To address the problem that the existing short-term power load forecasting methods have difficulty in effectively modeling non-linear structures and lack cross-scale and cross-variable interaction capabilities， a short-term power load forecasting model based on Dynamic Convolution Decomposition and Multi-Scale Graph （DCDMSG） was proposed. First，to cope with the complex non-linear structure， a dynamic convolution decomposition method was adopted to decompose the trend and seasonal items in the load sequence. Second， the trend item was forecasted using a linear layer directly， and for the seasonal item， a multi-scale sequence was constructed for deep modeling using an adaptive multi-scale sequence construction method. Third， to model the complex dependencies within and outside the multi-scale sequence， a multi-scale fusion graph was used to capture dependencies within sequences at different scales， a multi-variable correlation graph was utilized to model correlations between variables， and a multi-scale mix-hop propagation was employed to aggregate features in the graph. Finally， the seasonal items were forecasted， and the obtained forecast results were weighted and fused with the trend items' forecast results to obtain the final forecast values. Experimental results show that， on the Australian dataset， the Mean Absolute Error （MAE） and Root Mean Square Error （RMSE） of DCDMSG reached 0.379 MW and 0.529 MW， respectively， which were reduced by 7.11%-21.37% and 9.88%-26.32% compared with all comparison models. On the Cele dataset， DCDMSG achieved an MAE of 0.437 MW and an RMSE of 0.708 MW， representing decreases of 5.61%-24.66% and 5.22%-24.12% over all comparison models. In the short-term power load forecasting task， DCDMSG effectively improves the forecast accuracy through seasonal-trend decomposition as well as cross-scale and cross-variable modeling.

Aspect-Based Sentiment Analysis （ABSA） is a fine-grained sentiment analysis task aiming to analyze sentiment polarity of specific aspect words in a given text. Existing ABSA methods use Graph Convolutional Network （GCN） to process syntactic and semantic information， but they treat all syntactic dependencies of aspect words equally， ignoring the impact of distant unrelated words on target aspect words， resulting in inappropriate weight allocation of target aspect words and viewpoint words， and insufficient extraction of semantic information. Aiming at these issues， an ABSA model integrating syntax and sentiment knowledge was proposed. Firstly， a reachability matrix was constructed according to syntactic information. Based on this， a syntactic enhancement graph was constructed by weighting the central position through the aspect words. Secondly， a semantic enhancement graph was constructed by external emotional knowledge and aspect enhancement， and graph convolution was used to fully model the syntactic enhancement graph and semantic enhancement graph， respectively， so as to form different feature channels. Thirdly， biaffine attention was used to integrate syntactic and semantic information effectively. Finally， average-pooling and concatenation operations were used to obtain the final feature vectors corresponding to the aspect words. Experimental results indicate that compared with the deep dependency aware graph convolutional network model — DA-GCN-BERT （deep Dependency Aware GCN+BERT（Bidirectional Encoder Representations from Transformers））， the proposed model achieves the accuracy improvements of 1.71， 1.41， 1.27， 0.17， and 0.43 percentage points on five publicly available datasets， respectively. It can be seen that the proposed model has strong applicability in the ABSA field.

Sentiment classification in psychological counseling scenes aims to obtain the sentiment polarity of the inquirer’s utterance， which can provide support for establishing psychological counseling Artificial Intelligence （AI） assistants. Existing methods obtain the sentiment polarity of text through contextual information， failing to consider the sentiment transmission between the current sentence and the forward neighbor sentences in the dialogue record. To address the issue， a model for sentiment classification of psychological counseling text was proposed based on Attention Over Attention （AOA） mechanism. Historical sentiment words were assigned weights by temporal sequence， which improved the accuracy of sentiment classification for psychological counseling text. In a dialogue， historical sentiment word sequences of both sides were extracted by constructed sentiment lexicon of mental health. Subsequently， the current sentence and two sequences of historical sentiment words were input into the Bidirectional Long Short-Term Memory （BiLSTM） network to get corresponding feature vectors. The Ebbinghaus forgetting curve was used to allocate internal weights to the sequences of historical sentiment words. Both inertia features and interaction features were captured by AOA mechanism. Then， the above two features along with the text features were input into the classification layer， calculating the probability of sentiment polarity. Experimental results on public dataset Emotional First Aid Dataset show that the proposed model improves F1 value by 1.55% compared with Capsule network and Directional Graph Convolutional Network （Caps-DGCN） model. Hence the proposed model can effectively improve the sentiment classification effect of psychological counseling text.

As one of the basic tasks of natural language processing， new word identification provides theoretical support for the establishment of Chinese dictionary and analysis of word sentiment tendency. However， the current new word identification methods do not consider the homophonic neologism identification， resulting in low precision of homophonic neologism identification. To solve this problem， a Chinese homophonic neologism discovery method based on Pinyin similarity was proposed， and the precision of homophonic neologism identification was improved by introducing the phonetic comparison of new and old words in this method. Firstly， the text was preprocessed， the Average Mutual Information （AMI） was calculated to determine the degree of internal cohesion of candidate words， and the improved branch entropy was used to determine the boundaries of candidate new words. Then， the retained words were transformed into Chinese Pinyin with similar pronunciations and compared to the Chinese Pinyin of the old words in the Chinese dictionary， and the most similar results of comparisons would be retained. Finally， if a comparison result exceeded the threshold， the new word in the result was taken as the homophonic neologism， and its corresponding word was taken as the original word. Experimental results on self built Weibo datasets show that compared with BNshCNs （Blended Numeric and symbolic homophony Chinese Neologisms） and DSSCNN （similarity computing model based on Dependency Syntax and Semantics）， the proposed method has the precision， recall and F1 score improved by 0.51 and 5.27 percentage points， 2.91 and 6.31 percentage points， 1.75 and 5.81 percentage points respectively， indicating that the proposed method has better Chinese homophonic neologism identification effect.

Aiming at the problem of the difficulty in privacy protection and the cost increase caused by privacy protection in the user data submission stage in Mobile Crowd Sensing (MCS), CS-MVP algorithm for joint privacy protection and CS-MAP algorithm for independent privacy protection of the attributes of user submitted data were designed based on the principle of Local Differential Privacy (LDP). Firstly, the user submitted privacy model and the task data availability model were constructed on the basis of the attribute relationships. And CS-MVP algorithm and CS-MAP algorithm were used to solve the availability maximization problem under the privacy constraint. At the same time, in the edge computing supported MCS scenarios, the three-layer architecture for MCS under privacy protection of the user submitted data was constructed. Theoretical analysis proves the optimality of the two algorithms under the data attribute joint privacy constraint and data attribute independent privacy constraint respectively. Experimental results show that under the same privacy budget and amount of data, compared with LoPub and PrivKV, the accuracy of user submitted data recovered to correct sensor data based on CS-MVP algorithm and CS-MAP algorithm is improved by 26.94%, 84.34% and 66.24%, 144.14% respectively.

To improve the accuracy of short video content distribution, the interest tendencies and the personalized demands for short video content of social groups that the users belong to were analyzed, and in the short video application scenarios based on the active recommendation approaches, a short video content distribution strategy was designed with the goal of maximizing the profit of video content providers. Firstly, based on the federated learning, the interest prediction model was trained by using the local album data of the user group, and the user group interest vector prediction algorithm was proposed and the interest vector representation of the user group was obtained. Secondly, using the interest vector as the input, the corresponding short video content distribution strategy was designed in real time based on the Combinatorial Upper Confidence Bound (CUCB) algorithm, so that the long-term profit obtained by the video content providers was maximized. The average profit obtained by the proposed strategy is relatively stable and significantly better than that obtained by the short video distribution strategy only based on CUCB; in terms of total profit of video providers, compared with the Upper Confidence Bound (UCB) strategy and random strategy, the proposed strategy increases by 12% and 30% respectively. Experimental results show that the proposed short video content distribution strategy can effectively improve the accuracy of short video distribution, so as to further increase the profit obtained by video content providers.

Due to the problems of slow speed and error drift in the positioning of large-scale long-sequence Unmanned Aerial Vehicle (UAV) images, a positioning algorithm of UAV images based on scene graph division was proposed according to the characteristics of UAV images. Firstly, the Global Positioning System (GPS) ancillary information was used to narrow the spatial search scope for feature matching, so as to accelerate the extraction of corresponding points. After that, visual consistency and spatial consistency were combined to construct the scene graphs, and Normalized Cut (Ncut) was used to divide them. Then, incremental reconstruction was performed to each group of scene graphs. Finally, all scene graphs were fused to establish a 3S scene model by Bundle Adjustment (BA). In addition, the GPS spatial constraint information was added to the cost function in the BA stage. In the experiments on four UAV image datasets, compared with COLMAP and other Structure From Motion (SFM) algorithms, the proposed algorithm has the positioning speed increased by 50%, the reprojection error decreased by 41%, and the positioning error was controlled within 0.5 m. Through the experimental comparison of algorithms with or without GPS assistance, it can be seen that BA with relative and absolute GPS constraints solves the problem of error drift, avoids the ambiguous results and greatly reduces positioning error.

For the actual background of the shortage of self-owned vehicles of the transporters in the early stage of emergency, the combinatorial optimization problem of hybrid vehicle paths with transportation mode of joint distribution of self-owned vehicles and vehicles rented by third-party was studied. Firstly, with the different interests between demand points and transporters considered, a multi-objective hybrid vehicle routing optimization model with soft time windows was established with the goal of maximizing system satisfaction and minimizing system delivery time and total cost. Secondly, the shortcomings of NSGA-Ⅱ algorithm in solving this kind of problems such as poor convergence and uneven distribution of Pareto frontiers were considered, the heuristic strategy and pheromone positive feedback mechanism of ant colony algorithm were used to generate offspring population, non-dominated sorting strategy model was used to guide the multi-objective optimization process, and the variable neighborhood descent search was introduced to expand the search space. A multi-objective non-dominated sorting ant colony algorithm was proposed to break through the bottleneck of the original algorithm. The example shows that the proposed model can provide reference for decision makers to choose reasonable paths according to different optimization objectives in different situations, and the proposed algorithm shows better performance in solving different scale problems and different distribution type problems.

To solve load balancing problem of Power Line Communication (PLC) network in Smart Grid (SG), an adaptive opportunistic routing protocol named LBORP (Load Balancing Opportunistic Routing Protocol) was proposed. All the candidate forwarding nodes receiving a packet in LBORP had the opportunity to participate in packet forwarding. As a result, packet forwarding was no longer limited to one routing path, which avoided load imbalance caused by traffic with only one link for traffic to pass. And forwarding priority of the candidate forwarding nodes considered not only the distance from forwarding nodes to destination node, but also instability of PLC links and change of traffic. Besides, an implicit acknowledgment scheme was adopted in LBORP, further reducing the end-to-end delay of the proposed protocol. In simulation experiment, compared to PLC-TR (Power Line Communication-Tree Routing) and PLC-OR (Power Line Communication-Opportunistic Routing), LBORP reduced delay by 19.7% and 45.8% respectively and reduced packet loss rate by 23.4% and 32.5% respectively. Experimental results show that LBORP can achieve network load balancing, improve network reliability and reduce end-to-end delay.

The traditional road information extraction method is high-cost and slow-update. Compared with it, road or marine lane information extraction from crowdsourcing trajectory data is low-cost and easier to update. However, it is difficult to extract lane boundary due to vessel trajectory data with high noise, large data volume and uneven distribution across different regions. To solve this problem, an extraction method of marine lane boundary from exploiting trajectory big data was proposed. Firstly, the parallelized denoising, interpolation and trajectory segmentation for trajectory big data was conducted. Then, based on parallelization and Geohash-encoded spatial clustering, trajectory data was simplified into multiple square regions. The regions were divided and the NiBlack method was extended as SpatialNiBlack algorithm to recognize regions on lane. Finally, based on the filtering results, del-alpha-shape algorithm was proposed to construct a Delaunay triangulation network and obtain marine lane boundary. The theoretical analysis and experimental results show that the proposed method can achieve an accuracy of 86.7% and a recall rate of 79.4% when the maximum density value is 200, minimum density value is 10, length and width of window are 5 and 5 respectively. The experimental results show that the proposed method is effective to extract valuable marine lane boundaries from large-scale trajectory data.

Since the cost of mobile crowdsensing in full coverage of area is excessively high, a Compressive Sensing-based mobile crowdsensing Task Distribution (CS-TD) mechanism was proposed. Firstly, an overall cost model of perceived task was proposed. In this model, the number of nodes participating in a perceived task, the number of nodes perceived and data uploaded were comprehensively considered. Then based on cost model, the daily movement trajectory of sensory node was analyzed, by combining with the compressed sensing data acquisition technology, a compressed sensing sampling method based on perceived node trajectory was proposed. Secondly, the optimal node set was selected by the Region Covers Least Nodes (RCLN) algorithm, the tasks were assigned to the nodes, and then the compressed sensing technology was used to recover node data. Finally, the trustworthiness of perceived node was evaluated in iteration of multiple perceived tasks to ensure the optimality of task plan. The CS-TD distribution model was tested several times. Compared with the existing CrowdTasker algorithm, the average cost of CS-TD algorithm is reduced by more than 30%. CS-TD model can effectively reduce consumption of sensing node and reduce overall perceived cost in full coverage sensing task.

The existing hyperspectral image compression algorithms that aim at high compression quality generally have problems such as high computational complexity, off-line processing, and difficulty in implementing an embedded platform. They are difficult to be implemented in practical applications at present. To resolve the above problems, a real-time compression method for embedded hyperspectral images based on Karhunen-Loeve Transform (KLT) and HEVC (High Efficiency Video Coding) was designed. Firstly, the inter-spectral correlation was reduced by KLT. Then, the spatial correlation was removed by HEVC. Finally, the process of quantization and entropy coding was accomplished by HEVC. Based on NVIDIA Jetson TX1 platform, a heterogeneous parallel compression system which utilizes both the CPU and GPU was designed and implemented. Using real data sets, the performance of the designed algorithm and the practicability of the implemented platform were verified. The experimental results show that compared with the Discrete Wavelet Transform (DWT)+JPEG2000 algorithm, the reconstruction accuracy is improved significantly under the same compression ratio. The Peak Signal-to-Noise Ratio (PSNR) is increased by 1.36 dB on average; at the same time, compared with CPU, performing KLT calculations on GPU can also reduce the runtime by 33% at most.

To solve the traffic load-imbalance problem in electric power communication networks based on Open Shortest Path First (OSPF) protocol, an efficient Two-Step Optimized OSPF Protocol (TSO-OSPF) algorithm was proposed to balance the traffic in intra-area and inter-area of OSPF respectively. The bandwidth utilization and delay were adopted as link weights, the inward and outward traffic of a router was considered, the overloaded branches were decomposed into multiple routers to minimize the maximum traffic flow, thus the traffic-imbalance problem of internal and boundary router in the electric power communication networks was solved. The simulation results show that the TSO-OSPF algorithm can effectively balance the traffic in the network and reduce the packet loss rate by about 10% compared with the OSPF algorithm.

The binary descriptor based on Learned Arrangements of Three Patch Codes (LATCH) lacks of scale invariance and its rotation invariance depends upon feature detector, so a new feature detection and description algorithm was proposed based on Oriented fast and Rotated Binary robust independent elementary feature (ORB) and LATCH. Firstly, the Features from Accelerated Segment Test (FAST) was adopted to detect corner feature on the scale space of image pyramid. Then, the intensity centroid method of ORB was used to obtain orientation compensation. Finally, the LATCH was used to describe the feature. The experimental results indicate that, the proposed algorithm has the characteristics of low computational complexity, high real-time performance, rotation invariance and scale invariance. Under the same accuracy, the recall rate of the proposed algorithm is better than ORB and HARRIS-LATCH algorithm, the matching inner rate of the proposed algorithm is higher than ORB algorithm by 4.2 percentage points. In conclusion, the proposed algorithm can reduce the performance gap with histogram based algorithms such as Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Feature (SURF) while maintaining the real-time property, and it can deal with image sequence in real-time quickly and exactly.

In the era of big data, the social security data becomes more diverse and its amount increases rapidly, which challenges the analysis and decision of social security events significantly. How to accurately categorize the attack behavior in a short time and support the analysis and decision making of social security events becomes an urgent problem needed to be solved in the field of national and cyberspace security. Aiming at the behavior of aggression in social security events, a new Distributed Neural Network Classification (DNNC) algorithm was proposed based on the Spark platform. The DNNC algorithm was used to analyze the related features of the attack behavior categories, and the features were used as the input of the neural network. Then the function relationship between the individual features and attack categories were established, and a neural network classification model was generated to classify the attack categories of social security events. Experimental results on the data provided by the global terrorism database show that the proposed algorithm can improve the average accuracy by 15.90 percentage points compared with the decision tree classification, and by 8.60 percentage points compared with the ensemble decision tree classification, only decreases the accuracy on part attack type.

Data transmission based on opportunistic communication in mobile crowdsensing may take a long period of time. To address this issue, a new Hub-based multi-Task Assignment (HTA) algorithm was proposed. In this algorithm, some nodes were selected to perform as the hubs which could help the requester node to deliver the tasks, according to the different characteristics of the social relationship of the nodes in mobile networks. When the task requester encountered a hub node, the hub node itself and its slave nodes were assigned tasks. After that, the hub node would distribute the tasks to the salve nodes, and received the results from them. Simulations were conducted on The ONE simulator. Compared with the oNline Task Assignment (NTA) algorithm, HTA algorithm reduced the time cost by 24.9% on average and improved the task completion ratio by 150% on average. The experimental results demonstrate that HTA algorithm can accelerate the accomplishment speed of the task and reduce the time cost.

To solve the fault localization problem in electric power communication network, the large-scale connected area fault alarms caused by device or link faults were investigated, and a fault localization algorithm based on fault propagation model and supervised learning method was proposed. First, an improved fault propagation model was used to obtain an initial result with the minimum faults. Then the fault localization problem was transformed into a supervised classification problem by fault alarm vector decomposition to localize the faults within the fault warning areas. Finally, conjectural fault devices and links were added to improve the location results of previous two steps and increase the accuracy. The simulation results show that accuracy of fault localization of the proposed algorithm reaches 84%-95%, which achieves high reliability in fault location.

In electric power communication networks, load balance can reduce overloading on bottlenecks and improve the reliability and utilization of network resources. According to structure and flow characteristics of electric power communication network, a load balanced routing protocol combined with deterministic routing and opportunistic routing was proposed. Each node determined candidate sets to relay data packets from an area centered by it. Each candidate according to the precise local cost and the estimated remaining cost, and the forwarding probability was determined based on the priority. Compared with Load Balance Advanced-Open Shortest Path First (LBA-OSPF) protocol, the proposed routing protocol can reduce the average load by 32.3% and reduce the end-to-end delay by 50.3%.

The current method of image classification which uses the Speed Up Robust Feature (SURF) is low in efficiency and accuracy. To overcome these shortages, this paper proposed an approach for image classification which uses the statistical features of the SURF set. This approach took all dimensions and scale information of the SURF as independent random variables, and split the data with the sign of Laplace response. Firstly, the SURF vector set of the image was got. Then the feature vector was constructed with the first absolute order central moments and weighted first absolute order central moments of each dimision. Finally, the Support Vector Machine (SVM) accomplished the image classification process with this vector. The experimental results show that the precision of this approach is better than that of the methods of SURF histogram and 3-channel-Gabor texture features by increases of 17.6% and 5.4% respectively. By combining this approach with the HSV histogram, a high-level feature fusion method was got, and good classification performance was obtained. Compared with the fused method of the SURF histogram and HSV histogram, the fused method of 3-channel-Gabor texture features and HSV histogram, and the multiple-instance-learning method based on the model of Bag of Visual Word (BoVW), the fused method of this approach and HSV histogram has better precision with the increases of 5.2%, 6.8% and 3.2% respectively.

Bursty topics detection on microblog is an import branch of online public opinion analysis, and has attracted much attention from international scholars. In this paper, a new approach of calculating users' influence was proposed based on the analysis of users' behavior characteristics. Combining the user influence with text features and propagation features, this paper defined a concept named Bursty which is used to judge if a word was a burst word. Being judged by Bursty, burst words can be extracted from microblog corpus. Hierarchical clustering algorithm was introduced to cluster the burst words and chose appropriate burst word clusters to describe bursty topics on microblog in order to realize bursty topics detection on microblog. In experiments, the precision, recall and F-measure reached 63.64%,87.5% and 74% respectively. The method is proved effective on bursty topic detection based on mass microblog data.

There are many illegal Web pages on the Internet, which may have pornographic, violent, gambling or reactionary content. Without being filtered effectively, they will exercise a malign influence on the searching services. An improved K-Nearest Neighbors (KNN) classification algorithm to promote the recognition accuracy was proposed and implemented on a virtualized platform following the MapReduce model provided by the open source software Hadoop, which made it distributed and parallel. Through experiments and comparison with the existing work, it is proved that the proposed recognition method improves the accuracy and efficiency greatly. The algorithm is implemented on a virtualized platform following the MapReduce model provided by the open source software Hadoop, which makes it distributed and parallel. Through experiments and comparison with existing work, it is proved that the recognition method we propose improves the accuracy and efficiency greatly.

The influence of social network is closely related with its structural characteristics. Based on the data from Sina microblog, the distributions of the number of followers and followings were analyzed and found that the number of followers and followings both were power-law distributed. The distance characteristic between different pairs of nodes was discussed, and it was found and proved that there was "small-world" phenomenon in the microblog network. At last, the links between nodes in the network were investigated and found that the formation of the link satisfied triple closure principle. The investigation results on the above three topics are important for us to explore the relationship between the influence of micro-blog and the structural characteristics of its underlying social network, as well as to the design of mechanisms to control the influence.

A Two-hop Incentive Compatible (TIC) routing protocol was proposed for DisruptionTolerant Networks (DTN) to defend the degradation of communication performance caused by selfish nodes. TIC selected the optimal relay node, which took both the encounter probability and transmission cost into account and ensured that nodes could maximize their profit when they reported their encounter probability and transmission cost honestly. At the same time, a signature technology based on bilinear map was introduced to ensure the selected relay nodes to get the payment securely, which can effectively prevent the malicious nodes from tampering the messages.

In order to avoid network congestion, concerning that the current algorithms have not considered the aspects of network flow distribution and user's perception, a routing algorithm which can realize maximum load balance was proposed. The algorithm can decrease the maximal bandwidth utilization rate of network with delay guaranteed. The experiment based on real Abilene2 network topology shows that the proposed algorithm can alleviate the network congestion and improve the network utilization rate over 50% effectively. Compared with the existing algorithms, the proposed algorithm can meet two requirements of the bandwidth utilization and network delay. In addition, by adjusting the parameter values it can meet different business requirements in actual networks.

A new Particle Swarm Optimization (PSO) algorithm with linearly decreasing and dynamically changing inertia weight named L-DPSO was presented to solve the problem that the linearly decreasing inertia weight of the PSO cannot match with the nonlinear changing characteristic. The linear strategy of linearly decreasing inertia weight and the nonlinear strategy of dynamically changing inertia weight were used in the algorithm. The weights were given to two methods separately. Using the test functions of Griewank and Rastrigin to compare L-DPSO with linearly decreasing inertia weight (LPSO) and dynamically changing inertia weight (DPSO), the experimental results show that the convergence speed of L-DPSO is obviously superior to LPSO and DPSO, and the convergence accuracy is also increased. At last, the test functions of Griewank and Rastrigin were used to compare L-DPSO with several commonly used inertia weights, and results show that L-DPSO has obvious advantage too.

Password-based Authenticated Key Agreement (PAKA) is an important research point of Authenticated Key Agreement (AKA) protocols. The authors analyzed a new protocol named three-party Round Efficient Key Agreement (3REKA) and found that if the verification values were stolen or lost, the adversary could initiate the man-in-the-middle attack. The result of this attack was serious: the adversary could establish two session keys with two different participants. This attack was described and an improved protocol called Improved 3REKA (I-3REKA) was proposed in this paper. The analysis on the security and performance show that the proposed protocol can realize secure communication with lower computational cost.

To improve the efficiency of disk scheduling, this paper proposed an optimization algorithm of disk scheduling based on the Average Seek Time (AST). Deep research of the average seek time of disk scheduling algorithm was carried out. Firstly, to analyze the moving of the magnetic head under every algorithm and compute the average seek time respectively; groups of the service request list were generated randomly as experimental data. And then by simulative and analytical method, a vibration rule had been studied; furthermore, the optimization algorithm of disk scheduling based on the average seek time was proposed. The optimization algorithm can enhance the efficiency of disk scheduling by selecting proper algorithm in real time automatically.

Design of data structure is valuable to the concrete realization of DNA computer. Therefore, a method of designing a binary tree based on sequential storage model in DNA computer was proposed, which utilized the biological characteristics of DNA molecules and restriction endonucleases to complete sequential storage structure and basic operations of the binary tree. All the biological technology mentioned here could be practically implemented in the laboratory. To prove the feasibility of this method, an actual binary tree with detailed nucleotide encodings and an instance of algorithm were given. The process of an algorithm implemented on this binary tree was demonstrated.

Based on 3D features for time and space relationship of each human joint，a kind of temporal-spatial features was proposed in this paper, which can process local temporal-spatial features of each joints. 3D features can represent a part of the whole motion independently and avoid contacting with original motion data and eliminate "curse of dimensionality". Experimental results show that the approaches are effective for motion data analysis, which can be used in intelligent analysis for motion semantics.

Concerning the special requirements of collision detection in the virtual assembly environment, a virtual assembly-oriented two-layer exact collision detection algorithm named HSDHBB was proposed based on bounding volume boxes and space division method. The algorithm firstly usd space decomposition method to identify potential regional intersection and then used bounding volume boxes to locate the intersection triangles and the exact points. Methods of constructing the bounding volume boxes tree and space division were given, and the data structure of Hash table was used to accelerate the collision detection in space division. Finally, the algorithm was applied in CATIA, the results show that the algorithm can effectively meet the real-time and accuracy requirements of the virtual assembly environment.