Imbalanced Data Classification Using SVM Based on Improved Simulated Annealing Featuring Synthetic Data Generation and Reduction

Imbalanced data classification is one of the major problems in machine learning.This imbalanced dataset typically has significant differences in the number of data samples between its classes.In most cases,the performance of the machine learning algorithm such as Support Vector Machine(SVM)is affected when dealing with an imbalanced dataset.The classification accuracy is mostly skewed toward the majority class and poor results are exhibited in the prediction of minority-class samples.In this paper,a hybrid approach combining data pre-processing technique andSVMalgorithm based on improved Simulated Annealing(SA)was proposed.Firstly,the data preprocessing technique which primarily aims at solving the resampling strategy of handling imbalanced datasets was proposed.In this technique,the data were first synthetically generated to equalize the number of samples between classes and followed by a reduction step to remove redundancy and duplicated data.Next is the training of a balanced dataset using SVM.Since this algorithm requires an iterative process to search for the best penalty parameter during training,an improved SA algorithm was proposed for this task.In this proposed improvement,a new acceptance criterion for the solution to be accepted in the SA algorithm was introduced to enhance the accuracy of the optimization process.Experimental works based on ten publicly available imbalanced datasets have demonstrated higher accuracy in the classification tasks using the proposed approach in comparison with the conventional implementation of SVM.Registering at an average of 89.65%of accuracy for the binary class classification has demonstrated the good performance of the proposed works.

Strong synergy between physical and chemical properties:Insight into optimization of atomically dispersed oxygen reduction catalysts

Atomically dispersed catalysts exhibit significant influence on facilitating the sluggish oxygen reduction reaction(ORR)kinetics with high atom economy,owing to remarkable attributes including nearly 100%atomic utilization and exceptional catalytic functionality.Furthermore,accurately controlling atomic physical properties including spin,charge,orbital,and lattice degrees of atomically dispersed catalysts can realize the optimized chemical properties including maximum atom utilization efficiency,homogenous active centers,and satisfactory catalytic performance,but remains elusive.Here,through physical and chemical insight,we review and systematically summarize the strategies to optimize atomically dispersed ORR catalysts including adjusting the atomic coordination environment,adjacent electronic orbital and site density,and the choice of dual-atom sites.Then the emphasis is on the fundamental understanding of the correlation between the physical property and the catalytic behavior for atomically dispersed catalysts.Finally,an overview of the existing challenges and prospects to illustrate the current obstacles and potential opportunities for the advancement of atomically dispersed catalysts in the realm of electrocatalytic reactions is offered.

Data Secure Storage Mechanism for IIoT Based on Blockchain

With the development of Industry 4.0 and big data technology,the Industrial Internet of Things(IIoT)is hampered by inherent issues such as privacy,security,and fault tolerance,which pose certain challenges to the rapid development of IIoT.Blockchain technology has immutability,decentralization,and autonomy,which can greatly improve the inherent defects of the IIoT.In the traditional blockchain,data is stored in a Merkle tree.As data continues to grow,the scale of proofs used to validate it grows,threatening the efficiency,security,and reliability of blockchain-based IIoT.Accordingly,this paper first analyzes the inefficiency of the traditional blockchain structure in verifying the integrity and correctness of data.To solve this problem,a new Vector Commitment(VC)structure,Partition Vector Commitment(PVC),is proposed by improving the traditional VC structure.Secondly,this paper uses PVC instead of the Merkle tree to store big data generated by IIoT.PVC can improve the efficiency of traditional VC in the process of commitment and opening.Finally,this paper uses PVC to build a blockchain-based IIoT data security storage mechanism and carries out a comparative analysis of experiments.This mechanism can greatly reduce communication loss and maximize the rational use of storage space,which is of great significance for maintaining the security and stability of blockchain-based IIoT.

Hadoop-based secure storage solution for big data in cloud computing environment

In order to address the problems of the single encryption algorithm,such as low encryption efficiency and unreliable metadata for static data storage of big data platforms in the cloud computing environment,we propose a Hadoop based big data secure storage scheme.Firstly,in order to disperse the NameNode service from a single server to multiple servers,we combine HDFS federation and HDFS high-availability mechanisms,and use the Zookeeper distributed coordination mechanism to coordinate each node to achieve dual-channel storage.Then,we improve the ECC encryption algorithm for the encryption of ordinary data,and adopt a homomorphic encryption algorithm to encrypt data that needs to be calculated.To accelerate the encryption,we adopt the dualthread encryption mode.Finally,the HDFS control module is designed to combine the encryption algorithm with the storage model.Experimental results show that the proposed solution solves the problem of a single point of failure of metadata,performs well in terms of metadata reliability,and can realize the fault tolerance of the server.The improved encryption algorithm integrates the dual-channel storage mode,and the encryption storage efficiency improves by 27.6% on average.

基于re3data的中英科学数据仓储平台对比研究

以re3data为数据获取源,选取中英两国406个科学数据仓储为研究对象,从分布特征、责任类型、仓储许可、技术标准及质量标准等5个方面、11个指标对两国科学数据仓储的建设情况进行对比分析,试图为我国数据仓储的可持续发展提出建议:广泛联结国内外异质机构,推进多学科领域的交流与合作,有效扩充仓储许可权限与类型,优化技术标准的应用现况,提高元数据使用的灵活性。

Defect Detection Model Using Time Series Data Augmentation and Transformation

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

Cu-Based Materials for Enhanced C_(2+) Product Selectivity in Photo-/Electro-Catalytic CO_(2) Reduction: Challenges and Prospects

Carbon dioxide conversion into valuable products using photocatalysis and electrocatalysis is an effective approach to mitigate global environmental issues and the energy shortages. Among the materials utilized for catalytic reduction of CO_(2), Cu-based materials are highly advantageous owing to their widespread availability, cost-effectiveness, and environmental sustainability. Furthermore, Cu-based materials demonstrate interesting abilities in the adsorption and activation of carbon dioxide, allowing the formation of C_(2+) compounds through C–C coupling process. Herein, the basic principles of photocatalytic CO_(2) reduction reactions(PCO_(2)RR) and electrocatalytic CO_(2) reduction reaction(ECO_(2)RR) and the pathways for the generation C_(2+) products are introduced. This review categorizes Cu-based materials into different groups including Cu metal, Cu oxides, Cu alloys, and Cu SACs, Cu heterojunctions based on their catalytic applications. The relationship between the Cu surfaces and their efficiency in both PCO_(2)RR and ECO_(2)RR is emphasized. Through a review of recent studies on PCO_(2)RR and ECO_(2)RR using Cu-based catalysts, the focus is on understanding the underlying reasons for the enhanced selectivity toward C_(2+) products. Finally, the opportunities and challenges associated with Cu-based materials in the CO_(2) catalytic reduction applications are presented, along with research directions that can guide for the design of highly active and selective Cu-based materials for CO_(2) reduction processes in the future.

Numerical Study on Reduction in Aerodynamic Drag and Noise of High-Speed Pantograph

Reducing the aerodynamic drag and noise levels of high-speed pantographs is important for promoting environmentally friendly,energy efficient and rapid advances in train technology.Using computational fluid dynamics theory and the K-FWH acoustic equation,a numerical simulation is conducted to investigate the aerodynamic characteristics of high-speed pantographs.A component optimization method is proposed as a possible solution to the problemof aerodynamic drag and noise in high-speed pantographs.The results of the study indicate that the panhead,base and insulator are the main contributors to aerodynamic drag and noise in high-speed pantographs.Therefore,a gradual optimization process is implemented to improve the most significant components that cause aerodynamic drag and noise.By optimizing the cross-sectional shape of the strips and insulators,the drag and noise caused by airflow separation and vortex shedding can be reduced.The aerodynamic drag of insulator with circular cross section and strips with rectangular cross section is the largest.Ellipsifying insulators and optimizing the chamfer angle and height of the windward surface of the strips can improve the aerodynamic performance of the pantograph.In addition,the streamlined fairing attached to the base can eliminate the complex flow and shield the radiated noise.In contrast to the original pantograph design,the improved pantograph shows a 21.1%reduction in aerodynamic drag and a 1.65 dBA reduction in aerodynamic noise.

Oxygen‑Coordinated Single Mn Sites for Efficient Electrocatalytic Nitrate Reduction to Ammonia

Electrocatalytic nitrate reduction reaction has attracted increasing attention due to its goal of low carbon emission and environmental protection.Here,we report an efficient NitRR catalyst composed of single Mn sites with atomically dispersed oxygen(O)coordination on bacterial cellulose-converted graphitic carbon(Mn-O-C).Evidence of the atomically dispersed Mn-(O-C_(2))_(4)moieties embedding in the exposed basal plane of carbon surface is confirmed by X-ray absorption spectroscopy.As a result,the as-synthesized Mn-O-C catalyst exhibits superior NitRR activity with an NH_(3)yield rate(RNH_(3))of 1476.9±62.6μg h^(−1)cm^(−2)at−0.7 V(vs.reversible hydrogen electrode,RHE)and a faradaic efficiency(FE)of 89.0±3.8%at−0.5 V(vs.RHE)under ambient conditions.Further,when evaluated with a practical flow cell,Mn-O-C shows a high RNH_(3)of 3706.7±552.0μg h^(−1)cm^(−2)at a current density of 100 mA cm−2,2.5 times of that in the H cell.The in situ FT-IR and Raman spectroscopic studies combined with theoretical calculations indicate that the Mn-(O-C_(2))_(4)sites not only effectively inhibit the competitive hydrogen evolution reaction,but also greatly promote the adsorption and activation of nitrate(NO_(3)^(−)),thus boosting both the FE and selectivity of NH_(3)over Mn-(O-C_(2))_(4)sites.

Enhanced prediction of anisotropic deformation behavior using machine learning with data augmentation

Mg alloys possess an inherent plastic anisotropy owing to the selective activation of deformation mechanisms depending on the loading condition.This characteristic results in a diverse range of flow curves that vary with a deformation condition.This study proposes a novel approach for accurately predicting an anisotropic deformation behavior of wrought Mg alloys using machine learning(ML)with data augmentation.The developed model combines four key strategies from data science:learning the entire flow curves,generative adversarial networks(GAN),algorithm-driven hyperparameter tuning,and gated recurrent unit(GRU)architecture.The proposed model,namely GAN-aided GRU,was extensively evaluated for various predictive scenarios,such as interpolation,extrapolation,and a limited dataset size.The model exhibited significant predictability and improved generalizability for estimating the anisotropic compressive behavior of ZK60 Mg alloys under 11 annealing conditions and for three loading directions.The GAN-aided GRU results were superior to those of previous ML models and constitutive equations.The superior performance was attributed to hyperparameter optimization,GAN-based data augmentation,and the inherent predictivity of the GRU for extrapolation.As a first attempt to employ ML techniques other than artificial neural networks,this study proposes a novel perspective on predicting the anisotropic deformation behaviors of wrought Mg alloys.

Single-atom catalysts for the electrochemical reduction of carbon dioxide into hydrocarbons and oxygenates

The electrochemical reduction of carbon dioxide offers a sound and economically viable technology for the electrification and decarbonization of the chemical and fuel industries.In this technology,an electrocatalytic material and renewable energy-generated electricity drive the conversion of carbon dioxide into high-value chemicals and carbon-neutral fuels.Over the past few years,single-atom catalysts have been intensively studied as they could provide near-unity atom utilization and unique catalytic performance.Single-atom catalysts have become one of the state-of-the-art catalyst materials for the electrochemical reduction of carbon dioxide into carbon monoxide.However,it remains a challenge for single-atom catalysts to facilitate the efficient conversion of carbon dioxide into products beyond carbon monoxide.In this review,we summarize and present important findings and critical insights from studies on the electrochemical carbon dioxide reduction reaction into hydrocarbons and oxygenates using single-atom catalysts.It is hoped that this review gives a thorough recapitulation and analysis of the science behind the catalysis of carbon dioxide into more reduced products through singleatom catalysts so that it can be a guide for future research and development on catalysts with industry-ready performance for the electrochemical reduction of carbon dioxide into high-value chemicals and carbon-neutral fuels.

Reliability evaluation of IGBT power module on electric vehicle using big data

There are challenges to the reliability evaluation for insulated gate bipolar transistors(IGBT)on electric vehicles,such as junction temperature measurement,computational and storage resources.In this paper,a junction temperature estimation approach based on neural network without additional cost is proposed and the lifetime calculation for IGBT using electric vehicle big data is performed.The direct current(DC)voltage,operation current,switching frequency,negative thermal coefficient thermistor(NTC)temperature and IGBT lifetime are inputs.And the junction temperature(T_(j))is output.With the rain flow counting method,the classified irregular temperatures are brought into the life model for the failure cycles.The fatigue accumulation method is then used to calculate the IGBT lifetime.To solve the limited computational and storage resources of electric vehicle controllers,the operation of IGBT lifetime calculation is running on a big data platform.The lifetime is then transmitted wirelessly to electric vehicles as input for neural network.Thus the junction temperature of IGBT under long-term operating conditions can be accurately estimated.A test platform of the motor controller combined with the vehicle big data server is built for the IGBT accelerated aging test.Subsequently,the IGBT lifetime predictions are derived from the junction temperature estimation by the neural network method and the thermal network method.The experiment shows that the lifetime prediction based on a neural network with big data demonstrates a higher accuracy than that of the thermal network,which improves the reliability evaluation of system.

Detection of Turbulence Anomalies Using a Symbolic Classifier Algorithm in Airborne Quick Access Record(QAR)Data Analysis

As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation safety.The eddy dissipation rate(EDR)has been established as the standard metric for quantifying turbulence in civil aviation.This study aims to explore a universally applicable symbolic classification approach based on genetic programming to detect turbulence anomalies using quick access recorder(QAR)data.The detection of atmospheric turbulence is approached as an anomaly detection problem.Comparative evaluations demonstrate that this approach performs on par with direct EDR calculation methods in identifying turbulence events.Moreover,comparisons with alternative machine learning techniques indicate that the proposed technique is the optimal methodology currently available.In summary,the use of symbolic classification via genetic programming enables accurate turbulence detection from QAR data,comparable to that with established EDR approaches and surpassing that achieved with machine learning algorithms.This finding highlights the potential of integrating symbolic classifiers into turbulence monitoring systems to enhance civil aviation safety amidst rising environmental and operational hazards.

Porous metal oxides in the role of electrochemical CO_(2) reduction reaction

The global energy-related CO_(2) emissions have rapidly increased as the world economy heavily relied on fossil fuels.This paper explores the pressing challenge of CO_(2) emissions and highlights the role of porous metal oxide materials in the electrocatalytic reduction of CO_(2)(CO_(2)RR).The focus is on the development of robust and selective catalysts,particularly metal and metal-oxide-based materials.Porous metal oxides offer high surface area,enhancing the accessibility to active sites and improving reaction kinetics.The tunability of these materials allows for tailored catalytic behavior,targeting optimized reaction mechanisms for CO_(2)RR.The work also discusses the various synthesis strategies and identifies key structural and compositional features,addressing challenges like high overpotential,poor selectivity,and low stability.Based on these insights,we suggest avenues for future research on porous metal oxide materials for electrochemical CO_(2) reduction.

Full-frame Data Reduction Method:A Data Mining Tool to Detect the Potential Variations in Optical Photometry

A Synchronous Photometry Data Extraction(SPDE)program,performing indiscriminate monitoring of all stars appearing in the same field of view of an astronomical image,is developed by integrating several Astropy affiliated packages to make full use of time series observed by traditional small/medium aperture ground-based telescopes.The complete full-frame stellar photometry data reductions implemented for the two time series of cataclysmic variables:RX J2102.0+3359 and Paloma J0524+4244 produce 363 and 641 optimal light curves,respectively.A cross-identification with SIMBAD finds 23 known stars,of which 16 are red giant-/horizontal-branch stars,2 W UMa-type eclipsing variables,2 program stars,an X-ray source and 2 Asteroid Terrestrial-impact Last Alert System variables.Based on the data products from the SPDE program,a follow-up light curve analysis program identifies 32 potential variable light curves,of which 18 are from the time series of RX J2102.0+3359,and 14 are from that of Paloma J0524+4244.They are preliminarily separated into periodic,transient,and peculiar types.By querying for the 58 VizieR online data catalogs,their physical parameters and multi-band brightness spanning X-ray to radio are compiled for future analysis.

Surface engineering of ZnO electrocatalyst by N doping towards electrochemical CO_(2) reduction

The discovery of efficient,selective,and stable electrocatalysts can be a key point to produce the largescale chemical fuels via electrochemical CO_(2) reduction(ECR).In this study,an earth-abundant and nontoxic ZnO-based electrocatalyst was developed for use in gas-diffusion electrodes(GDE),and the effect of nitrogen(N)doping on the ECR activity of ZnO electrocatalysts was investigated.Initially,a ZnO nanosheet was prepared via the hydrothermal method,and nitridation was performed at different times to control the N-doping content.With an increase in the N-doping content,the morphological properties of the nanosheet changed significantly,namely,the 2D nanosheets transformed into irregularly shaped nanoparticles.Furthermore,the ECR performance of Zn O electrocatalysts with different N-doping content was assessed in 1.0 M KHCO_(3) electrolyte using a gas-diffusion electrode-based ECR cell.While the ECR activity increased after a small amount of N doping,it decreased for higher N doping content.Among them,the N:ZnO-1 h electrocatalysts showed the best CO selectivity,with a faradaic efficiency(FE_(CO))of 92.7%at-0.73 V vs.reversible hydrogen electrode(RHE),which was greater than that of an undoped Zn O electrocatalyst(FE_(CO)of 63.4%at-0.78 V_(RHE)).Also,the N:ZnO-1 h electrocatalyst exhibited outstanding durability for 16 h,with a partial current density of-92.1 mA cm^(-2).This improvement of N:ZnO-1 h electrocatalyst can be explained by density functional theory calculations,demonstrating that this improvement of N:ZnO-1 h electrocatalyst comes from(ⅰ)the optimized active sites lowering the free energy barrier for the rate-determining step(RDS),and(ⅱ)the modification of electronic structure enhancing the electron transfer rate by N doping.

Model reduction of fractional impedance spectra for time–frequency analysis of batteries, fuel cells, and supercapacitors

Joint time–frequency analysis is an emerging method for interpreting the underlying physics in fuel cells,batteries,and supercapacitors.To increase the reliability of time–frequency analysis,a theoretical correlation between frequency-domain stationary analysis and time-domain transient analysis is urgently required.The present work formularizes a thorough model reduction of fractional impedance spectra for electrochemical energy devices involving not only the model reduction from fractional-order models to integer-order models and from high-to low-order RC circuits but also insight into the evolution of the characteristic time constants during the whole reduction process.The following work has been carried out:(i)the model-reduction theory is addressed for typical Warburg elements and RC circuits based on the continued fraction expansion theory and the response error minimization technique,respectively;(ii)the order effect on the model reduction of typical Warburg elements is quantitatively evaluated by time–frequency analysis;(iii)the results of time–frequency analysis are confirmed to be useful to determine the reduction order in terms of the kinetic information needed to be captured;and(iv)the results of time–frequency analysis are validated for the model reduction of fractional impedance spectra for lithium-ion batteries,supercapacitors,and solid oxide fuel cells.In turn,the numerical validation has demonstrated the powerful function of the joint time–frequency analysis.The thorough model reduction of fractional impedance spectra addressed in the present work not only clarifies the relationship between time-domain transient analysis and frequency-domain stationary analysis but also enhances the reliability of the joint time–frequency analysis for electrochemical energy devices.

An adaptive physics-informed deep learning method for pore pressure prediction using seismic data

Accurate prediction of formation pore pressure is essential to predict fluid flow and manage hydrocarbon production in petroleum engineering.Recent deep learning technique has been receiving more interest due to the great potential to deal with pore pressure prediction.However,most of the traditional deep learning models are less efficient to address generalization problems.To fill this technical gap,in this work,we developed a new adaptive physics-informed deep learning model with high generalization capability to predict pore pressure values directly from seismic data.Specifically,the new model,named CGP-NN,consists of a novel parametric features extraction approach(1DCPP),a stacked multilayer gated recurrent model(multilayer GRU),and an adaptive physics-informed loss function.Through machine training,the developed model can automatically select the optimal physical model to constrain the results for each pore pressure prediction.The CGP-NN model has the best generalization when the physicsrelated metricλ=0.5.A hybrid approach combining Eaton and Bowers methods is also proposed to build machine-learnable labels for solving the problem of few labels.To validate the developed model and methodology,a case study on a complex reservoir in Tarim Basin was further performed to demonstrate the high accuracy on the pore pressure prediction of new wells along with the strong generalization ability.The adaptive physics-informed deep learning approach presented here has potential application in the prediction of pore pressures coupled with multiple genesis mechanisms using seismic data.

A Power Data Anomaly Detection Model Based on Deep Learning with Adaptive Feature Fusion

With the popularisation of intelligent power,power devices have different shapes,numbers and specifications.This means that the power data has distributional variability,the model learning process cannot achieve sufficient extraction of data features,which seriously affects the accuracy and performance of anomaly detection.Therefore,this paper proposes a deep learning-based anomaly detection model for power data,which integrates a data alignment enhancement technique based on random sampling and an adaptive feature fusion method leveraging dimension reduction.Aiming at the distribution variability of power data,this paper developed a sliding window-based data adjustment method for this model,which solves the problem of high-dimensional feature noise and low-dimensional missing data.To address the problem of insufficient feature fusion,an adaptive feature fusion method based on feature dimension reduction and dictionary learning is proposed to improve the anomaly data detection accuracy of the model.In order to verify the effectiveness of the proposed method,we conducted effectiveness comparisons through elimination experiments.The experimental results show that compared with the traditional anomaly detection methods,the method proposed in this paper not only has an advantage in model accuracy,but also reduces the amount of parameter calculation of the model in the process of feature matching and improves the detection speed.

ST-Map:an Interactive Map for Discovering Spatial and Temporal Patterns in Bibliographic Data

Getting insight into the spatiotemporal distribution patterns of knowledge innovation is receiving increasing attention from policymakers and economic research organizations.Many studies use bibliometric data to analyze the popularity of certain research topics,well-adopted methodologies,influential authors,and the interrelationships among research disciplines.However,the visual exploration of the patterns of research topics with an emphasis on their spatial and temporal distribution remains challenging.This study combined a Space-Time Cube(STC)and a 3D glyph to represent the complex multivariate bibliographic data.We further implemented a visual design by developing an interactive interface.The effectiveness,understandability,and engagement of ST-Map are evaluated by seven experts in geovisualization.The results suggest that it is promising to use three-dimensional visualization to show the overview and on-demand details on a single screen.