In Query-by-Example Spoken Term Detection （QbE-STD）， the Acoustic Word Embedding （AWE） speech information extracted by Convolutional Neural Network （CNN） or Recurrent Neural Network （RNN） is limited. To better represent speech content and improve model performance， an acoustic word embedding model based on Bi-directional Long Short-Term Memory （Bi-LSTM） and convolutional-Transformer was proposed. Firstly， Bi-LSTM was utilized for extracting features， modeling speech sequences and improving the model learning ability by superposition. Secondly， to learn local information while capturing global information， CNN and Transformer encoder were connected in parallel to form convolutional-Transformer， which taking full advantages in feature extraction to aggregate more efficient information and improving the discrimination of embeddings. Under the constraint of contrast loss， the Average Precision （AP） of the proposed model reaches 94.36%， which is 1.76% higher than that of the Bi-LSTM model based on attention. The experimental results show that the proposed model can effectively improve model performance and better perform QbE-STD.

Leukocyte detection is difficult due to different shapes and degrees of staining of leukocytes during real detection process in complex scenarios. To solve the problem， a dual feature fusion CenterNet based leukocyte detection method TFF-CenterNet （Twice-Fusion-Feature CenterNet） was proposed. Firstly， the features of the backbone network were fused with the features of deconvolution layers through Feature Pyramid Network （FPN）. In this way， the feature extraction ability of the method was improved to solve the problems of individual differences and different degrees of staining of leukocytes. Then， aiming at the problem of severe imbalance between the image area of leukocytes and the background image area， the heatmap loss function was improved to enhance the focus on positive samples of leukocyte and improve detection mean Average Precision （mAP）. Finally， for the characteristics of the tiny target， random location， and cell adhesion of leukocyte images， coordinate attention and coordinate convolution were introduced to improve the attention and sensitivity of leukocyte location information. For leukocytes in complex scenarios， TFF-CenterNet achieves the mAP of 97.01% and the detection speed of 167 frame/s， which are 3.24 percentage points higher and 42 frame/s faster than those of CenterNet respectively. Experimental results show that the proposed method can improve the mAP of leukocyte detection in complex situations while achieving real-time requirements， and improves the robustness， so that this method can provide technical support for rapid automatic leukocyte detection in complementary medical diagnosis.

The traditional social collaborative filtering algorithms based on rating prediction have the inherent deficiency in which the prediction value does not match the real sort， and social collaborative ranking algorithms based on ranking prediction are more suitable to practical application scenarios. However， most existing social collaborative ranking algorithms focus on explicit feedback data only or implicit feedback data only， and not make full use of the information in the dataset. In order to fully exploit both the explicit and implicit scoring information of users’ social networks and recommendation objects， and to overcome the inherent deficiency of traditional social collaborative filtering algorithms based on rating prediction， a new social collaborative ranking model based on the newest xCLiMF model and TrustSVD model， namely SPR_SVD++， was proposed. In the algorithm， both the explicit and implicit information of user scoring matrix and social network matrix were exploited simultaneously and the learning to rank’s evaluation metric Expected Reciprocal Rank （ERR） was optimized. Experimental results on real datasets show that SPR_SVD++ algorithm outperforms the existing state-of-the-art algorithms TrustSVD， MERR_SVD++ and SVD++ over two different evaluation metrics Normalized Discounted Cumulative Gain （NDCG） and ERR. Due to its good performance and high expansibility， SPR_SVD++ algorithm has a good application prospect in the Internet information recommendation field.

The methods of image super-resolution via sparse representation achieve good quality image reconstruction, but the CPU-based implementation of the methods hardly satisfies the requirement of real-time video super-resolution because of high computational complexity. Then, the method of real-time video super-resolution via sparse representation based on GPU acceleration was proposed. It focused on optimizing data parallel processing and improving resource utilization of GPU, including utilizing queues for video sequences, improving memory concurrent access rates, employing Principal Component Analysis (PCA) dimensionality reduction and optimizing dictionary querying operation. As a result, compared with the CPU-based implementation, the speed of data processing is increased two orders of magnitude, and the speed of playing a video with the size of 669×546 reaches 33 frames per second.

Concerning the deficiency of the digital image scrambling algorithm in double scrambling, an image scrambling algorithm based on cloud model was proposed. The algorithm used the function value generated by the three-dimensional cloud model to change the positions and values of the image pixels, to achieve a double scrambling. The experimental verification as well as quantitative and qualitative analysis show that the scrambling image renders white noise and realizes the image scrambling. There is no security issue on cyclical recovery. The algorithm can quickly achieve the desired effect, resistant to shear, plus noise, filtering and scaling attacks. This proves that the algorithm is effective and reasonable, and also can be better applied to the image scrambling.

According to the shape features of mechanical design images, an asynchronous retrieval method based on weighted distance was proposed. The algorithm firstly got preliminary results from the image database by using the circumcircle distance feature, and then calculated the weighted distances between the input image and the preliminary results, by considering both the formal output positions and the Hu invariant moments feature. The experiments show that compared with the traditional methods, the proposed method gets higher precision and recall ratio.

This paper proposed a simple and effective method to remove haze from a single input image degraded by bad weather. First, it estimated the airlight by using dark channel prior knowledge. Then, under a mathematical model for describing the formation of a hazy image, the depth of field of each pixel was sampled to get a virtual haze-free image sequence. Finally, an exposure criterion introduced by exposure fusion algorithm was used to extract a haze-free image from the image sequence by multi-scale fashion image fusion method. The experimental results show that the proposed method can yield good results and it is appropriate for real-time applications.

The hyperspectral remote sensing image is rich in spectrum information, so it has advantages in object recognition. One-Class Support Vector Machine (OCSVM) not only holds the advantages of support vector machines but also only needs the train samples of the recognized objects. The algorithm proposed in this paper selected mathematical model, designed kernel function, adjusted parameter adaptively, and added the theory of OCSVM into the object recognition algorithm for hyperspectral image which improved the precision of recognition and reduced the demand of train samples. Lastly, the experiments were conducted on two hyperspectral images, and the results prove the validity of the proposed method.

A two-stage approach was proposed which can solve the optimal packing of single size rectangles effectively. The best cutting patterns of standard sub-segment were solved and the problem was transformed into one-dimensional cutting stock problems in the first stage. In the second stage the best ideal solution was found with different methods for the one-dimensional cutting stock problems. With this method, an optimal packing of single size rectangles system was developed. The system not only can solve the segment layout of single size rectangles but also can solve other kinds of optimal packing of single size rectangles. Enterprise applications show that this method is an effective solution to the problem of single size rectangles packing.