The Ship Collision Accidents Based on Logistic Regression and Big Data

Wang, Yi-han; Ou, Yang Kun; Xudong, Deng; Zhao, Lu-ran; Zhang, Chao-yu

doi:10.1109/ccdc.2019.8832686

Cited by 14 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The long-term average revenue-cost ratio indicates the merits of the network resource allocation scheme, and we calculate it using the following formula. The Equation ( 11) is derived from Equation ( 8) and (9).…”

Section: Sr = Limmentioning

confidence: 99%

“…In the future, the network will have more stringent requirements for the storage of massive data, and will have higher and higher requirements for cost, bandwidth and delay [7]. Traditional heuristic algorithms are prone to fall into local optimal solutions when the data volume is large and cannot meet the requirements for differentiated quality of service in edge network-based smart grids [8], [9]. With the improvement of computer computing power, deep reinforcement learning (DRL) shows excellent performance in solving high-dimensional spatial problems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Reinforcement Learning Based Edge Computing Network Aided Resource Allocation Algorithm for Smart Grid

et al. 2023

View full text Add to dashboard Cite

The dramatic increase in the volume of users and services makes scheduling network resources for smart grids a key challenge. Network slicing is an important technology to solve this problem. We introduce edge computing networks into the smart grid to intelligently allocate resources based on users' quality of service (QoS) and available resources. However, existing heuristic resource scheduling algorithms often lead to resource fragmentation and thus fall into local optima. To this end, we propose a deep reinforcement learning (DRL)-based virtual network embedding algorithm to optimize the resource allocation strategy of smart grids from a network virtualization perspective. We extract the network properties of the smart grid to construct a policy network as a training environment for DRL agents. Finally, DRL derives the probability of each node being embedded based on the extracted attributes of edge computing nodes and completes user request (UR) embedding based on this probability. The experimental results show that the algorithm proposed in this paper has excellent performance with guaranteed low latency, 21% improvement in long-term revenue and 5.6% improvement in UR success rate compared with the other two algorithms.

show abstract

Section: Sr = Limmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning Based Edge Computing Network Aided Resource Allocation Algorithm for Smart Grid

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A specific mathematical tool is required to develop a model that relates the current and historical states of medication-related adverse events to predict future states of error development. In recent years, logistic regression has been used in many studies to predict and prevent accidents in different fields, such as aviation [29], tank farms [30], ship collisions [31], and petrochemical industries [32]. Many studies have analyzed the error factors of medication-related adverse events; however, few have considered the present and historical states of the lapse factors when calculating the occurrence frequency of error factors.…”

Section: Causality Between Error Factorsmentioning

confidence: 99%

Human Error Analysis and Modeling of Medication-Related Adverse Events in Taiwan Using the Human Factors Analysis and Classification System and Logistic Regression

Hsieh

Huang

2023

Healthcare

View full text Add to dashboard Cite

Medical institutions worldwide strive to avoid adverse medical events, including adverse medication-related events. However, studies on the comprehensive analysis of medication-related adverse events are limited. Therefore, we aimed to identify the error factors contributing to medication-related adverse events using the Human Factors Analysis and Classification System (HFACS) and to develop error models through logistic regression. These models calculate the probability of a medication-related adverse event when a healthcare system defect occurs. Seven experts with at least 12 years of work experience (four nurses and three pharmacists) were recruited to analyze thirty-seven medication-related adverse events. The findings indicate that decision errors, physical/mental limitations, failure to correct problems, and organizational processes were the four factors that most frequently contributed to errors at the four levels of the HFACS. Seven error models of two types (error occurrence and error analysis pathways) were established using logistic regression models, and the relative probabilities of failure factor occurrences were calculated. Based on our results, medical staff can use the error models as a new analytical approach to improve and prevent adverse medication events, thereby improving patient safety.

show abstract

“…Based on machine learning, there are many classification models such as Faster-rcnn, Yolo, SSD, and Resnet. There are also many classification algorithms such as SVM [4] (Support Vector Machine), DT [5] (Decision Tree), LR [6](Logistic Regression) and many other algorithms. In this paper, the algorithm we use is a simplified version of SVM named LMC.…”

Section: Introductionmentioning

confidence: 99%

Feature selected based on PCA and optimized LMC

Cai

2021

MATEC Web Conf.

View full text Add to dashboard Cite

In this article, we propose an optimization algorithm for the original LMC [1] (Large Margin Classifier). We use PCA [2] (Principal Component Analysis) to reduce the dimensionality of the images, and then put the data after dimensionality reduction into the optimized LMC for the feature selection [3]. We will get several features with the greatest distinction. We use these features to classify images. Finally, the experiment shows that the accuracy of the optimized LMC under the same dimensions is higher than that of the original LMC, and in many cases, the accuracy of the optimized LMC after taking 6 feature vectors has exceeded the highest accuracy of the original LMC.

show abstract

The Ship Collision Accidents Based on Logistic Regression and Big Data

Cited by 14 publications

References 0 publications

Deep Reinforcement Learning Based Edge Computing Network Aided Resource Allocation Algorithm for Smart Grid

Deep Reinforcement Learning Based Edge Computing Network Aided Resource Allocation Algorithm for Smart Grid

Human Error Analysis and Modeling of Medication-Related Adverse Events in Taiwan Using the Human Factors Analysis and Classification System and Logistic Regression

Feature selected based on PCA and optimized LMC

Contact Info

Product

Resources

About