Social force model is a classical model in crowd simulation. Since it was proposed in 1995, the model has been widely used and modified. In 2000, the concept of panic degree was added to the model to propose an improved version. Although many studies focus on social force model, there are few studies on this concept. Therefore, some key parameters and the concept of panic degree in the social force model were analyzed, and the change of panic degree was used to explain the phenomenons of "fast is slow" and "herd behavior" in crowd evacuation. To overcome the problem in the original model:very few pedestrians may not follow others or may not evacuate at the exit in some conditions caused by the not detailed enough description of pedestrian perception in social force model, the visual field range description of the pedestrian was added and the self-motion state for the pedestrian was redefined and other methods were performed to optimize the social force model. Experimental results show that the improved model can simulate the crowd's herd phenomenon well and is helpful for understanding the concept of panic degree in social force model.

There are two main contradictions in the existing electronic voting schemes, one is to ensure the legality and compliance of election behavior while ensuring the anonymity of election process, and the other is to ensure the privacy security of ballot information while ensuring the public verifiability of election results. Focusing on these contradictions, a decentralized electronic voting scheme based on Ethereum blockchain and zero-knowledge proof was proposed. In the proposed scheme, the non-interactive zero-knowledge proof algorithm and decentralized blockchain architecture were fused to build zero knowledge proof of voter identity and zero knowledge proof of ballot legality. And smart contract and Paillier algorithm were used to realize self-counting without trusted third-party counting mechanism. The theoretical analysis and simulation results show that the scheme can achieve security requirements of electronic voting and can be applied to small-scale community election.

The number of defect region samples is far less than that of the normal region samples in aircraft engine borescope inspection image defect detection task, and the defect samples cannot cover the whole sample space, which result in poor generalization of the detection algorithms. In order to solve the problems, a new interactive data augmentation method based on style transfer technology was proposed. Firstly, background image and defect targets were selected according to the interactive interface, and the informations such as size, angle and position of the target needed to be pasted were specified according to the background image. Then, the style of background image was transferred to the target image through style transfer technology, so that the background image and the target to be detected had the same style. Finally, the boundary of the fusion region was modified by Poisson fusion algorithm to achieve the effect of natural transition of the connected region. Two-class classification and defect detection were conducted to verify the effectiveness of the proposed method. The testers achieve 44.0% classification error rate for the two-class classification on the dataset with real images and augmented images averagely. In the detection task based on Mask Region-based Convolutional Neural Network (Mask R-CNN) model, the proposed method has the Average Precision (AP) of classification and segmentation improved by 99.5% and 91.9% respectively compared to those of the traditional methods.

For a Mobile Crowd Sensing (MCS) network has a large group of participants, and the acquisition and submission of tasks are almost unrestricted, so that data redundancy is high and data quality cannot be guranteed. To solve the problem, a method called Participant Reputation Evaluation Scheme (PRES) was proposed to evaluate the data quality and the reputation of participants. A participant's reputation was evaluated from five aspects:response time, distance, historical reputation, data correlation and quality of submitted data. The five parameters were quantified, and a regression equation was established by using logistic regression model to get the participant reputation after submitting data. The reputation credibility of a participant was in the interval[0.0, 1.0], and concentrated in[0.0,0.2] and[0.8, 1.0], making it easier for the group of mental perception network to choose appropriate participants, and the accuracy of the evaluation results by the crowd sensing showed that PRES was more than 90%.

Domain Name System (DNS) provides domain name resolution service, i.e., converting domain names to IP addresses. Malicious domain detection is mainly for discovering illegal activities and ensuring the normal operation of the domain name servers. Prior work on malicious domain name detection was summarized, and a new machine learning based malicious domain detection algorithm for exploiting multiple-dimensional features was further proposed. With respect to domain name lexical features, more fine-grained features were extracted, such as the conversion frequency of the numbers and letters and the maximum length of continuous letters. As for the network attribute features, more attentions were paid to the name servers, such as the quantity, and the degree of dispersion. The experimental results show that the accuracy, recall rate, F1 value of the proposed method reaches 99.8%, which means a better performance on malicious domain name detection.

In order to overcome the non-person entity's interference, the difficulties in selection of feature words and muti-person influence on target personal relation extraction, this paper proposed person judgment based on decision tree, relation feature word generation based on minimum set cover and statistical approach based on three-layer sentence pattern rules. In the first step, 18 features were extracted from attribute files of China Conference on Machine Learning (CCML) competition 2015, C4.5 decision was used as the classifier, then 98.2% of recall rate and 92.6% of precision rate were acquired. The results of this step were used as the next step's input. Next, the algorithm based on minimum set cover was used. The feature word set covers all the personal relations as the scale of feature word set is maintained at a proper level, which is used to identify the relation type in text headline. In the last step, a method based on statistics of three-layer sentence pattern rules was used to filter small proportion rules and specify the sentence pattern rules based on positive and negative proportions to judge whether the personal relation is correct or not. The experimental result shows the approach acquires 82.9% in recall rate and 74.4% in precision rate and 78.4% in F1-measure, so the proposed method can be applied to personal relation extraction from text headlines, which helps to construct personal relation knowledge graph.

The details of phase information are lost in the use of mean filtering algorithm to repair singular point by using Stoilov phase shift algorithm, which leads to incorrect phase calculation. In order to solve this problem, a new weighted mean filtering algorithm based on short distance priority was proposed. First, singular points were marked by statistical approach. Then, the size of filter window, which was built basing on the short distance priority principle for each singular point, was up to the number of non-singular points and the shortest distance in current situation. Last, this algorithm used the weighted mean of the non-singular points in the window instead of the singular point to implement singular point correction. The experimental results show that window is more detailed in this method, and the proposed method can effectively remove impulse noise, especially may have advantage in protecting details of phase, and may reduce Root Mean Squared Error (RMSE) less than 0.06 cm in the actual measurement experiments.

Aiming at the problem of mismatching of the extreme points in extremum method for digital speckle images, a new algorithm named the whole pixel extremum displacement measurement for laser speckle images with multi-level crossing was proposed. The extremum method was used to figure out the extreme points of speckle images before and after displacement, constructed extremum value matrix and generated 3-D figure. Then the truncation points were got by multiple specified gray planes crossing 3-D figure. And relative displacement matrix of truncation points was analyzed to calculate displacement of object. The simulation results under the condition of no noise and noise prove that the improved algorithm under guaranteeing the accuracy of displacement measurement, decreases the number of extreme points of error matching and improves operation efficiency 10³ times. The algorithm was applied to the laser mouse positioning and the experimental results show that the displacement of the mobile resolution reached 1 microns, and moving direction angle error was less than 2.72°. It is conclued proves that multi-level truncation extremum displacement method based on laser speckle image is a rapid, efficient and practical algorithm.

Optimum Multi-user Detection (OMD) technique can achieve the theoretical minimum error probability, but it has been proven to be a Non-deterministic Polynomial (NP) problem. As a new swarm intelligence algorithm, Artificial Bee Colony (ABC) algorithm has been widely used in various optimization problems. However, the traditional Binary Artificial Bee Colony (BABC) algorithm has the shortcomings of slower convergence speed and falling into local optimum easily. Concerning the shortcomings, an improved binary artificial bee colony algorithm was proposed and used for optimum multi-user detection. The initialization process was simplified. The one-dimensional-reversal neighborhood search strategy was adopted. Compared with optimum multi-user detection, the computation complexity of the improved algorithm declines obviously. The simulation results show that the proposed scheme has significant performance improvement over the conventional detection in anti-multiple access interference and near-far resistance.