Search

Temperature and humidity prediction plays an important role in various fields of the national economy. In view of the poor predictions of temperature and humidity and the failure to achieve multimodal prediction, this paper uses the Gaussian mixture process (GPM) model to predict the multimodal temperature and humidity. GPM model was developed from the Gaussian process (GP) model. It was proposed by Tresp in 2000. The main idea of GPM is to fit the samples in various input regions with different GP models in order to fit different patterns in these regions. However, the existing GPM models are rather complicated and thus the learning algorithms involve various approximation schemes, which can lead to much computation or rough prediction. So, in order to improve the model learning efficiency, a variable-hidden posterior hard-cut iterative training algorithm is proposed for the GPM model. This algorithm improves the EM (expectation maximization) learning with a new approximation strategy, which achieves the optimal grouping of samples through iterative learning and using the maximum a posteriori estimation. Prior to the experiment, the autocorrelation function and partial autocorrelation function were used to verify the nonlinear and non-stationary property of humidity and temperature sequences. Largest Lyapunov, saturation correlation dimension and recursive graph were used to verify the chaotic characteristic of humidity and temperature sequences. Finally, the GPM proposed in this paper is compared with the kernel regression (K-R), the minimax probability machine regression (MPMR), the linear regression (L-R), and GP models. K-R is a kind of prediction model based on kernel function. By adjusting the optimal window width, K-R gradually gets the corresponding prediction result. K-R has been the basis of predictive model because it can predict the linear and non-linear time series simultaneously. MPMR does not need to make specific assumptions about the model distribution. It only needs to know the mean and covariance matrix of the data distribution. This model improves the neural network easy to fall into the minimum and over-fitting. L-R is a very traditional model, using the quantitative relationship between variables to obtain a linear expression and then predict the test sample. The results show that not only GPM can perform multimodal prediction, but also the accuracy of the model is significantly better than other traditional models. In the humidity sequence prediction, the minimum of RMSE can reach 0.0620 and the maximum of R2 can reach 0.9362. In the temperature sequence prediction, the minimum of RMSE can reach 0.0426 and the maximum of R2 can reach 0.9666. In the prediction time consumed, GPM is a little more than the other 4 traditional models. The main reason is that GPM requires iterative learning to achieve the optimal grouping of samples. Finally, humidity prediction needs 113.4175 s and temperature prediction needs 90.0049 s. The research in this paper not only can promote atmospheric temperature and humidity forecasting, but also has some reference value for indoor and solid surface temperature and humidity forecasting because GPM is the prediction model without environment factors input. [ABSTRACT FROM AUTHOR]

Aiming at the problems that existing human skeleton action recognition methods couldn't explore sufficient human body information and extract sufficient temporal feature, this paper proposed a model based on posture transformation module and posture fusion module (PTF-SGN), which realized the utilization of the key spatio-temporal information in skeleton diagram. Firstly, by preprocessing the skeleton diagram, the model mined the displacement information of limbs and joints, and extracted the features. Then it used the posture transformation module to obtain the posture adjustment factors from the skeleton image data in an unsupervised learning manner, and adaptively adjusted the body posture to enhance the robustness of the model in different environments. Secondly, it proposed a posture fusion module based on the time attention mechanism, which learned the short-term features and the long-term features, and fused the time characteristics of long and short moments to strengthen the characterization ability of time characteristics. Finally, it extracted the global spatio-temporal feature of the skeleton feature to input into the classification network to obtain the action recognition result. The experimental results on the two 3D skeleton datasets of NTU60 RGB+D and NTU120 RGB+D and the two 2D skeleton datasets of Penn-Action and HARPET show that PTF-SGN model can effectively recognize actions of skeleton time series data. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the existing automatic image description generation models based on visual attention and text attention cannot describe the image details and the whole image at the same time, this paper proposed a model for image captioning which included three sub-modules, ie, an image encoder, an evolutionary neural network, and an adaptive merging decoder. The proposed model could effectively integrate both the visual information and text information, and automatically calculated the proportion of these two information at each time step. The experimental results on two public data sets, Flickr30k and COCO2014, show that the proposed EDLMIC model is superior to other baseline models in four indicators such as METEOR, ROUGE-L, CIDEr and SPICE, and has good performance in a variety of different life scenes. [ABSTRACT FROM AUTHOR]

Existing deep learning based single image super-resolution (SISR) models usually improve the fitting ability of the model by increasing the number of network layers, but fail to fully extract and reuse features, leading low quality of reconstructed images. To solve this problem, this paper proposed an image super-resolution model based on feature fusion and attention mechanism. This model used residual in residual (RIR) structure in feature extraction module. The feature extraction module of the network consisted of several residual groups. Each residual group consisted of several residual blocks. This module implemented local feature fusion in each residual group and global feature fusion between each group. In addition, this model introduced coordinate attention module into each residual block and spatial attention module into each residual group. It verifies that the model is able to fully extract features and reuse features. The final experimental results show that the model is superior to the existing models in objective evaluation indexes and subjective visual effect. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low accuracy of TLBO and easy falling into local optima, the paper proposed a new TLBO algorithm integrating cognitive psychology theory. Incorporating the theory of foot in the door effect in the teaching stage, it could set the periodic learning goals for students with learning difficulties, so as to improve the overall level of students. Adding teacher guidance mechanism in the learning stage was good for increasing the speed of algorithm convergence. There was a self-adjustment stage after learning stage. According to psychological locus of control theory, it divided students into internal control type and external control type. Different types of students adopt different attribution methods for their own performance and took corresponding measures. Using the classic benchmark function to test CPTLBO, the results show that the improved algorithm has advantages in optimization accuracy and convergence speed. Constructing the CPTLBO-ELM tap water supply prediction model and using CPTLBO algorithm to optimize the input weights and hidden layer threshold parameters of the extreme learning machine, so as to improve the prediction accuracy and generalization ability of the model. The simulation results show that it is more accurate for the model which is optimized by CPTLBO algorithm. The simulation results show that it is more accurate for the model which is optimized by CPTLBO algorithm. The simulation results show that it is more accurate for the model which is optimized by CPTLBO algorithm. [ABSTRACT FROM AUTHOR]

This paper proposed an optimization model of deep-knowledge tracking（KTSA-BiGRU） based on self-attention mechanism and bidirectional GRU neural networks owing to the existing deep-knowledge tracking models with weak capture of complex relationships between input exercises and inability to effectively handle long-sequence input data. Firstly, it mapped the learner’s historical learning interaction sequence data to the real value vector sequence. Then, it trained the bidirectional GRU neural network as input to model the learner’s learning process, and finally used, the self-attention mechanism to calculate the probability of the learner correctly answering the next question based on the hidden vectors of the bidirectional GRU neural network output and the attention weight. The performance analysis on the three public datasets can improve the prediction accuracy of deep knowledge tracking. [ABSTRACT FROM AUTHOR]

Traffic condition prediction is an important part of intelligent transportation system, and traffic flow is the most direct embodiment of traffic condition. Therefore, traffic flow prediction has important application value. On the one hand, the roads in the city have spatial topological properties, on the other hand, the traffic flow changes dynamically with time. Therefore, the key to the prediction of traffic flow is to model the time and space dependence in the data. In view of this characteristic, this paper used neural network model and attention mechanism to explore the temporal and spatial dependence relationship in traffic flow data, and proposed a traffic flow prediction model based on time map attention. In terms of spatial dependence, it used a learning algorithm combining graph convolution network and attention to assign different weights to nodes with different influence degrees, and added node adaptive learning to effectively extract spatial features. In terms of time dependence, it used the temporal convolution network to extract the temporal features, and expanded the sensing domain by expanding convolution, so as to capture the features of longer time series data. A spatial-temporal network layer was composed of graph attention network and time convolution network, which was finally connected to the output layer to output the prediction results. The model used the combination of graph convolution neural network and attention mechanism to extract spatial features, fully considered the spatial relationship between roads, and used temporal convolution network to capture temporal features. After experiments on two real datasets, it is found that it has good performance in the next 15, 30 and 60 minutes, and the results are better than the existing baselines. [ABSTRACT FROM AUTHOR]

Aiming at the problem of intra-modality feature representation and inter modality feature fusion in multimodal sentiment analysis, this paper proposed a multi-level hybrid fusion multi-modal sentiment analysis model based on attention mechanism and multi-task learning. Firstly, the model used convolution neural network and bi-directional gated unit to extract the single-modality internal feature. Secondly, it used the cross-modality attention mechanism to realize the pairwise feature fusion between modalities. Thirdly, it used the self-attention mechanism to select the modality Finally, combining with multi-task learning, the model obtained both sentiment and emotion classification results. The experimental results on CMU-MOSEI dataset show that this method can improve the accuracy and F 1-score of sentiment and emotion classification. [ABSTRACT FROM AUTHOR]

In many machine learning applications, the data may be symmetric positive definite (SPD) matrices which are not living in Euclidean space. This paper presented a new probabilistic Riemannian space quantization method based on log-Euclidean metric learning. The proposed method extended the Euclidean probabilistic learning vector quantization (PLVQ) method to deal with SPD matrices by treating them as points on the Riemannian manifold of SPD matrices equipped with log-Euclidean metric, through utilizing a parameterized distance function from log-Euclidean metric learning. On the BCI IV 2 a dataset, the proposed method outperformed Euclidean PLVQ by 20% in terms of recognition accuracy. The proposed method also performs better than the first winner of BCI competition IV on this data set. It obtains comparable classification accuracy to PLVQ using affine invariant Riemannian metric, but requires much less computing time, ieonly needs 1% of the training time, while 10% of the test time. The proposed method also obtains superior performance on the BCI III IIIa and ETH-80 datasets, showing its effectiveness and efficiency. [ABSTRACT FROM AUTHOR]

Iterative learning control problem is studied for a class of discrete nonlinear partial difference systems where the trial lengths vary randomly in this paper. The considered systems are composed of parabolic partial difference equations. Firstly, for the trial lengths vary randomly in systems, a stochastic variable satisfying Bernoulli distribution is introduced. Then, according to the properties of partial difference systems and P-type distributed update schemes, iterative learning controller is designed. Through rigorous theoretical analysis, the convergence sufficient condition of output error under λ norm and contractive mapping principle is established to ensure the convergence of tracking error in the sense of norm. The convergence speed of the algorithm is faster than the classical iterative learning algorithm. Finally, the effectiveness of the algorithm is verified by the numerical simulation. [ABSTRACT FROM AUTHOR]

Real-time bidding( RTE) is a widely used advertising mode in online display advertising. In response to the problem that the best bidding strategy is difficult to obtain due to the high dynamics of the RTE auction environment, this paper proposed a method of optimizing bid strategy based on reinforcement learning (RL), which used the policy optimization with penalized point probability distance (POP3D) algorithm to learn the best bidding strategy. In the POP3D-based bidding framework, the advertising bidding process was modeled as an episodic Markov decision process. Each episode contained a fixed number of time steps, and the bid for each ad display was determined by its estimated click-through rate and bidding factors were jointly determined. At each time step, the bidding agent would adjust the bidding factors according to the auction situation at the previous time step, so that the bidding strategy could adapt to the highly dynamic auction environment. The goal of the bidding agent was to learn the best bidding factor adjustment strategy. The experimental results on the iPin You data set demonstrate that compared with the DRLB algorithm, the proposed bidding algorithm increases the number of clicks by 0. 2 % when the budget ratio is 1/16 and 1/32, as well as increased the win rate by 1. 8%, 1. 0% and 1. 7 % when the budget ratio is were 1/8, 1/16 and 1/32. In addition, the proposed method also has advantages in terms of stability. It shows the superiority of this method. [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]

Joint extraction of entities and relations from unstructured text is an important task in information extraction. The existing methods have achieved considerable performance, but are still subject to some inherent limitations, such as error propagation, redundancy of relation prediction, inability to solve the problem of relations overlap, etc. For this reason, this paper proposed a joint entity relationship extraction model BSGB( BiLSTM + SDA-GAT + BiGCN) based on graph neural network. BSGB was a two-stage predicting process. The first stage of this model extended the semantic dependency analysis to the semantic dependency graph, and proposed a graph attention network to integrate the semantic dependency graph(SDA-GAT). By stacking BiLSTM and SDA-GAT, it extracted sentence sequence and local dependent features, and performed entity span detection and preliminary relationship prediction. In the second stage, it constructed the relation-weighted GCN, which further modeled the interaction between entities and relations, and completed the final extraction of entity-relationship triples. The experimental results on the NYT dataset show that the F1 value of this model reaches 67 .1 %, which is 5. 2% higher than the baseline model in this dataset, and the prediction of the overlap relation is also significantly improved. [ABSTRACT FROM AUTHOR]

Traditional aspect-based sentiment analysis methods lack the research on the interaction between aspect object and its context, which leads to the low accuracy of sentiment analysis. In order to effectively extract richer text features, this paper pro-posed an aspect-based sentiment analysis model (IIMAN) to improve the effect of sentiment polarity judgment, which used multi-head attention mechanism to learn the interaction between aspect object and its context. Firstly, the model used the BERT pre-training model to complete the word vectorization of the input sentences. Then, it used the intra multi-head attention network and the inter multi-head attention network in the attention network to learn the interaction between aspect object and its context, as well as the internal interactions within the context. Finally, it realized the sentiment polarity classification through the pointwise convolution transfer layer, the aspect object attention layer and the output softmax layer. Through the experiments on three public aspect-level sentiment analysis datasets: Twitter, laptop and restaurant, the results show that, compared with other baseline models, IIMAN model achieves better effect in accuracy and F1 value, improves the results of the sentiment polarity classification. [ABSTRACT FROM AUTHOR]

Occlusion in a real environment is one of the main obstacles to accurately analyze and recognize facial expressions. In recent years, researchers have used deep learning technology to solve the problem of high misrecognition rate of facial ex-pressions under occlusion conditions. It mainly summarized the deep learning algorithm of occlusion facial expression recognition and occlusion-related issues. Firstly, this paper summarized the development status of facial expression recognition under partial occlusion conditions, expression representation, and the data set used to study occlusion expression. Secondly, it re-viewed the occlusion expression identify the latest developments in deep learning methods and analyzed the impact of occlusion on expressions. Finally, it summarized the main technical challenges, research difficulties and possible coping strategies. The purpose is to provide a more useful reference and benchmark for future research on occlusion expression recognition. [ABSTRACT FROM AUTHOR]

Because convolutional neural networks( CNN) mostly focus on global feature learning and ignore local feature information containing more details, it is difficult to improve the accuracy of indoor scene recognition. To solve this problem, this paper proposed an indoor scene recognition method based on improved global-local attention network ( GLANet). Firstly, it used GIAN et to capture the global and local features of the scene image to increase the detail information of the image features. Then, it introduced a non-local attention module into the local network to further preserve the detail features of the image through the convolution of attention diagram and feature graph. Finally, it used various features of different stages of the network for classification. Through training and verification on the MIT lndoor67 and the SUN397 dataset, the recognition accuracy of the proposed method was increased by l. 98% and 3. 07% respectively compared with the LGN method. Experimental results show that the algorithm can effectively capture global semantic information and fine spatial details, and significantly improves the recognition accuracy. [ABSTRACT FROM AUTHOR]

With the popularity and development of deep learning, the existence of adversarial samples is a serious threat to the security of the deep learning model. For the attack problem of adversarial samples in the physical world, this paper proposed a physical adversarial sample detection method based on attention mechanism. The method combined attention mechanism and feature compression to detect pertinently of local visual adversarial samples, excluded effects of non-major regions, and reduced calculation effort. It effectively combined multiple feature compression methods to deal with the main areas of the sample, which destroyed the structure of the antagonistic block and made them unaggressive. Perform defense tests on different adversarial attacked on the MNIST and CIFAR-10 data sets and compared with other countermeasures. The experimental results show that the defense accuracy of the method can reach more than 95%. This method is higher versatility and stronger stability than other local adversarial sample defense methods, and can effectively defense the attack of local visual adversarial samples. [ABSTRACT FROM AUTHOR]

The rectangle layout optimization problem with balance constraints is derived from the layout design of satellite module equipment. It belongs to combinatorial optimization problem. Deep reinforcement learning uses reward mechanism to realize high-performance decision optimization through data training. This paper proposed a new deep reinforcement learning algorithm DAR and its extension IDAR. The DAR algorithm output the optimized location sequence with a pointer network, and then used the positioning mechanism to give the layout results. The training of pointer network was realized by deep reinforcement learning. The time complexity of the DAR algorithm was O ( n ³ ). The IDAR algorithm was an iteration version of DAR, which had better results but with a time complexity of 0 ( n 4 ). The test results show that DAR algorithm has good learning ability, and the model obtained by small layout problems can be effectively applied to large-scale problems. The results on two typical large-scaled instances show that the proposed algorithms have achieved or approached to the current best results, so that they have advantages both in time and solution quality. [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]

Implicit aspect extraction is important for improving the accuracy of fine-grained sentiment analysis. However, existing implicit aspect extraction techniques do not have strong generalization ability when dealing with large-scale data. To address the problem, this paper proposed an implicit aspect extraction model combining dependency syntactic parsing and interactive attention mechanism. First, the model generated the initial representation of the text by the pre-trained language model BERT. Then, it passed the initial representation to the self-attention layer guided by the dependency syntactic parsing. Due to the interactive attention mechanism, the model further extracted the results of the above two processes. Finally it used a classifier to determine the implicit aspect of the sentence. Compared with baseline BERT and other deep neural network models, the proposed model has achieved higher F1 and AUC on the enhanced SemEval implicit aspect dataset, which proves the effectiveness of the model. [ABSTRACT FROM AUTHOR]

Objectives: With the rise of location service applications and the popularization of mobile smart terminals, the demand for high ‑ precision navigation and positioning is extending from isolated areas to seamless whole areas, from professional groups to mass users. However, real‑time, continuous, and complete pedestrian navigation still faces many challenges, such as occlusion of global navigation satellite system (GNSS) signals, frequent updates of Wi‑Fi/ bluetooth low energy (BLE)/geomagnetic fingerprint data‑ bases, and smoothly switching in the transitional area of indoor and outdoor. In addition, the positioning sensors of popular mobile smart terminals are limited by cost and power consumption, and the observation data is generally noisy and poor in stability. Methods: Therefore, this paper proposes a pedestrian indoor and outdoor seamless positioning technology based on cloud‑end collaboration of smartphone, which breaks through the crowd sourced collection and rapid update of the beacon fingerprint database, the precise positioning of the smart phone multi‑sensor information fusion, and the indoor and outdoor seamless switching. We have developed a smartphone positioning application for pedestrians. The collaborative precision positioning enhancement information is provided by the location service platform and the multi‑source observations data (GNSS, miniature inertial measurement unit (MIMU), Wi ‑ Fi, BLE, magnetometer, barometer) are obtained by the smartphone. Results: The feild test results show that the outdoor positioning accuracy of ordinary users is better than 1.5 m, and indoor accuracy is about 1 ‒ 3 m. Conclusions: It supports the demand of mass‑market users for seamless and precise positioning indoors and outdoors. [ABSTRACT FROM AUTHOR]

Ocean mesoscale eddy is an important ocean mesoscale phenomenon that plays an important role in ocean circulation, mat erial and energy transport, and has an important impact on the safety of ship navigation and hydroacoustic communication. Efficient and accurate detection and identification of ocean mesoscale eddies are of great research value for both physical ocean cognition and ocean exploitation. Traditional eddy detection and identification methods rely on a single threshold designed by experts experiences. With the rise of deep learning, the current machine learning methods show certain advantages in the accuracy and automation of eddy detection and identification. This paper summarizes and comparatively analyzes the existing machine learning-based detection and identification methods to provide a systematic knowledge and reference basis for the development of ocean mesoscale eddy detection and identification research. [ABSTRACT FROM AUTHOR]

Cloud segmentation is a key task in applications of Landsat8 remote sensing images. At present, most existing deep learning based approaches usually adopt the U-type coder-encoder network structure. Although this structure can make use of spatial location information from the coding end effectively, the whole network has too many parameters and cause high computation cost. Meanwhile, the coding end only adopts simple convolution and subsampling operation, which makes it impossible to obtain high-quality contextual semantic feature information effectively. In view of the above situation, this paper proposed a new lightweight U-Net model for cloud segmentation. The whole model adopted a new U-shaped codec structure that jumped and connected the information between the shallow layer and the middle layer at the coding end, and also embedded novel optimization blocks consist of grouping convolution and attention mechanism in coding end. It also built context-semantic fusion connection to link corresponding layers in coding and decoding end. Experimental results on the common benchmark dataset 38-Cloud illustrates, compared with other mainstream cloud segmentation networks, the proposed new U-Net can achieve better segmentation precision with less model parameters. [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]

It is critical to obtain sufficient and effective EEG features in mental workload evaluation. This paper presented a multiclass classification network which combined multi-branch LSTM with attention mechanism. Firstly, this network segmented an EEG signal into a number of temporal slices, in each of which multi-branch LSTM extracted temporal feature from the EEG slices. Then attention mechanism optimized the features. Finally, softmax function evaluated mental workload level. The experimental results show that the performance of the proposed network is better than that of the existing network in both binary class and multiclass classification task. [ABSTRACT FROM AUTHOR]

According to the problem that the model in the generative text summarization doesn’t fully understand the semantics of the text and the generated summary lacks key information, this paper proposed a Key-BERT-Pen model that integrated keywords in Chinese abstract generation. The KBPM first used the TextRank method to extract the keywords in the text, and then obtained a more accurate contextual representation through the BERT pre-training model using the extracted keywords and the original text. Finally, it input the obtained word vector into a pointer model with a dual attention mechanism, and the pointer model took vocabularies from the vocabulary or original text to generate the final abstract. Experimental results show that the KBPM can generate text summaries with better readability and higher ROUGE scores. The comparative analysis also verifies that the KBPM effectively solves the problem of the lack of key information in the generated abstract. [ABSTRACT FROM AUTHOR]

Despite their prior knowledge，a large amount of unsupervised industrial data cannot be effectively exploited in real-world applications regions. In this paper，we propose a semi-supervised learning algorithm based on similarity measurement. This method combines specific prior knowledge and unsupervised learning to calculate the similarity between unlabeled data and a small amount of labeled data to augment the minority samples. By improving the classification effect of the model on the minority class，we can mitigate sample imbalance in training phrases and marking difficulty. Empirically，a good minority recognition effect has been achieved in a series of power-sensor detection classification tasks. Compared with state-of-the-art methods， including the traditional and semi-supervised methods，the recall rate and the F1 value comprehensively exceed the traditional ones. [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]

For the weakness of traditional malware detection methods, this paper proposed a method in the detection of Unknown malicious applications based data mining and machine learning algorithm. While a single feature of machine learning algorithms could not play the role of ability of data processing, detection effect. This paper proposed a method to combine speech recognition model with random forest algorithm, which considered multi-class APK features in unknown malware detection. First, it combined a variety of ways to extract 3 classes which could reflect the behaviors of Android malware including sensitive permissions, DVM function calls and OpCodes characteristics. Then, according to the characteristics of each type of N-gram model,each one could evaluate behaviors of malware independently. Finally, 3 classes of feature model would join into a random forest learning algorithm, so as to detect the Android apps. It implemented an automated system based on this method to detect 811 non-malicious and 826 malicious apps with higher accuracy. Considering comprehensive evaluation of various indicators, the experimental results show that the malware detection system has a better performance than other related works on effective and accuracy. [ABSTRACT FROM AUTHOR]

In order to systematically analyze Internet traffic features, this paper researched the taxonomy of traffic features based on the objects used for building traffic features,and overviewed the related traffic features in each category. It further analyzed the stability of traff ic features, the impact of packet sampling, network environment and obfuscating on traffic features. And then it compared the different kinds of traffic features from classification accuracy .stability, timeliness and granularity. Finally, this paper concluded future works about traffic features. [ABSTRACT FROM AUTHOR]

[Purpose/Significance] This paper proposes a fine-grained automatic extraction method for document structure based on PDF layout features, in order to realize fine-grained organization of literature resources and meet the increasingly growing needs of users for accurate information services. [Method/Process] The method takes full advantage of machine learning in information classification, which can automatically analyze, identify and extract the chapter title of unstructured PDF documents based on layout features. And according to the coordinate positioning of chapter titles, the body content is automatically matched to the subordinated position of the title with paragraph as the minimum granularity, and the fine-grained extraction and identification of the full text of the document is finally realized. [Results/Conclusions] The test result shows that the average accuracy of automatic extraction can reach 80%. The method of fine-grained extraction of unstructured PDF documents proposed has practical significance and application prospect, and the data processing system designed based on the underlying method has been put into practical application, which will greatly liberate us from the mechanical drudgery of chapter structure extraction tasks. [ABSTRACT FROM AUTHOR]

Since it is difficult to online measure the underflow concentration of the thickener in the thickening-dehydration process, a broad learning system(BLS) based soft sensor modeling method is proposed in this paper. The method has high precision and strong generalization capability. First, several pressure sensors are installed inside the thickener, and the historical dataset under normal operating conditions is established. Then, the soft sensor model is trained by employing the BLS method to online predict the underflow concentration of the thickener. Finally, the efficiency of the proposed method is verified by simulation experiments. Compared with other traditional machine learning methods, the BLS method has higher prediction accuracy. [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]

In order to maintain security and reliability of operating system, this paper developed a universal framework for net-work intrusion detection system based on artificial intelligence( AI) model. This framework was capability of detecting all sorts of network traffic, catching out possible malicious connection or attack from Internet and identifying it. Firstly, this system pre-processed the network traffic data by sampling, one-hot encoding, feature selection and normalization for basic feature extrac-tion. Secondly,it utilized feature distribution in network connection instance to build a scoring mechanism for information ex-traction once again. Thirdly, it applied the different types of ML/DL models for different forms of network traffic to do final classification for extracted features. In experiments, this system applied three benchmark datasets, KDDCup99, UNSW-NB15 and CICIDS2017. The result of experiments shows it possesses exceedingly good performance and has better accuracy and F1 score than related works under these datasets. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a common chronic neurological disease. Because of its unclear etiology, the early diagnosis of is quite difficult. This article proposed a novel model based on improved optimized kernel extreme learning machine (KELM) for the early diagnosis of PD. This paper used chaos theory and Gauss mutation factor to improve salp swarm algorithm (SSA), and designed the intelligent diagnosis model named as ISSA-KELM based on evolution mechanism. The improved SSA (ISSA) used to conduct adjust KELM important parameters and feature subsets selection synchronously. Moreover, the model was processing on multi-thread scheduling on open MP platform, which could achieve the maximum classification accuracy of model. and further improved the computational efficiency. The experimental results show that the classification accuracy of the proposed model is higher than those of the existing methods, the computational efficiency is algo greatly enhanced, it demonstrated the good comprehensive performance. Therefore, it proves that the proposed model has goods prospects for application and it will be helpful for clinicians to make more accurate decision in diagnosis of PD. [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 the field of machine learning, graph neural network plays an increasingly important role in works such as social recommendation compared with traditional neural network, but most of the current work use static graph. Aiming at the problem hat the existing static graph neural network method is difficult to consider the dynamic characteristics of social users, this paper proposed a method of social network node classification based on a heterogeneous dynamic graph model by introducing a dynamic graph model. On the basis of dynamic graph modeling, this method realized efficient node classification of dynamic social network through node feature updating mechanism based on point-edge interaction and time series aggregation method based on recurrent neural network. The experimental results on multiple real datasets show that the proposed method has a good effect in dynamic social network data node classification, which has a significant improvement compared with the reference method of the I static graph and dynamic graph. [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]

Objective: Develop a machine learning model, and to evaluate its accuracy in the diagnosis of primary bone tumor around the knee joint. Methods: In this paper, the deep learning method of deep convolutional neural network（DCNN） was applied to the imagomics analysis of knee X-ray images, its clinical value in assisting the diagnosis of primary bone tumor around the knee joint were explored. Results: The deep learning model showed excellent diagnostic accuracy in differentiating normal images from tumor images.The overall accuracy of 5 rounds of testing using the DCNN model was（99.8±0.4） %, while the positive predictive value and negative predictive value were（100.0±0.0） % and（99.6±0.8） % respectively. The area under the curve（AUC） of each dataset was 0.99, 1.00,1.00, 1.0 and 1.0 respectively, average AUC was（0.998±0.004). A further 10 rounds of testing using the DCNN model showed an overall accuracy of（71.2±1.6） % in differentiating benign from malignant bone tumors, and a strong positive predictive value（91.9±8.5） %was achieved in differentiating benign and malignant bone tumor, the AUC of each dataset was 0.63, 0.63, 0.58, 0.69, 0.55, 0.63, 0.54,0.57, 0.73, 0.63 respectively, average AUC was（0.62±0.06). Conclusion: This is the first study on the application of artificial intelligence technology in the imaging analysis of X-ray images for bone tumor diagnosis, Artificial intelligence imaging models can help doctors to automatically and quickly screen bone tumors and identify benign or malignant tumors, with a high positive predictive value. MoreReset [ABSTRACT FROM AUTHOR]

This paper proposed a Chinese-Korean neural machine translation model called QE-Transformer based on reinforcement learning and machine translation quality estimation to solve the problems about exposure bias and diversity in current machine translation. First of all, this model introduced an evaluation mechanism into the sentence level to guide the model when the prediction couldn't converge completely on the ground truth. And furthermore, it used reinforcement learning as a guiding strategy to optimize the sequence of objectives at the sentence level. Finally, by using monolingual data and different granularity data preprocessing in the training process, it alleviated the problem of data sparsity. Experimental results show that the QETransformer can improve effectively the Chinese-Korean machine translation performance compared with Transformer, the BLEU value increases by 5. 39 and the QE score decreases by 5. 16 in the direction of the Chinese to Korean machine translation, the BLEU value increases by 2. 73 and the QE score decreases by 2. 82 in the direction of the Korean to Chinese machine translation. [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]

BKT can track the state of the learners ' knowledge, as well as predict their mastery level and future performance in the intelligent teaching system. Because BKT easily ignores the phenomenon of memory forgetting, and does not consider the impact of learning behavior on performance results, the model prediction results deviate from the actual situation. So this paper proposed a new Bayesian knowledge tracking model that integrated learner behavior and forgetting factors. Firstly, the method used the decision tree algorithm to process learning behavior data and introduced behavior nodes. Then, the model initialized the forgetting parameters and assigned them, and updated the algorithm of the learner ' s knowledge mastery level. Finally, the experiment compared the prediction accuracy of related models through the public data set provided by ASSISTMENTS. Experimental results show that the BF-BKT model can achieve better prediction accuracy. [ABSTRACT FROM AUTHOR]

The existing reinforcement learning algorithms have low sample utilization, which leads to a decrease in the ability of the agent to find the optimal strategy. To solve this problem, this paper proposed a sample evaluation method based on incremental similarity. It designed a novel measure method of state and a sample value evaluation function. It calculated the similarity between the new state and the baseline state, and calculated the novelty based on the similarity of the state,and then updated the baseline state incrementally until the end of the training. When calculating the sample value, it took the novelty degree of the state into account, and then calculated the sample reward value separately according to whether the sample reward value was greater than zero. Finally, it conducted the sampling according to the sample value, ranking selection and random selection. This method achieved higher reward values in the control problems of Playing Atari 2600. It shows that this method alleviates the problem of low sample utilization and reduces the computational burden by incremental similarity calculation. [ABSTRACT FROM AUTHOR]

In order to solve the problem of complex parameter configuration in radar emitter signal recognition, this paper found a tree-based machine learning pipeline optimization method, based on the study of machine learning parameter optimization. This method used GP to generate the tree-based machine learning pipeline, and got the best machine learning pipeline with the best parameters through the evolution of the pipeline and parameters. The pipeline could include any combination of feature processing and modeling to achieve the learning and recognition of the original data set. This paper compared recognition effect of this method and the SVM method in the radar emitter signal feature sets of two different dimensions. In contrast, this method does not require cumbersome parameter configuration, and the highest accuracy is improved by more than 6%. It is proved that the tree-based machine learning pipeline obtained by this method has obvious advantages. [ABSTRACT FROM AUTHOR]

In global friction measurement, thin oil film technique can well represent the distribution of surface friction. Irradiated with ultraviolet light of a specific wavelength, the oil film with different thickness of the fluorescent color molecules will emit different brightness. Using this principle, the thickness of the oil film can be calculated by detecting the gray value of the excited fluorescent oil film.In this paper, BP neural network and extreme learning machine（ELM）neural network are used to build models to complete the prediction of the relationship between the fluorescence oil film thickness and gray level, and Hopfield neural network is used to complete the identification of the corresponding parameters. The experimental results show that the prediction errors of ELM neural network model, BP neural network model and interpolation model are 5.150%, 5.485% and 5.935%, respectively. Through Hopfield neural network identification, the parameter error rates of the influence factors such as light source power, optical distance and exposure coefficient are controlled at about 1%, which meets the requirements of practical engineering application. Compared with the traditional interpolation method, the higher precision can be obtained by using the neural network, which provides a feasible method for the study of the gray and thickness of the fluorescent oil film. [ABSTRACT FROM AUTHOR]

With the increase of transmission rate, transmission length and structure complexity of high-speed channel, channel modeling technology becomes more complex and difficult. This paper proposes a novel method by combining the popular machine learning method with high-speed channel. A large number of analog data are collected, and deep neural network (DNN) and recurrent neural network (RNN) methods are used to model the channeL Once the model is trained successfully, the eye diagram of the output signal can be predicted by the simulation model, and the signal integrity can be evaluated and analyzed quickly and accurately. In addition, in the high-speed channel, the serious interference and attenuation of the signal limits the transmission distance and transmission rate, which brings difficulties to the test and information collection. In order to recover the ideal signal, the high-speed serial link usually contains complex equalization blocks. The least mean square (LMS) algorithm is adopted to effectively eliminate the interference, reduce the bit error rate and improve the transmission rate. [ABSTRACT FROM AUTHOR]

Landslide disasters threaten the safety of human life and properties. It is important to accurately assess the risk of regional landslides. At present, common machine learning methods cannot extract deeper data features and obtain higher precision landslide hazard assessment maps. Therefore, this paper proposes a deep one-dimensional convolutional neural network method for landslide risk assessment, in order to extract deeper features and obtain higher precision evaluation results by based on its powerful learning ability. Taking Lushan, Sichuan, China as an example, 346 historical landslide pionts of Lushan in 2016 were selected for model training and verification. In order to verify the validity and precision of the model, the support vector machine, the information value method and the proposed convolutional neural network model were compared in the experiments. The overall accuracies of the convolutional neural network and the support vector machine are 0. 9015 and 0. 842. The AUC values of the one-dimensional convolutional neural network, support vector machine, and information value model are 0. 888, 0. 876, and 0. 818, respectively, The results show that the proposed convolutional neural network model has a higher accuracy and is superior to the support vector machine and the information value method in data fitting ability and evaluation effect, and can be effectively applied to the regional landslide risk evaluation. [ABSTRACT FROM AUTHOR]

A review often involves multiple categories and their emotional tendencies, but the traditional attention mechanism is difficult to distinguish the correspondence between aspect words and emotion words, which affects the analysis of emotional polarity when there are multiple aspect categories in a review. In order to solve the above problems, this paper proposed an context aware learning for aspect category sentiment classification model ( MA-DSA) . The model captured more diverse and effective semantic features in the sentence by reconstructing the aspect vector, and integrated it into the context vector. Then, it used the context vector to further capture the internal emotional characteristics of the sentence through the DiSA module to determine the aspect and emotion words. Then the sentiment classification was performed on the specified aspect category. The experimental results on SemEval' s three datasets show that the three index values of MA-DSA on the Restaurant-2014 dataset are better than the baseline model, which proves the effectiveness of this model. [ABSTRACT FROM AUTHOR]

Aspect words consist of multiple words, averaging the word vectors of all words may lead to semantic errors or confusion, and different context words have different influence on the judgment of emotional polarity for aspect words. This paper proposed a text sentiment analysis model that integrated the left and right bilateral attention mechanisms. First, the model designed an internal attention mechanism to process aspect words, and designed a bilateral interactive attention mechanism based on aspect words and context words, and finally cascaded the three parts of the processing result of bilateral interactive attention and the aspect word processing value for classification. Experiments on the two datasets from SemEval2014 task 4 show that the proposed model achieves 81. 33% and 74. 22% accuracy respectively, and has achieved better results than models that combine machine learning or attention mechanisms. [ABSTRACT FROM AUTHOR]

Aiming at the system instability caused by the uncertainty of the extreme learning machine( ELM) hidden nodes and the problem of overburdening large data calculations, this paper proposed an optimization algorithm based on the adaptive and momentum method (AdaMom) . This algorithm constructed a continuously differentiable objective function, and calculated the adaptive learning rate during the gradient descent process,obtained the exponentially weighted average of the product of the adaptive learning rate and the gradient. At last it obtained the hidden layer output weight matrix corresponding to the minimum value of the loss function through iteration. The experimental results show that in the training of the same benchmark data set, the AdaMom- ELM algorithm has very good generalization performance and robustness, which improves the computational efficiency. [ABSTRACT FROM AUTHOR]