Abstract:While the existing deep neural networks have earned great successes in various application scenarios，they are still facing black-box challenges that they are not very suitable for some application fields such as healthcare， finance and transportation. Therefore， explainable artificial intelligence （XAI） has been becoming a hot research topic in recent years. Among the existing XAI means， since fuzzy AI systems have the impressive ability to achieve an excellent trade-off between performance and interpretability，interpretable deep Takagi-Sugeno-Kang （TSK） fuzzy systems have been drawing more and more attentions. We first state the concept of the classical TSK fuzzy systems，then give a comprehensive overview of interpretable deep TSK fuzzy systems which are based on stacked generalization principle， including their structures，representative models and application scenarios， and finally discuss their future development direction according to their existing problems.

Abstract:With the development of unmanned aerial vehicle （UAV） software and hardware technology， the flying Ad-Hoc networks （FANETs） formed by the self-organization of multiple UAV clusters have received more and more attention from academia and industry. Its flexible deployment and rapid response capabilities enable it to complete a variety of tasks efficiently and inexpensively. Moreover， the UAV routing protocol is one of the most critical methods to improve the quality of service （QoS）. The mobility and dynamics of FANETs make the design of routing protocols face severe challenges. Conventional mobile routing protocols cannot sufficiently meet the routing requirements of FANETs. Therefore， researchers have proposed a variety of UAV self-organizing network routing protocols from the perspectives of topology， geography， and layering， aiming to overcome mobility and improve network QoS. This paper facuses on UAV Ad-Hoc networks， categorizes and summarizes routing protocols from different routing decision-making methods， and prospects future research directions.

Abstract:Photoacoustic imaging （PAI） is a newly emerging hybrid functional imaging modality. High-quality image reconstruction is the key to improve the imaging accuracy. Incomplete photoacoustic（PA） measurements usually lead to the reduction in the imaging depth and the quality of images which are rendered by using conventional reconstruction techniques such as back projection （BP）， time reversal （TR）， and delay and sum （DAS）. The iterative algorithms are capable of solving this issue to a certain extent at the cost of high computational burden and a properly selected regularization tool. In recent years， deep learning （DL） has exhibited promising performances in the field of medical imaging. It has also shown great potential in reconstructing images with high quality and high efficiency. This paper provides a survey on PA image reconstruction from sparely sampled data in a limited view based on DL. The current methods are summarized and classified， and their advantages and limits are also discussed.

Abstract:This paper proposes a medical image encryption scheme based on Gray code scrambling and block chaotic scrambling Gray+block chaotic scrambling optimized for medical image encryption（GBCS）， which is applied to privacy protection classification. First， the image is sliced by bit-planes.Then， different bit-planes of images are scrambled by the Gray code and then divided into blocks， and chaotic encryption is carried out on these blocks. Finally， the encrypted images are classified by deep learning network. We quantitatively analyze the privacy protection and classification performance of GBCS through cross-validation simulation on public breast cancer and glaucoma datasets， and perform a safety analysis of the method by histogram， information entropy， and anti-attack ability. The experimental results prove the effectiveness of our method. The performance gap of medical images before and after GBCS encryption are within an acceptable range. The proposed scheme can better balance the contradiction between performance and privacy protection requirements， and effectively resist the attack of adversarial samples.

Abstract:Concept drift is an important and difficult issue in streaming data mining tasks. At present， the concept drift processing methods adopt the ensemble learning strategy mostly. However， most of these methods cannot extract the key information of the new data distribution after concept drift， leading to poor model performance. To solve this problem， this paper proposes a concept drift detection and convergence method based on hybrid ensemble of serial and cross （SC_ensemble）. When streaming data are in a stable state， the method trains serial base classifiers for ensemble learning， to extract effective information representing the overall data distribution. After concept drift occurs， parallel cross base classifiers are constructed near the drift site for ensemble learning， to extract the local effective information representing the latest data distribution. By ensemble learning of serial base classifiers and cross classifiers， the method takes into account the overall distribution information contained in streaming data， and strengthens the important local information when concept drift occurs， so that the ensemble model contains more “good but different” base learners， and realizes the efficient combination of learning models after concept drift. The experimental results show that the proposed method can make the online learning model converge quickly after concept drift， and improve the generalization performance of the model.

Abstract:Principal component analysis （PCA） is a commonly used method for feature extraction and data dimension reduction. In many applications， the components whose eigenvalues are greater than the average value are retained. However， there is no specific analysis result for the relationship between the number of principal components and the application results. Therefore， an experimental analysis of the difference in selection of PCA threshold is carried out to provide basis for the PCA threshold selection in different applications. The experiment analysis is used to reduce the dimension of handwritten digital sample set MNIST， and different neural networks are constructed according to different thresholds for classification. Furthermore， the change of classification accuracy under different thresholds is analyzed. The experimental results show that when the threshold of PCA is between 79%—81% （dimension is 41—50）， the classification accuracy is the highest， and the accuracy decreases accordingly when the threshold is lower or higher than that region. It is proved that there is no positive correlation between application results and threshold selection of PCA， and the average of the eigenvalues is not a mandatory criterion.

Abstract:Aiming at the problem of outlier detection of mixed attributes，this paper proposes a method for outlier detection of mixed attributes based on neighborhood approximate accuracy. First， a heterogeneous neighborhood relationship metric is defined to represent the proximity between mixed data. Then， a specific neighborhood approximation accuracy is defined to construct the neighborhood grain outliers. Further， a neighborhood approximation accuracy-based outlier factor is defined and a neighborhood approximation accuracy-based outlier detection （NAAOD） algorithm is proposed. Finally，the effectiveness of the NAAOD algorithm is evaluated using the UCI dataset. Theoretical research and experimental results show that the NAAOD algorithm is effective for detecting outliers with mixed attributes.

Abstract:The purpose of extracting evaluation object of the microblog involved in a case is to identify the case object terms of the user evaluation from the microblog comments， which helps to grasp public thought on different aspects of a certain case. In general， the existing methods regard evaluation object extraction as a sequence labeling task， but do not take into account the domain characteristics of the microblog involved in the case， that is， comments are usually discussed around the case keywords that appear in the microblog text. For this reason， this paper proposes a sequence labeling model based on case keyword structured encoding to extract the evaluation objects of the microblog involved in the case. First of all， a number of case keywords are obtained from the text of microblogs， and the structured encoding mechanism is used to convert them into keyword structural representations. After that， the representations are integrated into the comment sentence representation through the cross attention mechanism. In the end， the evaluation target terms are extracted by the conditional random field （CRF）. Experiments are conducted on the data sets of two cases. Compared with the multiple baselines， the encouraging progress validates the effectiveness of the proposed approach.

Abstract:With the increase of the volume of data， multi-view clustering with missing view data is becoming progressively common， which is regarded as the incomplete multi-view clustering. Powered by the development of deep learning models， clustering models introduced deep learning can normally get more outstanding performance than shallow models. A novel deep incomplete multi-view clustering model is proposed， which is called improved self-paced deep incomplete multi-view clustering. In this model， the complementarity of multi-view data is fully considered， and the missing views are completed by the nearest neighbor imputation scheme based on multi-view data characteristics. Multiple encoders are exerted to obtain the low-dimensional potential features of multiple views. Meanwhile， the graph embedding strategy is introduced to maintain the geometric structure among the potential features. The consistency principle is exerted to fuse the potential features from different views to obtain consistent potential features. Experimental results indicate that， compared with the existing incomplete multi-view clustering models， our model can deal with various incomplete multi-view clustering more flexibly and efficiently， thus improving the robustness and performance of incomplete multi-view clustering.

Abstract:The interactive query analysis technology represented by data warehouse application provides support for intelligent decision-making. With the continuous increase of data scale， accurate calculation of query results often requires global data scanning， which makes the group-by query face the problem of insufficient real-time response ability. Based on the pre-extracted sample data， it can provide fast approximate answers for aggregate queries， which is a feasible solution to this problem in many scenarios. This paper analyzes the specific conditions that stratified sampling is better than random sampling， and proposes a two-stage stratified sampling method. In the first stage， the sampling is grouped according to the business characteristics. In each grouping， the random sampling method is first used for random sampling， and the sampling effect is evaluated. To improve the effect of approximate query， the second stage sampling is carried out， and the self-organizing feature mapping （SOM） clustering method is used to group the values. Experimental results on the public data set and the actual power grid data show that， compared with random sampling， stratified random sampling and congressional sampling algorithm， performance of the proposed method can be improved by 15% at most under the same sampling rate. And SOM has better approximate query results than K-means and density-based spatial clustering of applications with noise （DBSCAN） clustering methods.

Abstract:Aiming at the problems of insufficient utilization of syntactic dependencies between words and lack of global semantic information in Chinese event detection， a Chinese event detection model based on syntactic and full-text information enhancement is proposed. Firstly， the model introduces graph convolutional network （GCN） to enhance the feature representation of words by capturing the dependency syntactic relationship between words. Then， bidirectional gate recurrent unit （Bi-GRU） is used to learn the context information within and between sentences respectively， and the sentence vector containing the global information of the article is obtained. Finally， the information of word， phrase and sentence is dynamically fused through the gate structure， and the conditional random field （CRF） is used to identify and label the trigger words in the sentence. Experimental results on ACE2005 and CEC Chinese data sets show that the proposed method effectively improves the effect of Chinese event detection.

Abstract:As for low-resolution face detection in real-world video surveillance， achieving balance in terms of speed， accuracy， and memory consumption is of great importance due to the hardware constraints. Towards the problem， inspired by the more recent RetinaFace this paper proposes a light-weight scale-adaptive deep face detection model， termed as DLFace. Firstly， the improved depthwise separable convolution can effectively prevent information loss during training. Secondly， the improved deformable convolution is introduced into the backbone network and single stage headless （SSH） face detector， so as to enlarge the receptive field while also to adapt to facial changes such as expression， pose and so on. Finally， a Lambda layer is introduced in the high level of the backbone network， attempting to effectively explore the semantic and location information to form a richer representation of facial features. Experimental results on the WiderFace dataset show that DLFace has achieved a comparable or even better performance than existing light-weight face detection methods. Meanwhile， DLFace also achieves a better performance balance than most of previous methods in prediction efficiency and effectiveness.

Abstract:Sparse principal component analysis is an unsupervised method for dimensionality reduction and feature selection. An adaptive sparse principal component analysis （ASPCA） algorithm is proposed， because the principal load vectors do not have the same sparse pattern when calculating multiple principal components， and it is difficult to determine a small number of the variables that contribute the most to the principal components from the original feature space. Firstly， the group lasso model is used， and the ASPCA formula is obtained by applying block sparse constraints on the load vector. Subsequently， different adjustment parameters are used for different columns of the sparse matrix to obtain adaptive penalty. Finally， the block-coordinate descent method is used to optimize the adaptive sparse principal component analysis formula in two stages， so as to find the sparse load matrix and the orthogonal matrix and achieve the optimization of dimensionality reduction. The comparison results of the sparse principal component analysis （SPCA） algorithm， the structured and sparse principal component analysis （SSPCA） algorithm and the ASPCA algorithm show that the ASPCA algorithm has better dimensionality reduction performance and can extract more valuable features， thereby effectively improving the average classification accuracy of the classification model.

Abstract:The blurry ultrasound image is not sparse enough after the extreme channel prior deblurring， resulting in the extreme channel sparse constraint may not exist. Therefore， in order to make full use of the image channel information， a blind ultrasound image deblurring algorithm via quadratic sparse extreme channel prior is proposed by enhancing the sparsity of the obtained ultrasound image after deblurring. First， relevant theoretical proofs and experiments are presented to illustrate the feasibility of quadratic sparse extreme channel priors for constrained blurry ultrasound images. Then， making full use of the prior information of the dark and bright channels， the half-quadratic splitting method is used to estimate the intermediate image and the blur kernel. Finally， the Fourier transform is used to obtain the final clear image and blur kernel. Experimental results on the ultrasound image set show that the feasibility and superiority of the proposed algorithm compared other current ultrasound image deblurring methods.

Abstract:The identity resolution across social platforms is an important research aspect， which integrates the user’s information from various platforms. Most of the existing user identity resolution work is aimed at social platforms with similar types. The information between platforms is relatively symmetrical. Whether the user is the same user is determined by the similarity of user’s profile attributes， spatial location， network relations and other information on different platforms. However， in the two heterogeneous social platforms， the user information is asymmetric so that we cannot get the corresponding attribute information for user identity resolution. This paper discusses the method of user identity resolution across comment and activity platforms. To solve the problem of user information attribute asymmetry of across social platforms， the user information is organized according to three types of information： profile attribute， semantic sequence and feature word sequence. The corresponding information is extracted from their respective social platforms to establish mapping relationships， and an integrated matching algorithm integrating the three types of information is proposed. Considering the time offset phenomenon of user activities， the back propagation learning method is used to obtain the time offset weights， and a similarity measurement method between semantic sequence and feature word sequence based on back propagation learning is proposed. At the same time， an overall similarity is designed for user identity. Experimental results on real dataset show that the proposed method is effective on user identity resolution.

Abstract:Currently， there is heterogeneity in the functional brain images of suicidal patients with major depressive disorder （MDD） from multiple imaging sites， resulting in computational difficulties and affecting the reliability. According to the data from homogenizing multisite resting-state functional magnetic resonance imaging（rfMRI） from patients with MDD， the influence of suicidal tendencies on the MDD brain functional network is studied. Firstly， rfMRI of 99 MDD patients （including 67 non-suicidal MDD（nMDD）， 32 suicidal MDD（sMDD）） along with 72 healthy controls（HC） subjects from 3 sites are enrolled. After preprocessing of rfMRI， the functional connectivity of the Pearson correlation is calculated on the whole brain， and multisite functional connectivity is homogenized by ComBat technology. Then， the brain network topology is established and the graph theory analysis is performed by taking the existence of small-world attributes as the criterion for sparsity， the functional connectivity as edges and the brain areas as the nodes. Comparisons of the significance between groups are made on node degrees and node efficiency indicators in the graph theory. Experimental results show that the heterogeneity of functional connectivity in sites is effectively eliminated by the homogenization algorithm.Compared with the nMDD and HC groups，the sMDD group has siginificant between-group difference （p_FDF<0.05）in inferior cerebellar lobule and vermis cone. There exist abnormal functional activities in the inferior cerebellar lobules and vermis cones due to the suicidal tendencies. Based on the multisite homogenization of MDD network-level functional connectivity， this study effectively extracts the network characteristic indicators of suicidal patients and provides the functional imaging markers for the suicide risk assessment.

Abstract:Molecular machine is a kind of machine composed of molecular scale materials and can perform a certain processing function. Three-dimensional structure determines the related properties and functions of proteins. How the amino acid （residue） sequence of a protein folds into a specific three-dimensional structure， that is， understanding the folding mechanism and characteristics of protein structure is of great significance for the study of molecular machines. Therefore， it is necessary to use a fast and simple simulation method to study the folding mechanism information of protein structure. In this paper， based on the natural state topology of protein， we use Gaussian network model to study protein GB1 and analyze the structural characteristics of protein GB1 and its unfolding process. The results are in good agreement with experimental data and molecular dynamics simulation data， showing that the elastic network model is suitable for the study of protein structure.

Abstract:Aiming at the problem that the performance of the paper citation prediction method is degraded when the features are sparse， a method based on heterogeneous feature fusion is proposed， thus can use fixed-length features， citation network features and citation time series features at the same time， thus effectively improving the accuracy of the citation prediction method. Firstly， this paper defines a citation attribute network for the paper citation prediction task， and models three types of heterogeneous features. Secondly， a paper citation prediction method for heterogeneous feature fusion is proposed. The method uses the graph neural network to process fixed-length features and citation network features， uses the recurrent neural network to process citation time series features， and fuses the extracted heterogeneous features and predicts the number of citations based on multi-head attention mechanism. Experiments on large-scale real datasets show that the proposed method can effectively utilize multiple heterogeneous features and alleviate the problem of data sparsity， and its root mean square error（RMSE） is 0.31 lower than that of the best benchmark method.

Abstract:In order to solve the problem that the existing virtual fitting methods cannot be applied to academic uniforms， a virtual try-on method oriented to the generation of academic uniforms is proposed. The method first trains the image-based virtual try-on network composed of the clothing deformation module and the virtual try-on module， and then generates try-on results through the trained network of the portrait and the academic dress image. Then， the generated academic dress try-on results are synthesized with the specific background through the background fusion module. During the experiment， this paper constructs a new dataset of academic dress and long skirt. From the experimental results， the algorithm proposed in this paper can greatly reduce the impact of the clothes in the original portrait on the academic dress try-on， and can better complete the academic dress try-on work and generate more ideal fitting results.

Abstract:In order to improve the joint estimation accuracy of time of arrival （TOA） and direction of arrival （DOA） in existing impulse radio ultra wideband （IR-UWB） systems， a joint estimation method of TOA and DOA based on discrete Fourier transform （DFT） is proposed. First， the received signal is modeled in the frequency domain. Second， the rough TOA estimation results of the two antennas can be obtained via processing DFT on the covariance matrix of the received signal in the frequency domain. Based on the rough estimation results， we search the compensation value with a small interval， thereby the accurate estimation of TOA can be obtained. Third， according to the relationship between the time difference of arrival of the two antennas and DOA， we obtain the DOA estimation results， thus realize the joint estimation of TOA and DOA. The simulation results show that the performance of the proposed algorithm is better than that of the matrix pencil algorithm and the traditional propagation method， and the advantage becomes more obvious with the increase of SNR. Moreover， the proposed algorithm is easier to be implemented in engineering because it does not need complex eigenvalue decomposition and generalized inverse solution steps.

Abstract:The equipment monitoring of the merging unit relies on on-site staff records， practical experience and preset alarm threshold， and the lack of analysis and mining of the system monitoring data makes it impossible to realize the device state prediction. In view of this， according to the timing characteristics of the level data of the monitoring merge unit， a combined model of the traditional timing model of autoregressive integrated moving average （ARIMA） and long short-term memory（LSTM） is constructed and optimized by using shuffled frog leaping algorithm（SFLA）. The optimized model is applied to the level data prediction analysis of the combined unit laser monitoring. The comparison of the ARIMA-LSTM optimized combination model with the single model verifies that the former has higher accuracy than the latter. Further comparison experimental results show that the combined model is superior to the other combined models after the SFLA algorithm optimization， which can better mine the hidden information and trend in the data， improving the accuracy of time series data prediction and the efficiency of fault troubleshooting. By comparing the combined ARIMA-SVM model and the proposed ARIMA-LSTM model， experimental results show that the proposed ARIMA-LSTM model is superior to the ARIMA-SVM model， and it can better analyze and grasp the device state information， and realize the level data prediction of the merging unit equipment.