Automatic detection method of epileptic seizures based on IRCMDE and PSO-SVM

Shovel-loading cooperative control of loader under typical working conditions

The difference in power demand and the driver's operation in various operation stages make the loader have the problem of low energy utilization. Changeable operating objects and drastically changing loads have exacerbated the difficulty of energy-saving research in different operating stages of loaders. Therefore, based on identifying the operation stage and analyzing the load characteristics under typical working conditions of the loader, this paper proposes a shovel-loading cooperative control strategy. Specifically, the Drag Reduction Insertion (DRI) in the shoveling stage is realized based on learning the driving intention. Based on different operation stages, the load characteristics of different materials for shovel-loading are deeply analyzed, and the prediction research of the power output characteristics of the power unit is carried out. The shovel-loading cooperative control solves the problem of the poor economy caused by different power requirements in different operation stages and significantly reduces the impact of the driver's operating experience.

Bird sound recognition based on adaptive frequency cepstral coefficient and improved support vector machine using a hunter-prey optimizer

Bird sound recognition is crucial for bird protection. As bird populations have decreased at an alarming rate, monitoring and analyzing bird species helps us observe diversity and environmental adaptation. A machine learning model was used to classify bird sound signals. To improve the accuracy of bird sound recognition in low-cost hardware systems, a recognition method based on the adaptive frequency cepstrum coefficient and an improved support vector machine model using a hunter-prey optimizer was proposed. First, in sound-specific feature extraction, an adaptive factor is introduced into the extraction of the frequency cepstrum coefficients. The adaptive factor was used to adjust the continuity, smoothness and shape of the filters. The features in the full frequency band are extracted by complementing the two groups of filters. Then, the feature was used as the input for the following support vector machine classification model. A hunter-prey optimizer algorithm was used to improve the support vector machine model. The experimental results show that the recognition accuracy of the proposed method for five types of bird sounds is 93.45%, which is better than that of state-of-the-art support vector machine models. The highest recognition accuracy is obtained by adjusting the adaptive factor. The proposed method improved the accuracy of bird sound recognition. This will be helpful for bird recognition in various applications.