Proliferation of multimodal harmful content on social media harms public interests and disrupts social order severely at the same time， highlighting the urgent need for effective detection methods of this content. The existing researches rely on pre-trained models to extract and fuse multimodal features， often neglect the limitations of general semantics in harmful content detection tasks， and fail to consider complex， dynamic combinations of harmful content. Therefore， a multimodal harmful content detection method based on weakly Supervised modality semantic enhancement （weak-S） was proposed. In the proposed method， weakly supervised modality information was introduced to facilitate the harmful semantic alignment of multimodal features， and a low-rank bilinear pooling-based multimodal gated integration mechanism was designed to differentiate the contributions of various information. Experimental results show that the proposed method achieves the F1 value improvements of 2.2 and 3.2 percentage points， respectively， on Harm-P and MultiOFF datasets， outperforming SOTA （State-Of-The-Art） models and validating the significance of weakly supervised modality semantics in multimodal harmful content detection. Additionally， the proposed method has improvement in generalization performance for multimodal exaggeration detection tasks.

Small sample data can lead to over-fitting problems in machine learning models. In the field of drug development， most data tend to be small samples， which greatly limits the application of machine learning techniques in this field. To solve the above problem， a drug data enhancement method based on graph structure was proposed. The samples were perturbed by the proposed method and new similar samples were generated to expand the dataset. The proposed method are consisted of four sub-methods， which are node discarding method based on molecular backbone， edge discarding method based on molecular backbone， multi-sample splicing methods and hybrid strategy method. In specific， the perturbation of drug molecules was completed by the node and edge discarding method based on molecular backbone in the way of a small number of deletion operation on the composition and structure of drug molecules； the perturbation was completed by the multi-sample splicing method through using an addition operation to combine different molecules； in the hybrid strategy method， the diversity of data enhancement results was improved by combining the deletion and addition operation in a certain ratio. The proposed method improved the Area Under receiver operating characteristic Curve （AUC） of the drug attribute prediction baseline model MG-BERT （Molecular Graph Bidirectional Encoder Representations from Transformer） by 1.94% to 12.49% on public datasets BACE， BBBP， ToxCast and ClinTox. Experimental results demonstrate the effectiveness of the proposed method on small sample drug data enhancement.

Concerning the deployment of virtual machines in the cloud computing, an algorithm on the deployment of virtual machines with clustering method based on frame load awareness was proposed. First of all, the load of each layer in datacenter was computed and the clustering of physical machines in each layer was constructed. In the process of deploying virtual machines, the clustering of virtual machines was first done according to some rules and then the frame with lower load was chosen preferentially. The last step was to match the virtual machines cluster and physical machines cluster in order to deploy the optimal physical machines cluster. The performance of the algorithm was validated with the experiments in CloudSim. The result was compared to that of the greedy algorithm and basic deployment algorithm with the frame load awareness, which shows that the algorithm proposed in this article has evident priority, and improves the utilization rate of network resources.

To solve the detection problem of selfish behavior in IEEE802.15.4 Wireless Sensor Network (WSN), an improved Sliding Window Non-parameter Cumulation Sum (SWN-CUSUM) algorithm based on statistics was proposed to decrease the detection delay. By tracing the delay characteristic sequence between successful transmissions, the algorithm could distinguish if there was a selfish behavior in the WSNs. The NS2 simulation tool was conducted to validate the feasibility of the proposed algorithm. The experimental results show that the improved algorithm not only weakens the impact of the threshold on the performance of the algorithm, but also reduces the size of sliding window used to detect selfish behavior, and the improved algorithm makes improvement in the calculation and the detection delay than the primitive SWN-CUSUM algorithm, so the improved algorithm can detect effectively and rapidly the selfish behavior of nodes in IEEE802.15.4 WSNs.