Browsing by Author "Tran, Trung Hieu"

Now showing 1 - 15 of 15
  • Thumbnail Image
    ItemOpen Access
    Advanced visual slam and image segmentation techniques for augmented reality
    (IGI Global, 2022-08-10) Jiang, Yirui; Tran, Trung Hieu; Williams, Leon
    Augmented reality can enhance human perception to experience a virtual-reality intertwined world by computer vision techniques. However, the basic techniques cannot handle complex large-scale scenes, tackle real-time occlusion, and render virtual objects in augmented reality. Therefore, this paper studies potential solutions, such as visual SLAM and image segmentation, that can address these challenges in the augmented reality visualizations. This paper provides a review of advanced visual SLAM and image segmentation techniques for augmented reality. In addition, applications of machine learning techniques for improving augmented reality are presented.
  • Thumbnail Image
    ItemOpen Access
    An agent-based model for improving museum design to enhance visitor experience.
    (Cranfield University, 2022-11) Ji, Yijing; Tran, Trung Hieu; Simon, Jude; Williams, Leon
    Museum experience is a multi-layered journey including ontological, sensory, intellectual, aesthetic, and social aspects. In recent years, the museum sector has faced a number of challenges in terms of the need to enhance the potential of the experience while maintaining authenticity and credibility. For public science communication in museums, exhibition is an important medium for connecting exhibits and visitors, and as such, the study of visitors' senses and behaviours under impact of various museum layout designs has become an important research direction. The purpose of this study is to explore the recall of visitors' memories in the exhibition space by integrating images, echoes and tactile senses, and then transform memories and interactions into their own experience and knowledge base. The impact of spatial design and other design elements on visitors' memories is also explored. We have conducted Agent-based simulation, by setting up virtual visitors, exhibition spaces and artefact based on real gallery spaces, as a time-saving and cost-saving method to improve exhibition interactivity and content coherence. Meanwhile, through the simulation of this novel way, visitors can observe and predict the interactive experience between visitors and the exhibition, so as to improve the curatorial team's research on tourist behaviour and spatial design scheme. Next, the simulated data on visitors' memory recall behaviour is compared with the actual observed data to explore the authenticity of visitors' behaviour in the simulated museum. The impact of this study is by integrating a variety of shared understandings between curators, exhibition management and participants, drawing on diverse information based on experience, practice and simulation. It seeks to provide future museum- oriented practitioners, particularly in small and medium-sized museum exhibition spaces, with a novel perspective and approach to observing or predicting the experience of visitors' sensory interactions within an exhibition. Furthermore, at the same time as enhancing the visitor’s exhibition experience, the content of exhibition story is fully transformed into its own knowledge accumulation.
  • Thumbnail Image
    ItemOpen Access
    The circular economy transformation of airports: an alternative model for retail waste management
    (MDPI, 2023-02-20) Tjahjono, Michelle; Ünal, Enes; Tran, Trung Hieu
    Airport terminals worldwide generate approximately 6 million tons of passenger waste annually. Increased awareness of climate change and global interventions for environmental sustainability requires a reassessment of airports’ current methods of waste management. This paper proposes a new design concept solution called circular airport retail waste management (CAWM) for airport terminal retail waste processing, which aims to reduce and ideally eliminate airport waste ending up in landfill or incineration. Given the need for novelty and challenging the status-quo, the double diamond design process was adopted as the research method. The research began by collating the current practices of retail waste processing in airports via a literature review and field observations. Secondly, a critical analysis of the current processes was conducted to identify the intervention points. Thirdly, a concept solution was developed based on the circular economy (CE) 9R framework. Finally, the CAWM concept was delivered to airport waste management personnel for review. CAWM offers a structured way of airport retail waste management practices, including the segregation of nonrecyclable and recyclable waste (i.e., different bin designs, color coding, harmonization of waste colors, improved instructions and signage, various bin locations, training, and installing more liquid disposal and donation stations). Airports can leverage CAWM for greater efficiency and cost-effectiveness regarding airport terminal waste processing, such that more waste can be diverted from incineration and landfill to recovery, which will subsequently help airports achieve net-zero targets. This research contributes to the extant CE literature, especially in the aviation industry context, where the academic discourse surrounding this subject and its peculiarities are limited.
  • Thumbnail Image
    ItemOpen Access
    Development of efficient data management and analytics tools for Intelligent sanitation network design.
    (Cranfield University, 2023-05) Jiang, Yirui; Tran, Trung Hieu; Williams, Leon
    According to the World Health Organisation, billions of people lack access to basic sanitation facilities and services, resulting in estimated 2.9 million cases of diseases and 95,000 deaths each year. This is because poor planning, design, maintenance, and access in traditional sanitation networks. Nowadays, intelligent sanitation systems leveraging the Internet of Things (IoT) technology can provide efficient and sustainable services, incorporating sensors, hardware, software, and wireless communication. Furthermore, advanced data analytics tools combined with the intelligent sanitation systems can provide a deeper insight into operations, make informed decisions, and enhance user experience, thereby improving sanitation services. The thesis provides a comprehensive review of literature on intelligent sanitation systems from both academic and industrial perspectives, with the objective of identifying recent advances, research gaps, opportunities, and challenges. Existing solutions for intelligent sanitation are fragmented and immature due to a lack of a unified framework and tool. To address these issues, the thesis introduces a generalised Sanitation-IoT (San-IoT) framework to manage sanitation facilities and a standardised Sanitation-IoT-Data Analytics (San-IoT-DA) tool to analyse sanitation data. The framework and tool can serve as a foundation for future research and development in intelligent sanitation systems. The San-IoT framework can enhance the connectivity, operability, and management of IoT-based sanitation networks. The San-IoT-DA tool is designed to standardise the collection, analysis, and management of sanitation data for providing efficient data processing and improving decision making. The feasibility of the proposed framework and tool was evaluated on a case study of the Cranfield intelligent toilet. The San-IoT framework has the potential to enable system monitoring and control, user health monitoring, user behaviour analysis, improve water usage efficiency, reduce energy consumption, and facilitate decision-making among global stakeholders. The San-IoT-DA tool can detect patterns, identify trends, predict outcomes, and detect anomalies. The thesis offers valuable insights to practitioners, academics, engineers, policymakers, and other stakeholders on leveraging IoT and data analytics to improve the efficiency, accessibility, and sustainability of the sanitation industry.
  • Thumbnail Image
    ItemOpen Access
    Development of Internet of Things and Artificial Intelligence for intelligent sanitation systems: a literature review
    (EnPress Publisher, 2024-10-30) Jiang, Yirui; Tran, Trung Hieu; Collins, Matt; Williams, Leon
    Adequate sanitation is crucial for human health and well-being, yet billions worldwide lack access to basic facilities. This comprehensive review examines the emerging field of intelligent sanitation systems, which leverage Internet of Things (IoT) and advanced Artificial Intelligence (AI) technologies to address global sanitation challenges. The existing intelligent sanitation systems and applications is still in their early stages, marked by inconsistencies and gaps. The paper consolidates fragmented research from both academic and industrial perspectives based on PRISMA protocol, exploring the historical development, current state, and future potential of intelligent sanitation solutions. The assessment of existing intelligent sanitation systems focuses on system detection, health monitoring, and AI enhancement. The paper examines how IoT-enabled data collection and AI-driven analytics can optimize sanitation facility performance, predict system failures, detect health risks, and inform decision-making for sanitation improvements. By synthesizing existing research, identifying knowledge gaps, and discussing opportunities and challenges, this review provides valuable insights for practitioners, academics, engineers, policymakers, and other stakeholders. It offers a foundation for understanding how advanced IoT and AI techniques can enhance the efficiency, sustainability, and safety of the sanitation industry.
  • Thumbnail Image
    ItemOpen Access
    Enhancing automotive safety through advanced object behaviour tracking for intelligent traffic and transport system
    (IEEE, 2024-06-26) Saha, Chandni; Tran, Trung Hieu; Syamal, Soujanya
    In the ever-evolving landscape of vehicle motion analysis, the imperative for enhanced road safety has underscored the importance of tracking object behavior, with a particular focus on vehicles. This paper proposes an innovative approach specifically designed for tracking vehicle behavior, emphasizing collision risk analysis. Central to this approach is the development of a powerful model for meticulous vehicle detection and classification, using real-world video feeds. By leveraging the YOLO algorithm, our method achieves real-time object detection, which is crucial for effective traffic monitoring. We extend our work beyond simple detection to include trajectory tracking, wherein we analyze the complexities of vehicle movement to identify patterns of traffic behavior and potential congestion hotspots. To refine our system further, we have integrated the DeepSORT algorithm, which applies the Kalman Filter and Hungarian algorithm to achieve enhanced multi-object tracking. This allows for seamless tracking through occlusions and at intersections. Our system is adept at identifying potential collision risks by employing advanced risk analysis techniques that assess severity and predict possible incidents. This paves the way for robust preventative measures and underscores our commitment to improving road safety, reducing accidents, saving lives, and enhancing traffic flow. As urban environments grow, such technological advancements are poised to make a significant impact on traffic management and safety standards. We have validated our system's performance using comprehensive datasets, showcasing marked improvements in detection accuracy, precision, and tracking capabilities under various conditions. The development and successful validation of our system not only confirm the viability of our approach but also lay the foundation for future developments in object-tracking technology for autonomous systems.
  • Thumbnail Image
    ItemOpen Access
    An evolution of statistical pipe failure models for drinking water networks: a targeted review
    (IWA, 2022-01-19) Barton, Neal A.; Hallett, Stephen; Jude, Simon R.; Tran, Trung Hieu
    The use of statistical models to predict pipe failures has become an important tool for proactive management of drinking water networks. This targeted review provides an overview of the evolution of existing statistical models, grouped into three categories: deterministic, probabilistic and machine learning. The main advantage of deterministic models is simplicity and relative minimal data requirement. Deterministic models predicting failure rates for the network or large groups of pipes performs well and are useful for shorter prediction intervals that describe the influences of seasonality. Probabilistic models can accommodate randomness and are useful for predicting time to failure, interarrival times and the probability of failure. Probability models are useful for individual pipe models. Generally, machine learning describes large complex data more accurately and can improve predictions for individual pipe failure models yet are complex and require expert knowledge. Non-parametric models are better suited to the non-linear relationships between pipe failure variables. Census data and socio-economic data requires further research. The complexity of choosing the most appropriate statistical model requires careful consideration of the type of variables, prediction interval, spatial level, response type and level of inference is required.
  • Thumbnail Image
    ItemOpen Access
    Formulation and solution technique for agricultural waste collection and transport network design
    (Elsevier, 2023-09-07) Tran, Trung Hieu; Nguyen, Thu Ba T.; Le, Hoa Sen T.; Phung, Duc Chinh
    Agricultural waste management in developing countries has become a challenging issue for rural planners due to the lack of an efficient planning tool. In the countries, farmers burnt agricultural waste at fields after each harvesting season to solve the issue. As a result, it has caused air and water pollution in the rural areas of the countries. In this paper, we present a mixed-integer nonlinear programming model for agricultural waste collection and transport network design that aims to stop burning waste and use the waste to produce bio-organic fertilizer. The model supports rural planners to optimally locate waste storages, and to determine the optimal set of routes for a fleet of vehicles to collect and transport the waste from the storages to the bio-organic fertilizer production facility. In the novel location-assignment-routing problem, the overall objective is to minimize total cost of locating storages, collecting waste from fields and planning vehicle routes. A solution technique is developed to linearise the mixed-integer nonlinear programming model into a model in linear form. In addition, a parallel water flow algorithm is developed to solve efficiently the large-sized instances. The efficiency of the proposed model and algorithm is validated and evaluated on the real case study in Trieu Phong district, Quang Tri province, Vietnam, as well as a set of randomly generated large-sized instances. The results show that our solution approach outperforms the general optimisation solver and tabu search algorithm. Our algorithm can find the optimal or near-optimal solutions for the large-sized instances within a reasonable time.
  • Thumbnail Image
    ItemOpen Access
    Generalised network architectures for environmental sensing: case studies for a digitally enabled environment
    (Elsevier, 2022-04-08) Mead, Mohammed Iqbal; Bevilacqua, M.; Loiseaux, C.; Hallett, Stephen H.; Jude, Simon; Emmanouilidis, Christos; Harris, Jim A.; Leinster, Paul; Mutnuri, S.; Tran, Trung Hieu; Williams, Leon
    A digitally enabled environment is a setting which incorporates sensors coupled with reporting and analytics tools for understanding, observing or managing that environment. Large scale data collection and analysis are a part of the emerging digitally enabled approach for the characterisation and understanding of our environment. It is recognised as offering an effective methodology for addressing a range of complex and interrelated social, economic and environmental concerns. The development and construction of the approach requires advances in analytics control linked with a clear definition of the issues pertaining to the interaction between elements of these systems. This paper presents an analysis of selected issues in the field of analytics control. It also discusses areas of progress, and areas in need of further investigation as sensing networks evolve. Three case studies are described to illustrate these points. The first is a physical analytics test kit developed as a part of the “Reinvent the Toilet Challenge” (RTTC) for process control in a range of environments. The second case study is the Cranfield Urban Observatory that builds on elements of the RTTC and is designed to allow users to develop user interfaces to monitor, characterise and compare a variety of environmental and infrastructure systems plus behaviours (e.g., water distribution, power grids). The third is the Data and Analytics Facility for National Infrastructure, a cloud-based high-performance computing cluster, developed to receive, store and present such data to advanced analytical and visualisation tools.
  • Thumbnail Image
    ItemOpen Access
    A hybrid algorithm for large-scale non-separable nonlinear multicommodity flow problems
    (SAGE, 2023-03-06) Tran, Trung Hieu; Nguyen, ThuBa T.; Jiang, Yirui
    We propose an approach for large-scale non-separable nonlinear multicommodity flow problems by solving a sequence of subproblems which can be addressed by commercial solvers. Using a combination of solution methods such as modified gradient projection, shortest path algorithm and golden section search, the approach can handle general problem instances, including those with (i) non-separable cost, (ii) objective function not available analytically as polynomial but are evaluated using black-boxes, and (iii) additional side constraints not of network flow types. Implemented as a toolbox in commercial solvers, it allows researchers and practitioners, currently conversant with linear instances, to easily manage large-scale convex instances as well. In this article, we compared the proposed algorithm with alternative approaches in the literature, covering both theory and large test cases. New test cases with non-separable convex costs and non-network flow side constraints are also presented and evaluated. The toolbox is available free for academic use upon request.
  • Thumbnail Image
    ItemOpen Access
    Machine learning and mixed reality for smart aviation: applications and challenges
    (Elsevier, 2023-06-04) Jiang, Yirui; Tran, Trung Hieu; Williams, Leon
    The aviation industry is a dynamic and ever-evolving sector. As technology advances and becomes more sophisticated, the aviation industry must keep up with the changing trends. While some airlines have made investments in machine learning and mixed reality technologies, the vast majority of regional airlines continue to rely on inefficient strategies and lack digital applications. This paper investigates the state-of-the-art applications that integrate machine learning and mixed reality into the aviation industry. Smart aerospace engineering design, manufacturing, testing, and services are being explored to increase operator productivity. Autonomous systems, self-service systems, and data visualization systems are being researched to enhance passenger experience. This paper investigate safety, environmental, technological, cost, security, capacity, and regulatory challenges of smart aviation, as well as potential solutions to ensure future quality, reliability, and efficiency.
  • Thumbnail Image
    ItemOpen Access
    Minimizing total cost of home energy consumption under uncertainties
    (Taylor and Francis, 2022-11-29) Tran, Trung Hieu; Nguyen, Thu Ba T.
    long with the development of renewable energy sources, energy storage units are introduced to increase the stability and reliability of electricity production. The storage units can improve the efficiency of energy consumption for consumers as well. By smartly controlling home appliances, renewable energy sources and energy storage units, consumers can satisfy their energy demand with a minimum cost. However, the declined maximum capacity of energy storage units and the unstable power of electricity grid, due to randomly unexpected failures, can cause challenges for consumers’ energy plans. In this article, we develop a novel joint chance-constraint mixed-integer linear programming model to support consumers in finding the optimal energy plans for a minimum cost of energy consumption under the simultaneous impact of unexpected failures on energy storage units and electricity grid. A case study for a set of households in Nottingham, United Kingdom, is used to demonstrate the efficiency of the proposed model. Some interesting insights are achieved for home energy management under uncertainties.
  • Thumbnail Image
    ItemOpen Access
    Predicting the risk of pipe failure using gradient boosted decision trees and weighted risk analysis
    (Nature Publishing Group, 2022-06-17) Barton, Neal Andrew; Hallett, Stephen H.; Jude, Simon R.; Tran, Trung Hieu
    Pipe failure prediction models are essential for informing proactive management decisions. This study aims to establish a reliable prediction model returning the probability of pipe failure using a gradient boosted tree model, and a specific segmentation and grouping of pipes on a 1 km grid that associates localised characteristics. The model is applied to an extensive UK network with approximately 40,000 km of pipeline and a 14-year failure history. The model was evaluated using the Receiver Operator Curve and Area Under the Curve (0.89), briers score (0.007) and Mathews Correlation Coefficient (0.27) for accuracy, indicating acceptable predictions. A weighted risk analysis is used to identify the consequence of a pipe failure and provide a graphical representation of high-risk pipes for decision makers. The weighted risk analysis provided an important step to understanding the consequences of the predicted failure. The model can be used directly in strategic planning, which sets long-term key decisions regarding maintenance and potential replacement of pipes.
  • Thumbnail Image
    ItemOpen Access
    Strategic flood impact mitigation in developing countries’ urban road networks: application to Hanoi
    (Elsevier, 2024-12-16) Phouratsamay, Siao-Leu; Scaparra, Maria Paola; Tran, Trung Hieu; Laporte, Gilbert
    Due to climate change, the frequency and scale of flood events worldwide are increasing dramatically. Flood impacts are especially acute in developing countries, where they often revert years of progress in sustainable development and poverty reduction. This paper introduces an optimization-based decision support tool for selecting cost-efficient flood mitigation investments in developing countries’ urban areas. The core of the tool is a scenario-based, multi-period, bi-objective Mixed Integer Linear Programming model which minimizes infrastructure damage and traffic congestion in urban road networks. The tool was developed in collaboration with Vietnamese stakeholders (e.g., local communities and government authorities), and integrates data and inputs from other disciplines, including social science, transport economics, climatology and hydrology. A metaheuristic, combining a Greedy Randomized Adaptive Search Procedure with a Variable Neighborhood Descent algorithm, is developed to solve large scale problem instances. An extensive computational campaign on randomly generated instances demonstrates the efficiency of the metaheuristic in solving realistic problems with hundreds of interdependent flood mitigation interventions. Finally, the applicability of the interdisciplinary approach is demonstrated on a real case study to generate a 20-year plan of mitigation investments for the urban area of Hanoi. Policy implications and impacts of the study are also discussed.
  • Thumbnail Image
    ItemOpen Access
    Toward baggage-free airport terminals: a case study of London City Airport
    (MDPI, 2021-12-26) Jiang, Yirui; Yang, Runjin; Zang, Chenxi; Wei, Zhiyuan; Thompson, John; Tran, Trung Hieu; Encinas-Oropesa, Adriana; Williams, Leon
    Nowadays, the aviation industry pays more attention to emission reduction toward the net-zero carbon goals. However, the volume of global passengers and baggage is exponentially increasing, which leads to challenges for sustainable airports. A baggage-free airport terminal is considered a potential solution in solving this issue. Removing the baggage operation away from the passenger terminals will reduce workload for airport operators and promote passengers to use public transport to airport terminals. As a result, it will bring a significant impact on energy and the environment, leading to a reduction of fuel consumption and mitigation of carbon emission. This paper studies a baggage collection network design problem using vehicle routing strategies and augmented reality for baggage-free airport terminals. We use a spreadsheet solver tool, based on the integration of the modified Clark and Wright savings heuristic and density-based clustering algorithm, for optimizing the location of logistic hubs and planning the vehicle routes for baggage collection. This tool is applied for the case study at London City Airport to analyze the impacts of the strategies on carbon emission quantitatively. The result indicates that the proposed baggage collection network can significantly reduce 290.10 tonnes of carbon emissions annually.