Claim Missing Document
Check
Articles

Found 21 Documents
Search

SOSIALISASI CHATGPT UNTUK MEMPERMUDAH PEKERJAAN DINAS PPA PEMPROV DKI JAKARTA Arrachman, Abdul Kholiq; maesaroh, siti; afiyati, Afiyati; Mubarak, Roy; Kurnia, Rizki Ade
Universal Raharja Community (URNITY Journal) Vol. 5 No. 1 (2025): URNITY (Universal Raharja Community)
Publisher : UNIVERSITAS RAHARJA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33050/urnity.v5i1.3272

Abstract

Abstract : ChatGPT is a language model developed by OpenAI, based on the GPT-3.5 architecture. GPT stands for "Generative Pre-trained Transformer," which indicates that the model is pre-trained to generate text and uses a Transformer architecture. Transformer is a neural network architecture that has proven to be very effective in processing data sequences, such as text. GPT-3.5 is a third generation GPT model that has extraordinary capabilities in understanding and producing text with a high level of intelligence. ChatGPT is specifically designed to support human-machine interactions via text, allowing users to communicate with models using questions or text statements. These models can be used for a variety of purposes, such as responding to questions, generating creative text, or providing assistance in problem solving. In the context of public services or organizations such as the DKI Jakarta Provincial Government's PPA Service, ChatGPT can be integrated as a tool to increase efficiency in communication, provide information, and handle certain tasks automatically. The aim of ChatGPT socialization is to make the work of the DKI Jakarta Provincial Government's PPA Service easier, with the urgency of increasing efficiency and productivity in handling public service tasks. The main aim of this socialization is to introduce and ensure good understanding regarding the use of ChatGPT as a tool in the work of the PPA Service. The targeted output involves increasing the ability of the PPA Service to provide information services, community services, and handling general inquiries through the use of ChatGPT technology. With this outreach, it is hoped that time efficiency can be achieved, service quality improvement and resource optimization in carrying out administrative and communicative tasks.
Improving Inclusive Students Competence through 3D Flashcard Animation-Based Animal Exploration Hasanudin, Muhaimin; Riskinanti, Karisma; Santoso, Hadi; Novrizal, Kevin; Lestari, Mulyati; Afiyati, Afiyati
Engagement: Jurnal Pengabdian Kepada Masyarakat Vol 9 No 1 (2025): May 2025
Publisher : Asosiasi Dosen Pengembang Masyarajat (ADPEMAS) Forum Komunikasi Dosen Peneliti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29062/engagement.v9i1.1817

Abstract

Children with special needs often face challenges in recognizing animal shapes and sounds. This community service program (PKM), based on the Service Learning approach, developed an application called Teh Melati, which utilizes Augmented Reality (AR) by combining 3D animation with traditional 2D flashcards to aid in animal recognition. The PKM was conducted over one day with 32 students with disabilities aged 6–14 years (N=32) at HS-Lantaburo. The Service Learning methodology involved actively engaging the community (teachers, parents, and students) in the design, implementation, and evaluation of the learning intervention. Students participated in an interactive animal exploration game that focused on animal images and sounds. Pre-intervention test scores averaged 63.75, while post-intervention scores increased to 81.25. A total of 25 students (78% of the participants) showed significant improvement. The active participation of teachers and parents in hands-on workshops further extended the impact of the intervention. These results demonstrate that learning gaps in special needs education can be addressed through community involvement and the integration of 3D flashcard animation technology, with Service Learning serving as an effective framework for creating meaningful educational experiences for both the students and the community.
Linear Regression Algorithm in Pulse Purchase System Simple Using Python Afiyati, Afiyati; Ayu, Kurnia Gusti; Roza, Yuni; Sakhrassalam, Haytsam; Syafiq, Nur Muhammad Zihni
Journal Collabits Vol 1, No 2 (2024)
Publisher : Journal Collabits

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/collabits.v1i2.27256

Abstract

In today's digital era, the online credit purchase system has become an integral part of everyday life. The use of linear regression algorithms in this context is becoming increasingly relevant, as it provides a powerful approach to analyzing and predicting pulse buying patterns. This research proposes a simple pulse purchase system that implements a linear regression algorithm, using the Python programming language. The purpose of this study is to develop a predictive model that can estimate the amount of credit to be purchased based on certain variables, such as the time of purchase, the number of previous transactions, and the value of prior purchases. By analyzing historical transaction data, the system can take into account possible purchase patterns and estimate future credit needs with an adequate level of accuracy. The implementation of linear regression algorithms in Python allows users to easily access and use this pulse purchase system. Through a simple but intuitive interface, users can enter their transaction parameters and the system will predict the required number of pulses. Experiments were conducted to test the performance of this system in producing accurate predictions. The results of the experiment show that this system can provide estimates close to the real value, with a high degree of accuracy. This indicates that the use of linear regression algorithms in pulse purchase systems has great potential to improve efficiency and reliability in online transactions. In addition, the implementation of this algorithm also has a positive impact on transaction security. By analyzing purchasing patterns, the system can detect anomalies or suspicious activities that may occur, thereby increasing the level of security in the process of buying credit online. Overall, this study shows that the use of linear regression algorithms in pulse purchase systems has significant benefits in improving the efficiency, reliability, and security of online transactions. The practical implementation of this algorithm in the Python programming language opens the door for further development in the analysis and optimization of future pulse purchase system.
Implementation of the Random Forest algorithm to predict rice needs in DKI Jakarta Santoso, Hadi; Hakim, Lukman; Afiyati, Afiyati; Jokonowo, Bambang
Telematika Vol 22 No 1 (2025): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v22i1.12850

Abstract

Purpose : to build collaborative partners between government institutions and universities in food processing, especially rice, by predicting rice needs in the DKI Jakarta area.Design/methodology/approach:The approach in this research uses the Random Forest algorithm which functions to predict rice needs in the DKI Jakarta area.Results: rice demand prediction application with evaluation values Mean Squared Error 207.86, Mean Absolute Error 9.43, MAPE 0.048, Root Mean Squared Error 14.4, accuracy 0.63Originality/value/state of the art:research using data from BAPANAS, Cipinang Main Market, with 2 datasets of rice stock, population, year and rice consumption using a random forest algorithm to predict rice needs in the DKI Jakarta area 
Web-based Application Design "UMB Eats" With Laravel Framework Afiyati, Afiyati; Fahrezi, Zidane; Rizky, Muhammad; Ardi, Liandy Hayanto; Ahmad, Ersa
Journal Collabits Vol 2, No 1 (2025)
Publisher : Journal Collabits

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/collabits.v2i1.31239

Abstract

The ‘UMB Eats’ application was developed to improve the efficiency of Mercu Buana University canteen services by providing online ordering and payment features. This application makes it easier for users to access menu information, prices, and food stocks, while reducing long queues at the canteen. This research aims to design a web-based system that is practical and helps the management of orders and stock by sellers. As a result, ‘UMB Eats’ proved to provide a faster and more convenient experience for users, as well as supporting a more organised canteen operation.
SOSIALISASI DAN EDUKASI LINGKUNGAN RUMAH SEHAT : PENINGKATAN KUALITAS HIDUP BAGI PEKERJA MIGRAN INDONESIA DI PULAU PINANG Maun Harahap, Rachmita; Syaban, Zulfikar; Zulia Suriastuti, Mira; Afiyati, Afiyati
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 8, No 7 (2025): MARTABE : JURNAL PENGABDIAN KEPADA MASYARAKAT
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v8i7.2779-2786

Abstract

Yayasan Permai di Pulau Pinang, Malaysia, dipilih sebagai mitra pelaksana dalam kegiatan pengabdian kepada masyarakat, dengan fokus pada sosialisasi dan edukasi tentang lingkungan rumah sehat bagi pekerja migran. Kegiatan ini sangat penting untuk menjaga kualitas psikologis pekerja migran dan keluarganya, sehingga dapat berkontribusi pada kelancaran aktivitas masyarakat secara lebih luas. Sosialisasi dan edukasi ini didukung oleh tim pelaksana dari Fakultas Desain dan Seni Kreatif Universitas Mercu Buana dan Yayasan Permai. Dalam pelaksanaannya, kegiatan menggunakan media visual seperti poster dan banner sebagai metode penyampaian materi utama. Pendekatan ini terbukti efektif dalam meningkatkan minat dan antusiasme peserta. Program ini bertujuan untuk meningkatkan pengetahuan lingkungan rumah sehat melalui edukasi berbasis media visual upaya peningkatan kualitas hidup sehat bagi peserta. Pemahaman yang meningkat diharapkan menjadi bagian dari upaya berkelanjutan untuk memperbaiki kualitas hidup para pekerja migran. Materi disampaikan melalui edukasi berbasis media visual guna meningkatkan pemahaman peserta. Para ahli yang terlibat dalam inisiatif ini berasal dari berbagai latar belakang, termasuk akademisi (dosen dan mahasiswa dari Universiti Sains Malaysia), perwakilan dari Kedutaan Besar Republik Indonesia di Malaysia, serta Direktur Yayasan Permai. Kolaborasi lintas-disiplin ini memperkuat relevansi dan kualitas materi yang diberikan. Hasil dari program ini menunjukkan adanya peningkatan signifikan dalam kesadaran, partisipasi, dan keterlibatan masyarakat mengenai pentingnya lingkungan rumah yang sehat. Edukasi berbasis media visual telah terbukti efektif dalam menyampaikan pesan utama, sementara gaya hidup sehat mulai muncul sebagai bagian dari kehidupan sehari-hari para pekerja migran. Inisiatif ini merupakan langkah awal yang menjanjikan dalam membangun komunitas pekerja migran yang tangguh serta menciptakan lingkungan hunian yang berkelanjutan di masa depan.
Toothpaste Brand Prediction Based on Analysis of Teeth Condition and Price Preferences Using the Random Forest Algorithm Afiyati, Afiyati; Ningrum, Rahma Farah; Naima, Faaza
Journal Collabits Vol 1, No 1 (2024)
Publisher : Journal Collabits

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/collabits.v1i1.25560

Abstract

This study aimed to predict toothpaste brands based on an analysis of dental conditions and price preferences using the Random Forest algorithm and the CRISP-DM approach. The research results indicated that the variables of tooth color range and frequency of toothache had the highest influence, suggesting that consumers were more likely to choose a brand based on tooth color and sensitivity. Evaluation using the Confusion Matrix and Classification Report models demonstrated good performance with an accuracy of 91.3%. Based on the result, the model could serve as a robust foundation for developing a GUI-based Toothpaste Brand Prediction Application using the tkinter library, assisting users in making more informed decisions.
Implementasi Algoritma XGBoost untuk Memprediksi Harga Jual Cabai Rawit di DKI Jakarta Riando, Dhafin; Afiyati, Afiyati
Eduvest - Journal of Universal Studies Vol. 4 No. 9 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i9.3784

Abstract

This research focuses on applying the XGBoost algorithm to analyze and predict cayenne pepper prices. The main aim is to exploit XGBoost's exceptional capability to manage large datasets and discern intricate patterns for precise price forecasting. The dataset comprises historical cayenne pepper price data, along with pertinent economic and climatic factors. The XGBoost model was developed and validated on this dataset, with its performance assessed using metrics. The results indicated a high level of accuracy, achieving an R² score of 99% on the training set and 92% on the test set, reflecting a strong alignment between predicted and actual prices. Moreover, the model attained an average cross-validation score of 96%, reinforcing its robustness and reliability. These findings highlight XGBoost's efficacy in agricultural price prediction, offering stakeholders a potent tool for data-driven decision-making. This study enriches the literature on machine learning applications in agriculture and emphasizes XGBoost's potential to enhance predictive accuracy and operational efficiency.
DIGITAL LITERACY PROGRAM DAILY LIFE WITH AI TOOLS Jokonowo, Bambang; Santoso, Hadi; Afiyati, Afiyati
Jurnal Pengabdian Masyarakat Nasional Vol 4, No 2 (2024)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/pemanas.v4i2.29638

Abstract

The "Digital Literacy Program: Daily Life with AI Tools" is a community service initiative aimed at enhancing digital literacy by integrating artificial intelligence (AI) tools into daily routines. Conducted at Rumah Pertubuhan Masyarakat Indonesia (PERMAI) in Pulau Pinang, Malaysia, this program seeks to democratize access to AI technologies, fostering a foundational understanding that bridges the gap between complex AI concepts and their practical applications in everyday life. By equipping participants with the skills to utilize AI tools effectively, the program not only improves efficiency in personal and professional activities but also empowers individuals with the knowledge to navigate the evolving digital landscape. The innovative approach of this program is its focus on making AI accessible to a broader audience, promoting digital inclusivity and literacy. Through hands-on workshops and real-world applications, participants learn to integrate AI into tasks such as time management, data organization, and problem-solving, leading to enhanced productivity and informed decision-making. This initiative ultimately contributes to the broader goal of fostering a digitally literate society capable of leveraging emerging technologies for personal and collective advancement.
Comparison of Linear Regression and Random Forest Algorithms for Premium Rice Price Prediction (Case Study: West Java) Muchtar, Irfan Rasyid; Afiyati, Afiyati
Jurnal Indonesia Sosial Teknologi Vol. 5 No. 7 (2024): Jurnal Indonesia Sosial Teknologi
Publisher : Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59141/jist.v5i7.1184

Abstract

The staple food commodity that is crucial to the Indonesian society is rice. Rice often experiences fluctuations in prices. These fluctuations can be predicted using machine learning methods. The aim of this research is to evaluate the accuracy of machine learning algorithms in predicting the premium rice prices in the West Java Province, Indonesia. Two methods used in this study are Linear Regression and Random Forest. The dataset used consists of 6096 records from the Indonesian Food Commodity Management Agency. The evaluation results show that the Random Forest algorithm has an accuracy rate of 98.69%, while the Linear Regression algorithm has an accuracy rate of 95.08%. Based on these results, it is concluded that the Random Forest algorithm is more effective in predicting premium rice prices in the West Java Province compared to the Linear Regression algorithm.