Xiao Song

Xiao Song
Beihang University (BUAA) | BUAA · Department of Intelligent Systems and Control

Doctor of Philosophy

About

120
Publications
14,720
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,633
Citations
Introduction
Skills and Expertise
Additional affiliations
January 2006 - present
Beihang University (BUAA)
Position
  • Professor (Associate)

Publications

Publications (120)
Article
Full-text available
An electret-based mechanical antenna (EBMA), which can transmit extremely low frequency (ELF) electromagnetic signals, has the advantages of miniaturization and high transmitting efficiency, with great potential applications in air, underwater, and underground communications. To improve the charge density of the electret, which is a key factor in d...
Article
For combat simulation, the simulation scenario serves as the foundation and data source. It is not, however, easy to develop military simulation scenario because the developing process of these texts was time-consuming. To solve this problem, in this paper, we propose a distant supervised method for developing military simulation scenarios based on...
Article
In recent years, Human-Robot Interaction (HRI) has become emerging innovation in robotics research and development. Research in Human-Robot Interaction (HRI) aims to understand, design, and evaluate robotic systems intended for human use. Robots and humans must communicate for interaction to occur. Human-robot communication can take various forms,...
Article
Currently, Big Data Analytics help educators better analyze students and monitor their progress and likelihood of success. The online learning experience applies to the experiences in the online computer-mediated digital system to collect information. An essential part of education training programs is challenging and effectively implemented betwee...
Article
Submarine communication and geologic examination in deep earth are challenging because high-frequency electromagnetic (EM) waves with short wavelength can be blocked by soil and seawater, as a result, the low-frequency (LF) waves are preferred in these applications. However, the conventional LF transmitter facility requires size on the scale of the...
Article
The existing Internet of Things (IoT) architectures are employed for different real-time smart city applications adaptively. The adaptability of the architecture to the application depends on the robust quality of experience (QoE) granted to the end-users. By considering the robust requirements of end-user applications, this article introduces an A...
Article
Future pedestrian trajectory prediction offers great prospects for many practical applications. Most existing methods focus on social interaction among pedestrians but ignore the fact that in addition to pedestrians there are other kinds of objects (cars, dogs, bicycles, motorcycles, etc.) with a great influence on the subject pedestrian’s future t...
Article
Full-text available
Due to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep, and features of distinct scales are neglected. Mo...
Chapter
The chapter introduces a Cyber-Physical System Engineering Oriented Intelligent High Performance Simulation Cloud (CPSEO-IHPSC) developed by the author’s team. CPSEO-IHPSC is a kind of intelligent high performance simulation cloud system with the characteristics of digitization, networking, cloud, and intelligence, supporting user to access service...
Article
In recent years, data-driven approaches for remaining useful life (RUL) prognostics have aroused widespread concern. Bearings act as the fundamental component of machinery and their conditioning status is closely associated with the normal operation of equipment. Hence, it is crucial to accurately predict the remaining useful life of bearings. This...
Article
Full-text available
Measurement of electric fields is crucial for the evaluation of the electromagnetic environment in electric power transmission system. Due to limited transmission corridor resources, the hybrid transmission lines including high‐voltage alternating current and high‐voltage direct current (HVAC/HVDC) are more common nowadays. However, commonly used f...
Article
Pedestrian behavior modelling is a challenging problem especially in crowded transportation scenarios. Some recent studies have addressed this problem using deep neural network, but the accuracy of trajectory prediction is still not high because the internal structure of the typical deep neural network with long short-term memory (LSTM) is a one-di...
Article
A scheduling algorithm is crucial for running a simulation model so that tasks can be performed efficiently.The traditionally used blade-based parallel engine system cannot be adapted to a new simulation model. This study proposed a combined dynamic priority and static method, that is, a hybrid load-balancing scheduling (HLB) algorithm. The algorit...
Article
Full-text available
Pedestrian trajectory prediction is vital for transportation systems. Generally we can divide pedestrian behavior modeling into two categories, i.e., knowledge-driven and data-driven. The former might bring expert bias, and it sometimes generates unrealistic pedestrian movement due to unnecessary repulsive forces. The latter approach is popular now...
Article
In the past few years, the graphics processing unit (GPU) has been widely used to accelerate time-consuming models in simulations. Since both model computation and simulation management are main factors that affect the performance of large-scale simulations, only accelerating model computation will limit the potential speedup. Moreover, models that...
Chapter
Full-text available
Pedestrian trajectory prediction is a challenging problem in the crowded and chaotic scenarios. Currently, the prediction error is still high because the input of Long Short-Term Memory (LSTM) network is a 1D vector, which cannot represent the spatial information of pedestrians. To tackle this, we propose to use tensors to represent the complex env...
Chapter
In this paper, pedestrian evacuation is investigated by using an extended social force model that considers patience factor which can solve the situation pedestrian in the corner stay where they are until everyone is finished or there is an occasional gap. In the simulation of indoor evacuation, we add the endurance coefficient attribute to pedestr...
Chapter
In this study we designed a joint simulation framework for distributed Functional Mock-up Interfaces (FMUs), which could be regarded as an extension of FMI criterion. The proposed framework includes remote procedure call to exchange data in distributed network efficiently. Meanwhile, a node management is designed to monitor and manage connection st...
Article
In an LF/VLF transmission system, the performance of the antenna is of great importance to the entire system. Currently, the electret-based mechanical LF/VLF antenna uses mechanical movement to accelerate electret charges to produce LF/VLF electromagnetic waves, and the frequency of these electromagnetic waves is limited by the rotation speed of th...
Article
Full-text available
!Numerous object-tracking and multiple-person-tracking algorithms have been developed in the field of computer vision, but few trackers can properly address the issue of when a pedestrian is partially or fully occluded by other objects or persons. In order to achieve efficient pedestrian tracking in various occlusion conditions, a pedestrian tracki...
Article
Ion-current density is a significant indicator of electromagnetic environment under High Voltage Direct Current (HVDC) lines. To improve measurement accuracy and convenience, this paper concluded factors that affect measurement results and a wireless measurement method was proposed. Wilson plate kind of sensor was designed according to IEEE standar...
Chapter
Pedestrian simulation is an important approach for engineers to evaluate the safety issues of metro buildings. Although there exist many works of pedestrian evacuation, it is still lacking of rich evacuation data to calibrate simulation models. To overcome this problem, we conducted several real-life pedestrian experiments and create a data set nam...
Chapter
A new scientific and technological revolution is emerging around the world and the era of “New Internet + Big Data + Artificial Intelligence+” is coming. As a third approach of understanding and transforming the world after theoretical approach and experimental approach, simulation technology faces major challenge in paradigm, approach, and ecosyst...
Chapter
In this paper we designed a HLA-based federation development framework supporting model reuse. The framework, including model filter, wrapper and scheduler, uses HLA/RTI as distributed underlying communication and management skeleton, and adopts model database and matching algorithm to select satisfying state-machine models for users, adopts FMI to...
Article
Pedestrian evacuation simulation is vital for urban civil engineers. Although there exist many works addressing the issue of emergency evacuation, only a few study the phenomenon of people actively squeezing to pass through an exit. To model this behavior, a three-circle model is adopted to represent the shape of pedestrians. Active rotation torque...
Article
As artificial intelligence becomes a research hotspot, more and more researchers are trying to apply it to numerous domains. It is therefore interesting and challenging to apply data-driven neural network technology to pedestrian movement modeling to test its effect against traditional social force model which can be applied to manifold pedestrian...
Article
Pedestrian modeling is essential for evacuation simulations. One unrealistic phenomenon observed in AnyLogic and open-source software is that running pedestrians often hit the wall then they try to pass an exit. We find that there is only one characteristic time in the social force model (SFM), which means SFM does not divide the desired speed effe...
Chapter
This paper focuses on the impact of an opened or enclosed residential community on a congested road network. The two-dimensional cellular automata-based model (CA) is used, combined with vehicle behavior such as left-turning and waiting. Also, the traffic controller is an employed model in the intersection. We divide the whole network into several...
Chapter
In cloud computing, it is desirable for an infrastructure as a service (IaaS) provider to gain more profit by executing more tasks with hybrid clouds scheduling strategy. Most existing methods suggest IaaS provider to execute tasks within its limit processing capacity. This means the excessive tasks are abandoned and revenue is lost. In this paper,...
Article
Deep neural networks have achieved state-of-the-art performance on many object recognition tasks, but they are vulnerable to small adversarial perturbations. In this paper, several extensions of generative stochastic networks (GSNs) are proposed to improve the robustness of neural networks to random noise and adversarial perturbations. Experimental...
Article
High voltage direct current (HVDC) transmission lines have been implemented in many countries, including Australia, Brazil, China and Sweden and the safety concerns as the result of the high electromagnetic-radiation underneath the HVDC lines have garnered increased public attentions. Here, we report on the model, design and testing of field-mill e...
Article
Recently, image simulation has widely attracted people’s attentions. In this paper, we propose a novel statistical approach to remove salt-and-pepper noise. A statistic model of the number of noise pixels is built and the noise ratio of the corrupted image is estimated. To remove the noise, two steps including pixels analysis and noise removal are...
Article
Intelligent coal stockpiles management system is significant for the next-generation cleaner power plants. Prevention of spontaneous combustion is a key issue for such a system, both in economic and environmental terms. As many factors can influence the self heating process of coal such as moisture and ash in coal, temperature distribution and stoc...
Article
Mesoscopic traffic simulation is a promising technology for handling large-scale dynamic traffic assignment problems. Meanwhile, GPU has been a research hotspot in the last decade because of its massive parallel performance compared with CPU. Although several works deal with GPU-based parallel performance, few have addressed the issue of real-world...
Article
Value function approximation plays an important role in reinforcement learning (RL) with continuous state space, which is widely used to build decision models in practice. Many traditional approaches require experienced designers to manually specify the formulization of the approximating function, leading to the rigid, non-adaptive representation o...
Article
Full-text available
It is important yet difficult to develop a multifunction simulation framework that provides simulation language specifications, compiler transferring language script to simulation components, simulation engine, etc. To provide simulationists with a useful multifunction framework, we develop a simulation-language-compiler-based modeling and simulati...
Article
Full-text available
An image degraded by noise is a common phenomenon. In this letter, we propose a novel adaptive fuzzy switching weighted mean filter to remove salt-And-pepper noise. The process of denoising includes two stages: noise detection and noise elimination. In the first stage, pixels in a corrupted image are classified into two categories: original pixels...
Conference Paper
For lower cost and better performance, different applications concurrently run in distributed simulation data centers (SDCs). Requests arrive in a highly dynamic way, and they are difficult to accurately predict. This work presents the Revenue-Aware Request Admission Control (RARAC) approach to intelligently accept arriving requests by incorporatin...
Conference Paper
To finally guarantee the stability and real-time data transmission of network-induced distributed systems, the study of the maximum allowable advancing step of a constructive flight simulation is carried out. Firstly, time performance indicators of the flight dynamics model and the closed control system model are obtained by analyzing their dynamic...
Conference Paper
With the development of military intelligence training system, behavior modeling becomes the core technology in Computer Generated Forces (CGF). The Context-based Reasoning (CxBR) Framework facilitates building behavior model of Computer Generated Forces because of its visualization, maintainability and non-predetermination. However, it is limited...
Conference Paper
Full-text available
Most existing HLA based simulation frameworks do not support simulation on WAN. To tackle this problem, we propose an Internet Communication Engine (ICE) based framework (ISF) that is capable of running on WAN, generating simulation codes automatically, and managing simulation procedures efficiently. ICE as well as its several powerful services is...
Conference Paper
Fire is one of the most deadly disaster in human life. Large quantities of people lose their life every year. Recently, researchers have carried out a great number of studies and simulations, however, few of which focus on evacuation in fire environment, let alone the impact on human health of fire?s products. This paper proposes an improved social...
Conference Paper
Opinion dynamics utilize mathematical and physical models and agent-based computational modeling tools to describe the interactive features and rules among individuals, reduction and explain the opinion formation and evolution in the real life. Based on the analysis of the basic ideas and methods of the modeling of opinion dynamics, the main conten...
Article
Most pedestrian evacuation literatures are about routing algorithm, human intelligence and behavior etc. Few works studied how to fully explore the function of authority/security figures, who know more of the environment by simply being there every day To evaluate the effect of authority figure (AF) in complex buildings, this paper fully investigat...
Conference Paper
Latin Hypercube Design (LHD) is a traditional method of Design Of Experiments (DOE) and is often employed in system analysis. However, this method imposes restriction on experiment trials and needs much computation capacity to obtain the optimal design. A novel experiment design method called ETPLHD is proposed in this paper to solve this problem....
Article
Simulation language is a key technology of integrated simulation based design software environment. A difficulty of developing simulation language is the compiler that automatically transfers simulation language Semantics to programming language such as C++. The contents and features of CMSL were introduced. And a compiler which could analyze simul...
Article
Full-text available
To simulate and analyze a large aircraft with severe wind shear, nonlinear equations for a rigid aircraft under various wind conditions were designed. In this paper, a double-vortex-ring method is adopted to generate a three-dimensional microburst wind field. This model incorporates a flight dynamics module and three flight simulations based on var...
Article
Cloud computing provides the essential infrastructure for multi-tier Ambient Assisted Living (AAL) applications that facilitate people's lives. Resource provisioning is a critically important problem for AAL applications in cloud data centers (CDCs). This paper focuses on modeling and analysis of multi-tier AAL applications, and aims to optimize re...
Article
Full-text available
Complex variable-structure systems (CVSSs) are a common type of complex systems that exhibit changes both at structural and behavior levels. Simulations of CVSSs challenge current collaborative execution methods with increasingly big and complex models. The emergence of multi-core paradigm presents an exciting opportunity to address such challenge,...
Book
This four-volume set (CCIS 643, 644, 645, 646) constitutes the refereed proceedings of the 16th Asia Simulation Conference and the First Autumn Simulation Multi-Conference, AsiaSim / SCS AutumnSim 2016, held in Beijing, China, in October 2016. The 265 revised full papers presented were carefully reviewed and selected from 651 submissions. The pape...
Book
This four-volume set (CCIS 643, 644, 645, 646) constitutes the refereed proceedings of the 16th Asia Simulation Conference and the First Autumn Simulation Multi-Conference, AsiaSim / SCS AutumnSim 2016, held in Beijing, China, in October 2016. The 265 revised full papers presented were carefully reviewed and selected from 651 submissions. The pap...
Book
This four-volume set (CCIS 643, 644, 645, 646) constitutes the refereed proceedings of the 16th Asia Simulation Conference and the First Autumn Simulation Multi-Conference, AsiaSim / SCS AutumnSim 2016, held in Beijing, China, in October 2016. The 265 revised full papers presented were carefully reviewed and selected from 651 submissions. The pape...
Book
This four-volume set (CCIS 643, 644, 645, 646) constitutes the refereed proceedings of the 16th Asia Simulation Conference and the First Autumn Simulation Multi-Conference, AsiaSim / SCS AutumnSim 2016, held in Beijing, China, in October 2016. The 265 revised full papers presented were carefully reviewed and selected from 651 submissions. The pap...
Article
We describe a metric named averaged ratio between complementary profiles to represent the distortion of map projections, and the shape regularity of spherical cells derived from map projections or non-mapprojection methods. The properties and statistical characteristics of our metric are investigated. Our metric (1) is a variable of numerical equiv...
Article
Full-text available
To construct a corresponding distributed system from a continuous system, the most convenient way is to partition the system into parts according to its topology and deploy the parts on separated nodes directly. However, system error will be introduced during this process because the computing pattern is changed from the sequential to the parallel....
Article
Full-text available
Continuous system can be discretized for computer simulation. Quantized state systems (QSS) method has been used to discretize time invariant systems based on the discretization of the state space. A HLA based QSS method is proposed in this paper to address issues of real-time advancements in simulation and an aircraft control example was introduce...
Article
Opinion exchange is useful when a military agent needs to take the opinions of others into account before decision making. Few studies have addressed opinion dynamics in military command and control (C2) organizations, which are often hierarchically ranked in a tree structure. Moreover, military agents should have different tolerance levels when co...
Article
Full-text available
For social organizations, formal communication transmits goals, policies, and directions, while informal communications are supplement to the formal structure filling organizational gaps and maintaining the linkages. This communication model has been researched and named opinion dynamics for some years. However, the relations between formal and inf...
Article
Full-text available
A maturing and promising technology, Cloud computing can benefit large-scale simulations by providing on-demand, anywhere simulation services to users. In order to enable multitask and multiuser simulation systems with Cloud computing, Cloud simulation platform (CSP) was proposed and developed. To use key techniques of Cloud computing such as virtu...
Article
Full-text available
A real-time infrastructure, called MLRTI, is proposed in this paper to fulfill the requirement of real-time simulation in distributed environment. There are two novel contributions in this work. Firstly, a flexible timing mechanism is proposed to integrate external time source and local timer utility, enabling the distributed nodes to advance their...
Article
A scheduling algorithm is crucial for real-time simulations because it guarantees that each model meets its deadline. Traditional online real-time scheduling algorithms such as Earliest Deadline First (EDF) introduce a high overhead when scheduling a large number of models. In this paper, a new algorithm called time-stepped load balancing (TLS) is...