Article Per Year (5 Year)
p-Index From 2021 - 2026
0.553
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) INOVTEK Polbeng - Seri Informatika
Alwin Hartono Limaran
STMIK Indonesia Mandiri
Computer Science & IT

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

Found 2 Documents
Search

 1 
Performance enhancement of embedded object detection via neural hardware acceleration Alwin Hartono Limaran; Agung Wicaksono; Patah Herwanto
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 24, No 1: February 2026
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v24i1.27448

Abstract

This paper presents the first benchmarking of you only look once version 11 (YOLO11) on the Rockchip RK3566 neural processing unit (NPU) within the Orange Pi 3B platform. Performance was compared between the quad-core ARM Cortex-A55 CPU and the integrated NPU using the COCO2017 dataset, evaluating latency, energy, and accuracy. NPU acceleration achieved >80% latency reduction and ≈ 94% lower per-inference energy consumption, with speedup of up to 16.7× while maintaining accuracy within 0.03 mean average precision (mAP) of the baseline. Average power remained nearly constant (3.60 W central processing unit (CPU) vs. 3.59 W NPU), indicating that the efficiency gains stem from reduced inference time rather than lower wattage. Limitations included unstable INT8 quantization due to unsupported operators and calibration-range mismatch, as well as minor CPU-side overhead in preprocessing and non-maximum suppression. The findings confirm that the RK3566 NPU delivers substantial efficiency gains without accuracy loss, enabling compact and low-cost platforms to sustain modern object-detection workloads. This demonstrates that affordable NPUs can provide reliable, real time artificial intelligence (AI) inference for embedded vision, internet of things (IoT), and robotics applications.
A Comparative Study of Webrtc and Websocket Performance in Real-Time Voice Communication Alwin Hartono Limaran; Agung Wicaksono; Patah Herwanto
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 3 (2025): November
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/rsx41r57

Abstract

This study compares the performance of Web Real-Time Communication (WebRTC) and WebSocket for bidirectional voice interaction with the ChatGPT API on an Orange Pi 3B edge device over a 50 Mbps Ethernet connection. The objective is to determine the most efficient and reliable protocol for real-time interaction on resource-constrained devices. The study evaluates latency, bandwidth, CPU utilization, and jitter metrics automatically collected to assess the efficiency and stability of both protocols. Results show that WebRTC achieves approximately 150 ms latency with lower network and CPU consumption and near-zero jitter, while WebSocket exhibits around 200 ms latency with higher bandwidth usage and CPU load. Practically, WebRTC is more efficient and stable for client-side production due to its resource-efficient and responsive characteristics, whereas WebSocket is better suited for custom data streaming or high-throughput server-to-server communication. These findings provide a quantitative foundation for developers in selecting the optimal protocol for real-time voice applications in edge environments.
Co-Authors Agung Wicaksono Herwanto, Patah