This work focuses on exploring the accuracy of heading estimation in x dead-reckoning (xDR) positioning methods across different time scales to address the limitations of pedestrian dead-reckoning (PDR) which relies solely on step analysis for location updates. To this end, we first give the relationship among position update frequency of PDR, sampling rate and step frequency in formula which shows the instability. And we propose a method utilizing an improved VIT-Encoder to mine the correlation features of Inertial Measurement Unit (IMU) sequences for heading estimation to eliminate the instability of PDR and evaluate their generalization performance. Results indicate that the model achieves accurate heading estimation on both training and test sets at larger time scales, with substantial disparities observed at smaller scales. Notably, the robustness of smaller-scale estimations mirrors or even surpasses that of longer time scales, revealing an intriguing finding. Additionally, the model exhibits high recognition accuracy across different time scales in straight trajectories, whereas shorter time scales demonstrate advantages at bends, offering higher fault tolerance for misestimations. Increasing the positioning update frequency to 10 Hz in xDR positioning methods is deemed feasible, which holds significant implications for enhancing the performance and user experience of indoor positioning systems, thereby promoting the development and application of indoor positioning technology.

Integrated sensing and communication technologies provide essential sensing capabilities that address pressing challenges in remote health monitoring systems. However, most of today’s systems remain obtrusive, requiring users to wear devices, interfering with people’s daily activities, and often raising privacy concerns. Herein, we present HealthDAR, a low-cost, contactless, and easy-to-deploy health monitoring system. Specifically, HealthDAR encompasses three interventions: i) Symptom Early Detection (monitoring of vital signs and cough detection), ii) Tracking & Social Distancing, and iii) Preventive Measures (monitoring of daily activities such as face-touching and hand-washing). HealthDAR has three key components: (1) A low-cost, low-energy, and compact integrated radar system, (2) A simultaneous signal processing combined deep learning (SSPDL) network for cough detection, and (3) A deep learning method for the classification of daily activities. Through performance tests involving multiple subjects across uncontrolled environments, we demonstrate HealthDAR’s practical utility for health monitoring.

Fall detection and recognition play a crucial role in enabling timely medical interventions for people who are at risk of falls, especially among vulnerable populations like older adults and those with mobility limitations. In this article, a cost-effective integrated sensing and communication system, namely, FallDR, is presented for fall detection and recognition using ultrawideband communication. First, we collected the time of flight information of falls (four types) and nonfall events by 10 participants using FallDR. We then proposed a convolutional neural network incorporated with squeeze-and-excitation blocks to detect and recognize falls based on fall trajectories. It proves that the proposed model is accurate, energy-efficient, and lightweight to achieve 100% accuracy in fall detection and recognition. Our proposed solution is proven to be highly robust against environmental changes, such as interference, distance, and direction changes. Further tests in an office showed that FallDR could achieve nearly 100% accuracy, even when the environment was changed. FallDR efficiently employs the characteristics of fall trajectory and the advanced modeling ability of the neural network. We have published our archived data sets and code for comparisons and improvements.

Waypoint estimation (WE) has a wide range of applications for indoor walkers, such as fire rescue and navigation to find exit doors, lifts, or stairs as examples of waypoints, etc. Data-driven WE has been on the rise with advancements in deep learning algorithms. The current WE methods, however, face two challenges. On the one hand, most waypoint detection approaches rely on visual sensors, hence, their estimation performance is limited by light when collecting visual data. On the other hand, data-driven methods necessitate a large number of labeled data to train a WE model, which significantly increases the time spent manually marking labels. Targeting the above two challenges, our work first proposes a novel deep Bayesian active learning waypoint estimator for indoor walkers (DeepWE) based on human activity recognition (HAR). This estimates six indoor waypoints through walkers’ daily activities due to the strong correlation between human activities and waypoints. First, an initial DeepWE model is developed using a Bayesian ensembled convolutional neural network (B-CNN) using the accelerometer and gyroscope data. Then, active learning is employed to query the most formative samples from pool points with four acquisition functions, and only these queried samples are labeled manually. Finally, the initial DeepWE model is updated from this labeled data using an incremental learning algorithm. Empirical results on two publicly available USC-HAD and OPPORTUNITY data sets show DeepWE performs a considerable accuracy boost for WE, with a substantial amount of acquired pool points reduction (more than 40%).

Automatic fall detection and recognition are challenging problems. In this paper, a novel solution is proposed based on the trajectories of human falls by using the ultra-wideband (UWB) communication system and machine learning methods for fall detection and recognition. Most previous studies of fall detection based on active UWB sensing used electromagnetic signals directly, which may bring problems like radar clutter, signal coupling, multi-path, fading, and interference. Our proposed method only uses human falls trajectories by passive UWB sensing, which achieved fall recognition performance of 93.26% by using the support vector machine with RBF kernel function (SVM-RBF). Compared with previous research, the superiority of this study is that our solution is robust against interference and environmental changes, which means it is reliable for real-world applications. The archived UWB datasets and code have been already published, which may provide the basis for the comparison of techniques and improvements.

In this article, a cost-effective ultrawideband (UWB) communication system for gesture recognition in a smart home environment is proposed, which uses gesture trajectories and a deep learning model. Most previous studies of gesture recognition using the UWB technology used electromagnetic signals directly, which may bring problems, such as radar clutter, signal coupling, multipath, fading, and interference. However, instead of using UWB’s high-frequency pulse signals, the proposed method only uses gesture trajectories by data positioning. To this end, first, a data set of four gesture activities was created. Then, this data set was trained using a convolutional neural network (CNN) integrated with a squeeze-and-excitation (SE) block, namely, the SE-Conv1D model. Finally, the system was prototyped to interact with appliances in practical smart homes. The experimental data was used to demonstrate the superiority of the SE-Conv1D model in comparison with four baselines: 1) support vector machines; 2)$K$-nearest neighbor; 3) random forest; and 4) binarized neural networks. Experimental results show that all collected gesture activities are correctly recognized with an overall accuracy of over 95%, among which the proposed SE-Conv1D model achieves the best accuracy of 99.48%. The proposed system is a complete end-to-end sensing system specifically designed for tracking and recognizing human gestures, which is robust against interference and changes in distance or direction. In addition, the proposed system can tackle the device selection problems for smart homes, which means it is reliable for real-world applications.

The aim of this research is to implement a precise Wi-Fi indoor positioning system (IPS) or localization system based upon the IEEE 802.11mc fine-timing measurement (FTM) scheme also known as the Wi-Fi round trip time (RTT) ranging technique, where ranging refers to a sub-process of positioning that determines the distance between a transmitter and receiver. Our system and its algorithms were implemented using a COTS (Commercial-Off-The-Shelf) smartphone and Wi-Fi access points. Experiments were conducted in several real-life indoor environments. This paper presents the detailed Wi-Fi RTT ranging performance of these devices in different system configurations and characterizes the systematic biases and noise model to improve the ranging accuracy. A novel three-step-positioning method is proposed to overcome the issues of no or multiple intersect points in trilateration due to ranging errors to improve positioning accuracy. This consists of the following: 1) systematic bias determination and removal; 2) clustering-based trilateration (CbT) supported by weighted concentric circle generation (WCCG), namely CbT & WCCG; 3) positioning result and trajectory optimization using a Kalman filter. As a result, the evaluation experiments gave a position accuracy of ±1.2 m in 2D static positioning and ±1.3 m for dynamic motion tracking. Also, our CbT & WCCG method demonstrate good tolerance against ranging errors. Moreover, the computational cost and positioning accuracy of CbT & WCCG methods are compared with least square (LS) and recursive least square (RLS) methods and the accuracy standard deviation of our algorithm is the closest to the Cramer–Rao bound (CRB).

A Convolutional neural network (CNN) has emerged as a widely used approach to computer vision tasks, including object classification and detection tasks. The high requirement for the model to be more computationally efficient on lower information and communication technology (ICT) resource, e.g., mobile terminals can benefit from model distillation. However, most existing distillation methods suffer from a significant accuracy reduction, which requires a large number of pre-training models or doesn't make good use of the more of the network information, e.g., in the middle layers, during the distillation. In this paper, we study how knowledge about traffic signs recognition could be transferred to smaller models by distillation while cutting channels. We present an optimized object detection network, which uses a Region Proposal Network (RPN) weighted loss and hard-soft distribution-wise distillation loss for structural differences between teacher and student networks. We validate the network on multiple real-world datasets, the experiments demonstrate that the classification accuracy can be improved by 9 % with about 16 times parameter reduction while the detection network performance could be increased by 10.6% using an optimized object detection network.

One of the most fundamental features of living organisms is their growth, a biological phenomenon that can be considered as a type of slow, tangible output responding to an environmental stimulus or an input. Given the relative slowness of growth, once it becomes part of game mechanics, the feature can lead to slow interactivity and slow gameplay in biotic games – a relatively new type of bio-digital game that enables playful human-microbe interactions. Currently, there is a lack of annotations on existing biotic game design guidelines, that 1) recognise biological slowness as a potentially beneficial feature in game design, and 2) provide specific advice on how organism's slow response time can be effectively incorporated in biotic games. To start addressing these limitations, we report on an initial set of design lessons learnt from our research on slow biotic games. Through these lessons, we have formulated and outlined a set of practical recommendations for prospective designers of slow biotic games.

Remote characterisation of the environment during physical robot-environment interaction is an important task commonly accomplished in telerobotics. This paper demonstrates how tactile and proximity sensing can be efficiently used to perform automatic crack detection. A custom-designed integrated tactile and proximity sensor is implemented. It measures the deformation of its body when interacting with the physical environment and distance to the environment's objects with the help of fibre optics. This sensor was used to slide across different surfaces and the data recorded during the experiments was used to detect and classify cracks, bumps and undulations. The proposed method uses machine learning techniques (mean absolute value as feature and random forest as classifier) to detect cracks and determine their width. An average crack detection accuracy of 86.46% and width classification accuracy of 57.30% is achieved. Kruskal-Wallis results (p<; 0.001) indicate statistically significant differences among results obtained when analysing only force data, only proximity data and both force and proximity data. In contrast to previous techniques, which mainly rely on visual modality, the proposed approach based on optical fibres is suitable for operation in extreme environments, such as nuclear facilities in which nuclear radiation may damage the electronic components of video cameras.

Motion trajectories contain rich information about human activities. We propose to use a 2-D LIDAR to perform multiple people activity recognition simultaneously by classifying their trajectories. We clustered raw LIDAR data and classified the clusters into human and nonhuman classes in order to recognize humans in a scenario. For the clusters of humans, we implemented the Kalman filter to track their trajectories which are further segmented and labeled with corresponding activities. We introduced spatial transformation and Gaussian noise for trajectory augmentation in order to overcome the problem of unbalanced classes and boost the performance of human activity recognition (HAR). Finally, we built two neural networks, including a long short-term memory (LSTM) network and a temporal convolutional network (TCN) to classify trajectory samples into 15 activity classes collected from a kitchen. The proposed TCN achieved the best result of 99.49% in overall accuracy. In comparison, the TCN is slightly superior to the LSTM network. Both the TCN and the LSTM network outperform the hidden Markov model (HMM), dynamic time warping (DTW), and support vector machine (SVM) with a wide margin. Our approach achieves a higher activity recognition accuracy than the related work.

In addition to smarter road vehicles and smarter roads, more smartly human driven vehicles (that are as yet still predominantly more common-place than autonomously driven ones) currently still have a huge potential to improve road safety, fuel efficiency and to reduce vehicle exhaust emissions. In this work, we propose a human driving profiling algorithm with the means of Serious Games (SGs) – games for training and learning drivers’ trip purpose beyond a behavioral improvement via users’ motivation and engagement in a digital environment – to assist the driver in promoting more fuel efficient (low fuel consumption, FC) driving. The game supplies drivers or players with direct feedback when more inefficient, and riskier, driving manoeuvres are detectable, via sensing and analysing the changes of throttle position, engine revolutions per minute (RPM), car speed and jerks (changes in acceleration with respect to time). Such manoeuvres derived from the On-Board Diagnostic-II interface to the vehicle sensors complemented by additional sensors such as GPS location, e.g., from a mobile phone or inbuilt vehicle sensor, can be regarded as eco-driving events. Providing eco-driving feedback via the user interface of a SG, keeps the driver aware of the fuel economy and safety. We also argue that evaluating the driving style for the whole trip allows us to take into account how the dynamic driving behavior is sometimes affected by other factors (e.g., traffic congestion). In addition, this quantitative evaluation is important as a gaming mechanism, i.e., an updated score can facilitate reaching a higher gaming level, etc. In contrast to existing studies, we combine fuel efficiency with the throttle position values in the eco-driving classification module. We have done some initial analysis for this, using the naturalistic historical driving data from the enviroCar project’s open data initiative. We reason that throttle position is the most powerful indicator of fuel efficiency and driving style among the other studied parameters.

Human activity detection plays a crucial role in the recognition of activities of daily living (ADLs). In the past ten years, research on activity detection in the home was achieved through the data aggregation from several different sensors (presence sensors, door contacts, appliances tagging, cameras, wearable beacons, mobile phones, etc.). However, the cost of deployment and maintenance of a multitude of sensor devices and the intrusiveness they can infer are quite high. Research on minimal and non-intrusive sensing for recognition of ADLs are vital for the future of remote care. In this paper, we propose a minimal and non-intrusive low-power low-cost radar-based sensing network system that uses an innovative approach for recognizing human activity in the home. We applied our novel approach to the challenging problem of kitchen activity recognition and investigated fifteen different activities. We designed and trained a deep convolutional neural network (DCNN) that classifies different activities based on their distinct micro-Doppler signatures. We achieved an overall classification rate of 92.8% in activity recognition. Most importantly, in nearly real-time, our approach successfully recognized human activities in more than 89% of the time.

Internet of Things (IoT) technologies have a promising potential for instructional serious games related to field operations. We explore IoT's potential for serious games in the automotive application domain to improve driving, choosing fuel consumption (FC) as an indicator of the driver performance as it is strongly influenced by driving styles and can be quantified and validated. We propose a FC prediction model, exploiting three vehicular signals that are controllable by the driver (player), that are able to provide direct coaching feedback to the driver and are easily available through the widely available On-Board Diagnostic-II (OBD-II) vehicular interface: throttle position, engine rotation speed (RPM) and car speed. We processed the data with two techniques, random forest (RF) and fuzzy logic (FL). Implementation, training and testing of both models, were made using the enviroCar database which freely provides a significant amount of naturalistic drive data. Results show that RF achieves quite a higher estimation accuracy, which complements FL's ability to provide driver with easily understandable feedback. We thus argue that the combination of the two models can supply valuable information usable by game designers in the automotive environment.

A biotic game integrates real biological materials and processes into digital/video gaming platforms. Given its relatively recent introduction to the field of game design, there are limited examples and discussions around biotic games to help designers to explore this genre in depth. This paper introduces a new type of biotic game called Mould Rush. It is a part-tangible, part-digital, online multiplayer strategy game, mostly driven by real-time growth of living micro-organisms. By outlining the design process of Mould Rush, the paper aims to use the game as a case study to highlight the opportunities and challenges that need to be addressed in creating games of this nature, speed, and scale. In particular, we suggest that the slowness of microbial growth may not necessarily compromise playing experience, but rather, enhance it instead. We also highlight the complexity of human, biology and computer interaction pathways that are involved in biotic gaming. And finally, we acknowledge the potential value of designing formal evaluation models that would help in meaningful evaluation of a 'biotic' gaming experience.

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, we propose an access control solution for exchanging Blockchain-based Electronic Medical Records (EMRs) called BBACS (Block-based Access Control Scheme) that includes an access model and an access scheme. Unlike the existing Blockchain-oriented access schemes for EMRs, our access model can omit the agent layer (gateway) in order to authorise users' access with block level granularity, whilst maintaining compatibility with the underlying Blockchain data structure. Furthermore, the authorisation, encryption, and decryption algorithms presented in BBACS dispense with the need to use a public key infrastructure (PKI) and hence cut down the cost of network construction and improve the computational performance. We validated the efficiency (time cost) of local computation and data transmission (over Wi-Fi) for BBACS using a simulation of BBACS against another Blockchain-oriented access control scheme for EMRs called HDG as our baseline. To the best of our knowledge, BBACS is the first Blockchain-oriented access control solution without the need for an agent (or gateway) design, supporting granular authorisation (block level), that has been proposed for secure EMRs management in eHealth.

In this paper, we propose an architecture for Blockchain-based Electronic Medical Records (EMRs) called GAA-FQ (Granular Access Authorisation supporting Flexible Queries) that comprises an access model and an access authorisation scheme. Unlike existing Blockchain schemes, our access model can authorise different levels of granularity of authorisation, whilst maintaining compatibility with the underlying Blockchain data structure. Furthermore, the authorisation, encryption, and decryption algorithms proposed in the GAA-FQ scheme dispense with the need to use a public key infrastructure (PKI) and hence improve the computation performance needed to support more granular and distributed, yet authorised, EMR data queries. We validated the computation performance and transmission efficiency for GAA-FQ using a simulation of GAA-FQ against an access control scheme for EMRs called ESPAC as our baseline that was not designed using a Blockchain. To the best of our knowledge, GAA- FQ is the first Blockchain-oriented access authorisation scheme with granular access control, supporting flexible data queries, that has been proposed for secure EMR information management.

This paper describes a study in which participants were made aware of the presence of Global Navigation Satellite Systems (GNSS) infrastructure (often colloquially known as GPS) through an exaggeration of its breakdowns and a defamiliarisation of its use. We found that, by drawing attention to satellites and their signals, participants began to feel part of a larger system and to reflect on their sociotechnical practices within that system. These reflections included playful exploration and an interrogation of power relations made invisible by the blackboxing of GNSS infrastructure. Despite these shifts from established practices, smartphone visual interfaces continued to be a powerful arbiter of how participants situated their experience. Drawing on the experience of this study, we suggest ways for designers and researchers using Location Based Services (LBS) to inspire critical relationships with infrastructure which circumvent dominant design inscriptions. We also offer these techniques for others working more broadly in the fields of participatory and critical design.

The use of magnetic field (MF) measurements, unlike typical Wi-Fi or Bluetooth positioning measurements, are unaffected by moving humans, providing more time-invariant location information. We present a novel Fast Path Matching algorithm for MF and Inertial sensor measurements, FPM-MI, to localise a person using MF measurements fused with inertial sensor measurements. Our novelty is twofold: it has a reduced computational cost compared to a particle filter algorithm; it has a fast convergence performance, i.e., a person can walk a much shorter distance, about 3 m, to have an arm-span location accuracy. We validated our system in a library, a retail-like building, with multiple metal shelves and pillars, and determined the positioning error to be 1.8 m (90% confidence).

Deploying trusted (private) cloud computing to exchange, store and analyse data from IoT networks has become mainstream. In this paper, we describe a data privacy transmission scheme for IoT data collection, which supports one-way identity authentication and a dual data integrity validation for low resource devices called the Lo-A&DI (Low-resource for IoT 1-way Authentication and Dual Integrity) scheme. Unlike other schemes that use trusted clouds, the Lo-A&DI can be applied to untrusted public clouds while protecting data security and privacy. Unlike other untrusted cloud security schemes, the Lo-A&DI scheme can be used to support end-to-end data security and privacy from low-resource ICT IoT devices. An experimental validation shows that the performance of the Lo-A&DI is much more adaptable for use in resource-constrained IoT devices when compared to a baseline trusted cloud scheme such as one based upon an interactive (2-way) certificate authentication scheme for IoT data exchange.

If we are to engage a younger generation to become future engineering and science innovators, we need to widen participation and interaction with technology and science. Maker movements have the potential to do this by making tools, materials, and processes more readily available to people in a more informal learning setting who may not initially self-identify as makers. We address a chief limitation of such maker communities, where it can be difficult for participants to develop and continue an application outside the inherent limited time and space of the maker event. We ran a series of 6 maker events aimed at groups of six 14-15 year olds that focused on learning through making the BBC micro:bit device interact as part of an Internet of Things (IoT) application. We report on one event and a challenge to develop a sharable wearable IoT application to address the aim for participants that could sustain interest outside the event. This application was a club badge to send secret messages to members. The evaluation revealed a keen engagement and commitment to social wearable design, as seen through the students building and participating in the successful use of the application through authenticity. This authentic engagement to problem solving at a technical level to motivate personal goals was inspired through a sharable wearable design that participants deemed to be beneficial.

In this paper we present the requirements, design and pre-deployment testing of a transportation bus as a Mobile Enterprise Sensor Bus (M-ESB) service in China that supports two main requirements: to monitor the urban physical environment, and to monitor road conditions. Although, several such projects have been proposed previously, integrating both environment and road condition monitoring and using a data exchange interface to feed a data cloud computing system, is a novel approach. We present the architecture for M-ESB and in addition propose a new management model for the bus company to act as a Virtual Mobile Service Operator. Pre-deployment testing was undertaken to validate our system.

The key benefits of using the smartphone accelerometer for human mobility analysis, with or without location determination based upon GPS, Wi-Fi or GSM is that it is energy-efficient, provides real-time contextual information and has high availability. Using measurements from an accelerometer for human mobility analysis presents its own challenges as we all carry our smartphones differently and the measurements are body placement dependent. Also it often relies on an on-demand remote data exchange for analysis and processing; which is less energy-efficient, has higher network costs and is not real-time. We present a novel accelerometer framework based upon a probabilistic algorithm that neutralizes the effect of different smartphone on-body placements and orientations to allow human movements to be more accurately and energy-efficiently identified. Using solely the embedded smartphone accelerometer without need for referencing historical data and accelerometer noise filtering, our method can in real-time with a time constraint of 2 seconds identify the human mobility state. The method achieves an overall average classification accuracy of 92 percent when evaluated on a dataset gathered from fifteen individuals that classified nine different urban human mobility states.

A variety of event detection algorithms for microblog services have been proposed, but their accuracy relies on the microblog feeds they analyse. Existing research explores datasets that are collected using either a set of manually predefined terms or information from external sources. These methods fail to provide comprehensive and quality feeds for real-time event detection. In this paper, we present a novel adaptive keyword identification approach to retrieve a greater amount of event relevant content. This approach continuously monitors emerging hashtags and rates them by their similarity to specific pre-defined event hashtags using TF-IDF vectors. Top rated emerging hashtags are added as filter criteria in real time. By comparing our proposed approach, called CETRe (Content-based Event Tweet Retrieval) with an existing baseline approach applied to real-world events, we show that CETRe not only identifies event topics and contents, but also enables better event detection.

Researchers have capitalized on microblogging services, such as Twitter, for detecting and monitoring real world events. Existing approaches have based their conclusions on data collected by monitoring a set of pre-defined keywords. In this paper, we show that this manner of data collection risks losing a significant amount of relevant information. We then propose an adaptive crawling model that detects emerging popular hashtags, and monitors them to retrieve greater amounts of highly associated data for events of interest. The proposed model analyzes the traffic patterns of the hashtags collected from the live stream to update subsequent collection queries. To evaluate this adaptive crawling model, we apply it to a dataset collected during the 2012 London Olympic Games. Our analysis shows that adaptive crawling based on the proposed Refined Keyword Adaptation algorithm collects a more comprehensive dataset than pre-defined keyword crawling, while only introducing a minimum amount of noise.

Advances in location tracking sensors in smartphones have led to the emergence of many location-based services (LBS). Continuous use of these location sensors improves the reliability and accuracy when identifying a user's location, but results in quicker battery depletion due to high energy consumption. In this paper, we present an energy-efficient location determination method for smartphones named Low Power Accelerometer Assisted Location Sensing (LALS). LALS is a high-availability hybrid technique that combines the use of GPS, Wi-Fi Positioning System (WPS), GSM Positioning System (GSMPS) and accelerometer. The novelty of our method is threefold. First, it involves extracting 6 features (5 novel and 1 derived) from the embedded smartphone accelerometer data without need for accelerometer noise filtering. Second, it provides real-time smartphone based user activity classification with a time constraint of 2 seconds avoiding the need to use a remote link to an in-network activity state analyzer. The user activities are stationary, sitting, lying down, standing, walking, jogging, cycling, and motorized movement (travel by bus, overhead train, underground train, taxi, and car). Third, it detects a user's activity transition, promoting a more energy-efficient location sensor selection algorithm. Results show LALS can achieve energy-savings of up to 53% in a typical commuter scenario without compromising on the location accuracy as compared to combinations of GPS, and WPS or GSMPS.

Smart devices such as Apple's iPod nano (5th generation), Nike+, and existing smartphone applications can provide the functions of a pedometer using the accelerometer. To achieve a high accuracy the devices must be worn on specific on-body locations such as on an armband or in footwear. Generally people carry smart devices such as smartphones in different positions, thus making it impractical to use these devices due to the reduced accuracy. Using the embedded smartphone accelerometer in a low-power mode we present an algorithm named Energy-efficient Real-time Smartphone Pedometer (ERSP), which accurately and energy-efficiently infers the real-time human step count within 2 seconds using the smartphone accelerometer. Our method involves extracting 5 features (4 novel and 1 derived) from the smartphone 3D accelerometer without the need for noise filtering or specific smartphone on-body placement and orientation, ERSP classification accuracy is approximately 94% when validated using data collected from 17 volunteers.

Congestion slows road traffic. This has become a prominent urban road traffic problem. For commuters about to travel, or on route, accurate travel forecasts enable them to choose the right routes in a timely manner to avoid travel delays. In this paper, a personalised online travel time prediction model is proposed. The novelty of the work is threefold. First, commuters' travel status according to their movement status, OD (origin-destination) status and plan status can be identified. Second, a traffic data critical factor evaluator system is proposed to extract critical factors from raw traffic data that can predict travel time episodically. Third, travel information can be personalised to the individual commuter's current travel status. The evaluation of the proposed model is conducted with a Google Android mobile application prototype and traffic data from the city of Enschede. The results suggest that the model can provide commuters with accurate travel time prediction (>93%) by leveraging machine learning techniques such as a M5 tree model.

An innovative Internet streaming video player, called ePlayer, oriented to live events, has been researched, developed and evaluated. This supports a personalised zoom able user interface. The main novelty of the system is first that it is designed to optimise the zoomed video quality when viewing live events via adaptation of the streamed video quality across multi-video streams with a differing network quality of service. Second, it also personalises the live video zooming with respect to users' zooming preferences, easing the user interaction needed for the zooming task. The experimental results indicate that the system is not only able to zoom effectively but that it can also maintain the visual quality of the video at the same time. ePlayer is also able to infer a user's zooming preferences via dynamically clustering a user's zooming regions of interest when viewing live sports video content.

Transportation mode plays an important role in enabling us to derive a mobile user's context, and to adapt intelligent services to this. However, current methods have two key limitations: a low recognition accuracy and coarse-grained recognition capability. In this paper, we propose a new Post Correction Algorithm (PoCoA) that is applied after the use of typical classifiers to address these limitations. We evaluated the use of PoCoA for the following transportation modes, walking, cycling, bus passenger, metro passenger, car passenger, and car driver. PoCoA enhances a typical accelerometer-based transportation recognition method with a more accurate sub-classification of motorized transportation modes when tested on a dataset obtained from 15 individuals. Overall accuracy improved from 69% to 88% when comparing with a state of the art two-stage classifier (Decision Tree + Discrete Hidden Markov Model).

Smartphones with an embedded GPS sensor are being increasingly used for location determination to enable Location based services (LBS) deliver location context pervasive computing services such as maps and navigation. Although a Smartphone GPS provides adequate accuracy, it has limitations such as high energy consumption and is unavailable in locations with an obscured view of GPS satellites. Use of alternate location sensors such as Wi-Fi and GSM can be used to augment GPS and to alleviate these GPS limitations, but they can increase the average localization error. The novelty of our contribution is twofold. First we present an accelerometer based architecture that reduces GPS energy-consumption without compromising on either the location accuracy or sampling rate. Evaluation of our system shows energy-savings of up to 27% in typical circumstances. Second, as a user's mobility state is complex we also propose a method to not only detect that a user is non-stationary but also classify a representative set of mobility states.

Images that have a different visual appearance may be semantically related using a higher level conceptualization. However, image classification and retrieval systems tend to rely only on the low-level visual structure within images. This paper presents a framework to deal with this semantic gap limitation by exploiting the well-known bag-of-visual words (BVW) to represent visual content. The novelty of this paper is threefold. First, the quality of visual words is improved by constructing visual words from representative keypoints. Second, domain specific “non-informative visual words” are detected which are useless to represent the content of visual data but which can degrade the categorization capability. Distinct from existing frameworks, two main characteristics for non-informative visual words are defined: a high document frequency (DF) and a small statistical association with all the concepts in the collection. The third contribution in this paper is that a novel method is used to restructure the vector space model of visual words with respect to a structural ontology model in order to resolve visual synonym and polysemy problems. The experimental results show that our method can disambiguate visual word senses effectively and can significantly improve classification, interpretation, and retrieval performance for the athletics images.

A major limitation of many image classification and retrieval systems is that they only rely on the visual structure within images. However, images that have a different visual appearance may be semantically related at a higher level conceptualization. This paper presents a framework to deal with this problem by exploiting the well-known bag-of-visual words (BVW) model, to represent visual content. There are two key contributions of this paper. First, a novel approach for visual words construction is presented which takes the spatial information of keypoints into account in order to enhance the quality of visual words generated from extracted keypoints. Second, an approach to discover semantically similar visual word sets is proposed, which enables the BVW model to become invariant to certain changes in visual appearance. Consequently, the BVW model strengthens the discrimination power for visual content classification.

The increasing capabilities of mobile devices, and advances in wireless networking technologies enable mobile computing systems to introduce more intelligent behaviors to support their services such as spatial navigation for drivers. Mobile applications should be able to be aware of, and adapt to environment changes to provide more customized services to their users. Building mobile applications by specifying built-in adaptation mechanisms would be inefficient, error-prone, and lack of flexibility. This research proposes a context adaptation layer (CAL) which incorporates current environment contexts and user goal contexts, to generate a holistic adaptation view at CAL and therefore provide a deliberative guide to the service adaption in the separate service adaptation layer (SAL). The system model is validated through a dynamic spatial routing application in urban area.

Multi-Agent-Systems or MAS represent a powerful distributed computing model, enabling agents to cooperate and complete with each other and to exchange both semantic content and a semantic context to more automatically and accurately interpret the content. Many types of individual agent and MAS models have been proposed since the mid-1980s, but the majority of these have led to single developer homogeneous MAS systems. For over a decade, the FIPA standards activity has worked to produce public MAS specifications, acting as a key enabler to support interoperability, open service interaction, and to support heterogeneous development. The main characteristics of the FIPA model for MAS and an analysis of design, design choices and features of the model is presented. In addition, a comparison of the FIPA model for system interoperability versus those of other standards bodies is presented, along with a discussion of the current status of FIPA and future directions.