The LoRaWAN based Low Power Wide Area networks aim to provide long-range connectivity a large number of devices by exploiting limited radio resources. Adaptive Data Rate (ADR) mechanism controls the assignment these resources individual end-devices runtime adaptation their communication parameters when quality links inevitably changes over time. This paper provides detailed performance analysis ADR technique presented in recently released LoRaWan Specifications (v1.1). We show that lacks...

Stress, anxiety and depression in the workplace are detrimental to human health productivity with significant financial implications. Recent research this area has focused on use of sensor technologies, including smartphones wearables embedded physiological movement sensors. In work, we explore possibility using such devices for mood recognition, focusing work environments. We propose a novel recognition framework that is able identify five intensity levels eight different types moods every...

Angle-of-arrival (AoA) estimation is of great interest, particularly for using radio to localize a device; good estimates angles result in location. In this letter, we propose signal processing and machine learning combined tool the AoA estimation. particular, utilize regression models trained snapshot data collected multiple antennas estimating angle arrival. Based on set simulation real measurements underthe Bluetooth 5 low-energy system an indoor environment, proposed method able provide...

The next generation of human activity recognition applications in ubiquitous computing scenarios focuses on assessing the quality activities, which goes beyond mere identification activities interest. Objective assessments are often difficult to achieve, hard quantify, and typically require domain specific background information that bias overall judgement limit generalisation. In this paper we propose a framework for skill assessment enables automatic analysis activities. Our approach is...

Saving energy in residential and commercial buildings is of great interest due to diminishing resources. Heating ventilation air conditioning systems, electric lighting are responsible for a significant share usage, which makes it desirable optimise their operations while maintaining user comfort. Such optimisation requires accurate occupancy estimations. In contrast current, often invasive or unreliable methods we present an approach estimation using wireless sensor network (WSN) that only...

UMBRELLA <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</sup> is an open, large-scale IoT ecosystem deployed across South Gloucestershire, UK. It intended to accelerate innovation multiple technology domains. built bridge the gap between existing specialised testbeds and address holistically real-world technological challenges in a System-of-Systems (SoS) fashion. provides open access devices infrastructure, enabling researchers industry...

Health literacy is widely defined as “people’s knowledge, motivation and competences to access, understand, appraise, apply health information in order make judgments take decisions everyday life concerning healthcare, disease prevention promotion maintain or improve quality of during the course.” Despite availability accessibility information, considerable parts population still engage risky behaviour such insufficient physical activity, unbalanced nutrition, smoking. The woman’s experience...

Quality assessment in cricket is a complex task that performed by understanding the combination of individual activities player able to perform and assessing how well these are performed. We present framework for inexpensive accessible, automated recognition cricketing shots. By means body-worn inertial measurement units, movements batsmen recorded, which then analysed using parallelised, hierarchical system automatically classifies relevant categories shots as required batting quality. Our...

This paper studies a WiFi indoor localisation technique based on using deep learning model and its transfer strategies. We take CSI packets collected via the standard channel sounding as training dataset verify CNN subsets in three experimental environments. achieve accuracy of 46.55 cm an ideal (6.5m × 2.5m) office with no obstacles, 58.30 102.8 sports hall (40 35m). Then, we evaluate ability proposed to different The results show that, for trained model, feature extraction layers can be...

The vast increase of Internet Things (IoT) technologies and the ever-evolving attack vectors have increased cyber-security risks dramatically. A common approach to implementing AI-based Intrusion Detection Systems (IDSs) in distributed IoT systems is a centralised manner. However, this may violate data privacy prohibit IDS scalability. Therefore, intrusion detection solutions ecosystems need move towards decentralised direction. Federated Learning (FL) has attracted significant interest...

The processing and analysis of large-scale journey trajectory data is becoming increasingly important as vehicles become ever more prevalent interconnected. Mapping these trajectories onto a road network complex task, largely due to the inevitable measurement error generated by GPS sensors. Past approaches have had varying degrees success, but achieving high accuracy has come at expense performance, memory usage, or both.In this paper, we solve issues proposing map matching algorithm based...

Data integrity becomes paramount as the number of Internet Things (ioT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities prevent disruptions bias in state an IoT application. This paper presents LE3D, ensemble framework drift estimators capable detecting abnormal behaviours. Working collaboratively with surrounding ioT devices, type (natural/abnormal) also identified reported to end-user. The...

Federated Learning (FL) is fast becoming one of the most prevalent distributed learning techniques focused on privacy preservation and communication efficiency for large-scale Internet Things (IoT) deployments. FL a approach to training models devices. Since local data remains on-device, through network reduced. However, in IoT environments or resource constrained networks, typical approaches significantly suffer performance due longer times. In this paper, we propose two methods further...

Finding on-street parking in congested urban areas is a challenging chore that most drivers worldwide dislike. Previous vehicle traffic studies have estimated around thirty percent of vehicles travelling inner city are made up searching for vacant space. While there hardware sensor based solutions to monitor occupancy real-time, instrumenting and maintaining such wide system substantial investment. In this paper, novel activity detection method, called ParkUs, introduced tested with the aim...

This paper studies the indoor localisation of WiFi devices based on a commodity chipset and standard channel sounding. First, we present novel shallow neural network (SNN) in which features are extracted from state information (CSI) corresponding to subcarriers received different antennas used train model. The single-layer architecture this makes it lightweight easy-to-deploy with stringent constraints computational resources. We further investigate for use deep learning models design...

t is challenging to precisely identify the boundary of activities in order annotate activity datasets required train recognition systems. This case for experts, as well non-experts who may be recruited crowd-sourcing paradigms reduce annotation effort or speed up process by distributing task over multiple annotators. We present a method automatically adjust boundaries, presuming correct label, but imprecise otherwise known "label jitter". The approach maximizes Fukunaga Class-Separability,...

We propose four variants of a novel hierarchical hidden Markov models strategy for rule induction in the context automated sports video annotation including multilevel Chinese takeaway process (MLCTP) based on restaurant and Cartesian product label-based bottom-up clustering (CLHBC) method that employs prior information contained within label structures. Our results show significant improvement by comparison against flat model: optimal performance is obtained using hybrid method, which...

Localization accuracy varies significantly across multiple radio and optical technologies. The choice of which technology is a best-fit for particular application not only based on the alone but also other factors including cost, availability in commodity hardware such as mobile phones, need to have pre-existing fixed infrastructure. As such, there no one-size-fits-all solution therefore we provide, from single indoor testbed, localization data collected three very different technologies...

Recent studies show that a key contributor to congestion and increased CO2 emissions within cities are drivers searching (or cruising) find vacant on-street parking space. It has been shown approximately (depending on the city) 20-30% of vehicles in congested urban areas were cruising space with search time varying order several minutes. In city Bristol alone, we have shown, using our collected trip publicly available census data over 790 metric tons is generated every year due cruising. At...

Over the last half century, proportion of humans living in cities has dramatically risen from around a third to just over half. As continue rise popularity, demand for basic services such as transportation increases. The automobile been dominant method inner city many across globe, resulting increased congestion and air pollution. rises, so does number vehicles, which leads greater competition publicly available parking spaces. Use land can be an inefficient use space, it is expensive, both...