Search results

In autonomous driving, the inherent sparsity of point clouds often limits the performance of object detection, while existing multimodal architectures struggle to meet the real-time requirements for 3D object detection. Therefore, the main purpose of this paper is to significantly enhance the detection performance of objects, especially the recognition capability for small-sized objects and to address the issue of slow inference speed. This will improve the safety of autonomous driving systems and provide feasibility for devices with limited computing power to achieve autonomous driving.

BRTPillar first adopts an element-based method to fuse image and point cloud features. Secondly, a local-global feature interaction method based on an efficient additive attention mechanism was designed to extract multi-scale contextual information. Finally, an enhanced multi-scale feature fusion method was proposed by introducing adaptive spatial and channel interaction attention mechanisms, thereby improving the learning of fine-grained features.

Extensive experiments were conducted on the KITTI dataset. The results showed that compared with the benchmark model, the accuracy of cars, pedestrians and cyclists on the 3D object box improved by 3.05, 9.01 and 22.65%, respectively; the accuracy in the bird’s-eye view has increased by 2.98, 10.77 and 21.14%, respectively. Meanwhile, the running speed of BRTPillar can reach 40.27 Hz, meeting the real-time detection needs of autonomous driving.

This paper proposes a boosting multimodal real-time 3D object detection method called BRTPillar, which achieves accurate location in many scenarios, especially for complex scenes with many small objects, while also achieving real-time inference speed.

This study aims to explore the characteristics of the Love wave propagation through a heterogeneous hydrogel layer bounded to a functionally graded PFRC substrate while determining the displacement and electric potential in a di-electrically faintly conducting, mechanically compliant interface.

In order to calculate the value of response variables, the Wave mode method has been used. The governing modeled equations are non-homogeneous. The analytical solution has been obtained by deploying the boundary conditions.

The effect of thickness on the field variables for different values of variation parameter, mechanical constant of proportionality, electrical constant of proportionality and volume fraction of the PFRC substrate is examined for both, electrically open and short cases.

To the best of authors' knowledge, no attempt has been made to analyze the propagation characteristics of Love wave through the heterogeneous hydrogel Layer bedded over the functionally graded piezoelectric fiber-reinforced composites substrate.

Accurate prediction of port cargo throughput within Free Trade Zones (FTZs) can optimize resource allocation, reduce environmental pollution, enhance economic benefits and promote sustainable transportation development.

This paper introduces a novel self-adaptive grey multivariate prediction modeling framework (FARDCGM(1,N)) to forecast port cargo throughput in China, addressing the challenges posed by mutations and time lag characteristics of time series data. The model explores policy-driven mechanisms and autoregressive time lag terms, incorporating policy dummy variables to capture deviations in system development trends. The inclusion of autoregressive time lag terms enhances the model’s ability to describe the evolving system complexity. Additionally, the fractional-order accumulative generation operation effectively captures data features, while the Grey Wolf Optimization algorithm determines optimal nonlinear parameters, enhancing the model’s robustness.

Verification using port cargo throughput forecasts for FTZs in Shanghai, Guangdong and Zhejiang provinces demonstrates the FARDCGM(1,N) model’s remarkable accuracy and stability. This innovative model proves to be an excellent forecasting tool for systematically analyzing port cargo throughput under external interventions and time lag effects.

A novel self-adaptive grey multivariate modeling framework, FARDCGM(1,N), is introduced for accurately predicting port cargo throughput, considering policy-driven impacts and autoregressive time-lag effects. The model incorporates the GWO algorithm for optimal parameter selection, enhancing adaptability to sudden changes. It explores the dual role of policy variables in influencing system trends and the impact of time lag on dynamic response rates, improving the model’s complexity handling.

Achieve a lightweight design for a bogie frame while ensuring it meets strength requirements by conducting static and fatigue strength assessments and optimizing plate thickness.

Establish a finite element model and determine loads according to the UIC615-4 standard. Fatigue strength assessments are conducted using the structural stress method. Size optimization for plate thickness is performed with constraints on maximum static strength and total fatigue damage of the weld. Multi-objective optimization design is carried out using Isight software, with sensitivity analysis to identify key plates. The neural network model is chosen as the approximation model, and the NSGA-II multi-objective genetic algorithm is selected as the optimization algorithm.

The strength assessment reveals a significant margin. Through size optimization of plate thickness with constraints on static strength and fatigue damage, the frame’s mass is reduced by 9.59%, achieving a lightweight design while meeting strength requirements.

In many lightweight studies, the inclusion of fatigue assessment through the structural stress method in the optimization process is often overlooked. However, this paper addresses this gap by incorporating it and providing a detailed operational procedure. Such consideration holds reference value for the design of lightweight optimization, especially when fatigue strength is a critical consideration.

During the cooperation process between prefabricated building construction enterprises (PBCEs) and Internet platforms (IPs), the sentiments of both parties influence their behavioral strategies. They are the key to improving the informatization and operational efficiency of the prefabricated building industry chain (PBIC).

This paper introduces mental accounting theory and rank-dependent expected utility theory to construct the MA-RDEU game model, exploring the evolutionary mechanism between sentiment and behavioral strategies of PBCEs and IPs.

The study indicates that (1) a mixed strategy equilibrium can be achieved when both parties have no sentiments. (2) PBCEs and IPs are more likely to achieve an optimal equilibrium for cooperation if the latter is optimistic. In contrast, pessimism may lead both parties to prioritize self-interest when only one party has a sentiment. (3) The combined impact of sentiments and behavioral strategies on decision-making is significant: the influence of sentiments from PBCEs or IPs on the optimal strategy for achieving cooperation is contingent upon the behavioral strategies of the other party; different behavioral strategies of IPs or PBCEs can have varying effects on sentiments when both parties have sentiments. (4) The influence of external factors on the sentiments and behavior strategies of PBCEs and IPs is apparent. PBCEs and IPs should concurrently consider the combined influence of external factors and sentiments to contribute to the realization of cooperation between the two parties. Additionally, government supervision is an effective means to restrain “free-riding” behavior.

Finally, based on the above conclusions, the paper proposes measures to improve the construction of service-oriented IPs and establish a mechanism for monitoring and adjusting risk sentiments. Meanwhile, this paper also indicates that under the combined effect of the government, PBCEs and IPs, the influence of external factors on sentiments can be maintained within a controllable scope and the risks of uncertainty can be mitigated.

This paper aims to investigate the cooperative governance mechanisms for personal information security, which can help enrich digital governance research and provide a reference for the formulation of protection policies for personal information security.

This paper constructs an evolutionary game model consisting of regulators, digital enterprises and consumers, which is combined with the simulation method to examine the influence of different factors on personal information protection and governance.

The results reveal seven stable equilibrium strategies for personal information security within the cooperative governance game system. The non-compliant processing of personal information by digital enterprises can damage the rights and interests of consumers. However, the combination of regulatory measures implemented by supervisory authorities and the rights protection measures enacted by consumers can effectively promote the self-regulation of digital enterprises. The reputation mechanism exerts a restricting effect on the opportunistic behaviour of the participants.

The authors focus on the regulation of digital enterprises and do not consider the involvement of malicious actors such as hackers, and the authors will continue to focus on the game when assessing the governance of malicious actors in subsequent research.

This study's results enhance digital governance research and offer a reference for developing policies that protect personal information security.

This paper builds an analytical framework for cooperative governance for personal information security, which helps to understand the decision-making behaviour and motivation of different subjects and to better address issues in the governance for personal information security.

The sustainable development of the platform economy has been hindered by the absence and alienation of platform corporate social responsibility. Previous studies have mainly focused on the contents and governance models for platform corporate social responsibility. This study seeks to explore which strategy participants choose in the governance of platform corporate social responsibility and their influencing factors.

Using a platform ecosystem approach, a quadrilateral evolutionary game model was developed, and the stabilities of subjects’ behavioral strategies and their combinations in various scenarios were analyzed. Additionally, the effects of key parameters on the system’s evolutionary path were simulated.

The ideal steady state system is achieved when platform enterprises, complementors and consumers adopt positive strategies while the government adopts lax regulation. Moreover, the evolutionary strategies of the subjects are influenced by several factors, including the participation costs of governance, the rewards and punishments imposed by platform enterprises, as well as the reputational losses of platform enterprises and complementors due to media coverage.

This study offers insights into improving the governance effectiveness of platform corporate social responsibility for managers and practitioners.

This study contributes to existing literature by considering the rational orientation of platform ecosystem members and revealing the interaction mechanisms among members. Furthermore, this study combines collective action theory and reputation theory to clarify the influencing factors on members’ behaviors.

The purpose of this study is to improve the accuracy of industrial robot kinematic parameter identification and position accuracy by solving the problem of insufficient consideration of error sources in the kinematic parameter identification model and optimizing the selection of measurement pose set.

In this study, a kinematic calibration method for industrial robots considering multiple error sources is proposed. Based on the Modified Denavit Hartenberg (MD-H) model, a robot kinematics identification model including joint reduction ratio error, target ball installation error and coordinate system transformation error is established. Taking the optimal observability index O1 and the minimum flexible deformation as the optimization objectives, a measurement pose set optimization method based on Non-dominated Sorting Genetic Algorithm II (NSGA-II) is proposed to obtain a measurement pose set with higher identification accuracy.

Through experiments conducted with the Nantong Zhenkang ZK1400-6 robot as the test subject, the kinematic parameters identified by the optimized measurement pose set are more accurate than the randomly selected measurement pose set, and the positioning accuracy of the robot is improved from 2.11 to 0.31 mm, an increase of 85.3%.

This study introduces a position error model that comprehensively accounts for the error sources causing positioning inaccuracies. Building on this foundation, a novel flexible deformation index is proposed to quantify the flexible deformation in the measurement pose set, thereby reducing the impact of such deformation on the position error in the model. To the best of the authors’ knowledge, for the first time, this study presents an optimization method for the measurement pose set based on NSGA-II, using the flexible deformation index and observability index as objectives for multi-objective optimization, simultaneously optimizing the pose error and Jacobian matrix in the error model.

A densely distributed network radar system compensates for the disadvantages of sparse radars and poses a significant threat to low-altitude penetration by an unmanned combat aerial vehicle (UCAV). Unlike previous studies, this paper aims to consider radar blind areas and proposes a rapid online method for planning low-altitude penetration paths.

First, the optimization problem coupling digital elevation map (DEM), radar detection probability model and nonholonomic UCAV kinematic model is established. Second, an online solution framework of penetration path planning is constructed. An intervisibility method and map scaling are proposed to generate a detection probability map (DPM). Through completeness and consistency analysis, an adaptive hybrid A* algorithm with fast local replanning strategy is proposed to search a path that takes into account time-consuming, detection probability under nonholonomic constraints. Finally, three scenarios of multiple known, pop-up and vanished static radars are simulated using C++. The computational performance is compared and analyzed.

The results showed that the proposed online method can generate low-detection-probability penetration paths within subseconds.

This paper provides a new online method to plan UCAV penetration trajectory in military and academic contexts.

This study aims to assess the mediating and driving roles of knowledge cooperation in the effectiveness of G60 Sci-tech Innovation Corridor (G60 STIC) for regional collaborative innovation within the knowledge economy context. Furthermore, it focuses on whether knowledge cooperation is more effective than resource cooperation in terms of spatial spillover and its mediating effects on collaborative innovation.

This study employs multiple statistical and econometric approaches, including social cooperation network, Super-DEA, spatial difference-in-difference model (SDID) and mediating effect model, to measure the effectiveness of knowledge cooperation and resource cooperation paths within the framework of the G60 STIC on regional collaborative innovation in the Yangtze River Delta region (YRD) from 2002 to 2022.

First, the knowledge cooperation networks validate the strengthening of collaborative innovation is primarily centred on provincial cities and leading manufacturing locales, with smaller cities radiating outwards from these centres. The knowledge cooperation network was generally stronger than the resource cooperation network. Second, the G60 STIC significantly enhances collaborative innovation efficiency by intensifying knowledge, resource and interactive cooperation networks. Third, within the context of the knowledge economy, knowledge cooperation presents a stronger spillover and mediating effect in stimulating collaborative innovation than resource cooperation.

This study clarifies the existence of a knowledge cooperation network and its mediating role in stimulating the effectiveness of strategic, innovative platforms on collaborative innovation. This further verifies the stronger role of the knowledge cooperation than the resource cooperation, which serves as a vital element in promoting strategic innovative platforms to optimise collaborative innovation.