Finding similar exercises aims to retrieve exercises with similar testing goals to a given query exercise from the exercise database. As online education evolves， the exercise database is growing in size， and due to the professional characteristic of the exercises， it is not easy to annotate their relations. Thus， online education systems require an efficient and unsupervised model for finding similar exercise. Unsupervised semantic hashing can map high-dimensional data to compact and efficient binary representation under the premise of unsupervised signals. However，it is inadequate to simply apply the semantic hashing model to the similar exercise retrieval model because exercise data contains rich semantic information while the representation space of binary vector is limited. To address this issue， a similar exercise retrieval model was introduced to acquire and retain crucial information. Firstly， a crucial information acquisition module was designed to acquire critical information from exercise data and a de-redundancy object loss was proposed to eliminate redundant information. Secondly， a time-aware activation function was introduced to reduce coding information loss. Thirdly， to maximize the utilization of the Hamming space， a bit balance loss and a bit independent loss were introduced to optimize the distribution of binary representation in the optimization process. Experimental results on MATH and HISTORY datasets demonstrate that the proposed model outperforms the state-of-the-art text semantic hashing model Deep Hash InfoMax （DHIM）， with an average improvement of approximately 54% and 23% respectively across three recall settings. Moreover， compared to the best-performing similar exercise retrieval model QuesCo， the proposed model demonstrates a clear advantage on search efficiency.

In order to solve the local and global contextual information adaptive aggregation problem in traffic scene parsing， a Local and Global Context Attentive Fusion Network （LGCAFN） with three-module architecture was proposed. The front-end feature extraction module consisted of the improved 101-layer Residual Network （ResNet-101） which was based on Cascaded Atrous Spatial Pyramid Pooling （CASPP） unit， and was able to extract object’s multi-scale local features more effectively. The mid-end structural learning module was composed of eight Long Short-Term Memory （LSTM） branches， and was able to infer spatial structural features of object’s adjacent scene regions in eight different directions more accurately. In the back-end feature fusion module， a three-stage fusion method based on attention mechanism was adopted to adaptively aggregate useful contextual information and shield from noisy contextual information， and the generated multi-modal fusion features were able to represent object’s semantic information in a more comprehensive and accurate way. Experimental results on Cityscapes standard and extended datasets demonstrate that compared to the existing state-of-the-art methods such as Inverse Transformation Network （ITN）， and Object Contextual Representation Network （OCRN）， LGCAFN achieves the best mean Intersection over Union （mIoU）， reaching 84.0% and 86.3% respectively， showing that LGCAFN can parse traffic scenes accurately and is helpful to realize autonomous driving of vehicles.

Based on the principle and characteristics of the Differential Power Analysis (DPA) attack, the kernel function was used to estimate the probability distribution density of the leakage of power consumption in the password chip work process. By calculating the mutual information between the attack model and the power leakage, when the guessed key was correct, this paper quantified the risk value of the password chip in the face of DPA attacks. The experiments show that the risk quantification method can be a good estimate of the correlation degree between the attack model and power leakage when the guessed key is correct and then provides important indicators to complete password chip risk evaluation.

In the recommendation system, some new items and the accuracy issue cannot be well controlled. Therefore, a new recommendation method based on general content Probabilitistic Latent Semantic Analysis (PLSA) model was proposed. The general content PLSA model contained two latent variables indicating the user groups and item groups, and contained features of items that were trained by asymmetric learning algorithm. The experimental results show that the new method has good quality for recommendation on three different data sets.

Concerning that the resource in mobile Ad Hoc network is limited and the existing ant routing algorithms are complex, a basic ant routing algorithm was proposed. Based on the analysis of ant routing process, it only maintained basic ant routing mechanism, without any extra overhead, discussed pheromone update and pheromone use which were two key components of the algorithm; moreover, it analyzed their impact on performance by simulation. Finally, the experiment results show that it can get a performance closed to other routing protocols under a lower overhead.