Browsing by Author "Jiang, Yirui"

Now showing 1 - 8 of 8
  • 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
    Design innovation and user experience of sensory interactive experience in museum exhibition space
    (IOS Press, 2024-11-21) Ji, Yijing; Lin, Qianqian; Yin, Wenjuan; Han, Bing; Jiang, Yirui
    This research examines the influence of multi-sensory experiences on visitor engagement within museums in the United Kingdom, with particular emphasis on the roles of physical design elements, technological integration, and sensory stimuli. Utilizing a comprehensive literature review, along with observational studies and surveys across 12 specialized museums, this study identifies critical factors that enhance visitor interaction and satisfaction. The findings reveal that the incorporation of interactive and multi-sensory elements, such as augmented reality and tactile exhibits, significantly augments visitor engagement. This study highlights the evolving function of museums as dynamic educational platforms that amalgamate entertainment and learning. It underscores the imperative for future museum designs to adapt to the digital era and cater to the diverse expectations of visitors. The results suggest that a strategic integration of sensory experiences can transform museums into more inclusive and immersive environments, thereby enriching the educational and cultural experiences of their audiences.
  • 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
    DSDCLNet: Dual-Stream Encoder and Dual-Level Contrastive Learning Network for supervised multivariate time series classification
    (Elsevier, 2024-03-13) Liu, Min; Sheng, Hui; Zhang, Ningyi; Zhao, Panpan; Yi, Yugen; Jiang, Yirui; Dai, Jiangyan
    In recent years, deep learning approaches have shown remarkable advancements in multivariate time series classification (MTSC) tasks. However, the existing approaches primarily focus on capturing the long-term correlations of time series or identifying local key sequence fragments, inevitably neglecting the synergistic properties between global and local components. Additionally, most representation learning methods for MTSC rely on self-supervised learning, which limits their ability to fully exploit label information. Hence, this paper proposes a novel approach termed Dual-Stream Encoder and Dual-Level Contrastive Learning Network (DSDCLNet), which integrates a dual-stream encoder (DSE) and dual-level contrastive learning (DCL). First, to extract multiscale local-global features from multivariate time series data, we employ a DSE architecture comprising an attention-gated recurrent unit (AGRU) and a dual-layer multiscale convolutional neural network (DMSCNN). Specifically, DMSCNN consists of a series of multi-scale convolutional layers and a max pooling layer. Second, to maximize the utilization of label information, a new loss function is designed, which combines classification loss, instance-level contrastive loss, and temporal-level contrastive loss. Finally, experiments are conducted on the UEA datasets and the results demonstrate that DSDCLNet achieves the highest average accuracy of 0.77, outperforming traditional approaches, deep learning approaches, and self-supervised approaches on 30, 23, and 27 datasets, respectively.
  • 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
    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.