A Cross-Simulation Method for Large-Scale Traffic Evacuation with Big Data

2014 ◽  
pp. 14-21 ◽  
Author(s):  
Shengcheng Yuan ◽  
Yi Liu ◽  
Gangqiao Wang ◽  
Hui Zhang
Keyword(s):  
Big Data ◽  
Large Scale ◽  
Simulation Method

A NOVEL ANALYTIC APPROACH FOR LARGE SCALE POWER PLANT WIDE PROCESSES WITH BIG DATA

2020 ◽  
Vol 9 (6) ◽  
pp. 3509-3517
Author(s):  
K. Malakonda Rayudu ◽  
A. Kumar
Keyword(s):  
Big Data ◽  
Power Plant ◽  
Large Scale ◽  
Analytic Approach

Multi Disease-Prediction Framework Using Hybrid Deep Learning: An Optimal Prediction Model (Preprint)

2020 ◽  
Author(s):  
Anusha Ampavathi ◽  
Vijaya Saradhi T
Keyword(s):  
Feature Extraction ◽  
Big Data ◽  
Deep Learning ◽  
Weight Function ◽  
Optimization Algorithm ◽  
Large Scale ◽  
Heuristic Algorithms ◽  
Disease Prediction ◽  
Health Care Decisions ◽  
Proposed Model

UNSTRUCTURED Big data and its approaches are generally helpful for healthcare and biomedical sectors for predicting the disease. For trivial symptoms, the difficulty is to meet the doctors at any time in the hospital. Thus, big data provides essential data regarding the diseases on the basis of the patient’s symptoms. For several medical organizations, disease prediction is important for making the best feasible health care decisions. Conversely, the conventional medical care model offers input as structured that requires more accurate and consistent prediction. This paper is planned to develop the multi-disease prediction using the improvised deep learning concept. Here, the different datasets pertain to “Diabetes, Hepatitis, lung cancer, liver tumor, heart disease, Parkinson’s disease, and Alzheimer’s disease”, from the benchmark UCI repository is gathered for conducting the experiment. The proposed model involves three phases (a) Data normalization (b) Weighted normalized feature extraction, and (c) prediction. Initially, the dataset is normalized in order to make the attribute's range at a certain level. Further, weighted feature extraction is performed, in which a weight function is multiplied with each attribute value for making large scale deviation. Here, the weight function is optimized using the combination of two meta-heuristic algorithms termed as Jaya Algorithm-based Multi-Verse Optimization algorithm (JA-MVO). The optimally extracted features are subjected to the hybrid deep learning algorithms like “Deep Belief Network (DBN) and Recurrent Neural Network (RNN)”. As a modification to hybrid deep learning architecture, the weight of both DBN and RNN is optimized using the same hybrid optimization algorithm. Further, the comparative evaluation of the proposed prediction over the existing models certifies its effectiveness through various performance measures.

A real-time control method-based simulation for high-speed trains on large-scale rail network

2017 ◽  
Vol 28 (10) ◽  
pp. 1750126 ◽  
Author(s):  
Yutong Liu ◽  
Chengxuan Cao ◽  
Yaling Zhou ◽  
Ziyan Feng
Keyword(s):  
Real Time ◽  
Traffic Flow ◽  
High Speed ◽  
Large Scale ◽  
Simulation Method ◽  
Real Time Control ◽  
Rail Network ◽  
Time Control ◽  
High Speed Trains ◽  
Rail Traffic

In this paper, an improved real-time control model based on the discrete-time method is constructed to control and simulate the movement of high-speed trains on large-scale rail network. The constraints of acceleration and deceleration are introduced in this model, and a more reasonable definition of the minimal headway is also presented. Considering the complicated rail traffic environment in practice, we propose a set of sound operational strategies to excellently control traffic flow on rail network under various conditions. Several simulation experiments with different parameter combinations are conducted to verify the effectiveness of the control simulation method. The experimental results are similar to realistic environment and some characteristics of rail traffic flow are also investigated, especially the impact of stochastic disturbances and the minimal headway on the rail traffic flow on large-scale rail network, which can better assist dispatchers in analysis and decision-making. Meanwhile, experimental results also demonstrate that the proposed control simulation method can be in real-time control of traffic flow for high-speed trains not only on the simple rail line, but also on the complicated large-scale network such as China’s high-speed rail network and serve as a tool of simulating the traffic flow on large-scale rail network to study the characteristics of rail traffic flow.

Thermo-mechanical coupling particle simulation of three-dimensional large-scale non-isothermal problems

2017 ◽  
Vol 34 (5) ◽  
pp. 1551-1571 ◽  
Author(s):  
Ming Xia
Keyword(s):  
Large Scale ◽  
Three Dimensional ◽  
Simulation Method ◽  
Particle Simulation ◽  
Similarity Criteria ◽  
Particle Model ◽  
Length Scale ◽  
Content Type ◽  
Mechanical Coupling ◽  
Particle Simulation Method

Purpose The main purpose of this paper is to present a comprehensive upscale theory of the thermo-mechanical coupling particle simulation for three-dimensional (3D) large-scale non-isothermal problems, so that a small 3D length-scale particle model can exactly reproduce the same mechanical and thermal results with that of a large 3D length-scale one. Design/methodology/approach The objective is achieved by following the scaling methodology proposed by Feng and Owen (2014). Findings After four basic physical quantities and their similarity-ratios are chosen, the derived quantities and its similarity-ratios can be derived from its dimensions. As the proposed comprehensive 3D upscale theory contains five similarity criteria, it reveals the intrinsic relationship between the particle-simulation solution obtained from a small 3D length-scale (e.g. a laboratory length-scale) model and that obtained from a large 3D length-scale (e.g. a geological length-scale) one. The scale invariance of the 3D interaction law in the thermo-mechanical coupled particle model is examined. The proposed 3D upscale theory is tested through two typical examples. Finally, a practical application example of 3D transient heat flow in a solid with constant heat flux is given to illustrate the performance of the proposed 3D upscale theory in the thermo-mechanical coupling particle simulation of 3D large-scale non-isothermal problems. Both the benchmark tests and application example are provided to demonstrate the correctness and usefulness of the proposed 3D upscale theory for simulating 3D non-isothermal problems using the particle simulation method. Originality/value The paper provides some important theoretical guidance to modeling 3D large-scale non-isothermal problems at both the engineering length-scale (i.e. the meter-scale) and the geological length-scale (i.e. the kilometer-scale) using the particle simulation method directly.

Prospects for Cooperation Between Russia and the Republic of Korea in the Fields of Big Data, Network and Artificial Intelligence for the Development of the Digital Economy

2021 ◽  
Vol 65 (8) ◽  
pp. 51-60
Author(s):  
Yujeong Kim
Keyword(s):  
Artificial Intelligence ◽  
Big Data ◽  
Large Scale ◽  
Technology Development ◽  
Technological Development ◽  
Digital Economy ◽  
Republic Of Korea ◽  
Data Network ◽  
Leading Position ◽  
The Government

Today, each country has interest in digital economy and has established and implemented policies aimed at digital technology development and digital transformation for the transition to the digital economy. In particular, interest in digital technologies such as big data, 5G, and artificial intelligence, which are recognized as important factors in the digital economy, has been increasing recently, and it is a time when the role of the government for technological development and international cooperation becomes important. In addition to the overall digital economic policy, the Russian and Korean governments are also trying to improve their international competitiveness and take a leading position in the new economic order by establishing related technical and industrial policies. Moreover, Republic of Korea often refers to data, network and artificial intelligence as D∙N∙A, and has established policies in each of these areas in 2019. Russia is also establishing and implementing policies in the same field in 2019. Therefore, it is timely to find ways to expand cooperation between Russia and Republic of Korea. In particular, the years of 2020and 2021marks the 30th anniversary of diplomatic relations between the two countries, and not only large-scale events and exchange programs have prepared, but the relationship is deepening as part of the continued foreign policy of both countries – Russia’s Eastern Policy and New Northern Policy of Republic of Korea. Therefore, this paper compares and analyzes the policies of the two countries in big data, 5G, and artificial intelligence to seek long-term sustainable cooperation in the digital economy.

scholarly journals Parallel Motion Simulation of Large-Scale Real-Time Crowd in a Hierarchical Environmental Model

2012 ◽  
Vol 2012 ◽  
pp. 1-15 ◽  
Author(s):  
Xin Wang ◽  
Jianhua Zhang ◽  
Massimo Scalia
Keyword(s):  
Real Time ◽  
Large Scale ◽  
Simulation Method ◽  
Crowd Simulation ◽  
Motion Path ◽  
Motion Simulation ◽  
Environmental Model ◽  
Parallel Methods ◽  
Parallel Motion ◽  
Methods Numerical

This paper presents a parallel real-time crowd simulation method based on a hierarchical environmental model. A dynamical model of the complex environment should be constructed to simulate the state transition and propagation of individual motions. By modeling of a virtual environment where virtual crowds reside, we employ different parallel methods on a topological layer, a path layer and a perceptual layer. We propose a parallel motion path matching method based on the path layer and a parallel crowd simulation method based on the perceptual layer. The large-scale real-time crowd simulation becomes possible with these methods. Numerical experiments are carried out to demonstrate the methods and results.

Sign in / Sign up

Export Citation Format

Share Document