False Alarm Rate Research Articles

Comparison of Force, Neuromuscular, and Metabolic Responses During Sustained, Isometric Handgrip Holds to Failure Anchored to Low and High Perceptual Intensities in Men: An Exploratory Study.

Kwak, M, Succi, PJ, Benitez, B, Mitchinson, C, Samaan, MA, Abel, MG, and Bergstrom, HC. Comparison of force, neuromuscular, and metabolic responses during sustained, isometric handgrip holds to failure anchored to low and high perceptual intensities in men: An exploratory study. J Strength Cond Res 38(8): e405-e416, 2024-This study examined the responses of force alterations, relative to critical force (CF), neuromuscular parameters, and muscle oxygenation (SmO2) for isometric handgrip holds to failure (HTF) anchored to ratings of perceived exertion (RPE) of 3 and 7. Twelve men completed pre-maximal voluntary isometric contractions (pre-MVIC), submaximal HTF at 4 percentages of pre-MVIC, HTF at RPE = 3 and 7, and post-MVIC. Mechanomyograpic (MMG) signals and SmO2 were recorded during the RPE HTF. Analyses included paired-samples t-tests and repeated-measures ANOVAs at an alpha level of p ≤ 0.05. Time to task failure was not different between RPE 3 (478.7 ± 196.6 s) and RPE 7 (495.8 ± 173.8 s). Performance fatigability (PF) and MMG amplitude (AMP) were greater for RPE 7 (PF: 37.9 ± 12.9%; MMG AMP: 15.7 ± 7.4% MVIC) than RPE 3 (PF: 30.0 ± 14.5%; MMG AMP: 10.2 ± 6.5% MVIC), but MMG mean power frequency (MPF) was greater for RPE 3 (146.2 ± 31.1% MVIC) than RPE 7 (128.8 ± 23.0% MVIC). There were RPE-dependent decreases in force (p ≤ 0.01) across 3 discernable phases during the HTF. There were decreases in MMG AMP across time for both RPEs, but there were no significant changes in MMG MPF or SmO2. There were overall similar motor unit control strategies and local metabolic demand between RPEs. The majority of the HTF performed below CF at RPE 3 and 7 indicated CF did not reflect the highest sustainable force. When prescribing isometric exercise anchored to RPE, practitioners should be aware of the magnitude of force loss and relative intensity of the task to be sure desired training loads are met.

The Influence of Marketing Mix on Fruit Purchasing Decisions (Case Study: Hokky Buah Panglima Sudirman)

This study aims to analyze the effect of the 4P marketing mix (Product, Price, Promotion, Place) on fruit purchasing decisions at Hokky Panglima Sudirman Minimarket. This research is motivated by the high productivity of horticultural fruits, the lack of public interest in fruit consumption, and the intense competition faced by Hokky Buah Panglima Sudirman Minimarket. The research sample of 100 respondents was analyzed using the SEM-PLS method. The results showed that: Product, Price, and Promotion have a significant influence on Purchasing Decisions at the 5% Alpha level; Place has a significant influence on Purchasing Decisions at the 10% Alpha level. This research contributes to knowledge about the influence of the 4P marketing mix on fruit purchasing decisions at minimarkets. The results of this study can help Minimarket Hokky Panglima Sudirman in improving its marketing strategy to increase sales of fruit products.

HOME, SCHOOL AND STUDENTS’ CHARACTERISTICS AS PREDICTORS OF SENIOR SECONDARY SCHOOL STUDENTS’ ACHIEVEMENT IN MATHEMATICS

Students’ performance in mathematics in Nigeria in recent times is not at a desired level. Despite relentless efforts by stakeholders to improve on this situation, yet no significant change. Studies that looked into student’s variables combined with importance of mathematics, teacher, school, and parent variables to predict students’ achievement in mathematics, seem not to be in existence. Thus, empirical documentation of such is needful. This study assessed home, school and students’ characteristics as predictors of Senior Secondary School students’ achievement in Mathematics in Osun State. Expo-facto design of non-experimental type was used. Descriptive statistics and Multiple Regression were used to analyze data at 0.05 alpha level. Results reveal that parenting type, family size, teachers qualification, years of teaching, class size, interest in mathematics, student academic engagement, and importance of mathematics, jointly accounted for 11% of observed variance in achievement in Mathematics, and it is statistically significant, F(17,575) = 5.183; P < 0.05. Also, importance of mathematics, student engagement, teachers qualification, class size and teacher years of teaching, were found to have significant relative contribution towards students’ achievement in mathematics, and they could reliably predict achievement in mathematics.

Network Intrusion Detection Based on Deep Belief Network Broad Equalization Learning System

Network intrusion detection systems are an important defense technology to guarantee information security and protect a network from attacks. In recent years, the broad learning system has attracted much attention and has been introduced into intrusion detection systems with some success. However, since the traditional broad learning system is a simple linear structure, when dealing with imbalanced datasets, it often ignores the feature learning of minority class samples, leading to a poorer recognition rate of minority class samples. Secondly, the high dimensionality and redundant features in intrusion detection datasets also seriously affect the training time and detection performance of the traditional broad learning system. To address the above problems, we propose a deep belief network broad equalization learning system. The model fully learns the large-scale high-dimensional dataset via a deep belief network and represents it as an optimal low-dimensional dataset, and then introduces the equalization loss v2 reweighing idea into the broad learning system and learns to classify the low-dimensional dataset via a broad equalization learning system. The model was experimentally tested using the CICIDS2017 dataset and fully validated using the CICIDS2018 dataset. Compared with other algorithms in the same field, the model shortens the training time and has a high detection rate and a low false alarm rate.

Mastery Through Frequency: Embracing New Techniques and Strategies for Comprehensive Understanding in the Education Field

Previous observations in the English language learning domain revealed that traditional techniques to memorize vocabulary were insufficient for enhancing students’ vocabulary proficiency. This issue leads to an exploration of substitute learning strategies. This study aimed to determine the effectiveness of integrating English songs into language learning to enhance students’ vocabulary mastery.This study used a quantitative research methodology. The study involved 54 students divided into an experimental group and a control group, with 40 students ultimately participating. The control group adhered to the conventional learning procedure and denoted with variable Y, while the experimental group was exposed to English Songs and denoted with variable X. The mastery of vocabulary was assessed in relation to exposure to English songs. The study’s findings demonstrated a significant improvement in vocabulary mastery among the experimental group, with an average score of 82.25, compared to the control group score, which was 63.25. Statistical analysis confirmed the effectiveness of the intervention, with a p-value of 0.000, which is well below the threshold alpha level of 0.05. The incorporation of English songs into the vocabulary learning process not only significantly improved students’ vocabulary mastery but also raised their interest and engagement levels. This study supports the use of musical component as a beneficial teaching aid in language instruction as well as pleasurable learning experiences.

L-Carnitine Ameliorates Amiodarone-Mediated Alveolar Damage: Oxidative Stress Parameters, Inflammatory Markers, Histological and Ultrastructural Insights

The aim of this study was to assess L-carnitine’s effects on adult male rats’ lung damage brought on by amiodarone, which is a potent antiarrhythmic with limited clinical efficacy due to potentially life-threatening amiodarone-induced lung damage. Because of the resemblance among the structural abnormalities in rats’ lungs that follows amiodarone medication and pulmonary toxicity in human beings, this animal model may be an appropriate example for this disease entity. Amiodarone produced pulmonary toxicity in twenty-four healthy male albino rats (150–180 g) over a period of 6 weeks. Four groups of six rats each were established: control, sham, amiodarone, and L-carnitine plus amiodarone. Histological, ultrastructural, oxidative stress, and inflammatory markers were determined during a 6-week exposure experiment. Amiodarone-induced lung damage in rats may be brought on due to oxidative stress producing significant pulmonary cytotoxicity, as evidenced by the disruption of the mitochondrial structure, severe fibrosis, and inflammatory response of the lung tissue. Lungs already exposed to such harmful effects may be partially protected by the antioxidant L-carnitine. Biochemical markers of lung damage brought on by amiodarone include lung tissue levels of the enzyme’s catalase, superoxide dismutase, and reduced glutathione. The levels of lipid peroxides in lung tissue measured as malondialdehyde increased significantly upon exposure to amiodarone. In addition, the levels of tumor necrosis factor alpha were significantly elevated in response to amiodarone. The effect of L-carnitine on amiodarone-induced pulmonary toxicity was studied in rats. It is interesting to note that the intake of L-carnitine in rats treated with amiodarone partially restored the biochemical and histopathological alterations brought on by amiodarone to their original levels. Tumor necrosis factor alpha levels were significantly reduced upon L-carnitine exposure. These results suggest that L-carnitine can be used to treat amiodarone-induced pulmonary dysfunction.

Automated detection of tonic seizures using wearable movement sensor and artificial neural network.

Although several validated wearable devices are available for detection of generalized tonic-clonic seizures, automated detection of tonic seizures is still a challenge. In this phase 1 study, we report development and validation of an artificial neural network (ANN) model for automated detection of tonic seizures with visible clinical manifestation using a wearable wristband movement sensor (accelerometer and gyroscope). The dataset prospectively recorded for this study included 70 tonic seizures from 15 patients (seven males, age 3-46 years, median = 19 years). We trained an ANN model to detect tonic seizures. The independent test dataset comprised nocturnal recordings, including 10 tonic seizures from three patients and additional (distractor) data from three subjects without seizures. The ANN model detected nocturnal tonic seizures with visible clinical manifestation with a sensitivity of 100% (95% confidence interval = 69%-100%) and with an average false alarm rate of .16/night. The mean detection latency was 14.1 s (median = 10 s), with a maximum of 47 s. These data suggest that nocturnal tonic seizures can be reliably detected with movement sensors using ANN. Large-scale, multicenter prospective (phase 3) trials are needed to provide compelling evidence for the clinical utility of this device and detection algorithm.

Large-scale building damage assessment based on recurrent neural networks using SAR coherence time series: A case study of 2023 Turkey–Syria earthquake

The Turkey–Syria earthquakes that occurred on February 6, 2023, have caused significant human casualties and economic damage. Emergency services require quick and accurate assessments of widespread building damage in affected areas. This can be facilitated by using remote sensing methods, specifically all-day and all-weather Synthetic Aperture Radar (SAR). In this study, we aimed to improve the detection of building anomalies in earthquake-affected areas using SAR images. To achieve this, we employed Recurrent Neural Network (RNN) to train coherence time series and predict co-seismic coherence. This approach allowed us to generate a Damage Proxy Map (DPM) for building damage assessment. The results of our study indicated that the estimated proportion of building damage in Kahramanmaras was approximately 24.08%. These findings were consistent with the actual damage observed in the field. Moreover, when utilizing the mean and standard deviation of coherence time series, our method achieved higher accuracy (0.761) and a lower false alarm rate (0.136) compared to directly using coherence with only two views of SAR data. Overall, our study demonstrates that this method provides an accurate and reliable approach for post-earthquake building damage assessment.

Research on transformer fault diagnosis method based on ACGAN and CGWO-LSSVM

This paper proposes a transformer fault diagnosis method based on ACGAN and CGWO-LSSVM to address the problem of misjudgment and low diagnostic accuracy caused by the small number and uneven distribution of some fault samples in transformer fault diagnosis. Firstly, generate adversarial networks through auxiliary classification conditions, The ACGAN method expands a small and imbalanced number of samples to obtain balanced and expanded data; Secondly, the non coding ratio method is used to construct the characteristics of dissolved gases in oil, and kernel principal component analysis is used, KPCA method for feature fusion; Finally, using the improved cubic gray wolf optimization algorithm, CGWO for least square support vector machines, optimize the parameters of the LSSVM model and construct a transformer fault diagnosis model. The results show that the proposed method has a low false alarm rate and a diagnostic accuracy of 97.66%, compared to IGOA-LSSVM the IChOA-LSSVM and PSO-LSSVM methods improved accuracy by 0.12, 1.76, and 2.58%, respectively. This method has been proven to solve the problems of misjudgment and low diagnostic accuracy caused by small sample sizes and uneven distribution. It is suitable for multi classification fault diagnosis of transformer imbalanced datasets and is superior to other methods.

Near space detection technology combining van der Waals heterojunction photodetectors with long-range infrared target detection algorithms

To test the target detection accuracy of infrared detectors in practical applications, this study proposes a near space detection (NSD) technology that integrates van der Waals heterojunction photodetectors with long-range infrared target detection algorithms (ITDAs). A van der Waals heterojunction infrared photodetector (MoS2/CdTe) is prepared by combining molybdenum disulfide thin film and cadmium telluride substrate, and depositing gold electrodes on both substrates. A fusion algorithm of spatiotemporal target detection network and local contrast method is proposed for long-distance detection of weak infrared targets, and a near-space infrared detection system is designed. The data showed that the MoS2/CdTe heterojunction photodetector had a detection range of 200–1700 nm and a response of 36.7 mA/W, demonstrating excellent optoelectronic performance. The false alarm rates of the long-distance ITDA were 0.006% and 0.009%, respectively, which are significantly better than the target detection algorithm based on local contrast. In the testing of the near-space infrared detection system, the errors in the shortwave and longwave field of view tests were 2.5% and 5.2%, respectively, and the resolution test errors were 3.6% and 3.7%. The infrared detection system meets the performance standards, has high detection ability and stability, and provides a more effective solution for NSD.

Thresholding optimization of global navigation satellite system acquisition with constant false alarm rate detection using metaheuristic techniques

Thresholding optimization of global navigation satellite system acquisition with constant false alarm rate detection using metaheuristic techniques

IDS-DEC: A novel intrusion detection for CAN bus traffic based on deep embedded clustering

As the automotive industry advances towards greater automation, the proliferation of electronic control units (ECUs) has led to a substantial increase in the connectivity of in-vehicle networks with the external environment. However, the widely used Controller Area Network (CAN), which serves as the standard for in-vehicle networks, lacks robust security features, such as authentication or encrypted information transmission. This poses a significant challenge to the security of these networks. Despite the availability of powerful intrusion detection methods based on machine learning and deep learning, there are notable limitations in terms of stability and accuracy in the absence of a supervised learning process with labeled data. To address this issue, this paper introduces a novel in-vehicle intrusion detection system, termed IDS-DEC. This system combines a spatiotemporal self-coder employing LSTM and CNN (LCAE) with an entropy-based deep embedding clustering. Specifically, our approach involves encoding in-vehicle network traffic into windowed messages using a stream builder, designed to adapt to high-frequency traffic. These messages are then fed into the LCAE to extract a low-dimensional nonlinear spatiotemporal mapping from the initially high-dimensional data. The resulting low-dimensional mapping is subjected to a dual constraint in conjunction with our entropy-based pure deep embedding clustering module. This creates a bidirectional learning objective, addressing the optimization problem and facilitating an end-to-end training pattern for our model to adapt to diverse attack environments. The effectiveness of IDS-DEC is validated using both the benchmark Car Hacking dataset and the Car Hacking-Attack & Defense Challenge dataset. Experimental results demonstrate the model's high detection accuracy across various attacks, stabilizing at approximately 99% accuracy with a 0.5% false alarm rate. The F1 score also stabilizes at around 99%. In comparison with unsupervised methods based on deep stream clustering, LSTM-based self-encoder, and classification-based methods, IDS-DEC exhibits significant improvements across all performance metrics.

Insights from the first phylogenomic analysis of flat wasps (Hymenoptera, Bethylidae) reveal two new subfamilies.

Despite significant advances in alpha level taxonomy in the past few decades, the higher-level phylogeny of flat wasps (Hymenoptera, Bethylidae) remains poorly explored. Herein we provide the first phylogenomic assessment of the family based on data from ultraconserved elements for 96 species in 61 genera of the family, with material from 29 countries and all biogeographic regions. Dataset cutoffs including ultraconserved element loci recovered for 50 and 70% of terminals resulted in matrices with 1513 and 451 loci, which were analysed in both parsimony and maximum likelihood frameworks. We also provide the first analyses of divergence dating for the family based on the calibration of 12 nodes. All analyses recovered the Bethylidae as a monophyletic group and estimated the origin of the family at around 143 Ma. The results suggest that all extant subfamilies had already diversified by the Late Cretaceous. All topologies suggest that Glenosema and Chilepyris form a clade separate from other Scleroderminae; owing to the morphological distinctiveness of each genus, we propose that they are accommodated in two new subfamilies, Glenoseminae subf. nov. and Chilepyrinae subf. nov. The monotypic sclerodermine genus Galodoxa was consistently recovered within Epyrinae and is transferred to the latter subfamily.

GLDOC: detection of implicitly malicious MS-Office documents using graph convolutional networks

Nowadays, the malicious MS-Office document has already become one of the most effective attacking vectors in APT attacks. Though many protection mechanisms are provided, they have been proved easy to bypass, and the existed detection methods show poor performance when facing malicious documents with unknown vulnerabilities or with few malicious behaviors. In this paper, we first introduce the definition of im-documents, to describe those vulnerable documents which show implicitly malicious behaviors and escape most of public antivirus engines. Then we present GLDOC—a GCN based framework that is aimed at effectively detecting im-documents with dynamic analysis, and improving the possible blind spots of past detection methods. Besides the system call which is the only focus in most researches, we capture all dynamic behaviors in sandbox, take the process tree into consideration and reconstruct both of them into graphs. Using each line to learn each graph, GLDOC trains a 2-channel network as well as a classifier to formulate the malicious document detection problem into a graph learning and classification problem. Experiments show that GLDOC has a comprehensive balance of accuracy rate and false alarm rate − 95.33% and 4.33% respectively, outperforming other detection methods. When further testing in a simulated 5-day attacking scenario, our proposed framework still maintains a stable and high detection accuracy on the unknown vulnerabilities.

Mono-(2-ethylhexyl) phthalate induces trophoblast hypoxia and mitochondrial dysfunction through HIF-1α-miR-210-3p axis in HTR-8/SVneo cell line

The exposure to the ubiquitous phthalate metabolite mono-(2-ethylhexyl) phthalate (MEHP) is connected to dysregulated trophoblast function and placenta health; however, the underlying mechanisms preluding this scenario remain to be elucidated. In this study, we explored the hypoxemic effects of MEHP on a human placental first-trimester trophoblast cell line (HTR-8/Svneo). MEHP-treated trophoblast cells displayed significantly increased levels of oxidative stress and hypoxia-inducible factor-1 alpha (HIF-1α) attributed by the induction of hypoxia. Further, HIF-1α exhibited higher DNA binding activity and upregulated gene expression of its downstream target vascular endothelial growth factor A (VEGFA). The hypoxia-induced microRNA miR-210-3p was also significantly increased upon MEHP treatment followed by disrupted mitochondrial ATP generation and membrane potential. This was identified to possibly be facilitated by lowered mitochondrial DNA copy number and inhibited expression of electron transport chain subunits, such as mitochondrial complex-IV. These results suggest potential adverse effects of MEHP exposure in a trophoblast cell line mediated by HIF-1α and the epigenetic modulator miR-210-3p. Chronic placental hypoxia and oxidative stress have long been implicated in the pathogenesis of pregnancy complications such as preeclampsia. As we’ve revealed genetic and epigenetic factors underscoring a potential mechanism induced by MEHP, this brings to light another significant implication of phthalate exposure on maternal and fetal health.

A feature sample screening and local outlier factor fusion method for detecting tidal stream turbine blade impact fault

The impact fault caused by ocean creatures poses a risk to the safe operation of tidal stream turbine blades. However, it is difficult to detect the weak impact fault directly because the collected signal is disturbed by the waves, turbulence, and continuously variable flow velocity. To solve this problem, a fusion method of feature sample screening and local outlier factor is proposed in this paper. This method consists of three main parts. First, the Teager–Kaiser energy operator and the sliding window technique are introduced to extract the envelope statistical features from the current signal. Second, a parameter optimized density-based spatial clustering of applications with noise (DBSCAN) algorithm is proposed to perform feature sample screening before detecting. Notably, the conventional DBSCAN algorithm is sensitive to the parameter selection and lacks the capability of adaptive screening, so this paper proposes an adaptive sand cat swarm optimization algorithm to optimize the parameters. Finally, the local outlier factor is utilized to detect faults based on the screened feature samples. The experimental results show that the proposed method stands out in reducing the false alarm rate compared with traditional methods. Specifically, within the flow velocity ranges of 1.0–1.3 m/s and 1.3–1.6 m/s, the false alarm rates can reach 0% and 0.17%, respectively.

Simulation based Ecological Risk Assessment of the Black Sea Ecosystem

The article presents results of the conducted simulation research in ecological risk for three shelf areas of the Black Sea exposed to different combinations of the external stressors. Simulated risk calculations were performed for the aggregated phytoplankton taking into account the intra-annual variations in biomass values obtained from the observation data. The results revealed significant dependence of the ecological risk on the intra-annual state of phytoplankton, and also made it possible to calculate dependence of the acceptable probability of impacts on the ecological risk. The latter identified areas of probable errors of the second kind, which is of practical importance for ensuring ecological safety in the shelf resources development.

Impact of continuous Triazophos exposure on Labeo rohita: Physiological, biochemical, and histological alterations and IBRv2 index assessment

Pesticides are commonly used in agriculture and aquaculture. Triazophos, an organophosphate-based pesticide, is widely used in agriculture to control many insect pests. Due to its high photochemical stability and mode of action, Triazophos could persist in the aquatic ecosystem and cause toxic effects on non-target organisms. We have studied the potential toxic effects of Triazophos on L. rohita. Primarily, we determined the median lethal concentration (LC50) of Triazophos for 24 and 96 h. Next, we studied acute (96 h, LC50–96 h) toxicity. Then, we studied chronic (35 days, 1/10th LC50–96 h Treatment I: 0.522 mg/L, 1/5th LC50–96 h Treatment II: 1.044 mg/L) toxicity. We analyzed blood biomarkers such as hematology (Hb, Hct, RBC, WBC, MCV, MCH and MCHC), prolactin, cortisol, glucose and protein levels. Concurrently, we analyzed tissue biomarkers such as glycogen, GOT, GPT, LDH and histopathology. IBRv2 index assessment method was also to evaluate the Triazophos toxicity. Studied hematological, hormonal, biochemical and enzymological biomarkers were affected in Triazophos treated groups when compare to the control group. The changes in these biomarkers were statistically significant at the 0.05 alpha level. Triazophos exposed fish shown a severe degenerated primary and secondary lamellae, lamellar fusion, hypertrophy and telangiectasia in the gills. In the hepatic tissue, it caused moderate necrosis, blood congestion, distended sinusoids with minor vacuolation, prominent pyknotic nuclei, hypertrophy, cloudy swelling of cells, lipid accumulation and fibrotic spaces. In the renal tissue, Triazophos caused thickening of Bowman's capsule, hyaline droplets degeneration, irregular renal corpuscle, congestion, cellular swelling, degeneration of tubular epithelium, necrosis, shrunken glomerulus, vacuolated glomerulus, hypertrophy, exudate and edema. IBRv2 analysis suggested that tissue biomarkers are highly sensitive to Triazophos toxicity and prolonged exposure could cause serious health effects like acute toxicity in fish. Triazophos could cause multiorgan toxicity at studied concentrations.

Wavelet-modified segmented phase-only filter for in-plane rotated object recognition

In this paper, we propose and implement a wavelet-modified segmented phase-only filter for in-plane rotated object recognition. The wavelet filter is combined with the segmented phase-only filter to significantly enhance the correlation capability of the optical processor. To verify the consistency of the results, we have calculated the performance measure parameters such as peak-to-correlation energy, peak-to-sidelobe ratio, discrimination ratio and signal-to-noise ratio and compared the performance with a conventional segmented phase-only filter. For carrying out the study, we have developed a dataset of different distorted objects such as alphabets, digits, vehicles, fighter planes. Through a series of experiments and case studies, we are able to prove that the proposed filter reduces the false alarm rate while increasing recognition capability.

An Optimal Spatio-Temporal Hybrid Model Based on Wavelet Transform for Early Fault Detection.

An optimal spatio-temporal hybrid model (STHM) based on wavelet transform (WT) is proposed to improve the sensitivity and accuracy of detecting slowly evolving faults that occur in the early stage and easily submerge with noise in complex industrial production systems. Specifically, a WT is performed to denoise the original data, thus reducing the influence of background noise. Then, a principal component analysis (PCA) and the sliding window algorithm are used to acquire the nearest neighbors in both spatial and time dimensions. Subsequently, the cumulative sum (CUSUM) and the mahalanobis distance (MD) are used to reconstruct the hybrid statistic with spatial and temporal sequences. It helps to enhance the correlation between high-frequency temporal dynamics and space and improves fault detection precision. Moreover, the kernel density estimation (KDE) method is used to estimate the upper threshold of the hybrid statistic so as to optimize the fault detection process. Finally, simulations are conducted by applying the WT-based optimal STHM in the early fault detection of the Tennessee Eastman (TE) process, with the aim of proving that the fault detection method proposed has a high fault detection rate (FDR) and a low false alarm rate (FAR), and it can improve both production safety and product quality.