Search

In view of the problems of data sparsity and the diversity in academic paper recom-mender systems,based on CONVNCF, this paper proposed an algorithm of convolution with word and heterogeneous information network for academic paper recommendation ( WN -APR) . Firstly, WN -APR algorithm learned user and paper' s diverse features from different semantics to alleviate the sparsity problem. Then it designed an outer product fusing way to seamlessly combine user features with paper features. Replacing of 2D CNN, this algorithm applied 3 D convolution to mine the influence of different features on the performance. Finally, it modified the BPR loss function to enhance diversity in recommendations. Experimental results on CiteULike-a and CiteULike-t datasets show that WN-APR improves the performance of accuracy and diversity over the baseline models. [ABSTRACT FROM AUTHOR]

Most of the existing MAPF methods based on communication learning have poor scalability or aggregate too much redundant information, resulting in inefficient communication. To solve these problems, this paper proposed disruptor identifiable communication (DIC), which learned concise communication excluding non-disruptors by judging whether the agent in the center of the field of view would change its decision-making due to the presence of neighbors, and successfully filtered out redundant information. At the same time, this paper further instantiated DIC and developed a new highly scalable distributed MAPF solver: disruptor identifiable communication based on reinforcement and imitation learning algorithm (DICRIA). Firstly, the disruptor discriminator and the policy output layer of DICRIA identified the disruptor. Secondly, the algorithm updated the information of the disruptor and the communication wish sender in two rounds of communication respectively. Finally, DICRIA output the final policy according to the coding results of each module. Experimental results show that DICRIA S performance is better than other similar solvers in almost all environment settings, and the algorithm increases the success rate by 5.2% on average compared to the baseline solver. Especially in dense problem instances with large-size maps, the algorithm even increases the success rate of DICRIA by 44.5% compared to the baseline solver. [ABSTRACT FROM AUTHOR]

In recent years, various human action recognition algorithms have achieved excellent recognition performance based on a large number of labeled samples. However, in practical applications, acquiring training samples and their corresponding labels is time-consuming and laborious, which limits the actual implementation of the algorithm. This paper summarized the deep learning algorithms for action recognition under weak supervision and few-shot learning. Firstly, in the case of weak supervision, it classified and summarized the semi-supervised action recognition methods and unsupervised domain adaptation video action recognition methods separately. Then, it reviewed video action recognition algorithms based on few-shot learning in detail. Further, it summarized the relevant human behavior datasets and analyzed and compared the performance of various relevant video action recognition algorithms on these datasets. Finally, the paper summarized the full text and discusses the future development trend of human action recognition. [ABSTRACT FROM AUTHOR]

The complexity of modern war is increasing，and the rapid operational mission planning is of great importance to improve the efficiency of command and control. This paper presents a joint operational Task Matrix （TM） model，which is a theoretical method for mission planning; A belief network model is put forward to describe the relationship among the elements in TM model ;A naive bayesian learning method for belief network is designed; A mechanism of imagination is put forward to speed up the learning process ; A search algorithm named Deep Minimum Threat Generation Tree（DMTGT） is proposed, which can efficiently calculate task priority by balancing search error and search speed. Finally, the validity of above models and algorithms is verified by simulation experiments. [ABSTRACT FROM AUTHOR]

Aiming at the deficiency that K2 algorithm depends on the maximum number of parent nodes and node of order, this paper proposed an improved Bayesian network structure learning algorithm (MWST-CS-K2). The algorithm firstly obtained the maximum number of parent nodes by constructing the maximum support tree (MWST). Then it used the correlation degree and updated coefficient between variables to set rules for adding, subtracting and reversing edges. The paper used improved cuckoo algorithm to optimize the nest location, and applied the breadth first search strategy to search and traverse to get the node order. Finally, the paper used maximum number of parent nodes and the order of nodes as the input of K2 algorithm to get the final network. Experiments show that in the standard ASIA,SACHS and CHILD network data tests, the average correct edge ratio of MWST-CS-K2 algorithm reaches 97.3%, 87.7 % and 95.6% respectively. The learning effect is better than other corresponding comparison algorithms, and the network structure obtains the most similar to the standard network structure. [ABSTRACT FROM AUTHOR]

Most of the existing image tampering detection methods are only for a certain tampering method, and there is a problem that the detection accuracy of the tampered area boundary is not high. In this regard, this paper proposed a U-shaped network based on dual-stream encoder-decoder architecture for image tampering. Firstly, the method used the skip connection between the encoder and the decoder to fuse the low-level and high-level features in the tampered image, and used the atrous convolution and CBAM attention mechanism to fuse the features output by the encoder, so that the network had better localization performance for tampered regions of different scales; Secondly, in order to improve the network’s detection accuracy of the boundary of the tampered area, this algorithm used the image morphological method to make a tampered boundary dataset; Finally, it used multiple loss functions to optimize the performance of the network simultaneously, namely it used cross-entropy and root-mean-square loss functions to measure the tampered region loss and tampered boundary loss of the prediction graph respectively. The experimental results on 4 public datasets: CASIA, Columbia, NIST16, Coverage show that the method proposed in this paper can effectively detect the tampering area of the fake image with splicing and copy-paste tampering methods, and output pixel-level tampering region location map. Compared with other mainstream tampering detection methods, the proposed method achieves the highest AUC values on the CASIA and Columbia dataset and the highest F1 values on the Columbia dataset. [ABSTRACT FROM AUTHOR]

In order to solve the problem of low accuracy of 6D pose estimation for textured models under occlusion, this paper proposes an end-to-end 6D pose estimation algorithm based on local feature representation. Firstly, this paper proposes a Spatial and Coordinate Attention mechanism to obtain accurate localization information. A YOLOv5-CBE detection network forms by adding the attention mechanism to the backbone network and introducing a weighted Bidirectional Feature Pyramid Network in the detection layer. The Precision, Recall and mAP@0.5 of YOLOV5-CBE algorithm rise by 3.6%, 2.8% and 2.5% respectively, and the coordinate error of local feature center point decreases by 25% at most. Secondly, the YOLOv5-CBE network detects the local feature key points and calculates 6D pose of the model with 3 D Harris key points by Singular Value Decomposition, and the algorithm can guarantee 2D reprojection Accuracy and ADD Accuracy above 95% with 70% occlusion, which has a strong robustness. [ABSTRACT FROM AUTHOR]

In reality, the data generated in many fields usually have multiple classes and are imbalanced. In multi-class imbalance classification, problems such as class overlap, noise and multiple minority classes reduce the capability of classifiers, and effective solution of multi-class imbalance problem has become an important research topic in the field of machine learning and data mining. Based on the recent literature on multi-class imbalance classification methods, this paper analyzed and summarized both data preprocessing and algorithm-level classification methods, and conducted a detailed analysis of all algorithms in terms of advantages, disadvantages and data sets. The data preprocessing methods introduced oversampling, under-sampling, hybrid sampling and feature selection methods to compare the performance of the algorithms using the same datasets. In addition, the algorithm-level classification methods described and analyzed base classifier optimization, ensemble learning and multi-class decomposition techniques. Finally, this paper summarizes the future development directions of the multi-class imbalanced data classification research field. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low detection accuracy in massive unbalanced data and poor model generalization ability caused by data heterogeneity in traditional anomaly detection methods in IoT scenarios, this paper proposed an adversarial dual-coding anomaly detection network based on federated learning(GB-AEnet-FL). Firstly, this paper proposed an active feature distribution learning algorithm based on abnormal data, which actively learns the potential feature distribution of data, expands abnormal data through data reconstruction, and balances the proportion of positive and negative samples. Secondly, this paper introduced an adversarial training mechanism in the latent feature layer adding consistency enhancement constraints and shrinkage constraints to improve the accuracy of feature extraction. Finally, this paper designed a federated learning algorithm based on dynamic model selection which compares the confidence scores of the local model and the global model, dynamically selects part of the federated bodies to participate, accelerates the aggregation of models, and protects user privacy to a certain extent. Validated on four different datasets, the results show that the proposed algorithm is better than the traditional algorithm in detection accuracy, and the generalization ability is improved accordingly. [ABSTRACT FROM AUTHOR]

Multiple random empirical kernel learning machine(MREKLM) selects a small number of samples to construct the empirical feature space, but does not take into account the distribution of data when projecting, and takes a long time to select samples. In order to utilize the distribution information of samples, this paper introduced the intraclass dispersion matrix, and proposed an intra-class variance based multiple empirical kernel learning(ICVMEKL), which enabled samples to take into account the intra-class information when projecting. The method enhanced the classification boundary and improved the classification accuracy. Further, in order to reduce the selection time of samples, this paper proposed an improved ICVMEKL(ICVMEKL＿I) based on locality-sensitive hashing algorithm by using the border point extraction based on locality-sensitive hashing(BPLSH) to select samples, so that the samples for constructing the empirical kernel no longer need to be obtained from the candidate set, and the method reduced the training time. Experiments on multiple datasets show that ICVMEKL can effectively improve the accuracy, ICVMEKL＿I can significantly reduce the training time, both of which show good generalization performance. [ABSTRACT FROM AUTHOR]

In order to overcome the challenges of policy learning in Multi-Agents Systems（MASs）, such as the unstable environment and the interaction of agent decisions, this paper proposes a method named Observation Relation Extraction（ORE）, which uses a complete graph to model the relationship between different parts of each agent’s observation, and takes advantage of the attention mechanism to calculate the importance of the relationship between different parts of each agent’s observation. By applying the above method to multi-agent reinforcement learning algorithms based on value decomposition, this paper proposes multi-agent reinforcement learning algorithms based on observation relation extraction. Experimental results on StarCraft Multi-Agent Challenge（SMAC） show the proposed algorithms with ORE leads to better performance than the original algorithms in terms of both convergence speed and final performance [ABSTRACT FROM AUTHOR]

With the continuous rise of federated learning, gradient boosting decision tree（GBDT）,as a traditional machine learning method, is gradually applied to federated learning to achieve ideal classification results.Aiming at the problems of the existing horizontal federated learning model of GBDT,such as the accuracy is greatly influenced by non-IID dataset, information leakage and high communication cost, the paper proposed a federated gradient boosting decision tree for non-IID dataset, called nFL-GBDT.Firstly, the algorithm calculated similar samples among the participants by utilizing the LSH,and using weighted gradient constructed the first tree.Secondly, a reliable third party calculated the global leaf weight that only needed one round of communication.Finally, the experimental analysis shows that the algorithm can protect the privacy of the original data, and its communication cost is lower than that of simFL and FederBoost.At the same time, the experiment divides three groups of public data sets according to the imbalance ratio.The results show that the accuracy of this algorithm is improved by 3.53%,5.46% and 4.43% respectively compared with Individual, TFL and F-GBDT-G. [ABSTRACT FROM AUTHOR]

In dynamic gesture recognition methods based on deep learning, aiming at the problems of large network scale, simple dimension of extracted spatiotemporal features, and insufficient extraction ability of effective features, this paper proposed a deep network framework. Firstly, this paper applied a novel spatiotemporal convolution module based on multiscale information fusion in the time domain to improve the 3D residual network structure, greatly reduced the size of the network and obtained rich spatiotemporal receptive field characteristics. Then it introduced a spatiotemporal feature channel attention mechanism with global information synchronization, and used a few parameters to construct the global dependency between feature maps, and the module could obtain the key features of dynamic gestures more efficiently. The experimental results on the self-built gesture dataset SHC and the public gesture dataset SKIG show that the proposed gesture recognition method has fewer parameters and more powerful multiscale spatiotemporal feature extraction ability, and gains a higher recognition rate than the current mainstream algorithms. [ABSTRACT FROM AUTHOR]

【Objective】 Aiming at the problems of easy falling off and easy to cause pig infection in traditional pig breeding ear tag recognition, the paper used the improved YOLOv5s model to carry out non-invasive recognition of pig face.【Method】 Firstly, the distance of K-Means was changed to 1-IOU, which improved the adaptability of the target anchor frame of the model; Secondly, the CA coordinate attention mechanism was introduced to improve the model feature extraction; Finally, BiFPN feature fusion was introduced to effectively use the features to improve the detection ability of the model. The pig face dataset used in the experiment was divided into 5 categories, with 12 756 samples after data enhancement, and the training set and test set were divided into a ratio of 9∶1.【Result】 The improved algorithm reached 0.926, 0.897 and 0.955 in accuracy, recall, and average accuracy (IOU=0.5), which were 13.2%, 3.0% and 2.2%, while the improved algorithm has better generalization ability and high recognition accuracy in single, multiple, small target, dense, and occluded scenes. 【Conclusion】 Using deep learning algorithm can get the facial information of pigs and identify them accurately, reduce the situation of missed inspection and wrong inspection, and provide better technical support for intelligent management of pigs. [ABSTRACT FROM AUTHOR]

LLP is a machine learning method that puts instances into packages. It only provides instance information and label proportional information in packages, but does not provide label information. Aiming at the LLP problem of multiple related tasks, this paper proposed a label proportion integrated learning model based on transfer learning, called AT-LLP for short. The model connected related tasks by constructing shared parameters between tasks, and migrated the knowledge learned in the source task to the target task, so as to improve the learning efficiency of the target task. At the same time, the algorithm introduced the ensemble learning algorithm, which continuously adjusted the weight coefficient of the training set in the multi-iteration learning process of the classifier, so as to further train the weak classifier into a strong classifier. Experiments show that the proposed AT-LLP model has better performance than the existing LLP method. [ABSTRACT FROM AUTHOR]

Local path planning for unmanned surface vehicle ( USV) plays an important role in maritime rescue and marine transportation. Existing local path planning algorithms achieve good results in simple scenarios, but have poor performance when facing complex obstacles and sea current disturbances present in the environment. To this end, this paper proposed a reinforcement learning algorithm based on spatial and temporal sensing-enhanced deep Q-network. Firstly, it introduced a multiscale spatial attention module to capture the multiscale spatial information of distance sensors, which enhanced the perception capability of complex obstacle environments. Secondly, it used the LSTM-based current sensing module to extract the temporal sequence features of the current disturbance environment, which enhanced the perception capability of the current disturbance. In addition, by simulating the sensor and motion model of USV, it designed the reinforcement learning state space, action space and direction-guided reward function, it improved the navigation performance and convergence speed of the algorithm. Simulation experiments in complex scenarios show that the proposed algorithm improves both success rate and average arrival time metrics comparing to the original algorithm, and the algorithm shows strong adaptability to complex environment. [ABSTRACT FROM AUTHOR]

In recommender systems, graph convolutional networks have stronger information extraction capabilities for graphstructured data. However, existing graph convolutional networks mainly focus on enhancing the model structure, ignoring the importance of improving the sampling quality of the original samples and mining the implicit relationship between users and items. Aiming at the above problems, this paper proposed a graph contrastive learning recommendation algorithm based on mixed sampling. Firstly, the algorithm used a mixed sampling method to extract part of the information in positive samples and injected them into negative samples, thereby generating new informative hard negative samples. Secondly, to extract features on hard negative samples, it used the light graph convolution network to obtain node representations of users and items. Finally, it carried out a multi-task strategy to jointly optimize the recommendation supervision task and the contrastive learning task. The experiments on real datasets Yelp2018 and Amazon-book demonstrate that the proposed algorithm improves performance compared with other recommendation algorithms in recall and NDCG evaluation indexes. [ABSTRACT FROM AUTHOR]

To accomplish the task of aerial manipulator’s autonomous grasping, it is very important to recognize and locate the object. At present, most of the recognition algorithms of aerial manipulators use traditional feature extraction methods. In order to improve the accuracy and efficiency of object recognition and positioning, this paper designs a visual recognition and positioning algorithm based on YOLOv5 deep learning object detection algorithm and RGB‑D sensor. The algorithm can detect the object in real‑time and estimate its pose, which serves for the grasping task of aerial manipulator. At the same time, aiming at the problems that the deep learning algorithm has a huge amount of calculation and cannot achieve high‑performance real‑time detection in the embedded system, model quantization is introduced to optimize the algorithm, which can greatly improve the processing speed of the algorithm. This paper introduces the overall framework and implementation process of the algorithm and verifies the effectiveness of some algorithms of object detection and pose estimation by using the COCO dataset and motion capture system. [ABSTRACT FROM AUTHOR]

Aiming at the problems of the current semantic segmentation network's spatial and channel feature mismatch, as well as the pixel loss of small target objects, this paper designed a dual-path semantic segmentation algorithm based on spatial feature extraction and attention mechanism. The spatial information path used four times downsampling to retain high-resolution features, and introduced a spatial feature extraction module to fuse multi-scale spatial information, thereby strengthening the network's ability to recognize small target objects. In addition, it used a semantic context path combined with two-stage channel attention to extract discriminative features, so that deep features could guide shallow features to capture more accurate semantic information, thereby reducing accuracy loss. This paper verified the algorithm on the CamVid dataset and Aeroscapes dataset, the mean intersection over union can reach 70. 5% and 51. 8% respectively. Compared with the current mainstream dual-path semantic segmentation model, the results verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

There is dynamic complexity of preference among members in group recommendation, and the preferences of group members will affect each other. As for these questions, this paper proposes a group recommendation algorithm that combines the context information and self attention mechanism. Specifically, first of all, in order to better capture the dynamic relationship among group members, the author used self attention mechanism to automatically learn the context information of users in the group and the relationship weights among other members in the group; Secondly, according to the group matrix learned from the self attention mechanism, the author embedded the average value to obtain the group preference expression. Finally, according to group preference, the author applied the Bayesian personalized ranking method into the test for group recommendation. During the research, the author used the above mentioned method to test on two datasets, namely Movielens-1 M and CAMRa2011. As a result, compared with the benchmark algorithm, this method has improved the evaluation indexes HR and NDCG. And the experimental results show that this method has achieved better effect in group recommendation. [ABSTRACT FROM AUTHOR]

In order to resolve the problems of large scale change, susceptibility to occlusion and similar object interference when target tracking by UAV, based on SiamCAR,this paper proposed IMPSiamCAR algorithm. The algorithm used the improved ResNet50 network to extract the target features, introduced the channel attention mechanism to make the model learn the semantic information of different channels, and assigned different weights to channels according to the importance of the features, so that the algorithm could pay more attention to the regions where the tracking targets exist. Then it fed the fused target features into the region regression network for positive and negative sample classification, centrality calculation and bounding box regression. Finally, it obtained the position of the target in each frame. Test experimental results of UAV123 and OTB100 datasets show that the proposed algorithm has higher tracking accuracy and success rate compared with the comparison algorithm, and can better deal with challenges such as occlusion, similar object interference as well as scale change. Moreover the results of real-time testing on VOT2018 and UAV123 datasets show that the proposed algorithm can fulfill the UAV real-time request. [ABSTRACT FROM AUTHOR]

Objectives: In recent years, the brain‑like navigation algorithm is a new research hotspot, which is expected to achieve autonomous navigation by imitating the ability of biological navigation. The core is‑ sue is how to improve generalization ability. Methods: This paper introduces the research background and theoretical basis of the brain‑like navigation algorithm. After investigation, we propose a computational framework of brain ‑ like navigation algorithm. The outstanding works in this field are discussed and analyzed under this framework, and we carried out experimental verification of some basic methods. Results： The main contributions of this paper are: (1) Comprehensively introduces and summarizes the theoretical basis and outstanding works in this field. (2) Proposes the computational framework of the brain‑like navigation algorithm, which scientifically defines the functions of different modules of the algorithm. (3) Through theoretical analysis and experimental verification, we summarized valuable conclusions and expectations. Conclusions: In terms of model design, mature methods of deep learning can also be applied to this problem, but need more modifications to further improve navigation capabilities; in terms of model training, combining the advantages of multiple learning algorithms is hopeful to further improve the generalization ability. [ABSTRACT FROM AUTHOR]

At present, researches on short-term load forecasting mainly focus on the analysis of influencing factors and the optimization of the model, and there are few researches on the robustness of the model. This paper took the extreme learning machine as the research object, conducted in-depth research on the robustness of the model, and applied it to the short-term load forecasting problem. The robustness of the ELM model was affected by the loss function. The current ELM model had poor robustness and low prediction accuracy when dealing with the samples containing outliers. To solve this problem, this paper proposed a new loss function based on p-order maximum correntropy criterion. It applied the loss function to the ELM model to improve its robustness in regression prediction. It proposed a method to estimate the percentage of noise in the actual sample, and gave the degree of noise pollution in the sample before established the load forecasting model. The simulation results show that the proposed algorithm model has better robustness and prediction accuracy when the outlier is more than 12%. [ABSTRACT FROM AUTHOR]

Aiming at the problem of fine-grained visual categorization, this paper proposed an effective algorithm to achieve end-to-end fine-grained visual categorization. The ECA module in ECA-Net was a channel attention mechanism with significant performance advantages. It model-fused with the classic network ResNet-50 to form the ResEca. Then, it used the object-level image positioning module and the part-level image generation module to generate object-level and part-level images. Those images combined with original images could be as the input of the new constructed network Tb-ResEca-Net. This paper trained the 95. 1% and 95. 3% respectively on the test set of the corresponding dataset. The experimental results show that this method has higher classification accuracy and stronger robustness compares with other traditional fine-grained classification methods, which is an effective fine-grained image classification method. [ABSTRACT FROM AUTHOR]

Meta reinforcement learning（Meta-RL）aims at automatically learning induction bias for a new reinforcement learning task from a set of different but related tasks. It plays an important role in improving the sample efficiency and generalization of reinforcement learning algorithm in difficult scenarios. This paper first introduces a framework in which three key components of Meta-RL are identified，i.e.，learning experience （related tasks），inductive bias and learning objective. Based on this，current research progress in this field is analyzed and reviewed，and the principles and characteristics of several representative algorithms are described. The paper also gives a detailed account of commonly used benchmark environments and performance evaluation methods for meta-RL. The limitation of current research and potential future development directions are also discussed. [ABSTRACT FROM AUTHOR]

People have widely used air quality prediction models composed of traditional machine learning methods. However, such models still have shortage on data validity, especially the validity of spatial-temporal related data selection. In response to the input data validity of deep learning networks, this paper proposed a prediction model based on spatial-temporal similarity LSTM to select more effective data at the time and space level. STS-LSTM contained three modules, pre-order, middle-order and post-order module. The pre-order module was the time-space similar selection input module, which proposed the GCWDTW algorithm. This paper used it to select data with higher temporal and spatial similarity. The in-order module used LSTM as a deep. learning network for training. The post-order module selected different output groups for integration according to the characteristies of the target station. The STS-LSTM overall model improves the air quality prediction error by about 8% compared with the existing algorithm, and the data selected by the validity improves the accuracy of the model by up to 21%. The experimental results show that this model has achieved significant results in the effective data selection, and the data input and output method as a part of the applied deep learning network can effectively improve the final effect of the deep learning network. [ABSTRACT FROM AUTHOR]

Aiming at the problem of insufficient accuracy of 3D face reconstruction and dense alignment algorithm,this paper introduced densely connected multi-scale feature fusion module and residual attention mechanism to design a powerful network. For the encoder structure, this paper introduced a densely connected multi-scale feature fusion module to obtain multi-scale fusion features, which made the encoder obtain richer information. The decoder module introduced residual attention mechanism to strengthen the network 's attention to important features while suppressing unnecessary noise. According to the experimental results, compared with other algorithms, the proposed algorithm achieves a significant improvement. Compared with the PRN et, the algorithm uses fewer parameters to achieve a performance improvement of 7. 7% to 12. 1 % in various indicators. [ABSTRACT FROM AUTHOR]

Loop closure detection is important for visual simultaneous localization and mapping (VSLAM) systems to reduce cumulative errors and perform re-localization. In order to shorten the loop closure detection online runtime while meeting the accuracy recall rate requirement, the paper proposed a fast loop closure detection algorithm using broad autoencoder (FLCD-BA). The algorithm improved broad learning architecture to learn feature representations autonomously from the input data in an unsupervised manner, and then accomplished loop closure detection tasks. Differing from the traditional deep learning methods, the network used a pseudo-inverse ridge regression algorithm to solve the weight matrix and achieved fast reconfiguration of the network by incremental learning without retraining the entire network. The proposed algorithm experimented on three public datasets without using GPU devices, and the training time of the network greatly reduced compared to bag-of-words models as well as deep learning methods. The experimental results show that the algorithm has high accuracy and recall in detecting loop closure, and the average running time per frame in the test is only 21 ms, which provides a new algorithm for loop closure detection in visual SLAM systems. [ABSTRACT FROM AUTHOR]

To address the problem of low efficiency of speech transmission in emergency broadcast, this paper proposes a speech compression method based on the wavelet transform and K-singular value decomposition(K-SVD) to improve the information transmission timeliness of emergency broadcast. Firstly, the proposed method discards the high-frequency components which is obtained from the speech wavelet decomposition, and replaces them with random signals during the wavelet synthesis process. Next, in the compressed sensing process of the low-frequency component, it is sparsely represented by an overcomplete dictionary which is trained by the K-SVD learning algorithm. Finally, the method reconstruct this signal by an improved algorithm of the generalized orthogonal matching pursuit based on subspace backtracking. Experimental results show that the perceptual evaluation of speech quality(PESQ) of the reconstructed emergency broadcast speech reaches 3.717 at a compression efficiency of 50%, the PESQ is 3% to 47% better than the comparison algorithms. This indicates that the method can improve the speech reconstruction quality of emergency broadcast and ensure the timeliness of emergency broadcast transmission while ensuring the compression efficiency. [ABSTRACT FROM AUTHOR]

Reinforcement learning method has many advantages in solving the robot manipulation problems. However, the traditional reinforcement learning algorithm faces the difficulty of sparse reward, and the policy is difficult to be directly applied to the reality. In order to improve the success rate of policy migration from simulation to reality, this paper proposes a goal-based domain randomization method: The method uses the goal-based reinforcement learning algorithm to train the model, which can effectively deal with the sparse reward of robot manipulation tasks, and the policy can run well in the simulation environment. At the same time, the method uses the goal-conditioned domain randomization algorithm, which has a good performance on improving the universality of policy and overcoming the reality gap between simulation and reality. The policy in simulation is easy to migrate to reality and execute successfully. The results show that the reinforcement learning algorithm using the goal-based domain randomization method helps to improve the success rate of policy migration from simulation to reality. [ABSTRACT FROM AUTHOR]

In order to detect online spam reviews effectively, this paper proposed a method to detect spam reviews based on XGBoost-EasyEnsemble algorithm. Firstly, according to the characteristics of spam reviews, this paper proposed a calculation method of subjectivity and built a multi-dimensional feature model. Secondly, in view of the class-imbalance problem, EasyEn semble algorithm used integration strategy to make up for the defects of the under-sampling method, and fully utilized sample information. Finally, it chose XGBoost model with higher diversity and accuracy as base classifier to train. In terms of AUC. comparative experiments on reviews from Yelp. com was conducted with five hot machine learning algorithms, and the results verify the validity of the method. [ABSTRACT FROM AUTHOR]

There are few studies on the problem of stochastic resource-constrained distributed multi-project scheduling (SDRCMPSP） and most of them are static scheduling schemes, which cannot adjust and optimize the strategy in real time according to changes in the environment and respond to frequent dynamic factors in a timely manner. Therefore, this paper established a stochastic resource-constrained multi-project dynamic scheduling DRL model with the goal of minimizing the total drag cost, design the corresponding agent interaction environment, and use the DDDQN algorithm in reinforcement learning to solve the model. The experiment first analyzes the hyperparameters of the algorithm, and then trains and tests the model under two different conditions of variable activity duration and uncertain arrival time, and the results show that the deep reinforcement learning algorithm can obtain scheduling results that are better than any single rule, effectively reduce the total drag-off cost of random resources limited multi-project expectations, and provide a good basis for multi-project scheduling decision optimization. [ABSTRACT FROM AUTHOR]

Applying knowledge graph to recommendation system can make use of semantic relations between entities of knowledge graph to learn user and item representation. The embedding propagation method uses the graph structure of the knowledge graph to learn relevant features, but the semantic dependency between multi-hop entities decreases as the propagation range increases. In order to effectively improve the semantic expression ability of recommendation and improve the accuracy of recommendation, this paper proposes a knowledge-aware propagation recommendation algorithm based on users’ potential interests. The model adopts heterogeneous propagation method to disseminate item relevant knowledge and iteratively learn users’ potential interests, so as to enhance the representation ability of the model to users and items. Specifically, first, graph embedding layer generate initialize representation of users and items, and in the heterogeneous propagation layer, the knowledge-aware attention mechanism can distinguish the importance of entities in the same layer, so the model can generate the representation of target entities more accurately. Then the user’s potential interest propagation can effectively learn the user’s higher-order potential interest and enhance the semantic relevance of multi-hop entities. Finally, information decay factor is used in the prediction layer to distinguish the importance of different communication levels and generate the final representation of users and items. Experiments show that the AUC value of the model on the Last. FM and Book-Crossing increases by 2.25% and 4.71% compared with the most advanced baseline, and the F1 value increases by 3.05% and 1.20% respectively, and the Recall@K value is superior to the comparison baseline model. The proposed model can effectively improve the accuracy of recommendation. [ABSTRACT FROM AUTHOR]

For the accuracy and real-time performance of multiple input multiple output (MIMO) nonlinear time-delay system, this paper propose the identification scheme based on multi-dimensional Taylor Network (MTN). It use MTN as an identification model. MTN identification model’s learning algorithm adopts the WE-CG algorithm, which combines the weight-elimination (WE) algorithm with the conjugate gradient (CG) algorithm. WE algorithm can simplify the structure of MTN model so as to reduce computational complexity and improve the real-time performance. Finally, there are two experimental examples containing a numerical example and a project one to verify the effectiveness of the proposed identification scheme. And use the traditional MTN identification scheme to compare. Both the accuracy and the computational complexity analysis illustrate the accuracy and the real-time performance of the proposed scheme. Results from the experiments and comparison show that the proposed scheme can identify the MIMO nonlinear time-delay system accurately, and the proposed identification scheme has a simpler structure and lower computational complexity than the traditional MTN identification scheme. [ABSTRACT FROM AUTHOR]

Mobile edge computing is a method to solve the computing-intensive task requirements of robots. Traditional algorithms are based on intelligent algorithms or convex optimization methods, and the iteration time is long. Deep reinforcement learning can be solved in a single forward pass, but only for a fixed number of robots. Through the analysis and research of deep reinforcement learning, this paper performed input regularization before the input layer in the deep reinforcement learning neural network, and added a convolution layer after the output layer so that the network could adaptively meet the unloading requirements of the number of dynamic mobile robots. Finally, it carried out the simulation experiments to verify the effectiveness and feasibility of proposed algorithm, compared with the adaptive gen etic algorithm and reinforcement learning . [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing super-resolution algorithm based on deep learning didn't make full use of the feature information of each level, resulting in low reconstruction accuracy and large parameter quantity, this paper proposed a double dense connection structure named densely channel attention skip connection network. In the inner structure of the network, it improved the original dense cascade block to generate a channel separable dense cascade block. The outer structure adopted a densely residual connection and attention mechanism to fuse the features extracted by the dense block to achieve the goal that less convolution layer and higher precision effect. This paper tested the network models on several benchmark datasets . The results show the proposed model has higher accuracy and fewer parameters than the other models. [ABSTRACT FROM AUTHOR]

Based on video action recognition, this paper firstly reviewed the traditional action recognition algorithms based on RGB, including traditional algorithms and deep learning algorithms. Because of the influence of background lighting, RGB-videobased action recognition is low accuracy, but it has rich color appearance information. Then this paper analyzed and summarized action recognition algorithms based on RGB-D, which was divided into depth sequence, bone and multi-feature fusion. RGB-D video has multiple modes and can provide more information for action recognition, which performs better than RGB video but also brings new challenges. Finally, this paper prospected the common data sets and the possible future development direction. [ABSTRACT FROM AUTHOR]

With the rapid growth of the number of Internet of Things devices, the frequency of illegal attacks by botnets composed of hijacked IoT devices has increased greatly, and the security of IoT devices has become a serious issue. In order to detect abnormal traffic initiated by IoT devices, this paper proposed an individual learner selection algorithm ( IISA) based on ensemble learning. IISA was a selection method based on correlation coefficient measurement. It used correlation coefficient to integrate individual learners with large differences in similarity and made judgements by voting, which could reduce individual learners while improving the accuracy and efficiency of detection. The experimental results show that compared with the eight semi-supervised machine learning detection algorithms, the recall rate can be reduced by 9 . 12%, the accuracy can be increased by 4. 69%, and the detection efficiency can be increased by 70. 72% . [ABSTRACT FROM AUTHOR]

The development of society has brought countless data, with the unbalancedness becoming a significant feature of many data sets. So it has come to be a research hotspot for machine learning on how to make those unbalanced data sets obtain better effects of classification. Based on this, this paper conducted a comprehensive research on the current unbalanced data set classification method, and made an overall interpretation and conclusion from such three aspects as the unbalanced data sampling method, the method of machine learning-based improved algorithm and the combination method. It also analyzed and took int o account many factors, including the problems solved by each method, algorithm mentality, application scenarios, as well as the advantages and disadvantages of each, and delivered a summary on potential problems of the classification methods and a prospect on the future research directions [ABSTRACT FROM AUTHOR]

With the rising of SDN and achieving great success of machine learning methods in classification, prediction and control tasks, to find new TE technology, manage or route the traffic in the network adaptively and dynamical, ensuring QoS and improving quality of user experience (QoE) have become the focus of network research. Firstly, this paper introduced the basic structure of SDN and the research content and objectives of SDN traffic engineering. Secondly, it analyzed the application of supervised learning methods and reinforcement learning in SDN traffic engineering, and analyzed the advantages and disadvantages of existing algorithms. Finally, it summarized the future research directions and challenges. [ABSTRACT FROM AUTHOR]

In order to enhance the network representation learning quality with the edge signed semantic information, focusing on the weakness of existing fusion methods in dealing with complex edge signed semantic information, this paper proposed a network representation learning algorithm incorporating with edge signed semantic information, and introduced the edge signed semantic information containing positive and negative relations into the network representation learning process. Firstly, this paper designed a relationship prediction model based on the three-layer perceptron to depict different types of context link relations between nodes. Then it introduced the random walk strategy to implement context link sampling to adapt the large-scale network scenarios. Experiments on three data sets show that this algorithm can effectively model different types of context links between nodes and mine the complex semantic information contained in them. Compared with the current optimal SIDE method, the performance of the proposed algorithm is improved by 0. 31 %, 1. 3 % and 1. 85 % . [ABSTRACT FROM AUTHOR]

The data sources of existing link prediction algorithms are mainly based on neighbors, paths, and random walk methods. The link prediction algorithms use mainly node similarity assumptions or maximum likelihood estimates. The link prediction based on neural network is still absent. Some research achievements based on neural network show that the Deep Walk algorithm based on neural network is an efficient network representation learning algorithm, which can more effectively learn the network structure features in the network. It has been proven that DeepWalk is equivalent to factorize the target matrix. Therefore, this paper proposed a link prediction algorithm (LPMF) based on matrix factorization of Deep Walk. This algorithm based on matrix factorization used the Deep Walk algorithm to get the network representation vectors. And then, it calculated the similarities between node pairs of nod es by the cosine similarity method. Based on that, the similarity matrix of the target network was constructed. Finally, this paper used the similarity matrix to conduct the link prediction experiments on three real -world citation networks. The experimental results show that the new method is superior to the existing 20 kinds of link prediction algorithms, which fully shows that LPMF can effectively find the structural correlation between nodes in the network, and performs a more excellent performance in the actual tasks of link prediction. [ABSTRACT FROM AUTHOR]

Aiming at the order dependency problem of the K2 algorithm, this paper proposed a heuristic algorithm (H-vnK2) to learn the node order effectively from a given data set. Specifically, based on the v-structure knowledge learned by the PC algorithm, it corrected the order of some parent-child nodes in the form of node blocks quickly and accurately, and then obtained the optimal order of some nodes. Based on the neighbor set knowledge learned by the PC algorithm, with the distance threshold heuristic strategy, it further modified the order of the parent-child nodes from the global optimal point of view, and then obtained the best order of all nodes. Experiments show that the proposed algorithm is significantly better than the comparison algorithm on the Asia and Alarm standard data set. Among them, compared with the best-performing method based on causal effects, the proposed algorithm improves the accuracy rate by 7% on average, and the increment can reach up to 33 .3 %. It can learn a more accurate network structure. [ABSTRACT FROM AUTHOR]

When the deep reinforcement learning algorithm is trained in a complex dynamic environment, it is difficult for the agent to obtain useful information due to the partial observability of the environment, which leads to typical problems such as failure to learn good strategies and slow algorithm convergence speed. This paper proposed an improved DDPG algorithm based on LSTM and asymmetric actor-critic network. This method introduced the LSTM structure into actor-critic network to learn the hidden states in partially observable Markov through memory reasoning. At the same time, when the actor network only used RGB images as partially observable inputs, the critic network used the complete state of the simulation environment to train, which formed an asymmetric network and speeded up the training convergence. The simulation experiment of manipulator grasping in ROS shows that the proposed algorithm has higher success rate and faster convergence speed compared with DDPG, PPO and LSTM-DDPG. [ABSTRACT FROM AUTHOR]

Aiming at the problems of complex background, variety of change types, missing detection and rough boundary recognition in high-resolution remote sensing image of the same region, this paper proposed a high-resolution remote sensing image building change detection algorithm based on Siam-UNet++network. The algorithm used UNet++as the backbone extraction network. In the encoder phase, it applied the Siam-diff structure to extract the change features of the two sequential images, and employed the attention mechanism after the up sampling and lateral jump path connection in the decoding stage to highlight the building change features and inhibit the network learning from other types of features. Meanwhile, it used the MSOF strategy to weight and fuse feature information of different semantic levels, which improved the accuracy of building change detection. Finally, it adopted a sliding window method to predict large-scale remote sensing images, reducing the hole pattern generated by the change result map during the splicing process. The experimental results demonstrate that proposed algorithm shows better performance than other models. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the recommendation model cannot mine the diversity of user interest and capture the order information between the sequence of user behavior, and the interaction occurs at the element level rather than between the feature vectors, etc., based on multiple attention mechanism and location information, this paper proposed the x DMAL FM. Firstly, it extracted the feature depth from different subspaces by using the multi-head attention mechanism, and then location information could capture the sequential relationship between user behavior sequences. Finally, it used three public datasets to conduct comparative experiments and the AUC index to evaluate the results. The experimental results show that the proposed algorithm has better recommendation performance than the xDeepFM model and show the effectiveness and feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The identification of encryption algorithms is the primary task of cryptanalysis. The current identification schemes cover the identification of block ciphers, the identification of stream ciphers, and the identification of hybrid algorithms of sym-metric ciphers and public key ciphers. With the popularization of Chinese national cryptographic algorithms, their security has also attracted much attention. For the national secret algorithm, this paper proposed the SM4 block cipher system identification based on random characteristics, and identified the national secret SM4 algorithm with the main international standard block cipher algorithm. It used the randomness test method to perform feature extraction on the ciphertext to obtain feature vectors. These feature vectors formed the feature space. Finally, it used machine learning algorithms to train and test the feature space. Experimental results show that the recognition rate of SM4 and other block cipher algorithms are over 90%. This work provides new possibilities for cryptanalysis and at the same time increases the diversity of password identification schemes. [ABSTRACT FROM AUTHOR]

To settle the exact consensus problem of a class of multi-agent systems subjected to actuator saturations on a finite time interval [0,7], this paper utilized the adaptive iterative learning control scheme to design the time-varying gains with fully saturated difference adaptive updating laws. By constructing a proper composite energy function, it was proved strictly that the vectors of consensus error tended to zero as the iteration number approaches to infinity, and obtained the adaptive learning consensus algorithm without dependence on eigenvalues of the communication topology matrix. Finally, the result of a given simulation example illustrates the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

In order to improve the information processing ability of the model in complex scenes, this paper proposed a dynamic selection mechanism based on attention, which selectively allocated weights according to the current information, effectively fused the feature outputs of deformation convolution and ordinary convolution, and adaptively balanced deformable convolution and standard convolution, so as to improve its representation ability. In addition, the learning ability of the model was further enhanced by means of iteration without additional parameters. It used seven different kinds of noises from Noise-X92 in TIMIT corpus, and carried out experiments in various SNR environments. The results show that the proposed algorithm outperforms other recent deep learning algorithms in terms of intelligibility and speech quality, regardless of SNR and whether noise appears in the training data set. [ABSTRACT FROM AUTHOR]

Aiming at the ill-posedness of the single-image low-resolution to super-resolution mapping, the low utilization of feature space information by the super-resolution reconstruction network, and the excessive amount of network parameters, this paper proposed a dual learning algorithm based on progressive up-sampling, which was applied to super-resolution reconstruction of a single image. The algorithm adopted deep separable convolution to significantly reduced the amount of network parameters, and constructed the progressive up-sampling network based on sub-pixel convolution to efficiently use the spatial information of the feature image. Meanwhile, it used dual learning to construct a closed-loop feedback connection network to obtain the optimal mapping function to estimate the down-sampling kernel to reconstruct low-resolution images . Analyzing on benchmark datasets such as Set5, Set14, BSDS100, Urban100, and Manga109 compared with the state-of-the-arts models, this algorithm can reduce the number of parameters by 9%, and can effectively alleviate the image edge distortion and artifact phenomenon under the large factors, the average PSRN/ SSIM are 26. 90/0. 751, 24. 84/0. 645, 24. 74/0. 619, 22. 30/0. 560,24. 38/0. 706 . [ABSTRACT FROM AUTHOR]