A Normalizing Flow-Based Bidirectional Mapping Residual Network for Unsupervised Defect Detection

Unsupervised methods based on density representation have shown their abilities in anomaly detection,but detection performance still needs to be improved.Specifically,approaches using normalizing flows can accurately evaluate sample distributions,mapping normal features to the normal distribution and anomalous features outside it.Consequently,this paper proposes a Normalizing Flow-based Bidirectional Mapping Residual Network(NF-BMR).It utilizes pre-trained Convolutional Neural Networks(CNN)and normalizing flows to construct discriminative source and target domain feature spaces.Additionally,to better learn feature information in both domain spaces,we propose the Bidirectional Mapping Residual Network(BMR),which maps sample features to these two spaces for anomaly detection.The two detection spaces effectively complement each other’s deficiencies and provide a comprehensive feature evaluation from two perspectives,which leads to the improvement of detection performance.Comparative experimental results on the MVTec AD and DAGM datasets against the Bidirectional Pre-trained Feature Mapping Network(B-PFM)and other state-of-the-art methods demonstrate that the proposed approach achieves superior performance.On the MVTec AD dataset,NF-BMR achieves an average AUROC of 98.7%for all 15 categories.Especially,it achieves 100%optimal detection performance in five categories.On the DAGM dataset,the average AUROC across ten categories is 98.7%,which is very close to supervised methods.

Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

OpenNAU:An open-source platform for normalizing,analyzing,and visualizing cancer untargeted metabolomics data

Objective:As an important part of metabolomics analysis,untargeted metabolomics has become a powerful tool in the study of tumor mechanisms and the discovery of metabolic markers with high-throughput spectrometric data which also poses great challenges to data analysis,from the extraction of raw data to the identification of differential metabolites.To date,a large number of analytical tools and processes have been developed and constructed to serve untargeted metabolomics research.The different selection of analytical tools and parameter settings lead to varied results of untargeted metabolomics data.Our goal is to establish an easily operated platform and obtain a repeatable analysis result.Methods:We used the R language basic environment to construct the preprocessing system of the original data and the LAMP(Linux+Apache+MySQL+PHP)architecture to build a cloud mass spectrum data analysis system.Results:An open-source analysis software for untargeted metabolomics data(openNAU)was constructed.It includes the extraction of raw mass data and quality control for the identification of differential metabolic ion peaks.A reference metabolomics database based on public databases was also constructed.Conclusions:A complete analysis system platform for untargeted metabolomics was established.This platform provides a complete template interface for the addition and updating of the analysis process,so we can finish complex analyses of untargeted metabolomics with simple human-computer interactions.The source code can be downloaded from https://github.com/zjuRong/openNAU.

Effect of Normalizing and Hardening on Mechanical Properties of Spring

This study was carried out to investigate the effect of heat treatment (Normalizing and Hardening) on the mechanical properties of springs. The springs were made from mild steel rod having a diameter of 6 mm, a total of 15 springs were made. The springs were then subjected to various heat treatment processes which included;normalizing, hardening and tempering. The heat treated springs were then subjected to various test in other to determine their mechanical properties, these included;impact toughness test, hardness test and tension test. The normalized spring had more strength, was harder and was much tougher than both the annealed and as received springs. The water quenched springs were the hardest of all the heat treated springs, were very brittle and had the lowest percentage elongation. Their strength was also lower than that of the normalized and as received springs. The water quenched and tempered springs had better mechanical properties required for spring making, they had the optimum combination of hardness, strength and toughness when compared with the other heat treated springs.

Robust adaptive output stabilization using dynamic normalizing signal

For a class of nonlinear systems with dynamic uncertainties, robust adaptive stabilization problem is considered in this paper. Firstly, by introducing an observer, an augmented system is obtained. Based on the system, we construct an exp-ISpS Lyapunov function for the unmodeled dynamics, prove that the unmodeled dynamics is exp-ISpS, and then obtain a dynamic normalizing signal to counteract the dynamic disturbances. By the backstepping technique, an adaptive controller is given, it is proved that all the signals in the adaptive control system are globally uniformly ultimately bounded, and the output can be regulated to the origin with any prescribed accuracy. A simulation example further demonstrates the efficiency of the control scheme.

Performance Study of an FFH/BFSK Self-Normalizing Receiver with Multitone Jamming's Frequency Offsets

This study investigates how frequency offsets of multitone jamming affect the fast frequencyhopped binary frequency shift keying （FFH/BFSK） self-normalizing （SNZ） receiver under additive white Gaussian noise （AWGN）. The average bit-error-rate （BER） expressions of the FFH/BFSK SNZ receiver and the average BER expressions of an FFH/BFSK spread-spectrum （SS） communication system with frequency offsets of multitone jamming for the sake of understanding the simulation results better. Simulation results show that BER performance of the FFH/BFSK SNZ receiver with diversity under the worst case multitone jamming （MTJ） and AWGN suffers from multitone jamming＇s frequency offsets when the jamming power is moderate, which is validated by several simulations with different frequency offsets configured in multitone jamming. Therefore, an FFH/BFSK SNZ receiver under multitone jamming can be combated with the help of frequency offsets of multitone jamming.

Normalizing Relationships

AS diplomatic relations were restored between China and the Islamic Republic of the Gambia in March,China’s Foreign Minister Wang Yi called it a“historic moment”for the two countries.Wang met with his Gambian counterpart Neneh Mac Douall-Gaye in Beijing to sign a joint communique on March 17.

New formulas for normalizing photon-added(-subtracted) two-mode squeezed thermal states

For the first time,we derive the compact forms of normalization factors for photon-added（-subtracted） two-mode squeezed thermal states by using the P-representation and the integration within an ordered product of operators（IWOP） technique.It is found that these two factors are related to the Jacobi polynomials.In addition,some new relationships for Jacobi polynomials are presented.

Normalizing Book Citations in Google Scholar: A Hybrid Cited-side Citing-side Method

Purpose: To design and test a method for normalizing book citations in Google Scholar.Design/methodology/approach: A hybrid citing-side, cited-side normalization method was developed and this was tested on a sample of 285 research monographs. The results were analyzed and conclusions drawn.Findings: The method was technically feasible but required extensive manual intervention because of the poor quality of the Google Scholar data. Research limitations: The sample of books was limited and also all were from one discipline —business and management. Also, the method has only been tested on Google Scholar, it would be useful to test it on Web of Science or Scopus.Practical limitations: Google Scholar is a poor source of data although it does cover a much wider range citation sources that other databases. Originality/value: This is the first method that has been developed specifically for normalizing books which have so far not been able to be normalized.

Efficient parameter inference for gravitational wave signals in the presence of transient noises using temporal and time-spectral fusion normalizing flow

Glitches represent a category of non-Gaussian and transient noise that frequently intersects with gravitational wave(GW)signals,thereby exerting a notable impact on the processing of GW data.The inference of GW parameters,crucial for GW astronomy research,is particularly susceptible to such interference.In this study,we pioneer the utilization of a temporal and time-spectral fusion normalizing flow for likelihood-free inference of GW parameters,seamlessly integrating the high temporal resolution of the time domain with the frequency separation characteristics of both time and frequency domains.Remarkably,our findings indicate that the accuracy of this inference method is comparable to that of traditional non-glitch sampling techniques.Furthermore,our approach exhibits a greater efficiency,boasting processing times on the order of milliseconds.In conclusion,the application of a normalizing flow emerges as pivotal in handling GW signals affected by transient noises,offering a promising avenue for enhancing the field of GW astronomy research.

Pretreating and normalizing metabolomics data for statistical analysis

Metabolomics as a research field and a set of techniques is to study the entire small molecules in biological samples.Metabolomics is emerging as a powerful tool generally for pre-cision medicine.Particularly,integration of microbiome and metabolome has revealed the mechanism and functionality of microbiome in human health and disease.However,metabo-lomics data are very complicated.Preprocessing/pretreating and normalizing procedures on metabolomics data are usually required before statistical analysis.In this review article,we comprehensively review various methods that are used to preprocess and pretreat metabolo-mics data,including MS-based data and NMR-based data preprocessing,dealing with zero and/or missing values and detecting outliers,data normalization,data centering and scaling,data transformation.We discuss the advantages and limitations of each method.The choice for a suitable preprocessing method is determined by the biological hypothesis,the characteristics of the data set,and the selected statistical data analysis method.We then provide the perspective of their applications in the microbiome and metabolome research.

Effects of Normalizing Annealing on Grain-oriented Silicon Steel

The grain-oriented silicon steel is a kind of important magnetic materials with low iron loss and high induc tion. Hot hand normalizing annealing is an important process which influences the microstructure and the development of the inhibitors. The effects of different annealing temperatures and cooling conditions on the inhibitors and microstructures of normalizing annealing band were investigated. The microstructure and different kinds of the inhibitors, i. e. , A1N, AIN＋Cu, S＋MnS, and TiN, were discovered. The result shows that a suitable cooling condition leads to more nano scale inhibitors and uniform microstructure of the normalizing annealing band and consequently results in better magnetic properties.

Precipitation Behavior of V-N Microalloyed Steels during Normalizing

The precipitation behavior of V-N microalloyed steel during normalizing process was studied by physicochemical phase analysis and transmission electron microscopy（TEM）. The effect of precipitation behavior on mechanical properties was investigated by theoretical calculations. The results showed that 32.9% of V（C,N） precipitates remained undissolved in the austenite during the soaking step of the normalizing process. These precipitates prevented the growth of the austenite grains. During the subsequent cooling process, the dissolved V（C,N） re-precipitated and played a role in precipitation strengthening. The undissolved V（C,N） induced intragranular ferrite nucleation and refined the ferrite grains. Consequently, compared with hot-rolled steel, the normalized steel exhibited increased grain-refining strengthening but diminished precipitation strengthening, leading to an improvement of the impact energy at the expense of about 40 MPa yield strength.

Identifying the best common factor model via exploratory eactor analysis

Currently,there is no solid criterion for judging the quality of the estimators in factor analysis.This paper presents a new evaluation method for exploratory factor analysis that pinpoints an appropriate number of factors along with the best method for factor extraction.The proposed technique consists of two steps:testing the normality of the residuals from the fitted model via the Shapiro-Wilk test and using an empirical quantified index to judge the quality of the factor model.Examples are presented to demonstrate how the method is implemented and to verify its effectiveness.

Nonlinear constitutive models of rock structural plane and their applications

Structural planes play an important role in controlling the stability of rock engineering,and the influence of structural planes should be considered in the design and construction process of rock engineering.In this paper,mechanical properties,constitutive theory,and numerical application of structural plane are studied by a combination method of laboratory tests,theoretical derivation,and program development.The test results reveal the change laws of various mechanical parameters under different roughness and normal stress.At the pre-peak stage,a non-stationary model of shear stiffness is established,and threedimensional empirical prediction models for initial shear stiffness and residual stage roughness are proposed.The nonlinear constitutive models are established based on elasto-plastic mechanics,and the algorithms of the models are developed based on the return mapping algorithm.According to a large number of statistical analysis results,empirical prediction models are proposed for model parameters expressed by structural plane characteristic parameters.Finally,the discrete element method(DEM)is chosen to embed the constitutive models for practical application.The running programs of the constitutive models have been compiled into the discrete element model library.The comparison results between the proposed model and the Mohr-Coulomb slip model show that the proposed model can better describe nonlinear changes at different stages,and the predicted shear strength,peak strain and shear stiffness are closer to the test results.The research results of the paper are conducive to the accurate evaluation of structural plane in rock engineering.

A novel mitigation measure for normal fault-induced deformations on pile-raft systems

Evidence from recent earthquakes has shown destructive consequences of fault-induced permanent ground movement on structures.Such observations have increased the demand for improvements in the design of structures that are dramatically vulnerable to surface fault ruptures.In this study a novel connection between the raft and the piles is proposed to mitigate the hazards associated with a normal fault on pile-raft systems by means of 3D finite element(FE)modeling.Before embarking on the parametric study,the strain-softening constitutive law used for numerical modeling of the sand has been validated against centrifuge test results.The exact location of the fix-head and unconnected pile-raft systems relative to the outcropping fault rupture in the free-field is parametrically investigated,revealing different failure mechanisms.The performance of the proposed connection for protecting the pile-raft system against normal fault-induced deformations is assessed by comparing the geotechnical and structural responses of both types of foundation.The results indicate that the pocket connection can relatively reduce the cap rotation and horizontal and vertical displacements of the raft in most scenarios.The proposed connection decreases the bending moment response of the piles to their bending moment capacity,verging on a fault offset of 0.6 m at bedrock.

Understanding the combustion behavior of electric bicycle batteries and unveiling its relationship with fire extinguishing

In this study,a detailed analysis of the combustion behaviors of the lithium iron phosphate(LFP)and lithium manganese oxide(LMO)batteries used in electric bicycles was conducted.This research included quantitative measurements of the combustion duration,flame height,combustion temperature,heat release rate,and total heat release.The results indicated that LMO batteries exhibited higher combustion temperatures of 600–700°C,flame heights of 70–75 cm,a significantly higher heat release rate of40.1 k W(12 Ah),and a total heat release of 1.04 MJ(12 Ah)compared to LFP batteries with the same capacity.Based on these experimental results,a normalized total heat release(NORTHR)parameter was proposed,demonstrating good universality for batteries with different capacities.Utilizing this parameter,quantitative calculations and optimization of the extinguishing agent dosage were conducted for fires involving these two types of batteries,and the method was validated by extinguishing fires for these two types of battery packs with water-based extinguishing fluids.

Shear band evolution and acoustic emission characteristics of sandstone containing non-persistent flaws

Direct shear tests were conducted on sandstone specimens under different constant normal stresses to study the coalescence of cracks between non-persistent flaws and the shear sliding characteristics of the shear-formed fault.Digital image correlation and acoustic emission(AE)techniques were used to monitor the evolution of shear bands at the rock bridge area and microcracking behaviors.The experimental results revealed that the shear stresses corresponding to the peak and sub-peak in the stressdisplacement curve are significantly affected by the normal stress.Strain localization bands emerged at both the tip of joints and the rock bridge,and their extension and interaction near the peak stress caused a surge in the AE hit rate and a significant decrease in the AE b value.Short and curvilinear strain bands were detected at low normal stress,while high normal stress generally led to more microcracking events and longer coplanar cracks at the rock bridge area.Furthermore,an increase in normal stress resulted in a higher AE count rate and more energetic AE events during friction sliding along the shearformed fault.It was observed that the elastic energy released during the crack coalescence at the prepeak stage was much greater than that released during friction sliding at the post-peak stage.More than 75%of AE events were located in the low-frequency band(0e100 kHz),and this proportion continued to rise with increasing normal stress.Moreover,more AE events of low AF value and high RA value were observed in specimens subjected to high normal stress,indicating that greater normal stress led to more microcracks of shear nature.

Climate-Vegetation Coverage Interactions in the Hengduan Mountains Area, Southeastern Tibetan Plateau, and Their Downstream Effects

Little is known about the mechanism of climate-vegetation coverage coupled changes in the Tibetan Plateau(TP)region,which is the most climatically sensitive and ecologically fragile region with the highest terrain in the world.This study,using multisource datasets(including satellite data and meteorological observations and reanalysis data)revealed the mutual feedback mechanisms between changes in climate(temperature and precipitation)and vegetation coverage in recent decades in the Hengduan Mountains Area(HMA)of the southeastern TP and their influences on climate in the downstream region,the Sichuan Basin(SCB).There is mutual facilitation between rising air temperature and increasing vegetation coverage in the HMA,which is most significant during winter,and then during spring,but insignificant during summer and autumn.Rising temperature significantly enhances local vegetation coverage,and vegetation greening in turn heats the atmosphere via enhancing net heat flux from the surface to the atmosphere.The atmospheric heating anomaly over the HMA thickens the atmospheric column and increases upper air pressure.The high pressure anomaly disperses downstream via the westerly flow,expands across the SCB,and eventually increases the SCB temperature.This effect lasts from winter to the following spring,which may cause the maximum increasing trend of the SCB temperature and vegetation coverage in spring.These results are helpful for estimating future trends in climate and eco-environmental variations in the HMA and SCB under warming scenarios,as well as seasonal forecasting based on the connection between the HMA eco-environment and SCB climate.

Prediction of Ground Vibration Induced by Rock Blasting Based on Optimized Support Vector Regression Models

Accurately estimating blasting vibration during rock blasting is the foundation of blasting vibration management.In this study,Tuna Swarm Optimization(TSO),Whale Optimization Algorithm(WOA),and Cuckoo Search(CS)were used to optimize two hyperparameters in support vector regression(SVR).Based on these methods,three hybrid models to predict peak particle velocity(PPV)for bench blasting were developed.Eighty-eight samples were collected to establish the PPV database,eight initial blasting parameters were chosen as input parameters for the predictionmodel,and the PPV was the output parameter.As predictive performance evaluation indicators,the coefficient of determination(R2),rootmean square error(RMSE),mean absolute error(MAE),and a10-index were selected.The normalizedmutual information value is then used to evaluate the impact of various input parameters on the PPV prediction outcomes.According to the research findings,TSO,WOA,and CS can all enhance the predictive performance of the SVR model.The TSO-SVR model provides the most accurate predictions.The performances of the optimized hybrid SVR models are superior to the unoptimized traditional prediction model.The maximum charge per delay impacts the PPV prediction value the most.