With the increasing population of Industry 4.0, industrial big data (IBD) has become a hotly discussed topic in digital and intelligent industry field. The security problem existing in the signal ...processing on large scale of data stream is still a challenge issue in industrial internet of things, especially when dealing with the high-dimensional anomaly detection for intelligent industrial application. In this article, to mitigate the inconsistency between dimensionality reduction and feature retention in imbalanced IBD, we propose a variational long short-term memory (VLSTM) learning model for intelligent anomaly detection based on reconstructed feature representation. An encoder-decoder neural network associated with a variational reparameterization scheme is designed to learn the low-dimensional feature representation from high-dimensional raw data. Three loss functions are defined and quantified to constrain the reconstructed hidden variable into a more explicit and meaningful form. A lightweight estimation network is then fed with the refined feature representation to identify anomalies in IBD. Experiments using a public IBD dataset named UNSW-NB15 demonstrate that the proposed VLSTM model can efficiently cope with imbalance and high-dimensional issues, and significantly improve the accuracy and reduce the false rate in anomaly detection for IBD according to F1, area under curve (AUC), and false alarm rate (FAR).
Along with the popularity of the Internet of Things (IoT) techniques with several computational paradigms, such as cloud and edge computing, microservice has been viewed as a promising architecture ...in large-scale application design and deployment. Due to the limited computing ability of edge devices in distributed IoT, only a small scale of data can be used for model training. In addition, most of the machine-learning-based intrusion detection methods are insufficient when dealing with imbalanced dataset under limited computing resources. In this article, we propose an optimized intra/inter-class-structure-based variational few-shot learning (OICS-VFSL) model to overcome a specific out-of-distribution problem in imbalanced learning, and to improve the microservice-oriented intrusion detection in distributed IoT systems. Following a newly designed VFSL framework, an intra/inter-class optimization scheme is developed using reconstructed feature embeddings, in which the intra-class distance is optimized based on the approximation during a variation Bayesian process, while the inter-class distance is optimized based on the maximization of similarities during a feature concatenation process. An intelligent intrusion detection algorithm is, then, introduced to improve the multiclass classification via a nonlinear neural network. Evaluation experiments are conducted using two public datasets to demonstrate the effectiveness of our proposed model, especially in detecting novel attacks with extremely imbalanced data, compared with four baseline methods.
The impact of Internet of Things (IoT) has become increasingly significant in smart manufacturing, while deep generative model (DGM) is viewed as a promising learning technique to work with large ...amount of continuously generated industrial Big Data in facilitating modern industrial applications. However, it is still challenging to handle the imbalanced data when using conventional Generative Adversarial Network (GAN) based learning strategies. In this article, we propose a distribution bias aware collaborative GAN (DB-CGAN) model for imbalanced deep learning in industrial IoT, especially to solve limitations caused by distribution bias issue between the generated data and original data, via a more robust data augmentation. An integrated data augmentation framework is constructed by introducing a complementary classifier into the basic GAN model. Specifically, a conditional generator with random labels is designed and trained adversarially with the classifier to effectively enhance augmentation of the number of data samples in minority classes, while a weight sharing scheme is newly designed between two separated feature extractors, enabling the collaborative adversarial training among generator, discriminator, and classifier. An augmentation algorithm is then developed for intelligent anomaly detection in imbalanced learning, which can significantly improve the classification accuracy based on the correction of distribution bias using the rebalanced data. Compared with five baseline methods, experiment evaluations based on two real-world imbalanced datasets demonstrate the outstanding performance of our proposed model in tackling the distribution bias issue for multiclass classification in imbalanced learning for industrial IoT applications.
Proteomics technology reveals the marker proteins, potential pathogenesis, and intervention targets after noise-induced hearing loss. To study the differences in cochlea protein expression before and ...after noise exposure using proteomics to reveal the pathological mechanism of noise-induced hearing loss (NIHL). A guinea pig NIHL model was established to test the ABR thresholds before and after noise exposure. The proteomics technology was used to study the mechanism of differential protein expression in the cochlea by noise stimulation. The average hearing threshold of guinea pigs on the first day after noise exposure was 57.00 ± 6.78 dB Sound pressure level (SPL); the average hearing threshold on the seventh day after noise exposure was 45.83 ± 6.07 dB SPL. The proteomics technology identified 3122 different inner ear proteins, of which six proteins related to the hearing were down-regulation: Tenascin C, Collagen Type XI alpha two chains, Collagen Type II alpha one chain, Thrombospondin 2, Collagen Type XI alpha one chain and Ribosomal protein L38, and are enriched in protein absorption, focal adhesion, and extracellular matrix receptor pathways. Impulse noise can affect the expression of differential proteins through focal adhesion pathways. This data can provide an experimental basis for the research on the prevention and treatment of NIHL.
Covalent organic frameworks (COFs) were nano-coated onto single-walled carbon nanotubes (SWCNTs) by in situ polymerization of TpPa-COFs together with SWCNTs under solvotherma conditions. At the ...molecular level, the COF/SWCNT interface can be efficiently controlled. Thus, the TpPa-COF-SWCNTs nano-hybrid wire, which combines the excellent conductivity of SWCNTs and the high porosity and good redox activity of TpPa-COFs, was employed as active electrode materials for supercapacitors. The strategy reported in this work can give guidance for the design of other similar COF-based electrodes, and hold a great potential in energy storages
Based on the theory of failure physics, reliability enhancement test is a test technology of stimulation in order to improve reliability by discovering, researching and curing failure. In this paper, ...the main factors inducing failure modes of undercarriage light box were analyzed, and the environmental sensitive stresses affecting reliability were determined. The testing program was designed and test profiles were established based on the theory of reliability enhancement test. Additionally, the test results were analyzed based on failures of products in order to carry out improvement measures.
The impact of Internet of Things (IoT) has become increasingly significant in smart manufacturing, while deep generative model (DGM) is viewed as a promising learning technique to work with large ...amount of continuously generated industrial Big Data in facilitating modern industrial applications. However, it is still challenging to handle the imbalanced data when using conventional Generative Adversarial Network (GAN) based learning strategies. In this article, we propose a distribution bias aware collaborative GAN (DB-CGAN) model for imbalanced deep learning in industrial IoT, especially to solve limitations caused by distribution bias issue between the generated data and original data, via a more robust data augmentation. An integrated data augmentation framework is constructed by introducing a complementary classifier into the basic GAN model. Specifically, a conditional generator with random labels is designed and trained adversarially with the classifier to effectively enhance augmentation of the number of data samples in minority classes, while a weight sharing scheme is newly designed between two separated feature extractors, enabling the collaborative adversarial training among generator, discriminator, and classifier. An augmentation algorithm is then developed for intelligent anomaly detection in imbalanced learning, which can significantly improve the classification accuracy based on the correction of distribution bias using the rebalanced data. Compared with five baseline methods, experiment evaluations based on two real-world imbalanced datasets demonstrate the outstanding performance of our proposed model in tackling the distribution bias issue for multiclass classification in imbalanced learning for industrial IoT applications.
•Two-stage alkaline hydrolysis process was first applied to treat excess sludge.•The running conditions of two-stage alkaline hydrolysis process were determined.•P and N were recovered from ...supernatant of two-stage alkaline hydrolysis sludge.•The supernatant pH of the two-stage alkaline hydrolysis sludge was below 10.5.•Optimum conditions for PO43−-P recovery were determined.
Magnesium ammonium phosphate (MAP) method was used to recover orthophosphate (PO43−-P) and ammonium nitrogen (NH4+-N) from the alkaline hydrolysis supernatant of excess sludge. To reduce alkali consumption and decrease the pH of the supernatant, two-stage alkaline hydrolysis process (TSAHP) was designed. The results showed that the release efficiencies of PO43−-P and NH4+-N were 41.96% and 7.78%, respectively, and the pH of the supernatant was below 10.5 under the running conditions with initial pH of 13, volume ratio (sludge dosage/water dosage) of 1.75 in second-stage alkaline hydrolysis reactor, 20g/L of sludge concentration in first-stage alkaline hydrolysis reactor. The order of parameters influencing MAP reaction was analyzed and the optimized conditions of MAP reaction were predicted through the response surface methodology. The recovery rates of PO43−-P and NH4+-N were 46.88% and 16.54%, respectively under the optimized conditions of Mg/P of 1.8, pH 9.7 and reaction time of 15min.
Background Plants must acquire at least 14 mineral nutrients from the soil to complete their life cycles. Insufficient availability or extreme high levels of the nutrients significantly affect plant ...growth and development. Plants have evolved a series of mechanisms to adapt to unsuitable growth conditions where nutrient levels are too low or too high. microRNAs (miRNAs), a class of small RNAs, are known to mediate post-transcriptional regulation by transcript cleavage or translational inhibition. Besides regulating plant growth and development, miRNAs are well documented to regulate plant adaptation to adverse environmental conditions including nutrient stresses. Scope In this review, we focus on recent progress in our understanding of how miRNAs are involved in plant response to stresses resulting from deficiency in nutrients, such as nitrogen, phosphorus, sulfur, copper and iron, as well as toxicities from heavy metal ions. Conclusions Accumulated evidence indicates that miRNAs play critical roles in sensing the abundance of nutrients, controlling nutrient uptake and phloem-mediated long-distance transport, and nutrient homeostasis. miRNAs act as systemic signals to coordinate these physiological activities helping plants respond to and survive nutrient stresses and toxicities. Knowledge about how miRNAs are involved in plant responses to nutrient stresses promise to provide novel strategies to develop crops with improved nutrient use efficiency which could be grown in soils with either excessive or insufficient availability of nutrients.