Processes that utilise low-value wastes and convert them to high-value food ingredients systemically add value across commercial operations. Current common disposal options include use as animal feed, anaerobic digestion, composting, incineration, and the worst-case options of landfill and wastewater disposal. The pressure is acute with food manufacturers needing to align with the UN Sustainable Development Goals and reach targets of zero waste to landfill. This research identifies black soldier fly larvae as a bioreactor that converts most food waste into high-value feed materials. Production of larvae and the regulatory framework for their use as animal feed is being assessed in several nations. The requirement to understand the availability of feedstocks for larvae production and the capability to establish feedstock supply chains was tested in this study using geographical information system and life cycle assessment methodologies, providing new research insights for resource utilisation in a circular economy.

There exist various types of information on retail food packages, including use by date, food product name and so on. The correct coding of use by dates on food packages is vitally important for avoiding potential health risks to customers caused by erroneous mislabelling of use by dates. It is extremely tedious and laborious to check the use by dates coding manually by a human operator, which is prone to generate errors thus an automatic system for validating the correctness of the coding of use by dates is needed. In order to construct such a system, firstly it needs to correctly automatic recognize use by dates on food packages. In this work, we propose a novel dual deep neural networks-based methodology for automatic recognition of use by dates in food package photographs recorded by a camera, which is a combination of two networks: a fully convolutional network for use by date ROI detection and a convolutional recurrent neuron network for date character recognition. The proposed methodology is the first attempt to apply deep learning for automatic use by date recognition. From comprehensive experimental evaluations, it is shown that the proposed method can achieve high accuracies in use by date recognition (more than 95% on our testing dataset), given food package images with varying lighting conditions, poor printing quality and varied textual/pictorial contents collected from multiple real retailer sites.

Supervised deep learning has been highly successful in recent years, achieving state-of-the-art results in most tasks. However, with the ongoing uptake of such methods in industrial applications, the requirement for large amounts of annotated data is often a challenge. In most real-world problems, manual annotation is practically intractable due to time/labour constraints; thus, the development of automated and adaptive data annotation systems is highly sought after. In this paper, we propose both a (1) deep Bayesian self-training methodology for automatic data annotation, by leveraging predictive uncertainty estimates using variational inference and modern neural network (NN) architectures, as well as (2) a practical adaptation procedure for handling high label variability between different dataset distributions through clustering of NN latent variable representations. An experimental study on both public and private datasets is presented illustrating the superior performance of the proposed approach over standard self-training baselines, highlighting the importance of predictive uncertainty estimates in safety-critical domains.

Bacteria have evolved to become proficient at adapting to both extracellular and environmental conditions, which has made it possible for them to attach and subsequently form biofilms on varying surfaces. This has resulted in major health concerns and economic burden in both hospital and industrial environments. Surfaces which prevent this bacterial fouling through their physical structure represent a key area of research for the development of antibacterial surfaces for many different environments. Laser surface treatment provides a potential candidate for the production of antibiofouling surfaces for wide ranging surface applications within healthcare and industrial disciplines. In the present study, a KrF 248 nm Excimer laser was utilized to surface pattern polyethylene terephthalate (PET). The surface topography and roughness were determined with the use of a Micromeasure 2, 3D profiler. Escherichia coli (E. coli) growth was analyzed at high shear flow using a CDC Biofilm reactor for 48 h, scanning electron microscopy was used to determine morphology and total viable counts were made. Through this work, it has been shown that the surface modification significantly influenced the distribution and morphology of the attached E. coli cells. What is more, it has been evidenced that the laser-modified PET has been shown to prevent E. coli cells from attaching themselves within the laser-induced micro-surface-features.