Search results

The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems.

On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects.

The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model.

This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

To evacuate passengers arriving at intercity railway stations efficiently, metros and intercity railways usually share the same station or have stations close to each other. When intercity trains arrive intensively, a great number of passengers will burst into the metro station connecting with the intercity railway station within a short period, while the number of passengers will decrease substantially when intercity trains arrive sparsely. The metro timetables with regular headway currently adopted in real-world operations cannot handle the injected passenger demand properly. Timetable optimization of metro lines connecting with intercity railway stations is essential to improve service quality.

Based on arrival times of intercity trains and the entire process for passengers transferring from railway to metro, this paper develops a mathematical model to characterize the time-varying demand of passengers arriving at the platform of a metro station connecting with an intercity railway station. Provided the time-varying passenger demand and capacity of metro trains, a timetable model to optimize train departure time of a bi-direction metro line where an intermediate station connects with an intercity railway station is proposed. The objective is to minimize waiting time of passengers at the connecting station. The proposed timetable model is solved by an adaptive large neighborhood search algorithm.

Real-world case studies show that the prediction accuracy of the proposed model on passenger demand at the connecting station is higher than 90%, and the timetable model can reduce waiting time of passengers at the connecting station by 28.47% which is increased by 5% approximately than the calculation results of the generic algorithm.

This paper puts forward a model to predict the number of passengers arriving at the platform of connection stations via analyzing the entire process for passengers transferring from intercity trains to metros. Also, a timetable optimization model aiming at minimizing passenger waiting time of a metro line where an intermediate station is connected to an intercity railway station is proposed.

To combine the forecasting by single method using influence information fully, other than regular combined methods only focusing on historical forecasting errors.

To combine the single methods based on the analysis of improved gray correlation, with more related information being considered to enhance the price forecasting precision, such as the trend of the prices, the historical forecasting errors, and the temporal influence factors on prices.

A case of PJM market of USA shows that the proposed method has better performance than any other combined methods, and all single models as well.

The combined performance depends on the forecasting precision of single methods, and the correlation between the single methods, as well as the number of single method that to be combined.

It is a novel idea for combined method to forecasting the time series data, such as electricity prices, electric power loads.

The proposed method considers all the following factors: the similarity between the trends of the single forecasting, the errors of the single models and the temporal influence.

The purpose of this paper is to develop a virtual reality (VR)-based and user-oriented decision support system for interior design and decoration. The four-phase decision-making process of the system is verified through a case study of an office building.

Different “spatial layouts” are presented by VR for users to decide their preference (Phase 1). According to the selected spatial layout, a “spatial scene” is constructed by VR and Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is used to determine the spatial scene preference (Phase 2). Based on the binary integer programming method, the system provides the optimal preliminary solution under a limited decoration budget (Phase 3). Finally, the consistency between the overall color scheme and pattern is fine-tuned by VR in order to obtain the final solution (Phase 4).

The questionnaire survey results show that decision makers generally affirm the operation and application of VR, and especially recognize the advantages in the improvement of VR-based interior design feasibility, communication efficiency and design decision-making speed. The optimization of the costs and benefits enables decision makers to effectively evaluate the impact of design decisions on subsequent project implementation during the preliminary design process.

The VR-based decision support system for interior design retains the original immersive experience of VR, and offers a systematic multiple criteria decision- making and operations research optimization method, thus, providing more complete decision-making assistance. Compared with traditional design communication, it can significantly reduce cognitive differences and improve decision-making quality and speed.

The purpose of this paper is to find an appropriate sliding mode control strategy for neutral systems with time‐delays in the presence of unmatched parameter uncertainties and external disturbance.

Owing to the complexity of uncertain neutral time‐delay systems, some conclusions for system stability and stabilization are complicated non‐linear matrix inequality (NLMI). Through virtual state feedback control, a sliding mode controller is designed to guarantee state trajectories from any initial condition are attracted to the sliding mode plane in a finite time and remain there for all subsequent time, which can avoid the complicated NLMI. Furthermore, a delay‐independent sufficient condition for the design of robust stable sliding mode plane is obtained in term of LMI.

The sliding mode controller for uncertain neutral time‐delay systems is designed and a delay‐independent sufficient condition for the design of robust stable sliding mode plane is obtained.

The main limitations are that external disturbance must meet matched condition.

A useful control strategy for uncertain neutral systems with time‐delays.

The virtual state feedback control is designed so to avoid the complicated NLMI.

The tremendous market growth of mobile platforms for esports underscores the need to understand players' psychological states and consumption behavior. Based on flow theory, this study examines players' psychological states (flow and clutch experiences) and consumption behavior based on the interaction effects of playing frequency, playing duration and players' levels on the PC (LOL – League of Legends) and mobile (LOLWR – League of Legends: Wild Rift) versions of the same esports title.

Data were collected from 930 valid responses and analyzed with confirmatory factor analysis and multiple regression (PROCESS macro, Model 3).

There are two main findings. First, across PC and mobile participants, casual gamers (low playing frequency and duration) have firm purchase intention when they have a clutch experience, but flow experience hinders their purchasing intention. Second, hardcore gamers' (high playing frequency and duration) psychological states are clearly distinguished according to technological platforms. Flow experience is the most effective for their purchase intention in the PC platform, but both flow and clutch states are important in the mobile platform. Flow experience is essential overall for hardcore gamers to intend their in-game item purchasing.

This study has two primary originality/values. First, this study explores flow and clutch together to measure psychological states and the impact on the purchase intention of in-game items. Second, the interacting effects of playing frequency, duration, and skill level with technical platforms (i.e. PC and mobile) for esports gaming.

This paper aims to investigate whether the establishment of commodity futures can effectively hedge systemic risk in the spot network, given the context of financialization in the commodity futures market.

Utilizing industry association data from the Chinese commodity market, the authors identify systemically important commodities based on their importance in the production process using multiple graph analysis methods. Then the authors analyze the effect of listing futures on the systemic risk in the spot market with the staggered difference-in-differences (DID) method.

The findings suggest that futures contracts help reduce systemic risks in the underlying spot network. Systemic risk for a commodity will decrease by approximately 5.7% with the introduction of each corresponding futures contract, since the hedging function of futures reduces the timing behavior of firms in the spot market. Establishing futures contracts for upstream commodities lowers systemic risks for downstream commodities. Energy commodities, such as crude oil and coal, have higher systemic importance, with the energy sector dominating systemic importance, while some chemical commodities also have considerable systemic importance. Meanwhile, the shortest transmission path for risk propagation is composed of the energy industry, chemical industry, agriculture/metal industry and final products.

The paper provides the following policy insights: (1) The role of futures contracts is still positive, and future contracts should be established upstream and at more systemically important nodes in the spot production chain. (2) More attention should be paid to the chemical industry chain, as some chemical commodities are systemically important but do not have corresponding futures contracts. (3) The risk source of the commodity spot market network is the energy industry, and therefore, energy-related commodities should continue to be closely monitored.

To contribute to achieving the Sustainable Development Goals, this study aims to explore how to encourage innovative green behaviors among college students and the mechanisms behind the formation of green innovation behavior. Specifically, this study examines the influences of schools, mentors and college students themselves.

A multilevel, multisource study involving 261 students from 51 groups generally supported this study’s predictions.

Proenvironmental and responsible mentors significantly predicted innovative green behavior among college students. In addition, creative motivation mediated the logical chain among green intellectual capital, emotional intelligence and green innovation behavior.

The study findings offer new insights into the conditions required for college students to engage in green innovation. In addition, they provide practical implications for cultivating green innovation among college students.

The authors proposed and tested a multilevel theory based on the ability–motivation–opportunity framework. In this model, proenvironmental and responsible mentors, green intellectual capital and emotional intelligence triggered innovative green behavior among college students through creative motivation.

This study aims to use the ego depletion theory to examine the impact of hindrance stressors on knowledge sharing behaviors by investigating the mediating role of ego depletion and the moderating role of self-enhancing humor.

Data were obtained from a two-wave sample of 226 dyads, including employees in the manufacturing industry and their direct supervisors. The hypotheses were tested by hierarchical regression analyzes and Hayes’ PROCESS macro.

The results demonstrated that employees’ self-enhancing humor style could alleviate the impact of hindrance stressors on employees’ ego depletion state and buffer the negative indirect effect of hindrance stressors on employees’ knowledge-sharing behaviors.

Although the authors collected mediator and dependent variables from different sources, this study used a cross-sectional research design, making it difficult to draw causal conclusions. Besides, hindrance stressors, ego depletion and self-enhancing humor style were all reported by employees.

Through the study, the authors highlight the important role of the self-control view in explaining proactive behavior in the workplace and a great awareness of the unforeseeable consequences of ego depletion for employees.

Engineering components/structures with geometric discontinuities normally bear complex and variable loads, which lead to a multiaxial and random/variable amplitude stress/strain state. Hence, this study aims how to effectively evaluate the multiaxial random/variable amplitude fatigue life.

Recent studies on critical plane method under multiaxial random/variable amplitude loading are reviewed, and the computational framework is clearly presented in this paper.

Some basic concepts and latest achievements in multiaxial random/variable amplitude fatigue analysis are introduced. This review summarizes the research status of four main aspects of multiaxial fatigue under random/variable amplitude loadings, namely multiaxial fatigue criterion, method for critical plane determination, cycle counting method and damage accumulation criterion. Particularly, the latest achievements of multiaxial random/variable amplitude fatigue using critical plane methods are classified and highlighted.

This review attempts to provide references for further research on multiaxial random/variable amplitude fatigue and to promote the development of multiaxial fatigue from experimental research to practical engineering application.