Journal of Intelligent & Fuzzy Systems - Volume 41, issue 4

Authors: Zhuang, Kai | Wu, Sen | Gao, Xiaonan

Article Type: Research Article

Abstract: To deal with the systematic risk of financial institutions and the rapid increasing of loan applications, it is becoming extremely important to automatically predict the default probability of a loan. However, this task is non-trivial due to the insufficient default samples, hard decision boundaries and numerous heterogeneous features. To the best of our knowledge, existing related researches fail in handling these three difficulties simultaneously. In this paper, we propose a weakly supervised loan default prediction model WEAKLOAN that systematically solves all these challenges based on deep metric learning. WEAKLOAN is composed of three key modules which are used for encoding …loan features, learning evaluation metrics and calculating default risk scores. By doing so, WEAKLOAN can not only extract the features of a loan itself, but also model the hidden relationships in loan pairs. Extensive experiments on real-life datasets show that WEAKLOAN significantly outperforms all compared baselines even though the default loans for training are limited. Show more

Keywords: Metric learning, loan default prediction, weakly supervised learning, pair-wise learning

DOI: 10.3233/JIFS-189987

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5007-5019, 2021

Authors: Guo, Junhua | Xiao, Xiaofang | Ye, Yutao | Yan, Lixin

Article Type: Research Article

Abstract: A novel green delivery method for express delivery based on the urban metro network, referred to as Green metro express delivery (GMED), is presented. A multi-objective mathematical programming model is first proposed to maximize the search for the best transportation costs and lowest carbon emissions. To solve the GMED model e-ciently, a two-layer coding method is used to encode the path and the non-dominated sorting genetic algorithm II (NSGA-II) is adopted. Finally, a numerical experiment was conducted with Ningbo Metro Network as a case to prove the effectiveness and stability of NSGA-II in solving the GMED model. The result shows …that: (a) Compared with the vehicle express delivery method (VED), GMED has lower carbon emissions and vehicle mileage. (b) For the same quantity of express delivery, the transportation costs of GMED and VED have their own advantages over different transportation distances. (c) For delivery distances with the same transportation cost, the lager the quantity of express delivery, the lower the transportation cost of GMED compared to VED. Show more

Keywords: Green delivery, lower carbon emissions, NSGA-II

DOI: 10.3233/JIFS-189988

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5021-5034, 2021

Authors: Wan, Ming | Chen, Zhifang | Guo, Junhua | Wan, Ping

Article Type: Research Article

Abstract: Rational and orderly passenger organization in subway station can improve travel efficiency and safety. How to improve the efficiency of security check, which has a significant impact on the passenger organization, to reduce passengers staying time in the terminal level has the potential to improve service satisfaction. The Weidong Station of Line 1 of Nanchang Metro was selected as the research object. Anylogic software was used to simulate the process of arrival, ticket purchase, security check, gate-crossing machine etc. The results indicate that the dynamic adjustment of security checkpoints and fast passage for passengers without luggage can improve the security …efficiency and relieve the congestion in the station hall. Show more

Keywords: Subway, efficiency of security check, Anylogic

DOI: 10.3233/JIFS-189989

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5035-5043, 2021

Authors: Zhang, Cheng | Liu, Min | Wan, Ping | Guo, Junhua

Article Type: Research Article

Abstract: High-speed railway is an indispensable part of the transportation system. The construction and opening of high-speed railway will contribute to the economic development of cities along the route, but it will also have an adverse impact on peripheral areas. The research of the article is mainly carried out from an empirical point of view, using comparative analysis, regression analysis and other methods to measure and quantitatively describe the impact of high-speed railways on urban and regional spatial development. The study found that the operation of the Shanghai-Kunming high-speed rail had a siphon effect on cities along the Jiangxi Province, leading …to unbalanced regional development. Show more

Keywords: High-speed railway, regional economy, linear regression, siphon effect

DOI: 10.3233/JIFS-189990

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5045-5051, 2021

Authors: Zhang, Zhijian | Jiang, Yubin | Chen, Zhijun | Xiong, Yubing

Article Type: Research Article

Abstract: The purpose of this study is to deeply analyze the influencing factors of drivers’ traffic accident casualties and reduce the occurrence of casualties. From the FARS database of the National Highway Safety Administration (NHTSA), 93248 traffic accident data were extracted as analysis samples. On this basis, the Bayesian network and multinomial logit model are established. The constructed model was tested from the perspective of model prediction accuracy and variables importance. Bayesian networks are used to analyze the interrelationships among influencing factors, and multinomial logit models are used to compare and evaluate the impact of different variables on the injury severity …under different circumstances. The results show that: the prediction accuracy of the Bayesian network model and multinomial logit model is 64.57% and 65.97%, respectively. The Bayesian network reference analyses indicate that injury severity is affected by the crash factors, and there are various interactions between the various factors. The multinomial logit model analyses indicate that the factors including drivers’ age, female driver, rural roads, drunk driving, drug driving, crash time, side collision accident, etc. could significantly increase injury severity. Airbags are more effective in reducing fatal crash than injury crash. The probability of accidents caused by drug driving drivers is greater than drunk driving, drunk driving drivers are 1.79 times and 2.34 times more likely to suffer an injury severity and fatal injury severity in crashes as compared to a no injury severity, respectively, and drug driving is 1.93 times and 2.6 times, respectively. Seat belts may avoid 92.2% of fatalities. Roadside guardrail reduces the incidence of fatal crash better than injury crash. Fatal injuries severity and injury severity are 1.124 times and 1.141 times more likely to occur during the 0 : 00 to 6 : 00 as compared to no injuries, respectively, etc. Show more

Keywords: Road safety, traffic accident, injury severity, Bayesian network, multinomial logit model

DOI: 10.3233/JIFS-189991

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5053-5063, 2021

Authors: Yan, Lixin | Zeng, Tao | Xiong, Yubing | Li, Zhenyun | Liu, Qingmei

Article Type: Research Article

Abstract: With the development of urbanization, urban traffic has exposed many problems. To study the subway’s influence on urban traffic, this paper collects data on traffic indicators in Nanchang from 2008 to 2018. The research is carried out from three aspects: traffic accessibility, green traffic, and traffic security. First, Grey Relational Analysis is used to select 18 traffic indicators correlated with the subway from 22 traffic indicators. Second, the data is discretized and learned based on Bayesian Networks to construct the structural network of the subway’s influence. Third, to verify the reliability of using GRA and the effectiveness of Bayesian Networks …(GRA-BNs), Bayesian Networks with full indicators analysis and other four algorithms (Naive Bayes, Random Decision Forest, Logistic and regression) are employed for comparison. Moreover, the receiver operating characteristic (ROC) area, true positive (TP) rate, false positive (FP) rate, precision, recall, F-measure, and accuracy are utilized for comparing each situation. The result shows that GRA-BNs is the most effective model to study the impact of the subway’s operation on urban traffic. Then, the dependence relations between the subway and each index are analyzed by the conditional probability tables (CPTs). Finally, according to the analysis, some suggestions are put forward. Show more

Keywords: Subway, traffic accessibility, green traffic, traffic security, Bayesian networks

DOI: 10.3233/JIFS-189992

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5065-5080, 2021

Authors: Guo, Bin | Hao, Shengyue | Cao, Guangmei | Gao, Honghu

Article Type: Research Article

Abstract: Profit distribution plays an important role in the sustainable and stable development of liner alliances, this paper tries to solve the profit distribution issues in the liner alliance based on Shapley Value Method. Meanwhile, seeing that there is little consideration from the customer satisfaction, this paper establishes a new model by revising Shapley Value Method to distribute the profit of liner alliances from the perspectives of suppliers and customers and carry out verification through case analysis. The profit distribution method proposed in the paper is helpful to the reasonable profit distribution of liner alliance. It ensures the continuity and stability …of liner alliance and provides a scientific decision-making basis for the profit distribution of liner alliance. Show more

Keywords: Profit distribution, liner alliance, shapley value

DOI: 10.3233/JIFS-189993

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5081-5085, 2021

Authors: Zhang, Ying | Yinge, A. | Wang, Bing | Tian, Wen | Wen, Tao

Article Type: Research Article

Abstract: To solve the strategic flight schedule optimization problem for multiple airport and multiple operation days, a two-stage stochastic programming model is established. Flight schedule optimization is made in the first stage of the model, and the tactical flight delay decision is made in the second stage with consideration of the impact of the uncertain operational airport capacity at the tactical stage. The arrival and departure service rates are also optimized as decision variables in the second stage so as to simulate the actual operation characteristics of the airports and more accurately estimate the operation delay at the tactical stage. The …model’s objective function considers the minimum deviation of flight scheduled time in the strategic stage and the expected delay in the tactical stage. A hybrid evolutionary algorithm is designed to solve the model by two-stage decomposition. The model is simulated and verified using the flight plan data of Beijing Capital Airport and Guangzhou Baiyun Airport. The effect of the model in optimizing flight scheduled time and reducing the mean value of operational delay in the tactical phase under different capacity scenarios is analyzed, and the effectiveness of the model and the hybrid evolutionary algorithm is verified. Show more

Keywords: Flight schedule optimization, uncertainty, airport capacity, hybrid evolutionary algorithm, sample average approximation

DOI: 10.3233/JIFS-189994

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5087-5098, 2021

Authors: Wu, Zhifeng | Liu, Yisheng

Article Type: Research Article

Abstract: Based on the transmission characteristics of networks and the systematization of technical risks in national major science and technology projects, the risk transmission mechanism of national major science and technology projects is deeply discussed herein. Firstly, the system of systems (SoS) engineering process model of national major science and technology projects is constructed, including two levels and three stages. Secondly, the hierarchical structure of national major science and technology projects is analyzed, and the risks are divided into different levels, such as SoS, system, subsystem, equipment, module, and components. Finally, we describe the risk transfer mechanism using the forest-fire model …and outline a risk control strategy. The results show that the findings are helpful for recognizing the essence and transmission mechanism of technical risks of national major science and technology projects and for reducing the risk from the source. The research results can be applied to project management in the transportation field. Show more

Keywords: SoS engineering, risk transfer, forest-fire model

DOI: 10.3233/JIFS-189995

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5099-5105, 2021

Authors: Tang, Zhaoping | Li, Wenda | Yu, Shijun | Sun, Jianping

Article Type: Research Article

Abstract: In the initial stage of emergency rescue for major railway emergencies, there may be insufficient emergency resources. In order to ensure that all the emergency demand points can be effectively and fairly rescued, considering the fuzzy properties of the parameters, such as the resource demand quantity, the dispatching time and the satisfaction degree, the railway emergency resources dispatching optimization model is studied, with multi- demand point, multi-depot, and multi-resource. Based on railway rescue features, it was proposed that the couple number of relief point - emergency point is the key to affect railway rescue cost and efficiency. Under the premise …of the maximum satisfaction degree of quantity demanded at all emergency points, a multi-objective programming model is established by maximizing the satisfaction degree of dispatching time and the satisfaction degree of the couple number of relief point - emergency point. Combined with the ideal point method, a restrictive parameter interval method for optimal solution was designed, which can realize the quick seek of Pareto optimal solution. Furthermore, an example is given to verify the feasibility and effectiveness of the method. Show more

Keywords: Emergency resource dispatching, equitable distribution principle, couple number of relief point - emergency point, satisfaction degree, restrictive parameter interval method

DOI: 10.3233/JIFS-189996

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 4, pp. 5107-5116, 2021