36057 research outputs found
Sort by
Masked convolutions within skip connections for video anomaly detection
No full textVideo anomaly detection plays a crucial role in various fields such as surveillance, health monitoring, and industrial quality control. This research paper introduces a novel contribution to the field by presenting MaskedConv3D layers within a modified UNet architecture. These MaskedConv3D layers provide a unique approach to information propagation in three-dimensional video data by selectively masking temporal regions of convolutional kernels. By incorporating these layers into the skip connections of the UNet, the model gains the ability to infer missing information in the temporal domain based on the surrounding context. This innovative mechanism enhances the preservation of spatial and temporal details, addressing the challenge of effectively detecting anomalies in video data. The proposed methodology is evaluated on popular video datasets, showcasing its effectiveness in capturing intricate patterns and contexts. The results highlight the superiority of the modified UNet with MaskedConv3D layers compared to traditional approaches. Overall, this research introduces a novel technique for information propagation in video data and demonstrates its potential for advancing video anomaly detection
Optimisation of bridge maintenance strategy and cost considering whole life costs and carbon emissions
No full textThis paper describes the optimisation of bridge maintenance strategy and cost, utilising a Structures Asset Valuation and Investment (SAVI) tool and considering whole life costs, traffic delays and carbon emissions arising from the bridge maintenance programme. Parametric studies were carried out with SAVI to compare maintenance costs and traffic delays for different maintenance strategies. Carbon emissions for each maintenance strategy were estimated using a popular carbon calculator tool and monetised, based on UK carbon valuations, before incorporating into the whole life costing of the bridge. The results demonstrate that a planned preventive maintenance strategy was the most cost effective and sustainable strategy with 7.7% lower discounted maintenance costs and 7% less carbon emission compared to an unplanned reactive maintenance strategy
Integrating thermal infrared and RGB imaging for early detection of water stress in lettuces with comparative analysis of IoT sensors
No full textEarly water stress detection is important for water use yield and sustainability. Traditional methods using the Internet of Things (IoT), such as soil moisture sensors, usually do not provide timely alerts, causing inefficient water use and, in some cases, crop damage. This research presents an innovative early water stress detection method in lettuce plants using Thermal Infrared (TIR) and RGB images in a controlled lab setting. The proposed method integrates advanced image processing techniques, including background elimination via Hue-Saturation-Value (HSV) thresholds, wavelet denoising for thermal image enhancement, RGB-TIR fusion using Principal Component Analysis (PCA), and Gaussian Mixture Model (GMM) clustering to segment stress regions. The leaves stressed areas annotated in the RGB image through yellow pseudo-coloring. This approach is predicated on the fact that when stomata close, transpiration decreases, which causes an increase in the temperature of the affected area. Experimental results reveal that this new approach can detect water stress up to 84 h earlier than conventional soil humidity sensors. Also, a comparative analysis was conducted where key components of the proposed hybrid framework were omitted. The results show inconsistent and inaccurate stress detection when excluding wavelet denoising and PCA fusion. A comparative analysis of image processing performed on a single-board computer (SBC) and through cloud computing over 5 G showed that SBC was 8.27% faster than cloud computing over a 5 G connection. The proposed method offers a more timely and accurate identification of water stress and promises significant benefits in improving crop yield and reducing water usage in indoor farming
Numerical modeling of pulsatile blood flow in the pulmonary artery under the influence of pulmonary hypertension and concomitant pathologies
No full textWriting, reading and teaching the (fr)agile/fragmented self : mapping life writing’s intimate geographies
No full textThe typical relation between a writing self that identifies as chronically ill, disabled, impacted by traumatic experience(s), or otherwise ‘fragile’ and the autobiographical writing that portrays that self has tended historically towards a mapping of the subject’s fragility and fragmentation. From academic autoethnographers to literary memoirists the works of such writers often comprise a chronicle of difficulties imposed by a condition or conditions seen and portrayed as a deficit. More recently, however, life stories and their readers have demonstrated a rising cultural interest in a range of skills ‘assets’ referred to by buzzwords like ‘agility’ and ‘resilience’. Such terminology and the attributes to which it attaches (self-reflection leading to positive growth and adaptation) have travelled from the spheres of psychology and self-help to those of education and business. This essay explores how a range of those self-declared ‘fragile’ life-writer-selves from Virginia Woolf to Joanne Limburg have mapped intimate geographies of both struggle and capacity-building. In so doing, they enable reflection on the often-generative dynamic between the fragile and the agile, the challenged, isolated self and the self who creates spaces of possibility, connection, and relation, open to the demands of the future
Deep learning for liver lesion segmentation and classification on staging CT scans of colorectal cancer patients : a multi-site technical validation study
No full textTrials and tribulations in perfecting student collaboration and teamwork
No full textCollaboration and teamwork are regarded as essential skills for students to develop in order to succeed in the modern workplace. They are ubiquitously listed as one of the key graduate attributes to develop and approaches to the development of teams are expected by Professional, Statutory, and Regulatory Bodies (PSRBs). However, perfecting, teaching, and assessing these skills giving weight and wider context can be challenging along with convincing students of their value. This presentation will explore a ten-year journey into the trials and tribulations in attempting to replicate and test many of the available examples to perfecting student collaboration and teamwork
Utopias – where do we go from here? Inspiring ideas for schools of tomorrow
No full textThere are many definitions of Utopia. This chapter aims to aid reflection on Utopias and the ‘Schools of Tomorrow.’ It does not intend to give any final definitions nor commit to one theoretical framework. Instead, it invites the reader to embark on a journey of theorising and co-creating Utopia in educational spaces, within learning and teaching, reflecting on past, future and existing educational practice, philosophy and theory. Considering individual values, unique human perspectives and contexts, the chapter starts an exploration of the authors’ belief in inclusive education and, presents the authors’ idea that there are as many Utopias as there are people in the World
