Matching Matrix Research Articles

Two-Sided Stable Matching Decision-Making Method Considering Matching Intention under a Hesitant Fuzzy Environment

In this paper, a stable two-sided matching (TSM) method considering the matching intention of agents under a hesitant fuzzy environment is proposed. The method uses a hesitant fuzzy element (HFE) as its basis. First, the HFE preference matrix is transformed into the normalized HFE preference matrix. On this basis, the distance and the projection of the normalized HFEs on positive and negative ideal solutions are calculated. Then, the normalized HFEs are transformed into agent satisfactions. Considering the stable matching constraints, a multiobjective programming model with the objective of maximizing the satisfactions of two-sided agents is constructed. Based on the agent satisfaction matrix, the matching intention matrix of two-sided agents is built. According to the agent satisfaction matrix and matching intention matrix, the comprehensive satisfaction matrix is set up. Furthermore, the multiobjective programming model based on satisfactions is transformed into a multiobjective programming model based on comprehensive satisfactions. Using the G-S algorithm, the multiobjective programming model based on comprehensive satisfactions is solved, and then the best TSM scheme is obtained. Finally, a terminal distribution example is used to verify the feasibility and effectiveness of the proposed method.

Soft Tissue Feature Tracking Based on Deep Matching Network

Research in the field of medical image is an important part of the medical robot to operate human organs. A medical robot is the intersection of multi-disciplinary research fields, in which medical image is an important direction and has achieved fruitful results. In this paper, a method of soft tissue surface feature tracking based on a depth matching network is proposed. This method is described based on the triangular matching algorithm. First, we construct a self-made sample set for training the depth matching network from the first N frames of speckle matching data obtained by the triangle matching algorithm. The depth matching network is pre-trained on the ORL face data set and then trained on the self-made training set. After the training, the speckle matching is carried out in the subsequent frames to obtain the speckle matching matrix between the subsequent frames and the first frame. From this matrix, the inter-frame feature matching results can be obtained. In this way, the inter-frame speckle tracking is completed. On this basis, the results of this method are compared with the matching results based on the convolutional neural network. The experimental results show that the proposed method has higher matching accuracy. In particular, the accuracy of the MNIST handwritten data set has reached more than 90%.

Study on Optimization Method of Visual Odometry Based on Feature Matching

The mismatching of image features affects the calculation of the fundamental matrix and then leads to poor estimation accuracy of SLAM visual odometry. Aiming at the above problems, a visual odometry optimization method based on feature matching is proposed. Firstly, the initial matching set is roughly filtered by the minimum distance threshold method, and then, the relative transformation relationship between images is calculated by the RANSAC algorithm. If it conforms to the transformation relationship, it is an interior point. The iteration result with most interior points is the correct matching result. Then, the homography transformation between images is calculated, and the fundamental matrix is calculated by it. The interior points are determined by epipolar geometric constraints, and the fundamental matrix with the most interior points is obtained. Finally, the effects of the visual odometry optimization algorithm are verified by the TUM data set from two aspects: feature matching and fundamental matrix calculation. The experimental results show that an improved feature matching algorithm can effectively remove mismatched feature points while improving the operation efficiency. At the same time, the accuracy of feature point matching is increased by 15.8%. The fundamental matrix estimation algorithm not only improves the calculation accuracy of the fundamental matrix but also increases the interior point rate by 11.9%. A theoretical basis for improving the accuracy estimation of visual odometry will be provided.

Classification and model reconstruction method of non‐cooperative multifunctional radar waveform unit

AbstractThere are many variations in the form of multifunctional radar signals. At present, the problem associated with the highest concern in the field of electronic reconnaissance is the inversion of its working mode from the reconnaissance data. A method is proposed for waveform unit classification and model reconstruction using the non‐cooperatively extracted waveform units as input data based on the hierarchical structure of multifunctional radars. The method performs multiparametric matching on waveform units subject to the constraint of the match level to obtain the similarity measure between waveform units; it then recursively expands the waveform unit pairing score matrix to complete the classification of the waveform units. Further, based on similar waveform units, the matching state matrix of the waveform unit model can be reconstructed. The feasibility and performance of the proposed method are verified by setting up typical multitype simulation experiments. The experimental results show that the proposed method can complete the classification of waveform units in the small‐data content and extensive noise intensity cases and supports the reconstruction of waveform unit models with low errors.

VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration

3D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points. To handle this problem, a widely adopted strategy is to estimate the relative pose based only on some accurate correspondences, which is achieved by building correspondences on the identified inliers or by selecting reliable ones. However, these approaches are usually complicated and time-consuming. By contrast, the virtual point-based methods learn the virtual corresponding points (VCPs) for all source points uniformly without distinguishing the outliers and the inliers. Although this strategy is time-efficient, the learned VCPs usually exhibit serious collapse degeneration due to insufficient supervision and the inherent distribution limitation. In this paper, we propose to exploit the best of both worlds and present a novel robust 3D point cloud registration framework. We follow the idea of the virtual point-based methods but learn a new type of virtual points called rectified virtual corresponding points (RCPs), which are defined as the point set with the same shape as the source and with the same pose as the target. Hence, a pair of consistent point clouds, i.e. source and RCPs, is formed by rectifying VCPs to RCPs (VRNet), through which reliable correspondences between source and RCPs can be accurately obtained. Since the relative pose between source and RCPs is the same as the relative pose between source and target, the input point clouds can be registered naturally. Specifically, we first construct the initial VCPs by using an estimated soft matching matrix to perform a weighted average on the target points. Then, we design a correction-walk module to learn an offset to rectify VCPs to RCPs, which effectively breaks the distribution limitation of VCPs. Finally, we develop a hybrid loss function to enforce the shape and geometry structure consistency ...

P^3-Net: Part Mobility Parsing from Point Cloud Sequences via Learning Explicit Point Correspondence

Understanding an articulated 3D object with its movable parts is an essential skill for an intelligent agent. This paper presents a novel approach to parse 3D part mobility from point cloud sequences. The key innovation is learning explicit point correspondence from a raw unordered point cloud sequence. We propose a novel deep network called P^3-Net to parallelize trajectory feature extraction and point correspondence establishment, performing joint optimization between them. Specifically, we design a Match-LSTM module to reaggregate point features among different frames by a point correspondence matrix, a.k.a. the matching matrix. To obtain this matrix, an attention module is proposed to calculate the point correspondence. Moreover, we implement a Gumbel-Sinkhorn module to reduce the many-to-one relationship for better point correspondence. We conduct comprehensive evaluations on public benchmarks, including the motion dataset and the PartNet dataset. Results demonstrate that our approach outperforms SOTA methods on various 3D parsing tasks of part mobility, including motion flow prediction, motion part segmentation, and motion attribute (i.e. axis & range) estimation. Moreover, we integrate our approach into a robot perception module to validate its robustness.

End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration

Even though considerable progress has been made in deep learning-based 3D point cloud processing, how to obtain accurate correspondences for robust registration remains a major challenge because existing hard assignment methods cannot deal with outliers naturally. Alternatively, the soft matching-based methods have been proposed to learn the matching probability rather than hard assignment. However, in this paper, we prove that these methods have an inherent ambiguity causing many deceptive correspondences. To address the above challenges, we propose to learn a partial permutation matching matrix, which does not assign corresponding points to outliers, and implements hard assignment to prevent ambiguity. However, this proposal poses two new problems, i.e. existing hard assignment algorithms can only solve a full rank permutation matrix rather than a partial permutation matrix, and this desired matrix is defined in the discrete space, which is non-differentiable. In response, we design a dedicated soft-to-hard (S2H) matching procedure within the registration pipeline consisting of two steps: solving the soft matching matrix (S-step) and projecting this soft matrix to the partial permutation matrix (H-step). Specifically, we augment the profit matrix before the hard assignment to solve an augmented permutation matrix, which is cropped to achieve the final partial permutation matrix. Moreover, to guarantee end-to-end learning, we supervise the learned partial permutation matrix but propagate the gradient to the soft matrix instead. Our S2H matching procedure can be easily integrated with existing registration frameworks, which has been verified in representative frameworks including DCP, RPMNet, and DGR. Extensive experiments have validated our method, which creates a new state-of-the-art performance.

Self-feature-based point cloud registration method with a novel convolutional Siamese point net for optical measurement of blade profile

Currently, non-contact optical measurement technologies have shown prominent power in measuring blade profiles. One of the critical issues is how to align measured point clouds in different viewpoints into an entire profile. However, extracting efficient features for registration is difficult due to the thin-walled and twisted spatial freeform surfaces of blades. Besides, various densities and small overlaps between two adjacent point cloud data also increase the difficulty of registration. To overcome these issues, in this paper, laying on the foundation of a developed multi-axis motion system, we present a novel and general framework titled convolutional Siamese point net (CSPN) for partial-to-partial point cloud registration. Our network mainly consists of three parts: feature extraction, matching matrix computation and singular value decomposition (SVD). To make a balance between low-level and high-level semantics, we design a pyramidal architecture to learn the multiscale features of each point. In matching matrix computation, both feature space and coordinate space are utilized. Also, a novel attention mechanism is proposed to deal with the conflicts between matching matrices obtained by feature space and coordinate space. Experimental results demonstrate the feasibility and good practical application prospect of this method.

A Dynamic Task Allocation Algorithm for Heterogeneous UUV Swarms.

Aiming at the task allocation problem of heterogeneous unmanned underwater vehicle (UUV) swarms, this paper proposes a dynamic extended consensus-based bundle algorithm (DECBBA) based on consistency algorithm. Our algorithm considers the multi-UUV task allocation problem that each UUV can individually complete multiple tasks, constructs a “UUV-task” matching matrix and designs new marginal utility, reward and cost functions for the influence of time, path and UUV voyage. Furthermore, in view of the unfavorable factors that restrict the underwater acoustic communication range between UUVs in the real environment, our algorithm complete dynamic task allocation of UUV swarms with optimization in load balance indicator by the update of the UUV individual and the task completion status in the discrete time stage. The performance indicators (including global utility and task completion rate) of the dynamic task allocation algorithm in the scenario with communication constraints can be well close to the static algorithm in the ideal scenario without communication constraints. The simulation experiment results show that the algorithm proposed in this paper can quickly and efficiently obtain the dynamic and conflict-free task allocation assignment of UUV swarms with great performance.

Searching Dense Point Correspondences via Permutation Matrix Learning

Although 3D point cloud data has received widespread attentions as a general form of 3D signal expression, applying point clouds to the task of dense correspondence estimation between 3D shapes has not been investigated widely. Furthermore, even in the few existing 3D point cloud-based methods, an important and widely acknowledged principle, i.e . one-to-one matching, is usually ignored. In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the one-to-one principle fundamentally. Note that the classical solutions of this assignment problem are always non-differentiable, which is fatal for deep learning frameworks. Thus we design a special matching module, which solves a doubly stochastic matrix at first and then projects this obtained approximate solution to the desired permutation matrix. Moreover, to guarantee end-to-end learning and the accuracy of the calculated loss, we calculate the loss from the learned permutation matrix but propagate the gradient to the doubly stochastic matrix directly which bypasses the permutation matrix during the backward propagation. Our method can be applied to both non-rigid and rigid 3D point cloud data and extensive experiments show that our method achieves state-of-the-art performance for dense correspondence learning.

Personalized content recommendation in online health communities

PurposeRecommending suitable content for users of online health communities (OHCs) is critical for overcoming information overload problem and facilitate medical decision making, but remains not fully investigated. This study aims to provide a content recommendation approach to automatically match valuable health-related information for OHC members.Design/methodology/approachA framework of health-related content recommendation was proposed by leveraging rich social information in online communities. The authors constructed user influence relationship (UIR) utilizing users' interaction records, user profiles and user-generated content. The initial user rating matrix and the user post matching matrix were then created by analyzing text content of posts. Finally, the user rating matrix and the recommended content were generated for community members. Datasets were collected from an OHC to evaluate the effectiveness of the proposed approach.FindingsThe experimental results revealed that the proposed method statistically outperformed baseline models in content recommendation for users of OHCs.Research limitations/implicationsThe incorporation of social information can significantly enhance the performance of content recommendation in OHCs. The user post matching degree based on text analysis can improve the effectiveness of recommendation.Practical implicationsThis study potentially contributes to the social support exchange and medical decision making of community members and the sustainable prosperity of OHCs.Originality/valueThis study proposes a novel social content recommendation method for online health consumers based on UIRs by leveraging social information in OHCs. The results indicate the significance of social information in content recommendation of healthcare social media.

An Automated Recognition of Work Activity in Industrial Manufacturing Using Convolutional Neural Networks

The automated assessment and analysis of employee activity in a manufacturing enterprise, operating in accordance with the concept of Industry 4.0, is essential for a quick and precise diagnosis of work quality, especially in the process of training a new employee. In the case of industrial solutions, many approaches involving the recognition and detection of work activity are based on Convolutional Neural Networks (CNNs). Despite the wide use of CNNs, it is difficult to find solutions supporting the automated checking of work activities performed by trained employees. We propose a novel framework for the automatic generation of workplace instructions and real-time recognition of worker activities. The proposed method integrates CNN, CNN Support Vector Machine (SVM), CNN Region-Based CNN (Yolov3 Tiny) for recognizing and checking the completed work tasks. First, video recordings of the work process are analyzed and reference video frames corresponding to work activity stages are determined. Next, work-related features and objects are determined using CNN with SVM (achieving 94% accuracy) and Yolov3 Tiny network based on the characteristics of the reference frames. Additionally, matching matrix between the reference frames and the test frames using mean absolute error (MAE) as a measure of errors between paired observations was built. Finally, the practical usefulness of the proposed approach by applying the method for supporting the automatic training of new employees and checking the correctness of their work done on solid fuel boiler equipment in a manufacturing company was demonstrated. The developed information system can be integrated with other Industry 4.0 technologies introduced within an enterprise.

Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit

This paper addresses the taxi fleet dispatch problem, which is critical for many transport service platforms such as Uber, Lyft, and Didi Chuxing. We focus on maximizing the revenue and profit a taxi platform can generate through the dispatch approaches designed with various criteria. We consider determining the proportion of taxi fleets to different destination zones given the expected rewards from the future states following the distribution decisions learned through reinforcement learning (RL) algorithms. We also take into account more straightforward greedy algorithms that look ahead fewer decision time steps in the future. Our dispatch decision algorithms commonly leverage contextual information and heuristics using a data structure called Contextual Matching Matrix (CMM). The key contribution of our paper is the insight into the trade-off between different design criteria. Primarily, through the evaluation with actual taxi operation data offered by Seoul Metropolitan Government, we challenge the natural expectation that the RL-based approaches yield the best result by showing that a lightweight greedy algorithm can have a competitive advantage. Moreover, we break the norm of dissecting the service area into sub-zones and show that matching passengers beyond arbitrary boundaries generates significantly higher operating income and profit.

Meter-wave MIMO radar height measurement method based on adaptive beamforming

Meter-wave MIMO radar has multipath effects in the low elevation angle area, seriously affecting the target elevation estimation performance. Therefore, the mainstream height measurement methods are generalized MUSIC and maximum likelihood estimation algorithms that do not require decoherence processing. Still, their complexity is high, and their performance is poor at low signal-to-noise ratios. Compressed sensing and time-reversal have been applied in height measurement, with good accuracy but high complexity. To quickly and accurately obtain the height parameters of the target, this paper proposes a low-elevation height measurement method for meter-wave MIMO radar based on adaptive beamforming. First, we analyze and simplify the signal model; then use the channel matching matrix to eliminate the influence of the reflected wave on the direct wave; then use the target direct wave direction and the reflected wave direction as the interference direction, and perform adaptive beamforming on it to obtain the target elevation angle value. Furthermore, the dimension reduction matrix is used to reduce the dimensionality of the received data signal. Then an algorithm suitable for undulating terrain and inclined ground is proposed and simulated. In addition, this paper gives the complexity of the proposed algorithm and the comparison algorithm. At last, in terms of the signal-to-noise ratio, the number of snapshots, the number of array elements, and the elevation angle, many simulation experiments are carried out to compare the proposed height measurement algorithm with the mainstream height measurement algorithm. The simulation results show that the accuracy and robustness of the proposed height measurement algorithm are the best under these factors.

Multi-features guidance network for partial-to-partial point cloud registration

To eliminate the problems of large dimensional differences, big semantic gap, and mutual interference caused by hybrid features, in this paper, we propose a novel Multi-Features Guidance Network for partial-to-partial point cloud registration(MFG). The proposed network mainly includes four parts: keypoints' feature extraction, correspondences searching, correspondences credibility computation, and SVD, among which correspondences searching and correspondence credibility computation are the cores of the network. Unlike the previous work, we utilize the shape features and the spatial coordinates to guide correspondences search independently and fusing the matching results to obtain the final matching matrix. In the correspondences credibility computation module, based on the conflicted relationship between the features matching matrix and the coordinates matching matrix, we score the reliability for each correspondence, which can reduce the impact of mismatched or non-matched points. Experimental results show that our network outperforms the current state-of-the-art while maintaining computational efficiency.

New process function-based selection and configuration methodology for Process Equipment Assemblies (PEAs) exemplified on the unit operation distillation

Process Equipment Assemblies (PEA) are pre-designed equipment sets which are selected instead of time-consuming tailor-made design. This paper introduces a new method for the selection and configuration of PEAs exemplified on the unit operation distillation. First step of the new methodology is the selection of the most suitable technology applying matching matrices. The matching matrix required for selecting a suitable distillation technology is introduced. Next a process function-based planning approach is executed using so called master block flowcharts (MBF). These technology specific flowcharts contain all possible process functions required for any potential separation task and contain the technology specific main function and technology independent process functions. Considering process boundary conditions and functions already available in the infrastructure, the MBF is reduced to the functions required for the process. Next, concrete PEAs are selected starting with the main function where the separation of the fluids takes place using the PEA operating range as the main selection criterion. A tool required to determine the operating range of a distillation column is demonstrated. Finally, the PEAs for auxiliary functions are selected from a databank.

Convolutional Neural Network with an Elastic Matching Mechanism for Time Series Classification

Recently, some researchers adopted the convolutional neural network (CNN) for time series classification (TSC) and have achieved better performance than most hand-crafted methods in the University of California, Riverside (UCR) archive. The secret to the success of the CNN is weight sharing, which is robust to the global translation of the time series. However, global translation invariance is not the only case considered for TSC. Temporal distortion is another common phenomenon besides global translation in time series. The scale and phase changes due to temporal distortion bring significant challenges to TSC, which is out of the scope of conventional CNNs. In this paper, a CNN architecture with an elastic matching mechanism, which is named Elastic Matching CNN (short for EM-CNN), is proposed to address this challenge. Compared with the conventional CNN, EM-CNN allows local time shifting between the time series and convolutional kernels, and a matching matrix is exploited to learn the nonlinear alignment between time series and convolutional kernels of the CNN. Several EM-CNN models are proposed in this paper based on diverse CNN models. The results for 85 UCR datasets demonstrate that the elastic matching mechanism effectively improves CNN performance.

SOIDP: Predicting Interlayer Links in Multiplex Networks

Many link prediction algorithms regarding single-layer social networks have been proposed, and however, how to predict interlayer links in multiplex social networks is still in the initial stage. In fact, the prediction of interlayer links in multiplex networks is of great significance, which is closely related to network security, product recommendation, social network mining, and so forth. Given that many social networks are sparse and the number of the first-order common matched neighbors (CMNs) is very few, it is not sufficient to implement link prediction only based on the first-order CMNs. Moreover, many social networks have scale-free property, leading to the roles of CMNs in link prediction which are significantly different. In doing so, we propose a second-order iterative degree penalty (SOIDP) algorithm to predict interlayer links in multiplex networks, in which the information of the first- and second-order CMNs is integrally considered, as well as a degree penalty mechanism is introduced to give larger weight to the CMNs with fewer connections. In particular, to solve the problem of cumulative error in the iterative process, we demonstrate that the interlayer links can be predicted by directly calculating the matching degree matrix without iteration. Experiments on real-world networks show that the performance of SOIDP algorithm in predicting interlayer links is always better than the baseline algorithms, and the accuracy is increased 10% at least. For synthetic networks, the improvement is also very surprising when networks are rather sparse.

A classification model for formal high-end menswear retailers in Italy

PurposeDespite menswear is gaining a significant relevance in terms of retail sales, it represents a neglected topic within the academic literature. Therefore, this paper aims at providing a better understanding of the formal menswear market by developing a tailor-made classification model for the identification of retailers' clusters and at discovering the critical success factors (CSFs).Design/methodology/approachThis research looked at most formal high-end menswear retailers in Italy adopting a methodology based on the Analytic Hierarchy Process and multiple case studies. Thirty interviews were conducted with experts, managers and shopkeepers from case studies.FindingsThe study develops for the first time a classification framework of formal high-end menswear retailers and a matching matrix to jointly analyse retailers' clusters and customer profiles in Italy. The results identify the CSFs pursued by menswear retailers and highlight the existence of four clusters of retailers (Differentiated Fashion Firms; Formal Menswear Leaders; Tailoring Firms and Luxury Brands) and seven customer profiles (Habitual Professionals, Special Events, Young People, Occasional Professionals, Foreigners, VIPs and Fashionistas).Originality/valueThe formal high-end menswear represents one of the most traditional Italian heritage markets while being almost ignored in the academic literature. Thus, the value of this research lays in deepening our understanding of this market from the retailers' perspective, by providing for the first time a taxonomy of its players and contributing to identifying the CSFs and the main customer profiles.

Valley to charge current conversion in graphene linear defects

The conduction properties of a grain boundary junction with Fermi velocity mismatch are analyzed. We provide a generalization of the Dirac Hamiltonian model taking into account the Fermi velocity gradient at the interface. General boundary conditions for the scattering problem are derived within the framework of the matching matrix method. We show that the scattering properties of the interface, as predicted by the theory, strongly depend on the boundary conditions used. We demonstrate that when the valley degeneracy is broken a charge current is established at the grain boundary interface. These findings provide the working principle of a valley to charge current converter, which is relevant for the emergent field of valleytronics.