Dila Puspita Dewi
Unknown Affiliation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Peran Rumah Sakit Terhadap Pecandu Narkotika Dalam Rehabilitasi Medis Dila Puspita Dewi
JISPENDIORA Jurnal Ilmu Sosial Pendidikan Dan Humaniora Vol. 1 No. 1 (2022): April : Jurnal Ilmu Sosial, Pendidikan Dan Humaniora (JISPENDIORA)
Publisher : Badan Penerbit STIEPARI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56910/jispendiora.v1i1.572

Abstract

The reasons for the use of narcotics due to heavy work, socio-economic abilities, and environmental pressures from co-workers are the trigger factors for narcotics abuse in the worker group. Rehabilitation programs are needed to free addicts from narcotics dependence so that the responsibility of medical rehabilitation institutions against narcotics abuse is very necessary. The formulation of the problem in this study is how is the responsibility of Bhayangkara Hospital Semarang towards members of the Police who are addicted to narcotics abuse in medical rehabilitation? The author uses a juridical and empirical approach. Data analysis used descriptive qualitative analysis. The results showed that: 1) Hospital responsibilities in the medical rehabilitation process include assessment, preparation of rehabilitation plans, outpatient or inpatient rehabilitation programs and post-rehabilitation programs. Hospitalization is in accordance with the rehabilitation plan that has been prepared taking into account the results of the assessment which includes medical intervention. 2) Obstacles in the implementation of rehabilitation are poor behavior, dealers or dealers are not necessarily users (pure dealers), lack of medical personnel, inadequate facilities, poor coordination in the security sector between the police and the rehabilitation center so that if it occurs conflicts between residents and the presence of residents who make a fuss, the rehabilitation center has difficulty in overcoming these problems. The solution to the problems above is to reorganize the behavior of addicts with regular monitoring, further investigation and investigation are needed to find out whether they are dealers or just users (addicts), adding medical personnel, adding facilities for rehabilitation homes, improving conditions between the police and rehabilitation centers. in this case Bhayangkara Hospital.
Analisis Epoch dan Learning Rate untuk Meningkatkan Akurasi Pemrosesan Data Jilbab Instan dan Non-Instan di Teachable Machine: Analisis Epoch dan Learning Rate untuk Meningkatkan Akurasi Pemrosesan Data Jilbab Instan dan Non-Instan di Teachable Machine Dila Puspita Dewi; Zaehol Fatah
Jurnal Mahasiswa Teknik Informatika Vol. 4 No. 1 (2025): Jurnal Jamastika, Volume 4 Nomor 1 April 2025
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/jamastika.v4i1.3501

Abstract

Penelitian ini mengkaji cara menggunakan Teachable Machine untuk mengoptimalkan pemrosesan data penggunaan hijab non-instan dan instan dengan menganalisis nilai learning rate dan epoch. Tujuan dari penelitian ini adalah menerapkan teknik pembelajaran transfer pada Teachable Machine untuk meningkatkan akurasi pengenalan penggunaan hijab. Dataset penggunaan hijab instan dan non instan Detection merupakan data gambar yang digunakan dalam penelitian ini.Data yang digunakan pada gambar dataset penelitian ini adalah dataset hijab instan dan non- instan yang diperoleh dari sumber internet dengan menggunakan metode web scraping pada platform internet di google image dan pinterest. Dalam pengumpulan data, dilakukan Scraping untuk mengunduh hasil pencarian pada platform. proses pelatihan model di Teachable Machine, agar model dapat mengenali dan mengklafikasikan hijab dengan akurasi yang tinggi sehingga dengan cara ini, dapat dengan mudah menemukan hijab yang sesuai dengan preferensi mereka. Kata Kunci: Hijab Instan dan Non-Instan, Teachable Machine, Machine Learning   Teachable machine is a platform that makes it easy for anyone to design machine learning models. The aim of this research is to apply transfer learning techniques on Teachable Machine to increase the accuracy of recognizing the use of the hijab. The dataset of instant and non-instant hijab use Detection is the image data used in this research. The data used in the image dataset of this research is the instant and non-instant hijab dataset obtained from internet sources using the web scraping method on the internet platform at Google Image and pinterest. In data collection, scraping is carried out to download search results on the platform and the model training process on Teachable Machine. Through effective parameter configuration, namely 50 epochs, batch size 64, and learning rate 0.001, the model managed to achieve 100% accuracy on training and testing data. The results show that the model not only learns quickly, as evidenced by the loss graph which experiences a sharp decline at the beginning of training and stabilizes after several epochs. Consistent performance in testing data shows that the model has been able to generalize well. Further analysis through cross-validation and testing with different datasets is recommended to ensure generalizability and identify potential overfitting. These findings indicate that the approach used is effective in producing high-performing and stable models.   Keyword: Instant hijab, Non instant hijab, Teachable Machine, Machine Learning