Only one semantic vector can be generated by word-embedding technologies such as Word2vec or GloVe for polysemous word. In order to solve the problem, a sentiment analysis model based on ELMo (Embedding from Language Model) and Multi-Scale Convolutional Neural Network (MSCNN) was proposed. Firstly, ELMo model was used to learn the pre-training corpus and generate the context-related word vectors. Compared with the traditional word embedding technology, in ELMo model, word features and context features were combined by bidirectional LSTM (Long Short-Term Memory) network to accurately express different semantics of polysemous word. Besides, due to the number of Chinese characters is much more than English characters, ELMo model is difficult to train for Chinese corpus. So the pre-trained Chinese characters were used to initialize the embedding layer of ELMo model. Compared with random initialization, the model training was able to be faster and more accurate by this method. Then, the multi-scale convolutional neural network was applied to secondly extract and fuse the features of word vectors, and generate the semantic representation for the whole sentence. Experiments were carried out on the hotel review dataset and NLPCC2014 task2 dataset. The results show that compared with the attention based bidirectional LSTM model, the proposed model obtain 1.08 percentage points improvement of the accuracy on hotel review dataset, and on NLPCC2014 task2 dataset, the proposed model gain 2.16 percentage points improvement of the accuracy compared with the hybrid model based on LSTM and CNN.

How to improve the accuracy of recommendation is an important issue for the current recommendation system. The matrix decomposition model was studied, and in order to exploit the group structure of the rating data, a Score Similarity based Matrix Factorization recommendation algorithm with Group Sparsity (SSMF-GS) was proposed. Firstly, the scoring matrix was divided into groups according to the users' rating behavior, and the similar user group scoring matrix was obtained. Then, similar users' rating matrix was decomposed in group sparsity by SSMF-GS algorithm. Finally, the alternating optimization algorithm was applied to optimize the proposed model. The latent item features of different user groups could be filtered out and the explanability of latent features was enhanced by the proposed model. Simulation experiments were tested on MovieLens datasets provided by GroupLens website. The experimental results show that the proposed algorithm can improve recommendation accuracy significantly, and the Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) both have good performance.

Due to the swallow and over-enhancement problems of traditional histogram equalization, an improved histogram equalization algorithm combining scene classification and details preservation was proposed. In this algorithm, images were classified according to their histogram features. The parameter of piecewise histogram equalization was optimized according to the scene classification and the characteristics of image histogram. The complexity of the improved algorithm is only O(L).L is the level of image grayscale, and equals to 256 here. The improved algorithm has the small amount of computation and solves the swallow and over-enhancement problems of traditional histogram equalization. The results from TI (Texas Instruments) DM648 platform show the algorithm can be used for real-time video image enhancement.