Search

The homework tidiness assessment aims to auto evaluate the writing tidiness of homework, playing an important role in daily teaching. However, there is still no comprehensive basis for homework tidiness assessment. For this, a benchmark for homework tidiness assessment (HTA) is proposed. Firstly, a database named HTA 1.0 containing 1000 homework images is collected. Each image is manually annotated by multiple volunteers. Secondly, a comprehensive evaluation protocol is designed, using mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) and accuracy (Acc) as performance indicators. Finally, three deep learning models (i.e., LeNet, AlexNet and VGGNet) are applied as baseline methods and the results are reported and analyzed.

The speech recognition technology makes it possible for people to communicate with intelligent electronic devices. However, existing speech recognition algorithms are overly complex for small intelligent electronic devices (e.g., mini speakers, intelligent toys, intelligent remote controls, etc.). For this, an efficient speech recognition algorithm is proposed. Firstly, the Mel-scale Frequency Cepstral Coefficients (MFCC) is applied to extract features of voices. Secondly, the Support Vector Machines (SVM) is used to train speech classification models. Finally, a speech database is collected to validate the proposed algorithm. The speech database contains 500 audio files of 10 speech commands for an electric motor car driving assistant and 550 audio files of 11 speech commands for a intelligent remote control. The proposed method is evaluated via a 5-fold cross-validation, and experiments show that the propose method acquires 94.20% and 88.73% average accuracy rates for the electric motor car driving assistant and the intelligent remote control, respectively.

Shielding techniques are widely applied in suppression of near electric field interference from power converters, so as to enhance their electromagnetic compatibility (EMC) performance. However, sometimes traditional shielding method cannot effectively suppress the electromagnetic interference (EMI) in the full frequency range. In order to make a power converter meet the limit requirement of EMC standard, this paper proposes an improved non-ideal electric field shielding method to balance the suppression effects of the low frequency and high frequency interference. A resistor with appropriate resistance is connected between the shielding layer and the reference ground so as to balance the suppression effect of the high frequency and the low frequency interference. The EMI measurement results show that the power converter with improved shielding method had good EMC performance.

Electromagnetic interference (EMI) couplings between motor drive and adjacent communication network induce a considerable common-mode (CM) current in sensitive communication cable, which increases the probability of communication error and threatens the reliability of the overall system. In order to improve the communication performance, it is necessary to study the coupling mechanism between the motor drive and the communication network, and to evaluate the effect of the EMI coupling. In this paper, a commercial motor drive system with RS485 communication circuit is used for analysis. The conducted and near-field coupling paths are analyzed and modeled. And a model for estimating the CM current coupled to GND cable is proposed. Besides, communication error rate is employed to evaluate the effect of coupling, and the correlation between error rate and CM current in communication GND cable is established by statistical analysis. And the estimation models of CM current and error rate are validated by measurements.