17628 research outputs found
Sort by
Expressive Talking Avatars
Get PDFStylized avatars are common virtual representations used in VR to support interaction and communication between remote collaborators. However, explicit expressions are notoriously difficult to create, mainly because most current methods rely on geometric markers and features modeled for human faces, not stylized avatar faces. To cope with the challenge of emotional and expressive generating talking avatars, we build the Emotional Talking Avatar Dataset which is a talking-face video corpus featuring 6 different stylized characters talking with 7 different emotions. Together with the dataset, we also release an emotional talking avatar generation method which enables the manipulation of emotion. We validated the effectiveness of our dataset and our method in generating audio based puppetry examples, including comparisons to state-of-the-art techniques and a user study. Finally, various applications of this method are discussed in the context of animating avatars in VR
The interests, ideas, and institutions shaping public participation in local climate change governance in Ireland
Get PDFPublic participation in local governance is crucial for effective climate action and for ensuring that policies are designed in a way that respects the rights of communities. Policy developments and choices are shaped by the groups that participate, by the ideas that they hold, and by the institutions that enable and constrain their participation. This paper seeks to understand local climate change governance in Ireland by identifying the environmental interests and the ideas of the groups that participate, and by examining how they engage with institutionalised local policymaking processes and with the organisations that represent the officially recognised views of the country’s national environmental movement. An analysis of survey data collected from the groups that are members of one of Ireland’s Public Participation Networks shows that a majority of groups are small, rural, voluntary, interested in a wide variety of environmental issues and have a pro-ecological worldview. Most groups follow a pro-institutional advocacy strategy at the local level, while only a minority interact with the national environmental movement, mostly limiting their engagement to the acquisition of information. This paper contributes to the literature that examines how interests, ideas, and institutions shape public participation in local climate politics
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Get PDFRecent years have seen a tremendous growth in Artificial Intelligence (AI)-based methodological development in a broad range of domains. In this rapidly evolving field, large number of methods are being reported using machine learning (ML) and Deep Learning (DL) models. Majority of these models are inherently complex and lacks explanations of the decision making process causing these models to be termed as 'Black-Box'. One of the major bottlenecks to adopt such models in mission-critical application domains, such as banking, e-commerce, healthcare, and public services and safety, is the difficulty in interpreting them. Due to the rapid proleferation of these AI models, explaining their learning and decision making process are getting harder which require transparency and easy predictability. Aiming to collate the current state-of-the-art in interpreting the black-box models, this study provides a comprehensive analysis of the explainable AI (XAI) models. To reduce false negative and false positive outcomes of these back-box models, finding flaws in them is still difficult and inefficient. In this paper, the development of XAI is reviewed meticulously through careful selection and analysis of the current state-of-the-art of XAI research. It also provides a comprehensive and in-depth evaluation of the XAI frameworks and their efficacy to serve as a starting point of XAI for applied and theoretical researchers. Towards the end, it highlights emerging and critical issues pertaining to XAI research to showcase major, model-specific trends for better explanation, enhanced transparency, and improved prediction accuracy
Deep learning methods for early detection of Alzheimer’s disease using structural MR images: A survey
Get PDFIn this paper, we present an extensive review of the most recent works for Alzheimer’s disease (AD) prediction, particularly Moderate Cognitive Impairment (MCI) conversion prediction. We aimed to identify the most useful brain-magnetic resonance imaging (MRI) biomarkers as well as the most successful deep learning frameworks used for prediction. To achieve this, we analysed more than 130 works and 7 review articles. A closer look revealed that the hippocampus is an important region of interest (ROI) is affected early by AD and that many related features help detect the disease in its early stages. However, considered alone, this ROI is not sufficient enough to ensure high prediction performance. Therefore, many other brain regions can also provide additional information to improve prediction accuracy. In relation to state-of-the-art deep neural networks, the U-Net represents the most efficient architecture for hippocampus segmentation. The best Dice Similarity Coefficient (DSC) value, equal to 94%, was achieved by the RESU-Net architecture. The best results for MCI conversion prediction were obtained for two models that identify significant landmarks from the whole brain for classification. The multi-stream convolutional neural network achieved the best AUC and specificity of 94.39% and 99.70%, respectively. Finally, a region ensemble model delivered the best accuracy of 85.90%, demonstrating the need for further research to address this challenging problem
British Sign Language Detection Using Ultra-Wideband Radar Sensing and Residual Neural Network
No full textThis study represents a significant advancement in Sign Language Detection (SLD), a crucial tool for enhancing communication and fostering inclusivity among the hearing-impaired community. It innovatively combines radar technology with deep learning techniques to develop a sophisticated, non-invasive SLD system. Traditional SLD methods often rely on cumbersome wearable devices or struggle with environmental inconsistencies. In contrast, this system utilizes the distinctive ability of radar to function effectively across various lighting conditions. The core of this research lies in its application to British Sign Language (BSL) detection, employing advanced neural network architectures for real-time interpretation. A key highlight is the impressive 92% accuracy rate achieved in BSL recognition, utilizing the Residual Neural Network (ResNet) model. This success is attributed to a comprehensive dataset and the strategic adaptation of ResNet for processing radar data. The fusion of radar technology with deep learning in this context not only marks a novel approach in the field but also establishes this research as a foundational contribution to the realm of SLD. Its implications extend beyond technical achievement, offering a more accessible and inclusive communication alternative for the hearing-impaired
The retailer perspective on the potential for using urban consolidation centres (UCCs)
Get PDFThis paper examines the role of supportive policies and value-added services which may incentivise retailers to use an urban consolidation centre (UCC). The methodology is a case study of the city of Edinburgh, Scotland, based on semi-structured interviews with 30 retailers. Results show that retailers are generally not positive towards using UCCs, and the services that they need are already being provided by their existing logistics service providers (LSPs). Nevertheless, if they were forced by restrictions and rising costs to use a UCC, they would be prepared to do so. In that case, they would want those services currently provided by LSPs to be provided by the UCC and would be prepared to pay for them. For a successful transfer to a UCC model, the retailer, LSP and UCC would need to work together to avoid loss of revenue to the LSP
Very Accurate Time-Frequency Representation of Induction Motors Harmonics for Fault Diagnosis Under Load Variations
Get PDFInduction motors work under steady-state in many applications. Nevertheless, in some cases they experience periodic load fluctuations, which generate constant frequency harmonics close to variable frequency bar breakage harmonics. In these cases, time-frequency (t-f) transforms are better suited than steady-state analysis since the fault harmonic frequencies change in time. Even if the healthy and faulty frequencies do not overlap in the spectrum, if the speed is unknown, it is difficult to distinguish the constant frequency healthy harmonic from the variable frequency bar breakage harmonic. On the other hand, transient techniques present in technical literature are not precise enough to deal with both the changing frequency of the bar breakage harmonic and a close constant frequency (as the one generated by most of the periodic load fluctuations). To achieve reliable results under these challenging situations, a very precise time-frequency transform must be used, enabling to simultaneously draw the constant and variable frequencies, even if they are very close in the t-f plane. The Dragon-Transform is here proposed to address the problem. It is shown through simulation and experimental results, how it enables to very accurately plot up to five faulty harmonics evolutions, distinguishing at the same time the constant frequency of the load oscillation, traced as a very thin horizontal line. Precision is so high that even the oscillations caused by ripple effect can be observed for the first time in technical literature, enhancing the reliability of the diagnosis performed, and opening the path for a true solution of the problem
Solar Wall Technology and Its Impact on Building Performance
Get PDFSolar walls provide transformative solutions by harnessing solar energy to generate electricity, improve thermal comfort, and reduce energy consumption and emissions, contributing to zero-energy buildings and mitigating climate change. In hot and humid regions, solar walls can reduce indoor temperatures by 30% to 50%, significantly improving energy efficiency. Optimizing the performance of solar walls includes factors such as glazing, shading, solar orientation, ventilation, and catalytic techniques, allowing them to be adapted to different climates. Innovative solar wall variants that include photovoltaic panels, water storage, and phase-change materials offer multifunctionality and sustainability in building design and are in line with global energy efficiency and environmentally conscious goals. In addition, innovative solar wall variants that combine photovoltaic panels, water storage, and phase-change materials promise even more sustainability in building design. These multifunctional solar wall systems can efficiently heat, cool, and generate energy, further reducing a building’s environmental impact. Solar walls have the potential to significantly reduce heating energy consumption; align with global goals for energy-efficient, environmentally conscious, and climate-responsive building design; and offer dynamic and adaptable solutions for sustainable architecture
SkipGateNet: A Lightweight CNN-LSTM Hybrid Model with Learnable Skip Connections for Efficient Botnet Attack Detection in IoT
Get PDFThe rise of Internet of Things (IoT) has led to increased security risks, particularly from botnet attacks that exploit IoT device vulnerabilities. This situation necessitates effective Intrusion Detection Systems (IDS), that are accurate, lightweight, and fast (having less inference time), designed particularly to detect botnet attacks in resource constrained IoT devices. This paper proposes SkipGateNet, a novel deep learning model designed for detecting Mirai and Bashlite botnet attacks in resource constrained IoT and fog computing environments. SkipGateNet is a lightweight, fast model combining 1D-Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) layers. The novelty of this model lies in the integration of ‘Learnable Skip Connections’. These connections feature gating mechanisms that enhance detection by focusing on relevant features and ignoring irrelevant ones. They add adaptability to the architecture, performing feature selection and propagating only essential features to deeper layers. Tested on the N-BaIoT dataset, SkipGateNet efficiently detects ten types of botnet attacks, with a remarkable test accuracy of 99.91%. It is also compact (2596.87 KB) and demonstrates a quick inference time of 8.0 milliseconds, suitable for real-time implementation in resource-limited settings. While evaluating its performance, parameters like precision, recall, accuracy, and F1 score were considered, along with statistical reliability measures like Cohen’s Kappa Coefficient and Matthews Correlation Coefficient. These highlight its reliability and effectiveness in IoT security challenges. The paper also compares SkipGateNet to existing models and four other deep learning architectures, including two sequential CNN architectures, a simple CNN+LSTM architecture, and a CNN+LSTM with standard skip connections. SkipGateNet surpasses all in accuracy and inference time, demonstrating its superiority in addressing IoT security issues
Implementing Virtualization on Single-Board Computers: A Case Study on Edge Computing
Get PDFThe widespread adoption of cloud computing has resulted in centralized datacenter structures; however, there is a requirement for smaller-scale distributed infrastructures to meet the demands for speed, responsiveness, and security for critical applications. Single-Board Computers (SBCs) present numerous advantages such as low power consumption, low cost, minimal heat emission, and high processing power, making them suitable for applications such as the Internet of Things (IoT), experimentation, and other advanced projects. This paper investigates the possibility of adopting virtualization technology on Single-Board Computers (SBCs) for the implementation of reliable and cost-efficient edge-computing environments.The results of this study are based on experimental implementations and testing conducted in the course of a case study performed on the edge infrastructure of a financial organization, where workload migration was achieved from a traditional to an SBC-based edge infrastructure. The performance of the two infrastructures was studied and compared during this process, providing important insights into the power efficiency gains, resource utilization, and overall suitability for the organization’s operational needs
Data sources:
Access Repository Dashboard
Do you manage Repository@Napier? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!