A large vehicle first clustering method based road section risk level estimation

2016 ◽  
Author(s):  
Qingwen Han ◽  
Xiaoying Liu ◽  
Lingqiu Zeng ◽  
Lei Ye ◽  
Dongmei Chen ◽  
...  
Keyword(s):  
Risk Level ◽  
Clustering Method ◽  
Road Section

scholarly journals A Predictive Pedestrian Crash Model Based on Artificial Intelligence Techniques

2021 ◽  
Vol 11 (23) ◽  
pp. 11364
Author(s):  
Monica Meocci ◽  
Valentina Branzi ◽  
Giulia Martini ◽  
Roberto Arrighi ◽  
Irene Petrizzo
Keyword(s):  
Prediction Model ◽  
Risk Level ◽  
Gradient Boosting ◽  
Accurate Analysis ◽  
Accident Prediction ◽  
Road Section ◽  
Linear Relationships ◽  
Potential Safety ◽  
Machine Learning Approach ◽  
Crash Model

Every year in Italy, there are about 20,000 road accidents involving pedestrians, with a significant number of injuries and deaths. Out of these, about 30% occur at pedestrian crossings, where pedestrians should be protected the most. Here, we propose a new accident prediction model to improve pedestrian safety assessments that allows us to accurately identify the sites with the largest potential safety improvements and define the best treatments to be applied. The accident prediction model was developed using the ISTAT dataset, including information about the fatal and injurious crashes that occurred in Italy in a 5-year period. The model allowed us to estimate the risk level of a road section through a machine-learning approach. Gradient Boosting seems to be an appropriate tool to fit classification models for its flexibility that allows us to capture non-linear relationships that would be difficult to detect via a classical approach. The results show the ability of the model to perform an accurate analysis of the sites included in the dataset. The locations analyzed have been classified based on the potential risk in the following three classes: High, medium, and low. The proposed model represents a solid and reliable tool for practitioners to perform accident analysis with pedestrian involvement.

scholarly journals Integral Assessment of Risk Level in Libraries using the Grey Clustering Method

2019 ◽  
Vol 8 (3) ◽  
pp. 6644-6650
Keyword(s):  
Real Data ◽  
Environmental Engineering ◽  
The Other ◽  
Risk Level ◽  
Clustering Method ◽  
Standard Data ◽  
Minimum Standards ◽  
Grey Clustering ◽  
National University ◽  
Integral Assessment

The purpose of this study is to simultaneously analyze the different risk factors (lighting, noise, and ergonomics), obtain an overall assessment of the risk of these factors and classify them in scales of levels of: Very poor, poor, good and very good, from three libraries of the National University of Engineering. In order to classify them, the grey clustering method was used, which establishes two types of data: Standard data and sampling data, the first one refers to the minimum standards required to be met by a library according to each criterion (lighting, noise, ergonomics). The second one refers to the real data obtained in the field. Both data are evaluated in the indicated methodology and the clustering vector is constructed, which will allow to classify the libraries in the scales of established levels. According to the results obtained, it was determined that the lowest noise levels were obtained in the library of the Faculty of Environmental Engineering; nevertheless, these levels are not within the minimum standards of noise for libraries; in addition, it was determined that the lowest values obtained in illumination of each library correspond to the library of the Faculty of Environmental Engineering, since it is in levels of illumination significantly below what is required according to the minimum standards. On the other hand, adequate lighting levels were obtained in the library of the Faculty of Sciences, and it was determined that the best ergonomic comfort was obtained in the Central Library. According to the overall assessment of each of the libraries under study, according to the scale of levels established, it is concluded that the library of the Faculty of Environmental Engineering is at a poor level with respect to the other libraries (good level).

Pengaruh Manajemen Modal Kerja Terhadap Profitabilitas Dan Risiko

Liquidity ◽  
2017 ◽  
Vol 6 (2) ◽  
pp. 95-102
Author(s):  
Sri Setia Ningsih
Keyword(s):  
T Test ◽  
Raw Material ◽  
Risk Level ◽  
Capital Management ◽  
Working Capital ◽  
Working Capital Management ◽  
Trading Company ◽  
Regression Correlation ◽  
Descriptive Method

The purpose of this research is to know about working capital management applied, and its influence on profitability and risk. The research object is trading company moves in import & distribute chemical raw material. The research used analysis descriptive method, and the hypothesis was testing by simple linier regression, correlation, and determination. The result of the research shows that the effect of the implementation of working capital management on the change of the net working capital with tend to rise has a profitability level of 10.4% lower than the net working capital change with tend to go down of 46%, but instead on the risk level, the net working capital change with tend to rise has a risk level of 43.8% higher than the change in net working capital with tend to go down of 0.3%.Based on  t test, the result shows that the net working capital change influence  is not significant  to profitability and risk.

Optimizing genotype-environment-management interactions to ensure silage maize production in the Chinese Maize Belt

2020 ◽  
Vol 80 (2) ◽  
pp. 133-146
Author(s):  
L Zhang ◽  
Z Zhang ◽  
J Cao ◽  
Y Luo ◽  
Z Li
Keyword(s):  
Field Experiments ◽  
Weather Conditions ◽  
Growth Cycle ◽  
High Energy ◽  
Risk Level ◽  
Energy Yield ◽  
Maize Production ◽  
Early Date ◽  
Environment Management ◽  
Silage Maize

Grain maize production exceeds the demand for grain maize in China. Methods for harvesting good-quality silage maize urgently need a theoretical basis and reference data in order to ensure its benefits to farmers. However, research on silage maize is limited, and very few studies have focused on its energetic value and quality. Here, we calibrated the CERES-Maize model for 24 cultivars with 93 field experiments and then performed a long-term (1980-2017) simulation to optimize genotype-environment-management (G-E-M) interactions in the 4 main agroecological zones across China. We found that CERES-Maize could reproduce the growth and development of maize well under various management and weather conditions with a phenology bias of <5 d and biomass relative root mean square error values of <5%. The simulated results showed that sowing long-growth-cycle cultivars approximately 10 d in advance could yield good-quality silage. The optimal sowing dates (from late May to July) and harvest dates (from early October to mid-November) gradually became later from north to south. A high-energy yield was expected when sowing at an early date and/or with late-maturing cultivars. We found that Northeast China and the North China Plain were potential silage maize growing areas, although these areas experienced a medium or even high frost risk. Southwestern maize experienced a low risk level, but the low soil fertility limited the attainable yield. The results of this paper provide information for designing an optimal G×E×M strategy to ensure silage maize production in the Chinese Maize Belt.

Sign in / Sign up

Export Citation Format

Share Document