Convolutional neural networks (CNNs) exhibit excellent performance in hyperspectral image classification (HSIC) and have attracted significant interest. Nevertheless, the common CNN-based ...classification techniques still suffer from the following drawbacks. 1) Although deep CNNs can effectively extract features from hyperspectral images, a network that is too deep often leads to negative effects such as overfitting, vanishing gradients, and decreased accuracy. 2) Most of these models for HSIC do not fully consider the strong complementarity and correlation between features at different levels. To address these issues, firstly, a self-regularization parameter correction non-monotonic activation function, called Lush, was first proposed. Then, this study proposes a novel bias update method that can update network bias parameters more efficiently. On the basis of the above, a Lush multi-layer feature fusion polarization network (LMFFBNet) for hyperspectral image classification was proposed in this study. It designs a new after-melting technology to fuse deep and shallow features in multiple stages and layers, which can obtain more discriminative features, thereby improving the classification performance of hyperspectral images. Extensive experiments on five challenging datasets (Indian Pines, Pavia University, Kennedy Space Center, Salinas Valley, and Houston) have demonstrated that compared to some state-of-the-art methods, the proposed LMFFBNet method can provide better classification performance for hyperspectral images and has strong robustness. This fully proves the effectiveness of the LMFFBNet method.
Margaret Alison Lush Lush, Patrick St Lawrence
BMJ (Online),
03/2018, Volume:
360
Journal Article
Peer reviewed
Margaret Alison Lush (née Gee) followed her older siblings into medicine and entered King's College London in 1940.Margaret was an excellent gardener and used to open her garden to the public until ...she was in her 80s She leaves her husband, Brandon; two daughters; and a son.
Odorant-binding proteins (OBPs) have attracted considerable attention as sensing substrates for the development of olfactory biosensors. The Drosophila LUSH protein is an OBP and is known to bind to ...various alcohols. Technology that uses the LUSH protein has great potential to provide crucial information through odorant detection. In this work, the LUSH protein was used as a sensing substrate to detect the ethanol concentration. Furthermore, we fused the LUSH protein with a silicon-on-insulator (SOI)-based ion-sensitive field-effect transistor (ISFET) to measure the electrical signals that arise from molecular interactions between the LUSH and ethanol. A dual-gate sensing system for self-amplification of the signal resulting from the molecular interaction between the LUSH and ethanol was then used to achieve a much higher sensitivity than a conventional ISFET. In the end, we successfully detected ethanol at concentrations ranging between 0.001 and 1% using the LUSH OBP-fused ISFET olfactory sensor. The OBP-fused SOI-based olfactory ISFET sensor can lead to the development of handheld sensors for various purposes such as detecting toxic chemicals, narcotics control, testing for food freshness, and noninvasive diagnoses.
2018 Lush Science Prize McCann, Jenny; McCann, Terry
Alternatives to laboratory animals,
11/2020, Volume:
48, Issue:
1_suppl
Journal Article
Peer reviewed
The Lush Prize supports animal-free testing by awarding money prizes of up to £350,000 per year to the most effective projects and individuals who have been working towards the goal of replacing ...animals in product or ingredient safety testing. Since its inception in 2012, the Lush Prize has distributed almost £2 million. Prizes are awarded for developments in five strategic areas: Science; Lobbying; Training; Public Awareness; and Young Researchers. In 2015, the judges also awarded a Black Box prize for the development of the skin sensitisation Adverse Outcome Pathway and its associated in vitro assays. The Science Prize is awarded to researchers whose work the judging panel believe to have made the most significant contribution, in the preceding year, to the replacement of animal testing. This 2018 Science Background paper outlines the research projects that were presented to the Prize judges as potential candidates for the 2018 Lush Science Prize award. To obtain an overview of developments in the field of animal replacement in toxicity research, recent work by the relevant scientific institutions and projects in this area, including the OECD, CAAT, ECVAM, UK NC3Rs, US Tox21 Programme, the ToxCast programme and EU-ToxRisk, was reviewed. Recent developments in toxicity testing research were investigated by searching the relevant literature. Abstracts from conferences focusing on animal replacement in toxicity testing that were held in the preceding 12 months, were also analysed, including those from the 2017 10th World Congress on Alternatives and Animals in the Life Sciences and the 2018 Society of Toxicology annual conference.
Detection of food-borne bacteria present in the food products is critical to prevent the spread of infectious diseases. Intelligent quality sensors are being developed for detecting bacterial ...pathogens such as
Salmonella in beef. One of our research thrusts was to develop novel sensing materials sensitive to specific indicator alcohols at low concentrations. Present work focuses on developing olfactory sensors mimicking insect odorant binding protein to detect alcohols in low concentrations at room temperature. A quartz crystal microbalance (QCM) based sensor in conjunction with synthetic peptide was developed to detect volatile organic compounds indicative to
Salmonella contamination in packaged beef. The peptide sequence used as sensing materials was derived from the amino acids sequence of
Drosophila odorant binding protein, LUSH. The sensors were used to detect alcohols: 3-methyl-1-butanol and 1-hexanol. The sensors were sensitive to alcohols with estimated lower detection limits of <5
ppm. Thus, the LUSH-derived QCM sensors exhibited potential to detect alcohols at low ppm concentrations.