Human activity recognition (HAR) based on sensor data is a significant problem in pervasive computing. In recent years, deep learning has become the dominating approach in this field, due to its high accuracy. However, it is difficult to make accurate identification for the activities of one individual using a model trained on data from other users. The decline on the accuracy of recognition restricts activity recognition in practice. At present, there is little research on the transferring of deep learning model in this field. This is the first time as we known, an empirical study was carried out on deep transfer learning between users with unlabeled data of target. We compared several widely-used algorithms and found that Maximum Mean Discrepancy (MMD) method is most suitable for HAR. We studied the distribution of features generated from sensor data. We improved the existing method from the aspect of features distribution with center loss and get better results. The observations and insights in this study have deepened the understanding of transfer learning in the activity recognition field and provided guidance for further research.

A collaborative planning framework combining the Lagrangian relaxation method and genetic algorithms is developed to coordinate and optimize the production planning of the independent partners linked by material flows in multiple tier supply chains. Linking constraints and dependent demand constraints were added to the monolithic multi-level, multi-item capacitated lot sizing problem (MLCLSP) for supply chains. Model MLCLSP was Lagrangian relaxed and decomposed into facility-separable sub-problems. Genetic algorithms was incorporated into Lagrangian relaxation method to update Lagrangian multipliers, which coordinated decentralized decisions of the facilities in supply chains. Production planning of independent partners could be appropriately coordinated and optimized by this framework without intruding their decision authorities and private information. This collaborative planning scheme was applied to a large set problem in supply chain production planning. Experimental results show that the proposed coordination mechanism and procedure come close to optimal results as obtained by central coordination in terms of both performance and robustness

In trained deep neural networks, unstructured pruning can reduce redundant weights to lower storage cost. However, it requires the customization of hardwares to speed up practical inference. Another trend accelerates sparse model inference on general-purpose hardwares by adopting coarse-grained sparsity to prune or regularize consecutive weights for efficient computation. But this method often sacrifices model accuracy. In this paper, we propose a novel fine-grained sparsity approach, balanced sparsity, to achieve high model accuracy with commercial hardwares efficiently. Our approach adapts to high parallelism property of GPU, showing incredible potential for sparsity in the widely deployment of deep learning services. Experiment results show that balanced sparsity achieves up to 3.1x practical speedup for model inference on GPU, while retains the same high model accuracy as fine-grained sparsity.