Search

As an important part of the bridge structure system, the underwater pile-pier structure usually occurs various defects on its surfaces due to its complex hydrological environment. The existing conventional defect detection approaches exist two aspects of problems: (1) insufficient definition and color distortion of the underwater images, and (2) low efficiency and error-prone. To solve these problems, this paper proposed the target defect detection model by integrating the image-fusion enhancement algorithm and the deep learning algorithm. Firstly, by analyzing the reasons for the degradation of the underwater images, the ACE (automatic color equalization) and CLAHE (contrast limited adaptive histogram equalization) algorithms are selected to enhance the image, respectively. Secondly, the two enhanced images are fused based on the point sharpness weight, and then the fusion results are further sharpened by the USM (unsharp mask) algorithm, thus obtaining the final fused images. Thirdly, 3,200 fused images are taken as the training set, by adopting the YOLOv3 algorithm to train the detection model, and then the training model is validated and tested by the other each 400 fused images, thus building up the target automatic detection model of underwater pile-pier surface defects. Finally, a series of comparison and discussion were conducted to validate the effectiveness of image-fusion and the robustness and effectiveness of the target detection model. The results found that the target detection model has excellent robustness against noise and effectiveness in the surface defect detection. This indicates that the image-fusion approach proposed in this paper can effectively enhance the image features, and the target detection model is feasible, robust, and effective in the automatic detection of surface defects on underwater pile-pier structures. [ABSTRACT FROM AUTHOR]

Based on ML algorithm, this paper puts forward a method that can search instructional resources through keyword indexing technology, and then cluster and recombine the related results and present them centrally. In this paper, the semantic processing of user query based on the subject index of educational resources is adopted to make up for the deficiency of query semantics, solve the problem of mismatch between query words and document words, and improve the recall and precision of resource retrieval. It is proposed to select the category feature items manually and establish the category feature model. In the environment of small sample set, the weight of category feature items is trained by ML method. The research shows that the user rating of this system is ideal, reaching 93.21% at the highest. In addition, the stability of the system can still reach 89.31% under the condition of relatively large usage, and its performance is excellent. This system can effectively solve the problem of scattered distribution of English instructional resources and make the presentation of knowledge more in line with the needs of users, thereby further improving the utilization rate of English instructional resources and users' satisfaction. [ABSTRACT FROM AUTHOR]

Facial expression recognition based on residual networks is important for technologies related to space human-robot interaction and collaboration but suffers from low accuracy and slow computation in complex network structures. To solve these problems, this paper proposes a multiscale feature fusion attention lightweight wide residual network. The network first uses an improved random erasing method to preprocess facial expression images, which improves the generalizability of the model. The use of a modified depthwise separable convolution in the feature extraction network reduces the computational effort associated with the network parameters and enhances the characterization of the extracted features through a channel shuffle operation. Then, an improved bottleneck block is used to reduce the dimensionality of the upper layer network feature map to further reduce the number of network parameters while enhancing the network feature extraction capability. Finally, an optimized multiscale feature lightweight attention mechanism module is embedded to further improve the feature extractability of the network for human facial expressions. The experimental results show that the accuracy of the model is 73.21%, 98.72%, and 95.21% on FER2013, CK+ and JAFFE, respectively, with a covariance of 10.14 M. Compared with other networks, the model proposed in this paper has faster computing speed and better accuracy at the same time. [ABSTRACT FROM AUTHOR]

The research on artistic psychological intervention to judge emotional fluctuations by extracting emotional features from interactive vocal signals has become a research topic with great potential for development. Based on the interactive vocal music instruction theory of emotion recognition, this paper studies the design of artistic psychological intervention system. This paper uses the vocal music emotion recognition algorithm to first train the interactive recognition network, in which the input is a row vector composed of different vocal music characteristics, and finally recognizes the vocal music of different emotional categories, which solves the problem of low data coupling in the artistic psychological intervention system. Among them, the vocal music emotion recognition experiment based on the interactive recognition network is mainly carried out from six aspects: the number of iterative training, the vocal music instruction rate, the number of emotion recognition signal nodes in the artistic psychological intervention layer, the number of sample sets, different feature combinations, and the number of emotion types. The input data of the system is a training class learning video, and actions and expressions need to be recognized before scoring. In the simulation process, before the completion of the sample indicators is unbalanced, the R language statistical analysis tool is used to balance the existing unbalanced data based on the artificial data synthesis method, and 279 uniformly classified samples are obtained. The 279 ∗ 7 dataset was used for statistical identification of the participants. The experimental results show that under the guidance of four different interactive vocal music, the vocal emotion recognition rate is between 65.85%-91.00%, which promotes the intervention of music therapy on artistic psychological intervention. [ABSTRACT FROM AUTHOR]

In the machine learning model, intelligent recommendation system can select valuable information from a lot of data to help users find the products or services they need, which has been more and more widely used in recent years. However, there are still many problems in machine learning recommender systems, such as data sparsity, natural noise, and cold start, which leads to the fact that machine learning recommender systems cannot obtain accurate user preferences. When a project is rated, the quality of the recommendation is greatly affected. In order to solve the problem that the existing recommendation algorithms have poor recommendation results in sparse data sets, this paper proposes a machine learning method for recommendation rating prediction based on user interest concept lattice. Firstly, the nearest neighbors are divided into direct nearest neighbors and indirect nearest neighbors by user interest concept lattice. Then, different methods are used to calculate the similarity between the direct "nearest neighbor" and the target user, and the similarity between the indirect "nearest neighbor" and the target user. Finally, the invisible item score of the target user is calculated by the similarity value. Experiments are carried out on real data sets, and the experimental results show that the CFCNN-CL algorithm and RRP-UI CL algorithm proposed in this paper have high recommendation accuracy and still have good performance in the case of sparse data. [ABSTRACT FROM AUTHOR]

Engineers strive to realize the goal of control in the best possible way based on a given quality criterion when developing control system. The well-known optimal control problem requires finding a solution as a function of time. Such a function cannot be directly used to control a real object because its application corresponds to an open-loop control system and engineers usually complete it with a feedback stabilization system. Hence, there is an obvious need to reformulate the optimal control problem so that its solution can be directly applied to real objects. The paper presents a new extended statement of the optimal control problem. An additional requirement for the control function is introduced to give the system describing the control object properties that will ensure the stability of solutions. The desired control function must provide for the optimal trajectory given the properties of the attractor in the neighbourhood. The solution to the extended optimal control problem can be directly used to control a real object. The paper presents a computational machine learning approach to solving the extended problem of optimal control based on the application of a synthesized optimal control technique. Examples of the practical solution to the stated problem are given to illustrate the efficiency of the approach, where the solution to the conventional optimal control problem is compared with the proposed extended one in the presence of perturbations in models and initial conditions. [ABSTRACT FROM AUTHOR]

In recent years, many deep learning algorithms based on seismic signals have been proposed to solve the moving target recognition problem in unattended ground sensor systems. Despite the excellent performance of these deep networks, most of them can only be deployed on cloud-based devices and cannot be deployed on low-power hardware devices due to the large network size. Second, since seismic signals are affected by the terrain, employing only seismic signals as reconnaissance means for unattended ground sensors cannot achieve multiterrain-type adaptability. In response, this paper proposes an MFC-TinyNet method facing a multiterrain. The method adds depthwise separable convolutional layers to the network, which effectively reduces the size of the network while keeping the target recognition accuracy constant, and solves the problem that the model is difficult to deploy on low-power hardware. It also uses the Mel-frequency spectrum feature extraction method to fuse sound and seismic signals to improve the accuracy of the model's moving target recognition on a multiterrain. Experiments demonstrate that the method can combine the two advantages of the small network model and multiterrain applicability. [ABSTRACT FROM AUTHOR]

An intrusion detection system (IDS) is a network security device that performs real-time monitoring of network transmissions and sends out alarms or takes active response measures when suspicious transmissions are found. In this regard, many researches have combined traditional machine learning models with other optimization algorithms to improve intrusion detection performance. However, although the existing intrusion detection model can effectively improve the performance of the model, there are still problems such as unsatisfactory detection accuracy and data preprocessing operations that may lead to a decrease in accuracy. To solve this problem, in this paper, we have proposed a novel intrusion detection system model based on logarithmic autoencoder (LogAE) and eXtreme Gradient Boosting (XGBoost). First, we build LogAE to learn the hidden features of the input data to reconstruct new data similar to the training samples, with the purpose of highlighting important features. It is worth mentioning that LogAE is not necessary to normalize the training data. This is because we add a logarithmic layer to learn this mapping. Then, XGBoost is used as a classifier to identify the data set that combines the original data set with the generated data set. In the experiment, our proposed model is evaluated on the UNSW-NB15 data set and CICIDS2017 data set. Additionally, we use accuracy, recall, precision, F1-score, and runtime as evaluation metrics. For detection performance, the detection accuracy of our proposed model is 95.11% for UNSW-NB15 and 99.92% for CICIDS2017, which is better than most state-of-the-art intrusion detection methods. Meantime, the runtime of our proposed model is the lowest for UNSW-NB15. [ABSTRACT FROM AUTHOR]

In the order picking process of the warehouse center, considering the rapid increase in the volume of orders arriving at the picking center at the time of the promotional festival, a hybrid operation mode with multiple picking tables is used to meet the picking requirements of the huge number of real-time orders. Therefore, in this paper, a hybrid picking mode is proposed, taking into account both the idle degree of picking stations and their order item centers of gravity, and a new reinforcement learning algorithm embedding mechanism (PRL) with placeholder control is designed to solve the problem of a huge number of real-time item orders arriving at the picking center system on promotional holidays and in inconsistent quantities, and numerical simulations are performed for this algorithm. The experimental results show that the PRL algorithm in hybrid picking mode can handle a huge number of orders simultaneously and improve picking efficiency effectively. [ABSTRACT FROM AUTHOR]

In order to solve the prewarning problem of South-to-North Water Transfer Project safety, an intelligent cooperative prewarning method based on machine learning was proposed under the framework of intelligent information processing. Driven by the monitoring data of the South-to-North Water Transfer Project, the single sensor in typical scenes was studied, and the security threshold was predicted along the vertical axis of time, firstly. With the support of the data correlation calculation, the sensors in the typical scene were intelligently grouped, and the study objectives were changed into sensor grouping, secondly. Then, the nonlinear regression model between the single sensor and the multisensors was built on the time cross section, and the model was used to dynamically calculate the safety threshold of the current sensor for the second time. Finally, in the framework of intelligent information processing, a double verification mechanism was proposed to support the construction of the intelligent prewarning method for the safety of South-to-North Water Transfer Project. The paper collected the monitoring data from November 2015 to September 2016 in the typical scenarios. The experimental results showed that the methods constructed in the paper can be able to identify the abnormal causes of data sudden jump effectively and give the different level prewarning. The method provides a strong theoretical support for further manual investigation work. [ABSTRACT FROM AUTHOR]

Nowadays, deep learning has made great achievements in the field of rotating machinery fault diagnosis. But in the practical engineering scenarios, when facing a large number of unlabeled data and variable operating conditions, only using a deep learning algorithm may reduce the performance. In order to solve the above problem, this paper uses a method of combining transfer learning with deep learning. First, the deep shrinkage residual network is constructed by adding soft thresholds to extract the characteristics of bearing vibration data under noise redundancy. Then, the joint maximum mean deviation (JMMD) criterion and conditional domain adversarial (CDA) learning domain adapting network are used to align the source and target domains. At the same time, adding transferable semantic augmentation (TSA) regular items improves alignment performance between classes. Finally, the proposed model is verified by three experiments: variable load, variable speed, and variable noise, which overcomes the shortcomings of traditional deep learning and shallow transfer learning algorithms. [ABSTRACT FROM AUTHOR]

With fast learning speed and high accuracy, extreme learning machine (ELM) has achieved great success in pattern recognition and machine learning. Unfortunately, it will fail in the circumstance where plenty of labeled samples for training model are insufficient. The labeled samples are difficult to obtain due to their high cost. In this paper, we solve this problem with transfer learning and propose joint transfer extreme learning machine (JTELM). First, it applies cross-domain mean approximation (CDMA) to minimize the discrepancy between domains, thus obtaining one ELM model. Second, subspace alignment (sa) and weight approximation are together introduced into the output layer to enhance the capability of knowledge transfer and learn another ELM model. Third, the prediction of test samples is dominated by the two learned ELM models. Finally, a series of experiments are carried out to investigate the performance of JTELM, and the results show that it achieves efficiently the task of transfer learning and performs better than the traditional ELM and other transfer or nontransfer learning methods. [ABSTRACT FROM AUTHOR]

When making regression predictions, the traditional random forest (RF) algorithm can only make predictions within the training set, which can easily lead to overfitting when modeling data have some specific noise. To solve the problem of over‐fitting, an improved RF method is proposed in this paper for wind pressure prediction. With the aim to verify the prediction performance of the improved RF algorithm, this paper predicts the wind pressure coefficients of a high‐rise building model without wind pressure measurement points. The results show that the improved RF can achieve good results in predicting the mean and fluctuating wind pressure coefficients of high‐rise buildings, and its relative error for each measurement point is basically controlled at 5%, which is acceptable in engineering terms. Further applications show that this improved RF can be used for wind pressure distribution prediction in other large‐span building type wind tunnel tests. [ABSTRACT FROM AUTHOR]

For decades, machine learning techniques have been used to process Amharic texts. The potential application of deep learning on Amharic document classification has not been exploited due to a lack of language resources. In this paper, we present a deep learning model for Amharic news document classification. The proposed model uses fastText to generate text vectors to represent semantic meaning of texts and solve the problem of traditional methods. The text vectors matrix is then fed into the embedding layer of a convolutional neural network (CNN), which automatically extracts features. We conduct experiments on a data set with six news categories, and our approach produced a classification accuracy of 93.79%. We compared our method to well-known machine learning algorithms such as support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), XGBoost (XGB), and random forest (RF) and achieved good results. [ABSTRACT FROM AUTHOR]

With the rapid development of economy and Internet technology, e-government has been reflected in the reform of government information management and is closely related to the security of e-government networks. Existing technologies for evaluating network security can provide good evaluation results when dealing with deterministic data, but they are not sufficient to evaluate the uncertainty of information. In order to solve the problem of the construction and realization of the network training environment, a network security assessment method based on gray relational analysis and D-S theory proof is proposed. First, the scaling method is used to determine the weights of different levels of indicators, because different levels of indicators have different effects on the network state. Secondly, taking into account the differences in the degree of participation of different indicators at different levels, the participation function of each level indicator at the level is determined and a weighted amplitude coefficient to reduce the overall uncertainty is established. The network security situation is sudden and volatile. Therefore, the network security prediction method should have a good ability to deal with nonlinear problems. In this case, a network security state prediction method based on the GM performance model is proposed. The GM performance model has excellent nonlinear debugging functions. It has low requirements on the number of samples and good practicability. The experimental results show that the dynamic decision server push framework based on the XGBoost algorithm proposed in this paper has better performance than the single push method for push server, can use network resources appropriately, and improves the network environment security rate by at least 50%. [ABSTRACT FROM AUTHOR]

Summary: This paper presents a distributed secondary control strategy based on finite‐time consensus protocol for islanded microgrids to ensure the stability of frequency and voltage. Simple droop control cannot achieve high‐precision adjustment due to its inherent shortcomings. Although traditional secondary control can solve this problem, the required conditions are harsh and the system has poor robustness. Based on finite‐time consensus protocol, the proposed distributed secondary control is completely distributed, and agents of network layer only communicate through peer‐to‐peer sparse networks without a central node, so the frequency and voltage remain stable and reach the nominal value within the set time that then improves the system reliability and robustness. Moreover, the improved extreme learning machine, where the empirical risk and structural risk are involved, is used to predict the missing part to deal with the problem of packet loss and communication interruptions. The effectiveness of the intended methods is verified by the simulation of an islanded microgrid. [ABSTRACT FROM AUTHOR]

Summary: The inconsistency in the mass production of lithium‐ion battery (LIB) packs stem from the inconsistency in the capacity, voltage and internal resistance of single batteries that compose packs. The inconsistency issue of these battery packs can greatly reduce the output performance of a large power pack. This paper proposed the machine learning approach based on self‐organization mapping (SOM) neural networks for establishing the consistency of LIBs. This method comprehensively compares and analyzes the real‐LIB parameters (internal resistance, capacity and voltage) data obtained during charging and discharging to form the clusters of similar performing LIBs. Experimental result validated the clustering analysis and it indicates that the performance of clustered battery pack typically precedes than that of original. The capacity of clustered battery pack increased 1.9% compared with brand‐new pack. The temperature distribution of the battery pack assembled after screening is consistent. The peak temperature is 4°‐5° lower than the ordinary battery, and the temperature fluctuation is reduced by 2.6°. In addition, the application of cluster analysis is expanded and some key research directions are pointed out. [ABSTRACT FROM AUTHOR]

Multimodal tasks based on attention mechanism and language face numerous problems. Based on multimodal hierarchical attention mechanism and genetic neural network, this paper studies the application of image segmentation algorithm in data completion and 3D scene reconstruction. The algorithm refers to the process of concentrating attention that humans subjectively pay attention to and calculates the difference between each pixel in the genetic neural network test image in the color space and the average value of the target image, which solves the problem of static feature maps and dynamic feature maps of image sequences. In addition, in view of the problem that the number of attention enhancement feature extraction modules is too large and the parameters are too large, the recursive mechanism is used as the feature extraction branch, and new model parameters are not added when the network depth is increased. The simulation results show that the accuracy of the improved image saliency detection algorithm based on the attention mechanism reaches 89.7%, and the difference between the average value of the single-point pixel and the target image is reduced to 0.132, which further promotes the practicability and reliability of the image segmentation model. [ABSTRACT FROM AUTHOR]

On-board system fault knowledge base (KB) is a collection of fault causes, maintenance methods, and interrelationships among on-board modules and components of high-speed railways, which plays a crucial role in knowledge-driven dynamic operation and maintenance (O&M) decisions for on-board systems. To solve the problem of multi-source heterogeneity of on-board system O&M data, an entity matching (EM) approach using the BERT model and semi-supervised incremental learning is proposed. The heterogeneous knowledge fusion task is formulated as a pairwise binary classification task of entities in the knowledge units. Firstly, the deep semantic features of fault knowledge units are obtained by BERT. We also investigate the effectiveness of knowledge unit features extracted from different hidden layers of the model on heterogeneous knowledge fusion during model fine-tuning. To further improve the utilization of unlabeled test samples, a semi-supervised incremental learning strategy based on pseudo labels is devised. By selecting entity pairs with high confidence to generate pseudo labels, the label sample set is expanded to realize incremental learning and enhance the knowledge fusion ability of the model. Furthermore, the model's robustness is strengthened by embedding-based adversarial training in the fine-tuning stage. Based on the on-board system's O&M data, this paper constructs the fault KB and compares the model with other solutions developed for related matching tasks, which verifies the effectiveness of this model in the heterogeneous knowledge fusion task of the on-board system. [ABSTRACT FROM AUTHOR]

Support vector machine (SVM) is one of the most efficient machine learning tools, and it is fast, simple to use, reliable, and provides accurate classification results. Despite its generalization capability, SVM is usually posed as a quadratic programming (QP) problem to find a separation hyperplane in nonlinear cases. This needs huge quantities of computational time and memory for large datasets, even for moderately sized ones. SVM could be used for classification tasks whose number of samples is limited but does not scale well to large datasets. The idea is to solve this problem by a smoothing technique to get a new smaller dataset representing the original one. This paper proposes a fast and less time and memory-consuming algorithm to solve the problems represented by a nonlinear support vector machine tool, based on generating a Gaussian pyramid to minimize the size of the dataset. The reduce operation between dataset points and the Gaussian pyramid is reformulated to get a smoothed copy of the original dataset. The new dataset points after passing the Gaussian pyramid will be closed to each other, and this will minimize the degree of nonlinearity in the dataset, and it will be 1/4 of the size of the original large dataset. The experiments demonstrate that our proposed techniques can reduce the classical SVM tool complexity, more accurately, and are applicable in real time. [ABSTRACT FROM AUTHOR]

This paper presents an improved teaching-learning-based optimization (TLBO) algorithm for solving optimization problems, called RLTLBO. First, a new learning mode considering the effect of the teacher is presented. Second, the Q-Learning method in reinforcement learning (RL) is introduced to build a switching mechanism between two different learning modes in the learner phase. Finally, ROBL is adopted after both the teacher and learner phases to improve the local optima avoidance ability of RLTLBO. These two strategies effectively enhance the convergence speed and accuracy of the proposed algorithm. RLTLBO is analyzed on 23 standard benchmark functions and eight CEC2017 test functions to verify the optimization performance. The results reveal that proposed algorithm provides effective and efficient performance in solving benchmark test functions. Moreover, RLTLBO is also applied to solve eight industrial engineering design problems. Compared with the basic TLBO and seven state-of-the-art algorithms, the results illustrate that RLTLBO has superior performance and promising prospects for dealing with real-world optimization problems. The source codes of the RLTLBO are publicly available at https://github.com/WangShuang92/RLTLBO. [ABSTRACT FROM AUTHOR]

Based on the clinical states of the patient, dynamic treatment regime technology can provide various therapeutic methods, which is helpful for medical treatment policymaking. Reinforcement learning is an important approach for developing this technology. In order to implement the reinforcement learning algorithm efficiently, the computation of health data is usually outsourced to the untrustworthy cloud server. However, it may leak, falsify, or delete private health data. Encryption is a common method for solving this problem. But the cloud server is difficult to calculate encrypted health data. In this paper, based on Cheon et al.'s approximate homomorphic encryption scheme, we first propose secure computation protocols for implementing comparison, maximum, exponentiation, and division. Next, we design a homomorphic reciprocal of square root protocol firstly, which only needs one approximate computation. Based on the proposed secure computation protocols, we design a secure asynchronous advantage actor-critic reinforcement learning algorithm for the first time. Then, it is used to implement a secure treatment decision-making algorithm. Simulation results show that our secure computation protocols and algorithms are feasible. [ABSTRACT FROM AUTHOR]

There are two primary defects in the existing UAV avoidance systems: the system is memoryless; airborne radars are used to detect long-distance barriers, which are unreliable and expensive. The paper adopts the deep learning algorithm and ADS-B communication system based on a satellite base station to solve the above problems. It divides the avoidance problem into two parts: short-distance obstacle avoidance and long-distance route planning. On the one hand, the system establishes the knowledge base storing the previous avoidance experience and the matching mechanism, realizing the correspondence between input and experience through a deep learning algorithm. They can dramatically improve the reaction speed and safety of UAVs. On the other hand, the system realizes the interconnection between UAV and the satellite base station through the ADS-B communication system to replace the radars, putting the task of route planning on the satellite platform. Therefore, the satellite can achieve large-scale and all-weather detection to improve the overall safety of UAVs depending on its high and long-range characteristics. The paper also illustrates the design elements of the RF baseband integrated ADS-B transceiver and the simulation performance of the short-distance avoidance system in the end, whose results show that the system can be applied to dense obstacle environments and significantly improve the security of UAVs in a complex domain. [ABSTRACT FROM AUTHOR]

The CNN-based crowd counting method uses image pyramid and dense connection to fuse features to solve the problems of multiscale and information loss. However, these operations lead to information redundancy and confusion between crowd and background information. In this paper, we propose a multi-scale guided attention network (MGANet) to solve the above problems. Specifically, the multilayer features of the network are fused by a top-down approach to obtain multiscale information and context information. The attention mechanism is used to guide the acquired features of each layer in space and channel so that the network pays more attention to the crowd in the image, ignores irrelevant information, and further integrates to obtain the final high-quality density map. Besides, we propose a counting loss function combining SSIM Loss, MAE Loss, and MSE Loss to achieve effective network convergence. We experiment on four major datasets and obtain good results. The effectiveness of the network modules is proved by the corresponding ablation experiments. The source code is available at https://github.com/lpfworld/MGANet. [ABSTRACT FROM AUTHOR]

Cultural and creative design is a new design mode based on the Internet platform, which gathers the design wisdom of the public and provides online solutions for design tasks. Evaluation indicators are used to score cultural and creative design schemes that require manual construction of an evaluation matrix, which makes the evaluation efficiency very low and increases the product design cycle. Therefore, based on the deep belief network of cultural creation, the method of constructing the evaluation model of the scheme is designed in this paper. According to the characteristics of the deep belief network, the k-medoids clustering method is adopted, and the clustering key value k is set. Meanwhile, the clustering result is calculated, and k central point elements are obtained. Moreover, project the central point elements back to the cultural and creative design plan to obtain the characteristic plan, and use manual evaluation to calculate the comprehensive score. Besides, the feature scheme data and the data simulation formula are used to construct the training set of the deep belief network, which are used to train the evaluation model of the deep belief network to solve the problem of the length of time that requires a large amount of manual evaluation to construct the output of the training set. In addition, according to the number of evaluation indicators, the number of nodes in the input layer of the deep belief network is determined to define the initialization method of network weights and biases, formulating experimental procedures to determine the optimal network structure. In the simulation experiment, through the test analysis of the comparison model, the function synchronization rate in this paper is 4.2% better than that of the comparison method. After multiple iterations, the test effect is 7 times higher than that of the comparison method, realizing the optimal evaluation of the design schemes that have not been manually evaluated in the same design scheme set. [ABSTRACT FROM AUTHOR]

The traditional English teaching system has certain problems in the acquisition of teaching resources and the innovation of teaching models. In order to improve the effect of subsequent English online teaching, this paper improves the machine learning algorithm to make it a core algorithm that can be used by artificial intelligence systems. Moreover, this paper combines the WBIETS system to expand the system function, analyzes the needs of the English network teaching system, and constructs the system function modules and logical structure. The data layer, logic layer, and presentation layer in the system constructed in this paper are independent of each other and can be effectively expanded when subsequent requirements change. In addition, this paper solves the problem of acquiring English teaching resources through the WBIETS system. To evaluate the performance of the English network teaching system, this paper performs comprehensive mathematical and experimental analysis. The experimental results show that the system constructed in this paper basically meets the actual teaching requirements. [ABSTRACT FROM AUTHOR]

The reinforcement learning algorithms based on policy gradient may fall into local optimal due to gradient disappearance during the update process, which in turn affects the exploration ability of the reinforcement learning agent. In order to solve the above problem, in this paper, the cross-entropy method (CEM) in evolution policy, maximum mean difference (MMD), and twin delayed deep deterministic policy gradient algorithm (TD3) are combined to propose a diversity evolutionary policy deep reinforcement learning (DEPRL) algorithm. By using the maximum mean discrepancy as a measure of the distance between different policies, some of the policies in the population maximize the distance between them and the previous generation of policies while maximizing the cumulative return during the gradient update. Furthermore, combining the cumulative returns and the distance between policies as the fitness of the population encourages more diversity in the offspring policies, which in turn can reduce the risk of falling into local optimal due to the disappearance of the gradient. The results in the MuJoCo test environment show that DEPRL has achieved excellent performance on continuous control tasks; especially in the Ant-v2 environment, the return of DEPRL ultimately achieved a nearly 20% improvement compared to TD3. [ABSTRACT FROM AUTHOR]

Since the breakthrough of deep learning in object classification in 2012, extraordinary achievements have been made in the field of target detection, but the high time and space complexity of the target detection network based on deep learning has hindered the technology from application in actual product. To solve this problem, first of all, this paper uses the MobileNet classification network to optimize the Faster R-CNN target detection network. The experimental results on the rare earth element detection data set show that the MobileNet classification network is not suitable for optimizing the Faster R-CNN network. After that, this paper proposes a classification network that combines VGG16 and MobileNet, and uses the fusion network to optimize the Faster R-CNN target detection network. The experimental results on the rare earth element detection data set show that the Faster R-CNN target detection network optimized by the fusion classification network has the advantages of using VGG16 and MobileNet's Faster R-CNN target detection network to detect rare earth elements. The innovation of this article is that the results on 5 time series data sets show that CDA-WR has better predictive performance than other ELM variant models. The effect of determining trace cerium elements in rocks and minerals is increased by more than 50%, based on deep learning. The algorithm studies the methods of target detection and recognition and integrates it into the intelligent robot used in this subject, giving the robot the ability to accurately detect the target object in real time. [ABSTRACT FROM AUTHOR]

When traditional machine learning methods are applied to network intrusion detection, they need to rely on expert knowledge to extract feature vectors in advance, which incurs lack of flexibility and versatility. Recently, deep learning methods have shown superior performance compared with traditional machine learning methods. Deep learning methods can learn the raw data directly, but they are faced with expensive computing cost. To solve this problem, a preprocessing method based on multipacket input unit and compression is proposed, which takes m data packets as the input unit to maximize the retention of information and greatly compresses the raw traffic to shorten the data learning and training time. In our proposed method, the CNN network structure is optimized and the weights of some convolution layers are assigned directly by using the Gabor filter. Experimental results on the benchmark data set show that compared with the existing models, the proposed method improves the detection accuracy by 2.49% and reduces the training time by 62.1%. In addition, the experiments show that the proposed compression method has obvious advantages in detection accuracy and computational efficiency compared with the existing compression methods. [ABSTRACT FROM AUTHOR]

At present, traditional facial expression recognition methods of convolutional neural networks are based on local ideas for feature expression, which results in the model's low efficiency in capturing the dependence between long-range pixels, leading to poor performance for facial expression recognition. In order to solve the above problems, this paper combines a self-attention mechanism with a residual network and proposes a new facial expression recognition model based on the global operation idea. This paper first introduces the self-attention mechanism on the basis of the residual network and finds the relative importance of a location by calculating the weighted average of all location pixels, then introduces channel attention to learn different features on the channel domain, and generates channel attention to focus on the interactive features in different channels so that the robustness can be improved; finally, it merges the self-attention mechanism and the channel attention mechanism to increase the model's ability to extract globally important features. The accuracy of this paper on the CK+ and FER2013 datasets is 97.89% and 74.15%, respectively, which fully confirmed the effectiveness and superiority of the model in extracting global features. [ABSTRACT FROM AUTHOR]

k nearest neighbor (k NN) is a simple and widely used classifier; it can achieve comparable performance with more complex classifiers including decision tree and artificial neural network. Therefore, k NN has been listed as one of the top 10 algorithms in machine learning and data mining. On the other hand, in many classification problems, such as medical diagnosis and intrusion detection, the collected training sets are usually class imbalanced. In class imbalanced data, although positive examples are heavily outnumbered by negative ones, positive examples usually carry more meaningful information and are more important than negative examples. Similar to other classical classifiers, k NN is also proposed under the assumption that the training set has approximately balanced class distribution, leading to its unsatisfactory performance on imbalanced data. In addition, under a class imbalanced scenario, the global resampling strategies that are suitable to decision tree and artificial neural network often do not work well for k NN, which is a local information-oriented classifier. To solve this problem, researchers have conducted many works for k NN over the past decade. This paper presents a comprehensive survey of these works according to their different perspectives and analyzes and compares their characteristics. At last, several future directions are pointed out. [ABSTRACT FROM AUTHOR]

Commodity prices play a unique role as a lever to regulate the economy. Price forecasting is an important part of macrodecision-making and micromanagement. Because there are many factors affecting the price of goods, price prediction has become a difficulty in research. According to the characteristics that price data are also affected by other factors except for time series, a multifactor LSTM price prediction method is proposed based on the long-term and short-term memory network (LSTM) deep learning algorithm. This method not only makes use of the memory of LSTM to historical data but also introduces the influence of external factors on price through the full connection layer, which provides a new idea for solving the problem of price prediction. Compared with BP neural network, the experimental results show that this method has higher accuracy and better stability. Analyze the commodity description and commodity price characteristics, find out the commodities similar to the target commodity, complete the commodity price data by using the historical price data of similar commodities, and establish the training set to verify the validity of the proposed method. [ABSTRACT FROM AUTHOR]

Federated learning (FL) has emerged for solving the problem of data fragmentation and isolation in machine learning based on privacy protection. Each client node uploads the trained model parameter information to the central server based on the local training data, and the central server aggregates the parameter information to achieve the purpose of common training. In the real environment, the distribution of data among nodes is often inconsistent. By analyzing the influence of independent identically distributed data (non-IID) on the accuracy of FL, it is shown that the accuracy of the model obtained by the traditional FL method is low. Therefore, we proposed the diversified sampling strategies to simulate the non-IID data situation and came up with the OPTICS (ordering points to identify the clustering structure)-based clustering optimization federated learning method (OCFL), which solves the problem that the learning accuracy is reduced when the data of different nodes are non-IID in FL. Experiments indicate that OCFL greatly improves the model accuracy and training speed compared with the traditional FL algorithm. [ABSTRACT FROM AUTHOR]

A novel evolutionary extreme learning machine (ELM) based on improved quantum-behaved particle swarm optimization (IQPSO) for radar target classification is presented in this paper. Quantum-behaved particle swarm optimization (QPSO) has been used in ELM to solve the problem that ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. But the method for calculating the characteristic length of Delta potential well of QPSO may reduce the global search ability of the algorithm. To solve this issue, a new method to calculate the characteristic length of Delta potential well is proposed in this paper. Experimental results based on the benchmark functions validate the better performance of IQPSO against QPSO in most cases. The novel algorithm is also evaluated by using real-world datasets and radar data; the experimental results indicate that the proposed algorithm is more effective than BP, SVM, ELM, QPSO-ELM, and so on, in terms of real-time performance and accuracy. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs) are among the most robust and accurate methods in all well-known machine learning algorithms, especially for classification. The SVMs train a classification model by solving an optimization problem to decide which instances in the training datasets are the support vectors (SVs). However, SVs are intact instances taken from the training datasets and directly releasing the classification model of the SVMs will carry significant risk to the privacy of individuals, when the training datasets contain sensitive information. In this paper, we study the problem of how to release the classification model of kernel SVMs while preventing privacy leakage of the SVs and satisfying the requirement of privacy protection. We propose a new differentially private algorithm for the kernel SVMs based on the exponential and Laplace hybrid mechanism named DPKSVMEL. The DPKSVMEL algorithm has two major advantages compared with existing private SVM algorithms. One is that it protects the privacy of the SVs by postprocessing and the training process of the non-private kernel SVMs does not change. Another is that the scoring function values are directly derived from the symmetric kernel matrix generated during the training process and does not require additional storage space and complex sensitivity analysis. In the DPKSVMEL algorithm, we define a similarity parameter to denote the correlation or distance between the non-SVs and every SV. And then, every non-SV is divided into a group with one of the SVs according to the maximal value of the similarity. Under some certain similarity parameter value, we replace every SV with a mean value of the top-k randomly selected most similar non-SVs within the group by the exponential mechanism if the number of non-SVs is greater than k. Otherwise, we add random noise to the SVs by the Laplace mechanism. We theoretically prove that the DPKSVMEL algorithm satisfies differential privacy. The extensive experiments show the effectiveness of the DPKSVMEL algorithm for kernel SVMs on real datasets; meanwhile, it achieves higher classification accuracy than existing private SVM algorithms. [ABSTRACT FROM AUTHOR]

At present, the graph neural network has achieved good results in the semisupervised classification of graph structure data. However, the classification effect is greatly limited in those data without graph structure, incomplete graph structure, or noise. It has no high prediction accuracy and cannot solve the problem of the missing graph structure. Therefore, in this paper, we propose a high-order graph learning attention neural network (HGLAT) for semisupervised classification. First, a graph learning module based on the improved variational graph autoencoder is proposed, which can learn and optimize graph structures for data sets without topological graph structure and data sets with missing topological structure and perform regular constraints on the generated graph structure to make the optimized graph structure more reasonable. Then, in view of the shortcomings of graph attention neural network (GAT) that cannot make full use of the graph high-order topology structure for node classification and graph structure learning, we propose a graph classification module that extends the attention mechanism to high-order neighbors, in which attention decays according to the increase of neighbor order. HGLAT performs joint optimization on the two modules of graph learning and graph classification and performs semisupervised node classification while optimizing the graph structure, which improves the classification performance. On 5 real data sets, by comparing 8 classification methods, the experiment shows that HGLAT has achieved good classification results on both a data set with graph structure and a data set without graph structure. [ABSTRACT FROM AUTHOR]

In this paper, we examine the use of ensemble methods in a multirobot task allocation environment. The aim is to enable a robot that needs to estimate the required resources to complete a task, to utilize information coming from other robots of the same type. To our knowledge, it is the first attempt made, to use such methods, to combine data of the same type, coming from data sets of different agents, to form a prediction. Knowledge exchange is not continuous, but only ad hoc. To merge data, we use ensemble models. This keeps communication needs to a minimum, as only the models themselves-and no actual data- need to be exchanged. To further reduce communication costs, the number of robots that contribute information is being limited. Finally, we make an attempt to see how well the concept we use would perform in other domains. This is to examine whether the approach could yield the same results in other domains, or it is limited to the task allocation problem, as formulated in Tolmidis and Petrou ( Eng. Appl. Artif. Intell., 2013;26(5-6):1458-1468) . For this, we selected two additional, different, publicly available data sets. [ABSTRACT FROM AUTHOR]

The KNN algorithm is one of the most famous algorithms in machine learning and data mining. It does not preprocess the data before classification, which leads to longer time and more errors. To solve the problems, this paper first proposes a PK-means++ algorithm, which can better ensure the stability of a random experiment. Then, based on it and spherical region division, an improved KNNPK+ is proposed. The algorithm can select the center of the spherical region appropriately and then construct an initial classifier for the training set to improve the accuracy and time of classification. [ABSTRACT FROM AUTHOR]

Intrusion detection system (IDS), the second security gate behind the firewall, can monitor the network without affecting the network performance and ensure the system security from the internal maximum. Many researches have applied traditional machine learning models, deep learning models, or hybrid models to IDS to improve detection effect. However, according to Predicted accuracy, Descriptive accuracy, and Relevancy (PDR) framework, most of detection models based on model-based interpretability lack good detection performance. To solve the problem, in this paper, we have proposed a novel intrusion detection system model based on model-based interpretability, called Interpretable Intrusion Detection System (I2DS). We firstly combine normal and attack samples reconstructed by AutoEncoder (AE) with training samples to highlight the normal and attack features, so that the classifier has a gorgeous effect. Then, Additive Tree (AddTree) is used as a binary classifier, which can provide excellent predictive performance in the combined dataset while maintaining good model-based interpretability. In the experiment, UNSW-NB15 dataset is used to evaluate our proposed model. For detection performance, I2DS achieves a detection accuracy of 99.95%, which is better than most of state-of-the-art intrusion detection methods. Moreover, I2DS maintains higher simulatability and captures the decision rules easily. [ABSTRACT FROM AUTHOR]

Volatility is widely used in different financial areas, and forecasting the volatility of financial assets can be valuable. In this paper, we use deep neural network (DNN) and long short-term memory (LSTM) model to forecast the volatility of stock index. Most related research studies use distance loss function to train the machine learning models, and they gain two disadvantages. The first one is that they introduce errors when using estimated volatility to be the forecasting target, and the second one is that their models cannot be compared to econometric models fairly. To solve these two problems, we further introduce a likelihood-based loss function to train the deep learning models and test all the models by the likelihood of the test sample. The results show that our deep learning models with likelihood-based loss function can forecast volatility more precisely than the econometric model and the deep learning models with distance loss function, and the LSTM model is the better one in the two deep learning models with likelihood-based loss function. [ABSTRACT FROM AUTHOR]

Advances in machine learning (ML) in recent years have enabled a dizzying array of applications such as data analytics, autonomous systems, and security diagnostics. As an important part of the Internet of Things (IoT), wireless sensor networks (WSNs) have been widely used in military, transportation, medical, and household fields. However, in the applications of wireless sensor networks, the adversary can infer the location of a source node and an event by backtracking attacks and traffic analysis. The location privacy leakage of a source node has become one of the most urgent problems to be solved in wireless sensor networks. To solve the problem of source location privacy leakage, in this paper, we first propose a proxy source node selection mechanism by constructing the candidate region. Secondly, based on the residual energy of the node, we propose a shortest routing algorithm to achieve better forwarding efficiency. Finally, by combining the proposed proxy source node selection mechanism with the proposed shortest routing algorithm based on the residual energy, we further propose a new, anonymous communication scheme. Meanwhile, the performance analysis indicates that the anonymous communication scheme can effectively protect the location privacy of the source nodes and reduce the network overhead. [ABSTRACT FROM AUTHOR]

In supervised learning-based classification, ensembles have been successfully employed to different application domains. In the literature, many researchers have proposed different ensembles by considering different combination methods, training datasets, base classifiers, and many other factors. Artificial-intelligence-(AI-) based techniques play prominent role in development of ensemble for intrusion detection (ID) and have many benefits over other techniques. However, there is no comprehensive review of ensembles in general and AI-based ensembles for ID to examine and understand their current research status to solve the ID problem. Here, an updated review of ensembles and their taxonomies has been presented in general. The paper also presents the updated review of various AI-based ensembles for ID (in particular) during last decade. The related studies of AI-based ensembles are compared by set of evaluation metrics driven from (1) architecture & approach followed; (2) different methods utilized in different phases of ensemble learning; (3) other measures used to evaluate classification performance of the ensembles. The paper also provides the future directions of the research in this area. The paper will help the better understanding of different directions in which research of ensembles has been done in general and specifically: field of intrusion detection systems (IDSs). [ABSTRACT FROM AUTHOR]

Kernel extreme learning machine (KELM) is a novel feedforward neural network, which is widely used in classification problems. To some extent, it solves the existing problems of the invalid nodes and the large computational complexity in ELM. However, the traditional KELM classifier usually has a low test accuracy when it faces multiclass classification problems. In order to solve the above problem, a new classifier, Mexican Hat wavelet KELM classifier, is proposed in this paper. The proposed classifier successfully improves the training accuracy and reduces the training time in the multiclass classification problems. Moreover, the validity of the Mexican Hat wavelet as a kernel function of ELM is rigorously proved. Experimental results on different data sets show that the performance of the proposed classifier is significantly superior to the compared classifiers. [ABSTRACT FROM AUTHOR]

As the network is closely related to people's daily life, network security has become an important factor affecting the physical and mental health of human beings. Network flow classification is the foundation of network security. It is the basis for providing various network services such as network security maintenance, network monitoring, and network quality of service (QoS). Therefore, this field has always been a hot spot of academic and industrial research. Existing studies have shown that through appropriate data preprocessing techniques, machine learning methods can be used to classify network flows, most of which, however, are based on manually and expert-originated feature sets; it is a time-consuming and laborious work. Moreover, only features extracted by a single model can be used in classification tasks, which can easily make the model inefficient and prone to overfitting. In order to solve the abovementioned problems, this study proposes a multimodal automatic analysis framework based on spatial and sequential features. The framework is completely based on the deep learning method and realizes automatic extraction of two types of features, which is very suitable for processing large-flow information; this improves the efficiency of network flow classification. There are two types of frameworks based on pretraining and joint-training, respectively, with analyzing the advantages and disadvantages of them in practice. In terms of evaluation, compared with the previous methods, the experimental results show that the framework has good performance in both accuracy and stability. [ABSTRACT FROM AUTHOR]

In distributed computing/storage/machine learning system, the method of encoding and decoding combing shift-and-addition (SA) and zigzag decoding (ZD) is proposed to solve the problem of high computational complexity. However, in each encoded packet, one element takes part in the encoding only once, so the obtained overhead is extremely high. In this work, based on the idea of multidimensional encoding/modulation, we propose to employ one element of the encoding process multiple times when constructing one encoded packet based on the Cauchy matrix, thereby leveraging the favourable properties of the code based on Cauchy matrix. The overhead is reduced from square to logarithmic in certain parameters. Compared with the overhead of the existing square computational complexity, it is greatly reduced. [ABSTRACT FROM AUTHOR]

Dictionary learning problem has become an active topic for decades. Most existing learning methods train the dictionary to adapt to a particular class of signals. But as the number of the dictionary atoms is increased to represent the signals much more sparsely, the coherence between the atoms becomes higher. According to the greedy and compressed sensing theories, this goes against the implementation of sparse coding. In this paper, a novel approach is proposed to learn the dictionary that minimizes the sparse representation error according to the training signals with the coherence taken into consideration. The coherence is constrained by making the Gram matrix of the desired dictionary approximate to an identity matrix of proper dimension. The method for handling the proposed model is mainly based on the alternating minimization procedure and, in each step, the closed-form solution is derived. A series of experiments on synthetic data and audio signals is executed to demonstrate the promising performance of the learnt incoherent dictionary and the superiority of the learning method to the existing ones. [ABSTRACT FROM AUTHOR]

In many practical engineering applications, data are usually collected in online pattern. However, if the classes of these data are severely imbalanced, the classification performance will be restricted. In this paper, a novel classification approach is proposed to solve the online data imbalance problem by integrating a fast and efficient learning algorithm, that is, Extreme Learning Machine (ELM), and a typical sampling strategy, that is, the synthetic minority oversampling technique (SMOTE). To reduce the severe imbalance, the granulation division for major-class samples is made according to the samples’ distribution characteristic, and the original samples are replaced by the obtained granule core to prepare a balanced sample set. In online stage, we firstly make granulation division for minor-class and then conduct oversampling using SMOTE in the region around granule core and granule border. Therefore, the training sample set is gradually balanced and the online ELM model is dynamically updated. We also theoretically introduce fuzzy information entropy to prove that the proposed approach has the lower bound of model reliability after undersampling. Numerical experiments are conducted on two different kinds of datasets, and the results demonstrate that the proposed approach outperforms some state-of-the-art methods in terms of the generalization performance and numerical stability. [ABSTRACT FROM AUTHOR]

While MOOCs offer educational data on a new scale, many educators find great potential of the big data including detailed activity records of every learner. A learner’s behavior such as if a learner will drop out from the course can be predicted. How to provide an effective, economical, and scalable method to detect cheating on tests such as surrogate exam-taker is a challenging problem. In this paper, we present a grade predicting method that uses student activity features to predict whether a learner may get a certification if he/she takes a test. The method consists of two-step classifications: motivation classification (MC) and grade classification (GC). The MC divides all learners into three groups including certification earning, video watching, and course sampling. The GC then predicts a certification earning learner may or may not obtain a certification. Our experiment shows that the proposed method can fit the classification model at a fine scale and it is possible to find a surrogate exam-taker. [ABSTRACT FROM AUTHOR]

Distant supervision (DS) automatically annotates free text with relation mentions from existing knowledge bases (KBs), providing a way to alleviate the problem of insufficient training data for relation extraction in natural language processing (NLP). However, the heuristic annotation process does not guarantee the correctness of the generated labels, promoting a hot research issue on how to efficiently make use of the noisy training data. In this paper, we model two types of biases to reduce noise: (1) bias-dist to model the relative distance between points (instances) and classes (relation centers); (2) bias-reward to model the possibility of each heuristically generated label being incorrect. Based on the biases, we propose three noise tolerant models: MIML-dist, MIML-dist-classify, and MIML-reward, building on top of a state-of-the-art distantly supervised learning algorithm. Experimental evaluations compared with three landmark methods on the KBP dataset validate the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]