In power monitoring scenarios， real-time monitoring and analysis of personnel behavior are crucial for ensuring the safe and stable operation of power systems. However， directly exposing facial information in monitoring videos without proper processing poses serious privacy risks. Traditional face detection-based blurring methods face challenges such as insufficient robustness and high computational costs in complex power environments， making them hard to meet both accuracy and real-time requirements. To address these issues， a real-time face blurring method based on head skeleton point detection was proposed. Firstly， a lightweight head skeleton point detection framework based on a hierarchical processing strategy was designed to locate personnel regions in compressed videos rapidly and stitch the cropped areas at original resolution to batch-detect head skeleton points of all the people， thus improving detection efficiency and accuracy. Secondly， an adaptive inter-frame optimization strategy was introduced， to use frame differencing to detect changes in the number of personnel quickly and adjust detection frequency dynamically by incorporating a tracking mechanism for personnel detection boxes， thereby reducing redundant computational overhead effectively. Finally， a prototype system for real-time face blurring was constructed on edge nodes， and its performance was validated through experiments. Experimental results indicate that taking the KAPAO-S model as an example， the proposed method improves the face blurring accuracy in monitoring videos by 3.6 percentage points and reduces the processing time per frame by 2.5 ms approximately compared to the original model， thereby ensuring accuracy and real-time performance at the same time.

Concerning the structural diversity of medical Electronic Health Record （EHR） and the complicated correlation between coding in the automatic International Classification of Disease （ICD） coding task， an Automatic ICD Coding method integrating Heterogeneous Information （AIC-HI） was proposed. Firstly， various feature extractors were designed based on the distinctive characteristics of structured coding， semi-structured description， and unstructured medical text in the coding task. At the same time， the coding knowledge graph was constructed to fit the hierarchical relationship of coding， and the association relationships between different branches were transformed into triples containing head and tail coding. Then representation learning was used to fuse encoding and description information to calculate label features. Finally， the attention mechanism was used to extract the most relevant feature representation in unstructured documents. The experimental results show that， compared with the suboptimal baseline model MARN （Multitask bAlanced and Recalibrated Network）， the microscopic F1-score of the model AIC-HI on the real clinical dataset MIMIC-Ⅲ is increased by 4.3 percentage points.

The traditional Super-Resolution (SR) algorithm, based on sparse dictionary pairs, is slow in training speed, poor in dictionary quality and low in feature matching accuracy. In view of these disadvantages, a super-resolution algorithm based on the improved sparse coding was proposed. In this algorithm, a Morphological Component Analysis (MCA) method with adaptive threshold was used to extract picture feature, and Principal Component Analysis (PCA) algorithm was employed to reduce the dimensionality of training sets. In this way, the effectiveness of the feature extraction was improved, the training time of dictionary was shortened and the over-fitting phenomenon was reduced. An improved sparse K-Singular Value Decomposition (K-SVD) algorithm was adopted to train low-resolution dictionary, and the super-resolution dictionary was solved by utilizing overlapping relation, which enforced the effectiveness and self-adaptability of the dictionary. Meanwhile, the training speed was greatly increased. Through the reconstruction of color images in the Lab color space, the degradation of the reconstructed image quality, which may be caused by the color channel's correlation, was avoided. Compared with traditional methods, this proposed approach can get better high-resolution images and higher computational efficiency.

Through studying on one of the reasons leading to the high cost of mutation testing which is the large number of mutants produced during the process of testing, a mutants reduction method of clustering based on genetic algorithm was proposed. Mutants with similar characteristics would be placed in the same cluster, and then randomly selected one from each cluster as a representative in order to reduce the mutants. The experimental results show that: 1) the proposed method can reduce mutants without compromising the adequacy of the constituted test suite; 2) and compared with K-means algorithm and agglomerative clustering algorithm, it can automatically form an appropriate number of clusters, and is more effective.

For face recognition with single training sample per person, the conventional face recognition methods which work with many training samples do not function well. Especially, a number of methods based on Fisher linear discrimination criterion can not work because the within-class scatter matrix is a matrix with all elements being zero. To solve this problem, a new sample augment method, called generalized slide window, was proposed. In order to effectively maintain and strengthen the within-class and between-class information, the rule, "big window, small step", was adopted to produce a set of window images for each training image. Then, twodimensional Fisher linear discrimination analysis was performed on the window images obtained. The experimental results on ORL face database confirm that the proposed method is feasible and effective in face recognition with single training sample per person.