Dynamic Multi-Layer Perceptron for Fetal Health Classification Using Cardiotocography Data

Fetal health care is vital in ensuring the health of pregnant women and the fetus.Regular check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential problems.To know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,etc.Still,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during pregnancy.Several researchers have proposed various methods for classifying the status of fetus growth.Manual processing of CTG data is time-consuming and unreliable.So,automated tools should be used to classify fetal health.This study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal health.Various strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also illustrated.This study easily provides valuable interpretations for healthcare professionals in the decision-making process.

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related fields.Currently,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean temperature.Existing graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among data.In this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior knowledge.Temporal and spatial dependencies in the time series were then captured using temporal and graph convolutions.We also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid data.In this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea surface.We compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

Adaptive Method’s Application for the Identification Systems in Dynamic Weighing

In this work,the possibility of adaptive algorithm in WIM(weight-in-motion)systems,in which fibre optic sensors are used,is shown.Appointment of dynamic weighing device consists in determining the weight and type of vehicle.In this work an algorithm for processing the input data and fiber optic sensor to create the database used in the algorithm is presented.The results of the algorithm for the identification of vehicles are given.The conclusions are made and options of increasing the accuracy of the identification algorithm are considered.

Stability of Iterative Learning Control with Data Dropouts via Asynchronous Dynamical System

In this paper, the stability of iterative learning control with data dropouts is discussed. By the super vector formulation, an iterative learning control （ILC） system with data dropouts can be modeled as an asynchronous dynamical system with rate constraints on events in the iteration domain. The stability condition is provided in the form of linear matrix inequalities （LMIS） depending on the stability of asynchronous dynamical systems. The analysis is supported by simulations.

基于改进DDS的应答器动态检测系统2FSK调制器设计

基于高速综合检测列车平台的应答器动态检测系统可实现对应答器相关设备性能的实时检测。为测试车载应答器动态检测系统的性能,需产生高精度可控波特率和载频的调制信号(2FSK)作为上行链路信号。基于直接数字频率合成器(DDS)技术,通过对相位累加模块和相幅转换模块进行设计,提出分段相位累加算法,计算同周期内相位增量和码元跳变处的相位增量;通过改进的坐标旋转数字计算方法(CORDIC)实时计算对应的信号幅值,用数字模拟转换器(DAC)将离散信号转换为模拟信号,从而实现频偏和数据速率可变且相位连续的信号调制。在相幅转换模块设计中,采用改进CORDIC算法替代传统的查表法,将相位增量转换成信号幅度,有效减少了现场可编程逻辑门阵列(FPGA)存储资源的开销。基于改进DDS的2FSK调制器设计方法,可为应答器动态检测系统提供高精度可控波特率和载频的2FSK调制信号,保证了应答器动态检测系统校准的准确性。

Obtaining 2D Soil Resistance Profiles from the Integration of Electrical Resistivity Data and Standard Penetration Test (SPT) and Light Dynamic Penetrometer (DPL) Resistance Tests—Applications in Mass Movements Studies

In Brazil and various regions globally, the initiation of landslides is frequently associated with rainfall;yet the spatial arrangement of geological structures and stratification considerably influences landslide occurrences. The multifaceted nature of these influences makes the surveillance of mass movements a highly intricate task, requiring an understanding of numerous interdependent variables. Recent years have seen an emergence in scholarly research aimed at integrating geophysical and geotechnical methodologies. The conjoint examination of geophysical and geotechnical data offers an enhanced perspective into subsurface structures. Within this work, a methodology is proposed for the synchronous analysis of electrical resistivity geophysical data and geotechnical data, specifically those extracted from the Light Dynamic Penetrometer (DPL) and Standard Penetration Test (SPT). This study involved a linear fitting process to correlate resistivity with N10/SPT N-values from DPL/SPT soundings, culminating in a 2D profile of N10/SPT N-values predicated on electrical profiles. The findings of this research furnish invaluable insights into slope stability by allowing for a two-dimensional representation of penetration resistance properties. Through the synthesis of geophysical and geotechnical data, this project aims to augment the comprehension of subsurface conditions, with potential implications for refining landslide risk evaluations. This endeavor offers insight into the formulation of more effective and precise slope management protocols and disaster prevention strategies.

Dynamic Prediction Method for Valuable Spare Parts Demand in Weaponry Equipment Based on Data Perception

Missile is an important weapon system of the army.The spare parts of missile equipment are significant effect on military operations.In order to improve the mission completion rate of missile equipment in wartime,this paper introduces data sensing method to forecast the demand of valuable spare parts of missile equipment dynamically.Firstly,the information related to valuable spare parts of missile equipment was obtained by data sensing,and the sample size was determined by Bernoulli uniform sampling probability.Secondly,according to the data quality of multi-source and multi-modal,the data requirement for dynamic demand prediction of valuable spare parts of missile equipment was obtained.Finally,according to the characteristics of the spare parts,the life of the spare parts was predicted,realizing the dynamic prediction of the demand for valuable spare parts of missile equipment.The results show that the demand of valuable spare parts of missile equipment can be predicted dynamically by using this method,the accuracy is higher than 95%,and the real-time performance is more excellent.

Block Incremental Dense Tucker Decomposition with Application to Spatial and Temporal Analysis of Air Quality Data

How can we efficiently store and mine dynamically generated dense tensors for modeling the behavior of multidimensional dynamic data?Much of the multidimensional dynamic data in the real world is generated in the form of time-growing tensors.For example,air quality tensor data consists of multiple sensory values gathered from wide locations for a long time.Such data,accumulated over time,is redundant and consumes a lot ofmemory in its raw form.We need a way to efficiently store dynamically generated tensor data that increase over time and to model their behavior on demand between arbitrary time blocks.To this end,we propose a Block IncrementalDense Tucker Decomposition(BID-Tucker)method for efficient storage and on-demand modeling ofmultidimensional spatiotemporal data.Assuming that tensors come in unit blocks where only the time domain changes,our proposed BID-Tucker first slices the blocks into matrices and decomposes them via singular value decomposition(SVD).The SVDs of the time×space sliced matrices are stored instead of the raw tensor blocks to save space.When modeling from data is required at particular time blocks,the SVDs of corresponding time blocks are retrieved and incremented to be used for Tucker decomposition.The factor matrices and core tensor of the decomposed results can then be used for further data analysis.We compared our proposed BID-Tucker with D-Tucker,which our method extends,and vanilla Tucker decomposition.We show that our BID-Tucker is faster than both D-Tucker and vanilla Tucker decomposition and uses less memory for storage with a comparable reconstruction error.We applied our proposed BID-Tucker to model the spatial and temporal trends of air quality data collected in South Korea from 2018 to 2022.We were able to model the spatial and temporal air quality trends.We were also able to verify unusual events,such as chronic ozone alerts and large fire events.

Microscopic defects formation and dynamic mechanical response analysis of Q345 steel plate subjected to explosive load

As the basic protective element, steel plate had attracted world-wide attention because of frequent threats of explosive loads. This paper reports the relationships between microscopic defects of Q345 steel plate under the explosive load and its macroscopic dynamics simulation. Firstly, the defect characteristics of the steel plate were investigated by stereoscopic microscope(SM) and scanning electron microscope(SEM). At the macroscopic level, the defect was the formation of cave which was concentrated in the range of 0-3.0 cm from the explosion center, while at the microscopic level, the cavity and void formation were the typical damage characteristics. It also explains that the difference in defect morphology at different positions was the combining results of high temperature and high pressure. Secondly, the variation rules of mechanical properties of steel plate under explosive load were studied. The Arbitrary Lagrange-Euler(ALE) algorithm and multi-material fluid-structure coupling method were used to simulate the explosion process of steel plate. The accuracy of the method was verified by comparing the deformation of the simulation results with the experimental results, the pressure and stress at different positions on the surface of the steel plate were obtained. The simulation results indicated that the critical pressure causing the plate defects may be approximately 2.01 GPa. On this basis, it was found that the variation rules of surface pressure and microscopic defect area of the Q345 steel plate were strikingly similar, and the corresponding mathematical relationship between them was established. Compared with Monomolecular growth fitting models(MGFM) and Logistic fitting models(LFM), the relationship can be better expressed by cubic polynomial fitting model(CPFM). This paper illustrated that the explosive defect characteristics of metal plate at the microscopic level can be explored by analyzing its macroscopic dynamic mechanical response.

A LiDAR Point Clouds Dataset of Ships in a Maritime Environment

For the first time, this article introduces a LiDAR Point Clouds Dataset of Ships composed of both collected and simulated data to address the scarcity of LiDAR data in maritime applications. The collected data are acquired using specialized maritime LiDAR sensors in both inland waterways and wide-open ocean environments. The simulated data is generated by placing a ship in the LiDAR coordinate system and scanning it with a redeveloped Blensor that emulates the operation of a LiDAR sensor equipped with various laser beams. Furthermore,we also render point clouds for foggy and rainy weather conditions. To describe a realistic shipping environment, a dynamic tail wave is modeled by iterating the wave elevation of each point in a time series. Finally, networks serving small objects are migrated to ship applications by feeding our dataset. The positive effect of simulated data is described in object detection experiments, and the negative impact of tail waves as noise is verified in single-object tracking experiments. The Dataset is available at https://github.com/zqy411470859/ship_dataset.

Molecular Dynamics, Physical Properties, Diffusion Coefficients and Activation Energy of the Lithium Oxide (Li-O) and Sodium Oxide (Na-O) Electrolyte (Cathode)

This work is a simulation model with the LAMMPS calculation code of an electrode based on alkali metal oxides (lithium, sodium and potassium) using the Lennard Jones potential. For a multiplicity of 8*8*8, we studied a gap-free model using molecular dynamics. Physical quantities such as volume and pressure of the Na-O and Li-O systems exhibit similar behaviors around the thermodynamic ensembles NPT and NVE. However, for the Na2O system, at a minimum temperature value, we observe a range of total energy values;in contrast, for the Li2O system, a minimum energy corresponds to a range of temperatures. Finally, for physicochemical properties, we studied the diffusion coefficient and activation energy of lithium and potassium oxides around their melting temperatures. The order of magnitude of the diffusion coefficients is given by the relation Dli-O >DNa-O for the multiplicity 8*8*8, while for the activation energy, the order is well reversed EaNa-O > EaLi-O.

The influence of heterogeneous environmental regulation on the green development of the mining industry: empirical analysis based on the system GMM and dynamic panel data model

The intensity of environmental regulation (ERI) affects the short-term effect of the level of green mining (GML),and which structure determines the long-term mechanism.Based on the panel data from 2001 to 2015,with the dynamic panel model and system GMM estimation method were employed to test the influence of heterogeneous environmental regulation on green mining and its transmission mechanism.The results show that,there is a 'U' type nonlinear relationship between the ERI and GML.The direct effect of command-control-based (CAC) and the market incentive-based (MBI) environmental regulation on green development of mining shows the characteristics of inhibition and promotion.There is a 'U' type of indirectly moderating effect between technological innovation and the energy consumption structure on the GML.The technological innovation promotes the green development of the mining industry only after pass the inflection point of MBI,while the CAC plays a significant guiding role in upgrading of the energy consumption structure.There is an inhibition and promotion effect of MBI on the GML in the southeast coastal area,and the CAC is not significantly.Meanwhile,both of the ERI shows no positive effects in the central and western inland region.

Toward development of the 4Dvar data assimilation system in the Bering Sea:reconstruction of the mean dynamic ocean topography

The Bering Sea circulation is derived as a variational inverse of hydrographic profiles（ temperature and salinity） , atmospheric climatologies and historical observation of ocean curents. The important result of this study is estimate of the mean climatological sea surface height （SSH） that can be used as a reference for satellite altimetry sea level anomaly data in the Bering Sea region. Numerical experiments reveal that, when combined with satellite altimetry, the obtained reference SSH effectively constrains a realistic reconstruction of the Amukta Pass circulation.

Optimizing Memory Access Efficiency in CUDA Kernel via Data Layout Technique

Over the past decade, Graphics Processing Units (GPUs) have revolutionized high-performance computing, playing pivotal roles in advancing fields like IoT, autonomous vehicles, and exascale computing. Despite these advancements, efficiently programming GPUs remains a daunting challenge, often relying on trial-and-error optimization methods. This paper introduces an optimization technique for CUDA programs through a novel Data Layout strategy, aimed at restructuring memory data arrangement to significantly enhance data access locality. Focusing on the dynamic programming algorithm for chained matrix multiplication—a critical operation across various domains including artificial intelligence (AI), high-performance computing (HPC), and the Internet of Things (IoT)—this technique facilitates more localized access. We specifically illustrate the importance of efficient matrix multiplication in these areas, underscoring the technique’s broader applicability and its potential to address some of the most pressing computational challenges in GPU-accelerated applications. Our findings reveal a remarkable reduction in memory consumption and a substantial 50% decrease in execution time for CUDA programs utilizing this technique, thereby setting a new benchmark for optimization in GPU computing.

Sensitivity of Coupled Chaotic Dynamical System to Parameters in the Context of Data Assimilation

In this paper, a numerical modeling tool is described which can be used to explore various aspects of four dimensional variational data assimilation and parameter estimation arising in geophysical, environmental, biological and engineering sciences. A major component of this tool is a coupled chaotic dynamical system obtained by coupling two versions of the well-known Lorenz （1963） model with different time scales which differ by a certain time-scale factor. A tangent linear model and its adjoint are considered that correspond to a coupled chaotic system. The general idea of applying sensitivity measures （sensitivity functions） to coupled systems, emphasizing the data assimilation aspects, is explored as well by the forward sensitivity approach. For this purpose the set of sensitivity equations is derived from the nonlinear equations of the coupled dynamical system. To estimate the influence of model parameter uncertainties on the simulated state variables the relative error in the energy norm is used.

ARCHITECTURE OF DYNAMIC DATA DRIVEN SIMULATION FOR WILDFIRE AND ITS REALIZATION

Dynamic data driven simulation （DDDS） is proposed to improve the model by incorporaing real data from the practical systems into the model. Instead of giving a static input, multiple possible sets of inputs are fed into the model. And the computational errors are corrected using statistical approaches. It involves a variety of aspects, including the uncertainty modeling, the measurement evaluation, the system model and the measurement model coupling ,the computation complexity, and the performance issue. Authors intend to set up the architecture of DDDS for wildfire spread model, DEVS-FIRE, based on the discrete event speeification （DEVS） formalism. The experimental results show that the framework can track the dynamically changing fire front based on fire sen- sor data, thus, it provides more aecurate predictions.

DynamicData在邮政业市场监管系统中的应用

本文通过ASP.NET动态数据Dynamic Data在邮政业市场监管系统中的应用,探索VS2008和ASP.NET3.5 Extensions Preview的Web开发的新特点。

Simulation of Dynamic Electromagnetic Interference Environment for Unmanned Aerial Vehicle Data Link

In order to test the anti-interference ability of an Unmanned Aerial Vehicle(UAV) data link in a complex electromagnetic environment,a method for simulating the dynamic electromagnetic interference of an indoor wireless environment is proposed.This method can estimate the relational degree between the actual face of an UAV data link in an interface environment and the simulation scenarios in an anechoic chamber by using the Grey Relational Analysis(GRA) theory.The dynamic drive of the microwave instrument produces a real-time corresponding interference signal and realises scene mapping.The experimental results show that the maximal correlation between the interference signal in the real scene and the angular domain of the radiation antenna in the anechoic chamber is 0.959 3.Further,the relational degree of the Signal-toInterference Ratio(SIR) of the UAV at its reception terminal indoors and in the anechoic chamber is 0.996 8,and the time of instrument drive is only approximately 10 μs.All of the above illustrates that this method can achieve a simulation close to a real field dynamic electromagnetic interference signal of an indoor UAV data link.

A Novel Robust Nonlinear Dynamic Data Reconciliation

Outlier in one variable will smear the estimation of other measurements in data reconciliation （DR）. In this article, a novel robust method is proposed for nonlinear dynamic data reconciliation, to reduce the influence of outliers on the result of DR. This method introduces a penalty function matrix in a conventional least-square objective function, to assign small weights for outliers and large weights for normal measurements. To avoid the loss of data information, element-wise Mahalanobis distance is proposed, as an improvement on vector-wise distance, to construct a penalty function matrix. The correlation of measurement error is also considered in this article. The method introduces the robust statistical theory into conventional least square estimator by constructing the penalty weight matrix and gets not only good robustness but also simple calculation. Simulation of a continuous stirred tank reactor, verifies the effectiveness of the proposed algorithm.

Differential Privacy Preserving Dynamic Data Release Scheme Based on Jensen-Shannon Divergence

Health monitoring data or the data about infectious diseases such as COVID-19 may need to be constantly updated and dynamically released,but they may contain user's sensitive information.Thus,how to preserve the user's privacy before their release is critically important yet challenging.Differential Privacy(DP)is well-known to provide effective privacy protection,and thus the dynamic DP preserving data release was designed to publish a histogram to meet DP guarantee.Unfortunately,this scheme may result in high cumulative errors and lower the data availability.To address this problem,in this paper,we apply Jensen-Shannon(JS)divergence to design the OPTICS(Ordering Points To Identify The Clustering Structure)scheme.It uses JS divergence to measure the difference between the updated data set at the current release time and private data set at the previous release time.By comparing the difference with a threshold,only when the difference is greater than the threshold,can we apply OPTICS to publish DP protected data sets.Our experimental results show that the absolute errors and average relative errors are significantly lower than those existing works.