The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we present a Failure Prediction System (FPS) using a novel algorithm that extracts frequent anomalous behaviors based on multi-scale trend analysis of multiple network parameters. The proposed Correlation Analysis Across Parameters algorithm (CAAP) utilizes multiple levels of timescale analysis to reveal the frequent anomalous behaviors. The CAAP philosophy is that failures usually...
In this paper, we present a novel algorithm that extracts frequent anomalous behaviors based on multi-scale trend analysis of individual network parameters. The proposed Frequent Anomalous Behavior Mining (FABM) algorithm utilizes multiple levels of time-scale analysis to reveal the frequent anomalous behaviors. This makes the proposed algorithm robust to unreliable, redundant, incomplete and contradictory...
Telecom broadband is a main channel supporting internet surfing in China. With the market competition development, customer churn management has become a kernel task of marketing for telecommunication operators. The traditional market research methods are difficult to support the challenge of churn. Data mining techniques are applied to the customer churn management, to establish an early-warning...
The following topics are dealt with: neural networks; evolutionary computing and genetic algorithms; fuzzy systems and soft computing; particle swarm optimization; artificial life and artificial immune systems; systems biology and neurobiology; support vector machine; rough and fuzzy rough set; knowledge discovery and data mining; kernel methods; supervised & semi-supervised learning; hybrid system;...
With the rapid changes taking place in the network operation environment, ISPs today face a challenge. Networks are becoming more complex with the inclusion of diverse types of devices. New services such as IPTV and VoIP make the jobs of network administrators more difficult, by requiring new equipment, with new protocols and new technologies. As well, ISPs are forced to reduce the costs of network...
Policies enable management systems to adapt to changes in management strategies. At run time, management agents use information from the policies to monitor attributes of managed objects, to determine if specific events have occurred and to take management actions. In order to do this, information from the policies must first be extracted. The extracted information is then used to configure management...
The following topics are dealt with: network security; network privacy; computer vision; signal processing; data mining; semantic Web; network architecture protocols; network management; wireless sensor networks;and mobile ad-hoc networks.
Most users in a mobile environment are moving and accessing wireless services for the activities they are currently engaged in. We propose the idea of complex activity for characterizing the continuously changing complex behavior patterns of mobile users. For the purpose of data management, a complex activity is modeled as a sequence of location movement, service requests, the cooccurrence of location...
We present a State Estimation based Internet traffic flow control system where the objective is to maximize the aggregate bandwidth utility of network sources over their transmission rates. The network links and sources are viewed as processors of distributed computation and the control mechanism is based on estimation and optimization framework to solve the dual problem. The novelty of our approach...
This event-condition-action(ECA) rule description language for Web Services(named WS-ECA) is the latest buzzword in the realm of autonomous, intelligent agent based Web Service oriented computing (AWSOC). This rule description language supports interactions among service oriented, heterogeneous devices in a pervasive computing environment. It is based on ECA rules, which are embedded in distributed...
Active Queue Management (AQM) can potentially reduce packet loss rate in the Internet. This is used by routers for control congestion, where packets are dropped before queues become full. In this paper, a new framework of AQM, namely NEWQUE active queue management algorithm supporting explicit congestion notification (ECN), is proposed. The objective of the new algorithm is to improve performance...
The gateway queuing performance depends on the marking/dropping probability function chosen. This function plays an important role in managing the gateway buffer. It maps the current congestion level to marking/dropping probability that is applied to each arriving packet. Active queue management mechanisms drop arriving packets probabilistically before the gateway buffer gets full. Fast Congestion...
Key management in wireless sensor networks is a challenging problem because public key cryptosystems are unsuitable for using in resource constrained sensor nodes, and the nodes could by physically compromised by an adversary. For the existing key pre-distribution schemes, as the number of compromised nodes increasing, the fraction of affected pairwise keys will increase quickly. As a result, a small...
Predominant resources for execution of any process are computational power and memory. In current Distributed system approaches, when the host system memory is overloaded and a process is executed on a remote system, then all the files, used by the process must also be transferred to the remote system. The host system may already be overloaded and it needs to transfer required files which in turn...
How to evaluate network management capability is one of important research topics about network management. This paper proposes a novel quantity evaluation method of network management capability, Network management capability model. In this paper, key factors about network management capability, such as network resource gross, distribution, heterogeneity, available resource, network management cost...
Customer needs are increasingly fulfilled by a seamless integration of products and services. Complexity grows for firms to understand customers since their perception of firm performance can be affected by either product manufacturers or service providers. Our study is attempting to identify possible spillover effects of quality and customer satisfaction between products and services. Potential moderators...
The data mining application to analysis of alarm correlation in the telecom network has been put out, the data mining algorithms of association rules and sequential patterns have been introduced, the comparing between two algorithms has been made, the analyzing & discussing of experimental result have been given with the alarming data of a certain network management center at Wuhan Telecom.
We consider the revenue management problem on communication networks with multiple classes of traffic. Bandwidth allocation is determined to maximize revenue under network users' quality of service requirements. This paper presents the sensitivity analysis of an average revenue function for given traffic class by varying bandwidth allocation, traffic demand and the number of virtual paths. Numerical...
In enterprises and residential networks, there are always multiple classes of traffic sharing the limited access bandwidth, and multiple token buckets are used to guarantee the usage of every class. At the same time, network managers hope to utilize the idle resource, in case of the bandwidth for some classes is redundant, for higher classes, as well as lower classes. A bi-direction adjustable multi-class...
Cooperative communication usually shares a common model-one source, several relays and one destination. In this paper, we consider the multi-source scenario in a cell to carry on cooperative communication. However, multi-user setting might causes interference in the network, given this interference, the process of relaying selection applies SINR (signal to interference noise ratio) as a criterion...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.