A5009251304- Smart Agriculture and AI
- Animal Vocal Communication and Behavior
- Wildlife Ecology and Conservation
- Remote Sensing in Agriculture
- Plant responses to water stress
- Species Distribution and Climate Change
- Cassava research and cyanide
- Remote Sensing and LiDAR Applications
- Bat Biology and Ecology Studies
- Domain Adaptation and Few-Shot Learning
- Neural Networks and Applications
- Marine animal studies overview
- Fluid Dynamics and Mixing
- Plant Surface Properties and Treatments
- Plant nutrient uptake and metabolism
- Atmospheric and Environmental Gas Dynamics
- Fluid Dynamics and Heat Transfer
- Advanced Neural Network Applications
- Heat Transfer and Boiling Studies
- Machine Learning and Data Classification
- Drilling and Well Engineering
- COVID-19 diagnosis using AI
- Climate Change and Health Impacts
- Metabolomics and Mass Spectrometry Studies
- Multimodal Machine Learning Applications
University of Lincoln
2013-2024
University of Nottingham
2018-2019
The entrained droplet fraction (e) is an important quantity in annuar gas-liquid two-phase flows as it allows more precise calculation of the gas core density. This results accurate pressure drop pipes involving such flows. Accurate modelling which incorporates liquid crucial for appropriate design downstream oil and facilities predicting inception dry-out heat transfer applications boiling While experimentation correlations from experimental data are widely used closure relationships...
Root and tuber crops are becoming more important for their high source of carbohydrates, next to cereals. Despite commercial impact, there significant knowledge gaps about the environmental inherent regulation storage root (SR) differentiation, due in part innate problems studying roots lack a suitable model system monitoring growth. The research presented here aimed develop reliable, low-cost effective that enables study factors influencing cassava initiation development.We explored simple,...
Abstract There is an increase in consumption of agricultural produce as a result the rapidly growing human population, particularly developing nations. This has triggered high-quality plant phenotyping research to help with breeding high-yielding plants that can adapt our continuously changing climate. Novel, low-cost, fully automated systems, capable infield deployment, are required identify quantitative phenotypes. The identification phenotypes key challenge which relies heavily on precise...
Classifiers trained on disjointed classes with few labelled data points are used in one-shot learning to identify visual concepts from other classes. Recently, Siamese networks and similarity layers have been solve the problem, achieving state-of-the-art performance visual-character recognition datasets. Various techniques developed over years improve of these fine-grained image classification They focused primarily improving loss activation functions, augmenting features, employing...
Cassava roots are complex structures comprising several distinct types of root. The number and size the storage two potential phenotypic traits reflecting crop yield quality. Counting measuring cassava usually done manually, or semi-automatically by first segmenting root images. However, occlusion both fibrous makes process time-consuming error-prone. While Convolutional Neural Nets (CNNs) have shown performance above state-of-the art in many image processing analysis tasks, there currently...
The phenomenon of liquid droplet impingement on solid surfaces is particularly important in industrial applications related to spray coating, thermal spraying, inkjet printing, cooling, and powder generation industries. Atomized metal impact over where both stationary rotating surfaces, such as disks, can be used carefully control sizes. Furthermore, several other aspects, properties (especially its surface tension), falling height, roughness, wettability, play a vital role controlling...
Bird populations are an important bio-indicator; so collecting reliable data is useful for ecologists helping conserve and manage fragile ecosystems.However, existing manual monitoring methods labour-intensive, time-consuming, error-prone.The aim of our work to develop a system, capable automatically classifying individual bird species in flight from videos.This challenging, but appropriate use the field, since there often requirement identify flight, rather than when stationary.We present...
Abstract Climatic and atmospheric conditions impact mental health, including increased incidents of depression associated with air pollution. A growing body research considers time-bound ‘snap-shots’ climatic drivers health outcomes. Less is known about the likely effects future climate change on health. Research often inhibited by data scarcity, challenge synthesising across multiple geospatial temporal scales, under-representation hard-to-reach groups. Thus, methods are needed to integrate...
Recognising animals based on distinctive body patterns, such as stripes, spots, or other markings, in night images is a complex task computer vision. Existing methods for detecting often rely colour information, which not always available images, posing challenge pattern recognition conditions. Nevertheless, at night-time essential most wildlife, biodiversity, and conservation applications. The SPOTS-10 dataset was created to address this provide resource evaluating machine learning...