ABSTRACT
Highway projects are usually built in extremely complex natural and cultural environments, which is a continuous and dynamic management practice process. Therefore, it often has the characteristics of long construction period, large investment scale, many security risks and high technical requirements. How to effectively reduce these uncertain risk factors is the direction of continuous progress of relevant researchers.
At present, domestic and foreign scholars have carried out relevant research on the evaluation method of highway engineering investment risk, and achieved certain research results. However, the research in this field has the characteristics of extensive conceptual extension, overlapping terminology meaning and inconsistent paradigm. The traditional methods of highway engineering investment risk assessment include expert case analysis, empirical analysis and other traditional methods. These evaluation methods are extensive, biased towards macro, subjective factors have great influence, lack of intelligent means, low efficiency, low accuracy, and do not form a systematic evaluation system.
Therefore, this paper proposes to use the broad learning system to evaluate the investment risk of highway projects. Taking the actual investment risk data of highway projects in the Second Public Administration of China Communications Group as the research object, and using the method of combining experience and professional tools, we first establish a detailed highway risk evaluation index system, and then establish the broad learning system model without incremental learning and with incremental learning. The actual project data are used as the data source for training, and the intelligent evaluation results of the two are compared.
The experimental results show that the prediction accuracy of the broad learning system containing incremental learning has been significantly improved, which can provide investment risk decision support services for highway investment projects in China, and has important reference significance.
- Li Haidong. Theory of highway economy [D]. Sichuan University, 2004.Google Scholar
- Li Yun. Traffic flow characteristics and safety risk analysis of expressway construction area [D]. Chang ' an University, 2014.Google Scholar
- Zhao Wenzhong. Research on investment risk evaluation and response of highway construction projects [D]. Hebei University of Technology, 2016.Google Scholar
- Liu Yuan. Highway Project Investment Risk Assessment under PPP Mode [D]. Hebei University of Engineering, 2017.Google Scholar
- Jia Chen, Liu Huaping, Xu Xinying, Sun Fuchun. Multimodal information fusion based on broad learning method [J]. Journal of Intelligent Systems, 2019, 14 (01): 150--157.Google Scholar
- Yuan Liping, Chen Chuannan. Broad learning from the perspective of artificial intelligence and its application in education [J]. The Journal of Distance Education, 2018, 36 (04): 49--56.Google Scholar
- Ren Chang 'e, Yuan Chao, Sun Yanli, Liu Zhulin, Chen Junlong. Research progress of broad learning system [J]. Computer application research, 2021, 38 (08): 2258--2267.Google Scholar
- Jia Chen. Research and application of broad learning systems under different modal problems [D]. Taiyuan University of Technology, 2019.Google Scholar
- Chen Yonghong, Gan Wenjuan, Meng Xue, Han Jing. Structural settlement prediction based on broad learning [J]. Computer technology and development, 2021, 31 (01): 155--160.Google Scholar
- Guo Yu et al. Online robust echo state broad learning system[J]. Neurocomputing, 2021, 464: 438--449.Google ScholarDigital Library
- Li Wang, Yu Zhuliang. Application of broad learning system in mushroom toxicity identification [J]. Modern food science and technology, 2019, 35 (07): 267--272 + 54.Google Scholar
- Li Guoqiang, Xu Lizhuang. Broad learning algorithm of local receptive field and its application [J]. Computer engineering and application, 2020, 56 (09): 162--167.Google Scholar
- Li Junqiang, Liu Minjun. Highway PPP project operation management problems and countermeasures [J]. Yunnan hydropower, 2021, 37 (08): 195--198.Google Scholar
- Wu Dayong, Sun Kai, Zhang Ziyu, Qi Hang, Wu Yiping. Research on expressway operation monitoring and evaluation index system [J]. Traffic engineering, 2021, 21 (04): 1--6 + 38.Google Scholar
- Huang Xingming. Research on the self-management mode of investment risk control in highway engineering construction [J]. Traffic world, 2021 (16): 163--164.Google Scholar
- Dubusiao. Study on the dynamic model of carbon sink per plant of Platycladus orientalis, Pinus densiflora and Robinia pseudoacacia in central Shandong mountainous area [D]. Shandong Agricultural University, 2019.Google Scholar
Index Terms
- Risk Assessment of Highway Engineering Investment Based on Broad Learning System
Recommendations
Learning-assisted intelligent risk assessment of highway project investment
Highway project has the characteristics of large investment scale and high investment risk. Aiming at the problem of investment risk management, this paper takes 15 highway investment projects in recent ten years as the research object, and establishes an ...
Seismic Risk Assessment of Highway BOT Project
ISIC '11: Proceedings of the 2011 International Conference on Information Security and Intelligence ControlAlong with the increase of Highway Build Operate Transfer(BOT) Project,risk assessment is becoming more and more important. In this paper we are going to introduce the Bayesian Network method applied to the construction of projects, aiming at building a ...
Research on Multi-scale Highway Risk Prediction and Assessment in China
Web and Wireless Geographical Information SystemsAbstractHighway flood risk assessment research is one of the current hotspots and difficulties in the field of natural disaster research, and it is also an important basis for disaster prevention and mitigation planning and management. The research ...
Comments