Aiming at the problems of large number of model parameters, large computational cost and low accuracy when using deep learning algorithms for pointer instrument recognition task, an intelligent detection and recognition system of circular pointer instrument based on the combination of improved pre-trained MobileNetV2 network model and circular Hough transform was proposed. Firstly, the Hough transform was used to solve the interference problem of non-circular areas in complex scene. Then, the circular areas were extracted to construct datasets. Finally, the circular pointer instrument recognition was realized by using the improved pre-trained MobileNetV2 network model. The average confusion matrix was used to measure the performance of the proposed model. Experimental results show that, the recognition rate of the proposed system in the recognition task of circular pointer instruments reaches 99.76%. At the same time, the results of comparing the proposed model with other five different network models show that the proposed model and ResNet50 both have the highest accuracy, but compared with ResNet50, the proposed network model has the model parameter number and model computational cost reduced by 90.51% and 92.40% respectively, verifying that the proposed model is helpful for the further deployment and implementation of industrial grade real-time circular pointer instrument detection and recognition in mobile terminals or embedded devices.

The histopathological image is the gold standard for identifying breast cancer, so that the automatic and accurate classification of breast cancer histopathological images is of great clinical application. In order to improve the classification accuracy of breast cancer histopathology images and thus meet the needs of clinical applications, a high-precision breast classification method that incorporates spatial and channel features was proposed. In the method, the histopathological images were processed by using color normalization and the dataset was expanded by using data enhancement, and the spatial feature information and channel feature information of the histopathological images were fused based on the Convolutional Neural Network (CNN) models DenseNet and Squeeze-and-Excitation Network (SENet). Three different BCSCNet (Breast Classification fusing Spatial and Channel features Network) models, BCSCNetⅠ, BCSCNetⅡ and BCSCNetⅢ, were designed according to the insertion position and the number of Squeeze-and-Excitation (SE) modules. The experiments were carried out on the breast cancer histopathology image dataset (BreaKHis), and through experimental comparison, it was firstly verified that color normalization and data enhancement of the images were able to improve the classification accuracy of breast canner, and then among the three designed breast canner classification models, the one with the highest precision was found to be BCSCNetⅢ. Experimental results showed that BCSCNetⅢ had the accuracy of binary classification ranged from 99.05% to 99.89%, which was improved by 0.42 percentage points compared with Breast cancer Histopathology image Classification Network (BHCNet); and the accuracy of multi-class classification ranged from 93.06% to 95.72%, which was improved by 2.41 percentage points compared with BHCNet. It proves that BCSCNet can accurately classify breast cancer histopathological images and provide reliable theoretical support for computer-aided breast cancer diagnosis.

To solve the problems of color distortion and local detail information loss caused by the histogram expansion of High Dynamic Range (HDR) image generated by single image, an imaging algorithm of high dynamic range image based on luminance partition fusion was proposed. Firstly, the luminance component of normal exposure color image was extracted, and the luminance was divided into two intervals according to luminance threshold. Then, the luminance ranges of images of two intervals were extended by the improved exponential function, so that the luminance of low-luminance area was increased, the luminance of high-luminance area was decreased, and the ranges of two areas were both expanded, increasing overall contrast of image, and preserving the color and detail information. Finally, the extended image and original normal exposure image were fused into a high dynamic image based on fuzzy logic. The proposed algorithm was analyzed from both subjective and objective aspects. The experimental results show that the proposed algorithm can effectively expand the luminance range of image and keep the color and detail information of scene, and the generated image has better visual effect.

To solve the problem that stock and increment sharing of container can not be effectively implemented, a container sharing model based on blockchain principle was proposed. Firstly, the operation mechanism of blockchain based container sharing mode was elaborated. Secondly, the changes of container transportation process with the influence of this mode were analyzed. Thirdly, based on Petri net theory, Colored Timed Petri Net (CTPN) models of traditional mode and blockchain based container sharing mode were established respectively by CPN Tools. Finally, the simulation of the models were carried out with four indicators compared and analyzed under different modes. The four indicators were the time from receipt of orders to picking up of empty containers, the ratio of empty driving time in the road, the order loss rate and the proportion of unloaded containers. The experimental results show that compared with under the traditional mode, under the blockchain based container sharing mode, the shipper's picking up time is shortened, the empty driving proportion reduces by 5.28% while there is no longer any order lost due to the mismatch between the shipping time and the order time window, and the proportion of unloaded containers is reduced by 6.99%. The simulation results show that the blockchain based container sharing mode can not only make up for the shortcomings of stock and increment sharing of container in the traditional ways, but also optimize the container transportation process. It is an effective way to reduce costs and increase efficiency in container transportation industry.

In order to solve the problem that the number of output neurons in deep learning-based image annotation model is directly proportionate to the labeled vocabulary, which leads the change of model structure caused by the change of vocabulary, a new annotation model combining Generative Adversarial Network (GAN) and Word2vec was proposed. Firstly, the labeled vocabulary was mapped to the fixed multidimensional word vector through Word2vec. Secondly, a neural network model called GAN-W (GAN-Word2vec annotation) was established based on GAN, making the number of neurons in model output layer equal to the dimension of multidimensional word vector and no longer relevant to the vocabulary. Finally, the annotation result was determined by sorting the multiple outputs of model. Experiments were conducted on the image annotation datasets Corel 5K and IAPRTC-12. The experimental results show that on Corel 5K dataset, the accuracy, recall and F1 value of the proposed model are increased by 5,14 and 9 percentage points respectively compared with those of Convolutional Neural Network Regression (CNN-R); on IAPRTC-12 dataset, the accuracy, recall and F1 value of the proposed model are 2,6 and 3 percentage points higher than those of Two-Pass K-Nearest Neighbor (2PKNN). The experimental results show that GAN-W model can solve the problem of neuron number change in output layer with vocabulary. Meanwhile, the number of labels in each image is self-adaptive, making the annotation results of the proposed model more suitable for actual annotation situation.

Concerning the spatial and spectral distortions caused by the local spatial dissimilarity between the multispectral and panchromatic images, a component substitution-based remote sensing image fusion method was proposed via improving spatial detail extraction scheme. Different from the classical spatial detail extraction methods, a high-resolution intensity image was synthesized by the proposed method to replace the panchromatic image in spatial detail extraction with the aim of acquiring spatial detail information matching the multispectral image. Firstly, according the manifold consistency between the low-resolution intensity image and the high-resolution intensity image, locally linear embedding-based reconstruction method was used to reconstruct the first high-resolution intensity image. Secondly, after decomposing the low-resolution intensity image and the panchromatic image with the wavelet technique respectively, the low-frequency information of the low-resolution intensity image and the high-frequency information of the panchromatic image were retained, and the inverse wavelet transformation was performed to reconstruct the second high-resolution intensity image. Thirdly, sparse fusion was performed on the two high-resolution intensity images to acquire the high-quality intensity image. Finally, the synthesized high-resolution intensity image was input in the component substitution-based fusion framework to obtain the fused image. The experimental results show that, compared with the other eleven fusion methods, the proposed method has the fused images with higher spatial resolution and lower spectral distortion. For the proposed method, the mean values of the objective evaluation indexes such as correlation coefficient, root mean squared error, erreur relative global adimensionnelle de synthese, spectral angle mapper and quaternion theory-based quality index on three groups of GeoEye-1 fused images are 0.9439, 24.3479, 2.7643, 3.9376 and 0.9082 respectively. These values are better than those of the other eleven fusion methods. The proposed method can efficiently reduce the effect of local spatial dissimilarity on the performance of the component substitution-based fusion framework.

In order to solve the low speech recognition rate in noise environment, and the difficulty of traditional beamforming algorithm in dealing with spatial noise problem, an improved Minimum Variance Distortionless Response (MVDR) beamforming method based on dual micro-array was proposed. Firstly, the gain of micro-array was increased by diagonal loading, and the computational complexity was reduced by the inversion of recursive matrix. Then, through the modulation domain spectrum subtraction for further processing, the problem that music noise was easily produced by general spectral subtraction was solved, effectively reducing speech distortion, and well suppressing the noise. Finally, the Convolution Neural Network (CNN) was used to train the speech model and extract the deep features of speech, effectively solve the problem of speech signal diversity. The experimental results show that the proposed method achieves good recognition effect in the CNN trained speech recognition system, and has the speech recognition accuracy of 92.3% in F16 noise environment with 10 dB signal-to-noise ratio, means it has good robustness.

As an important part of social network analysis, Weibo user influence analysis has been concerned by researchers all the time. Concerning the timeliness shortage and neglect of the relevance between users and topics when analyzing user behaviors, a user influence analysis algorithm for Weibo topics, named Topic and Spread user Rank (TSRank), was proposed. Firstly, based on Weibo topics, the timeliness of user's forwarding behavior was analyzed to construct two topic forwarding networks, user forwarding and user blog forwarding, in order to predict the user's topic information dissemination capability. Secondly, the text contents of user's personal history Weibo and background topic Weibo were analyzed to mine the relevance between user and background topic. Finally, the influence of Weibo user was calculated by comprehensively considering user's topic information dissemination capability and relevance between user and background topic. The experiments on crawled real topic data of Sina Weibo were conducted. The experimental results show that the topic forwarding number of users with higher topic correlation is significantly greater than that of users with lower topic correlation. Compared with no forwarding timeliness, the Catch Ratio (CR) of TSRank algorithm is increased by 18.7%, which is further compared with typical influence analysis algorithms, such as WBRank, TwitterRank and PageRank, TSRank algorithm improves the precision and recall by 5.9%, 8.7%, 13.1% and 6.7%, 9.1%, 14.2% respectively, which verifies the effectiveness of TSRank algorithm. The research results can support theoretical research of social attributes and topic forwarding of social networks as well as the application research of friend recommendation and public opinion monitoring.

Concerning the problems that compression and spatial index for point cloud data in 3D model are inefficient and overlapping of two adjacent query windows is a large probability event in the process of roaming, the methods of Adjacent Point Difference Progressive Compression (APDPC) and R-tree spatial index for processing redundants based on trimming overlapped regions were proposed. Firstly, spatial subdivision of 3D model was done by an octree, the point cloud data managed by each leaf node was sorted by means of Morton codes, the data was partitioned according to outer cube size of R-tree leaf node, the data difference between adjacent points in the block was calculated, the difference was progressively compressed by using blocks as units, reading the data blocks in batches to create the R-tree. Secondly, the valid range of this query was calculated with the scope of the last query window. Finally, the query method of point cloud data based on R-tree index was given. This method improved the compression rate of point cloud data by 26.61 percentage points, and could realize streaming transmission. Meanwhile, it effectively reduced I/O overhead, the query performance was improved by 35.44%, and data redundancy was reduced by 16.49 percentage points. The experimental results show that the proposed methods have obvious advantages in 3D virtual travel, digital city and other systems.

The diffeomorphism is a differential transformation with smooth and invertible properties, which leading to topology preservation between anatomic individuals while avoiding physically implausible phenomena during MRI image registration. In order to yield a more plausible diffeomorphism for spatial transformation, nonlinear structure of high-dimensional data was considered, and an MRI image registration using manifold learning based on adaptive tangent space was put forward. Firstly, Symmetric Positive Definite (SPD) covariance matrices were constructed by voxels from an MRI image, then to form a Lie group manifold. Secondly, tangent space on the Lie group was used to locally approximate nonlinear structure of the Lie group manifold. Thirdly, the local linear approximation was adaptively optimized by selecting appropriate neighborhoods for each sample voxel, therefore the linearization degree of tangent space was improved, the local nonlinearization structure of manifold was highly preserved, and the best optimal diffeomorphism could be obtained. Numerical comparative experiments were conducted on both synthetic data and clinical data. Experimental results show that compared with the existing algorithm, the proposed algorithm obtains a higher degree of topology preservation on a dense high-dimensional deformation field, and finally improves the registration accuracy.

Acceleration data in 3 axes during a signature process can be collected to authenticate users. Because of complex structures of Chinese signature, the process of signing in the air is hard to be forged, but it also increases differences between signatures performed by the same user which brings more difficulties in authentication. Classical verification methods applied to 2-D signature or hand gesture cannot solve this problem. In order to improve the performance of in-air Chinese signature verification, the classical Global Sequence Alignment (GSA) algorithm was improved, and the interpolation was applied to matching sequences. Different from classical GSA algorithm which uses matching score to measure similarity between sequences, two distance indexes, Euclidean distance and absolute value distance, were introduced to calculate the differences between sequences after interpolation. Experimental results show that both of the two improved GSA algorithms can improve the accuracy of authentication, the Equal Error Rate (EER) of them are decreased by 37.6% and 52.6% respectively compared with the classical method.

Large amount of user rating data, involving plentiful users' opinion and preference, is produced in e-commerce applications. An construction and inference method for latent variable model (i.e., Bayesian Network with a latent variable) oriented to user preference discovery from rating data was proposed to accurately infer user preference. First, the unobserved values in the rating data were filled by Biased Matrix Factorization (BMF) model to address the sparseness problem of rating data. Second, latent variable was used to represent user preference, and the construction of latent variable model based on Mutual Information (MI), maximal semi-clique and Expectation Maximization (EM) was given. Finally, an Gibbs sampling based algorithm for probabilistic inference of the latent variable model and the user preference discovery was given. The experimental results demonstrate that, compared with collaborative filtering, the latent variable model is more efficient for describing the dependence relationships and the corresponding uncertainties of related attributes among rating data, which can more accurately infer the user preference.

Aiming at the task allocation problem of two echelon logistics service supply chain in emergency, a customer satisfaction model with time-to-service was put forward. First of all, considering the randomness of orders in emergency, the customer satisfaction model with time-to-service was established. Secondly, the minimum logistics cost model was established to ensure the optimization of logistics service supply chain cost. Again, using linear weighted method, multi-objective model including maximizing customer satisfaction and minimizing service cost was transformed into single-objective model. At last, Genetic Algorithm (GA) was used to solve this model, and sensitivity analysis was used to analyze the weight. Results of calculation example show that compared with target value of 0.0501 and 0.0825 of single-objective assignment, the comprehensive function model can obtain the optimal target value of 0.2716, which means the task allocation scheme of the established model can effectively solve task allocation problem of customer satisfaction with time-to-service. Analysis of weight sensitivity shows that when the weight is between 0.1 and 0.5, the optimal solution is more significant in slope variation degree compared to the weight of 0.5 to 0.9, which indicates that it should be more rational to choose allocation weight according to service ability parameter when allocating tasks in emergency, and paradox effect of customer satisfaction and logistics cost exists in the emergency task allocation. The results indicate that the task allocation model with time-to-service can effectively solve task allocation problem of logistics service supply chain in emergency.

Fashion sales forecasting is very important for the retail industry and accurate sales forecasting can improve the final fashion sales profits greatly. The current fashion sales forecast data is limited and the data volatility makes it harder to accurately forecast. In order to solve the problems, a new hybrid intelligent prediction algorithm comprising Artificial Neural Network (ANN) and Discrete Grey forecasting Model (DGM(1,1)) was proposed. The Correlation Analysis (CA) was used to get important influence variables with large correlation and DGM(1,1)+ANN were used to forecast the sales data. Then the residual of real sales data and the forecasting results of DGM(1,1)+ANN was added into influence variables for forecasting the second residual by using ANN and adopting an idea of secondary residual. Finally, the experiments based on real data sets of fashion sales were conducted to evaluate the feasibility and accuracy of the proposed hybrid algorithm. The experimental results show that, in forecasting fashion sales data, the forecasting Mean Absolute Percent Error (MAPE) of the proposed algorithm is about 25%. The forecast accuracy has greatly improved, compared to AutoregRessive Integrated Moving Average model (ARIMA), Extended Extreme Learning Machine (EELM), DGM(1,1), DGM(1,1)+ANN algorithm, the average forecasting accuracy is improved about 8 percentage points. The proposed hybrid intelligent algorithm for fashion sales can be used for real-time sales forecasting and improve sales greatly.

A strategy for integrated berth and quay-crane scheduling was proposed to cope with unreasonable allocation of port resources in container terminals. First, a nonlinear mixed integer programming model which aims at minimizing the port operational cost was presented. And the loading and unloading cost of quay-crane was considered in the objective of our model. To make the model more realistic, the handling time of a vessel was assumed to depend on the number of assigned quay-cranes. Second, an improved genetic algorithm based on extenics dependent function was used to solve this model. In this algorithm, infeasible solutions play an important role. They were evaluated by their extenics dependent degrees. Some infeasible solutions were always contained in the population to maintain the diversity of the population. This improved local search ability of traditional genetic algorithm. At last, the effectiveness and efficiency of the proposed model and algorithm were testified by several test instances. Compared with the model without considering the loading and unloading cost of quay-crane, the waste of resource is effectively reduced.

To solve the problems of current multi-screen interaction systems such as high bandwidth occupancy of Wide Local Area Network (WLAN) and unstability between terminal devices and the router, a multi-screen interaction system based on Wi-Fi Direct was proposed, which directly connected two intelligent devices not via any access points and delivered content of one device to the other. The design of the system was detailedly described. According to the the principles of low delay and high compatibility, the proposed system was realized by developing an Android APP used on a smart phone or a smart TV. The test of the proposed system in practice shows that time delay and packet loss rate have been reduced in comparison with conventional multi-screen system depending on the WLAN. Also, the connection provided by Wi-Fi Direct between two devices is stable and the distance has been doubled. Besides, the structure of the proposed system has no request for WLAN bandwidth.

Visual pipeline mechanism and basic structure of the parallel program were discussed based on the characteristics of Visualization ToolKit (VTK). Since the problem of visualization post-processing in computational fluid dynamics, VTK color mapping algorithm was introduced and a program of showing nephogram was written. In order to reduce the running time, a parallel algorithm was proposed. The proposed algorithm made full use of the parallelism between the VTK tasks, reduced the program running time and improved the running efficiency. Finally the speedup ratios of files of different sizes were compared and analyzed. The results show that the requirements of visualization post-processing is satisfied by visualization technology based on VTK and the good parallel effect is obtained with Message Passing Interface (MPI).

A new method for designing Fractional Hilbert Transformer (FHT) was proposed. The basic idea is to realize the FHT to design the allpass filter with desired phase characteristic. It is well known that the denominator polynomial of a stable allpass filter must be a minimum phase system. By constructing a pure imaginary odd symmetry phase function, and using symmetry properties of the Fourier transform, this method could obtain the cepstral sequence of the denominator polynomial using the relationship between cepstral sequence and phase function of a minimum phase system. Then, from the cepstral spectrum theory, the denominator polynomial coefficients could be determined through a nonlinear recursive difference equation. Approximated ideal and non-ideal characteristic methods were given. Design examples indicate that the proposed filters exhibit good approximation to the desired phase response, and have the advantage of simple, efficient and infinite precision.

To solve the problem of detecting human hand in complex background based on traditional camera, a fast, automatic method was proposed which can accurately detect and track foreground human fingertips by using Kinect camera. This method firstly used a combined vision-based information to roughly extract the hand region, then, by taking advantage of depth information, a bare hand could be successfully segmented without connecting to background. Subsequently, the fingertips of that bare hand could be extracted by using minimum circle and curvature relationship on the hand boundary. Finally, to improve the detecting accuracy, the fingertips were optimized by using Kalman filter. The experimental results show that compared with existing method the algorithm can successfully track the 3D locations of fingertips under multiple hand poses and with much lower error rate.

To coordinate the logistics service supply chain, composed by a sub-contractor with single function and an integrator, a forecast-commitment contract was proposed. In this contract, a forecast for a future order and a guarantee to purchase a portion of it were provided by the logistics service integrator. Base on the information from the integrator, the logistics services sub-contractor made a decision on logistics capabilities investment. It provided an optimal strategy for the logistics service sub-contractor and gave the optimal forecast for the logistics service integrator. Then a buyback parameter was drawn into the "forecast-commitment" contract. The experimental results show that if the parameters are reasonable, the proposed contract can moderate the logistics services sub-contractor to invest. It shows that this contract can coordinate the whole system by achieving Pareto improvement for the logistics service supply chain and the increase in revenue for the supply chain system and integrator. The buyback parameter can improve the logistics capabilities investment of the sub-contractor at the same forecast. Finally, a numerical experiment was carried out to illustrate the forecast-commitment contract, and results verified the theoretical analysis.

Concerning the difficulties of parameter estimation for industrial modeling in practice, an innovative approach through data mining to correct parameter of model was proposed. Mining data from a large number of actual data accumulated in production process could be used for correcting parameter through statistical method. The improved method of least square was used for industrial data which contained noise. In view of the characteristics of industrial data, such as incompletion and common distribution, parameter should be segmented and combined to be corrected. For dynamic compensation of statistical model, dynamic parameter can be estimated through data mining of historical dynamic process. Parameter correction and data mining should be interactive with each other. To reduce the scope of massive data mining and improve sufficiency of sample data required for parameter correction, the network model of co-ordination was designed. It is shown in actual cases that this method is efficient and practical. The accuracy of simulation can be greatly improved through this method.

Alternating Direction Implicit (ADI) scheme is a typical discretization scheme for solving partial differential equations. However, there are few researches on the implementations and optimizations of ADI scheme on GPUs for practical Computational Fluid Dynamics (CFD) applications. In this paper, through analysis of the characteristics and calculation processes of ADI solver in a practical CFD application, the authors implemented fine-grained GPU parallelization algorithm for the ADI solver based on grid points and grid lines by a Compute Unified Device Architecture (CUDA) model. Some performance optimization methods were discussed. The experimental results on the TianHe-1A supercomputer show that the proposed GPU-enabled ADI solver can achieve overall speedup of 17.3 compared to single CPU core when simulating a 128×128×128 grid. The speedups for inviscid flux calculation, viscous flux calculation and ADI iteration are 100.1, 40.1 and 10.3 respectively.

Focusing on the problem of high efficiency resource scheduling in cloud computing environment, since current research has been less concerned about the cost of the services of the cloud service provider, an improved Quantum Genetic Algorithm (QGA) was proposed to reduce the minimum service cost of cloud service provider. This algorithm converted quantum-bits encoded by binary number to real-coded quantum-bits as chromosome represented by binary-coded quantum-bits cannot describe the resource scheduling matrix, and used rotation strategy and mutation operator to guarantee the convergence of the algorithm. Comparative experiments were conducted among the improved QGA, Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) through simulation platform, the populations number is 1 and 100 with 100 iteration times. The experimental results show that the improved QGA can obtain smaller minimum service cost.

Load balancing is an important means to improve resource utilization and system stability. Based on Adaptive Mutation Particle Swarm Optimization (AMPSO) algorithm, a new task scheduling model and strategy about load balancing for cluster in heterogeneous cloud environment were proposed. In order to maximize customer satisfaction degree and reduce the total execution time of a collection of tasks under ensuring the system load as much balanced as possible, a concept of user bias degree on cluster node performance such as safety and reliability and a method of grasping the degree of preference on security and reliability of cluster nodes and estimating the load information of the tasks were added into the design of scheduling policy. The simulation shows that the improved AMPSO algorithm performs better than the original AMPSO algorithm and the basic Particle Swarm Optimization (PSO) algorithm at convergence speed and the capacity of jumping out the local optimum. The results prove that the improved AMPSO can better improve the profit margins of the cloud service provider while ensuring the load balancing of the cluster.

A new tags anti-collision algorithm was proposed for the reader collision problems in the Radio Frequency IDentification (RFID) technology. It divided tags into groups based on the coset partition theory, and restricted each group to response in a fixed timeslot. According to the query codes and collision flag bits, the reader could identify a group of tags in one slot. The Matlab simulation results show that, compared with the binary search algorithm and dynamic frame timeslot algorithm, the proposed algorithm improves the slot utilization and throughput when the number of tags is large.

A fuzzy multi-objective software reliability allocation model was established, and bacteria foraging optimization algorithm based on estimation of distribution was proposed to solve software reliability redundancy allocation problem. As the fuzzy target function, software reliability and cost were regarded as triangular fuzzy members, and bacterial foraging algorithm optimization based on Gauss distribution was applied. Different membership function parameters were set up, and different Pareto optimal solutions could be obtained. The experimental results show that the proposed swarm intelligence algorithm can solve multi-objective software reliability allocation effectively and correctly, Pareto optimal solution can help the decision between software reliability and cost.

Though PUF is a new concept in recent years, since it has application prospect for the security of system authentication and key generation, it has become a hot research topic in the field of hardware security. In order to get the whole picture of physical unclonable function for better application in the future research work, first, based on the the different PUF implementations available, this paper classified the detailed design, and summed up the main problems. Then based on these categories, this paper proposed a nonformal property description. Next, from the point of view of cryptographic applications, this paper summarized the PUF application. Finally, this paper pointed out a few meaningful PUF future research directions.

Design pattern plays a very important role in objectoriented software design, development and maintenance. In order to overcome the drawbacks and weaknesses of the previous methods for design patterns notation, SBPN，a stereotypebased pattern notation method was proposed. Based on the stereotype mechanism in Unified Modeling Language （UML）, SBPN provides some rules for labeling patternrelated information. It can not only identify precisely the role of a modeling element, such as a class, a method or an attribute in structural diagrams, but also label the information in interaction diagrams. Whats more SBPN provides a solution for labeling patternrelated information in source codes. Some cases were given to describe how to label patternrelated information in class diagrams, interaction diagrams and source codes, and a complex design diagram of sort system was also labeled by SBPN.

To cope with Multi-objective Programming on Manufacturing Cloud Service Composition (MOP-MCSC) problem in cloud manufacturing (CMfg) system, a mathematical model and a solution algorithm were proposed and studied. Firstly, inspired by the resource service composition technology in manufacturing grid, a QoS-aware MOP-MCSC model in CMfg system had been explored and described. Secondly, by analyzing the characteristics of manufacturing cloud services according to the domain knowledge of manufacturing, an eight-dimensional QoS evaluation criterion with corresponding quantitative calculation formulas was defined. Then, the QoS expression of manufacturing cloud service was eventually formulated. Lastly, the MOP-MCSC model was built, and an Adaptive Mutation Particle Swarm Optimization (AMPSO) was designed to realize this model. The simulation experimental results suggest that the proposed algorithm could solve the MOP-MCSC problem efficiently and effectively with a better performance than conventional particle swarm optimization.

An efficient Morphological Un-Decimated Wavelet (MUDW) transform with more delicate and accurate multi-scale decomposition performance that suites real-time image fusion was proposed. It took the average of dilation and erosion as the analysis operator, and the difference of adjacent scale images as the detail image. Size-increasing structure elements were adopted to get better fusion result. Due to the simplicity of dilation and erosion operator, computation time is shorter than other real-time algorithms. Furthermore, a factor was added during reconstruction, to obtain an obvious enhancement effect. The experimental results show that the new method outperforms other real-time algorithms.