Article Per Year (5 Year)
p-Index From 2021 - 2026
2.583
P-Index
This Author published in this journals
All Journal Jurnal Teliska Jupiter Elkom: Jurnal Elektronika dan Komputer PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Prosiding SNATIF Annual Research Seminar JETT (Jurnal Elektro dan Telekomunikasi Terapan) RABIT: Jurnal Teknologi dan Sistem Informasi Univrab JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING IT JOURNAL RESEARCH AND DEVELOPMENT JOURNAL OF APPLIED INFORMATICS AND COMPUTING JURNAL REKAYASA TEKNOLOGI INFORMASI MIND (Multimedia Artificial Intelligent Networking Database) Journal AMALIAH: JURNAL PENGABDIAN KEPADA MASYARAKAT Building of Informatics, Technology and Science Aviation Electronics, Information Technology, Telecommunications, Electricals, and Controls (AVITEC) Jurnal Digit : Digital of Information Technology Journal of Technology and Informatics (JoTI) Arcitech: Journal of Computer Science and Artificial Intelligence Bulletin of Network Engineer and Informatics (BUFNETS) CSRID
Aryanti Aryanti
Jurusan Teknik Elektro, Program Studi Teknik Telekomunikasi, Politeknik Negeri Sriwijaya
Aerospace Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Library & Information Science Mechanical Engineering

Published : 25 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 25 Documents
Search

 1   2   3 
Analisis Komparatif Algoritma Naïve Bayes dan XGBoost untuk Mengklasifikasikan Performa Akademik Mahasiswa Berdasarkan Tingkat Ketergantungan AI Aryanti Aryanti; Juriawan Raja Saputra; Taufik Permana; Putri Nabila; Ibnu Asrafi
Arcitech: Journal of Computer Science and Artificial Intelligence Vol. 6 No. 1 (2026): June 2026
Publisher : Institut Agama Islam Negeri (IAIN) Curup

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29240/arcitech.v6i1.17321

Abstract

While Artificial Intelligence (AI) integrates into higher education to streamline information retrieval, comprehension, and academic task completion, over-reliance on these tools may jeopardize student outcomes. Extant literature predominantly examines AI adoption rates, dependency levels, and user sentiments; however, comparative analyses of machine learning models for classifying academic performance relative to AI usage intensity remain scarce. To address this gap, this study evaluates and compares the efficacy of Naïve Bayes and XGBoost algorithms in predicting student performance based on their AI engagement. Utilizing the Academic Outcomes & AI Dependency Analysis Dataset—comprising 8,000 instances and 26 features—the methodology encompasses data preprocessing, normalization, partitioning, model training, and evaluation via accuracy, precision, recall, and F1-score. The empirical results demonstrate that XGBoost outperforms Naïve Bayes, achieving a superior accuracy of 84.17% compared to 79.03%. Consequently, XGBoost proves to be a more robust model for classifying academic performance driven by AI usage, offering valuable insights for the advancement of educational data analytics.
ShelfMind: Demand Forecasting and Stock Control for Retail SMEs using Global XGBoost and Context-Injected AI Chatbot Aulia Syafitri; Aryanti Aryanti; Sholihin Sholihin
Building of Informatics, Technology and Science (BITS) Vol 8 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v8i1.10280

Abstract

SME retail stores in Indonesia face serious challenges in inventory management: stockouts of popular products, waste from perishable items that expire before being sold, and restocking decisions relying on owner intuition. This research develops ShelfMind, a web-based inventory management system integrating three main components: a demand prediction model using a global XGBoost algorithm, an AI chatbot based on real-time data context injection, and an active notification system for low-stock and expiry risk alerts. Dataset from Toko Tika Baru covered 47 products in 11 categories with 8,225 daily sales records over 205 days. The XGBoost model was trained with 29 time-engineered features and achieved an MAE of 0.4107 units/day and RMSE of 0.5081 units/day on a 40-day test set. The global XGBoost method and context injection approach were selected due to their computational efficiency, avoiding the high costs associated with LLM fine-tuning, thus making it an ideal solution for SMEs with limited budget and infrastructure data. The AI chatbot, using context injection from inventory, sales, and XGBoost forecast data, achieved an average relevance and data accuracy of 4.94/5 across 20 test scenarios with an average response time of 2.94 seconds. Black-box functional testing of 31 scenarios passed completely. Usability evaluation scored 3.77/5, with notes on improving the communication of prediction features to non-technical users. This system proves that integrating XGBoost and LLM in an SME inventory management platform is technically feasible and provides tangible value for retail operations.
Real-Time Human Detection and Face Recognition System Using CCTV Stream and Localhost-Based Monitoring Dashboard M. A. Racka Eratama; Ade Silvia Handayani; Aryanti Aryanti; Asriyadi Asriyadi
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3954

Abstract

This study presents a real-time human detection and face recognition system that utilizes CCTV video streams and a localhost-based monitoring dashboard. Using a Research and Development (R&D) approach, a computer vision application was designed and implemented on a laptop platform. Human detection was performed using YOLO11n, facial regions were localized with YuNet, and face recognition was carried out using SFace to distinguish registered individuals from unknown persons. The detection results were displayed through a web-based dashboard that provided live video streaming, AI status information, face registration, and detection history records. Performance evaluation was conducted under various conditions, including human and non-human scenarios, registered and unknown faces, dark-room environments, and night-vision mode. The dashboard maintained a preview rate of approximately 20–30 FPS. Experimental results showed that human detection achieved an accuracy of 80%, while face recognition achieved 72% accuracy under the tested conditions. Alert Level 1 was triggered when a person was detected, whereas Alert Level 2 was activated for unknown-face events. The findings demonstrate the potential of integrating lightweight computer vision models into a local surveillance system without relying on cloud infrastructure. Nevertheless, system performance remained dependent on factors such as lighting conditions, camera distance, face orientation, image quality, and available computing resources.
Identifikasi CNN dalam Deteksi Penyakit Daun Jagung Berbasis Pengenalan Gambar ARYANTI ARYANTI; DEFINA APRILIANI; WULAN ZAHRA PUTRI; DWI RAMADHANI; THREA MALINDA; DIMAS ANDREANSYAH
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 10, No 2 (2025): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v10i2.195-205

Abstract

AbstrakProduktivitas jagung sangat terancam oleh penyakit daun seperti common rust, gray leaf spot, dan leaf blight. Identifikasi penyakit yang lambat dan tidak akurat menjadi masalah utama yang mendesak. Oleh karena itu, penelitian ini bertujuan mengembangkan mekanisme identifikasi otomatis penyakit daun jagung menggunakan algoritma Convolutional Neural Network (CNN) berbasis citra digital, mendukung upaya pertanian presisi. Penelitian menggunakan 4.188 citra daun (sehat, leaf blight, rust, dan gray leaf spot) yang diproses melalui preprocessing seperti normalisasi dan augmentasi. Hasil pengujian menunjukkan efektivitas tinggi, di mana model CNN mencapai akurasi klasifikasi 95% dengan waktu inferensi cepat, hanya 0,48 detik per gambar. Kontribusi utama penelitian ini adalah penyediaan model CNN yang sangat akurat dan efisien, berpotensi besar menjadi dasar sistem diagnostik lapangan untuk membantu petani meningkatkan kualitas dan hasil produksi jagung.Kata kunci: CNN, Deteksi Penyakit, Jagung, Pengenalan Citra, Deep Learning AbstractCorn productivity is severely threatened by leaf diseases such as common rust, gray leaf spot, and leaf blight. Slow and inaccurate disease identification is a pressing issue. Therefore, this study aims to develop an automatic corn leaf disease identification mechanism using a digital image-based Convolutional Neural Network (CNN) algorithm, supporting precision agriculture efforts. The study used 4,188 leaf images (healthy, leaf blight, rust, and gray leaf spot) that were processed through preprocessing such as normalization and augmentation. The test results demonstrated high effectiveness, where the CNN model achieved 95% classification accuracy with a fast inference time of only 0.48 seconds per image. The main contribution of this study is the provision of a highly accurate and efficient CNN model, with great potential to become the basis of a field diagnostic system to help farmers improve corn quality and yield.Keywords: CNN, Disease Detection, Corn, Image Recognition, Deep Learning
SMARTBAND TRACKER UNTUK ANAK USIA DIBAWAH 6 TAHUN MENGGUNAKAN WEMOS D1 DENGAN MONITORING MELALUI SMARTPHONE Dhea Syafitri; Aryanti Aryanti; Muhammad Zakuan Agung
JURNAL TELISKA Vol 18 No III (2025): TELISKA November 2025
Publisher : Teknik Elektro Polsri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.17761317

Abstract

Smartband tracker is designed to monitor the child's location directly through the blynk application on the smartphone. To make this smartband requires several components, namely the Wemos D1 Mini as the brain center of the smartband control device, GPS is used to determine the position point of the child's whereabouts, the battery functions as a power supply so that the smartband can operate independently, the Battery Mangament System functions as a backup battery life and the Switch is used as an On / Off button. This tool works in a way, if the red LED flashes it means the GPS has obtained a coordinate point where the results can be seen in the blynk application which can display the location point of the child's whereabouts, displaying coordinate points such as latitude, longitude, and speed. In this study, testing was carried out at 5 location points. The results of the study showed that speed variations were greatly influenced by the duration and intensity of movement, not only by the distance traveled. High speed is recorded at short distances when fast movement occurs, namely point 1 to point 6, while low speed occurs even though the distance is long, when the movement is slow, namely at point 1 to point 5. After testing the tool, the results show that the smartband can work well and can determine the location point in real-time and the advantage of this tool is that it has a buzzer feature that can be turned on via the blynk application on the smartphone where this buzzer will make a sound when activated. Key words : Smartband, IoT, Wemos D1, GPS Tracker, Children, Smartphone, Monitoring
ANALISIS ARUS DAN TEGANGAN PADA RANGKAIAN KOMBINASI MENGGUNAKAN SIMULATOR LIVEWIRE Jonathan Farrel Akbar; Noval Resti Ardiansyah; Kayla Luna Pasha; Aryanti Aryanti
JURNAL TELISKA Vol 18 No III (2025): TELISKA November 2025
Publisher : Teknik Elektro Polsri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.17761213

Abstract

This article discusses the use of LiveWire software as an interactive simulation medium for analyzing current and voltage in mixed resistor circuits, which are a combination of series and parallel circuits. This study aims to demonstrate how LiveWire can be used as a learning tool to understand basic electrical concepts more effectively and efficiently. Through digital simulation, users can accurately observe the distribution of current, voltage, and power in each resistor without the need for physical measuring instruments in the laboratory. The simulation results are then compared with theoretical calculations based on Ohm's Law, showing a very high degree of conformity with insignificant differences in values. This proves that LiveWire is capable of representing the behavior of electrical circuits realistically. In addition to simplifying the design and analysis process, the use of LiveWire also improves practitioners' understanding of the relationship between current, voltage, and resistance. Thus, LiveWire can be used as an interactive, safe, and efficient digital learning medium to support electronics practicum activities.
SIMULASI RANGKAIAN PENYEARAH SETENGAH GELOMBANG MENGGUNAKAN LIVEWIRE Aryanti Aryanti; Clara Alcahya Palpa; Dimas Iqbal Fahrozy; M.Nabil Ar-Rassya; Nadya Aprilia
JURNAL TELISKA Vol 18 No III (2025): TELISKA November 2025
Publisher : Teknik Elektro Polsri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.17761390

Abstract

This study discusses the design and analysis of a half-wave rectifier circuit using the LiveWire Circuit application as a simulation medium. The main objective of this research is to understand the working principle of the diode as a rectifying component and to analyze the waveform and output characteristics produced through simulation. The circuit consists of an AC voltage source, a step-down transformer, a 1N4007 silicon diode, and a 1 kΩ load resistor. The simulation results show that the diode conducts current only during the positive half-cycle of the AC signal and blocks current flow during the negative half-cycle, thus producing a pulsating direct current (DC) output. The average DC voltage obtained from the simulation is 0.32 V, which is close to the theoretical value of 0.318 V, with a rectification efficiency of 40.6%. These findings demonstrate that the LiveWire application effectively represents circuit characteristics and provides real-time waveform visualization. The use of simulation through LiveWire not only enhances the understanding of basic electronics concepts but also offers a practical learning approach without requiring physical circuit assembly, making it an efficient educational tool for analyzing half-wave rectifier performance.
Machine Learning for Classifying Priority Areas for School Infrastructure Improvement Funding Aryanti Aryanti; Nurul Mardhiyah; Aulia Syafitri; Muhammad Ghalib; Nabil Alrofi
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol. 10 No. 1 (2026): Issues July 2026
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v10i1.17789

Abstract

Equitable funding for school infrastructure is often hampered by subjective evaluation methods that lead to inappropriate prioritization. This study develops a data-driven approach that uses machine learning to objectively classify funding priority areas. Using the CRISP-DM (Cross-Industry Standard Process for Data Mining) framework and data from the Indonesian Ministry of Education, a support vector regression (SVR) model with an RBF kernel is developed. This model integrates key facility indicators including laboratory availability, sanitation, and access to utilities to predict infrastructure adequacy. Separate models were built for public and private secondary schools with a 70:15:15 data split. The results demonstrated excellent predictive accuracy, with an R² of 0.9938 for public schools and 0.9969 for private schools, at a minimal error rate (MAE <0.20). By grouping the regression results into priority categories, the model successfully identified twenty high-priority areas that require immediate intervention by 2024. These results demonstrate that the SVR-based framework provides a robust decision support system, enabling policymakers to allocate infrastructure funds more transparently, equitably, and in direct alignment with empirical realities on the ground.
Sosialisasi Aplikasi Mobile Untuk Sistem Antrian Pada Puskesmas Sako Kota Palembang Nurhajar Anugraha; Aryanti Aryanti; Dyah Utari Yusa Wardhani; Pertiwi Nurul Utami; Imas Ning Zhafarina; Muhammad Hanif Fatin; Diah Novita Sari; Yulia Hapsari; Adhelia Febriasari Harahap
Amaliah: Jurnal Pengabdian Kepada Masyarakat Vol 9 No 1 (2025): Amaliah Jurnal: Pengabdian kepada Masyarakat
Publisher : LPPI UMN AL WASHLIYAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32696/ajpkm.v9i1.4545

Abstract

This Community Service Activity aims to provide knowledge about mobile applications for queuing systems that are expected to make it easier for patients who will check their health or seek treatment at the Health Center. The methods used in this activity include interview methods with the Health Center to find out the source of the problem that is the basis for this community service activity. Furthermore, a socialization method is carried out, where in this socialization activity an explanation will be given to both the Health Center and patients about the use of the application that will be designed. The results of this activity are socialization regarding the Mobile application for the patient queuing system along with socialization of the procedures for using the application. Where after the implementation of this activity is carried out, the application that will be designed will make it easier for patients and patients no longer need to sit and queue for a long time when going to the Sako Health Center for treatment.
Yagi-Uda Antennas for Private LTE Band 3 FDD: Simulation, Fabrication, and Measurement Muhammad Rizko Justiano; Aryanti Aryanti; Mohammad Fadhli
Aviation Electronics, Information Technology, Telecommunications, Electricals, and Controls (AVITEC) Vol 8, No 2 (2026): August
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/avitec.v8i2.4168

Abstract

Private LTE Band 3 Frequency Division Duplex (FDD) systems require dedicated uplink and downlink antennas to improve channel isolation and communication reliability. However, experimentally validated split-frequency Yagi-Uda antennas for Software Defined Radio (SDR)-based base stations remain limited. This study presents the design, simulation, fabrication, and experimental validation of two four-element Yagi-Uda antennas operating at 1.840 GHz for downlink (DL) and 1.750 GHz for uplink (UL). Each antenna consists of one reflector, one driven element, and two directors fabricated from 6 mm diameter aluminum rods. The antenna dimensions were optimized using the Trust Region Framework in CST Studio Suite 2024 to achieve optimal impedance matching. Simulation results produced S11 values of −35.33 dB (DL) and −30.76 dB (UL), VSWR values of 1.035 and 1.059, and forward gains of 9.10 dBi and 8.38 dBi, respectively. Measurements using a NanoVNA over the 1.4–2.1 GHz frequency range yielded S11 values of −18.98 dB (DL) and −26.92 dB (UL), with corresponding VSWR values of 1.253 and 1.094. The measured resonant frequencies closely agreed with the simulation results, with a maximum deviation of only 1 MHz. The novelty of this work lies in the experimental validation of a low-cost, split-frequency, four-element aluminum-rod Yagi-Uda antenna pair that operates without an external impedance-matching network. These results demonstrate the suitability of the proposed antennas for SDR-based Private LTE Band 3 base station applications.
Co-Authors Ade Silvia Handayani Adhelia Febriasari Harahap Ahmad Rifqi Nugraha Aknes Tasia Pratama Amanda Tsabita Putri Aqilla Khairunnisya Asriyadi Asriyadi Asriyadi Asriyadi Aulia Syafitri Aulia Syafitri CIK SADAN Ciksadan Ciksadan Clara Alcahya Palpa Dava Anugrah Limanda Dea Oktavia DEFINA APRILIANI Devi Indah Pujiana Dhea Syafitri Diah Novita Sari DIMAS ANDREANSYAH Dimas Iqbal Fahrozy DWI RAMADHANI Dyah Utari Yusa Wardhani Fatia Salsabilla Kyara Fifteen Angelina Hari Ramadhan Hisanah Nakhwah Aulia Faruly Hj Lindawati Hj. Lindawati Ibnu Asrafi Ikhsan Yuda Pratama Ikhthison Mekongga Imas Ning Zhafarina Irma Salamah Jonathan Farrel Akbar Juriawan Raja Saputra Kayla Luna Pasha Khumairah Amira Sari M. A. Racka Eratama M.Nabil Ar-Rassya Mohammad Fadhli Muhammad Aulia Dzikri Muhammad Ghalib Muhammad Hanif Fatin Muhammad Imansyah Muhammad Iqbal Falevy Muhammad Juan Farza Rafly Alganiyu Muhammad Rizko Justiano Muhammad Zakuan Agung Nabil Alrofi Nadya Aprilia Noval Resti Ardiansyah Nurhajar Anugraha Nurul Mardhiyah Pertiwi Nurul Utami Putri Nabila Putri Nur Azizah R.A. Halimatussa&#039;diyah Roni Suhermawan Sarjana, Sarjana Sholihin Sholihin Siti Salwa Nurhadiva Sulistia Sulistia suzan zefi Taufik Permana THREA MALINDA Vina Rahmadiany WULAN ZAHRA PUTRI Yulia Hapsari Yuni Selvita Suci