Behavioural Classification of Cattle Using Neck-Mounted Accelerometer-Equipped Collars.

Monitoring and classification of dairy cattle behaviours is essential for optimising milk yields. Early detection of illness, days before the critical conditions occur, together with automatic detection of the onset of oestrus cycles is crucial for obviating prolonged cattle treatments and improving the pregnancy rates. Accelerometer-based sensor systems are becoming increasingly popular, as they are automatically providing information about key cattle behaviours such as the level of restlessness and the time spent ruminating and eating, proxy measurements that indicate the onset of heat events and overall welfare, at an individual animal level. This paper reports on an approach to the development of algorithms that classify key cattle states based on a systematic dimensionality reduction process through two feature selection techniques. These are based on Mutual Information and Backward Feature Elimination and applied on knowledge-specific and generic time-series extracted from raw accelerometer data. The extracted features are then used to train classification models based on a Hidden Markov Model, Linear Discriminant Analysis and Partial Least Squares Discriminant Analysis. The proposed feature engineering methodology permits model deployment within the computing and memory restrictions imposed by operational settings. The models were based on measurement data from 18 steers, each animal equipped with an accelerometer-based neck-mounted collar and muzzle-mounted halter, the latter providing the truthing data. A total of 42 time-series features were initially extracted and the trade-off between model performance, computational complexity and memory footprint was explored. Results show that the classification model that best balances performance and computation complexity is based on Linear Discriminant Analysis using features selected through Backward Feature Elimination. The final model requires 1.83 ± 1.00 ms to perform feature extraction with 0.05 ± 0.01 ms for inference with an overall balanced accuracy of 0.83.

Utilising Flow Aggregation to Classify Benign Imitating Attacks.

Cyber-attacks continue to grow, both in terms of volume and sophistication. This is aided by an increase in available computational power, expanding attack surfaces, and advancements in the human understanding of how to make attacks undetectable. Unsurprisingly, machine learning is utilised to defend against these attacks. In many applications, the choice of features is more important than the choice of model. A range of studies have, with varying degrees of success, attempted to discriminate between benign traffic and well-known cyber-attacks. The features used in these studies are broadly similar and have demonstrated their effectiveness in situations where cyber-attacks do not imitate benign behaviour. To overcome this barrier, in this manuscript, we introduce new features based on a higher level of abstraction of network traffic. Specifically, we perform flow aggregation by grouping flows with similarities. This additional level of feature abstraction benefits from cumulative information, thus qualifying the models to classify cyber-attacks that mimic benign traffic. The performance of the new features is evaluated using the benchmark CICIDS2017 dataset, and the results demonstrate their validity and effectiveness. This novel proposal will improve the detection accuracy of cyber-attacks and also build towards a new direction of feature extraction for complex ones.

Classification of Cattle Behaviours Using Neck-Mounted Accelerometer-Equipped Collars and Convolutional Neural Networks.

Monitoring cattle behaviour is core to the early detection of health and welfare issues and to optimise the fertility of large herds. Accelerometer-based sensor systems that provide activity profiles are now used extensively on commercial farms and have evolved to identify behaviours such as the time spent ruminating and eating at an individual animal level. Acquiring this information at scale is central to informing on-farm management decisions. The paper presents the development of a Convolutional Neural Network (CNN) that classifies cattle behavioural states ('rumination', 'eating' and 'other') using data generated from neck-mounted accelerometer collars. During three farm trials in the United Kingdom (Easter Howgate Farm, Edinburgh, UK), 18 steers were monitored to provide raw acceleration measurements, with ground truth data provided by muzzle-mounted pressure sensor halters. A range of neural network architectures are explored and rigorous hyper-parameter searches are performed to optimise the network. The computational complexity and memory footprint of CNN models are not readily compatible with deployment on low-power processors which are both memory and energy constrained. Thus, progressive reductions of the CNN were executed with minimal loss of performance in order to address the practical implementation challenges, defining the trade-off between model performance versus computation complexity and memory footprint to permit deployment on micro-controller architectures. The proposed methodology achieves a compression of 14.30 compared to the unpruned architecture but is nevertheless able to accurately classify cattle behaviours with an overall F1 score of 0.82 for both FP32 and FP16 precision while achieving a reasonable battery lifetime in excess of 5.7 years.

A Review of Techniques for RSS-Based Radiometric Partial Discharge Localization.

The lifespan assessment and maintenance planning of high-voltage power systems requires condition monitoring of all the operational equipment in a specific area. Electrical insulation of electrical apparatuses is prone to failure due to high electrical stresses, and thus it is a critical aspect that needs to be monitored. The ageing process of the electrical insulation in high voltage equipment may accelerate due to the occurrence of partial discharge (PD) that may in turn lead to catastrophic failures if the related defects are left untreated at an initial stage. Therefore, there is a requirement to monitor the PD levels so that an unexpected breakdown of high-voltage equipment is avoided. There are several ways of detecting PD, such as acoustic detection, optical detection, chemical detection, and radiometric detection. This paper focuses on reviewing techniques based on radiometric detection of PD, and more specifically, using received signal strength (RSS) for the localization of faults. This paper explores the advantages and disadvantages of radiometric techniques and presents an overview of a radiometric PD detection technique that uses a transistor reset integrator (TRI)-based wireless sensor network (WSN).

Organocatalytic Access to a cis-Cyclopentyl-γ-amino Acid: An Intriguing Model of Selectivity and Formation of a Stable 10/12-Helix from the Corresponding γ/α-Peptide.

In this study, we have developed a highly enantioselective organocatalytic route to the (1S,2R)-2-(aminomethyl)cyclopentane-1-carboxylic acid monomer precursor, which has a cis-configuration between the C- and N-termini around the cyclopentane core. Kinetic measurements show that the product distribution changes over time due to epimerization of the C1 center. Computations suggest the cis-selectivity is a result of selective C-C bond formation, while subsequent steps appear to influence the selectivity at higher temperature. The resulting γ-amino acid residue was incorporated into a novel γ/α-peptide, which forms a well-ordered 10/12-helix with alternate H-bond directionality in spite of the smallest value of the ζ-angle yet observed for a helix of this type. This highly defined structure is also a result of the narrow range of potential ζ-angles in our monomer. In contrast, the larger range of potential ζ-values observed for the corresponding trans-system can be fulfilled by several competing helical structures.

Composite Laminate Delamination Detection Using Transient Thermal Conduction Profiles and Machine Learning Based Data Analysis.

Delaminations within aerospace composites are of particular concern, presenting within composite laminate structures without visible surface indications. Transmission based thermography techniques using contact temperature sensors and surface mounted heat sources are able to detect reductions in thermal conductivity and in turn impact damage and large disbonds can be detected. However delaminations between Carbon Fibre Reinforced Polymer (CFRP) plies are not immediately discoverable using the technique. The use of transient thermal conduction profiles induced from zonal heating of a CFRP laminate to ascertain inter-laminate differences has been demonstrated and the paper builds on this method further by investigating the impact of inter laminate inclusions, in the form of delaminations, to the transient thermal conduction profile of multi-ply bi-axial CFRP laminates. Results demonstrate that as the distance between centre of the heat source and delamination increase, whilst maintaining the delamination within the heated area, the resultant transient thermal conduction profile is measurably different to that of a homogeneous region at the same distance. The method utilises a supervised Support Vector Classification (SVC) algorithm to detect delaminations using temperature data from either the edge of the defect or the centre during a 140 s ramped heating period to 80 °C. An F1 score in the classification of delaminations or no delamination at an overall accuracy of over 99% in both training and with test data separate from the training process has been achieved using data points effected by transient thermal conduction due to structural dissipation at 56.25 mm.

Defect Detection in Aerospace Sandwich Composite Panels Using Conductive Thermography and Contact Sensors.

Sandwich panels consisting of two Carbon Fibre Reinforced Polymer (CFRP) outer skins and an aluminium honeycomb core are a common structure of surfaces on commercial aircraft due to the beneficial strength-weight ratio. Mechanical defects such as a crushed honeycomb core, dis-bonds and delaminations in the outer skins and in the core occur routinely under normal use and are repaired during aerospace Maintenance, Repair and Overhaul (MRO) processes. Current practices rely heavily on manual inspection where it is possible minor defects are not identified prior to primary repair and are only addressed after initial repairs intensify the defects due to thermal expansion during high temperature curing. This paper reports on the development and characterisation of a technique based on conductive thermography implemented using an array of single point temperature sensors mounted on one surface of the panel and the concomitant induced thermal profile generated by a thermal stimulus on the opposing surface to identify such defects. Defects are classified by analysing the differential conduction of thermal energy profiles across the surface of the panel. Results indicate that crushed core and impact damage are detectable using a stepped temperature profile of 80 ∘C The method is amenable to integration within the existing drying cycle stage and reduces the costs of executing the overall process in terms of time-to-repair and manual effort.

Non-Destructive Identification of Fibre Orientation in Multi-Ply Biaxial Laminates Using Contact Temperature Sensors.

Fibre orientation within composite structures dictates the material properties of the laminate once cured. The ability to accurately and automatically assess fibre orientation of composite parts is a significant enabler in the goal to optimise the established processes within aftermarket aerospace industries. Incorrect ply lay-up results in a structure with undesirable material properties and as such, has the potential to fail under safe working loads. Since it is necessary to assure structural integrity during re-manufacture and repair assessment, the paper demonstrates a novel method of readily and non-destructively determining fibre orientation throughout multi-ply Biaxial woven composite laminates using point temperature contact sensors and data analysis techniques. Once cured, only the outermost laminates are visible to assess orientation. The inspection method is conducted visually, with reference guides to allow for rapid adoption with minimum training, as well as harnessing established temperature sensors within the Maintenance Repair and Overhaul (MRO) environment. The system is amenable to integration within existing repair/re-manufacture processes without significant impact to process flow. The method is able to identify noisy samples with an accuracy, precision and recall of 0.9, and for synthetically created samples of double the cure ply thickness, a precision of 0.75, a recall of 0.7 and an accuracy of 0.87.

Automatic Annotation of Subsea Pipelines using Deep Learning.

Regulatory requirements for sub-sea oil and gas operators mandates the frequent inspection of pipeline assets to ensure that their degradation and damage are maintained at acceptable levels. The inspection process is usually sub-contracted to surveyors who utilize sub-sea Remotely Operated Vehicles (ROVs), launched from a surface vessel and piloted over the pipeline. ROVs capture data from various sensors/instruments which are subsequently reviewed and interpreted by human operators, creating a log of event annotations; a slow, labor-intensive and costly process. The paper presents an automatic image annotation framework that identifies/classifies key events of interest in the video footage viz. exposure, burial, field joints, anodes, and free spans. The reported methodology utilizes transfer learning with a Deep Convolutional Neural Network (ResNet-50), fine-tuned on real-life, representative data from challenging sub-sea environments with low lighting conditions, sand agitation, sea-life and vegetation. The network outputs are configured to perform multi-label image classifications for critical events. The annotation performance varies between 95.1% and 99.7% in terms of accuracy and 90.4% and 99.4% in terms of F1-Score depending on event type. The performance results are on a per-frame basis and corroborate the potential of the algorithm to be the foundation for an intelligent decision support framework that automates the annotation process. The solution can execute annotations in real-time and is significantly more cost-effective than human-only approaches.

A Review of Cyber-Ranges and Test-Beds: Current and Future Trends.

Cyber situational awareness has been proven to be of value in forming a comprehensive understanding of threats and vulnerabilities within organisations, as the degree of exposure is governed by the prevailing levels of cyber-hygiene and established processes. A more accurate assessment of the security provision informs on the most vulnerable environments that necessitate more diligent management. The rapid proliferation in the automation of cyber-attacks is reducing the gap between information and operational technologies and the need to review the current levels of robustness against new sophisticated cyber-attacks, trends, technologies and mitigation countermeasures has become pressing. A deeper characterisation is also the basis with which to predict future vulnerabilities in turn guiding the most appropriate deployment technologies. Thus, refreshing established practices and the scope of the training to support the decision making of users and operators. The foundation of the training provision is the use of Cyber-Ranges (CRs) and Test-Beds (TBs), platforms/tools that help inculcate a deeper understanding of the evolution of an attack and the methodology to deploy the most impactful countermeasures to arrest breaches. In this paper, an evaluation of documented CR and TB platforms is evaluated. CRs and TBs are segmented by type, technology, threat scenarios, applications and the scope of attainable training. To enrich the analysis of documented CR and TB research and cap the study, a taxonomy is developed to provide a broader comprehension of the future of CRs and TBs. The taxonomy elaborates on the CRs/TBs dimensions, as well as, highlighting a diminishing differentiation between application areas.

Validation of an analytical method to quantify the permeation and penetration of flurbiprofen into human pharynx tissue.

The aim of this investigation was to develop receiver and extraction fluids, and subsequently validate an analytical method to quantify the permeation and penetration of flurbiprofen into human pharynx tissue using a Franz diffusion cell. The solubility and stability of flurbiprofen in a suitable receiver fluid, and a suitable extraction method and fluid to recover and quantitate flurbiprofen from human pharynx tissue, were investigated using high-performance liquid chromatography (HPLC). The potential interference of human pharynx tissue in the receiver fluid was also investigated. The HPLC analytical method was successfully validated according to current guidelines. The final receiver fluid demonstrated sufficient solubility and stability, and the extraction method and fluid resulted in >95% recovery of flurbiprofen following exposure to human pharynx tissue. The lower limit of quantitation of flurbiprofen was 0.045 µg/mL in both the receiver and extraction fluids. There was no interference of the human pharynx tissue with the HPLC method. This investigation validated an analytical method for quantitating flurbiprofen, and determined a suitable receiver fluid and extraction method and fluid, which can be used to investigate the permeation and penetration of flurbiprofen through human pharynx tissue using the Franz diffusion cell method.

An Efficient Algorithm for Partial Discharge Localization in High-Voltage Systems Using Received Signal Strength.

The term partial discharge (PD) refers to a partial bridging of insulating material between electrodes that sustain an electric field in high-voltage (HV) systems. Long-term PD activity can lead to catastrophic failures of HV systems resulting in economic, energy and even human life losses. Such failures and losses can be avoided by continuously monitoring PD activity. Existing techniques used for PD localization including time of arrival (TOA) and time difference of arrival (TDOA), are complicated and expensive because they require time synchronization. In this paper, a novel received signal strength (RSS) based localization algorithm is proposed. The reason that RSS is favoured in this research is that it does not require clock synchronization and it only requires the energy of the received signal rather than the PD pulse itself. A comparison was made between RSS based algorithms including a proposed algorithm, the ratio and search and the least squares algorithm to locate a PD source for nine different positions. The performance of the algorithms was evaluated by using two field scenarios based on seven and eight receiving nodes, respectively. The mean localization error calculated for two-field-trial scenarios show, respectively, 1.80 m and 1.76 m for the proposed algorithm for all nine positions, which is the lowest of the three algorithms.

Evaluation of RPE-Select: A Web-Based Respiratory Protective Equipment Selector Tool.

This article describes the evaluation of an open-access web-based respiratory protective equipment selector tool (RPE-Select, accessible at http://www.healthyworkinglives.com/rpe-selector). This tool is based on the principles of the COSHH-Essentials (C-E) control banding (CB) tool, which was developed for the exposure risk management of hazardous chemicals in the workplace by small and medium sized enterprises (SMEs) and general practice H&S professionals. RPE-Select can be used for identifying adequate and suitable RPE for dusts, fibres, mist (solvent, water, and oil based), sprays, volatile solids, fumes, gases, vapours, and actual or potential oxygen deficiency. It can be applied for substances and products with safety data sheets as well as for a large number of commonly encountered process-generated substances (PGS), such as poultry house dusts or welding fume. Potential international usability has been built-in by using the Hazard Statements developed for the Globally Harmonised System (GHS) and providing recommended RPE in picture form as well as with a written specification. Illustration helps to compensate for the variabilities in assigned protection factors across the world. RPE-Select uses easily understandable descriptions/explanations and an interactive stepwise flow for providing input/answers at each step. The output of the selection process is a report summarising the user input data and a selection of RPE, including types of filters where applicable, from which the user can select the appropriate one for each wearer. In addition, each report includes 'Dos' and 'Don'ts' for the recommended RPE. RPE-Select outcomes, based on up to 20 hypothetical use scenarios, were evaluated in comparison with other available RPE selection processes and tools, and by 32 independent users with a broad range of familiarities with industrial use scenarios in general and respiratory protection in particular. For scenarios involving substances having safety data sheets, 87% of RPE-Select outcomes resulted in a 'safe' RPE selection, while 98% 'safe' outcomes were achieved for scenarios involving process-generated substances. Reasons for the outliers were examined. User comments and opinions on the mechanics and usability of RPE-Select are also presented.

Supracondylar process syndrome: case report and literature review.

The supracondylar process is a congenital bone projection on the distal anteromedial humerus often associated with a ligament of Struthers, a fibrous connection between the process and medial epicondyle. It is largely asymptomatic and only on rare occasions presents with neurovascular compression resulting in a supracondylar process syndrome. This case report describes a 28-year-old woman with supracondylar process syndrome, and our management. The topic is further explored with a literature review of 43 reported cases. Analysis of the case reports indicates that isolated median nerve injuries are the most common. Other presentations such as fractures, vascular compromise, and ulnar nerve involvement are less frequent.

Lithium Plating Characteristics in High Areal Capacity Li-Ion Battery Electrodes.

Li-ion battery degradation and safety events are often attributed to undesirable metallic lithium plating. Since their release, Li-ion battery electrodes have been made progressively thicker to provide a higher energy density. However, the propensity for plating in these thicker pairings is not well understood. Herein, we combine an experimental plating-prone condition with robust mesoscale modeling to examine electrode pairings with capacities ranging from 2.5 to 6 mAh/cm2 and negative to positive (N/P) electrode areal capacity ratio from 0.9 to 1.8 without the need for extensive aging tests. Using both experimentation and a mesoscale model, we identify a shift from conventional high state-of-charge (SOC) type plating to high overpotential (OP) type plating as electrode thickness increases. These two plating modes have distinct morphologies, identified by optical microscopy and electrochemical signatures. We demonstrate that under operating conditions where these plating modes converge, a high propensity of plating exists, revealing the importance of predicting and avoiding this overlap for a given electrode pairing. Further, we identify that thicker electrodes, beyond a capacity of 3 mAh/cm2 or thickness >75 µm, are prone to high OP, limiting negative electrode (NE) utilization and preventing cross-sectional oversizing the NE from mitigating plating. Here, it simply contributes to added mass and volume. The experimental thermal gradient and mesoscale model either combined or independently provide techniques capable of probing performance and safety implications of mild changes to electrode design features.

Multi-Modal Convolutional Parameterisation Network for Guided Image Inverse Problems.

There are several image inverse tasks, such as inpainting or super-resolution, which can be solved using deep internal learning, a paradigm that involves employing deep neural networks to find a solution by learning from the sample itself rather than a dataset. For example, Deep Image Prior is a technique based on fitting a convolutional neural network to output the known parts of the image (such as non-inpainted regions or a low-resolution version of the image). However, this approach is not well adjusted for samples composed of multiple modalities. In some domains, such as satellite image processing, accommodating multi-modal representations could be beneficial or even essential. In this work, Multi-Modal Convolutional Parameterisation Network (MCPN) is proposed, where a convolutional neural network approximates shared information between multiple modes by combining a core shared network with modality-specific head networks. The results demonstrate that these approaches can significantly outperform the single-mode adoption of a convolutional parameterisation network on guided image inverse problems of inpainting and super-resolution.

Retinal cells derived from patients with DRAM2-dependent CORD21 dystrophy exhibit key lysosomal enzyme deficiency and lysosomal content accumulation.

Biallelic mutations in DRAM2 lead to an autosomal recessive cone-rod dystrophy known as CORD21, which typically presents between the third and sixth decades of life. Although DRAM2 localizes to the lysosomes of photoreceptor and retinal pigment epithelium (RPE) cells, its specific role in retinal degeneration has not been fully elucidated. In this study, we generated and characterized retinal organoids (ROs) and RPE cells from induced pluripotent stem cells (iPSCs) derived from two CORD21 patients. Our investigation revealed that CORD21-ROs and RPE cells exhibit abnormalities in lipid metabolism, defects in autophagic flux, accumulation of aberrant lysosomal content, and reduced lysosomal enzyme activity. We identified potential interactions of DRAM2 with vesicular trafficking proteins, suggesting its involvement in this cellular process. These findings collectively suggest that DRAM2 plays a crucial role in maintaining the integrity of photoreceptors and RPE cells by regulating lysosomal function, autophagy, and potentially vesicular trafficking.

Chronic social defeat stress induces meningeal neutrophilia via type I interferon signaling.

Animal models of stress and stress-related disorders are also associated with blood neutrophilia. The mechanistic relevance of this to symptoms or behavior is unclear. We used cytometry, immunohistochemistry, whole tissue clearing, and single-cell sequencing to characterize the meningeal immune response to chronic social defeat (CSD) stress in mice. We find that chronic, but not acute, stress causes meningeal neutrophil accumulation, and CSD increases neutrophil trafficking in vascular channels emanating from skull bone marrow (BM). Transcriptional analysis suggested CSD increases type I interferon (IFN-I) signaling in meningeal neutrophils. Blocking this pathway via the IFN-I receptor (IFNAR) protected against the anhedonic and anxiogenic effects of CSD stress, potentially through reduced infiltration of IFNAR+ neutrophils into the meninges from skull BM. Our identification of IFN-I signaling as a putative mediator of meningeal neutrophil recruitment may facilitate development of new therapies for stress-related disorders.

PRPF8-mediated dysregulation of hBrr2 helicase disrupts human spliceosome kinetics and 5´-splice-site selection causing tissue-specific defects.

The carboxy-terminus of the spliceosomal protein PRPF8, which regulates the RNA helicase Brr2, is a hotspot for mutations causing retinitis pigmentosa-type 13, with unclear role in human splicing and tissue-specificity mechanism. We used patient induced pluripotent stem cells-derived cells, carrying the heterozygous PRPF8 c.6926 A > C (p.H2309P) mutation to demonstrate retinal-specific endophenotypes comprising photoreceptor loss, apical-basal polarity and ciliary defects. Comprehensive molecular, transcriptomic, and proteomic analyses revealed a role of the PRPF8/Brr2 regulation in 5'-splice site (5'SS) selection by spliceosomes, for which disruption impaired alternative splicing and weak/suboptimal 5'SS selection, and enhanced cryptic splicing, predominantly in ciliary and retinal-specific transcripts. Altered splicing efficiency, nuclear speckles organisation, and PRPF8 interaction with U6 snRNA, caused accumulation of active spliceosomes and poly(A)+ mRNAs in unique splicing clusters located at the nuclear periphery of photoreceptors. Collectively these elucidate the role of PRPF8/Brr2 regulatory mechanisms in splicing and the molecular basis of retinal disease, informing therapeutic approaches.

FOOT INJURIES IN MICHIGAN, USA, GRAY WOLVES (CANIS LUPUS), 1992-2014.

The range of gray wolves (Canis lupus) in the contiguous US is expanding. Research and monitoring to support population recovery and management often involves capture via foothold traps. A population-level epidemiologic assessment of the effect of trap injuries on wolf survival remains needed to inform management. We describe the baseline rate, type, and severity of foot injuries of wolves born 1992-2013 in Michigan's Upper Peninsula, evaluate the reliability of field-scoring trap-related injuries, and the effect of injuries on wolf survival. We assessed foot injuries by physical and radiographic exam at postmortem and/or time of capture for 351 wolves using the International Organization for Standardization 10990-5 standard and the effects of injuries, sex, age, previous capture and body condition on survival using proportional hazards regression. We used ordinal regression to evaluate epidemiologic associations between sex, age, previous capture, body condition, cause of death and injury severity. Most wolves (53%) experienced no physically or radiographically discernable foot injuries over their lifetimes. Among those wolves that did experience injuries, 33% scored as mild. Foot injuries had little epidemiologically discernable effect on survival rates. Wolves with higher foot trauma scores did experience an increased risk of dying, but the magnitude of the increase was modest. Most limb injuries occurred below the carpus or tarsus, and scoring upper-limb injuries added little predictive information to population-level epidemiologic measures of survival and injury severity. There was little association between injury severity and cause of death. Based on necropsy exams, previous trap injuries likely contributed to death in only four wolves (1.1%). Our results suggest that injuries resulting from foothold traps are unlikely to be a limiting factor in recovery and ongoing survival of the Michigan gray wolf population.