Concerning the problem that current Transformer-based algorithms focus on capturing the global features of images， but ignore the key role of local features to restore image details， an image denoising network based on local and global feature decoupling was proposed. The proposed network included two multi-scale branches based on Hybrid Transformer Block （HTB） and a single-scale branch based on Convolutional Neural Network （CNN）， aiming at combining powerful global modeling capability of HTB with local modeling advantage of HTB， and yielding outputs with enriched contextual information and precise spatial details. Within the HTB， self-attention mechanism was employed to adaptively model spatial- and channel-dimensional dependencies， activating a wider range of input pixels for reconstruction. Given the potential information conflicts across different branches， feature transfer block was designed to facilitate cross-branch propagation of global features and suppress low-frequency information， thereby ensuring collaborative interactions among the branches. Experimental results showed that： on the real-world image dataset SIDD， compared with Transformer-based denoising network Uformer， the proposed network improved Peak Signal-to-Noise Ratio （PSNR） by 0.09 dB and Structural SIMilarity （SSIM） by 0.001； on the synthetic image dataset Urban100， compared with multi-stage denoising network MSPNet （Multi-Stage Progressive denoising Network）， the average PSNR of the proposed network was improved by 0.41 dB. It can be seen that the proposed network effectively removes image noise and reconstructs finer texture details.
Aiming at the problems of incomplete intra-modal information， poor inter-modal interaction， and difficulty in training in multimodal sentiment analysis， a Multimodal Sentiment analysis network with Self-supervision and Multi-layer cross Attention fusion （MSSM） was proposed with Visual-and-Language Pre-training （VLP） model applied to the field of multimodal sentiment analysis. The visual encoder module was enhanced through self-supervised learning， and multi-layer cross attention was added to better model textual and visual features. Thus， the intra-modal information was made more abundant and complete， and the inter-modal information interaction was made more sufficient. Besides， the fast and memory-efficient exact attention with IO-awareness： FlashAttention was adopted in the proposed algorithm to address the high complexity of attention computation in Transformer. Experimental results show that compared with the current mainstream model Contrastive Language-Image Pre-training （CLIP）， MSSM improves the accuracy by 3.6 percentage points on the processed MVSA-S dataset and 2.2 percentage points on MVSA-M dataset， proving that the proposed network can effectively improve the integrity of multimodal information fusion while reducing computational cost.
Speech emotion recognition has been widely used in multi-scenario intelligent systems in recent years， and it also provides the possibility to realize intelligent analysis of teaching behaviors in smart classroom environments. Classroom speech emotion recognition technology can be used to automatically recognize the emotional states of teachers and students during classroom teaching， help teachers understand their own teaching styles and grasp students’ classroom learning status in a timely manner， thereby achieving the purpose of precise teaching. For the classroom speech emotion recognition task， firstly， classroom teaching videos were collected from primary and secondary schools， the audio was extracted， and manually segmented and annotated to construct a primary and secondary school teaching speech emotion corpus containing six emotion categories. Secondly， based on the Temporal Convolutional Network （TCN） and cross-gated mechanism， dual temporal convolution channels were designed to extract multi-scale cross-fusion features. Finally， a dynamic weight fusion strategy was adopted to adjust the contributions of features at different scales， reduce the interference of non-important features on the recognition results， and further enhance the representation and learning ability of the model. Experimental results show that the proposed method is superior to advanced models such as TIM-Net （Temporal-aware bI-direction Multi-scale Network）， GM-TCNet （Gated Multi-scale Temporal Convolutional Network）， and CTL-MTNet （CapsNet and Transfer Learning-based Mixed Task Net） on multiple public datasets， and its UAR （Unweighted Average Recall） and WAR （Weighted Average Recall） reach 90.58% and 90.45% respectively in real classroom speech emotion recognition task.
Panoramic videos have attracted wide attention due to their unique immersive and interactive experience. The high bandwidth and low delay required for wireless streaming of panoramic videos have brought challenges to existing network streaming systems. Tile-based viewport adaptive streaming can effectively alleviate the streaming pressure brought by panoramic video， and has become the current mainstream scheme and hot research topic. By analyzing the research status and development trend of tile-based viewport adaptive streaming， the two important modules of this streaming scheme， namely viewport prediction and bit rate allocation， were discussed， and the methods in relevant fields were summarized from different perspectives. Firstly， based on the panoramic video streaming framework， the relevant technologies were clarified. Secondly， the user experience quality indicators to evaluate the performance of the streaming system were introduced from the subjective and objective dimensions. Then， the classic research methods were summarized from the aspects of viewport prediction and bit rate allocation. Finally， the future development trend of panoramic video streaming was discussed based on the current research status.
In view of a series of problems of security guarantee of construction site personnel such as casualties led by falling objects and tower crane collapse caused by mutual collision of tower hooks， a small target detection model in overlooking scenes on tower cranes based on improved Real-Time DEtection TRansformer （RT-DETR） was proposed. Firstly， the multiple training and single inference structures designed by applying the idea of model reparameterization were added to the original model to improve the detection speed. Secondly， the convolution module in FasterNet Block was redesigned to replace BasicBlock in the original BackBone to improve performance of the detection model. Thirdly， the new loss function Inner-SIoU （Inner-Structured Intersection over Union） was utilized to further improve precision and convergence speed of the model. Finally， the ablation and comparison experiments were conducted to verify the model performance. The results show that， in detection of the small target images in overlooking scenes on tower cranes， the proposed model achieves the precision of 94.7%， which is higher than that of the original RT-DETR model by 6.1 percentage points. At the same time， the Frames Per Second （FPS） of the proposed model reaches 59.7， and the detection speed is improved by 21% compared with the original model. The Average Precision （AP） of the proposed model on the public dataset COCO 2017 is 2.4， 1.5， and 1.3 percentage points higher than those of YOLOv5， YOLOv7， and YOLOv8， respectively. It can be seen that the proposed model meets the precision and speed requirements for small target detection in overlooking scenes on tower cranes.
Medical image registration models aim to establish the correspondence of anatomical positions between images. The traditional image registration method obtains the deformation field through continuous iteration， which is time-consuming and has low accuracy. The deep neural networks not only achieve end-to-end generation of deformation fields， thereby speeding up the generation of deformation fields， but also further improve the accuracy of image registration. However， all of the current deep learning registration models use single Convolutional Neural Network （CNN） or Transformer architecture， and have the problems such as the inability to fully utilize the advantages of the combination of CNN and Transformer， resulting in insufficient registration accuracy， and the inability to maintain the original topology effectively after image registration. To solve these problems， a parallel medical image registration model based on CNN and Transformer — PPCTNet （Parallel Processing of CNN and Transformer Network） was proposed. Firstly， the model was constructed using Swin Transformer， which currently has the excellent registration accuracy， and LOCV-Net （Lightweight attentiOn-based ConVolutional Network）， a very lightweight CNN. Then， the feature information extracted by Swin Transformer and LOCV-Net were fully integrated by designing a fusion strategy， so that the model not only had the local feature extraction capability of CNN and the long-distance dependency capability of Transformer， but also had the advantage of being lightweight. Finally， based on the brain Magnetic Resonance Imaging （MRI） dataset， PPCTNet was compared with 10 classical image alignment models. The results show that compared to the currently excellent registration model TransMorph （hybrid Transformer-ConvNet network for image registration）， PPCTNet has the highest registration accuracy 0.5 percentage points higher， and the folding rate of deformation field 1.56 percentage points reduced， maintaining the topological structures of the registered images. Besides， compared with TransMorph， PPCTNet has the parameters reduced by 10.39×106， and the computational cost reduced by 278×109， which reflects the lightweight advantage of PPCTNet.
As a specific type of big data in biology， similarity of gene expression data is not based on Euclidean distance but on whether gene expression values show a trend of both rise and fall together， although they are all ordinary real values. The current gene Bayesian network uses gene expression level values as node random variables and does not reflect the similarity of this kind of subspace pattern. Therefore， a Bayesian network disease Classification algorithm based on Gene Association analysis （BCGA） was proposed to learn Bayesian networks from labeled disease sample-gene expression data and predict the classification of new disease samples. Firstly， disease samples were discretized and filtered to select genes， and the dimensionally reduced gene expression values were sorted and replaced with gene column subscripts. Secondly， the subscript sequence of gene column was decomposed into a set of atomic sequences with a length of 2， and the frequent atomic sequence of this set was corresponding to the association of a pair of genes. Finally， causal relationships were measured through gene association entropy for Bayesian network structure learning. Besides， the parameter learning of BCGA became easy， and the conditional probability distribution of a gene node was able to be obtained by counting the atomic sequence occurrence frequency of the gene and its parent node gene. Experimental results on multiple tumor and non-tumor gene expression datasets show that BCGA significantly improves disease classification accuracy and effectively reduces analysis time compared to the existing similar algorithms. In addition， BCGA uses gene association entropy instead of conditional independence， and gene atomic sequences instead of gene expression values， which can better fit gene expression data better.
Cross-modal retrieval based on deep network often faces the challenge of insufficient cross-training data， which limits the training effect and easily leads to over-fitting. Transfer learning is an effective way to solve the problem of insufficient training data by learning the training data in the source domain and transferring the acquired knowledge to the target domain. However， most of the existing transfer learning methods focus on transferring knowledge from single-modal （like image） source domain to cross-modal （like image and text） target domain. If there is multiple modal information in the source domain， this asymmetric transfer would ignore the potential inter-modal semantic information contained in the source domain. At the same time， the similarity of the same modals in the source domain and the target domain cannot be well extracted， thereby reducing the domain difference. Therefore， a Deep Bi-modal source domain Symmetrical Transfer Learning for cross-modal retrieval （DBSTL） method was proposed. The purpose of this method is to realize the knowledge transfer from bi-modal source domain to multi-modal target domain， and obtain the common representation of cross-modal data. DBSTL consists of modal symmetric transfer subnet and semantic consistency learning subnet. With hybrid symmetric structure adopted in symmetric modal transfer subnet， the information between modals was more consistent to each other and the difference between source domain and target domain was reduced by this subnet. In semantic consistency learning subnet， all modalities shared the same common presentation layer， and the cross-modal semantic consistency was ensured under the guidance of the supervision information of the target domain. Experimental results show that on Pascal， NUS-WIDE-10k and Wikipedia datasets， the mean Average Precision （mAP） of the proposed method is improved by about 8.4， 0.4 and 1.2 percentage points compared with the best result obtained by the comparison methods respectively. DBSTL makes full use of the potential information of the dual-modal source domain to conduct symmetric transfer learning， ensures the semantic consistency between modals under the guidance of the supervision information， and improves the similarity of image and text distribution in the public representation space.
To address the difficulties in reconstructing high-frequency information in image super-resolution reconstruction due to the lack of dependency between low-resolution and high-resolution images and the lack of order during the reconstruction of feature map， a single-image super-resolution reconstruction method based on iterative feedback and attention mechanism was proposed. Firstly， high- and low-frequency information in the image was extracted respectively by using frequency decomposition block， and the two kinds of information was processed respectively， so that the network focused on the extracted high-frequency details to increase the restoration ability of the method on image details. Secondly， through the channel-wise attention mechanism， the reconstruction focus was put on the feature channels with effective features to improve the network ability of extracting the feature map information. Thirdly， the iterative feedback idea was adopted to increase quality of the restored image in the process of repeated comparison and reconstruction. Finally， the output image was generated through the reconstruction block. The proposed method shows better performance in comparison with mainstream super-resolution methods in the 2×， 4× and 8× experiments on Set5， Set14， BSD100， Urban100 and Manga109 benchmark datasets. In the 8× experiments on Manga109 dataset， the proposed method improves Peak Signal-to-Noise Ratio （PSNR） by about 3.01 dB and 2.32 dB averagely and respectively compared to the traditional interpolation method and the Super-Resolution Convolutional Neural Network （SRCNN）. Experimental results show that the proposed method can reduce the errors in the reconstruction process and effectively reconstruct finer high-resolution images.
Applying the compact constraint calculation method of S-box based on Mixed Integer Linear Programming （MILP） model can solve the low efficiency of differential path search of SPONGENT in differential cryptanalysis. To find the best description of S box， a compactness verification algorithm was proposed to verify the inequality constraints in S-box from the perspective of the necessity of the existence of constraints. Firstly， the MILP model was introduced to analyze the inequality constraints of SPONGENT S-box， and the constraint composed of 23 inequalities was obtained. Then， an index for evaluating the existence necessity of constraint inequality was proposed， and a compactness verification algorithm for verifying the compactness of group of constraint inequalities was proposed based on this index. Finally， the compactness of the obtained SPONGENT S-box constraint was verified by using the proposed algorithm. Calculation analysis show that the 23 inequalities have a unique impossible difference mode that can be excluded， that is， each inequality has the necessity of existence. Furthermore， for the same case， the number of inequalities was reduced by 20% compared to that screened by using the greedy algorithm principle. Therefore， the obtained inequality constraint of S-box in SPONGENT is compact， and the proposed compactness verification algorithm outperforms the greedy algorithm.
Aspect-oriented Fine-grained Opinion Extraction （AFOE） extracts aspect terms and opinion terms from reviews in the form of opinion pairs or additionally extracts sentiment polarities of aspect terms on the basis of the above to form opinion triplets. Aiming at the problem of neglecting correlation between the opinion pairs and contexts， an aspect-oriented Adaptive Span Feature-Grid Tagging Scheme （ASF-GTS） model was proposed. Firstly， BERT （Bidirectional Encode Representation from Transformers） model was used to obtain the feature representation of the sentence. Then， the correlation between the opinion pair and local context was enhanced by the Adaptive Span Feature （ASF） method. Next， Opinion Pair Extraction （OPE） was transformed into a uniform grid tagging task by Grid Tagging Scheme （GTS）. Finally， the corresponding opinion pairs or opinion triplet were generated by the specific decoding strategy. Experiments were carried out on four AFOE benchmark datasets adaptive to the task of opinion tuple extraction. The results show that compared with GTS-BERT （Grid Tagging Scheme-BERT） model， the proposed model has the F1-score improved by 2.42% to 7.30% and 2.62% to 6.61% on opinion pair or opinion triplet tasks， respectively. The proposed model can effectively reserve the sentiment correlation between opinion pair and context， and extract opinion pairs and their sentiment polarities more accurately.
In data poisoning attacks， backdoor attackers manipulate the distribution of training data by inserting the samples with hidden triggers into the training set to make the test samples misclassified so as to change model behavior and reduce model performance. However， the drawback of the existing triggers is the sample independence， that is， no matter what trigger mode is adopted， different poisoned samples contain the same triggers. Therefore， by combining image steganography and Deep Convolutional Generative Adversarial Network （DCGAN）， an attack method based on sample was put forward to generate image texture feature maps according to the gray level co-occurrence matrix， embed target label character into the texture feature maps as a trigger by using the image steganography technology， and combine texture feature maps with trigger and clean samples into poisoned samples. Then， a large number of fake pictures with trigger were generated through DCGAN. In the training set samples， the original poisoned samples and the fake pictures generated by DCGAN were mixed together to finally achieve the effect that after the poisoner injecting a small number of poisoned samples， the attack rate was high and the effectiveness， sustainability and concealment of the trigger were ensured. Experimental results show that this method avoids the disadvantages of sample independence and has the model accuracy reached 93.78%. When the proportion of poisoned samples is 30%， data preprocessing， pruning defense and AUROR defense have the least influence on the success rate of attack， and the success rate of attack can reach about 56%.
Due to the complex and variable structure of fundus vessels， and the low contrast between the fundus vessel and the background， there are huge difficulties in segmentation of fundus vessels， especially small fundus vessels. U-Net based on deep fully convolutional neural network can effectively extract the global and local information of fundus vessel images，but its output is grayscale image binarized by a hard threshold， which will cause the loss of vessel area， too thin vessel and other problems. To solve these problems， U-Net and Pulse Coupled Neural Network （PCNN） were combined to give play to their respective advantages and design a fundus vessel segmentation method. First， the iterative U-Net model was used to highlight the vessels， the fusion results of the features extracted by the U-Net model and the original image were input again into the improved U-Net model to enhance the vessel image. Then， the U-Net output result was viewed as a gray image， and the PCNN with adaptive threshold was utilized to perform accurate vessel segmentation. The experimental results show that the AUC （Area Under the Curve） of the proposed method was 0.979 6，0.980 9 and 0.982 7 on the DRVIE， STARE and CHASE_DB1 datasets， respectively. The method can extract more vessel details， and has strong generalization ability and good application prospects.
Traditional stock prediction methods are mostly based on time-series models， which ignore the complex relations among stocks， and the relations often exceed pairwise connections， such as stocks in the same industry or multiple stocks held by the same fund. To solve this problem， a stock trend prediction method based on temporal HyperGraph Convolutional neural Network （HGCN） was proposed， and a hypergraph model based on financial investment facts was constructed to fit multiple relations among stocks. The model was composed of two major components： Gated Recurrent Unit （GRU） network and HGCN. GRU network was used for performing time-series modeling on historical data to capture long-term dependencies. HGCN was used to model high-order relations among stocks to learn intrinsic relation attributes， and introduce the multiple relation information among stocks into traditional time-series modeling for end-to-end trend prediction. Experiments on real dataset of China A-share market show that compared with existing stock prediction methods， the proposed model improves prediction performance， e.g. compared with the GRU network， the proposed model achieves the relative increases in ACC and F1_score of 9.74% and 8.13%， respectively， and is more stable. In addition， the simulation back-testing results show that the trading strategy based on the proposed model is more profitable， with an annual return of 11.30%， which is 5 percentage points higher than that of Long Short-Term Memory （LSTM） network.
Aiming at the problem of influence of the channel on the characteristics of the vowel formant， a systematic experiment was carried out. Firstly， the standard recordings of 8 volunteers were collected. Then， the standard recordings were played with the mouth simulator， and 104 channel recordings were recorded using 13 different channels. Finally， the characteristic voice segments were extracted， and chi-square test analysis was used in the qualitative analysis of the spectral characteristics， and one-sample t-test was used in the quantitative analysis of acoustic parameters. The statistical results show that about 69% of the channels have a significant influence on the overall form of the high-order formants， and about 85% of the channels have significant differences in the relative intensity of the formants. The one-sample t-test results show that there is no significant difference between the standard recordings and the channel recordings in center frequency of the formant. Experimental results show that the frequency characteristics of formants should be paid more attention to when processing the identification of voices in different channels.
The Multi-Class Support Vector Machine （MSVM） has the defects such as strong sensitivity to noise， instability to resampling data and lower generalization performance. In order to solve the problems， the pinball loss function， sample fuzzy membership degree and sample structural information were introduced into the Simplified Multi-Class Support Vector Machine （SimMSVM） algorithm， and a structure-fuzzy multi-class support vector machine algorithm based on pinball loss， namely Pin-SFSimMSVM， was proposed. Experimental results on synthetic datasets， UCI datasets and UCI datasets adding different proportions of noise show that， the accuracy of the proposed Pin-SFSimMSVM algorithm is increased by 0~5.25 percentage points compared with that of SimMSVM algorithm. The results also show that the proposed algorithm not only has the advantages of avoiding indivisible areas of multi-class data and fast calculation speed， but also has good insensitivity to noise and stability to resampling data. At the same time， the proposed algorithm considers the fact that different data samples play different roles in classification and the important prior knowledge contained in the data， so that the classifier training is more accurate.
For the given multiple sequences, a certain threshold and the gap constraints, the study objective is to discover frequent patterns whose supports in multiple sequences are no less than the given threshold value, where any two successive elements of pattern fulfill the user-specified gap constraints, and any two occurrences of a pattern in a given sequence meet the one-off condition. To solve this problem, the existing algorithms only consider the first occurrence of each character of a pattern when they compute the support of a pattern in a given sequence, so that many frequent patterns are not mined. An efficient mining algorithm of multiple sequential patterns with gap constraints, named MMSP, was proposed. Firstly, it stored the candidate positions of a pattern using two-dimensional table, then it selected the position from the candidate positions according to the left-most strategy. The experiments were conducted on DNA sequences. The number of frequent patterns mined by MMSP was 3.23 times of that mined by the related algorithm named M-OneOffMine when the number of multiple sequence elements is constant and the sequence length changes, and the average number of mining patterns by MMSP was 4.11 times of that mined by M-OneOffMine when the number of multiple sequence elements changes. The average number of mined patterns by MMSP was 2.21 and 5.24 times of that mined by M-OneOffMine and MPP respectively when the number of multiple sequence elements changes, and the frequent patterns mined by M-OneOffMine was a subset of MMSP. The experimental results show that MMSP can mine more frequent patterns with shorter time, and it is more suitable for practical applications.
For automatic detection of tire crown cord overlap defect, a detection method based on the crown X ray image was presented. Firstly, the gray cumulative projection curves that X-ray image was projected along different angles were obtained. Secondly, the local peak energy distribution of curves were calculated and the energy feature vector was constructed by the n largest peak energy values. Thirdly, the tire crown crack image was recognized by the maximum projection curve which could be distinguished through the energy feature vector by Support Vector Machine (SVM). Lastly, using the position inverse calculation, the tire crown crack was located. The experimental results demonstrate that the proposed approach was effective to detect the defects of tire crown which caused by tire cord overlap. The highest rate of correct detection can reach 97.7% in the 1000 crown images collected by the process of production.
To tackle multi-label data with high dimensionality and label correlations, a multi-label classification approach based on Singular Value Decomposition (SVD)-Partial Least Squares Regression (PLSR) was proposed, which aimed at performing dimensionality reduction and regression analysis. Firstly, the label space was taken into a whole so as to exploit the label correlations. After that, the score vectors of both the instance space and label space were obtained by SVD, which was used for dimensionality reduction. Finally, the model of multi-label classification was established based on PLSR. The experiments performed on four real data sets with higher dimensionality verify the effectiveness of the proposed method.
Methods of parallel computation are used in validating topology of polygons stored in simple feature model. This paper designed and implemented a parallel algorithm of validating topology of polygons stored in simple feature model. The algorithm changed the master-slave strategy based on characteristics of topology validation and generated threads in master processor to implement task parallelism. Running time of computing and writing topology errors was hidden in this way. MPI and PThread were used to achieve the combination of processes and threads. The land use data of 5 cities in Jiangsu, China, was used to check the performance of this algorithm. After testing, this parallel algorithm is able to validate topology of massive polygons stored in simple feature model correctly and efficiently. Compared with master-slave strategy, the speedup of this algorithm increases by 20%.
To effectively improve the denoising effect of the original anisotropic diffusion model that used only the 4 neighborhood pixels information and ignored the diagonal neighborhood pixels information of the pixel to be repaired in the image denoising process, a image denoising algorithm using UK-flag shaped anisotropic diffusion model was proposed. This model not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also used another 4 diagonal neighborhood pixels information in the denoising process. Then the model using the 8 direction pixels information for image denoising was presented, and it was proved to be rational. The proposed algorithm, the original algorithm, and an improved similar algorithm were used to remove the noise from 4 images with noise. The experimental results show that the proposed algorithm has an average increase of 1.90dB and 1.43dB in Peak Signal-to-Noise Ratio (PSNR) value respectively, and an average increase of 0.175 and 0.1 in Mean Structure Similitary Index (MSSIM) value respectively, compared with the original algorithm and the improved similar algorithm, which concludes that the proposed algorithm is more suitable for image denoising. algorithm not only made full use of the reference information of the 4 neighborhood pixels as in original algorithm, but also another 4 diagonal neighborhood pixels information was used in the denoising process, and the algorithm was proved to be rationality. The experimental results showed that the proposed algorithm could increase the PSNR (peak signal-to-noise ratio) value 1.69db, and the MSSIM(mean structure similitary index) value 0.14, compared with the other similar algorithms in image denoising, which conclud that this proposed algorithm is more suitable for image denoising.
New difficulties are met when establishing accurate behavioral models of a transport robot. To solve this problem, behavioral models of a transport robot were built using Petri Nets (PN) with inhibitor arcs. There exist coupling, constraint, and asynchronization relationships among the behaviors of a transport robot. A Petri net metamodel with inhibitor arcs of interactive behaviors as well as a token flow control mechanism were utilized for modeling the behaviors of a transport robot. The Petri net models were converted into LabVIEW programs using LabVIEW2012 and the Robotics module. The robot behaviors were verified using a transport robot platform. The experimental results demonstrate that the transport robot's behaviors and interaction logic are achieved, and that the robot has behavioral identification, decision-making and implementation capabilities, and it is a suitable method model the behaviors of a transport robot using Petri nets with inhibitor arcs. The reference models of Petri nets are given for designing related behaviors of transport robots.
To improve the accuracy of recommended Web resources, a personalized recommendation algorithm based on ontology, named BO-RM, was proposed. Subject extraction and similarity measurement methods were designed, and ontology semantic was used to cluster Web resources. With a user's browser tracks captured, the tendency of preferences and recommendation were adjusted dynamically. Comparison experiments with collaborative filtering algorithm based on situation named CFR-RM and personalized prediction algorithm based on model were given. The results show that BO-RM has relatively stable overhead time and good performance in Mean Reciprocal Rank (MRR) and Mean Average Precision (MAP). The results prove that BO-RM improves the efficiency by using offline data analysis for large Web resources, thus it is practical. In addition, BO-RM captures the users' interest in real-time to updates the recommendation list dynamically, which meets the real needs of users.
In the domain of structural pattern recognition, the existing graph embedding methods lack versatility and have high computation complexity. A new graph embedding method integrated with multiscale features based on space syntax theory was proposed to solve this problem. This paper extracted the global, local and detail features to construct feature vector depicting the graph feature by multiscale histogram. The global features included vertex number, edge number, and intelligible degree. The local features referred to node topological feature, edge domain features dissimilarity and edge topological features dissimilarity. The detail features comprised numerical and symbolic attributes on vertex and edge. In this way, the structural pattern recognition was converted into statistical pattern recognition, thus Support Vector Machine (SVM) could be applied to achieve graph classification. The experimental results show that the proposed graph embedding method can achieve higher classifying accuracy in different graph datasets. Compared with other graph embedding methods, the proposed method can adequately render the graphs topology, merge the non-topological features in terms of the graphs domain property, and it has a favorable universality and low computation complexity.
