The differences between different protocols are not considered when selecting identification features in the existing statistical feature-based identification methods. In order to solve the problem, a Semi-supervised Subspace-clustering Protocol Identification Approach (SSPIA) was proposed by combining semi-supervised learning and Fuzzy Subspace Clustering (FSC) method. Firstly, the prior constraint condition was obtained by transforming the labeled sample flow into pairwise constraints information. Secondly, the Semi-supervised Fuzzy Subspace Clustering (SFSC) algorithm was proposed on this basis and was used to guide the process of subspace clustering by using the constraint condition. Then, the mapping between class clusters and protocol types was established to obtain the weight coefficient of each protocol feature, and an individualized cryptographic protocol feature library was constructed for subsequent protocol identification. Finally, the clustering effect and identification effect experiments of five typical cryptographic protocols were carried out. Experimental results show that, compared with the traditional K-means method and FSC method, the proposed SSPIA has better clustering effect, and the protocol identification classifier constructed by SSPIA is more accurate, has higher protocol identification rate and lower error identification rate. The proposed SSPIA improves the identification effect based on statistical features.

When the bubbles of medical plastic bottles are detected, the arbitrariness of the bubble position in the bottle body, the uncertainty of the bubble size, and the similarity between the bubble characteristics and the bottle body characteristics increase the difficulty of detecting the bubble defects. In order to solve the above problems in the detection of bubble defects, a real-time segmentation algorithm based on improved Fast Segmentation Convolutional Neural Network (Fast-SCNN) was proposed. The basic framework of the segmentation algorithm is the Fast-SCNN. In order to make up for the lack of robustness of the original network segmentation scale, the ideas of the usage of the information between the channels of Squeeze-and-Excitation Networks (SENet) and the multi-level skip connection were adopted. Specifically, the deep features were extracted by further down-sampling of the network, the up-sampling operation was merged with SELayer module in the decoding stage, and the skip connections with the shallow layer of the network were increased two times at the same time. Four sets of experiments were designed for comparison on the bubble dataset with the Mean Intersection over Union (MIoU) and the segmentation time for single image of the algorithm used as evaluation indicators. The experimental results show that the comprehensive performance of the improved Fast-SCNN is the best, this network has the MIoU of 97.08%, the average segmentation time for a medical plastic bottle of 24.4 ms, and the boundary segmentation accuracy 2.3% higher than Fast-SCNN, which improves the segmentation ability of tiny bubbles, and this network has the MIoU improved by 0.27% and the time reduced by 7.5 ms compared to U-Net, and the comprehensive detection performance far better than Fully Convolutional Networks (FCN-8s). The proposed algorithm can effectively segment smaller bubbles with unclear edges and meet the engineering requirements for real-time segmentation and detection of bubble defects.

Focusing on the problems such as low inspection speed and low accuracy caused by subjective factors in the manual inspection method of ampoule packaging quality, an inspection algorithm based on machine vision and lightweight neural network was proposed. First, threshold processing, tilt correction and cutting of ampoule regions were performed on the images to be inspected by using the threshold segmentation and affine transformation methods in machine learning. Second, the network structure of the classification algorithm was designed according to the characteristics of images and the requirements of defect recognition. Finally, the ampoule packaging defect dataset was constructed by collecting the images of the production site. After that, the proposed ampoule packaging defect identification network was verified, and the accuracy and inspection speed of the algorithm deployed on the Jetson Nano embedded platform were tested. Experimental results show that, taking the product of five ampoules each box as the example, the proposed ampoule packaging quality inspection algorithm takes 70.1 ms/box averagely, that is up to 14 boxes/s, and has the accuracy of 99.94%. It can achieve online high-precision ampoule packaging quality inspection on the Jetson Nano embedded platform.

The traditional link layer security mechanism can not fundamentally protect the security of information transmission of wireless communication system. In order to solve the problem, a parallel interpolation encryption algorithm based on the parallel modulation characteristics of Orthogonal Frequency Division Multiplexing (OFDM) system and physical layer security was proposed. Firstly, the number of inserted symbols was determined by the number of subcarriers modulated by the OFDM system, and the positions of inserted symbols were generated under the control of key. Secondly, the original OFDM symbols before and after the position of inserted symbol were taken out, and the inserted symbol was determined by calculating the mean value of these symbols. Finally, the pseudo-random interpolation was completed after Inverse Fast Fourier Transform (IFFT). Compared with the traditional link layer security methods, the proposed algorithm can realize the whole encryption of modulation symbols, ensure the security of signaling, flag and data information, and reduce the complexity of algorithm effectively. The simulation experimental results show that, the proposed algorithm can effectively resist a variety of eavesdropping attacks and has little influence on the inherent performance of communication system. Furthermore, the proposed algorithm can be well adapted to Gaussian channel and multipath channel, and shows a certain ability to resist multipath fading.

To solve the problem of data sparsity and cold start which is prevalent in recommender system, a new social recommendation algorithm was proposed, which integrates rating and trust relation. Firstly, the initial trust value of the new user in the network was reasonably assigned, which solves the problem of cold start of the new user. Since the user's preferences were affected by his friends, the user's own feature vector was modified by the trust matrix between friends, which solves the problem of user's feature vector construction and trust transition. The experimental results show that the proposed algorithm has a significant performance improvement over the traditional social network recommendation algorithm.

The existing recommender systems often use the nearest neighbors' preference behavior to predict current users' preference, and their recommendation accuracy are influenced by the lack of consideration that users' preference would change over time. To solve this problem, a cooperative preference prediction method based on time attenuation and preference fluctuation was proposed. First, attenuation increment and attenuation speed were obtained based on time and historical preference, and the attenuation function was generated by attenuation increment and attenuation speed to modify users' historical preference behavior. Then the distribution of historical preference was used to compute the preference fluctuation range. Finally, the recommender list was generated for user by applying the attenuation function and preference fluctuation range into the acquisition of nearest neighbors and the preference acquisition process. The experimental results on real data set show that, compared with the Collaborative Filtering based on Rating Distribution (RDCF) and Optimizing Top- N Collaborative Filtering (OTCF), the average Mean Absolute Error (MAE) of the proposed method is decreased by about 6.42% and 7.73% respectively. It also shows that the proposed method can achieve higher recommendation accuracy and better recommendation quality.

For linear system with time-domain constraints including control input constraints, state constraints or their mixed constraints, an H∞ control scheme via Linear Matrix Inequalities (LMI) optimization was proposed in this paper. First, by assumption of initial states and the energy of external disturbance, a fixed ellipsoid containing all perturbed feasible trajectories was confirmed. Then, sufficient conditions of the closed-loop system satisfying time-domain constraints with the controller gain varying during a certain scope were derived and converted to LMI, and the derivation process was given in detail. Finally, the non-fragile H∞ controller design with time-domain constraints was led to solving an optimization problem with LMI constraints. Simulation results for application in the disturbance reject problem of mass-spring-damper system were discussed. The simulation application results show that the designed controller can improve the robustness of the closed-cloop system with controller gain variations while the time-domain constraints are respected.

Concerning data sparsity and malicious behavior of traditional collaborative filtering algorithm, a new social recommendation method combining trust and matrix factorization was proposed in this paper. Firstly, the incredible nodes in the network were founded by computing their prestige value and bias value, and then the weight of their evaluation would be weakened. Finally, the collaborative recommendation was conducted under the social network circumstance by combining the user-item matrix and trust matrix. The experimental results show that the proposed algorithm reduces the importance of not credible node to weaken the negative influence the false or malicious score brings to recommendation system, the data sparsity and malicious behavior problems can be alleviated, and a higher prediction accuracy than that of the traditional collaborative filtering algorithms can be achieved.

With regard to the dynamic spectrum allocation on wireless cognitive network, a dynamic Bertrand game algorithm of the channel pricing of licensed users was proposed using Bertrand equilibrium. Then, the relationship between stability of Nash equilibrium and speed parameter adjustment was analyzed. Consequently, step response function was utilized to replace the non-concussive process of game, and three-value method was proposed for getting step response parameters. The simulation results show that the proposed algorithm can obtain stable channel price when the value of speed parameter is less than 0. 04. Besides, the feasibility of using a step function to analyze the concussion game process is proved, and this method is convenient for licensed users to make real-time price and bring more economic benefits.

A multi-object optimization model was constructed concerning the overall performance optimization problem of cognition radio system in the process of idle bands allocation. The model realized the maximization of system’s total bandwidth benefit and second user’s access fairness. An intelligent optimization algorithm as well as its concrete implementation were given, which is based on Particle Swarm Optimization (PSO). Simulations were conducted to compare the proposed method with the Color-Sensitive Graph Coloring (CSGC) algorithm under the Collaborative-Max-Sum-Reward (CSUM) and CollaborativeMaxProportional-Fair (CMPF) rules, which took system’s total bandwidth benefit, second user’s access fairness and system’s overall performance as the evaluation guidelines. As a result, the proposed method takes a good tradeoff between total system bandwidth benefit and user’s accessing fairness, and has a better overall system performance.

Traditional outlier detection algorithms fall short in efficiency for their holistic nearest neighboring search mechanism and need to be improved. This paper proposed a new outlier detection method using attribute reduction techniques which enabled the algorithm to focus its detecting scope only on the most meaningful attributes of the data space. Under the reduced set of attributes, a concept of neighborhood-based outlier factor was defined for the algorithm to judge data's abnormity. The combined strategy can reduce the searching complexity significantly and find more reasonable outliers in dataset. The results of experiments also demonstrate promising adaptability and effectiveness of the proposed approach.

The traditional intrusion detection systems mostly adopt the analysis engine of the concentrating type, so it is already difficult to meet extensive security demand of the distributed network environment. While dealing with the exotic pathogeny, the biological immune system demonstrates many characteristics, such as distribution, variety, adaptability and efficiency etc, which offers a new thought of the study of the intrusion detection systems. An immunity-based model combining immune theory and data mining technique for distributed intrusion detection was proposed in this paper. Moreover a detail description was given to the architecture and work mechanism of the model, and the character of the model was analyzed. Finally the future research was presented.