The demand of indoor positioning solution is on the increase dramatically, and WiFi-based indoor positioning is known as a very promising approach because of the ubiquitous WiFi signals and WiFi-compatible mobile devices. Improving the positioning accuracy is the primary target of most recent works, while the excessive deployment overhead is also a challenging problem behind. In this thesis, the author is investigating the indoor positioning problem from the aspects of indoor map information and the ubiquity of WiFi signals. This thesis proposes a set of novel WiFi positioning schemes to improve the accuracy and efficiency. Firstly, considering the access point (AP) placement is the first step to deploy indoor positioning system using WiFi, an AP placement algorithm is provided to generate the placement of APs in a given indoor environment. The AP placement algorithm utilises the floor plan information from the indoor map, in which the placement of APs is optimised to benefit the fingerprinting- based positioning. Secondly, the patterns of WiFi signals are observed and deeply analysed from sibling and spatial aspects in conjunction with pathway map from indoor map to address the problem of inconsistent WiFi signal observations. The sibling and spatial signal patterns are used to improve both positioning accuracy and efficiency. Thirdly, an AP-centred architecture is proposed by moving the positioning modules from mobile handheld to APs to facilitate the applications where mobile handheld doesn’t directly participate positioning. Meanwhile, the fingerprint technique is adopted into the AP-centred architecture to maintain comparable positioning accuracy. All the proposed works in this thesis are adequately designed, implemented and evaluated in the real-world environment and show improved performance.

When asked to define where a geographic place is, people normally resort to using qualitative expressions of location, such as north of and near to. This is evident in the domain of social geography, where qualitative research methods are used to gauge people’s understanding of their neighbourhood. Using a GIS to represent and map the location of neighbourhood boundaries is needed to understand and compare people’s perceptions of the spatial extent of their neighbourhoods. Extending the GIS to allow for the qualitative modelling of place will allow for the representation and mapping of neighbourhoods. On the other hand, a collaborative definition of place on the web will result in the accumulation of large sets of data resources that can be considered “location-poor”, where place location is defined mostly using single point coordinates and some random combinations of relative spatial relationships. A qualitative model of place location on the Linked Data Web (LDW) will allow for the homogenous representation and reasoning of place resources. This research has analysed the qualitative modelling of place location on the LDW and in GIS. On the LDW, a qualitative model of place is proposed, which provides an effective representation of individual place location profiles that allow place information to be enriched and spatially linked. This has been evaluated using the application of qualitative spatial reasoning (QSR) to automatic reasoning over place profiles, to check the completeness of the representation, as well as to derive implicit links not defined by the model. In GIS, a qualitative model of place is proposed that provides a basis for mapping qualitative definitions of place location in GIS, and this has been evaluated using an implementation-driven approach. The model has been implemented in a GIS and demonstrated through a realistic case study. A user-centric approach to development has been adopted, as users were involved throughout the design, development and evaluation stages.

The ready availability of image-editing software makes it important to ensure the authenticity of images. This thesis concerns the detection and localization of cloning, or Copy-Move Forgery (CMF), which is the most common type of image tampering, in which part(s) of the image are copied and pasted back somewhere else in the same image. Post-processing can be used to produce more realistic doctored images and thus can increase the difficulty of detecting forgery. This thesis presents three novel methods for CMF detection, using feature extraction, surface fitting and segmentation. The Dense Scale Invariant Feature Transform (DSIFT) has been improved by using a different method to estimate the canonical orientation of each circular block. The Fitting Function Rotation Invariant Descriptor (FFRID) has been developed by using the least squares method to fit the parameters of a quadratic function on each block curvatures. In the segmentation approach, three different methods were tested: the SLIC superpixels, the Bag of Words Image and the Rolling Guidance filter with the multi-thresholding method. We also developed the Segment Gradient Orientation Histogram (SGOH) to describe the gradient of irregularly shaped blocks (segments). The experimental results illustrate that our proposed algorithms can detect forgery in images containing copy-move objects with different types of transformation (translation, rotation, scaling, distortion and combined transformation). Moreover, the proposed methods are robust to post-processing (i.e. blurring, brightness change, colour reduction, JPEG compression, variations in contrast and added noise) and can detect multiple duplicated objects. In addition, we developed a new method to estimate the similarity threshold for each image by optimizing a cost function based probability distribution. This method can detect CMF better than using a fixed threshold for all the test images, because our proposed method reduces the false positive and the time required to estimate one threshold for different images in the dataset. Finally, we used the hysteresis to decrease the number of false matches and produce the best possible result.

The questions to be addressed here are all aimed at beginning to assess the emergence and utility of social behaviour and social learning in artificial evolutionary systems. Like any biological adaptation, the adaptation to process and use social information must lead to an overall increase in the long term reproductive capability of any population utilising such an adaptation - this increase in fecundity also being accompanied by increased survivability and therefore adaptability. In nature, social behaviours such as co-operation, teaching and agent aggregation, all seem to provide improved levels of fitness, resulting in an improved and more robust set of general behaviours - in the human case these social behaviours have led to cumulative culture and the ability to rapidly adapt to, and thrive in, an astonishing number of environments. In this thesis we begin to look at why the evolutionary adaptation to process and use social information, leading to social learning and social behaviour, proves to be such a useful adaptation, and under which circumstances we would expect to see this adaptation, and its resulting mechanisms and strategies, emerge. We begin by asking these questions in two contexts; firstly what does social learning enable that incremental genetic evolution alone does not, and secondly what benefit does social learning provide in temporally variable environments. We go on to assess how differing social learning strategies affect the utility of social learning, and whether social information can be utilised by an evolutionary process without any accompanying within-lifetime learning processes (and whether the accommodation of social information results in any notable behavioural changes). By addressing the questions posed here in this way, we can begin to shed some light on the circumstances under which the adaptations for the accommodation and use of social information begin to emerge, and ultimately lead to the emergence of robust socially intelligent artificial agents.

No description available.

No description available.

Traditional marine monitoring systems such as oceanographic and hydrographic re- search vessels use either wireless sensor networks with a limited coverage, or expensive satellite communication that is not suitable for small and mid-sized vessels. This the- sis proposes an Internet of Marine Things data acquisition and cartography system in the marine environment using Very High Frequency (VHF) available on the majority of ships. The proposed system is equipped with sensors such as sea depth, tempera- ture, wind speed and direction, and the collected data is sent through a Ship Ad-hoc Network (SANET) to 5G edge clouds connected to sink/base station nodes on shore. The sensory data is ultimately aggregated at a central cloud on the internet to produce up to date cartography systems. Several observations and challenges unique to the marine environment have been discussed and feed into the solutions presented. We have investigated the application of appropriate data quantization and compression techniques to the marine sensor data collected in order to reduce the size of transmit- ted data and achieve better transmission efficiency. The impact of marine sparsity on the network is examined and a marine Mobile Ad-hoc/Delay Tolerant hybrid routing protocol (MADNET) is proposed to switch automatically between Mobile Ad-hoc Network (MANET) and Delay Tolerant Network (DTN) routing according to the network connectivity. The low rate data transmission offered by VHF radio has been investigated in terms of the network bottlenecks and the data collection rate achiev- able near the sinks. A sensory data management and transmission approach has also been proposed at the 5G network core using Information Centric Networks (ICN) aimed at providing efficient and duplicate less transmission of marine sensory read- ings from the base station/sink nodes towards the central cloud. Therefore, SANETs are realized as part of a 5G infrastructure for marine environment monitoring, paving the way to the Internet of Marine Things (IoMaT).

Advancements in computing, electronics and mechanical systems have resulted in the creation of a new class of vehicles called autonomous vehicles. These vehicles function using sensory input with an on-board computation system. Self-driving vehicles use an ad hoc vehicular network called VANET. The network has ad hoc infrastructure with mobile vehicles that communicate through open wireless channels. This thesis studies the design and implementation of a novel intelligent intrusion detection system which secures the external communication of self-driving vehicles. This thesis makes the following four contributions: It proposes a hybrid intrusion detection system to protect the external communication in self-driving vehicles from potential attacks. This has been achieved using fuzzification and artificial intelligence. The second contribution is the incorporation of the Integrated Circuit Metrics (ICMetrics) for improved security and privacy. By using the ICMetrics, specific device features have been used to create a unique identity for vehicles. Our work is based on using the bias in on board sensory systems to create ICMetrics for self-driving vehicles. The incorporation of fuzzy petri net in autonomous vehicles is the third contribution of the thesis. Simulation results show that the scheme can successfully detect denial-of-service attacks. The design of a clustering based hierarchical detection system has also been presented to detect worm hole and Sybil attacks. The final contribution of this research is an integrated intrusion detection system which detects various attacks by using a central database in BusNet. The proposed schemes have been simulated using the data extracted from trace files. Simulation results have been compared and studied for high levels of detection capability and performance. Analysis shows that the proposed schemes provide high detection rate with a low rate of false alarm. The system can detect various attacks in an optimised way owing to a reduction in the number of features, fuzzification.

Objective. The main goal of this research is proposing a novel method of onset detection for Self-Paced (SP) Brain-Computer Interfaces (BCIs) to increase usability and practicality of BCIs towards real-world uses from laboratory research settings. Approach. To achieve this goal, various Sound-Production Related Cognitive Tasks (SPRCTs) were tested against idle state in offline and simulated-online experiments. An online experiment was then conducted that turned a messenger dialogue on when a new message arrived by executing the Sound Imagery (SI) onset detection task in real-life scenarios (e.g. watching video, reading text). The SI task was chosen as an onset task because of its advantages over other tasks: 1) Intuitiveness. 2) Beneficial for people with motor disabilities. 3) No significant overlap with other common, spontaneous cognitive states becoming easier to use in daily-life situations. 4) No dependence on user’s mother language. Main results. The final online experimental results showed the new SI onset task had significantly better performance than the Motor Imagery (MI) approach. 84.04% (SI) vs 66.79% (MI) TFP score for sliding image scenario, 80.84% vs 61.07% for watching video task. Furthermore, the onset response speed showed the SI task being significantly faster than MI. In terms of usability, 75% of subjects answered SI was easier to use. Significance. The new SPRCT outperforms typical MI for SP onset detection BCIs (significantly better performance, faster onset response and easier usability), therefore it would be more easily used in daily-life situations. Another contribution of this thesis is a novel EMG artefact-contaminated EEG channel selection and handling method that showed significant class separation improvement against typical blind source separation techniques. A new performance evaluation metric for SP BCIs, called true-false positive score was also proposed as a standardised performance assessment method that considers idle period length, which was not considered in other typical metrics.

In today modern life smart electrical devices are used to make the human lives more comfortable. Actually, this is the combination of electronics and communications that provides the opportunity for real time communication while the measured electricity by smart meters is sent to the energy provider. In this way smart meters in residential areas play an important role for two way interaction between several users and energy provider. Solving an optimization problem with regard to consideration of satisfaction of both sides of users and energy providers tends to achieve the optimum price that is sent to the users to optimize their consumption in peak demand periods that is the main goal of demand response management programs. As nowadays the renewable energy plays an important role in providing the request of the users specially in residential areas consideration of the concept of uncertainty is an important issue that is considered in this thesis. Therefore, solving the optimization problem in presence of load uncertainty is important topic that is investigated. Another interesting issue is consideration of users' number variation in presence of load uncertainty in dynamic pricing demand response programs which gives the advantage of having good estimation of optimum consumption level of users according to the optimum announced price. In this thesis these issues are considered for solving an Income Based and Utility Base optimization problems that are further explained in upcoming chapters. In chapter III ,which provides the first contribution of the thesis a novel algorithm called Income Based Optimization (IBO) is defined and compared with previously proposed Utility Based Optimization problem (UBO). The price, users' consumption versus provided energy capacity by energy provider in 24 hours period are simulated and analyzed. The effect of variation in other parameters dependent to the cost imposed to the energy provider and the parameters that affect the users level of satisfaction is also evaluated. In Chapter IV, existence of load uncertainty is considered in proposed UBO algorithm when it is assumed that number of users in each time slot is varying based on different distributions such as Uniform or Poison. The results for the average gap between energy provider's generating capacity and consumption of the users are compared with when number of users kept constant in presence of load uncertainty in 24 hours period. Moreover, the effect of different distributions on the gap between generating capacity and the users consumption is evaluated assuming the number of users are increasing and following the distributions. The results for the announced price in 24 hours period is also evaluated and further is extended to the average announced price with respect to increase in number of users when it is assumed that user entry and departure type is varying based on different distributions and the load uncertainty also is existed. In chapter V, the proposed IBO algorithm in chapter three is further extended to the Uncertain IBO and is called UIBO. Therefore, it is assumed that bounded uncertainty is added to the users consumption. This algorithm is further extended in a way that variation in number of users is considered based on different distributions. The results are evaluated for the average gap between generating capacity and users consumption in 24 hours period and is further extended with respect to consideration of the increasing pattern for the number of users in presence of load uncertainty and different types of distributions for the users number variation. With respect to consideration of UIBO algorithm the price in 24 hours period is evaluated and the results are further extended to evaluate the average price with respect to increasing pattern for number of users that are varying based on different distributions when the bounded uncertainty is added to the users consumption. Moreover, the achieved gain of the proposed algorithm based on the ratio of the variation of the announced price to the varying number of users is evaluated. Finally chapter VI provides the conclusion and suggestion for future work.