This work proposed an integrated model combining bagging and stacking considering the weight coefficient for short-time traffic-flow prediction, which incorporates vacation and peak time features, as well as occupancy and speed information, in order to improve prediction accuracy and accomplish deeper traffic flow data feature mining. To address the limitations of a single prediction model in traffic forecasting, a stacking model with ridge regression as the meta-learner is first established, then the stacking model is optimized from the perspective of the learner using the bagging model, and lastly the optimized learner is embedded into the stacking model as the new base learner to obtain the Ba-stacking model. Finally, to address the Ba-stacking model’s shortcomings in terms of low base learner utilization, the information structure of the base learners is modified by weighting the error coefficients while taking into account the model’s external features, resulting in a DW-Ba-stacking model that can change the weights of the base learners to adjust the feature distribution and thus improve utilization. Using 76,896 data from the I5NB highway as the empirical study object, the DW-Ba-Stacking model is compared and assessed with the traditional model in this paper. The empirical results show that the DW-Ba-stacking model has the highest prediction accuracy, demonstrating that the model is successful in predicting short-term traffic flows and can effectively solve traffic-congestion problems.
In the order picking process of the warehouse center, considering the rapid increase in the volume of orders arriving at the picking center at the time of the promotional festival, a hybrid operation mode with multiple picking tables is used to meet the picking requirements of the huge number of real-time orders. Therefore, in this paper, a hybrid picking mode is proposed, taking into account both the idle degree of picking stations and their order item centers of gravity, and a new reinforcement learning algorithm embedding mechanism (PRL) with placeholder control is designed to solve the problem of a huge number of real-time item orders arriving at the picking center system on promotional holidays and in inconsistent quantities, and numerical simulations are performed for this algorithm. The experimental results show that the PRL algorithm in hybrid picking mode can handle a huge number of orders simultaneously and improve picking efficiency effectively.
Background In recent years, the frequent occurrence of offshore oil leakage has increased the risk of offshore oil pollution. According to statistics, in the 1970s, there were two tanker accidents every week in the world. The American oil tanker “Tory Canyon” drowned in the English Channel after hitting a rock in 1967, and the “Exxon Valdez” ran aground in 1989. Oil tanker leakage has had a significant impact on the marine environment, economy and human health. Therefore, we must focus on the safety of oil tanker transportation in the port, so as to protect the mental health and property of the crew and the marine environment. The mental health of crew members in closed environment is also controversial. Research Objects and Methods A survey was conducted in Xiadong port, Shekou port and Ma'an port of Shenzhen port. Through questionnaire survey, expert interview and field survey, the comprehensive evaluation index system of coastal ports is determined, and the fuzzy comprehensive evaluation model is constructed. Finally, correlation analysis is used to determine the impact of each component on risk. Watson and friend (1969) defined “fear of negative evaluation” (fne) as being superior to others' evaluation, being distressed by others' negative evaluation, and expecting to be negatively evaluated by others.The items of this scale are completely consistent with the above concepts. The prototype of fne scale (Watson and friend, 1969) contains 30 “yes and no” items, of which the positive and negative scores are roughly the same. The revised concise scale (Leary, 1983) contains 12 items in the original scale and is rated at level 5 (1 = completely inconsistent with me: 5 = very consistent with me). The score range of the original fne scale is from. (minimum fne) to 30 (maximum fne). The concise scale ranged from 12 to 60. The opposite of high fne is that there is no guarantee of excellence in the evaluation of others, but not necessarily the expectation or need for positive evaluation. The average score of 205 college students in the original table was 15.5 (SD = 8.6), and the score was rectangular distribution. The mean score of another sample composed of 128 subjects was 13.6 (SD = 7.6) A. The mean score of the sample (n = 150) used to compile the 12 item concise scale was 35.7 (SD = 8.1). Results The results show that: (1) the risk value of oil spill in Xiadong port is the largest, followed by Shekou port and Mawan port. The average oil spill risk level of oil tankers in the three ports is “general risk”; (2) The responsibility coefficient is an important index to measure the safety of oil tankers; (3) In terms of natural environmental factors, Xiadong port is dominated by wind, Shekou port and Mawan port are dominated by visibility and velocity; Among the navigation environment factors, the navigation conditions of Xiadong port are the main factors affecting the safety of oil tankers, while the density is the main factor affecting the safety of oil tankers in the other two ports. The results showed that the scores of the four dimensions of suicide attitude in the two groups were less than 2 points, and the difference was not statistically significant (P > 0.05). After 8 weeks of cognitive behavioral intervention, the average scores of crew members in the four dimensions of understanding the nature of suicidal behavior, attitude towards suicides, attitude towards family members of suicides and attitude towards euthanasia were significantly higher than those in the control group (P < 0.01). It is suggested that cognitive behavioral intervention can change the cognition and attitude of depression patients towards suicide Conclusion The results of this study provide basis and support for port area and ship safety management decision-making, and have certain practical guiding significance. According to the evaluation model, ports and shipping companies can determine the risk degree of ships in the sea area and take appropriate preventive measures to reduce oil leakage. However, this paper also has some defects that need to be improved: (1) although the fuzzy comprehensive evaluation method has certain advantages in the case of relatively few accident data, the acquisition of its weight needs to be combined with expert experience, so it is difficult to avoid the subjectivity of its view, which has a certain impact on the final evaluation. (2) There are many factors affecting the oil spill risk of oil tankers. With the passage of time, the port environment and ship structure will change, and the factors affecting oil leakage will also change. At the same time, by comparing the effects of depression on crew suicidal ideation in a closed environment, this study found that cognitive behavioral therapy can improve the suicidal ideation of depressed patients. It can not only effectively improve patients' depression and suicide attitude, but also make patients face difficulties and setbacks rationally, and better adapt to the society. It is worthy of clinical promotion. (3) The tanker data used in this risk analysis is limited. If you want to obtain more comprehensive and rigorous analysis results, you should collect more data with the help of Shenzhen municipal government.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.