Participatory Sensing is a new paradigm of mobile sensing where users are actively involved in leveraging the power of their smart devices to collect and share information. Motivated by its potential applications, we tackle in this paper the task assignment problem for a requester encountering a crowd of participants while considering their mobility model and sensing preferences. We aim to minimize the overall processing time of sensing tasks. Hence, we introduce first the Mobility-Aware Task Assignment scheme in both oFfline (MATAF) and oNline (MATAN) models where requesters investigate the participants' arrival model in different compounds of the sensing region. Further, we enhance such schemes by jointly taking into account participants' mobility and sensing preferences. We advocate then two other task assignment models, P-MATAF (offline) and P-MATAN (online). All proposed algorithms adopt a greedy-based selection strategy and address the minimization of the average makespan of all sensing tasks. We conduct extensive performance evaluation based on real traces while varying the number of tasks and associated workloads. Results proved that our proposed schemes have achieved lower average makespan and higher number of delegated tasks.

Abstract In service‐oriented environments, service providers orchestrate distributed services from other providers to create new composite enterprise services. A component service can be invoked jointly by several distributed composite service providers. However, because a composite service is provided to the consumers as an integrated service, when failures or dissatisfaction of the consumers occurs, it is not possible to directly identify the untrustworthy component. In this paper, we describe a collaborative trustworthiness determination approach using optimisation that can provide a solution to selecting trustworthy component service constructs based on monitoring and consumer quality of experience reporting of existing composite services from peer providers. Copyright © 2014 John Wiley & Sons, Ltd.

The efficient radio resource management and interference coordination schemes became an important requirement for the successful adoption of heterogeneous networks with small cells. In this approach, a large number of low-power devices is deployed to increase the spatial frequency reuse of the selected area. In this paper, we propose a distributed multi-agent strategy, where small cells locally control resource usage to maximize the overall system capacity. The main goal is to provide each cell with the ability to make its decision autonomously while taking into account the resource occupation of the surrounding cells. We study the coexistence with non-cooperative macroenvironment and propose a mechanism to increase the efficiency of learning with a smart safe-shift procedure. We illustrate the application of this distributed learning strategy for the subband allocation and propose several mechanisms to improve the convergence speed in the absence of communication. The performances of the proposed method are evaluated in the case of Long Term Evolution (LTE) setup and compared to a number of traditional resource allocation schemes. System level simulations show that it achieves a considerable improvement in system performance for heterogeneous deployment with non- cooperating agents, without compromising the efficiency of the system.

Modern cars are transforming towards autonomous cars capable to make intelligent decisions to facilitate our travel comfort and safety. Such "Smart Vehicles" are equipped with various sensor platforms and cameras that are capable to constantly sense tremendous amount of heterogeneous data from urban streets. This paper aims to identify the appropriate vehicles, important to be selected as information hubs for the efficient collection, storage and distribution of such massive data. Therefore, we propose an Information-Centric algorithm, "GRank" for vehicles to autonomously find their importance based on their reachability for different location-aware information in a collaborative manner, without relying on any infrastructure network. GRank is the first step to identify socially important information hubs to be used in the network. Results from scalable simulations using realistic vehicular mobility traces show that GRank is an efficient ranking algorithm to find important vehicles in comparison to other ranking metrics in the literature.

Modern cars are transforming towards autonomous cars capable to make intelligent decisions to facilitate our travel comfort and safety. Such "Smart Vehicles" are equipped with various sensor platforms and cameras to collect, store and share tremendous amount of heterogeneous data from urban streets. This paper addresses the efficient collection and distribution of such massive data by allowing a popular Smart Vehicle to autonomously decide its user relevant importance in the vehicular network without relying on the infrastructure network. Therefore, we propose an Information-Centric algorithm, "InfoRank" for a vehicle to rank different location- dependent information associated to it. It then uses the information importance to analytically find its influence in the network. InfoRank is the first step towards identifying the best information hubs to be used in the network for the efficient collection, storage and distribution of urban sensory information. Results from scalable simulations using realistic vehicular mobility traces show that InfoRank is an efficient ranking algorithm to find top information facilitator vehicles in comparison to other ranking metrics in the literature.

This paper presents an approach to monitoring and predicting the trustworthiness of services that are assembled from component services. In service compositions the number of component services that need to be aggregated may be large and dynamically changing. Additionally, the component services may vary in their importance to the value of the composite service and in their trustworthiness and resource capacity. Service compositions require the capability to dynamically adapt to changes that may occur at runtime. Those changes can occur in supply and demand, in the environment or in the component services' properties and behaviour. Service composers need to be able to respond swiftly to changed trustworthiness requirements and capabilities of service compositions, where those changes may not be easily predictable. With the availability of alternatives providing the same functionality as those already integrated in a composition, service composers can take advantage of this by replacing degrading or unsatisfactory components.

With the rapid growth of social networks and users communities the need to attain privacy for end-users becomes mandatory especially with the recent privacy breaches and the inefficiency of anonymisation techniques [1]. The problem of maintaining privacy in recommender services become increasingly important since it aims at finding information that might be interesting to end-users without disclosing their real interests to the service. In this paper, we present a middleware that runs in end-users’ mobile phones to provide referrals for joining different sub-communities in conferences or exhibitions in private way. Moreover, the proposed middleware facilitates identifying similarity between various attendees in order to build a community with specific interest without disclosing their real preferences or interests to other parties. Our proposed middleware equipped with two cryptography protocols in order to achieve this purpose. In such case, the attendees can submit their preferences in an encrypted form and the further computation of recommendation proceeds over the encrypted data using secure multiparty computation protocols. We also provide a scenario for community based recommender service for conferences along with experimentation results. Our results shows that our proposed middleware not only protect the attendees’ privacy, but also can maintain the recommendation accuracy.

While many aspects of the Future Internet are uncertain, one thing that is clear is that service demand will continue to rise. Also, advances in mobile devices and service technology will almost certainly cause service usage patterns to vary considerably. Another issue that the Future Internet community must be acutely aware of is the huge movement towards more sustainable forms of computing and communications technology. With the recent attention that has been put on IT energy consumption (data-centres in particular), all computing and communications systems need to consider their environmental impact from the outset. With that in mind, we propose a solution for determining the optimal placement of services in data-centre network, in order to maximize the overall renewable energy usage and minimize the cooling energy consumption. We then perform a series of experiments in order to evaluate our solution, incorporating dynamic service request profiles and actual weather and renewable energy production values.

The emergence of new platforms providing Internet protocol television (IPTV) services, such as Google TV and Apple TV is expected to revolutionize the way multimedia services are provided on the Internet. However, the existing network infrastructure falls well short of meeting the resource requirements to provide satisfactory levels of such services. This has led the service providers like Google to contemplate deploying large farms of network cables to transport the traffic generated by their IPTV services. However, the huge cost involved in achieving their target, means careful resource planning and meeting users' expectations are essential. In this paper, we propose an effective adaptive HYbrid delivery System Adaptive Content management (HySAC), which dynamically selects the mode of video delivery from unicast, multicast and peer-to-peer (P2P) based on the popularity of the respective videos. The videos are dynamically classified into high, medium and low popularity groups and, they are delivered using multicast, P2P and unicast methods respectively. HySAC reduces the start-up delay as the mode of delivery is well defined and the resource availability to support the delivery is guaranteed. We have evaluated the performance of HySAC on a realistic simulated environment and presented experimental results; they indicate that HySAC performs significantly better than pure unicast, multicast and P2P mechanisms. This paper also provides a mechanism to classify the videos into different popularity classes.

The performance and scalability of access control systems is a growing concern as organisations deploy ever more complex communications and content management systems. This paper describes how an (offline) experimental testbed may be used to address performance concerns. To begin, timing measurements are collected from a server component incorporating the Policy Decision Point (PDP) under test, using representative policies and corresponding requests. Our experiments with two XACML PDP implementations show that measured request service times are typically clustered by request type; thus an algorithm for request cluster identification is presented. Cluster characterisations are used as inputs to a PDP performance model for a given policy/request mix and an analytic (queueing) model is used to estimate the equilibrium server load for different mixes of request clusters. The analytic performance prediction model is validated and extended by discrete event simulation of a PDP subject to additional load. These predictive models enable network administrators to explore the capacity of the PDP for different overall loadings (requests per unit time) and profiles (relative frequencies) of requests.

IPTV providers employ third party content recommendation service to help end users find personalized content, and at the same time increase content sales and gain competitive advantage over other IPTV providers. However current implementations of recommendation services are mostly centralized where all the information about the users' profiles is stored on a dedicated server. A common fear among users is that their user profile data being misused by recommendation provider. Also sharing profile data makes the end users vulnerable to attacks like insider attacks, where an employee of the recommendation service may compromise the confidentiality and integrity of their profiles. For these reasons, privacy aware users intentionally decline to use recommendation or even provide inaccurate or wrong information because they consider it as untrusted service. On the other hand, to build an accurate recommendation model the user must reveal information that is typically considered private such as watching history, previous buying behaviour, content ratings, etc. Further privacy concerns arise when the user data are stored in countries that have privacy laws different from the country where the service is consumed. This poses a severe privacy hazard, since the users profiles are fully under the control of recommendation provider and stored in locations that are not legally bound to ensure the privacy of its users. Due to different legal structures that relate to data privacy laws in different legal jurisdictions maintaining user profile privacy is not a trivial solution. Regardless of the official legal framework requirements, when outsourcing users' profiles the private data should be kept safe when it is in the possession of any third party service. In this paper we introduce a private recommendation method using collaborative filtering techniques. The method preserves the privacy of its users when using the system and allows sharing data among different users in the network. We also introduce two obfuscations algorithms that protect users profile privacy as well as preserve the aggregates in the dataset to maximize the utility of information to provide accurate recommendations. Using these algorithms provides the privacy of users personal profiles.

Group communication offers a means for resource sharing and collaboration, often delivered through diverse technologies. One of the technologies, Instant Messaging, traditionally took the role of a facilitating service within such communities. Driven by a flexible XML based protocol, XMPP, instant messaging has developed functionality to a point where it can be considered a standalone group communication medium. Harnessing the extensible nature of the protocol continues to be a challenge. Alternative usage scenarios not envisioned by its core group management models have since emerged. This paper examines the current XMPP group models and how they can fulfill the requirements of a modern scenario centered on dynamic shared groups.

The complexity and dynamicity of networks continue to increase. Furthermore, specialization of network operations, the de-regulation of vertically integrated network operators, new demands from end users, as well as new business models for Over-The-Top players, give rise to new challenges and emphasizes that networking becomes ever more dynamic and organic in nature. To address these trends the research community has been investigating how to integrate management capabilities into the networks in order to meet the foremost requirements on reduced OPEX, but also to enable faster responses to agile business operations for the support of new value chains, applications, and services. These management capabilities are however envisaged as an add-on to the existing functionality. This would impose scalability, performance, and extensibility issues when such capabilities are deployed incrementally and ad-hoc. In this paper, we give an overview of selected recent advances in network architectures supporting self-management capabilities, and identify both their strengths and their limitations. This analysis provides input for a definition of the requirements and core properties for networks to become inherently self-managed. We then outline a generic model termed the “Netcell” that seeks to support the identified requirements and core properties.

Designing innovative communications services that scale to facilitate potential new usage patterns can pose significant challenges. This is particularly the case if these services are to be delivered over existing protocols and interoperate with legacy services. This work explores design choices for such a service: large scale message delivery to existing Instant Messaging users. In particular we explore message throughput, accuracy and server load for several alternative implementation strategies. These strategies focus on approaches to concurrency, with best practice in current and emerging techniques thoroughly benchmarked. Specifically, a conventional Java Executor approach is compared with a functional approach realised through Scala and its Actors framework. These could be termed “blocking I/O” technology. A third approach has also been measured - a “non-blocking I/O” based on an alternative to Java Virtual Machine approaches - employing Node.js and Javascript. We believe that some of the results are startling.

IEEE 802.11 wireless networks have received much attention over the past number of years. Still certain aspects of behavior of wireless networks have not been studied well enough. For example, understanding MAC layer packet delay distribution remains challenging yet. However, obtaining such distribution is highly beneficial for modeling QoS provided by wireless networks. This paper proposes a way of obtaining MAC delay distribution in case of single-hop networks. The proposed way is based on theory of terminating renewal processes and delivers approximation of good precision.

Growing popularity of wireless ad hoc networks leads to higher demands on performance of all TCP/IP stack layers. Usually ad hoc networks operate according to IEEE 802.11 standard which provides a MAC layer protocol that uses a single channel for data transmissions. However, increasing the number of data channels on MAC layer improves performance of ad hoc wireless networks by letting nodes simultaneously transmit data through different channels. Nevertheless network performance improvement will be diminished if routing mechanisms are not efficient and reactive to load changes within the network. In this paper we introduce a multi-channel MAC layer cooperative technique that integrates gradient based routing to support multi-hop wireless transmission. We show that using the gradient based routing to support multi-channel MAC protocols can enhance overall throughput of the network, and improve network load balancing. Simulations have also been conducted to validate the proposed solution.

The performance and scalability of access control systems is growing more important as organisations deploy ever more complex communications and content management systems. Fine-grained access control is becoming more pervasive, so decisions are more frequent and policy sets are larger. We outline a flexible performance testing framework that accepts XACML PDP implementations (in the server component) and submits representative access control requests (from the client component) in a representative temporal ordering. The framework includes instrumentation and analysis modules to support performance experiments. We describe an initial realization of the framework and report on initial experiments comparing the performance of the SunXACML and Enterprise XACML PDPs.

QoS-aware network planning becomes increasingly important for network operators and ISP alike as the number and heterogeneity of applications supported by networks continue to increase. We have proposed an architecture and methodology to support QoS-aware route planning for IPTV networks. The route planning problem was formulated as a residual bandwidth optimization problem and solved using GA-VNS hybrid algorithm. The QoS guarantee is provided by performing route allocation for a QoS-aware demand matrix which is generated using efficient and accurate estimation of QoS requirements using empirical effective bandwidth estimations. This paper revisits our formerly proposed approach to perform residual bandwidth optimization with QoS guarantee in IPTV networks and proposes alterations and parameter settings to best suit the problem in terms of robustness and performance. This paper proposes the use of two cost functions to meet the above requirements and the use of a variation of the original VNS algorithm besides recommending the use of specific operators and general parameter settings. The proposals and recommendations are substantiated by the results of performance evaluations and analysis. The results indicate dramatic improvement when the proposed approaches are taken on board.

In this paper, we propose an approach that uses in-game reputation as a solution to the problem of cheating in massively multiplayer online games. What constitutes cheating is however quite context-specific and subjective, and there is no universal view. Thus our approach aims to adjust to the particular forms of cheating to which players object rather than deciding a priori which forms of cheating should be controlled.

The recent years have seen an explosive upsurge in the popularity of IPTV networks and the IPTV user base. The increased user base poses new challenges to IPTV provider in providing the IPTV services with the expected QoE to the users due to the increase in traffic and heterogeneity in networks. The VoD, being the most prominent and most lucrative of the triple play components, require efficient managing in order for the IPTV provider to meet the expectations of the users, i.e. efficient management of contents. In this paper, we propose PaCRAmby adding a new multicast approach SMoD which combines unicast and multicast, to our earlier proposed content replication strategy PaCRA. SMoD provides satisfactory levels of QoE by eliminating the batching delay which is present in the traditional multicast approaches by exploiting the segmentation of videos. We show that the application of SMoD significantly improves the performance of PaCRA in terms of resource utilization, rejection rate and number of content replications. We further recommend a pre-population strategy for video segments to improve the performance of SMoD by taking into account the segment numbers for future work.

Wireless networks have grown their popularity over the past number of years. Usually wireless networks operate according to IEEE 802.11, which specifies protocols of physical and MAC layers. A number of different studies have been conducted on performance of IEEE 802.11 wireless networks. However, questions of QoS control in such networks have not received sufficient attention from the research community. This paper considers modeling of QoS of IEEE 802.11 networks defined in terms of throughput requirements and packet loss probability limitations. An influence of sizes of packets being transmitted through the network on the QoS is investigated. Extensive simulations confirm results obtained from the mathematical model.

The recent years have seen an explosive upsurge in the popularity of IPTV networks and the IPTV user base. The increased user base poses new challenges to ISP in providing the IPTV services with the expected QoE to the users due to the increase in traffic and heterogeneity in networks. The VoD, being the most prominent and most lucrative of the triple play components, require efficient managing in order for the ISP to meet the expectations of the users, ie. efficient management of contents. The existing content management techniques that have been applied in CDN and P2P networks are not applicable to the VoD system in IPTV due to the difference in network characteristics. The available IPTV content management techniques can only provide sub-optimal performance as they do not take into account the load on the links. In this paper, we propose a new IPTV architecture that supports coordinated route planning and content management using overlays. We present a new distributed content management approach namely PaCRA which intelligently performs content management by taking into account the server storage status, network path status and the content utility. We present experimental evaluations that show that PaCRA performs significantly better than the other standard approaches. We further show that the traditionally used Zipf distribution fails to provide an approximation for content popularity distribution and propose a new content popularity distribution which is found to closely follow the actual video popularity distribution.

The current Internet infrastructure is facing a number of limitations that is not suitable to meet the growing number of services and users. In particular, one aspect that requires enhancement is routing, where original routing concepts were designed for static traffic patterns with minimal variations and supporting mainly low throughput traffic (e.g. Data). As the number of users as well as services supporting the user grows, the current routing mechanisms will not be feasible. In this paper we present a gradient based distributed routing technique that is based on discovering routes through a gradient field created in the topology. The gradient calculation is based on weighted sum of a number of components, which modifies the gradient field as the network load changes. Simulation results have also been presented to validate the proposed routing algorithm.

There is currently much debate in defining what form the future Internet will take. The current Internet is struggling to meet the needs of an ever-evolving society. This is largely due to the Internet now become a thriving marketplace with services at the core. The range, number and complexity of services are set to increase with an even more dynamic service environment envisioned in the future. However, as these services grow, service composition will become an important feature of the service environment, leading to new challenges in service discovery and composition mechanisms. At the same time, dynamic service environments will also require that the underlying infrastructure networks are flexible enough to handle the changing service landscape. One area this is particularly important is in dynamic routing to deal with highly dynamic and frequent service changes. In this paper, we adopt mechanisms from biology and apply these to the problems identified, resulting in an integrated bio-inspired service management and dynamic routing solution for Future Internet. We demonstrate how the bio-inspired mechanisms not only improve each problem individually, but through their integration also improve overall network performance. Simulation results are presented to validate the proposed solution.

This paper presents a purely empirical approach to estimating the effective bandwidth of aggregated traffic flows independent of traffic model assumptions. The approach is shown to be robust when used in a variety of traffic scenarios such as both elastic and streaming traffic flows of varying degrees of aggregation. The method then forms the basis of two Quality of Service related traffic performance optimisation strategies. The paper presents a cost efficient approach to supplying suitably accurate demand matrix input for QoS related network planning and a QoS provisioning, revenue maximising admission control algorithm for an IPTV services network. This paper summarises these approaches and discusses the major benefits of an appropriately accurate effective bandwidth estimation algorithm.

QoS-aware network planning becomes increasingly important for large network operators and ISPs as the number and heterogeneity of applications supported by networks continues to increase. This paper proposes a novel approach to performing residual bandwidth optimization with QoS guarantee to support IPTV services on the Internet backbone. The approach combines the use of a new highly scalable hybrid GAVNS algorithm (genetic algorithm with variable neighborhood search) with the efficient and accurate estimation of QoS requirements using empirical effective bandwidth estimations. The QoS requirements for expected traffic are estimated using a relatively small number of traffic samples for different traffic classes and a QoS-aware demand matrix is built based on the calculated effective bandwidth and expected mean rates. This paper further proposes a strategy to perform content replication to mitigate network load caused by VoD (video on demand) traffic component of IPTV traffic. Given such a demand matrix, experimental results indicate that the GA-VNS algorithm shows significantly better performance in comparison to OSPF in terms of link utilization distribution, maximum link utilization, rejection rate and suitability to incorporate content replication. Additional results indicate that GA-VNS algorithm is very effective under dynamic conditions when the knowledge of previous route plan is taken into consideration.

Heart disease is the number one killer in the civilized world, accounting for around 1.9 million people every year in the EU, with the associated annual health costs of approximately EUR 105 billion. Important aspects of treating cardiac problems are monitoring and directing critical data to key

The effectiveness of current anti-spam systems is limited by the ability of spammers to adapt to new filtering techniques and the lack of incentive for mail domains to filter outgoing spam. This paper describes a new approach to spam protection based on distributed trust management. This is motivated by the fact that the SMTP mail infrastructure is managed in a distributed way by a community of mail domain administrators. A trust overlay architecture and a new protocol is presented. The TOP AS protocol specifies how experiences and recommendations are communicated between a spam filter at each mail domain and its associated trust manager, and between trust managers of different mail servers. A technique for improving mail filtering using these trust measures is also described. Initial simulations indicate the potential of this approach to improve rates of false positives and false negatives in anti-spam systems

The vision of Autonomic Network Management seeks self-governance (e.g. self-organisation, self-management) capabilities amongst network devices and system to minimise complexities found in current network management. Policy based management system provides a mechanism to counter these complexities, where the system provides a consistent model for decision making process. In this paper we propose bio-inspired mechanisms to support network survivability that is integrated with policy based management. Our solution is based on adaptation and integration of various biological principles such as Blood Glucose Homeostasis, Chemotaxis, Reaction-Diffusion and Hormone Signaling. The bio-inspired principles support a high degree of robustness, which is a key feature towards adapting in fluctuating network environment. Simulations results have also been presented to illustrate our proposed solution.

In this paper we present a biological Nano and MEMS communication platform that uses Nano logic computation based on controlled cell-signaling mechanisms. The proposed solution also integrates compartmentalisation techniques to support parallel processing. Based on our solution, our objective is to create a nanoscale communication networks between various biological Nano and MEMS devices within a tissue to support various medical applications (e.g. patient monitoring).

This paper proposes a unique feedback governed multi layered architectural model to support ISP's traffic demands with multiple quality of service(QoS) constraints. The proposed model consists of different modules each responsible for a particular set of tasks. The most challenging task involved in satisfying the demands is routing the traffic subject to multiple QoS constraints for multiple internet service providers (ISP). Routing the traffic subject to multiple constraints itself is known to be an NP-hard problem. This paper addresses the problem of finding the optimum routes to satisfy the demands of different ISPs, where different ISPs have different demands and their priority of QoS keep changing. A genetic algorithm (GA) which makes use of heuristic technique is proposed in this paper. All the optimum routes are found in one run of the program, therefore the chromosome selected encodes all the demanded routes. This paper also makes use of employing a tournament selection mechanism where the diversity of the population is preserved while the best chromosomes are carried to the next generation. The evolutionary property of GA is utilised in this paper to evolve to suit the changing demands. The performance and the evolutionary property of the proposed solution are shown with the simulation tests.

In this paper we describe QoSPlan - a generalized process for preparing information relevant to QoS-aware IP network planning. QoSPlan is designed to reduce the cost of deployment and maintenance of traditional network monitoring systems for service providers, while maintaining a sufficient degree of precision. The process involves analysis of pre-existing accounting data to estimate a network-wide demand matrix. Part of this estimation process relates to the generalization of QoS-related effective bandwidth measurements taken from a set of collected packet traces. Based on experience, we offer recommendations on how to appropriately realise QoSPlan to maximise its accuracy and effectiveness when applied to different network traffic scenarios.

This paper is focused on the integration of strategies for managing trust in ad hoc and other unstructured networks and services. A general trust overlay architecture and model are provided, and the integration of a range of strategies is discussed. These include strategies for efficient exchange of trust information as well as for individual nodes to capture and use this information in making security decisions. Results are presented of simulations that assess the effectiveness of these strategies in ad hoc networks. Of particular interest is the robustness of the trust system when faced with malicious nodes that attempt to corrupt the system, possibly in collusion with each other.

Conference and social events provides an opportunity for people to interact and develop formal contacts with various groups of individuals. In this paper, we propose an efficient interaction mechanism in a pervasive computing environment that provide recommendation to users of suitable locations within a conference or expo hall to meet and interact with individuals of similar interests. The proposed solution is based on evaluation of context information to deduce each user's interests as well as bioinspired self-organisation mechanism to direct users towards appropriate locations. Simulation results have also been provided to validate our proposed solution.

This paper describes a collaborative approach to handling dynamic attack threats in mobile ad hoc networks. Our approach is biologically and socially motivated. Each network node maintains a trust score for each other node of which it is aware and distributes these to its neighbourhood. Services have associated trust thresholds - the more sensitive the service, the higher the threshold. We define a robust decentralised dynamic system involving nodes, services and trust scores that helps to quickly and reliably locate potential sources of attacks and their threat level. The paper presents results of simulations of the behaviour of the system's dynamics and its interpretation in the context of ad hoc networks.

In this paper we describe an activity recognition system capable of monitoring user activities in home environments. Activities are monitored by processing information from various sensors embedded in the environment that provide information pertinent to user's actions. We utilise the concept of self-organising object networks to gather and hierarchically process information related to user actions in a distributed manner. This information is then fed to the decision module which matches this information in the user's activity map in order to deduce user's activity. The decision module comprises a Bayesian network coupled with a rule-based engine which is used to provide accurate activity inference process.