A badminton training system based on body sensor networks has been proposed. The system may recognize different badminton strokes of badminton players. A two-layer hidden Markov model (HMM) classification algorithm is proposed to recognize 14 types of badminton strokes. In the first layer, we use acceleration magnitude of the right wrist to determine a threshold to detect strokes, and then, the HMM is applied to filter out nonstroke motions. In the second layer, we adopt the HMM to classify all the strokes into 14 categories. Experimental results show that the two-layer HMM can achieve good recognition accuracy. The effectiveness and feasibility of the two-layer HMM classification algorithm have been verified in a comparison.
20 December 2018 in IEEE Transactions on Human-Machine Systems
Human activity recognition techniques based on wearable inertial sensors have achieved great success, but the classification accuracy of human activities using wearable sensors is not good enough in practice. In this paper, a multisensor multiclassifier hierarchical fusion model based on entropy weight for human activity recognition using wearable inertial sensors is proposed. The fusion model has two layers, including basic-classifier fusion layer and sensor fusion layer. The entropy weight method has been applied to achieve the weight values that can affect the decision results of each layer. In addition, a novel feature selection method based on congruent transformation in matrix is also proposed. Three major experiments have been conducted to reveal the feasibility and availability of our algorithms. The experiments show that our fusion algorithm may achieve the better recognition performance when compared with basic classifiers and majority voting. For different feature dimensions, the performance of our algorithm is also better than that of majority voting, and the recognition accuracy rate may reach 96.72%. In addition, the recognition accuracy rate of the proposed feature-selection method is about 96.96%, which is better than the other method.
With the rapid growth of the Internet, a wealth of movie resources are readily available on the major search engines. Still, it is unlikely that users will be able to find precisely the movies they are more interested in any time soon. Traditional recommendation algorithms, such as collaborative filtering recommendation algorithms only use the user’s rating information of the movie, without using the attribute information of the user and the movie, which has the problem of inaccurate recommendations. In order to achieve personalized accurate movie recommendations, a movie recommendation algorithm based on a multi-feature attention mechanism with deep neural networks and convolutional neural networks is proposed. In order to make the predicted movie ratings more accurate, user attribute information and movie attribute information are added, user network and movie network are presented to learn user features and movie features, respectively, and a feature attention mechanism is proposed so that different parts contribute differently to movie ratings. Text features are also extracted using convolutional neural networks, in which an attention mechanism is added to make the extracted text features more accurate, and finally, personalized movie accurate recommendations are achieved. The experimental results verify the effectiveness of the algorithm. The user attribute features and movie attribute features have a good effect on the rating, the feature attention mechanism makes the features distinguish the degree of importance to the rating, and the convolutional neural network adding the attention mechanism makes the extracted text features more effective and achieves high accuracy in MSE, MAE, MAPE, R2, and RMSE indexes.
The remarkable development of human–computer interactions has created an urgent need for machines to be able to recognise human emotions. Human motions play a key role in emphasising and conveying emotions to meet the complexity of daily application scenarios, such as medical rehabilitation and social education. Therefore, this paper aims to explore hidden emotional states from human motions. Accordingly, we proposed a novel approach for emotion recognition using multiple inertial measurement unit (IMU) sensors worn on different body parts. First, the mapping relationship between emotion and human motion was established through fuzzy comprehensive evaluation, and data were collected for six emotional states: sleepy, bored, excited, tense, angry, and distressed. Second, the preprocessed data were used as input in a lightweight convolutional neural network to extract discriminative features. Third, an attention‐based sensor fusion module was developed to obtain the importance scores of each IMU sensor for generating a fused feature representation. In the recognition phase, we constructed a weighted kernel support vector machine (SVM) model with an auxiliary fuzzy function to improve the weight calculation method of kernel functions in a multiple kernel SVM. Finally, the results obtained are compared with those of similar state‐of‐the‐art studies, the proposed method showed a higher accuracy (99.02%) for the six emotional states mentioned above. These findings may promote the development of social robots with non‐verbal emotional communication capabilities.
5 January 2018 in Multimedia Tools and Applications