A5018639589- Context-Aware Activity Recognition Systems
- Mobile Agent-Based Network Management
- Indoor and Outdoor Localization Technologies
- Service-Oriented Architecture and Web Services
- Multi-Agent Systems and Negotiation
- Human Mobility and Location-Based Analysis
- IoT and Edge/Fog Computing
- Advanced Image and Video Retrieval Techniques
- Video Analysis and Summarization
- Access Control and Trust
- Robotics and Sensor-Based Localization
- Innovative Human-Technology Interaction
- Image Retrieval and Classification Techniques
- Transportation Planning and Optimization
- Air Quality Monitoring and Forecasting
- Advanced Vision and Imaging
- Non-Invasive Vital Sign Monitoring
- Semantic Web and Ontologies
- Vehicle emissions and performance
- Blockchain Technology Applications and Security
- Gait Recognition and Analysis
- Data Management and Algorithms
- Multimedia Communication and Technology
- Urban Transport and Accessibility
- Robotics and Automated Systems
Queen Mary University of London
2016-2025
University of London
2001-2014
National Technical University of Athens
2010
Imperial College London
1999-2004
Universidad de Londres
2003
Imperial Valley College
2001
University of Westminster
1995
More and more people combine several purposes with travelling, such as business, leisure, entertainment, education. Such may not have time to pre-plan a travel schedule in detail. They need location-aware information about the destination domain expect individualised services. The EU funded research project CRUMPET addresses these factors will provide new delivery services for far heterogeneous tourist population. proposed by take advantage of integrating four key emerging technology domains...
Multi-Agent-Systems or MAS represent a powerful distributed computing model, enabling agents to cooperate and complete with each other exchange both semantic content context more automatically accurately interpret the content. Many types of individual agent models have been proposed since mid-1980s, but majority these led single developer homogeneous systems. For over decade, FIPA standards activity has worked produce public specifications, acting as key enabler support interoperability,...
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 access model and authorisation scheme. Unlike existing Blockchain schemes, our can authorise different levels of granularity authorisation, whilst maintaining compatibility with the underlying data structure. Furthermore, encryption, decryption algorithms proposed in scheme dispense need to use a public key...
An early warning system (EWS) is a core type of data driven Internet Things (IoTs) used for environment disaster risk and effect management. The potential benefits using semantic-type EWS include easier sensor source plug-and-play, simpler, richer, more dynamic metadata-driven analysis service interoperability orchestration. challenges faced during practical deployments semantic EWSs are the need scalable time-sensitive exchange processing (especially involving heterogeneous sources)...
Every year, for ten years now, the IPIN competition has aimed at evaluating real-world indoor localisation systems by testing them in a realistic environment, with movement, using EvAAL framework. The provided unique overview of state-of-the-art systems, technologies, and methods positioning navigation purposes. Through fair comparison performance achieved each system, was able to identify most promising approaches pinpoint critical working conditions. In 2020, included 5 diverse off-site...
Indoor navigation in physical retail type spaces aids the of users to find items at known destinations. WiFi Fingerprinting using a mobile phone is perhaps most widely used method. However, this power-hungry, and its typical positioning accuracy (2.0 3.0 meters) not enough differentiate between adjacent narrow aisles locate items. In paper, we present novel (Bluetooth Low Energy) BLE Received Signal Strength Indication (RSSI) ranking based fingerprinting method that uses Kendall Tau...
Motion trajectories contain rich information about human activities. We propose to use a 2-D LIDAR perform multiple people activity recognition simultaneously by classifying their trajectories. clustered raw data and classified the clusters into nonhuman classes in order recognize humans scenario. For of humans, we implemented Kalman filter track which are further segmented labeled with corresponding introduced spatial transformation Gaussian noise for trajectory augmentation overcome...
The aim of this research is to implement a precise Wi-Fi indoor positioning system (IPS) or localization based upon the IEEE 802.11mc fine-timing measurement (FTM) scheme also known as round trip time (RTT) ranging technique, where refers sub-process that determines distance between transmitter and receiver. Our its algorithms were implemented using COTS (Commercial-Off-The-Shelf) smartphone access points. Experiments conducted in several real-life environments. This paper presents detailed...
IPIN 2019 Competition, sixth in a series of competitions, was held at the CNR Research Area Pisa (IT), integrated into program Conference. It included two on-site real-time Tracks and three off-site Tracks. The four presented this paper were set same environment, made buildings close together for total usable area 1000 m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> outdoors 6000 indoors over floors, with path length exceeding 500 m....
In recent years, the emergence of dockless bike-sharing has brought new ways transportation, while also providing support for observing urban dynamics at a finer granularity. This study uses data, combined with point interest (POI) to explore intra-urban human mobility and daily activity patterns, using Beijing as case study. Here, we employ spatial statistics graph network quantify characteristics travel behavior. Firstly, spatiotemporal analysis was conducted investigate patterns...
Images that have a different visual appearance may be semantically related using higher level conceptualization. However, image classification and retrieval systems tend to rely only on the low-level structure within images. This paper presents framework deal with this semantic gap limitation by exploiting well-known bag-of-visual words (BVW) represent content. The novelty of is threefold. First, quality improved constructing from representative keypoints. Second, domain specific...
Smartphones with an embedded GPS sensor are being increasingly used for location determination to enable Location based services (LBS) deliver context pervasive computing such as maps and navigation. Although a Smartphone provides adequate accuracy, it has limitations high energy consumption is unavailable in locations obscured view of satellites. Use alternate sensors Wi-Fi GSM can be augment alleviate these limitations, but they increase the average localization error. The novelty our...
Human activity detection outdoors is emerging as a very important research field due to its potential application in surveillance, assisted living, search and rescue, military applications. For such applications it have detailed information about the human target, for example, whether detected target single person or group of people, what performing, rough location target. In this paper, we propose novel usage machine learning techniques perform subject classification, people counting,...
Dealing safely with nuclear waste is an imperative for the industry. Increasingly, robots are being developed to carry out complex tasks such as perceiving, grasping, cutting, and manipulating waste. Radioactive material can be sorted, either stored or disposed of appropriately, entirely through actions remotely controlled robots. Radiological characterisation also critical during decommissioning facilities. It involves detection labelling radiation levels, materials, contaminants, well...
Air-borne particulate matter, PM2.5 (PM having a diameter of less than 2.5 micrometers), has aroused widespread concern and is core indicator severe air pollution in many cities globally. In our study, we present validated framework to predict the daily distributions, exemplified by use case Shijiazhuang City, China, based on aerosol optical depth (AOD) datasets. The involves obtaining high-resolution spatiotemporal AOD estimation spatial distributions prediction these convolutional long...
The frequency of marine oil spills has increased in recent years. growing exploitation and continuous increase crude transportation caused tremendous damage to the ecological environment. Using synthetic aperture radar (SAR) images monitor can help control spread spill pollution over time reduce economic losses environmental by such spills. However, it is a significant challenge distinguish between oil-spilled areas oil-spill-like SAR images. Semantic segmentation models based on deep...
Recent advances in the development of multimodal wearable sensors enable us to gather richer contexts mobile user activities. The combination foot force sensor (FF) and GPS is able afford fine-grained mobility activity recognition. We derive identify 12 (out 31) maximally informative FF features, minimal most effective insole positions (two per foot) for sensing, improve use + methods tested improved method using over 7000 samples collected from ten volunteers a natural, unconstrained,...
In this paper we present the requirements, design and pre-deployment testing of a transportation bus as Mobile Enterprise Sensor Bus (M-ESB) service in China that supports two main requirements: to monitor urban physical environment, road conditions. Although, several such projects have been proposed previously, integrating both environment condition monitoring using data exchange interface feed cloud computing system, is novel approach. We architecture for M-ESB addition propose new...