736 publications from this institution
Recently, the state-of-the-art performance in various sensor-based human activity recognition (HAR) tasks has been acquired by deep learning, which can extract automatically features from raw data. In standard convolutional neural networks (CNNs), there is usually the same receptive field (RF) size of artificial neurons within each feature layer. It is well known that the RF size of neurons is able to change adaptively according to the stimulus, which has rarely been exploited in HAR. In this article, a new multibranch CNN is introduced, which utilizes a selective kernel mechanism for HAR. To the best of our knowledge, it is for the first time to adopt an attention idea to perform kernel selection among multiple branches with different RFs in the HAR scenario. We perform extensive experiments on several benchmark HAR datasets, namely, UCI-HAR, UNIMIB SHAR, WISDM, PAMAP2, and OPPORTUNITY, as well as weakly labeled datasets. Ablation experiments show that the selective kernel convolution can adaptively choose an appropriate RF size among multiple branches for classifying numerous human activities. As a result, it can achieve a higher recognition accuracy under a similar computing budget.
This paper described a spring roll-style retractable sampling arm with open cylindrical shell structure. It has small shrink volume, long expand path, low power consumption, large pushing force, and wide adaption, which can be widely used in mini-sampler in dangerous or ungetatable place to sample the rock, dust and other materials. Specifically, the design of the sampling arm is described, and finite element method is then carried out to study the relationship between geometric parameters and the largest pushing force. Finally, a simple and efficient mathematical formula on the maximum pushing force is given and it agrees well with the finite element analysis through the comparison between them. Experimental results show the feasibility of this design.
