Search results

To the industrial application of intelligent and connected vehicles (ICVs), the robustness and accuracy of environmental perception are critical in challenging conditions. However, the accuracy of perception is closely related to the performance of sensors configured on the vehicle. To enhance sensors’ performance further to improve the accuracy of environmental perception, this paper aims to introduce an obstacle detection method based on the depth fusion of lidar and radar in challenging conditions, which could reduce the false rate resulting from sensors’ misdetection.

Firstly, a multi-layer self-calibration method is proposed based on the spatial and temporal relationships. Next, a depth fusion model is proposed to improve the performance of obstacle detection in challenging conditions. Finally, the study tests are carried out in challenging conditions, including straight unstructured road, unstructured road with rough surface and unstructured road with heavy dust or mist.

The experimental tests in challenging conditions demonstrate that the depth fusion model, comparing with the use of a single sensor, can filter out the false alarm of radar and point clouds of dust or mist received by lidar. So, the accuracy of objects detection is also improved under challenging conditions.

A multi-layer self-calibration method is conducive to improve the accuracy of the calibration and reduce the workload of manual calibration. Next, a depth fusion model based on lidar and radar can effectively get high precision by way of filtering out the false alarm of radar and point clouds of dust or mist received by lidar, which could improve ICVs’ performance in challenging conditions.

The era of crowd network is coming and the research of its steady-state is of great importance. This paper aims to establish a crowd network simulation platform and maintaining the relative stability of multi-source dissemination systems.

With this simulation platform, this paper studies the characteristics of “emergence,” monitors the state of the system and according to the fixed point judges the system of steady-state conditions, then uses three control conditions and control methods to control the system status to acquire general rules for maintain the stability of multi-source information dissemination systems.

This paper establishes a novel steady-state maintenance simulation framework. It will be useful for achieving controllability to the evolution of information dissemination and simulating the effectiveness of control conditions for multi-source information dissemination systems.

This paper will help researchers to solve problems of public opinion control in multi-source information dissemination in crowd network.

The purpose of this paper is to find a method for key assembly structure identification in complex mechanical assembly. Three-dimensional model reuse plays an increasingly important role in complex product design and innovative design. Assembly model has become important resource of models reuse in enterprises, which contains certain function assembly structures. These assembly structures implicating plenty of design intent and design experience knowledge can be used to support function-structure design, modular design reuse and semantics analysis for complex product.

A method for identifying key assembly structures in assembly model is presented from the viewpoint of assembly topology and multi-source attributes. First, assembly model is represented based on complex network. Then, a two-level evaluation model is put forward to evaluate importance of parts assembled, and the key function parts in assembly can be obtained. After that, on the basis of the function parts, a heuristic algorithm upon breadth first searching is given to identify key assembly structures.

The method could be used to evaluate key function parts and identify key assembly structures in complex mechanical assembly according to the specific circumstances.

The method can not only help designers find the key assembly structure in complex mechanical assembly model, facilitate the function-structure designing and semantics analyzing, and thereby improve the efficiency of product knowledge reuse, but also assist in analyzing influence scope of key function part changing and optimization of the assembly process for complex mechanical assembly.

The paper is the first to propose a method for key assembly structure identification in complex mechanical assembly, where the key function parts can be evaluated through a two-level evaluation model, and the key assembly structures are identified automatically based on complex network.

As productions show characteristics of multi-varieties and small batch in a recent new product system, it is more difficult to acquire its failure rate data. With the help of expert experience information, the authors can get the interval estimation of failure rate data under different methods, so how to make the interval convergence with the new information is an important problem to be solved. The paper aims to discuss this issue.

In this paper, the concept of generalized standard grey number is used to characterize the multi-source heterogeneous uncertainty failure rate data into a unified framework. Then, the engineering construction method is used to calculate the average failure rate and build the grey exponential distribution reliability function, whose image is presented as the possible region of the two-curve envelope.

Further, according to the normal distribution assumption of the regional convergence based on the information supplement, the convergence problem of the reliability function is transformed into the convergence of the area of the curve envelope region, and construct the multi-objective programming model with the minimum envelope area and the lowest total cost of information acquisition, acquire the conclusion that the failure rate is equal to the nuclear of the average failure rate when the envelope region converges.

Through the case analysis of the equipment ejection system of the Harbinger system, five groups of results are obtained by Matlab simulation, which verify the rationality and feasibility of the model described in this paper.

A good decision support system for credit scoring enables telecom operators to measure the subscribers' creditworthiness in a fine-grained manner. This paper aims to propose a robust credit scoring system by leveraging latent information embedded in the telecom subscriber relation network based on multi-source data sources, including telecom inner data, online app usage, and offline consumption footprint.

Rooting from network science, the relation network model and singular value decomposition are integrated to infer different subscriber subgroups. Employing the results of network inference, the paper proposed a network-aware credit scoring system to predict the continuous credit scores by implementing several state-of-art techniques, i.e. multivariate linear regression, random forest regression, support vector regression, multilayer perceptron, and a deep learning algorithm. The authors use a data set consisting of 926 users of a Chinese major telecom operator within one month of 2018 to verify the proposed approach.

The distribution of telecom subscriber relation network follows a power-law function instead of the Gaussian function previously thought. This network-aware inference divides the subscriber population into a connected subgroup and a discrete subgroup. Besides, the findings demonstrate that the network-aware decision support system achieves better and more accurate prediction performance. In particular, the results show that our approach considering stochastic equivalence reveals that the forecasting error of the connected-subgroup model is significantly reduced by 7.89–25.64% as compared to the benchmark. Deep learning performs the best which might indicate that a non-linear relationship exists between telecom subscribers' credit scores and their multi-channel behaviours.

This paper contributes to the existing literature on business intelligence analytics and continuous credit scoring by incorporating latent information of the relation network and external information from multi-source data (e.g. online app usage and offline consumption footprint). Also, the authors have proposed a power-law distribution-based network-aware decision support system to reinforce the prediction performance of individual telecom subscribers' credit scoring for the telecom marketing domain.

This paper aims to overcome the defect of single-source temperature measurement method and improve the measurement accuracy of FTR. The friction temperature rise (FTR) of brake affects braking performance seriously. However, it was mainly detected by single-source indirect thermometry, which has obvious deviations.

A three-point temperature measurement system was built based on three kinds of single-resource thermometry. Temperature characteristics of these thermometry were analyzed to achieve a standard FTR curve. Two fusion-monitoring models for FTR based on multi-source information were established by artificial neural network (ANN) and support vector machine (SVM).

Finally, the two models were verified based on the experimental results. The results showed that the fusion-monitoring model of SVM was more accurate than that of ANN in monitoring of FTR.

Then the temperature characteristics of the three single-source thermometry were analyzed, and the fusion-monitoring models based on multi-source information were established by ANN and SVM. Finally, the accuracy of the two models was compared by the experimental results. The more suitable fusion-monitoring model for FTR monitoring was determined which would be of theoretical and practical significance for remedying the monitoring defect of FTR.

This paper aims to present a multi-source information fusion algorithm based on factor graph for autonomous underwater vehicles (AUVs) navigation and positioning to address the asynchronous and heterogeneous problem of multiple sensors.

The factor graph is formulated by joint probability distribution function (pdf) random variables. All available measurements are processed into an optimal navigation solution by the message passing algorithm in the factor graph model. To further aid high-rate navigation solutions, the equivalent inertial measurement unit (IMU) factor is introduced to replace several consecutive IMU measurements in the factor graph model.

The proposed factor graph was demonstrated both in a simulated and vehicle environment using IMU, Doppler Velocity Log, terrain-aided navigation, magnetic compass pilot and depth meter sensors. Simulation results showed that the proposed factor graph processes all available measurements into the considerably improved navigation performance, computational efficiency and complexity compared with the un-simplified factor graph and the federal Kalman filtering methods. Semi-physical experiment results also verified the robustness and effectiveness.

The proposed factor graph scheme supported a plug and play capability to easily fuse asynchronous heterogeneous measurements information in AUV navigation systems.

This study focused on the relationship between 360‐degree (multi‐source) survey feedback to managers and subsequent selection of development goals. We hypothesized that performance ratings would be negatively related to setting development goals, that supervisor ratings would have a greater effect than ratings from peers or subordinates in the selection of developmental goals, and that self‐other discrepancies would be related to goal selection. Data from 2,163 managers showed that multi‐source feedback contributed to the selection of developmental goals. However, contrary to expectations, subordinate ratings were most important to goal setting compared to ratings from any other sources. Direct feedback itself affected goal selection, not its relationship to self‐perceptions. For several goals, the relationship between performance ratings and goal selection was stronger for lower level managers. Implications of the results for the practice of 360‐degree feedback and related research are discussed.

The purpose of this paper is to improve the existing paradigm of edge computing to maintain a balanced energy usage.

The new greedy algorithm is proposed to balance the energy consumption in edge computing.

The new greedy algorithm can balance energy more efficiently than the random approach by an average of 66.59 percent.

The results are shown in this paper which are better as compared to existing algorithms.

This paper aims to present a combination modeling method using multi-source information in the process to improve the accuracy of the dimension propagation relationship for assembly variation reduction.

Based on a variable weight combination prediction method, the combination model that takes the mechanism model and data-driven model based on inspection data into consideration is established. Furthermore, the combination model is applied to qualification rate prediction for process alarming based on the Monte Carlo simulation and also used in engineering tolerance confirmation in mass production stage.

The combination model of variable weights considers both the static theoretical mechanic variation propagation model and the dynamic variation relationships from the regression model based on data collections, and provides more accurate assembly deviation predictions for process alarming.

A combination modeling method could be used to provide more accurate variation predictions and new engineering tolerance design procedures for the assembly process.