Search Results (6)

The gearbox, a key transmission device in industrial applications, can cause severe vibrations or failures when anomalies occur. With increasing industrial automation complexity, precise anomaly detection is crucial. This paper introduces DCCopGAN, a novel unsupervised framework that uses a deep convolutional copula-generative adversarial network for unsupervised multi-sensor anomaly detection in industrial gearboxes. Firstly, a Deep Convolutional Generative Adversarial Network (DCGAN) generator is trained on high-dimensional normal operational data from multi-sensors to learn its underlying distribution, enabling the calculation of reconstruction errors for input samples. Then, these reconstruction errors are analyzed by Copula-Based Outlier Detection (CopOD), an efficient non-parametric technique, to identify anomalies. In the testing phase, reconstruction errors for test samples are similarly computed, normalized, and then evaluated by the CopOD mechanism to assign anomaly scores and detect deviations from normal behavior. The proposed DCCopGAN framework has been validated on a real gearbox dataset, where experimental results demonstrate its superior anomaly detection performance over other methods. Full article

Camellia oleifera C. Abel is a woody oil crop with multiple purposes. This study aims to investigate the mutagenic effects of ⁶⁰Co-γ radiation on C. oleifera seedlings and to screen anthracnose-resistant mutants. Two C. oleifera varieties were investigated: ‘Xianglin 1’ (XL1) and ‘Xianglin 210’ (XL210). Seeds were irradiated with 0 Gy, 30 Gy, 50 Gy, and 80 Gy of ⁶⁰Co-γ, and after one year of planting, the mutagenic lines were studied, and disease-resistant mutants were screened. Results showed that as the radiation intensity was increased, the emergence percentage of both C. oleifera XL210 and XL1 was significantly decreased. Radiation significantly changed the SOD and POD activities in both varieties. Furthermore, 80 Gy irradiated lines showed reduced anthracnose resistance in both varieties. However, 50 Gy irradiated lines showed enhanced disease resistance in XL210 while reducing it in XL1. The 30 Gy irradiated lines did not affect the disease resistance of either variety. Colletotrichum gloeosporioides infection tests were conducted on 94 mutant C. oleifera seedlings, resulting in 8 highly resistant mutants (A3, A8, A10, A19, A21, A32, A35, B17) and 3 susceptible mutants (A4, B15, B27) in XL210 and XL1. Differences in SOD and POD activities led to variations in disease resistance among different mutants. Additionally, the expression levels of CoSOD1, CoPOD, CoIDD4, and CoWKRY78 were varied among the different mutants. This study delivers the screening of disease-resistant mutants in C. oleifera through mutagenic breeding, providing material for the development of new C. oleifera varieties and serving as a resource for further research in mutagenic breeding. Full article

Cytoplasmic male sterility (CMS) plays a crucial role in the utilization of heterosis. The petaloid anther abortion in oil tea (Camellia oleifera Abel.) constitutes a CMS phenomenon, which is of great value for the hybrid breeding of oil tea. However, as the mechanism of its CMS is still poorly understood, it is necessary to study the cytology and physiological characteristics of anther abortion. In this study, a C. oleifera cultivar, Huashuo (HS), and its petalized CMS mutant (HSP) were used as materials to explore this mechanism. Compared with HS, cytological analysis demonstrated that HSP showed early-onset tapetum programmed cell death (PCD) and an organelle disorder phenotype during the tetrad stage. In HSP, anthers exhibited elevated levels of calcium deposition in anther wall tissues, tapetum layers, and microspores, and yet calcium accumulation was abnormal at the later stage. The contents of hydrogen peroxide and MDA in HSP anthers were higher, and the activities of superoxide dismutase (SOD), peroxidase (POD), and catalase (CAT) were lower than those of HS, which resulted in an excessive accumulation of reactive oxygen species (ROS). Real-time quantitative PCR confirmed that the transcription levels of CoPOD and CoCAT genes encoding key antioxidant enzymes in HSP were downregulated compared with HS in early pollen development; the gene CoCPK, which encodes a calcium-dependent protein kinase associated with antioxidase, was upregulated during the critical period. Thus, we suggest that excessive ROS as a signal breaks the balance of the antioxidant system, and along with an abnormal distribution of calcium ions, leads to the early initiation of PCD in the tapetum, and ultimately leads to pollen abortion for HSP. These results lay a cytological and physiological foundation for further studies on the CMS mechanism, and provide information for breeding male-sterile lines of C. oleifera. Full article

The increased demand for and use of autonomous driving and advanced driver assistance systems has highlighted the issue of abnormalities occurring within the perception layers, some of which may result in accidents. Recent publications have noted the lack of standardized independent testing formats and insufficient methods with which to analyze, verify, and qualify LiDAR (Light Detection and Ranging)-acquired data and their subsequent labeling. While camera-based approaches benefit from a significant amount of long-term research, images captured through the visible spectrum can be unreliable in situations with impaired visibility, such as dim lighting, fog, and heavy rain. A redoubled focus upon LiDAR usage would combat these shortcomings; however, research involving the detection of anomalies and the validation of gathered data is few and far between when compared to its counterparts. This paper aims to contribute to expand the knowledge on how to evaluate LiDAR data by introducing a novel method with the ability to detect these patterns and complement other performance evaluators while using a statistical approach. Although it is preliminary, the proposed methodology shows promising results in the evaluation of an algorithm’s confidence score, the impact that weather and road conditions may have on data, and fringe cases in which the data may be insufficient or otherwise unusable. Full article

With an increasing number of offshore wind farms, monitoring and evaluating the effects of the wind turbines on the marine environment have become important tasks. Here we conducted a feasibility study with the focus on monitoring these effects by utilizing different machine learning methods. A multi-source dataset for a study site in the North Sea is created by combining satellite data, local in situ data and a hydrodynamic model. The machine learning algorithm DTWkNN, which is based on dynamic time warping and k-nearest neighbor, is used for multivariate time series data imputation. Subsequently, unsupervised anomaly detection is performed to identify possible inferences in the dynamic and interdepending marine environment around the offshore wind farm. The anomaly results are analyzed in terms of location, density and temporal variability, granting access to information and building a basis for explanation. Temporal detection of anomalies with COPOD is found to be a suitable method. Actionable insights are the direction and magnitude of potential effects of the wind farm on the marine environment, depending on the wind direction. This study works towards a digital twin of offshore wind farms and provides a set of methods based on machine learning to monitor and evaluate offshore wind farm effects, supporting stakeholders with information for decision making on future maritime energy infrastructures. Full article

The aim of this study was to assess the efficacy of using real-time visual feedback (VF) during a one-week balance training intervention on postural sway parameters in young karatekas. Twenty-six young male karatekas (age = 14.0 ± 2.3 years) were randomly divided into two groups: real-time VF training (VFT; n = 14) and control (CTRL; n = 12). Their center of pressure (COP) displacement (path length, COPpl; distance from origin, COPod) was assessed pre- and post-training on a Wii Balance Board platform in two positions (Flex: knee of the supporting leg slightly bent, maximum hip and leg flexion of the other leg; Kick: knee of the supporting leg slightly bent, mawashi-geri posture for the kicking leg). Both groups trained twice a day for seven days, performing a one-legged stance on the non-dominant limb in the Kick position. During the training, VFT received real-time VF of COP displacement, while CTRL looked at a fixed point. No interaction effect was found (p > 0.05). VFT exhibited greater changes pre- and post-training in Flex COPpl (−25.2%, g = 1.5), Kick COPpl (−24.1%, g = 1.3), and Kick COPod (−44.1%, g = 1.0) compared to CTRL (−0.9–−13.0%, g-range: 0.1–0.7). It is possible that superimposing real-time VF to a week-long balance training intervention could induce a greater sport-specific balance-training effect in young karatekas. Full article