<p>This study proposes a smart clothing comfort evaluation and adjustment system based on fuzzy inference to improve wearability across varying environmental conditions. The system integrates real-time physiological data, environmental parameters, and subjective comfort ratings to dynamically regulate key garment properties, including breathability, thermal resistance, and moisture absorption. Optimized through a genetic algorithm, a fuzzy inference engine enables adaptive and responsive control in complex and variable scenarios. The system's performance was validated through indoor, outdoor, and extreme experiments. Results show that the fuzzy inference approach significantly enhances comfort levels, reduces response time, and consistently outperforms traditional control methods. The system also demonstrates robustness and adaptability, making it suitable for daily wear and challenging environmental conditions. These findings highlight the potential of fuzzy logic-based optimization in advancing intelligent clothing design and personalized comfort regulation in wearable technologies.</p>