Article Per Year (5 Year)
p-Index From 2021 - 2026
1.037
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Jurnal Pendidikan Informatika dan Sains Indonesian Journal of Electrical Engineering and Computer Science G-Tech : Jurnal Teknologi Terapan ELIT JOURNAL Electrotechnics And Information Technology Kapuas Journal of ICT, Design, Engineering and Technological Science
Freska Rolansa, Freska
Politeknik Negeri Pontianak
Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Energy Engineering Law, Crime, Criminology & Criminal Justice Mechanical Engineering Physics Other

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Dynamic Energy Conservation Based on Room Characteristics at Polytechnic State of Pontianak Yunita; Mariana Syamsudin; Wendhi Yuniarto; Freska Rolansa
Journal of ICT, Design, Engineering and Technological Science Volume 3, Issue 2
Publisher : Journal of ICT, Design, Engineering and Technological Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33150/JITDETS-3.2.4

Abstract

Generally, energy conservation is carried out on a building as a whole, but in this research the energy conservation is carried out dynamically based on the characteristics and the user of the room. In this research, the lux measurement has been taken at certain times. Based on the characteristics of the existing room at Polytechnic State of Pontianak, the lux measurements were taken at one of the electronics laboratory, one technician room, electrical engineering department library, one classroom for information technology students and one academic staff office. These rooms divided into three size: small, medium, and large. The data that has been taken was compared with the standard of room lighting according to the Indonesian National Standard SNI-03-6917-2000. Analysis in determining lux can be used with fuzzy logic based on room size, number of lights and electrical power. Lux can be obtained by 3 values, namely weak, medium, and strong. With fuzzy it is obtained that the value of output membership for Lux strong for library = 0.11, technician room = 0.10, and classroom IT 7 = 0.31 with the scale of 0 – 1. With 0 is the value of the minimum and 1 is the maximum value of the fuzzy membership. It can be seen between the 3 rooms that classroom It 7 is the room with better lighting, hence better lux value.
Privacy-Focused AIoT: Implementing an Offline Voice Assistant for Smart Building Management Using Local LLMs Fitri Wibowo; Suheri Suheri; Ferry Faisal; Freska Rolansa
G-Tech: Jurnal Teknologi Terapan Vol 10 No 2 (2026): G-Tech, Vol. 10 No. 2 April 2026
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v10i2.9342

Abstract

Voice assistants are increasingly used for smart building control, yet cloud-based architectures raise privacy risks and become unavailable during internet outages. This study designs and evaluates a fully offline AIoT voice assistant for smart building management using local speech and language models. The system employs an edge audio node (Raspberry Pi Zero 2W with ReSpeaker 2-Mics Pi HAT) and a local GPU server running containerized microservices for speech-to-text (Whisper), intent understanding and action planning (Ollama-hosted LLMs), and text-to-speech (Piper). Building devices and sensors are integrated through Home Assistant, enabling voice-driven control and monitoring without sending audio or interaction logs to external services. Experiments in a laboratory smart-building testbed evaluate speech recognition robustness under varying noise levels, LLM command understanding accuracy and memory footprint, and end-to-end IoT task execution. The speech subsystem achieves a Word Error Rate of 5–20% depending on background noise. Across 33 IoT entities, the assistant reaches a 96.67% execution success rate with an average response time of 5.5 s. Among the evaluated local models, Qwen3 8B achieves the highest intent-to-action accuracy (Acc_I2A=100% on an oracle-text command test set with N=43) with 6.8 GB memory use. The results demonstrate that privacy-preserving and resilient voice interaction for smart building management is feasible using current local LLM stacks.
Co-Authors Afiahayati Afiahayati, Afiahayati Aufaclav Zatu Kusuma Frisky Azhari S.N. Bangbang Hermanto Budianingsih Budianingsih Budianingsih, Budianingsih Ferry Faisal Ferry Faisal, Ferry Fitri Wibowo Fitri Wibowo Jayawarsa, A.A. Ketut Jazi Eko Istiyanto Mariana Syamsudin Sarah Bibi Siswanto, Lindung Suheri Suheri Suheri Suheri Suheri Suheri Suryanto, Tommi Tharam, Medi Yuwono Tri Bowo Atmojo Wendhi Yuniarto Yunita Yunita Yunita Yunita Yunita