In this study, we propose a novel, context-based, location-aware algorithm for identifying low-level micro-activities that can be used to derive complex activities of daily living (ADL) performed by home-care patients. This identification is achieved by gathering the location information of the target user by using a wearable beacon embedded with a magnetometer and inertial sensors. The shortcomings of beacon-signal stability and mismatch issues in magnetic-field sequences are overcome by adopting a hybrid, three-phase approach for deducing the locus of micro-activities and their associated zones in a smart home environment. The suggested approach is assessed in two different test environments, where the main intention is to map the location of a person performing an activity with pre-defined house landmarks and zones in the offline labeled database. In addition to the recognition of low-level activities, the proposed method also identifies the person's walking trajectory within the same zone or between different zones of the house. The experimental results demonstrate that it is possible to achieve centimeter-level accuracy for the recognition of micro-activities and to achieve the classification accuracy of 85% for trajectory prediction. These results are encouraging and imply that the collection of accurate low-level information for ADL recognition is possible using integration of inertial sensors, magnetic field and Bluetooth low energy (BLE) technologies from the wearable beacon without relying on other infrastructural sensors.

Conventional Radio Frequency (RF) based fingerprinting still remains one of the most popular methods amongst other indoor positioning techniques due to its inherent accuracy and reliability. However, not much prominence has been shown in analyzing certain factors that may affect the outcome of the fingerprinting method while designing the localization system. In this paper, we conduct a study to infer if a reduced number of receivers equipped with higher gain antennas can provide improved Bluetooth Low Energy (BLE) fingerprinting performance in a complex indoor environment. The evaluation is performed in a standard domestic apartment with an activity centric approach using a single wearable beacon and multiple receivers. A rank based route selection algorithm is used to list the candidate positions or routes that indicate the most likely path on which the subject was travelling. Furthermore, we discuss the benefits of implementing the inverse fingerprinting method with a trajectory based prediction model and also examine the effect of surrounding electrical interference. Experimental results indicate that an increased antenna gain in addition to deploying an adequate number of receivers have a positive effect on the overall ranking accuracy.

Device-free or off-body sensing methods, such as Lidar, can be used for location-driven Activities during Daily Life (ADL) recognition without the need for a mobile host such as a human or robot to use on-body location sensors. Because if such an attachment fails, or is not operational (powered up), when such mobile hosts are device free, it still works. Hence, this paper proposes an innovative method for recognizing ADLs using a state-of-art seq2seq Recurrent Neural Network (RNN) model to classify centimeter level accurate location data from a low-cost, 360°rotating 2D Lidar device. We researched, developed, deployed and validated the system. The results indicate that it can provide a centimeter-level localization accuracy of 88% when recognizing 17 targeted location-related daily activities.

In this paper a novel cloud-based Emergency Warning System (EWS) is described, using India as a primary case study. India is a country with nearly two dozen officially recognized languages and divergent communication technologies spread across a large geographical area. As of yet, this diversity has made the deployment of a single nationwide EWS near impossible. To address this deficiency, we have developed an EWS with adaptation as a central design tenet. This adaptation occurs on three levels: Dissemination adaptation addresses civilians' heterogeneous communication technologies; information adaptation morphs warnings to best reflect the capabilities of these communication technologies and users; while presentation adaptation is used to render information to the user in the most appropriate manner. We have developed a full cloud-based prototype, including the full EWS infrastructure and a civilian Android app.

Many software systems operate across different geographically distributed hardware platforms, operating systems and programming languages. Publish/subscribe based Message Oriented Middleware (MOM) provides loose coupling and an efficient, asynchronous and scalable way of communication. However, as the complexity of such systems increase, manual verification of reconfiguration policies becomes unrealistic. The task calls for automated means of proof-checking configuration information in order to improve the reliability of large-scale MOM systems. This paper proposes a new model checking approach with temporal logic specifications to design and verify a system configuration. Model checking is a powerful technique, however the creation of appropriate finite state models for the systems being checked are complex and difficult to use in practice by non-formalists. The research presented in this paper finds suitable abstractions that reduce the system to a finite state model. The tools we developed for the generation of such models can be easily used by non-formalists. The systems models created using our techniques manages state explosion thanks to the choices of our abstractions. An example of the use of our tools and techniques is presented for a 50 node MOM, where the reachability of all topics and the presence of loops are proof-checked.

A probabilistic approach for outdoor location estimation using GSM received signal strength (RSS) from base stations (BSs) is presented. The proposed approach first divides the region of interest into different clusters based on deviations from the path loss model for each RSS component. In each cluster, the proposed algorithm uses principal component analysis (PCA) to intelligently transform RSS into new uncorrelated dimensions. This retains accuracy by not losing the substantial RSS correlations in each cluster, but also accommodates the different RSS distributions in each cluster. Our experiments are conducted in a real GSM outdoor environment. The proposed approach is compared with a traditional probabilistic algorithm for three different area partitioning methods. The experimental results show that the positioning accuracy is significantly improved and our clustering scheme gives good support for location estimation. Furthermore, it also can be concluded that the clustering scheme created by using deviation RSS based on Mahalanobis distance performs better than that using deviation based on Euclidean distance in a complex environment. What's more, the proposed method can reduce the number of training data used while maintaining the accuracy required.

This paper presents results for an approach for indoor location estimation that integrates received signal strength (RSS) data from both WiFi and GSM networks. Previous work has focused on relatively small indoor environments. In many potential applications, getting approximate location information, such as in which room the mobile user is, is adequate. A hierarchical clustering method is used to partition the RSS space. To choose the best transmitters in a partition, we assess the amount of RSS variance that is attributable to different base stations (BSs) or access points (APs) by transforming the RSS tuples into principal components (PCs). This allows us to retain most of the useful information of detectable transmitters in fewer dimensions. In our experiments, we collected WiFi and cellular RSS on the 2nd and 3rd-floor electronic engineering (EE) building in Queen Mary campus. The experiment results show that the proposed method can provide a good accuracy of room prediction, especially when we integrate WiFi RSS with GSM RSS together to do the positioning.

To increase frequency efficiency in cellular communication networks, this paper describes a cell coloring based distributed frequency allocation approach (C-DFA) for all kinds of cellular networks. C-DFA has high computational efficiency and is simpler to realize than other distributed approaches. Building on C-DFA, a distributed dynamic fractional frequency allocation (DDFFA) algorithm is designed for IEEE 802.16j supported Relay Based Cellular Networks (RBCN). It is shown that: a) C-DFA can better realize frequency efficiency and network resilience compared to centralized traditional distributed frequency allocation approach. b) DDFFA can significantly increase frequency efficiency to provide high capacity and throughput to the RBCN though at the cost of extra computation and BS-BS communication. The evaluations and analysis are based on moderate and high user congestion RBCN scenarios.

In order to provide a more resilient communication for a Neighborhood Watch type (NHW) system, a mobile middleware architecture using delay-tolerant network (DTN) technology and publish/subscribe concepts is described. The purpose of the middleware is to add resilience and reach to wireless communications, and also to reduce the battery drainage of the mobile devices, hence extending their operational lifetime. A prototype developed on the Android mobile platform is presented and the effects of multiple radio access, routing algorithm and application activity on energy efficiency are investigated.

Relay Based Cellular Networks (RBCNs) are a key development in cellular networking technology. However, because of ever increasing demand and base station failure, RBCNs still suffer from user congestion and low resilience problems. This paper proposes two competing solutions: dynamic frequency allocation and antenna tilting to those problems. Firstly a new dynamic fractional frequency allocation algorithm and a heuristic antenna tilting algorithm are designed. The comparative benefits of each algorithm are investigated. Secondly, the additional benefits of applying the two algorithms sequentially or iteratively are evaluated. The benefits of iteratively integrating the two algorithms are more interesting. Such integration solution allows the two algorithms to be applied cooperatively. The evaluations are based on high demand scenarios and base station failure scenarios. The results show that for the high demand scenarios the new dynamic fractional frequency allocation algorithm is very powerful, and the advantage of antenna tilting is not large though present. However, for the BS failure case there is a marked additional benefit in antenna tilting. The integrated solution achieves significantly more benefit than simple sequential application of the two algorithms.

This paper describes an approach to providing more accurate estimates of current radio coverage and real-time monitoring of coverage changes over time, in the context of self-organizing networks (SON). Radio coverage probability models based on received signal strength (RSS) from base stations (BSs) in an outdoor environment are created. Clustering is used to partition the RSS space and a nonparametric probability approach is used to reliably estimate the radio coverage in each cluster, that is also used to test for discrepancies in the RSS coverage that may occur over time. It is assumed that data can be collected periodically from the physical environment. The analysis of discrepancies is based on models constructed from historical data and monitoring of current RSS from the mobile stations (MSs). The performance is evaluated using data generated from a network planning tool for a real environment.

An architecture for wireless communication between control centers and registered users in emergency situations when the cellular network is not operational is described. It is based on delay tolerant networks (DTN) and enables mobile users with multiple radio interface technologies to communicate across heterogeneous network technologies. With the help of asynchronous bundles passing from hop to hop, short message service (SMS), multimedia messaging and walkie-talkie communication services are provided. The security issues for deployment of DTN communication applications using this architecture are also described. To assess the performance of the system, results from simulations for the degree of message penetration of broadcasts into the community and the probability that a control centre receives uplink messages are presented for different user densities, routing protocols on the system. The approach has been implemented on the Android mobile platform.

Cellular networks provide a range of communication services and are the principal wireless technology for domestic and business users. However, in cellular networks, an accident or a storm or a malicious action may cause a base station to fail and so be unable to provide radio coverage to sections of users. Such base station failures also might result in user congestion to nearby operational base stations. Delay Tolerate Network (DTN) is used here to mitigate these problems. DTN enables user devices to self-organize to connect to functional base stations or other users through multiple hops. This paper augments DTN routing using geographic routing and Ant Colony Optimization (ACO) methods to enhance user to base station connection and network load balancing. Three DTN routing protocols: Epidemic, Binary Spray and Wait, and PRoPHET are considered in this paper. Compared to the geographic method described, the ACO does not require users and base stations to provide their geographic location, which is more appropriate to the context in which such an approach might be applied.

This paper proposes a learning approach to solve adaptive Connection Admission Control (CAC) schemes in future wireless networks. Real time connections (that require lower delay bounds than non-real-time) are subdivided into hard realtime (requiring constant bandwidth capacity) or adaptive (that have flexible bandwidth requirements). The CAC for such a mix of traffic types is a complex constraint reinforcement learning problem with noisy fitness. Noise deteriorates the final location and quality of the optimum, and brings a lot of fitness fluctuation in the boundary of feasible and infeasible region. This paper proposes a novel approach that learns adaptive CAC policies through NEAT combined with Superiority of Feasible Points. The objective is to maximize the network revenue and also maintain predefined several QoS constraints.

This paper illustrates an approach to improving the user perceived QoS in heterogeneous networks through the use of a two layered optimization. The top layer views the problem of prediction of the network that would be chosen by a user where the criteria are offered bit rate, price, mobility support and reputation. At the second level, conditional on the strategies chosen by the users, the network operator hypothetically, reconfigures the network, subject to the network constraints of bandwidth and acceptable SNR and optimizes the network coverage to support users who would otherwise not be serviced adequately. This forms an iterative cycle until a solution that optimizes the user satisfaction subject to the adjustments that the network operator can make to mitigate the binding constraints, is found. The process is illustrated through a simple example using a Wi-Fi and a WiMAX network.

In this paper an intra-class utility-fair bandwidth adaptation scheme for multi-class traffic in wireless networks is proposed. Each call is assigned a utility function according to its traffic class. When the network is overloaded the allocated bandwidth of ongoing calls is degraded dynamically to meet two objectives in the preference order: (1) all calls within the same class receive fair utilities (2) the utility sum of all traffic classes in each individual cell of the network is maximized. Simulation results have demonstrated the superior performance of our scheme.

Bandwidth adaptation is becoming very attractive in wireless communications since it can dynamically adjust the allocated bandwidth of ongoing calls to cope with the network resource fluctuations. In this paper, we propose an optimal bandwidth adaptation algorithm for multi-class traffic QoS provisioning in wireless networks. With the proposed algorithm, each call is assigned a utility function that maps its bandwidth allocation to the user satisfaction. When the network is overloaded the allocated bandwidth of ongoing calls can be degraded to free bandwidth to accept the new and handoff calls. The bandwidth adaptation algorithm is performed to meet two objectives in the preference order: (i) all calls belonging to the same class receive fair utility (ii) the utility sum of all different classes of calls in each individual cell is maximized. Simulation results show that our proposed algorithm is effective in both attaining intra-class utility fairness and maximizing the total utility of the network while keeping the call blocking and handoff dropping probabilities low.

The paper investigates a new load balancing scheme for mobile networks that changes cellular coverage in real time according to the current geographic traffic distribution. A bubble oscillation algorithm from our previous work is customized to work with WCDMA mobile networks with simple semi-smart antennas. After the algorithm converges, the sector sizes for each cell are re-adjusted using a heuristic method to balance the traffic load within each cell. The results of tests performed on a WCDMA network simulator show that significant capacity improvement can be obtained for uneven traffic by using the intelligent control algorithm and low cost semi-smart antennas.

In current commercial wireless networks the service providers mediate between end users and network operators. The service provider can be a good candidate to integrate the different network technologies in a flexible and expandable platform. This paper presents a framework for a service provider to perform resource management in heterogeneous wireless networks. We analyse the characteristics of the service provider, summarize the required management functions and propose an architecture that allows the service provider to support real time resource management and seamless service handover in heterogeneous wireless networks. Additionally, the resource management functions based on two service level agreements are described, and an algorithm to perform QoS degrades of live connections has been implemented. A computer simulator has been developed to demonstrate the functionality and evaluate the performance of the architecture.

A shift in customer requirements together with a growth in more demanding applications has exposed the limitations of the best-effort service offered in IP networks. The paper presents a novel approach to managing traffic demand across IP networks by modifying existing routing algorithms and employing agent-based intelligence. A hybrid multi-agent architecture to manage quality of service (QoS) provisioning in the Internet is detailed. This achieves a balance between centralisation and distribution to improve both robustness and scalability. Intelligent agents are employed in this system to anticipate congestion and respond to changes in traffic patterns and other network stresses. A pseudo-delay mechanism is used to reroute less vital traffic from optimal routes. Results indicate that routing such traffic along sub-optimal paths enhances traffic performance in multi-class networks.

This paper investigates a new load balancing scheme for mobile networks that changes cellular coverage according to the geographic traffic distribution in real time. The performance of the whole cellular network is improved by contracting the antenna pattern around a traffic "hot spot" and expanding adjacent cells coverage to fill in the coverage loss. This is essentially a constrained multidimensional optimization problem. A novel bubble oscillation algorithm is proposed to address this problem. Any unserved traffic in the network is absorbed by the geographic load balancing in a similar way that a vacuum between bubbles is filled by bubble oscillations. Simulations have been performed to evaluate the system performance for different traffic scenarios, and the results are presented. Some discussions on this algorithm are also presented. The bubble oscillation algorithm described has the potential of being used in other similar multidimensional resource allocation problems.

IEEE 802.11 based WLANs have been widely deployed. Currently research is concentrating on how to find the best location for these access points plus tuning their antennas in order to seamlessly cover large areas. With more and more WLAN users, the air interface acts as bottleneck even in high-speed WLAN systems such as IEEE 802.11a. To improve the overall performance of IEEE 802.11 WLAN systems under congestion conditions, an agent-based radio resource management system is proposed that can dynamically change an AP's radio coverage pattern in cooperation with surrounding APs. A low-cost four sector semismart antenna array is used for access points. In this paper we present results from a simulation showing system performance. The use of intelligent agents and negotiations for indoor radio resource management is presented and discussed.

In this paper, we investigate a novel distributed load balance scheme for cellular networks, which intelligently changes cellular coverage according to the geographic traffic distribution in real time. The performance of the whole cellular network can be improved by contracting the base station antenna pattern around a traffic "hot spot" and expanding adjacent cells' coverage to fill in the loss. A cooperative negotiation approach with semi-smart antennas for cellular network coverage control is described in this paper. By the use of negotiations between adjacent base stations, optimum local coverage agreements can be achieved in the context of the whole cellular network. Results showing the advantage of this technique are also presented.

The performance of CDMA cellular networks can be improved by contracting the base station antenna pattern around the source of peak traffic and expanding adjacent cells coverage loss. A novel distributed load-balancing scheme for cellular networks, which intelligently changes cellular coverage according to the geographic traffic distribution in real time has been investigated. A cooperative negotiation approach with semi-smart antennas for the real-time control of cellular network coverage is used. By the use of real time negotiations between adjacent base stations, optimum local coverage agreements can be reached in the context of the whole cellular network. In this paper we concentrate on the description of how the desired cell shaping can be achieved by using antenna pattern synthesis techniques. Results showing the advantage of such a distributed load-balancing scheme are also presented.

We investigate a novel geographic load-balancing scheme for cellular networks that intelligently changes cellular coverage according to the geographic traffic distribution in real time. A cooperative negotiation approach for the real-time control of cellular network coverage is described. The performance of the whole cellular network is improved by contracting and shaping the antenna radiation pattern around a traffic "hot spot" and expanding adjacent cells coverage to fill in the coverage loss. By the use of real time cooperative negotiations between base stations and associated antennas, a near optimal local coverage agreement is reached in the context of the whole cellular network. Results showing the advantage of this technique are presented. Global optimization using constrained real-coded genetic algorithms (RCGA) provides a benchmark. Convergence using penalty functions to manage the constraints was first investigated but gave poor results. A transformation of the problem space is used to remove the constraints, and a criterion that is necessary for successful transformations is explained.

In this paper, we investigate a novel geographic load balance scheme, which intelligently changes cellular coverage according to the geographic traffic distribution in real time. The performance of the whole cellular network can be improved by contracting the antenna pattern around the source of peak traffic and expanding adjacent cells coverage to fill in the coverage loss. Our previous global optimization work based on scenarios with non-uniformly distributed traffic scenarios has shown the improvement of system capacity of such a dynamical cellular coverage planning scheme exceeds 20%. A cooperative negotiation approach for the real-time control of cellular network coverage is described in this paper. By the use of real time negotiations between base stations and associated antennas, some optimum local coverage agreements can be reached in the context of the whole cellular network.The simulation results using 200 continuous traffic snapshots are presented and followed by some conclusions finally.

In this paper the potential of a smart antenna based dynamic cell size and shape control scheme is assessed. By intelligent control of antenna pattern, the whole cellular network performance can be improved by contracting the antenna pattern around the source of peak traffic and expanding adjacent cells coverage to fill in the coverage loss. We perform a constrained optimization of antenna patterns by using real-coded genetic algorithms (RCGA), and develop a CDMA cellular system simulator to evaluate the overall improvement of the system performance. A transformation of the problem space is used to remove the principal power constraint. A problem with the intuitive transformation is shown and a revised one is presented. This highlights a problem with transformation-based methods in genetic algorithms. While the aim of transformation is to speed convergence, a bad transformation can be counter-productive. Optimization results for two scenarios show potential capacity improvement exceeding 20%.