Claim Missing Document
Check
Articles

Found 14 Documents
Search

Implementasi Website Desa Pucang, Bawang, Banjarnegara Untuk Promosi Desa Dan Peningkatan Layanan Publik Susanto, Ajib; Sudaryanto, Sudaryanto; Kusumawati, Yupie; Budiman, Fikri
Jurnal Pengabdian kepada Masyarakat Nusantara Vol. 4 No. 4 (2023): Jurnal Pengabdian kepada Masyarakat Nusantara (JPkMN)
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Desa Pucang, Kec. Bawang, Kab. Banjarnegara adalah desa target pendampingan Abinayamuda Disporapar Provinsi Jawa Tengah. Kegiatan desa, produk UMKM desa, kegiatan karang taruna, badan usaha milik desa (BUMDES), layanan masyarakat dan berbagai potensi desa selama ini masih dikelola belum memanfaatkan teknologi informasi dengan maksimal, sehingga informasi tentang desa dan kegiatannya masih sering belum tersampaikan ke masyarakat yang membutuhkan serta informasi desa Pucang di internet belum tersebar dengan baik, hal ini diperlukan media yang memudahkan untuk dikelola dan tersebar dengan cepat salah satunya dengan mewujudkan web desa dan pemanfaatan media sosial.Tujuan yang ingin dicapai yaitu mengembangkan dan mengoptimalkan website desa Pucang, Kec. Bawang, Kab. Banjarnegara untuk peningkatan layanan publik dan layanan informasi yang dibutuhkan masyarakat saat ini. Hasil sudah dicapai berupa website desa untuk layanan publik, informasi desa, promosi dan penjualan produk UMKM desa.
Hiragana Character Classification Using Convolutional Neural Networks Methods based on Adam, SGD, and RMSProps Optimizer Mulyono, Ibnu Utomo Wahyu; Kusumawati, Yupie; Susanto, Ajib; Sari, Christy Atika; Islam, Hussain Md Mehedul; Doheir, Mohamed
Scientific Journal of Informatics Vol. 11 No. 2: May 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i2.2313

Abstract

Purpose: Hiragana image classification poses a significant challenge within the realms of image processing and machine learning. Despite advances, achieving high accuracy in Hiragana character recognition remains elusive. In response, this research attempts to enhance recognition precision through the utilization of a Convolutional Neural Network (CNN). Specifically, the study explores the efficacy of three distinct optimizers like Adam, Stochastic Gradient Descent with Momentum (SGDM), and RMSProp in improving Hiragana character recognition accuracy. Methods: This research adopts a systematic approach to evaluate the performance of a Convolutional Neural Network (CNN) in the context of Hiragana character recognition. A meticulously prepared dataset is utilized for in-depth testing, ensuring robustness and reliability in the analysis. The study focuses on assessing the effectiveness of three prominent optimization methods: Stochastic Gradient Descent (SGD), RMSProp, and Adam. Result: The results of the model performance evaluation show that the highest accuracy was obtained from the RMSP optimizer with an F1-Score reaching 99.70%, while the highest overall accuracy was 99.87% with the Adam optimizer. The analysis is carried out by considering important metrics such as precision, recall, and F1-Score for each optimizer. Novelty: The performance results of the developed model are compared with previous studies, confirming the effectiveness of the proposed approach. Overall, this research makes an important contribution to Hiragana character recognition, by emphasizing the importance of choosing the right optimizer in improving the performance of image classification models.
SISTEM MONITORING SUHU DAN KELEMBABAN KANDANG AYAM BERBASIS INTERNET OF THINGS (IOT) Novita Kurnia Ningrum; Kusuma, Tiara Widya; Wahyu Mulyono, Ibnu Utomo; Susanto, Ajib; Kusumawati, Yupie
Elkom: Jurnal Elektronika dan Komputer Vol. 16 No. 2 (2023): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v16i2.1153

Abstract

Broiler chickens are livestock whose growth is influenced by environmental temperature. The temperature of the chicken coop that is not suitable can affect the decrease in productivity and cause death in broiler chickens, so that the temperature setting of the cage must be considered. The design of this temperature and humidity monitoring system uses a nodemcu ESP8266 microcontroller and an arduino uno. If the measured temperature exceeds the set temperature limit, the system will send an SMS to the smartphone so that the cage officer can take appropriate action.
Data-Driven K-Means Clustering Analysis for Stunting Risk Profiling of Pregnant Women Nazella, Desvita Dian; Hadi, Heru Pramono; Al Zami, Farrikh; Ashari, Ayu; Kusumawati, Yupie; Suharnawi, Suharnawi; Megantara, Rama Aria; Naufal, Muhammad
Building of Informatics, Technology and Science (BITS) Vol 7 No 3 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i3.8415

Abstract

Stunting in children is influenced by maternal health conditions during pregnancy. This study aims to classify pregnant women to prevent stunting based on clinical, demographic, and environmental factors using the K-Means Clustering algorithm. A total of 229 data from the Primadona application (Disdalduk KB Kota Semarang) were analyzed using 14 normalized variables. The optimal number of clusters was determined using the Elbow Method and validated using the Silhouette Score, Davies-Bouldin Index, and Calinski-Harabasz Index. The Kruskal-Wallis test was performed to verify differences between clusters. This study resulted in seven clusters with different profiles, with a Silhouette Score of 0.134, Davies-Bouldin Index of 1.509, and Calinski-Harabasz Index of 29.54. These values ​​indicate that the cluster structure is formed and reflects the variation in risk for pregnant women, although there is overlap due to differences in characteristics between individuals. The clustering successfully differentiated pregnant women with low to high risk, influenced by health and environmental factors. This study proves the effectiveness of K-Means in identifying stunting risk patterns in pregnant women and supports more targeted interventions, such as nutritional counseling, disease risk monitoring, education on cigarette smoke exposure, and referrals. Limitations of this study include the unbalanced distribution of data between and the use of cross-sectional data. Future research is recommended to improve pre-processing and compare other clustering methods such as K-Medoids or DBSCAN for more precise stunting risk analysis.