Showing papers in "China Communications in 2013"

Situation and development tendency of indoor positioning

Abstract: This paper introduces the significance of indoor positioning and analyzes the related problems. The latest research on indoor positioning is introduced. Further, the positioning accuracy and the cost of typical local and wide area indoor positioning systems are compared. The results of the comparison show that Time & Code Division-Orthogonal Frequency Division Multiplexing (TC-OFDM) is a system that can achieve real-time meter-accuracy of indoor positioning in a wide area. Finally, in this paper, we indicate that the seamless high-accuracy indoor positioning in a wide area is the development trend of indoor positioning. The seamless Location Based Services (LBS) architecture based on a heterogeneous network, key technologies in indoor positioning for decimeter-accuracy and seamless outdoor and indoor Geographic Information System (GIS) are elaborated as the most important research fields of future indoor positioning.

Power control algorithm of cognitive radio based on non-cooperative game theory

Abstract: This paper addresses the power control problems of Cognitive Radio (CR) under transmission power and interference temperature constraints. First, we propose the interference constraint which ensures that the Quality of Service (QoS) standards for primary users is considered and a non-cooperative game power control model. Based on the proposed model, we developed a logical utility function based on the Signal-to-Interference-Noise Ratio (SINR) and a novel algorithm that is suitable for CR network power control. Then, the existence and uniqueness of the Nash Equilibrium (NE) in our utility function are proved by the principle of game theory and the corresponding optimizations. Compared to traditional algorithms, the proposed one could converge to an NE in 3-5 iterative operations by setting an appropriate pricing factor. Finally, simulation results verified the stability and superiority of the novel algorithm in flat-fading channel environments.

Aspect-level opinion mining of online customer reviews

Abstract: This paper focuses on how to improve aspect-level opinion mining for online customer reviews. We first propose a novel generative topic model, the Joint Aspect/Sentiment (JAS) model, to jointly extract aspects and aspect-dependent sentiment lexicons from online customer reviews. An aspect-dependent sentiment lexicon refers to the aspect-specific opinion words along with their aspect-aware sentiment polarities with respect to a specific aspect. We then apply the extracted aspect-dependent sentiment lexicons to a series of aspect-level opinion mining tasks, including implicit aspect identification, aspect-based extractive opinion summarization, and aspect-level sentiment classification. Experimental results demonstrate the effectiveness of the JAS model in learning aspect- dependent sentiment lexicons and the practical values of the extracted lexicons when applied to these practical tasks.

LTE-satellite: Chinese proposal for satellite component of IMT-Advanced system

Abstract: As a complementary to terrestrial mobile communication systems, mobile satellite communication system can fill the gaps that cannot be covered by terrestrial network, and provides an irreplaceable solution for emergency communication in disaster. To pave the road for future satellite/terrestrial integrated communication networks, ITU-R invited proposals for candidate Radio Interface Technology (RIT) for the satellite component of International Mobile Telecommunications (IMT)-Advanced. China proposed the RIT of Long Term Evolution (LTE)-satellite as a candidate to be considered as IMT-Advanced satellite technology. The submitted LTE-satellite candidate RIT is specified based on terrestrial LTE-Advanced FDD standards that are developed in 3GPP. Considering satellite requirements, a number of modifications to LTE-Advanced are made to adapt to satellite radio transmission environments. This paper provides a general introduction of the new characteristics of LTE-satellite.

Energy-aware scheduling scheme using workload-aware consolidation technique in cloud data centres

Abstract: To reduce energy consumption in cloud data centres, in this paper, we propose two algorithms called the Energy-aware Scheduling algorithm using Workload-aware Consolidation Technique (ESWCT) and the Energy-aware Live Migration algorithm using Workload-aware Consolidation Technique (ELMWCT). As opposed to traditional energy-aware scheduling algorithms, which often focus on only one-dimensional resource, the two algorithms are based on the fact that multiple resources (such as CPU, memory and network bandwidth) are shared by users concurrently in cloud data centres and heterogeneous workloads have different resource consumption characteristics. Both algorithms investigate the problem of consolidating heterogeneous workloads. They try to execute all Virtual Machines (VMs) with the minimum amount of Physical Machines (PMs), and then power off unused physical servers to reduce power consumption. Simulation results show that both algorithms efficiently utilise the resources in cloud data centres, and the multidimensional resources have good balanced utilizations, which demonstrate their promising energy saving capability.

Offloading mobile data from cellular networks through peer-to-peer WiFi communication: A subscribe-and-send architecture

Abstract: Currently cellular networks do not have sufficient capacity to accommodate the exponential growth of mobile data requirements. Data can be delivered between mobile terminals through peer-to-peer WiFi communications (e.g. WiFi direct), but contacts between mobile terminals are frequently disrupted because of the user mobility. In this paper, we propose a Sub-scribe-and-Send architecture and an opportunistic forwarding protocol for it called HPRO. Under Subscribe-and-Send, a user subscribes contents on the Content Service Provider (CSP) but does not download the subscribed contents. Some users who have these contents deliver them to the subscribers through WiFi opportunistic peer-to-peer communications. Numerical simulations provide a robust evaluation of the forwarding performance and the traffic offloading performance of Subscribe-and-Send and HPRO.

Adaptive soft frequency reuse scheme for in-building dense femtocell networks

Abstract: Femtocell networks have emerged as a key technology in residential, office building or hotspot deployments that can significantly fulfill high data demands in order to offload indoor traffic from outdoor macro cells. However, as one of the major challenges, inter-femtocell interference gets worse in 3D in-building scenarios because of the presence of numerous interfering sources and then needs to be considered in the early network planning phase. The indoor network planning and optimization tool suite, Ranplan Small-cell®, makes accurate prediction of indoor wireless RF signal propagation possible to guide actual indoor femtocell deployments. In this paper, a new adaptive soft frequency reuse scheme in the dense femtocell networks is proposed, where multiple dense femtocells are classified into a number of groups according to the dominant interference strength to others, then the minimum subchannels with different frequency reuse factors for these groups are determined and transmit powers of the grouping sub-channels are adaptively adjusted based on the strength to mitigate the mutual interference. Simulation results show the proposed scheme yields great performance gains in terms of the spectrum efficiency relative to the legacy soft frequency reuse and universal frequency reuse.

Mining topical influencers based on the multi-relational network in micro-blogging sites

Abstract: In micro-blogging contexts such as Twitter, the number of content producers can easily reach tens of thousands, and many users can participate in discussion of any given topic. While many users can introduce diversity, as not all users are equally influential, it makes it challenging to identify the true influencers, who are generally rated as being interesting and authoritative on a given topic. In this study, the influence of users is measured by performing random walks of the multi-relational data in micro-blogging: ret-weet, reply, reintroduce, and read. Due to the uncertainty of the reintroduce and read operations, a new method is proposed to determine the transition probabilities of uncertain relational networks. Moreover, we propose a method for performing the combined random walks for the multi-relational influence network, considering both the transition probabilities for intra- and inter-networking. Experiments were conducted on a real Twitter dataset containing about 260 000 users and 2.7 million tweets, and the results show that our method is more effective than TwitterRank and other methods used to discover influencers.

Comparison of node architectures for elastic optical networks with waveband conversion

Abstract: In Elastic Optical Networks (EONs) with flexible bandwidth allocation, the blocking probability is high because of spectral contention. Similar to the functionality of wavelength conversion in Wavelength-Division-Multiplexing (WDM) networks, waveband conversion has been proposed to solve spectral contention in EONs. In this paper, we discuss the design of node architectures for an EON with waveband conversion. Four node architectures with shared Tuneable Waveband Converters (TWBCs) are proposed, and their blocking performances are evaluated by simulation. Simulation results show that the blocking probability of a node is significantly improved by waveband conversion. The sharing efficiency of waveband converters is also investigated. Simulation results show that at the same blocking rate, the node architecture with converters shared per node can save more than 20% waveband converters compared with that of the one with converters shared per link.

Energy-efficient transmission scheme for mobile data gathering in Wireless Sensor Networks

Abstract: Energy conservation in Wireless Sensor Networks (WSNs) has always been a crucial issue and has received increased attention in the recent years. A transmission scheme for energy-constrained WSNs is proposed in this paper. The scheme, called MIHOP (MIMO and Multi-hop), combines cluster-based virtual MIMO and multi-hop technologies. The multi-hop mode is employed in transmitting data when the related sensors are located within a specific number of hops from the sink, and the virtual MIMO mode is used in transmitting data from the remaining sensor nodes. We compare the energy consumption of different transmission schemes and propose an algorithm for determining the optimal hop count in MIHOP. A controllable mobile sink that reduces the energy consumed in sensor transmission is also adopted for data collection. The theoretical analysis and the Monte Carlo simulation demonstrate that the proposed scheme significantly outperforms individual virtual MIMO, multi-hop technologies, and double-string networks in terms of energy conservation. The energy consumption levels under the MIHOP scheme are approximately 12.98%, 47.55% and 48.30% less than that under virtual MIMO schemes, multi-hop networks and double-string networks, respectively.

ReTweeting analysis and prediction in microblogs: An epidemic inspired approach

Abstract: Microblogs currently play an important role in social communication. Hot topics currently being tweeted can quickly become popular within a very short time as a result of retweeting. Gaining an understanding of the retweeting behavior is desirable for a number of tasks such as topic detection, personalized message recommendation, and fake information monitoring and prevention. Interestingly, the propagation of tweets bears some similarity to the spread of infectious diseases. We present a method to model the tweets' spread behavior in microblogs based on the classic Susceptible-Infectious-Susceptible (SIS) epidemic model that was developed in the medical field for the spread of infectious diseases. On the basis of this model, future retweeting trends can be predicted. Our experiments on data obtained from the Chinese micro-blogging website Sina Weibo show that the proposed model has lower predictive error compared to the four commonly used prediction methods.

RGB-Depth feature for 3D human activity recognition

Abstract: We study the problem of human activity recognition from RGB-Depth (RGBD) sensors when the skeletons are not available. The skeleton tracking in Kinect SDK works well when the human subject is facing the camera and there are no occlusions. In surveillance or nursing home monitoring scenarios, however, the camera is usually mounted higher than human subjects, and there may be occlusions. The interest-point based approach is widely used in RGB based activity recognition, it can be used in both RGB and depth channels. Whether we should extract interest points independently of each channel or extract interest points from only one of the channels is discussed in this paper. The goal of this paper is to compare the performances of different methods of extracting interest points. In addition, we have developed a depth map-based descriptor and built an RGBD dataset, called RGBD-SAR, for senior activity recognition. We show that the best performance is achieved when we extract interest points solely from RGB channels, and combine the RGB-based descriptors with the depth map-based descriptors. We also present a baseline performance of the RGBD-SAR dataset.

Ant Colony Optimization for task allocation in Multi-Agent Systems

Abstract: Task allocation is a key issue of agent cooperation mechanism in Multi-Agent Systems. The important features of an agent system such as the latency of the network infrastructure, dynamic topology, and node heterogeneity impose new challenges on the task allocation in Multi-Agent environments. Based on the traditional parallel computing task allocation method and Ant Colony Optimization (ACO), a novel task allocation method named Collection Path Ant Colony Optimization (CPACO) is proposed to achieve global optimization and reduce processing time. The existing problems of ACO are analyzed; CPACO overcomes such problems by modifying the heuristic function and the update strategy in the Ant-Cycle Model and establishing a three-dimensional path pheromone storage space. The experimental results show that CPACO consumed only 10.3% of the time taken by the Global Search Algorithm and exhibited better performance than the Forward Optimal Heuristic Algorithm.

Optimal power allocation for multiuser underlay cognitive radio networks under QoS and interference temperature constraints

Abstract: Power allocation is an important issue for Cognitive Radio Networks (CRNs), since it needs to consider the Quality of Service (QoS) for Secondary Users (SUs) while maintaining the interference power to Primary User (PU) below the Interference Temperature (IT) threshold. In this paper, based on Euclidean projection, we propose a distributed power control algorithm with QoS requirements to minimise the total power consumption of SUs under the time-varying channel scenario. Considering the maximum transmit power constraints and the minimum signal to interference plus noise constraints for each SU, together with the IT constraints for each PU, the power allocation problem is transformed into a convex optimization problem without auxiliary variables, and is solved by the Lagrangian dual method with less information exchange. Simulation results demonstrate that the proposed scheme is superior to the Iterative Water-Filling Algorithm (IWFA).

Non-line-of-sight ultraviolet communication performance in atmospheric turbulence

Abstract: Non-Line-of-Sight (NLOS) Ultraviolet (UV) communication uses the atmosphere as a propagation medium. As the communication range increases, turbulence becomes a significant atmospheric process that affects the propagation of optical waves. This paper presents a more accurate NLOS channel model by considering turbulence-induced Scintillation Attenuation (SA). Then, the Bit Error Rate (BER) during turbulence of the NLOS UV communication system with On-Off Keying (OOK) modulation and Maximum Likelihood (ML) detection is analysed and compared with that in free space without turbulence. The BER dependence is also analysed for different factors, including the refractive index structure parameter, transceiver range, pointing angles, transmitted power, and data rate.

Dynamic target wireless network selection technique using fuzzy linguistic variables

Abstract: Even though various wireless Network Access Technologies (NATs) with different specifications and applications have been developed in the recent years, no single wireless technology alone can satisfy the anytime, anywhere, and any service wireless-access needs of mobile users. A real seamless wireless mobile environment is only realized by considering vertical and horizontal handoffs together. One of the major design issues in heterogeneous wireless networks is the support of Vertical Handoff (VHO). VHO occurs when a multi-interface enabled mobile terminal changes its Point of Attachment (PoA) from one type of wireless access technology to another, while maintaining an active session. In this paper we present a novel multi-criteria VHO algorithm, which chooses the target NAT based on several factors such as user preferences, system parameters, and traffic-types with varying Quality of Service (QoS) requirements. Two modules i.e., VHO Necessity Estimation (VHONE) module and target NAT selection module, are designed. Both modules utilize several “weighted” users' and system's parameters. To improve the robustness of the proposed algorithm, the weighting system is designed based on the concept of fuzzy linguistic variables.

Mining and modelling the dynamic patterns of service providers in cellular data network based on big data analysis

Abstract: Understanding the dynamic traffic and usage characteristics of data services in cellular networks is important for optimising network resources and improving user experience. Recent studies have illustrated traffic characteristics from specific perspectives, such as user behaviour, device type, and applications. In this paper, we present the results of our study from a different perspective, namely service providers, to reveal the traffic characteristics of cellular data networks. Our study is based on traffic data collected over a five-day period from a leading mobile operator's core network in China. We propose a Zipf-like model to characterise the distributions of the traffic volume, subscribers, and requests among service providers. Nine distinct diurnal traffic patterns of service providers are identified by formulating and solving a time series clustering problem. Our work differs from previous related works in that we perform measurements on a large quantity of data covering 2.2 billion traffic records, and we first explore the traffic patterns of thousands of service providers. Results of our study present mobile Internet participants with a better understanding of the traffic and usage characteristics of service providers, which play a critical role in the mobile Internet era.

Analyzing motion patterns in crowded scenes via automatic tracklets clustering

Abstract: Crowded scene analysis is currently a hot and challenging topic in computer vision field. The ability to analyze motion patterns from videos is a difficult, but critical part of this problem. In this paper, we propose a novel approach for the analysis of motion patterns by clustering the tracklets using an unsupervised hierarchical clustering algorithm, where the similarity between tracklets is measured by the Longest Common Subsequences. The tracklets are obtained by tracking dense points under three effective rules, therefore enabling it to capture the motion patterns in crowded scenes. The analysis of motion patterns is implemented in a completely unsupervised way, and the tracklets are clustered automatically through hierarchical clustering algorithm based on a graphic model. To validate the performance of our approach, we conducted experimental evaluations on two datasets. The results reveal the precise distributions of motion patterns in current crowded videos and demonstrate the effectiveness of our approach.

Tree-structured parallel regeneration for multiple data losses in distributed storage systems based on erasure codes

Abstract: To reduce the time required to complete the regeneration process of erasure codes, we propose a Tree-structured Parallel Regeneration (TPR) scheme for multiple data losses in distributed storage systems. Under the scheme, two algorithms are proposed for the construction of multiple regeneration trees, namely the edge-disjoint algorithm and edge-sharing algorithm. The edge-disjoint algorithm constructs multiple independent trees, and is simple and appropriate for environments where newcomers and their providers are distributed over a large area and have few intersections. The edge-sharing algorithm constructs multiple trees that compete to utilize the bandwidth, and make a better utilization of the bandwidth, although it needs to measure the available bandwidth and deal with the bandwidth changes; it is therefore difficult to implement in practical systems. The parallel regeneration for multiple data losses of TPR primarily includes two optimizations: firstly, transferring the data through the bandwidth optimized-paths in a pipeline manner; secondly, executing data regeneration over multiple trees in parallel. To evaluate the proposal, we implement an event-based simulator and make a detailed comparison with some popular regeneration methods. The quantitative comparison results show that the use of TPR employing either the edge-disjoint algorithm or edge-sharing algorithm reduces the regeneration time significantly.

Emotional state transition model based on stimulus and personality characteristics

Abstract: In order to use mathematical methods to study how cognitive reappraisal strategies affect the output state of emotions, Gross's cognitive reappraisal strategy is transformed into a quantitative parameter which is proposed to describe the general perception of emotional events on the basis of the emotion regulation. According to Gross's emotional regulation model, the Finite State Machine (FSM) model is used for describing the process of emotional state transition and the Likert 5 grading scale is introduced to study the level of an individual's reappraisal according to the participant's self-evaluation. The experimental results verify that the algorithm can effectively describe the relationship between the reappraisal strategy, emotional events and an emotiongenerative process. There are multiple dimensions of a human's emotional state. Thus, in the field of human-computer interaction, further research requires the development of a specific algorithm which can be implemented by a computer for the emotion regulation process.

Dynamic optimization of handover parameters adjustment for conflict avoidance in long term evolution

Abstract: In order to achieve dynamical optimization of mobility load balancing, we analyze the conflict between mobility load balancing and mobility robustness optimization caused by the improper operation of handover parameters. To this end, a method of Handover Parameters Adjustment for Conflict Avoidance (HPACA) is proposed. Considering the movement of users, HPCAC can dynamically adjust handover range to optimize the mobility load balancing. The movement of users is an important factor of handover, which has a dramatic impact on system performance. The numerical evaluation results show the proposed approach outperforms the existing method in terms of throughput, call blocking ratio, load balancing index, radio link failure ratio, ping-pong handover ratio and call dropping ratio.

Design of wireless multi-media sensor network for precision agriculture

Abstract: To satisfy the needs of modern precision agriculture, a Precision Agriculture Sensing System (PASS) is designed, which is based on wireless multi-media sensor network. Both hardware and software of PASS are tailored for sensing in wide farmland without human supervision. A dedicated single-chip sensor node platform is designed specially for wireless multi-media sensor network. To guarantee the bulky data transmission, a bitmap index reliable data transmission mechanism is proposed. And a battery-array switching system is design to power the sensor node to elongate the lifetime. The effectiveness and performance of PASS have been evaluated through comprehensive experiments and large-scale real-life deployment.

Cross-layer design and ant-colony optimization based routing algorithm for low earth orbit satellite networks

Abstract: To improve the robustness of the Low Earth Orbit (LEO) satellites networks and realise load balancing, a Cross-layer design and Ant-colony optimization based Load-balancing routing algorithm for LEO Satellite Networks (CAL-LSN) is proposed in this paper. In CAL-LSN, mobile agents are used to gather routing information actively. CAL-LSN can utilise the information of the physical layer to make routing decision during the route construction phase. In order to achieve load balancing, CAL-LSN makes use of a multi-objective optimization model. Meanwhile, how to take the value of some key parameters is discussed while designing the algorithm so as to improve the reliability. The performance is measured by the packet delivery rate, the end-to-end delay, the link utilization and delay jitter. Simulation results show that CAL-LSN performs well in balancing traffic load and increasing the packet delivery rate. Meanwhile, the end-to-end delay and delay jitter performance can meet the requirement of video transmission.

Emerging of Telco Cloud

Abstract: Cloud computing is the latest major evolution in computing technology. The convergence between cloud computing and telecom networks could significantly reduce costs and bring new business opportunities for operators. Currently, traditional telecom operators are embarrassed by the fact that the increase in revenue cannot catch up with the quick growth of users and the expansion of networks. With the introduction of the cloud computing technology, operators can virtualize the network functions through low-cost COTS IT hardware. All kinds of existing services can be cloudi-fied and thus obtain the benefits of statistical multiplexing among IT resources. With the Telco Cloud architecture, operators can manage both IT infrastructures and network resources intelligently in order to adapt to the dynamic demands from the application and to establish open platforms for developing new services.

Spectrum handoff scheme based on recommended channel sensing sequence

Abstract: We consider the spectrum handoff delay of a Secondary User (SU) in cognitive radio networks. We propose a spectrum handoff scheme based on Recommended Channel Sensing Sequence (RCSS), which aims to optimise the spectrum handoff delay subject to the sensing reliability and link maintenance constraints. There are two cases that should be considered: 1) the SU performs spectrum handoff successfully during the current frame, and 2) the SU successfully performs the spectrum handoff using several frames. We develop a dynamic programming algorithm for RCSS to identify the optimal sensing sequence for the first case, and an updating algorithm for RCSS to improve the handoff performance for the second case. The numerical results confirm that the proposed RCSS handoff scheme can achieve better handoff delay performance than others when the received signal-to-noise ratios of the Pus' signals on different channels are non-identical.

Certificateless proxy identity-based signcryption scheme without bilinear pairings

Abstract: Signcryption, which was introduced by ZHENG, is a cryptographic primitive that fulfils the functions of both digital signature and encryption and guarantees confidentiality, integrity and non-repudiation in a more efficient way. Certificateless signcryption and proxy signcryption in identity-based cryptography were proposed for different applications. Most of these schemes are constructed by bilinear pairings from elliptic curves. However, some schemes were recently presented without pairings. In this paper, we present a certificateless proxy identity-based signcryption scheme without bilinear pairings, which is efficient and secure.

User-oriented graph based frequency allocation algorithm for densely deployed femtocell network

Abstract: Femtocell is a promising technology for improving indoor coverage and offloading the macrocell. Femtocells tend to be densely deployed in populated areas such as the dormitories. However, the inter-tier interference seriously exists in the co-channel Densely Deployed Femtocell Network (DDFN). Since the Femtocell Access Points (FAPs) are randomly deployed by their customers, the interference cannot be predicted in advance. Meanwhile, new characteristics such as the short radius of femtocell and the small number of users lead to the inefficiency of the traditional frequency reuse algorithms such as Fractional Frequency Reuse (FFR). Aiming for the downlink interference coordination in the DDFN, in this paper, we propose a User-oriented Graph based Frequency Allocation (UGFA) algorithm. Firstly, we construct the interference graph for users in the network. Secondly, we study the conventional graph based resources allocation algorithm. Then an improved two steps graph based frequency allocation mechanism is proposed. Simulation results show that UGFA has a high frequency reuse ratio mean while guarantees a better throughput.

Hybrid detection and tracking of fast-flux botnet on domain name system traffic

Abstract: Fast-flux is a Domain Name System (DNS) technique used by botnets to organise compromised hosts into a high-availability, load-balancing network that is similar to Content Delivery Networks (CDNs). Fast-Flux Service Networks (FFSNs) are usually used as proxies of phishing websites and malwares, and hide upstream servers that host actual content. In this paper, by analysing recursive DNS traffic, we develop a fast-flux domain detection method which combines both real-time detection and long-term monitoring. Experimental results demonstrate that our solution can achieve significantly higher detection accuracy values than previous flux-score based algorithms, and is lightweight in terms of resource consumption. We evaluate the performance of the proposed fast-flux detection and tracking solution during a 180-day period of deployment on our university's DNS servers. Based on the tracking results, we successfully identify the changes in the distribution of FFSN and their roles in recent Internet attacks.

User identification based on multiple attribute decision making in social networks

Abstract: Social networks are becoming increasingly popular and influential, and users are frequently registered on multiple networks simultaneously, in many cases leaving large quantities of personal information on each network. There is also a trend towards the personalization of web applications; to do this, the applications need to acquire information about the particular user. To maximise the use of the various sets of user information distributed on the web, this paper proposes a method to support the reuse and sharing of user profiles by different applications, and is based on user profile integration. To realize this goal, the initial task is user identification, and this forms the focus of the current paper. A new user identification method based on Multiple Attribute Decision Making (MADM) is described in which a subjective weight-directed objective weighting, which is obtained from the Similarity Weight method, is proposed to determine the relative weights of the common properties. Attribute Synthetic Evaluation is used to determine the equivalence of users. Experimental results show that the method is both feasible and effective despite the incompleteness of the candidate user dataset.

Video-based crowd density estimation and prediction system for wide-area surveillance

Abstract: Crowd density estimation in wide areas is a challenging problem for visual surveillance. Because of the high risk of degeneration, the safety of public events involving large crowds has always been a major concern. In this paper, we propose a video-based crowd density analysis and prediction system for wide-area surveillance applications. In monocular image sequences, the Accumulated Mosaic Image Difference (AMID) method is applied to extract crowd areas having irregular motion. The specific number of persons and velocity of a crowd can be adequately estimated by our system from the density of crowded areas. Using a multi-camera network, we can obtain predictions of a crowd's density several minutes in advance. The system has been used in real applications, and numerous experiments conducted in real scenes (station, park, plaza) demonstrate the effectiveness and robustness of the proposed method.