Search results

Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In order to solve such problems, the purpose of this paper is to propose a novel image super-resolution algorithm based on improved generative adversarial networks (GANs) with Wasserstein distance and gradient penalty.

The proposed algorithm first introduces the conventional GANs architecture, the Wasserstein distance and the gradient penalty for the task of image super-resolution reconstruction (SRWGANs-GP). In addition, a novel perceptual loss function is designed for the SRWGANs-GP to meet the task of image super-resolution reconstruction. The content loss is extracted from the deep model’s feature maps, and such features are introduced to calculate mean square error (MSE) for the loss calculation of generators.

To validate the effectiveness and feasibility of the proposed algorithm, a lot of compared experiments are applied on three common data sets, i.e. Set5, Set14 and BSD100. Experimental results have shown that the proposed SRWGANs-GP architecture has a stable error gradient and iteratively convergence. Compared with the baseline deep models, the proposed GANs models have a significant improvement on performance and efficiency for image super-resolution reconstruction. The MSE calculated by the deep model’s feature maps gives more advantages for constructing contour and texture.

Compared with the state-of-the-art algorithms, the proposed algorithm obtains a better performance on image super-resolution and better reconstruction results on contour and texture.

Revenue management (RM) is a significant technique to improve revenue with limited resources. With the macro environment of dramatically increasing transit capacity and rapid railway transport development in China, it is necessary to involve the theory of RM into the operation and decision of railway passenger transport.

This paper proposes the theory and framework of generalized RM of railway passenger transport (RMRPT), and the thoughts and methods of the main techniques in RMRPT, involving demand forecasting, line planning, inventory control, pricing strategies and information systems, are all studied and elaborated. The involved methods and techniques provide a sequential process to help with the decision-making for each stage of RMRPT. The corresponding techniques are integrated into the information system to support practical businesses in railway passenger transport.

The combination of the whole techniques devotes to railway benefit improvement and transit resource utilization and has been applied into the practical operation and organization of railway passenger transport.

The development of RMRPT would provide theoretical and technical support for the improvement of service quality as well as railway benefits and efficiency.

Global positioning system (GPS) kinematic positioning suffers from performance degradation in constrained environments such as urban canyons, which then restricts the application of high-precision vehicle positioning and navigation within the city. In December 2012, the BeiDou Navigation Satellite System (BDS) regional service was announced, and the combined BDS/GPS kinematic positioning has been enabled in the Asia-Pacific area. Previous studies have mainly focused on the performance evaluations of combined BDS/GPS static positioning. Not much work has been performed for kinematic vehicle positioning under constrained observation conditions. This study aims to analyze the performance of BDS/GPS kinematic vehicle positioning in various conditions.

In this study, three vehicle experiments under three observation conditions, an open suburban area, a less dense non-central urban area and a dense central urban area, are investigated using both the code-based differential global navigation satellite system (DGNSS) and phase-based real-time kinematic (RTK) modes. The comparison between combined BDS/GPS and GPS-only vehicle positioning solutions is conducted in terms of positioning availability and positioning precision.

Numerical results show that the combined BDS/GPS system significantly outperforms the GPS-only system under poor observation conditions, whereas the improvement was less significant under good observation conditions.

Thus, this paper studies the performance of combined BDS/GPS kinematic relative positioning under various observation conditions.

Current virtual simulation platforms provide various tools to generate non-immersive simulation processes purposefully in different domains. The generated simulation processes are adopted for analysis, presentation, demonstration and verification. In the virtual maintenance domain, this intuitive and visual method has benefitted product maintainability design and improvement. Generating an ideal and reasonable non-immersive virtual maintenance simulation is always time-consuming because of the complicated human operations and logical relationships involved. This study aims to propose a semiautomatic approach to increase efficiency in non-immersive virtual maintenance simulation implementation.

The methodology analyzes the general catalogs of common maintenance tasks and explores the corresponding secondary development approaches of simulation tools that can achieve motion simulation in virtual environments, by focusing on the diversity, complexity and uncertainty in non-immersive virtual simulation process generation. Afterward, a single virtual human motion can be generated by controlling the parameters and indices of the simulation tools. Subsequently, all of the generated single motions are connected logically to simulate the entire maintenance process.

Instead of selecting various tools, such as that in a traditional method, the proposed methodology analyzes and integrates the necessary basic parameters considering the characteristics of virtual maintenance simulation for a target maintenance activity.

The user can control the predefined parameters to generate the simulation combining several other simple operations in virtual environments. Consequently, the methodology decreases simulation tool selection and logic consideration and increases efficiency to a certain extent in non-immersive virtual maintenance simulation generation.

The conventional pedestrian detection algorithms lack in scale sensitivity. The purpose of this paper is to propose a novel algorithm of self-adaptive scale pedestrian detection, based on deep residual network (DRN), to address such lacks.

First, the “Edge boxes” algorithm is introduced to extract region of interests from pedestrian images. Then, the extracted bounding boxes are incorporated to different DRNs, one is a large-scale DRN and the other one is the small-scale DRN. The height of the bounding boxes is used to classify the results of pedestrians and to regress the bounding boxes to the entity of the pedestrian. At last, a weighted self-adaptive scale function, which combines the large-scale results and small-scale results, is designed for the final pedestrian detection.

To validate the effectiveness and feasibility of the proposed algorithm, some comparison experiments have been done on the common pedestrian detection data sets: Caltech, INRIA, ETH and KITTI. Experimental results show that the proposed algorithm is adapted for the various scales of the pedestrians. For the hard detected small-scale pedestrians, the proposed algorithm has improved the accuracy and robustness of detections.

By applying different models to deal with different scales of pedestrians, the proposed algorithm with the weighted calculation function has improved the accuracy and robustness for different scales of pedestrians.

Virtual maintenance simulation is of great importance to help designers find and avoid design problems. During its simulation phase, besides the high precision requirement, collision detection must be suitable for all irregular objects in a virtual maintenance environment. Therefore, in this paper, a collision detection approach is proposed based on encapsulation for irregular objects in the virtual maintenance environment.

First, virtual maintenance simulation characteristics and several commonly used bounding boxes methods are analyzed, which motivates the application of encapsulation theory. Based on these, three different encapsulation methods are oriented to the needs of simulation, including encapsulation of rigid maintenance objects, flexible maintenance objects and maintenance personnel. In addition, to detecting collisions accurately, this paper divides the detection process into two stages. That is, in the first stage, a rough detection is carried out and then a tiny slice space is constructed to generate corresponding capsule groups, which will be redetected in the secondary stage. At last, several case studies are applied to illustrate the performance of the methodology.

The automatic construction algorithm for bounding boxes can be adapted to all forms of objects. The number of detection primitives are greatly reduced. It introduces the reachable space of the human body in maintainability as the collision search area.

The advantages of virtual maintenance simulation could also be advantageous in the industry with further studies. The paper believes this study is of particular interest to the readers of your journal.

Based on virtual maintenance, this paper aims to propose a time prediction method of assembly and disassembly (A&D) actions of product maintenance process to enhance existing methods’ prediction accuracy, applicability and efficiency.

First, a framework of A&D time prediction model is constructed, which describes the time prediction process in detail. Then, basic maintenance motions which can comprise a whole A&D process are classified into five categories: body movement, working posture change, upper limb movement, operation and grasp/placement. A standard posture library is developed based on the classification. Next, according to motion characteristics, different time prediction methods for each motion category are proposed based on virtual maintenance simulation, modular arrangement of predetermined time standard theory and the statistics acquired from motion experiment. Finally, time correction based on the quantitative evaluation method of motion time influence factors is studied so that A&D time could be predicted with more accuracy.

Case study of time prediction of products’ various A&D processes is conducted by implementing the proposed method. The prediction process of diesel cooling fan disassemble time is presented in detail. Through comparison, the advantages and effectiveness of the method are demonstrated.

This paper proposes a more accurate, efficient and applicable product A&D time prediction method. It can help designers predict A&D time of a product maintenance accurately in early design phases without a physical prototype. It can also provide basis for the verification of maintainability, the balance of the design of product structure and system layout.

The purpose of this paper is to join AA5052 to AISI 1006 steel sheets using the spot friction forming technique.

A steel sheet was pre-holed with a diameter of 4.8 mm and pre-threaded with a single internal M6 thread. Lap joint configuration was used so that the aluminium specimen was put over steel. A rotating tool with a 10 mm diameter was used for the joining process. A Taguchi method was used to design three process parameters (plunging tool depth, rotating speed and preheating time), with three levels for each parameter. The effect of the process parameters on the joint shear strength was analysed. The macrostructure, microstructure and scanning electron microscope of the joint were investigated. The temperature distribution during the joining process was recorded.

The formed aluminium was extruded through the steel hole and penetrated through the thread slot. A mechanical interlock was achieved between the extruded aluminium and the steel. The plunging depth of the tool exhibited a significant effect on the joint shear strength. The joint efficiency increased gradually as the plunging depth increased. Two modes of failure were found shear and pull-out. The maximum temperature during the process reached 50 per cent of aluminium’s melting point.

For the first time, AA5052 was joined with AISI 1006 steel using a friction spot forming technique with an excellent joint efficiency.

As Chinese imported cross-border e-commerce has entered a stage of rapid development, the problem of consumer shopping risk is increasingly prominent and the crisis of consumer trust is intensified. The theory of establishing consumer trust in traditional online shopping can no longer meet the need of cross-border context.

The researchers used the methods of network logs and grounded theory. The data collection and analysis are conducted on consumer comments from Tmall Global, NetEase Koala and JD Worldwide in the product comment area. This article explored and extracted the moderating variables of consumer perceived risk and cross-border characteristics in cross-border e-commerce. Based on the theory of “perceived risk – consumer trust – consumer purchase decision – making,” this article deduced mechanism of consumer dynamic trust based on the whole process of cross-border e-commerce transaction.

In the prepurchase, purchase and postpurchase stages of cross-border e-commerce transactions, consumers' perceived cognitive risk, transaction risk and utility risk are moderated by the cultural distance, geographical distance and institutional distance caused by the cross-border transaction subjects. On this basis, the preinfluence factors of trust in each transaction stage are synthesized to respectively influence the establishment of cognitive trust, emotional trust and behavioral trust, so as to affect consumers to make the order payment, confirm receipt and praise repurchase decisions. At the same time, with the advance of prepurchase, purchase and postpurchase transactions in cross-border online shopping, consumer trust presents a dynamic evolutionary path of “cognitive trust – emotional trust – behavioral trust.”

This article expands the application context of the theory of consumer rational behavior from traditional online shopping to the context of cross-border online shopping and expands the scope of interpretation of the theory of consumer rational behavior. This article also supplements the theoretical gaps in the dynamic evolution of consumer trust in cross-border online shopping, enriches the decision-making process model of consumers in the context of cross-border online shopping and provides new ideas for follow-up research.

Visual tracking technology enables industrial robots interacting with human beings intelligently. However, due to the complexity of the tracking problem, the accuracy of visual target tracking still has great space for improvement. This paper aims to propose an accurate visual target tracking method based on standard hedging and feature fusion.

For this study, the authors first learn the discriminative information between targets and similar objects in the histogram of oriented gradients by feature optimization method, and then use standard hedging algorithms to dynamically balance the weights between different feature optimization components. Moreover, they penalize the filter coefficients by incorporating spatial regularization coefficient and extend the Kernelized Correlation Filter for robust tracking. Finally, a model update mechanism to improve the effectiveness of the tracking is proposed.

Extensive experimental results demonstrate the superior performance of the proposed method comparing to the state-of-the-art tracking methods.

Improvements to existing visual target tracking algorithms are achieved through feature fusion and standard hedging algorithms to further improve the tracking accuracy of robots on targets in reality.