Project Dragonfly is a two-in-one industrial wastewater and air toxicity monitoring solution that is environmentally friendly, noninvasive, and cost-effective. The project presents remarkable significance when regulation of industrial emissions becomes crucial.The project utilizes Microsoft Azure platform along with Microsoft's proprietary cloud products and services, and Android mobile application for its software components and database: Lolin D32 Pro, Neffos Y5i, multiple sensors and a quadrotor helicopter (quadcopter) are among its main hardware components. The sensors are packed into two functional units: air monitoring unit (AMU) and water monitoring unit (WMU).

Parking has been a common problem over several years in many cities around the globe. The search for parking space leads to congestion, frustration and increased air pollution. Information of vacant parking space would facilitate to reduce congestion and subsequent air pollution. Therefore, the aim of the study is to acquire vehicle occupancy in an open parking lot using deep learning. Thermal camera was used to collect videos during varying environmental conditions and frames from these videos were extracted to prepare the dataset. The frames in the dataset were manually labelled as there were no pre-labelled thermal images available. Vehicle detection with deep learning algorithms was implemented to perform multi-object detection. Multiple deep learning networks such as Yolo, Yolo-conv, GoogleNet, ReNet18 and ResNet50 with varying layers and architectures were evaluated on vehicle detection. ResNet18 performed better than other detectors which had an average precision of 96.16 and log-average miss rate of 19.40. The detected results were compared with a template of parking spaces to identify vehicle occupancy information. Yolo, Yolo-conv, GoogleNet and ResNet18 are computationally efficient detectors which took less processing time and are suitable for real-time detection while Resnet50 was computationally expensive.

The household solid waste (HSW) classification management plays an important role in reducing and recycling urban garbage in current residential community. However, with the rapid development of urbanisation in developing countries and the continuous increase of urban waste, the traditional waste management modes and technologies cannot satisfy the newly emerged needs of collecting and transporting solid waste in the accurate and effective way. Under this background, this research carries out a preliminary study on the HSW classification system and the resource servitisation. According to the HSW classification process, a cloud-based product-service systems (PSSs) platform, targeting on managing those solid waste management resources such as internet of things enabled smart waste bin, is established. The proposed PSS platform will be illustrated from four layers: physical layer, management layer, service layer and application layer. Additionally, the multi-stakeholders' value analysis of the platform will be provided from five aspects. Finally, a PSS-based real-life case of managing household waste bin is investigated and analysed in order to verify the feasibility of the proposed platform.

This study studies the technology of environmental monitoring and control in an intelligent Internet of Things (IoT) perception. To improve the issue of small coverage and low stability in the traditional environmental parameter testing, a new environment monitoring technique based on intelligent perception is proposed. The technical framework consists of three layers, intelligent perception layer, network communication layer, and application layer. The intelligent perception collects and transmits data to the application-level server via the network communication layer for data analysis and diversified display. Based on this technique, we constructed a smart home environment monitoring and control system. The experimental test result shows that the system can accurately collect and process the data through the server and diversified displayed, which verifies the accuracy and reliability of this technique which is potential for further application.

Five UK cities will implement clean air zones to improve air quality (AQ), specifically in relation to oxides of nitrogen, and 253 UK local authorities have declared AQ management areas. Extended range electric vehicles can offer zero emission (ZE) operation but cities lack the ability to monitor and control when vehicles can switch from engine to battery. Project Autonomous and Connected vehicles for CleaneR Air (ACCRA) aims to develop and demonstrate a system allowing hybrid vehicle to become part of a city's urban traffic management control system; monitoring the vehicles’ location and operational state, and controlling the strategy to ensure ZE operation through geofenced zones with poor AQ. This study demonstrates a new methodology to model emissions using state-of-the-art instantaneous vehicle emissions modelling, geographic information system (GIS) and a new method for capturing vehicle behaviour using global positioning system. Probe vehicles were used for the pilot study in Leeds, UK, to capture drive-cycle data and the emissions are modelled. A GIS interface is used to match these emissions to the network. Finally, a high-resolution emissions map is generated to be used as input for AQ dispersion models and the ACCRA decision-making engine for the generation of geofencing AQ zones.

Integrating heterogeneous wireless sensor networks with the Sensor Web will increase the utilisation of sensors and facilitate the sharing of their observations in environmental monitoring. A centralised framework was introduced for the semantic integration of heterogeneous sensors and their observations into open geospatial consortium sensor observation services (SOSs). An ontology called 1451 ontology was created following IEEE 1451 standards. The 1451 ontology not only describes the sensor properties and observations, but it also specifies the communication interface and protocol. Another ontology called SOS data ontology was also created to represent the feature of interest of the SOS. A matching rule was established to map the two created ontologies with the aim of creating a uniform collaboration of sensors scattered worldwide through the Sensor web. A case study of soil temperature sensor and three-dimensional digital compass shows that sensors can actively register themselves and insert observations into the SOS through the developed programme embedded in terminal devices and the ontology matching module of the web. A semantic link between the IEEE 1451 specifications and the SOS operations will enable the spatially distributed sensors to publish their information in a unified way and to work cooperatively in real-time for significant environmental monitoring.

Presents a collection of slides covering the following: Internet of Things; SCADA-as-a-service; WaterWorX SaaS model; smart canal; interoperability; Open Standards Reference Model; field device integration technology; and OPC architecture.

Activated sludge is a typical process for waste water treatment; meanwhile, it is an energy-intensive process. Operation optimization is a solution to save energy, where control models are much needed. In this paper, a dynamic LSSVM model for activated sludge process is proposed and validated. Time delay and model orders are involved during the re-establishment process of the training datasets; by this way, the dynamic characteristic of the process is reflected. Finally, BSM1 will be taken as the objective process for validation research, along with convincing results.

Studies on on-road behaviour imply that designing user-centred services is important for raising awareness about severe weather and adverse road conditions. Along with the developments of new communication technologies and practices, the research area of ITS is challenged to move on from traditional ways of collecting and distributing traffic weather information. This study presents two methods for potential improvements and personalisation of traffic weather information. The methods were demonstrated and evaluated by 440 respondents in Stockholm. Weather alerts were sent by SMS 12–48 h, up to a week, prior to the occurrence of severe weather events during 2008–2010. The service was personalised because of assumptions regarding perception and memory of weather, including user's recent observations. The second aspect of potential improvement was the introduction of a social network component, including user-generated local weather observations. The impact of the service was evaluated in a longitudinal study through a series of questionnaires on user behaviour and evaluation of the service. The combination of the two methods proved efficient as the amount of changed decisions was of considerable amplitude. A correlation between time of exposure and changed decisions implies that social components and interactivity may be a powerful tool in traffic weather services and ITS.

Recognition of individuals is necessary for accurate estimation of wildlife population dynamics for effective management and conservation. Identifying individual wildlife by their distinctive body marks is one of the least invasive methods available. Although widely practiced, this method is mostly manual where newly captured images are compared with those in the library of previously captured images. The ability to do so automatically using computer vision techniques can improve speed and accuracy, facilitate on-field matching, and so on. This paper reports the results of using a texture based image feature descriptor, the Local Binary Patterns (LBP), for the automatic identification of an important endangered species - The Great Crested Newt (GCN). The proposed approach is tested on a database of newts' distinctive belly images which are treated as a source of biometric information. Results indicate that when both appearance and spatial information of newt belly patterns are encoded into a composite LBP feature vector, the discriminating power of the system can improve significantly. (6 pages)