tantangan dalam pengembangan e-commerce karena keterbatasan modal, kurangnya pelatihan, dan keterbatasan infrastruktur internet.
The small and medium-sized exhaust pipe industry in Purbalingga Regency is one of the region's leading sectors with high economic value, but it still faces obstacles in terms of metal coating and coloring quality. The conventional processes used are generally energy-intensive and produce chemical waste. This community service activity aims to improve the quality of metal plating and coloring on exhaust products through the application of green manufacturing technology based on energy efficiency and environmental friendliness. The methods used in this activity include the application of a green plating system with measured current control and technical training in the use of environmentally friendly plating materials. The results of the activity showed a significant improvement in the quality of the coating, where the gloss level increased by 25%, heat resistance reached 600°C without color change, and corrosion resistance doubled. In addition to improving product quality, this activity also increased the awareness of SME actors of the importance of sustainable production processes in accordance with the principles of green manufacturing.
Kelompok Wanita Tani (KWT) Dawis41 di Argorejo merupakan salah satu wadah bagi ibu-ibu untuk meningkatkan perekonomian desa melalui kegiatan peternakan kambing dan mentok. Kelompok ini menghadapi tiga masalah prioritas, yaitu belum adanya sumber listrik alternatif untuk penerangan kandang, belum tersedianya sistem pengelolaan pakan ternak mandiri, serta belum adanya pengolahan sampah ternak menjadi kompos. Tujuan dari kegiatan pengabdian ini adalah untuk meningkatkan produksi dan penerapan manajemen serta energi alternatif di KWT Dawis41. Kegiatan ini dilaksanakan melalui lima metode sistematis yang mencakup sosialisasi program, pelatihan, penerapan teknologi, pendampingan dan evaluasi, serta keberlanjutan program. Teknologi Tepat Guna (TTG) yang diimplementasikan adalah satu unit panel surya, satu unit mesin pencacah pakan, dan satu unit mesin pengaduk kompos. Program ini berhasil menyelesaikan permasalahan yang dihadapi mitra di bidang produksi dan manajemen. Penerapan TTG berhasil meningkatkan tingkat keberdayaan masyarakat dengan perincian 100% untuk TTG Solar Panel, 58% untuk TTG Pencacah Pakan Ternak, dan 45% untuk TTG Mixer Kompos. Pelatihan yang diadakan juga menunjukkan hasil positif, di mana 61% dari total 23 anggota yang hadir memberikan respons tingkat pemahaman yang baik terkait penggunaan TTG dan pengolahan limbah. Pelaksanaan program kemitraan masyarakat ini berhasil menyelesaikan permasalahan mitra dengan penerapan TTG yang efektif untuk meningkatkan efisiensi usaha dan keberdayaan kelompok.
The need for more healthy food is increasing in line with population growth and human awareness. The use of fertilizers to increase productivity is a must and the choice of using organic fertilizers can be a solution to answer that need. Human urine has the potential to become liquid organic fertilizer (LOF). The objective of the study was to compare the growth of B. chinensis treated with human urine LOF, NPK fertilizer, and well water as the control, and to determine the best concentration of LOF. This research was conducted experimentally using a complete randomized design (CRD) with three repetitions. The treatments applied in this study were the treatment of LOF concentration variations with doses of 5 ml/1, 20 ml/1, 35 ml/1, 50 ml/1 and 65 ml/1, NPK fertilizer 10 grams/1 and well water. The data from this study were tabled, then analyzed descriptively, ANOVA analysis, and DMRT. The fermented LOF increased N by 0.6%, P2O5 by 0.8%, K2O by 0.9%. It was concluded that the best treatment in the growth of B. chinensis, which was observed from the parameters of width of leaf, height, wet weight, dry weight of plants, was in the treatment of NPK fertilizer 10 grams/1 and followed by LOF treatment 65 ml/1. The number of leaves parameter was less representative in expressing the impacts of LOF treatment, NPK fertilizer, and even the Well Water Treatment.
