Search

Foreign object detection is an important part of quality control of electricity meters. An automatic detection device is developed based on acoustic identification. In order to suppress background noise interference, we design a novel sound separation algorithm to separate the mixed sound signals to obtain the target source signal produced by foreign objects. Firstly, the improved principal-component-analysis-based multi-layered nonnegative matrix factorization (PMNMF) is used to separate sound signals. Secondly, the SVM is used to classify and identify sound signals. A suppot vector machine (SVM) as the classifier is used to compare the PMNMF algorithm with the basic NMF algorithm. The results indicate that the sound data pre-processed with the improved NMF algorithm results in a significantly higher identification rate up to about 95%.

Performance appraisal politics is widespread in the organization. It provides a new perspective for improving performance appraisal to study its effects on employee attitudes. In addition, its influence on employees’ attitude is still blank. This paper utilizes questionnaire survey and structural equation model to study the impact of different types of perception of performance appraisal politics on employees’ affective commitment. The result shows that different types of perception of performance appraisal politics have different effect on employees’ attitude. Perception of public-private concerned high ratings has positive effect, however, perception of organizational-interested low ratings, selfish high rating perception and self-interested low rating perception have negative effect. The effect strength was decided by employee’s attribution about perception of performance appraisal politics. Perception of organizational support played a complete mediate role in the impact of perception of performance appraisal politics on employees’ affective commitment. Based on the findings of the study, managers can reduce employees’ negative perception of performance appraisal politics and passive consequences by restricting estimators’ selfish leniency and conscious oppressive evaluation, guiding employees to attribute performance appraisal politics positively and enhancing perception of organizational support.