Search

The welding process for medium and thick plates typically involves multi-layering and multi-channeling, but its quality and reliability require further improvement. Therefore, this study introduces the convolution neural network algorithm to establish a deep learning model for weld seam recognition. Additionally, the structured light imaging method is used to accurately position the V-shaped weld groove. Meanwhile, a machine vision based multi-layer and multi-pass dynamic routing planning algorithm was also studied and designed, and a contour feature point recognition algorithm for the filling layer was developed. Thus, dynamic routing planning is achieved. It is demonstrated that the difference between the coordinates acquired by the deep learning model and the ideal region decreases steadily and reaches a minimum of (200,80). The confidence level of weld seam detection gradually increases with the adjustment of the welding robot, reaching a maximum of 98%. The confidence level of the detected feature points reaches 100%. In the meantime, the remaining height of the fusion after welding is 2.5mm. There are no negative phenomena present on the surface of the weld seam, meeting the necessary process requirements. Such discrepancies as undercut, incomplete penetration, slag inclusion, and porosity are absent. It shows that the welding technology based on machine vision has strong feasibility, effectively improves the automation level and efficiency of welding technology, and provides reliable technical support for the development of modern machine vision welding technology.

Considering the problem of difficulty in transmission and storage due to a large amount of data in the water-supply network monitoring system based on a wireless sensor network (WSN), we propose a sparse representation of the water-supply network monitoring data by using compressed sensing (CS) method. At the same time, aiming at the problem of low leakage identification accuracy caused by information loss under compressed sensing, we propose a leak identification method for a water-supply pipe network based on compressed sensing and deep residual neural network (ResNet). Firstly, under the condition that the observation matrix ensures the integrity of signal information, the compressed sensing theory is used to compress and observe leakage signals to obtain observation data, to reduce the redundant information and volume of the data. At the same time, the observation data is preprocessed to realize the transformation of a one-dimensional signal to a two-dimensional matrix. Then the residual neural network is trained by using the two-dimensional data to realize the automatic, efficient, and accurate leak identification under different leakage apertures. Experimental results show that the proposed method can obtain relatively high accuracy and greatly reduce the training time of ResNet by using compressed data. When the Compression rate (CR) is 70% and the observation matrix is a Gaussian random matrix, the average accuracy is 96.67% and the training time is only 50% compared to uncompressed data. The research work provides a new intelligent leak identification under different leak apertures using WSN and has important application prospects in saving water resources.

Underground metal target detection technology has been widely applied in industrial production, resource exploration, and engineering construction, etc. However, due to the influence of non-negligible noise and high dimensionality in collected data, achieving efficient and accurate underground target classification remains a grand challenge for further applications of underground metal target detection on portable devices with limited computing capability and energy supply. This study aimed to seek out robust and efficient data-based strategies to classify the underground metal targets of different shapes and materials based on electromagnetic induction detection. We investigated thirty-three classification strategies based on eleven dimensionality reduction methods, namely, the least absolute shrinkage and selection operator (LASSO), genetic algorithm-support vector machine (GA-SVM), Pearson correlation coefficient (PCC), mutual information (MI), maximal relevance minimal redundancy Pearson correlation (mRMRP), maximal relevance minimal redundancy mutual information (mRMRMI), statistical features (SF), principal component analysis (PCA), kernel principal component analysis (KPCA), locally linear embedding (LLE), and stacked denoising autoencoder (SDAE), and three machine learning models, namely, artificial neural network (ANN), linear support vector machine (L-SVM), and Gaussian Naïve Bayes (GNB). Several parameters, including classification accuracy, the number of features after dimensionality, the feature type importance, and the time consumption were considered to evaluate the data-based classification strategies. Among the classification strategies investigated and considering the above evaluation parameters, the artificial neural network (ANN) classifier assisted with the kernel principal component analysis (KPCA) feature extraction method yielded the best performance in the material-based classification (accuracy:0.99) and the shape-based classification (accuracy:0.99). The locally linear embedding (LLE) improved the robustness of machine learning classifiers and efficiency of the artificial neural network in the material-based classification (improvement of average accuracy:0.17, reduction of classification time cost:14%) and shape-based classification (improvement of average accuracy:0.16, reduction of classification time cost:22%). Our comparative investigation provides a robust and efficient data-based strategy for underground metal target classification, which is significant for applications of underground metal target detection on portable devices with limited computing capability and energy supply. The cross-combination strategy of dimensionality reduction methods and machine learning models provides a way to find the optimal machine learning model for underground target detection.

As an extensive prospect in communication technology, multi-hop unmanned aerial vehicle (UAV) faces some challenges as well. How to ensure the availability of time slots in high dynamic scenarios and the rationality and robustness of power allocation in massive scenarios remains to be resolved. In this paper, we propose a robust mean field game (MFG) framework to manage time slot resources and power resources. On the one hand, this framework can predict the potential conflicts of time slots and avoid them in time. On the other hand, it can well adapt to the massive scenarios with complex interference, in order to realize power control. The simulation results show that the robust MFG-based resource management scheme can not only reduce the probability of packet collision and packet loss, but also improve communication energy efficiency (EE) with better robustness.

In recent years, semisupervised spectral–spatial feature extraction (FE) methods for hyperspectral image (HSI) classification have shown promising performance by combining spectral–spatial information and label information. A problem that has not been addressed satisfactorily is that how to effectively and collaboratively use this abundant information contained in the hyperspectral data to exhibit better HSI classification performance. In this article, a novel FE method based on joint spectral–spatial information is proposed for HSI classification, which consists of the following steps. First, an effective re-expression for the original data is constructed by incorporating texture features extracted by extended multiattribute profiles with the original HSI. Thus, every pixel can be described by diverse and complementary information in the spectral–spatial domain. Then, the improved neighborhood preserving embedding (NPE) is proposed to establish a relatively accurate reconstruction model and mine high-reliable neighborhood structure from a global perspective by a new distance metric, which incorporates spectral bands, texture features, and geographical information simultaneously. Finally, the low-dimensional and high-discriminative features for HSI classification are obtained by combining the scatter matrices of local fisher discriminant analysis based on labeled samples and the improved NPE based on the whole data. Experimental results on three real-world HSI datasets show that the proposed method can effectively utilize both the label information and the spectral–spatial information, and hence, achieve much better classification performance compared to the conventional FE methods and some state-of-the-art spectral–spatial classification methods.

Aiming at the speed regulation problem of permanent magnet synchronous motor (PMSM) drives, a novel backstepping nonsingular terminal sliding mode control (BNTSMC) method with finite-time disturbance observer (FTDO) is proposed. In order to ensure excellent tracking and anti-disturbance performance, the backstepping nonsingular terminal sliding mode speed controller based on equivalent motor model and the recursive principle is designed for PMSM. The benefits of this approach are that the controller has asymptotic stability based on backstepping design and strong robustness for the matched disturbance based on sliding mode control. Then, to further improve the anti-disturbance performance, a finite-time disturbance observer is designed, and it is used to estimate the mismatched external disturbance in motor drive system. The stability of the system is also proved with Lyapunov criterion. Finally, the experimental results show that the proposed method has the advantages of fast convergence and strong robustness against parameter variations and external disturbance.

The advent of noisy intermediate-scale quantum (NISQ) devices provide crucial promise for the development of quantum algorithms. Variational quantum algorithms have emerged as one of the best hopes to utilize NISQ devices. Among these is the famous variational quantum eigensolver (VQE), where one trains a parameterized and fixed quantum circuit (or an ansatz) to accomplish the task. However, VQE also suffers from some serious challenges, which are training difficulty and accuracy reduction due to deep quantum circuit and hardware noise. Motivated by these issues, we propose a runtime and resource-efficient scheme, Monto Carlo tree (MCT) search-based quantum circuit architecture optimization, where the ansatz is built in the variable form. Our approach first models the search space with a MCT and regards it as a supernet, where we make use of layers dependence to reduce the size of the search space. Second, a two-stage scheme is proposed for the search space training, where weight sharing and warm-up strategies are employed to avoid huge computation cost. Training results are stored in nodes of the MCT for future decisions, and hierarchical node selection is presented to obtain an optimal ansatz. As a proof of principle, we carry out a series of numerical experiments for condensed matter and quantum chemistry in a quantum simulator with and without noise. Consequently, our scheme can be efficient to mitigate trainability and accuracy issues by minimizing the ansatz depth and the number of entanglement gates.

This paper investigates estimator-based control problems for pure-feedback nonlinear systems with incomplete measurements due to the transmission packet losing or sensor saturation. The incomplete measurements can cause the state variables unavailable or distorted, which can degrade the performance of the system. To solve these problems, a state estimator is designed for the data-losing case, based on which two backstepping control methods are developed. The output of the system is subject to a prescribed constraint by using an obstacle Lyapunov function. By solving a linear matrix inequality, the stability conditions of the state estimator and closed-loop system are derived. It is proved that the control scheme can guarantee that all the signals of the closed-loop system are uniformly ultimately bounded in mean square. The effectiveness of the proposed methods is confirmed by simulations.

In the Web 2.0 age, mass media disseminates the disinformation of companies and exerts considerable influence. How to manage this trend in a timely and effective fashion in this big data era has become difficult. In this study, we delve into this issue by trying to identify the core disseminators in the dissemination process. We propose the concept of a disinformation channel and quantitatively analyse these company-related disinformation channels among media outlets. By empirically analysing 4,689 disinformation news values and 330 channels in 2018, we reveal that the disinformation values and negative news values are characteristics. We also build automatic identification models to identify these channels from the media combined with machine learning algorithms. Our study sheds light on disinformation, thus providing managers with an empirical basis upon which to analyse the media and help them address the disinformation problem.

When an emergency occurs, as a factor in online emergency information dissemination, the peak represents the maximum strength and turning point. However, the role of these peaks in emergencies is still unclear. In this article, we try to disentangle this problem and investigate the effect of these peaks on the lifecycle and influence of online emergency information dissemination. We first propose an Online Emergency Information Dissemination Process (OEIDP) model drawing from the ideas of system cybernetics and system identification to present the emergency lifecycle with a decay parameter, time constant, and delay parameter. Based on this model, we then analyze the effect of peaks using empirical data from the Weibo, WeChat, and 20000 media platforms of 169 emergencies. The results reveal the positive significant impacts of the peak time, peak volume, and spikes on emergency information dissemination. The results enable us to make accurate judgements when facing peaks and remind us of the need to balance the strongest manifestation and final influence. Our work complements the gaps on the peak effect in the existing communication literature and introduces the concept of system cybernetics to solve information dissemination which provides a new direction for future studies to solve related problems using system control techniques.

This thesis studies the problem of three-dimensional guidance considering maneuvering acceleration and input saturation based on the background of missile intercepting maneuvering target. On the basis of the three-dimensional guidance model with impact angle constraints, a three-dimensional guidance law is designed by using the integral sliding mode control and adaptive control. To solve the problem of input saturation, an adaptive anti-saturation integral sliding mode three-dimensional guidance law is designed by introducing an auxiliary system. The stability of the designed guidance law is proved by Lyapunov theory, which ensures that the sliding mode manifold converges to zero in finite time. The effectiveness of the designed guidance law is verified by simulation analysis.

With the recent advancement of novel biomedical technologies such as high-throughput sequencing and wearable devices, multi-modal biomedical data ranging from multi-omics molecular data to real-time continuous bio-signals are generated at an unprecedented speed and scale every day. For the first time, these multi-modal biomedical data are able to make precision medicine close to a reality. However, due to data volume and the complexity, making good use of these multi-modal biomedical data requires major effort. Researchers and clinicians are actively developing artificial intelligence (AI) approaches for data-driven knowledge discovery and causal inference using a variety of biomedical data modalities. These AI-based approaches have demonstrated promising results in various biomedical and healthcare applications. In this review paper, we summarize the state-of-the-art AI models for integrating multi-omics data and electronic health records (EHRs) for precision medicine. We discuss the challenges and opportunities in integrating multi-omics data with EHRs and future directions. We hope this review can inspire future research and developing in integrating multi-omics data with EHRs for precision medicine. [ABSTRACT FROM AUTHOR]

In traffic accident, an accurate and timely severity prediction method is necessary for the successful deployment of an intelligent transportation system to provide corresponding levels of medical aid and transportation in a timely manner. The existing traffic accident's severity prediction methods mainly use shallow severity prediction models and statistical models. To promote the prediction accuracy, a novel traffic accident's severity prediction-convolutional neural network (TASP-CNN) model for traffic accident's severity prediction is proposed that considers combination relationships among traffic accident's features. Based on the weights of traffic accident's features, the feature matrix to gray image (FM2GI) algorithm is proposed to convert a single feature relationship of traffic accident's data into gray images containing combination relationships in parallel as the input variables for the model. Moreover, experiments demonstrated that the proposed model for traffic accident's severity prediction has a better performance.

Private processes are the basis to construct the collaborative business processes, and their correctness has a direct impact on the correctness of collaborative business processes. Thus, the modeling and correctness of private processes is a key issue that business designers should consider at design time. To this end, we propose an approach for constructing correct private processes in a refinement manner. In this approach, we first present a formal model for private processes and abstract the control flow of the model into four basic blocks. Then, we derive a set of refinement rules for the four basic blocks and present an approach that relies on the refinement rules for constructing correct private processes. Finally, we prove that the private process established by our approach is correct at the syntax and semantic levels, and thus a subsequent correctness verification is avoided. Our approach is validated through a case study, and the results show that the approach is more effective than the existing work in terms of modeling private processes.

In this paper, a novel method to design a multifunctional metasurface (MS) is proposed and demonstrated. Inspired by shared aperture technology, the proposed MS is integrated with both radiation and low backward scattering performance. Each MS unit cell consists of two parts, polarization conversion surface part and radiation part. Different from traditional MS design, the proposed two parts are integrated together, and thus, bi-functions are realized in one surface. To acquire radiation performance, the feeding structure is added to each radiation in part by introducing an antenna design concept. The peak gain of the MS attains 18.1 dBi and main-beam patterns are all along the normal direction. To obtain low backward scattering performance, the polarization of an incident electromagnetic wave is transformed by the reflected MS. The reflected wave will have a 180° phase difference through rotating the polarization conversion surface structure. Thus, two different types of MS units are arranged in chessboard array to achieve reflection suppression. The radar cross section reduction band is from 3.0 to 4.3 GHz with peak values of 7.2 and 16.8 dB. Both the simulated and experimental results prove that our method offers a feasible strategy for the multifunctional MS design which can lead to many exciting applications in different frequency domains.

A new strategy for designing low side-lobe level (SLL) antenna array is presented. This strategy utilizes special arrangement of antenna elements rather than direct tapered excitation amplitude to obtain an equivalent desired amplitude distribution in the main planes and thus achieve low SLL and high gain concurrently. To illustrate the strategy, 9-element microstrip antennas are arranged in four manners. An equivalent analysis method is also proposed to predict the SLL of the arrays. Using this method, a fast analysis of the trend of a microstrip array for a low SLL can be performed and thus a proper array-element arrangement is acquired. Both numerical and experimental results demonstrate that the SLLs in E and H planes of the novel array are fairly low. Meanwhile, the main beam of the novel array is almost the same with that of a conventional high-gain array. The antenna arrangement manner and the proposed strategy are particularly suitable for applications when low SLL and high gain are both demanded.

A Cow's ruminant behavior can provide information about a cow's health. Monitoring a cow's ruminant behavior could therefore be of use when assessing its health. However, it is difficult to simultaneously monitor multiple target cows' ruminations simultaneously without any contact-type equipment. A method for monitoring multiple target cows' ruminant behavior based on an optical flow method and an inter-frame difference method is proposed here in. The optical flow method is used to obtain the optical flow fields of the ruminant cows' mouth areas in the first 60 frames of a video. The optical flow values with large changes are selected from the first 60 frames of the test video and these values are superimposed to obtain the candidate ruminant cows' mouth areas. The candidate ruminant cows' mouth areas are magnified 1.5 times, and the inter-frame difference method is used to track the real cows' mouth areas in the new magnified areas. According to the “center error” and “overlap rate” indexes, the tracking result for the 15 videos is evaluated. The results show that the average successful tracking rate reaches 89.12%, demonstrating that the algorithm could be applied for the automatic monitoring of multiple target ruminant cows' mouth areas.

Collaborative business processes are indeed complex and difficult to be correctly designed as business processes involved in them are typically developed by different participating organizations and there is no way to foresee all potential interactions at design time. To this end, we propose a novel correctness enforcement approach for collaborative business processes. In this approach, given an original process, we first propose an algorithm for automatically detecting its correctness. Then, in case the original process is partially correct, we prune it to generate its core. The core captures all legal traces in the original process. Finally, an enforced process is yielded from the core through coordination mapping (i.e., inserting additional coordination activities into original processes). Our approach is implemented as a prototype tool called cet (a correctness enforcement tool for collaborative business processes), and a series of experiments is conducted to validate the applicability and effectiveness of the proposed approach.

Local Outlier Factor (LOF) outlier detecting algorithm has good accuracy in detecting global and local outliers. However, the algorithm needs to traverse the entire dataset when calculating the local outlier factor of each data point, which adds extra time overhead and makes the algorithm execution inefficient. In addition, if the K-distance neighborhood of an outlier point P contains some outliers that are incorrectly judged by the algorithm as normal points, then P may be misidentified as normal point. To solve the above problems, this paper proposes a Neighbor Entropy Local Outlier Factor (NELOF) outlier detecting algorithm. Firstly, we improve the Self-Organizing Feature Map (SOFM) algorithm and use the optimized SOFM clustering algorithm to cluster the dataset. Therefore, the calculation of each data point's local outlier factor only needs to be performed inside the small cluster. Secondly, this paper replaces the K-distance neighborhood with relative K-distance neighborhood and utilizes the entropy of relative K neighborhood to redefine the local outlier factor, which improves the accuracy of outlier detection. Experiments results confirm that our optimized SOFM algorithm can avoid the random selection of neurons, and improve clustering effect of traditional SOFM algorithm. In addition, the proposed NELOF algorithm outperforms LOF algorithm in both accuracy and execution time of outlier detection.

The abundance of event data in current software configuration management systems makes it possible to discover software process models automatically by using actual observed behavior. However, traditional process mining algorithms cannot be applied to event logs recorded in software configuration management (SCM) systems, such as SVN, because of missing activity attributes. To address this problem, a software process activity classifier is proposed to build event-activity mapping relationships from software development event streams, revealing activity attributes and associating the activity to the original SVN log. The proposed approach extracts activity from the SVN log based on semantic features and introduces a novel technique based on a naive Bayes approach to associate event activities dynamically. The approach has been applied to two real-world software development process logs, ArgoUML and jEdit, consisting of more than 80,000 events, covering development information from 1998 to 2015. With the application of our approach to such data, activities can be extracted from event logs and a classifier can be constructed for adding activity attributes to new events. The results of the classification are evaluated in terms of precision rate, recall rate, and the F-measure. Overall, two real-world software development process logs are used to validate the method, and the experimental results show that the approach can mine software process activities from SVN log events automatically and in real-time.

Sentiment classification for reviews has attracted increasingly more attention from the natural language processing community. By embedding prior knowledge into learning structures, classifiers often achieve a better performance than original methods. In this paper, we propose a sophisticated algorithm based on deep learning and information geometry in which the distribution of all training samples in the space is treated as prior knowledge and is encoded by deep belief networks (DBNs). From the view of information geometry, we construct the geodesic distance between the distributions over the features for classification. The study of the distributions contributes to the training of the DBN, since the distance is correlated to the error rate in the classification. Finally, we evaluate our proposal using empirical data sets that are dedicated for sentiment classification. The results show that our algorithm results in a significant improvement over existing methods.

In practical massive multiple-input-multiple-output (MIMO) system, limited transmitted antennas installed at the base station (BS) cannot guarantee the ideal orthogonality and the theoretical channel rate cannot thus be achieved. In this paper, we consider the approximation of channel rate for the configuration of large but finite number of antennas at BS in a massive MIMO system. A perturbation matrix is introduced to model the non-ideal orthogonality. And then, Taylor expansion of determinant is utilized to derive the closed form of the achievable channel rate. The convergence of the Taylor expansion is theoretically proved and simulated. Numerical results show that our calculation of channel rate can get a better approximation compared with the practical rate, especially in the case of high expansion order and large number of antennas.

With the wide deployment of cloud computing, many security challenges have arisen, such as data and storage integrity and virtualization security. The crisis of trust caused by these security issues has become one of the important factors restricting the wide applications of cloud service. Especially for security-sensitive users, it is challenging to quickly select a cloud service which has the high level of trust and can meet both the user preferences and specific functional demands. This paper explores the multi-granularity selection standard of trust level, the users' preference calculation model, and the cloud service selection algorithm. First, the trust evaluation mechanisms among different entities in the human society are fitted, and the multi-granularity selection standard of trust levels based on Gaussian cloud transformation is constructed. Then, the calculation model of user preferences based on the cloud analytic hierarchy process is developed. Finally, the trusted cloud service selection algorithm based on two-step fuzzy comprehensive evaluation is proposed and experimentally validated.

In recent years, tactile sensors have experienced tremendous progress. Among them, piezoresistive tactile sensors using nanocomposites exhibit good flexibility and sensitivity. Due to their low cost and good performance, piezoresistive tactile sensors have great potential for large-scale commercialization. However, the drawbacks are equally obvious, i.e., poor consistency and low-sensing range. The fundamental reason is that conductive fillers have poor decentralization in polymer and lacks an effective structural design. To solve these problems, we compared six common organic solvents in the solution blending method to prepare the multi-walled carbon nanotubes/polydimethylsiloxane (MWCNT/PDMS) composite. The optimal organic solvent by comparing the dispersion performance of MWCNT and the stability of MWCNT/PDMS is presented. Moreover, the well-consistent tactile sensors were proposed and fabricated using the micro-electromechanical systems technologies. The sensitivity reached 6.25% KPa-1, and the reproducibility test of the same sensor has been performed. The result proves that the proposed schemes for nano-materials preparation and processing have greatly improved the consistency of the piezoresistive tactile sensors.

Automatic grasping is playing an important role in robotics, and traditional grasping approaches cannot deal with both occlusions and texture-less objects well. To improve the stability and accuracy of grasping in a novel and occlusion environment, a grasping approach based on instance segmentation and self-supervised learning pose estimation network is proposed to grasp objects with the manipulator in this paper. The approach can be divided into three phases: instance segmentation, pose estimation, and pose transformation. Instance segmentation predicts classification masks for each pixel. Masks which stand for the contour of objects provide a heuristic knowledge for the self-supervised learning pose estimation network. Pose estimation network has two fully connected layers and regards estimation as a self-supervised classification problem. Then, the pose can be transformed from value in pixel coordinates to actual value relative to the base coordinate of the manipulator. As a result, the manipulator can be operated to grasp by the given actual value of pose. With the help of the approach proposed in this paper, we improve the grasping accuracy by 35%, compared to the former grasping approach based on the pose estimation network on the grasping dataset of CMU. Besides, grasping with this approach on hardware also shows a high success rate. Therefore, the proposed approach is a more robust and more accurate way of grasping.