With the rapid growth of graph data sizes， Graph Neural Network （GNN） faces computational and storage challenges in processing large-scale graph-structured data. Traditional stand-alone training methods are no longer sufficient to cope with increasingly large datasets and complex GNN models. Distributed training is an effective way to address these problems due to its parallel computing power and scalability. However， on one hand， the existing distributed GNN training evaluations mainly focus on the performance metrics represented by model accuracy and the efficiency metrics represented by training time， but pay less attention to the metrics of data processing efficiency and computational resource utilization； on the other hand， the main scenarios for algorithm efficiency evaluation are single machine with one card or single machine with multiple cards， and the existing evaluation methods are relatively simple in a distributed environment. To address these shortcomings， an evaluation method for model training in distributed scenarios was proposed， which includes three aspects： evaluation metrics， datasets， and models. Three representative GNN models were selected according to the evaluation method， and distributed training experiments were conducted on four large open graph datasets with different data characteristics to collect and analyze the obtained evaluation metrics. Experimental results show that all of model complexity， training time， computing node throughput and computing Node Average Throughput Ratio （NATR） are influenced by model architecture and data structure characteristics in distributed training； sample processing and data copying take up much time in training， and the time of one computing node waiting for other computing nodes cannot be ignored either； compared with stand-alone training， distributed training reduces the computing node throughput significantly， and further optimization of resource utilization for distributed systems is needed. It can be seen that the proposed evaluation method provides a reference for optimizing the performance of GNN model training in a distributed environment， and establishes an experimental foundation for further model optimization and algorithm improvement.

Considering the issues of physiological signal emotion recognition， a bimodal emotion recognition method based on Graph Neural Network （GNN） and attention was proposed. Firstly， the GNN was used to classify ElectroEncephaloGram （EEG） signals. Secondly， an attention-based Bi-directional Long Short-Term Memory （Bi-LSTM） network was used to classify ElectroCardioGram （ECG） signals. Finally， the results of EEG and ECG classification were fused by Dempster-Shafer evidence theory， thus improving the comprehensive performance of the emotion recognition task. To verify the effectiveness of the proposed method， 20 subjects were invited to participate in the emotion elicitation experiment， and the EEG signals and ECG signals of the subjects were collected. Experimental results show that the binary classification accuracies of the proposed method are 91.82% and 88.24% in the valence dimension and arousal dimension， respectively， which are 2.65% and 0.40% higher than those of the single-modal EEG method respectively， and are 19.79% and 24.90% higher than those of the single-modal ECG method respectively. It can be seen that the proposed method can effectively improve the accuracy of emotion recognition and provide decision support for medical diagnosis and other fields.

Random multiple access communication is an indispensable part of computer communication research. A three-slot P-Persistent Carrier Sense Multiple Access (P-CSMA) protocol with variable collision duration in Wireless Sensor Network (WSN) was proposed to solve the problem of traditional P-CSMA protocol in transmitting and controlling WSN and energy consumption of system. In this protocol, the collision duration was added to the traditional two-time-slot P-CSMA protocol in order to change the system model to three-time-slot model, that is, the duration of information packet being sent successfully, the duration of packet collision and the idle duration of the system.Through the modeling, the throughput, collision rate and idle rate of the system under this model were analyzed. It was found that by changing the collision duration, the loss of the system was reduced. Compared with the traditional P-CSMA protocol, this protocol makes the system performance improved, and makes the lifetime of the system nodes obtained based on the battery model obviously extended. Through the analysis, the system simulation flowchart of this protocol is obtained. Finally, by comparing and analyzing the theoretical values and simulation values of different indexes, the correctness of the theoretical derivation is proved.

Focused on the issue that traditional machine learning algorithms still need to manually represent features, a protein subcellular localization algorithm based on the deep network of Stacked Denoising AutoEncoder (SDAE) was proposed. Firstly, the improved Pseudo-Amino Acid Composition (PseAAC), Pseudo Position Specific Scoring Matrix (PsePSSM) and Conjoint Traid (CT) were used to extract the features of the protein sequence respectively, and the feature vectors obtained by these three methods were fused to obtain a new feature expression model of protein sequence. Secondly, the fused feature vector was input into the SDAE deep network to automatically learn more effective feature representation. Thirdly, the Softmax regression classifier was adopted to make the classification and prediction of subcells, and leave-one-out cross validation was performed on Viral proteins and Plant proteins datasets. Finally, the results of the proposed algorithm were compared with those of the existing algorithms such as mGOASVM (multi-label protein subcellular localization based on Gene Ontology and Support Vector Machine) and HybridGO-Loc (mining Hybrid features on Gene Ontology for predicting subcellular Localization of multi-location proteins). Experimental results show that the new algorithm achieves 98.24% accuracy on Viral proteins dataset, which is 9.35 Percentage Points higher than that of mGOASVM algorithm. And the new algorithm achieves 97.63% accuracy on Plant proteins dataset, which is 10.21 percentage points and 4.07 percentage points higher than those of mGOASVM algorithm and HybridGO-Loc algorithm respectively. To sum up, it can be shown that the proposed new algorithm can effectively improve the accuracy of the prediction of protein subcellular localization.

Concerning the bimodal distribution characteristics of the range boundary presented by the traditional Chebyshev mapping, in order to meet the requirements of homogenized distribution of sequences in optimization theory, the mathematical equation was given by using the probability density function of Chebyshev mapping, and a new system was constructed by combining with the original mapping into a new system. The comparative study shows that the system has good homogenized distribution characteristic, ergodic characteristic, balance and low complexity, and the random error of the generated sequences is small and the similarity is high. Finally, the system is applied to the initialization population stage of the optimization algorithm, and it is further shown that the homogenized distribution system has a significant effect on improving the homogenized distribution characteristic of the original mapping.

IntraVascular UltraSound (IVUS) imaging can provide information of the coronary atherosclerotic plaque. It allows the doctor to make comprehensive and accurate evaluation of diseased vessel. Some ultrasound data collecting devices for imaging system exhibited insufficient data transfer speed, high cost or inflexibility, so the authors presented a high speed data transfer and imaging method for intravascular ultrasound. After being collected and processed, ultrasound data was transferred to computer through USB3.0 interface. In addition, logarithmic compression and digital coordinate conversion were applied in computer before imaging. Data transmission experiment shows that the transfer speed always stays around 2040Mb/s. Finally, phantom imaging was conducted to demonstrate the performance of the system. It shows a clear pipe wall and a smooth luminal border.

The coherent signal is widespread in the actual environment. Concerning the problem that traditional 2-D Direction Of Arrival (DOA) algorithm of Multiple Signal Classification (MUSIC) cannot process the coherent signal, the Modified MUSIC (MMUSIC) algorithm was used to realize the 2-D DOA estimation for the coherent imaginaries signal. The applied range of the modified MUSIC algorithm was extended from 1-D Uniform Linear Array (ULA) to 2-D centre-symmetric array, and it had been deduced by theory that bearing performance of MMUSIC algorithm was inversely proportional to the cosine value of phase difference. For two coherent signals of being separated by more than 4 degrees, the successful probability of the 2-D MMSUIC algorithm can be more than 90% in simulation experiments.

Weight coefficients should be employed to transform multi-objective problem of hybrid system into a single objective one. In order to avoid setting weight coefficients, a methodological approach based on Strength Pareto Evolutionary Algorithm (SPEA2) was proposed to optimize parameters of constrained Parallel Hybrid Electric Vehicle (PHEV).The Pareto dominance principle was employed to judge candidate solutions and the objective was to minimum fuel consumption and exhaust emissions while ADVISOR was used to simulate the PHEV driving. The optimal results demonstrate that adopting the methodological approach proposed in this paper to optimize parameters of power control strategy and drivetrain has a significant effect on enhancing working efficiency, promoting vehicle performance, decreasing fuel consumption and reducing exhaust emissions of PHEV.

To solve the problem that the digital watermarking images suffer geometric attacks, a strong robust blind detection digital watermarking algorithm, integrated with the unchanged features of the image and the characteristics of the frequency-domain stability, was proposed. By constructing the self-adaptive Scale Invariant Feature Transform (SIFT) algorithm and filling the seats with the Harris method of the angle and the point, utilizing the density of feature points obtained in different scale space and adjusting the watermarking information self-adaptively to the intensity embedded into Discrete Cosine Transform (DCT) domain, it scrambled the image sub-block feature vector set with Arnold scrambling, and then generated the key documents, next matched the two-way feature with the secret image feature vector, got geometric distortion parameters and corrected the image restoratively, and extracted the IDCT inverse transform domain watermark information in the form of blind detection. Judging from the experimental results, the algorithmic Peak Signal to Noise Ratio (PSNR) in this paper improves by 13% than using Discrete Wavelet Transform (DWT) and Discrete Fourier Transform (DFT), and the similarity of watermark is over 11%. It shows that this algorithm has good robustness to both of the geometric attacks and the conventional signal processing, as well as better invisibility.

In Mobile Ad Hoc Networks (MANET), the routing overhead was heavy and routing latency was long by using conventional algorithms of route discovery such as flooding and Expanding Ring Search (ERS). In order to improve the performance of routing protocol, a scheme of route discovery was provided based on the neighbor cache. Neighbor information was extracted from data packets, and neighbor cache table was established to store historical neighbor records. And then the approach of route discovery included two stages: 1) Found the node meeting the destination node before a short time; 2) Started new ERS. The simulation results show that the new scheme significantly improves performance of the protocol under many kinds of simulation scenarios. The routing overhead is saved and the endtoend delay of the packet is reduced. At the same time, the new scheme is also easy to implement.

The accuracy of sensor data is a critical index to evaluate the performance of Wireless Sensor Network (WSN). Outlier detection is a crucial but challenging issue for WSN. In this paper, an outlier detection approach based on variable-width histogram was proposed. The dynamic sensor data were aggregated into variable-width histograms, which avoided unnecessary data transmissions while detecting outliers. The theoretical analysis and evaluation on real WSN dataset show that this approach has high detection accuracy, and the cost is effectively reduced.

According to the characteristics of clustering with obstacle constraints, using the knowledge of graph theory, a multi-step Arithmetic was proposed. Firstly, it clustered the objects without obstacles by minimum spanning tree clustering method. Then it took obstacles to divide the generated clusters. Lastly it merged the clusters whose obstruct distance was little enough. The algorithm need only one parameter, it is of good performance and can find clusters with arbitrary shapes and varying densities. At last its effectiveness was demonstrated through experiment.

Due to the defects of field bus, such as low communication rate and high cost, a new control system based on TCP/IP protocol was designed to embed control system with Server/Client structure. The communication network system, software structure and control method were described in detail. XML language was used to transfer frame data through TCP/IP Ethernet. Message queue scheduling algorithm and data clustering at memory sharing buffer technology were introduced to enhance the system’s real-time response performance and meet the function of warning and control. The experimental result shows that it adopts industrial Ethernet bus with the advantages of high rate of communication, good compatibility and low cost. This design is a feasible and efficient method for computer aided driving and control system in vehicle.

One of the key problems in noise speech recognition is how to extract the robust feature parameters. A two-dimensional root cepstrum feature parameter was first proposed, and then this parameter was combined with robust feature based on the Minimum Variance Distortless Response (MVDR) method of spectrum estimation proposed. Finally, a novel robust feature was presented to be successfully used in continuous speech recognition under different SNRs. Experimental results indicate that the two-dimensional PMCC robust feature parameter is superior to conventional Melt Frequency Cepstral Coefficients （MFCC） and Perceptually Linear Prediction （PLP） in improving the recognition accuracy under different noise conditions and SNRs.

By using the container-based security mechanism of J2EE, the system security of J2EE can be managed by RBAC (Role-based Access Control) without code modification of J2EE components. RBAC was realized simply by the deployment descriptor configure of J2EE container. RBAC security strategy, executed to protect J2EE system resource based on the security truss of container, was picked up from deploy descriptor. Because the development of J2EE component separates from security, the developers of components can be absorbed in the businesses logic of components. Therefore, the cost of system development and maintenance will fall down, and the components become transplantable.