Autonomous sensor node system for table tennis officiating: Optimized placement using enhanced chimp optimization algorithm
Yonggang Niu, Mohammad Khishe · Results in Engineering · 2025
Accurate table tennis officiating for side ball decisions and net is challenging due to human error and the high cost of systems like Hawk-Eye, which require numerous sensors and lack adaptability. This study proposes an Autonomous Sensor Node System (ASNS) with three Triboelectric Nanogenerator (TENG)-powered acceleration sensors, optimized by the Enhanced Chimp Optimization Algorithm (ECOA) for Collision Point (CP) detection. ECOA integrates adaptive group dynamics, chaos-based seeding, and a dual exploration–exploitation strategy to balance global and local search refinement. The system is tested on a standard 2.74 m × 1.525 m table, where ECOA is benchmarked against six metaheuristic algorithms, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Hypotrochoid Spiral Optimization Algorithm (HSOA), Butterfly Optimization Algorithm (BOA), Bald Eagle Search–Growth Optimizer (BES–GO), and Fractional-Order Sparrow Search Algorithm (FDSSA). Findings show that with ECOA, the sensor count is reduced from 60 to 42, the CP detection error is 3.2 ± 0.3 mm (40 % better than Hawk-Eye's 5.5 mm), and a coverage of 96.8 ± 1.2 % of the table is achieved with an energy expenditure of 45 ± 3 mJ. The ECOA results show a significant difference as validated by the Wilcoxon signed-rank test ( p < 0.05). The adaptability and precision of ECOA in these results demonstrate its efficacy for high-dynamics, high-accuracy scenarios. The ASNS offers a scalable automation approach for officiating table tennis, which can be extended to other sports while being cost-effective and environmentally friendly.