Search NASA⌕ Search

SEARCH · Search NASA

Results for “INJURIES”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

Temporal dynamics of the multi-omic response to endurance exercise training

Regular exercise promotes whole-body health and prevents disease, but the underlying molecular mechanisms are incompletely understood. Here, the Molecular Transducers of Physical Activity Consortium profiled the temporal transcriptome, proteome, metabolome, lipidome, phosphoproteome, acetylproteome, ubiquitylproteome, epigenome and immunome in whole blood, plasma and 18 solid tissues in male and female Rattus norvegicus over eight weeks of endurance exercise training. The resulting data compendium encompasses 9,466 assays across 19 tissues, 25 molecular platforms and 4 training time points. Thousands of shared and tissue-specific molecular alterations were identified, with sex differences found in multiple tissues. Temporal multi-omic and multi-tissue analyses revealed expansive biological insights into the adaptive responses to endurance training, including widespread regulation of immune, metabolic, stress response and mitochondrial pathways. Many changes were relevant to human health, including non-alcoholic fatty liver disease, inflammatory bowel disease, cardiovascular health and tissue injury and recovery. The data and analyses presented in this study will serve as valuable resources for understanding and exploring the multi-tissue molecular effects of endurance training and are provided in a public repository (https://motrpac-data.org/).

59 BASIC BIOLOGICAL SCIENCES↗

Tracking elemental changes in an ischemic stroke model with X-ray fluorescence imaging

Stroke is a leading cause of long-term disability in adults and a leading cause of death in developed nations. The cascade of cellular events and signalling that occur after cerebral ischemia are complex, however, analyzing global element markers of metabolic state affords the means to monitor stroke severity, status of injury, and recovery. These markers provide a multi-parameter method for assessing changes through the post-stroke time course. We employ synchrotron-based elemental mapping to follow elemental changes in the brain at 1 h, 1-, 2-, and 3-days, and at 1-, 2-, 3-, and 4-weeks post-stroke in a photothrombotic stroke model in mice. Our analysis reveals a highly consistent metabolic penumbra that can be readily identified based on the level of dysregulated potassium and other key elements. Maps of elemental distributions are also useful to demarcate events in the cellular response to the inflammatory cascade, including ion dysregulation, recruitment of cells to the lesion, and glial scar formation.

59 BASIC BIOLOGICAL SCIENCES↗

Radiation exposure induces cross-species temporal metabolic changes that are mitigated in mice by amifostine

Exposure to acute, damaging radiation may occur through a variety of events from cancer therapy and industrial accidents to terrorist attacks and military actions. Our understanding of how to protect individuals and mitigate the effects of radiation injury or Acute Radiation Syndrome (ARS) is still limited. There are only a few Food and Drug Administration-approved therapies for ARS; whereas, amifostine is limited to treating low dose (0.7–6 Gy) radiation poisoning arising from cancer radiotherapy. An early intervention is critical to treat ARS, which necessitates identifying diagnostic biomarkers to quickly characterize radiation exposure. Towards this end, a multiplatform metabolomics study was performed to comprehensively characterize the temporal changes in metabolite levels from mice and non-human primate serum samples following γ-irradiation. The metabolomic signature of amifostine was also evaluated in mice as a model for radioprotection. The NMR and mass spectrometry metabolomics analysis identified 23 dysregulated pathways resulting from the radiation exposure. These metabolomic alterations exhibited distinct trajectories within glucose metabolism, phospholipid biosynthesis, and nucleotide metabolism. A return to baseline levels with amifostine treatment occurred for these pathways within a week of radiation exposure. Together, our data suggests a unique physiological change that is independent of radiation dose or species. Furthermore, a metabolic signature of radioprotection was observed through the use of amifostine prophylaxis of ARS.

59 BASIC BIOLOGICAL SCIENCES↗

An image classification deep-learning algorithm for shrapnel detection from ultrasound images

Ultrasound imaging is essential for non-invasively diagnosing injuries where advanced diagnostics may not be possible. However, image interpretation remains a challenge as proper expertise may not be available. In response, artificial intelligence algorithms are being investigated to automate image analysis and diagnosis. Here, we highlight an image classification convolutional neural network for detecting shrapnel in ultrasound images. As an initial application, different shrapnel types and sizes were embedded first in a tissue mimicking phantom and then in swine thigh tissue. The algorithm architecture was optimized stepwise by minimizing validation loss and maximizing F1 score. The final algorithm design trained on tissue phantom image sets had an F1 score of 0.95 and an area under the ROC curve of 0.95. It maintained higher than a 90% accuracy for each of 8 shrapnel types. When trained only on swine image sets, the optimized algorithm format had even higher metrics: F1 and area under the ROC curve of 0.99. Overall, the algorithm developed resulted in strong classification accuracy for both the tissue phantom and animal tissue. This framework can be applied to other trauma relevant imaging applications such as internal bleeding to further simplify trauma medicine when resources and image interpretation are scarce.

59 BASIC BIOLOGICAL SCIENCES↗

Methods to capture proteomic and metabolomic signatures from cerebrospinal fluid and serum of healthy individuals

Discovery of reliable signatures for the empirical diagnosis of neurological diseases—both infectious and non-infectious—remains unrealized. One of the primary challenges encountered in such studies is the lack of a comprehensive database representative of a signature background that exists in healthy individuals, and against which an aberrant event can be assessed. For neurological insults and injuries, it is important to understand the normal profile in the neuronal (cerebrospinal fluid) and systemic fluids (e.g., blood). Here, we present the first comparative multi-omic human database of signatures derived from a population of 30 individuals (15 males, 15 females, 23–74 years) of serum and cerebrospinal fluid. In addition to empirical signatures, we also assigned common pathways between serum and CSF. Together, our findings provide a cohort against which aberrant signature profiles in individuals with neurological injuries/disease can be assessed—providing a pathway for comprehensive diagnostics and therapeutics discovery.

59 BASIC BIOLOGICAL SCIENCES↗

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗

Polyester functional graphenic materials as a mechanically enhanced scaffold for tissue regeneration

Traditional metal implants such as titanium, cobalt, and chromium have found wide utility in medicine; however, these come with a risk of toxicity. To overcome metal-related toxicity and enable degradability, polyesters including polycaprolactone (PCL), polylactic acid (PLA), and polyglycolic acid (PGA) show promise for the replacement of various biomedical applications of metals due to their accepted biocompatibility and FDA approval. However, polyesters are less stiff than their metallic counterparts, limiting their application to non-load bearing injury sites, such as fixation hardware for fingers. To improve mechanical properties, graphene oxide (GO)-polyester composites are a promising class of biodegradable scaffolds. Initial reports of these composites are encouraging, but mechanical properties still fall short. Traditional composites rely on non-covalent association between GO and the polyesters, which often leads to failure at the interface and weakens the overall strength of the material. Herein, we present a strategy for attachment of these FDA-approved polyesters onto a derivative of GO using a robust covalent bond. By covalently functionalizing the graphenic backbone with polyesters and without metal catalysts, we create functional graphenic materials (FGMs) to not only simultaneously retain biodegradability and compatibility, but also mechanically strengthen PCL, PLA, and PGA; we observed an average increase in the Young's modulus of over 140% compared to the graphenic backbone. These polyester-functionalized FGMs are a promising platform technology for tissue implants.

60 APPLIED LIFE SCIENCES↗

Prevalence of Self-Reported Bothersome Tinnitus in U.S. Army Soldiers From January 1, 2015, Through September 30, 2019

Purpose: Tinnitus is a symptom of auditory dysfunction or injury and can be a precursor to permanent hearing loss. Tinnitus can interfere with communication, sleep, concentration, and mood; when this occurs, it is referred to as bothersome tinnitus. Annual hearing surveillance in the U.S. Army includes screening for bothersome tinnitus. Estimating the prevalence of self-reported bothersome tinnitus can facilitate prioritization of prevention and education efforts. The objective of this study was to examine Army hearing conservation data to estimate the prevalence of self-reported bothersome tinnitus as a function of age, hearing, sex, service component, and pay grade. Method: The study employed a cross-sectional, retrospective design. Records from 1,485,059 U.S. Army Soldiers retrieved from the Defense Occupational and Environmental Health Readiness System–Hearing Conservation were analyzed. Descriptive statistics and multinomial logistic regression analysis were used to estimate the prevalence of bothersome tinnitus and its associations with Soldiers' demographic characteristics. Results: The estimated prevalence of self-reported bothersome tinnitus was 17.1% between January 1, 2015, and September 30, 2019; 13.6% of the Soldiers reported “bothered a little” and 3.5% reported “bothered a lot.” Proportionally, the prevalence of self-reported bothersome tinnitus was higher for males, older Soldiers, and Reserve Component Soldiers. For every 1-year increase in age, the odds of self-reporting “bothered a little” tinnitus relative to “bothered not at all tinnitus” would be expected to increase by 2.2% (2.1%, 2.3%), and the odds of self-reporting “bothered a lot” tinnitus relative to “bothered not at all” tinnitus would be expected to increase by 3.6% (3.5%, 3.7%). Conclusions: The self-reported prevalence of bothersome tinnitus in the U.S. Army (17.1%) is substantially higher than that of the general population, where prevalence of bothersome tinnitus is estimated at 6.6%. Examination of bothersome tinnitus among Soldiers is an important step toward optimizing prevention, education, and intervention efforts.

Audiology & Speech-Language Pathology↗

Connected Traffic Signal Coordination Optimization Framework through Network-Wide Adaptive Linear Quadratic Regulator–Based Control Strategy

Traffic congestion in metropolitan areas causes several significant challenges, such as longer travel times, decreased productivity, increased fuel consumption and vehicle emissions, and even severe injuries during crashes. Traffic signal control is a management approach to reduce traffic congestion and allocate the appropriate right of way for safety and mobility efficiency, both in temporal and spatial domains. Here, this study proposes a network-wide adaptive signal control coordination optimization framework based on the linear quadratic regulator algorithm. The traffic flow conditions driven by signal control inputs are formulated based on their network-wide state-space representation. After modeling traffic control regulation constraints, an adaptive linear quadratic regulator algorithm is designed to maximize the network-wide total throughput under the current conditions. Optimal signal control split time durations for multiple intersections in the network are derived by solving the algebraic Riccati equation. Furthermore, the recursive least square parameter estimation method is employed to quantify dynamic traffic condition changes. To verify the effectiveness of this proposed signal control framework, both simulation and real-world experimental tests are conducted for multiple intersections in downtown Chattanooga, Tennessee, United States. In preparation for real-world experimental tests, pipelines for real-time data processing implementation and historical traffic flow data analysis are conducted. The test results demonstrate that the proposed control framework achieves a decrease in travel time by up to 19.4%, total time spent (TTS) by up to 11.9%, and relative queue balance (RQB) by up to 15.6%. The research findings indicate that the proposed signal control framework can be generalized to handle large scale signal control optimization network-wide.

97 MATHEMATICS AND COMPUTING↗

Comparison of Different Variants of the U.S. Army Occupational Physical Assessment Test

The U.S. Army Occupational Physical Assessment Test (OPAT) is a pre-enlistment physical employment screening assessment developed to place recruits and soldiers into Military Occupational Specialties (MOSs) based on their physical capabilities in order to optimize performance and limit injury. The OPAT consists of the seated power throw (SPT), strength deadlift (SDL), standing long jump, and interval aerobic run. During the scientific validation of the OPAT, two variants of the SPT and two variants of the SDL were used. Although the OPAT was validated using both variants for each test, U.S. Army scientists and policymakers have received queries regarding how these variants compare to each other. Therefore, the purpose of this study was to compare different variants of the SPT and SDL. Thirty-two participants (14 male and 18 female) between the ages of 18 and 42 years visited the laboratory on one occasion and performed two variants of the SPT (seated on the ground [the current OPAT standard] versus seated in a chair with a 35 cm seat height) and two variants of the SDL (using a hex-bar [the current OPAT standard] versus using paired dumbbells). Testing order for the different variants was randomized. The protocol was approved by the U.S. Army Medical Research and Development Command Institutional Review Board. Performing the SPT from a chair significantly (P < .05) increased performance when compared to performing the SPT from the ground (5.4 ± 1.3 m versus 5.0 ± 1.4 m, respectively). Values for the two SPT variants were correlated (tau = 0.90). Performing the SDL using the hex-bar significantly increased the maximal weight lifted when compared to performing the SDL using paired dumbbells (86.9 ± 18.4 kg versus 83.1 ± 18.0 kg, respectively). Values for the two SDL variants were correlated (tau = 0.83). Performing different variants of the SPT and SDL influenced the resulting score. Although these findings do not alter the administration or scoring of the OPAT, they do provide a valuable reference in the event of future inquiries regarding the development of the OPAT.

General & Internal Medicine↗

Optimization of a Lethal, Combat-Relevant Model of Sterile Inflammation in Mice for Drug Candidate Screening

ABSTRACT Introduction Extensive trauma, commonly seen in wounded military Service Members, often leads to a severe sterile inflammation termed systemic inflammatory response syndrome (SIRS), which can progress to multiple organ dysfunction syndrome (MODS) and death. MODS is a serious threat to wounded Service Members, historically causing 10% of all deaths in trauma admissions at a forward deployed combat hospital. The importance of this problem will be exacerbated in large-scale combat operations, in which evacuation will be delayed and care of complex injuries at lower echelons of care may be prolonged. The main goal of this study was to optimize an existing mouse model of lethal SIRS/MODS as a therapeutic screening platform for the evaluation of immunomodulatory drugs. Materials and Methods Male C57BL/6 mice were euthanized, and the bones and muscles were collected and blended into a paste termed tissue–bone matrix (TBX). The TBX at 12.5%–20% relative to body weight of each recipient mouse was implanted into subcutaneous pouches created on the dorsum of anesthetized animals. Mice were observed for clinical scores for up to 48 hours postimplantation and euthanized at the preset point of moribundity. To test effects of anesthetics on TBX-induced mortality, animals received isoflurane or ketamine/xylazine (K/X). In a separate set of studies, mice received TBX followed by intraperitoneal injection with 20 mg/kg or 40 mg/kg Eritoran or a placebo carrier. All Eritoran studies were performed in a blinded fashion. Results We observed that K/X anesthesia significantly increased the lethality of the implanted TBX in comparison to inhaled anesthetics. Although all the mice anesthetized with isoflurane and implanted with 12.5% TBX survived for 24 hours, 60% of mice anesthetized with K/X were moribund by 24 hours postimplantation. To mimic more closely the timing of lethal SIRS/MODS following polytrauma in human patients, we extended observation to 48 hours. We performed TBX dose–response studies and found that as low as 15%, 17.5%, and 20% TBX caused moribundity/mortality in 50%, 80%, and 100% mice, respectively, over a 48-hour time period. With 17.5% TBX, we tested if moribundity/mortality could be rescued by anti-inflammatory drug Eritoran, a toll-like receptor 4 antagonist. Neither 20 mg/kg nor 40 mg/kg doses of Eritoran were found to be effective in this model. Conclusions We optimized a TBX mouse model of SIRS/MODS for the purpose of evaluating novel therapeutic interventions to prevent trauma-related pathophysiologies in wounded Service Members. Negative effects of K/X on lethality of TBX should be further evaluated, particularly in the light of widespread use of ketamine in treatment of pain. By mimicking muscle crush, bone fracture, and necrosis, the TBX model has pleiotropic effects on physiology and immunology that make it uniquely valuable as a screening tool for the evaluation of novel therapeutics against trauma-induced SIRS/MODS.

General & Internal Medicine↗

Seawater exposure causes hydraulic damage in dying Sitka-spruce trees

Sea-level rise is one of the most critical challenges facing coastal ecosystems under climate change. Observations of elevated tree mortality in global coastal forests are increasing, but the mechanism of salinity-stress induced tree mortality is currently unknown. We monitored progressive mortality and associated gas exchange and hydraulic shifts in Sitka-spruce (Picea sitchensis) trees located within a salinity gradient under an ecosystem-scale change of seawater exposure in Washington State, USA. Percentage of live foliated crown (PLFC) decreased and tree mortality increased with increasing soil salinity during the study period. A strong reduction in gas exchange and xylem hydraulic conductivity (Ks) occurred during tree death, with an increase of the percentage loss of xylem conductivity (PLC) and turgor loss point (ptlp). Hydraulic and osmotic shifts reflected that hydraulic function declined from seawater exposure and dying trees were unable to support osmotic adjustment. Constrained gas exchange was strongly related to hydraulic damage at both stem and leaf levels. Significant correlations between foliar sodium (Na+) concentration and gas exchange and key hydraulic parameters (Ks, PLC and ptlp ) suggest that cellular injury related to the toxic effects of ion accumulation impacted the physiology of these dying trees. This study provides evidence of toxic effects on cellular function that become manifest in all aspects of plant functioning, leading to unfavourable osmotic and hydraulic conditions.

Zhang, Hongxia↗

Adrenal Stress Hormone Regulation of Hepatic Homeostatic Function After an Acute Ozone Exposure in Wistar-Kyoto Male Rats

Ozone-induced lung injury, inflammation, and pulmonary/hypothalamus gene expression changes are diminished in adrenalectomized (AD) rats. Acute ozone exposure induces metabolic alterations concomitant with increases in epinephrine and corticosterone. We hypothesized that adrenal hormones are responsible for observed hepatic ozone effects, and in AD rats, these changes would be diminished. In total, 5–7 days after sham (SH) or AD surgeries, male Wistar-Kyoto rats were exposed to air or 0.8-ppm ozone for 4 h. Serum samples were analyzed for metabolites and liver for transcriptional changes immediately post-exposure. Ozone increased circulating triglycerides, cholesterol, free fatty-acids, and leptin in SH but not AD rats. Ozone-induced inhibition of glucose-mediated insulin release was absent in AD rats. Unlike diminution of ozone-induced hypothalamus and lung mRNA expression changes, AD in air-exposed rats (AD-air/SH-air) caused differential hepatic expression of ~1000 genes. Likewise, ozone in AD rats caused differential expression of ~1000 genes (AD-ozone/AD-air). Ozone-induced hepatic changes in SH rats reflected enrichment for pathways involving metabolic processes, including acetyl-CoA biosynthesis, TCA cycle, and sirtuins. Upstream predictor analysis identified similarity to responses produced by glucocorticoids and pathways involving forskolin. These changes were absent in AD rats exposed to ozone. However, ozone caused unique changes in AD liver mRNA reflecting activation of synaptogenesis, neurovascular coupling, neuroinflammation, and insulin signaling with inhibition of senescence pathways. In these rats, upstream predictor analysis identified numerous microRNAs likely involved in glucocorticoid insufficiency. These data demonstrate the critical role of adrenal stress hormones in ozone-induced hepatic homeostasis and necessitate further research elucidating their role in propagating environmentally driven diseases.

Toxicology↗

Irradiation of the kidneys causes pathologic remodeling in the nontargeted heart: A role for the immune system

Cardiac disease is a frequent and significant adverse event associated with radiotherapy for cancer. Identifying the underlying mechanism responsible for radiation injury to the heart will allow interventions to be developed. In the present study, we tested if local kidney irradiation results in remodeling of the shielded, nontargeted heart. One kidney, two kidneys, or the total body of male WAG and Dahl SS rats were irradiated with 10 Gy of X-rays. Local kidney irradiation resulted in systemic hypertension, increased BUN, infiltration of T lymphocytes, natural killer cells, and macrophages into the renal cortex and medulla, and renal fibrosis. Local irradiation of kidneys in WAG rats resulted in remodeling in the nontargeted heart after 120 days, manifested by perivascular fibrosis and increased interventricular septal thickness, but was not seen in Dahl SS rats due to a high baseline level of fibrosis in the sham-irradiated animals. Genetic depletion of T cells mitigated the nephropathy after local kidney irradiation, indicating a role for the immune system in mediating this outcome. Local kidney irradiation resulted in a cascade of pro-inflammatory cytokines and low-molecular weight metabolites into the circulation associated with transmission of signals resulting in pathologic remodeling in the nontargeted heart. A new model is proposed whereby radiation-induced cardiac remodeling in susceptible animals is indirect, with lower hemi body organs such as the kidney exporting factors into the circulation that cause remodeling outside of the irradiated field in the shielded, nontargeted heart. This nontargeted effect appears to be mediated, in part, by the immune system.

60 APPLIED LIFE SCIENCES↗

The Challenges of Troubleshooting

Troubleshooting work presents electrical and other workers with a challenging combination of physical hazards, working conditions, and time pressure, which can lead to unwanted outcomes if not carefully managed.Summaries of several incidents in which workers were injured or at risk of injury while performing troubleshooting work are presented, identifying organizational weaknesses and error precursors that contributed to each incident.The primary challenges include:Deranged equipment. Equipment that needs troubleshooting is not in a normal operating condition. Actions that are safe when the equipment is in a normal state may not be safe in the deranged state.Work planning and control. The steps taken in troubleshooting are most often determined by the results of the immediately previous diagnostic test, making effective work planning challenging.Multiple types of hazards. Most equipment will present a troubleshooting worker with several types of hazards, including hazardous energy as defined in 29 CFR 1910.147. Portions of the troubleshooting activity may be infeasible without these hazards present.Time pressure. Restoring operation of failed equipment often involves an explicit or implicit sense of urgency.Equipment design and construction. The physical construction of the equipment in large part will determine to which hazards troubleshooters may be exposed. It will also determine which hazards may be encountered while performing the servicing needed to restore the equipment or system to operation.There are effective methods for addressing each challenge, most of which require a combination of advance preparation and management commitment.

Mertz, David E.↗

Descriptor: Infrastructure Perception and Control: Multi-Sensor Object Tracking Dataset (IPC-MSOT)

Traffic intersections are crucial and challenging nodes in transportation networks where multiple lanes of vehicles and pedestrians converge. Traffic accidents often occur at traffic intersections, including a large proportion of traffic fatalities and about one-half of all traffic injuries in the United States. Object detection data were collected in 2024 across three intersections in Colorado Springs, CO, USA, over the course of multiple days and various times to induce a heterogeneous mix of traffic conditions and behaviors. The purpose of the data collection exercises was to learn various attributes about infrastructure sensors and to build a repository of high-resolution, object-level data that can be used for research and development (e.g., to develop multisensor data fusion algorithms). The Infrastructure Perception and Control:Multi-Sensor Object tracking (IPC-MSOT) dataset was collected as part of the U.S. Department of Transportation's Strengthening Mobility and Revolutionizing Transportation (SMART) project, where the city of Colorado Springs, Colorado, and the National Renewable Energy Laboratory collaborated to collect object-level trajectory data from road users using multiple types of infrastructure sensors deployed at different intersections. This dataset allows for testing of late-stage sensor fusion algorithms and their ability to ingest multimodal sensor data, and it can be utilized by traffic engineers to design and evaluate trajectory-based signal control strategies.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Solar/Photovoltaic DC Systems: Information for Electrical Workers and Firefighters

Solar photovoltaic (PV) systems are common and continue to gain popularity. This article helps electrical workers and firefighters understand basic operating principles and hazards of PV dc arrays. The effects of solar radiation and temperature on power output are discussed including; PV-module testing standards; methods for calculating the number of modules in a PV string; some National Electrical Code (NEC) guidelines that are aimed toward improving array safety; dc-array commissioning, periodic maintenance, and testing; arc-flash-hazard potential ways firefighters can work safely around PV arrays; potential risks posed by moonlight and other light sources; some unique dc-system hazards. We also present statistics on PV dc-array electrical incidents and injuries.

14 SOLAR ENERGY↗

Enhanced Machine-Learning Flow for Microwave-Sensing Systems for Contaminant Detection in Food

The presence of foreign bodies in packaged food is a serious concern for both fnal consumers (allergies, injuries, choking) and food manufacturers (reputation and economic losses). In particular, low-density plastics, glass and wood splinters are hard to detect even by the most advanced X-ray imagers. One solution is Machine-Learning-based Microwave Sensing (MLMWS): a non-invasive, contactless, and real-time method which uses a machine-learning (ML) classifer to analyze the scattered microwaves from the irradiated target object. In this paper, we want to extend our previous work about contaminant detection in cocoa-hazelnut spread jars by proposing an enhanced ML flow to increase the accuracy of the ML classifier. For the first time in this case study, we use a multi-class classifier, we train it with scattering parameters measured at multiple microwave frequencies, with a new pre-processing scaler, data augmentation, quantization-aware training and a pruning schedule. The results show a contaminant detection multi-class accuracy of 94.167% with a latency of 26 µs when targeting an AMD/Xilinx Kria K26 FPGA. Finally, we released our datasets publicly to OpenML.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗