Machine learning has been extensively applied for various classical software testing activities such as test generation, minimization, and prioritization. Along the same lines, recently, there has been interest in applying quantum machine learning to software testing. For example, Quantum Extreme Learning Machines (QELMs) were recently applied for testing classical software of industrial elevators. However, most studies on QELMs, whether in software testing or other areas, used ideal quantum simulators that fail to account for the noise in current quantum computers. While ideal simulations offer insight into QELM's theoretical capabilities, they do not enable studying their performance on current noisy quantum computers. To this end, we study how quantum noise affects QELM in three industrial and real-world classical software testing case studies, providing insights into QELMs' robustness to noise. Such insights assess QELMs potential as a viable solution for industrial software testing problems in today's noisy quantum computing. Our results show that QELMs are significantly affected by quantum noise, with a performance drop of 250% in regression tasks and 50% in classification tasks. Although introducing noise during both ML training and testing phases can improve results, the reduction is insufficient for practical applications. While error mitigation techniques can enhance noise resilience, achieving an average 3.0% performance drop in classification, but their effectiveness varies by context, highlighting the need for QELM-tailored error mitigation strategies.

翻译：机器学习已广泛应用于各类经典软件测试活动，如测试生成、最小化与优先级排序。近年来，量子机器学习在软件测试领域的应用也受到关注。例如，量子极限学习机（QELMs）近期被应用于工业电梯系统的经典软件测试。然而，现有关于QELMs的研究（无论是软件测试还是其他领域）大多基于理想量子模拟器，未能考虑当前量子计算机中存在的噪声问题。虽然理想模拟有助于理解QELM的理论能力，但无法评估其在当前含噪声量子计算机上的实际性能。为此，我们通过三个工业级真实场景的经典软件测试案例，研究量子噪声对QELM的影响，揭示QELM对噪声的鲁棒性特征。这些发现有助于评估QELM在当今含噪声量子计算环境下解决工业软件测试问题的可行性。实验结果表明：量子噪声对QELM性能产生显著影响，回归任务性能下降达250%，分类任务下降50%。虽然在机器学习训练与测试阶段同时引入噪声可改善结果，但其降幅仍无法满足实际应用需求。误差缓解技术虽能提升噪声适应能力（分类任务平均性能降幅缩减至3.0%），但其效果受具体场景制约，这凸显了开发针对QELM的定制化误差缓解策略的必要性。