A Review of Recent Hardware and Software Advances in GPU-Accelerated Edge-Computing Single-Board Computers (SBCs) for Computer Vision.

Computer Vision (CV) has become increasingly important for Single-Board Computers (SBCs) due to their widespread deployment in addressing real-world problems. Specifically, in the context of smart cities, there is an emerging trend of developing end-to-end video analytics solutions designed to address urban challenges such as traffic management, disaster response, and waste management. However, deploying CV solutions on SBCs presents several pressing challenges (e.g., limited computation power, inefficient energy management, and real-time processing needs) hindering their use at scale. Graphical Processing Units (GPUs) and software-level developments have emerged recently in addressing these challenges to enable the elevated performance of SBCs; however, it is still an active area of research. There is a gap in the literature for a comprehensive review of such recent and rapidly evolving advancements on both software and hardware fronts. The presented review provides a detailed overview of the existing GPU-accelerated edge-computing SBCs and software advancements including algorithm optimization techniques, packages, development frameworks, and hardware deployment specific packages. This review provides a subjective comparative analysis based on critical factors to help applied Artificial Intelligence (AI) researchers in demonstrating the existing state of the art and selecting the best suited combinations for their specific use-case. At the end, the paper also discusses potential limitations of the existing SBCs and highlights the future research directions in this domain.

Understanding the relationship between surfing performance and fin design.

This research aimed to determine whether accomplished surfers could accurately perceive how changes to surfboard fin design affected their surfing performance. Four different surfboard fins, including conventional, single-grooved, and double-grooved fins, were developed using computer-aided design combined with additive manufacturing (3D printing). We systematically installed these 3D-printed fins into instrumented surfboards, which six accomplished surfers rode on waves in the ocean in a random order while blinded to the fin condition. We quantified the surfers' wave-riding performance during each surfing bout using a sport-specific tracking device embedded in each instrumented surfboard. After each fin condition, the surfers rated their perceptions of the Drive, Feel, Hold, Speed, Stiffness, and Turnability they experienced while performing turns using a visual analogue scale. Relationships between the surfer's perceptions of the fins and their surfing performance data collected from the tracking devices were then examined. The results revealed that participants preferred the single-grooved fins for Speed and Feel, followed by double-grooved fins, commercially available fins, and conventional fins without grooves. Crucially, the surfers' perceptions of their performance matched the objective data from the embedded sensors. Our findings demonstrate that accomplished surfers can perceive how changes to surfboard fins influence their surfing performance.

Free public transport and older people: An ethnographic study of an Australian bus service.

OBJECTIVES: This study explores older people's use of a free bus service in Wollongong, Australia. The research focus was on understanding the experiences of people over the age of 60 who use the service and the extent to which it contributes to their physical, mental and social well-being. METHODS: The ethnographic research utilised fieldwork and interviews for data collection. Participant observations took place on the bus, and interviews were undertaken at bus stops. Data were analysed using an inductive thematic approach. RESULTS: The research highlighted how bus services can be caring places for older people and a bus journey could be characterised as a therapeutic milieu. Travelling on the bus provided opportunities for health promotion due to active transport. Subsidised access to public transport supported people to maintain social connections throughout the city. CONCLUSIONS: Bus travel has contributed positively to the physical, mental and social well-being of people over the age of 60 in Wollongong.

V2ReID: Vision-Outlooker-Based Vehicle Re-Identification.

With the increase of large camera networks around us, it is becoming more difficult to manually identify vehicles. Computer vision enables us to automate this task. More specifically, vehicle re-identification (ReID) aims to identify cars in a camera network with non-overlapping views. Images captured of vehicles can undergo intense variations of appearance due to illumination, pose, or viewpoint. Furthermore, due to small inter-class similarities and large intra-class differences, feature learning is often enhanced with non-visual cues, such as the topology of camera networks and temporal information. These are, however, not always available or can be resource intensive for the model. Following the success of Transformer baselines in ReID, we propose for the first time an outlook-attention-based vehicle ReID framework using the Vision Outlooker as its backbone, which is able to encode finer-level features. We show that, without embedding any additional side information and using only the visual cues, we can achieve an 80.31% mAP and 97.13% R-1 on the VeRi-776 dataset. Besides documenting our research, this paper also aims to provide a comprehensive walkthrough of vehicle ReID. We aim to provide a starting point for individuals and organisations, as it is difficult to navigate through the myriad of complex research in this field.

Edge-Computing Video Analytics Solution for Automated Plastic-Bag Contamination Detection: A Case from Remondis.

The increased global waste generation rates over the last few decades have made the waste management task a significant problem. One of the potential approaches adopted globally is to recycle a significant portion of generated waste. However, the contamination of recyclable waste has been a major problem in this context and causes almost 75% of recyclable waste to be unusable. For sustainable development, efficient management and recycling of waste are of huge importance. To reduce the waste contamination rates, conventionally, a manual bin-tagging approach is adopted; however, this is inefficient and requires huge labor effort. Within household waste contamination, plastic bags have been found to be one of the main contaminants. Towards automating the process of plastic-bag contamination detection, this paper proposes an edge-computing video analytics solution using the latest Artificial Intelligence (AI), Artificial Intelligence of Things (AIoT) and computer vision technologies. The proposed system is based on the idea of capturing video of waste from the truck hopper, processing it using edge-computing hardware to detect plastic-bag contamination and storing the contamination-related information for further analysis. Faster R-CNN and You Only Look Once version 4 (YOLOv4) deep learning model variants are trained using the Remondis Contamination Dataset (RCD) developed from Remondis manual tagging historical records. The overall system was evaluated in terms of software and hardware performance using standard evaluation measures (i.e., training performance, testing performance, Frames Per Second (FPS), system usage, power consumption). From the detailed analysis, YOLOv4 with CSPDarkNet_tiny was identified as a suitable candidate with a Mean Average Precision (mAP) of 63% and FPS of 24.8 with NVIDIA Jetson TX2 hardware. The data collected from the deployment of edge-computing hardware on waste collection trucks was used to retrain the models and improved performance in terms of mAP, False Positives (FPs), False Negatives (FNs) and True Positives (TPs) was achieved for the retrained YOLOv4 with CSPDarkNet_tiny backbone model. A detailed cost analysis of the proposed system is also provided for stakeholders and policy makers.

A process-driven and need-oriented framework for review of technological contributions to disaster management.

An escalation in the frequency and intensity of natural disasters is observed over the last decade, forcing the community to develop innovative technological solutions to reduce disaster impact. The multidisciplinary nature of disaster management suggests the collaboration between different disciplines for an efficient outcome; however, any such collaborative framework is found lacking in the literature. A common taxonomy and interpretation of disaster management related constraints are critical to develop efficient technological solutions. This article proposes a process-driven and need-oriented framework to facilitate the review of technology based contributions in disaster management. The proposed framework aims to bring technological contributions and disaster management activities in a single frame to better classify and analyse the literature. A systematic review of benchmark disruptive technology based contributions to disaster management has been performed using the proposed framework. Furthermore, a set of basic requirements and constraints at each phase of a disaster management process have been proposed and cited literature has been analysed to highlight corresponding trends. Finally, the scope of computer vision in disaster management is explored and potential activities where computer vision can be used in the future are highlighted.

A Clinician-Led, Experience-Based Co-Design Approach for Developing mHealth Services to Support the Patient Self-management of Chronic Conditions: Development Study and Design Case.

BACKGROUND: Despite the increasing use of mobile health (mHealth) services, such as mHealth apps or SMS text messaging services, that support the patient self-management of chronic conditions, many existing mHealth services lack theoretical guidance. In addition, although often the target audience for requirement acquisition at the initial mHealth app design stage, it is a common challenge for them to fully conceptualize their needs for mHealth services that help self-manage chronic conditions. OBJECTIVE: This study proposes a novel co-design approach with the initial requirements for mHealth services proposed by clinicians based on their experiences in guiding patients to self-manage chronic conditions. A design case is presented to illustrate our innovative approach to designing an mHealth app that supports the self-management of patients with obesity in their preparation for elective surgery. METHODS: We adopted a clinician-led co-design approach. The co-design approach consisted of the following four cyclic phases: understanding user needs, identifying an applicable underlying theory, integrating the theory into the prototype design, and evaluating and refining the prototype mHealth services with patients. Expert panel discussions, a literature review, intervention mapping, and patient focus group discussions were conducted in these four phases. RESULTS: In stage 1, the expert panel proposed the following three common user needs: motivational, educational, and supportive needs. In stage 2, the team selected the Social Cognitive Theory to guide the app design. In stage 3, the team designed and developed the key functions of the mHealth app, including automatic push notifications; web-based resources; goal setting and monitoring; and interactive health-related exchanges that encourage physical activity, healthy eating, psychological preparation, and a positive outlook for elective surgery. Push notifications were designed in response to a patient's risk level, as informed by the person's response to a baseline health survey. In stage 4, the prototype mHealth app was used to capture further requirements from patients in the two focus group discussions. Focus group participants affirmed the potential benefits of the app and suggested more requirements for the function, presentation, and personalization needs. The app was improved based on these suggestions. CONCLUSIONS: This study reports an innovative co-design approach that was used to leverage the clinical experiences of clinicians to produce the initial prototype app and the approach taken to allow patients to effectively voice their needs and expectations for the mHealth app in a focus group discussion. This approach can be generalized to the design of any mHealth service that aims to support the patient self-management of chronic conditions.

Impact of drivers on real-driving fuel consumption and emissions performance.

Eco-driving has attracted great attention as a cost-effective and immediate measure to reduce fuel consumption significantly. Understanding the impact of driver behaviour on real driving emissions (RDE) is of great importance for developing effective eco-driving devices and training programs. Therefore, this study was conducted to investigate the performance of different drivers using a portable emission measurement system. In total, 30 drivers, including 15 novice and 15 experienced drivers, were recruited to drive the same diesel vehicle on the same route, to minimise the effect of uncontrollable real-world factors on the performance evaluation. The results show that novice drivers are less skilled or more aggressive than experienced drivers in using the accelerator pedal, leading to higher vehicle and engine speeds. As a result, fuel consumption rates of novice drivers vary in a slightly greater range than those of experienced drivers, with a marginally higher (2%) mean fuel consumption. Regarding pollutant emissions, CO and THC emissions of all drivers are well below the standard limits, while NOx and PM emissions of some drivers significantly exceed the limits. Compared with experienced drivers, novice drivers produce 17% and 29% higher mean NOx and PM emissions, respectively. Overall, the experimental results reject the hypothesis that driver experience has significant impacts on fuel consumption performance. The real differences lie in the individual drivers, as the worst performing drivers have significantly higher fuel consumption rates than other drivers, for both novice and experienced drivers. The findings suggest that adopting eco-driving skills could deliver significant reductions in fuel consumption and emissions simultaneously for the worst performing drivers, regardless of driving experience.

A review of strategies for mitigating roadside air pollution in urban street canyons.

Urban street canyons formed by high-rise buildings restrict the dispersion of vehicle emissions, which pose severe health risks to the public by aggravating roadside air quality. However, this issue is often overlooked in city planning. This paper reviews the mechanisms controlling vehicle emission dispersion in urban street canyons and the strategies for managing roadside air pollution. Studies have shown that air pollution hotspots are not all attributed to heavy traffic and proper urban design can mitigate air pollution. The key factors include traffic conditions, canyon geometry, weather conditions and chemical reactions. Two categories of mitigation strategies are identified, namely traffic interventions and city planning. Popular traffic interventions for street canyons include low emission zones and congestion charges which can moderately improve roadside air quality. In comparison, city planning in terms of building geometry can significantly promote pollutant dispersion in street canyons. General design guidelines, such as lower canyon aspect ratio, alignment between streets and prevailing winds, non-uniform building heights and ground-level building porosity, may be encompassed in new development. Concurrently, in-street barriers are widely applicable to rectify the poor roadside air quality in existing street canyons. They are broadly classified into porous (e.g. trees and hedges) and solid (e.g. kerbside parked cars, noise fences and viaducts) barriers that utilize their aerodynamic advantages to ease roadside air pollution. Post-evaluations are needed to review these strategies by real-world field experiments and more detailed modelling in the practical perspective.

Green infrastructure for air quality improvement in street canyons.

Street canyons are generally highly polluted urban environments due to high traffic emissions and impeded dispersion. Green infrastructure (GI) is one potential passive control system for air pollution in street canyons, yet optimum GI design is currently unclear. This review consolidates findings from previous research on GI in street canyons and assesses the suitability of different GI forms in terms of local air quality improvement. Studies on the effects of various GI options (trees, hedges, green walls, green screens and green roofs) are critically evaluated, findings are synthesised, and possible recommendations are summarised. In addition, various measurement methods used for quantifying the effectiveness of street greening for air pollution reduction are analysed. Finally, we explore the findings of studies that have compared plant species for pollution mitigation. We conclude that the influences of different GI options on air quality in street canyons depend on street canyon geometry, meteorological conditions and vegetation characteristics. Green walls, green screens and green roofs are potentially viable GI options in existing street canyons, where there is typically a lack of available planting space. Particle deposition to leaves is usually quantified by leaf washing experiments or by microscopy imaging techniques, the latter of which indicates size distribution and is more accurate. The pollutant reduction capacity of a plant species largely depends on its macromorphology in relation to the physical environment. Certain micromorphological leaf traits also positively correlate with deposition, including grooves, ridges, trichomes, stomatal density and epicuticular wax amount. The complexity of street canyon environments and the limited number of previous studies on novel forms of GI in street canyons mean that offering specific recommendations is currently unfeasible. This review highlights a need for further research, particularly on green walls and green screens, to substantiate their efficacy and investigate technical considerations.

Traffic exhaust to wildfires: PM2.5 measurements with fixed and portable, low-cost LoRaWAN-connected sensors.

Air pollution with PM2.5 (particulate matter smaller than 2.5 micro-metres in diameter) is a major health hazard in many cities worldwide, but since measuring instruments have traditionally been expensive, monitoring sites are rare and generally show only background concentrations. With the advent of low-cost, wirelessly connected sensors, air quality measurements are increasingly being made in places where many people spend time and pollution is much worse: on streets near traffic. In the interests of enabling members of the public to measure the air that they breathe, we took an open-source approach to designing a device for measuring PM2.5. Parts are relatively cheap, but of good quality and can be easily found in electronics or hardware stores, or on-line. Software is open source and the free LoRaWAN-based "The Things Network" the platform. A number of low-cost sensors we tested had problems, but those selected performed well when co-located with reference-quality instruments. A network of the devices was deployed in an urban centre, yielding valuable data for an extended time. Concentrations of PM2.5 at street level were often ten times worse than at air quality stations. The devices and network offer the opportunity for measurements in locations that concern the public.

Computer Vision and IoT-Based Sensors in Flood Monitoring and Mapping: A Systematic Review.

Floods are amongst the most common and devastating of all natural hazards. The alarming number of flood-related deaths and financial losses suffered annually across the world call for improved response to flood risks. Interestingly, the last decade has presented great opportunities with a series of scholarly activities exploring how camera images and wireless sensor data from Internet-of-Things (IoT) networks can improve flood management. This paper presents a systematic review of the literature regarding IoT-based sensors and computer vision applications in flood monitoring and mapping. The paper contributes by highlighting the main computer vision techniques and IoT sensor approaches utilised in the literature for real-time flood monitoring, flood modelling, mapping and early warning systems including the estimation of water level. The paper further contributes by providing recommendations for future research. In particular, the study recommends ways in which computer vision and IoT sensor techniques can be harnessed to better monitor and manage coastal lagoons-an aspect that is under-explored in the literature.

Edge-Computing Video Analytics for Real-Time Traffic Monitoring in a Smart City.

The increasing development of urban centers brings serious challenges for traffic management. In this paper, we introduce a smart visual sensor, developed for a pilot project taking place in the Australian city of Liverpool (NSW). The project's aim was to design and evaluate an edge-computing device using computer vision and deep neural networks to track in real-time multi-modal transportation while ensuring citizens' privacy. The performance of the sensor was evaluated on a town center dataset. We also introduce the interoperable Agnosticity framework designed to collect, store and access data from multiple sensors, with results from two real-world experiments.

A systematic review of modelling approaches in economic evaluations of health interventions for drug and alcohol problems.

BACKGROUND: The overarching goal of health policies is to maximize health and societal benefits. Economic evaluations can play a vital role in assessing whether or not such benefits occur. This paper reviews the application of modelling techniques in economic evaluations of drug and alcohol interventions with regard to (i) modelling paradigms themselves; (ii) perspectives of costs and benefits and (iii) time frame. METHODS: Papers that use modelling approaches for economic evaluations of drug and alcohol interventions were identified by carrying out searches of major databases. RESULTS: Thirty eight papers met the inclusion criteria. Overall, the cohort Markov models remain the most popular approach, followed by decision trees, Individual based model and System dynamics model (SD). Most of the papers adopted a long term time frame to reflect the long term costs and benefits of health interventions. However, it was fairly common among the reviewed papers to adopt a narrow perspective that only takes into account costs and benefits borne by the health care sector. CONCLUSIONS: This review paper informs policy makers about the availability of modelling techniques that can be used to enhance the quality of economic evaluations for drug and alcohol treatment interventions.

An approach to plan and evaluate the location of radiotherapy services and its application in the New South Wales, Australia.

This paper proposes an integrated modelling approach for location planning of radiotherapy treatment services based on cancer incidence and road network-based accessibility. Previous research efforts have established travel distance/time barriers as a key factor affecting access to cancer treatment services, as well as epidemiological studies have shown that cancer incidence rates vary with population demography. Our study is built on the evidence that the travel distances to treatment centres and demographic profiles of the accessible regions greatly influence the uptake of cancer radiotherapy (RT) services. An integrated service planning approach that combines spatially-explicit cancer incidence projections, and the placement of new RT services based on road network based accessibility measures have never been attempted. This research presents a novel approach for the location planning of RT services, and demonstrates its viability by modelling cancer incidence rates for different age-sex groups in New South Wales, Australia based on observed cancer incidence trends; and estimations of the road network-based access to current NSW treatment centres. Using three indices (General Efficiency, Service Availability and Equity), we show how the best location for a new RT centre may be chosen when there are multiple competing locations.

Drivers influencing adaptive management: a retrospective evaluation of water quality decisions in South East Queensland (Australia).

This article analyzes interviews with natural resource managers in South East Queensland (SEQ), Australia. The objectives of the research are (i) to apply and test deductive/inductive text analysis methods for constructing a conceptual model of water quality decision-making in SEQ, (ii) to understand the role of information in the decision-making process, and (iii) to understand how to improve adaptive management in SEQ. Our methodology provided the means to quickly and objectively explore interview data and also reduce potential subjective bias normally associated with deductive text analysis methods. At a more practical level, our methodology indicates potential intervention points if one is to influence the decision-making process in the region. Results indicate that relevant information is often ignored in SEQ, with significant consequences for adaptive management. Contextual factors (political, social, and environmental) together with effective communication or lobbying strategies often prevent evidence-based decisions. We propose that in addition to generating information to support decisions, adaptive management also requires an appraisal of the true character of the decision-making process, which includes how stakeholders interact, what information is relevant and salient to management, and how the available information should be communicated to stakeholders and decision-making bodies.

Generating a dynamic synthetic population--using an age-structured two-sex model for household dynamics.

Generating a reliable computer-simulated synthetic population is necessary for knowledge processing and decision-making analysis in agent-based systems in order to measure, interpret and describe each target area and the human activity patterns within it. In this paper, both synthetic reconstruction (SR) and combinatorial optimisation (CO) techniques are discussed for generating a reliable synthetic population for a certain geographic region (in Australia) using aggregated- and disaggregated-level information available for such an area. A CO algorithm using the quadratic function of population estimators is presented in this paper in order to generate a synthetic population while considering a two-fold nested structure for the individuals and households within the target areas. The baseline population in this study is generated from the confidentialised unit record files (CURFs) and 2006 Australian census tables. The dynamics of the created population is then projected over five years using a dynamic micro-simulation model for individual- and household-level demographic transitions. This projection is then compared with the 2011 Australian census. A prediction interval is provided for the population estimates obtained by the bootstrapping method, by which the variability structure of a predictor can be replicated in a bootstrap distribution.

SimAmph: an agent-based simulation model for exploring the use of psychostimulants and related harm amongst young Australians.

BACKGROUND: Computer simulations provide a useful tool for bringing together diverse sources of information in order to increase understanding of the complex aetiology of drug use and related harm, and to inform the development of effective policies. In this paper, we describe SimAmph, an agent-based simulation model for exploring how individual perceptions, peer influences and subcultural settings shape the use of psychostimulants and related harm amongst young Australians. METHODS: We present the conceptual architecture underpinning SimAmph, the assumptions we made in building it, the outcomes of sensitivity analysis of key model parameters and the results obtained when we modelled a baseline scenario. RESULTS: SimAmph's core behavioural algorithm is able to produce social patterns of partying and recreational drug use that approximate those found in an Australian national population survey. We also discuss the limitations involved in running closed-system simulations and how the model could be refined to include the social, as well as health, consequences of drug use. CONCLUSION: SimAmph provides a useful tool for integrating diverse data and exploring drug policy scenarios. Its integrated approach goes some way towards overcoming the compartmentalisation that characterises existing data, and its structure, parameters and values can be modified as new data and understandings emerge. In a companion paper (Dray et al., 2011), we use the model outlined here to explore the possible consequences of two policy scenarios.

Are drug detection dogs and mass-media campaigns likely to be effective policy responses to psychostimulant use and related harm? Results from an agent-based simulation model.

BACKGROUND: Agent-based simulation models can be used to explore the impact of policy and practice on drug use and related consequences. In a linked paper (Perez et al., 2011), we described SimAmph, an agent-based simulation model for exploring the use of psychostimulants and related harm amongst young Australians. METHODS: In this paper, we use the model to simulate the impact of two policy scenarios on engagement in drug use and experience of drug-related harm: (i) the use of passive-alert detection (PAD) dogs by police at public venues and (ii) the introduction of a mass-media drug prevention campaign. RESULTS: The findings of the first simulation suggest that only very high rates of detection by PAD dogs reduce the intensity of drug use, and that this decrease is driven mainly by a four-fold increase in negative health consequences as detection rates rise. In the second simulation, our modelling showed that the mass-media prevention campaign had little effect on the behaviour and experience of heavier drug users. However, it led to reductions in the prevalence of health-related conditions amongst moderate drug users and prevented them from becoming heavier users. CONCLUSION: Agent-based modelling has great potential as a tool for exploring the reciprocal relationships between environments and individuals, and for highlighting how intended changes in one domain of a system may produce unintended consequences in other domains. The exploration of these linkages is important in an environment as complex as the drug policy and intervention arena.