<![CDATA[This paper presented an edge-deployed smart-load control system on Raspberry Pi 5 using independent Thai speech and vision-based finger-gesture channels mapped to a common ten-command GPIO actuation layer. Rather than proposing a new recognition algorithm, the study evaluated controller-side execution reliability using GPIO-confirmed binary outcomes and supplemented the human-trial evaluation with system-level engineering profiling. Structured trials examined interaction distance and background speech, yielding 90.0% execution success for both voice (54/60) and gesture (63/70), with different condition-specific performance patterns. A separate 10.5-min integrated profiling run measured computational behavior on the Raspberry Pi 5. Median processing latency was 46.90 ms for Vosk audio blocks and 72.15 ms for MediaPipe hand processing, while median GPIO software-update latency was 0.0688 ms. Median system CPU utilization was 32.30%, process memory was 427.55 MB, and CPU temperature was 83.70 °C; non-zero throttling-status values were observed during sustained workload. These results characterized both execution reliability and resource constraints for non-critical smart-load control on Raspberry Pi-class edge hardware.]]>
Copyrights © 2026
