Three-layer Model Research Articles

Проектирование состава высокопрочного самоуплотняющегося бетона с использованием нейронной сети

Purpose: To extend the possibility of interpreting the results of a limited number of physical experiments while selecting the components for the creation of concrete mixes and concrete on its basis with the required output properties. Methods: Using a neural network in the analytical environment Loginom, a model with six input variables representing introduced special additives and seven output variables representing the quality parameters of the concrete mix and concrete has been built. Results: In the process of training a three-layer network model has been formed, with the help of which the predicted output characteristics of concrete mix and concrete have been obtained. Experimental data and neural model prediction for each output variable have been compared in a clear graphical form. Practical significance: Prediction of the required characteristics of the synthesized material by means of the neural model response to various combinations of input data allows to carry out an optimal number of physical experiments. It is possible to apply the proposed modeling method for various multicomponent materials.

Deep learning-based vibration stress and fatigue-life prediction of a battery-pack system

The primary concerns of the automotive industry are structural integrity and battery-pack system (BPS) reliability. To ascertain the appropriate thickness of critical BPS components (e.g., the long bracket, crossbeam, and bottom shell), engineers are required to perform several simulations of finite element (FE) analysis. This procedure is laborious and requires a significant amount of time. This study introduces a very effective approach for predicting vibration-induced stress and fatigue life, intending to enhance dependability in the design process. Firstly, a three-layer lithium battery model is utilized to investigate the impact of vibration on the maximal Mises stress at various states of charge. This information is used to model the BPS, including the batteries. The nonlinear FE model of the BPS is validated using the modal test results. Secondly, a sensitivity analysis is performed to ascertain the impact of component thickness on the maximum Mises stress. For vibration simulations, multiple design variables are selected to collect data. Next, the nonlinear relationship between inputs (thicknesses of critical components) and outputs (maximum Mises stress and minimum fatigue life) is described using a deep learning (DL) modeling framework with forward and backward propagation. Finally, the accuracy of the DL model is assessed by measuring error functions and comparing its performance to six commonly employed methods. Furthermore, the inclusion of Gaussian noise is employed to assess the model’s robustness and ability to generalize. Additionally, the establishment of fatigue-life and stress boundaries serves to offer designers valuable insights. The results indicate that the proposed method for predicting vibration stress and fatigue life is highly efficient and cost-effective, making it useful for the design of a robust and reliable BPS.

Comparison of diffuse correlation spectroscopy analytical models for measuring cerebral blood flow in adults.

Although multilayer analytical models have been proposed to enhance brain sensitivity of diffuse correlation spectroscopy (DCS) measurements of cerebral blood flow, the traditional homogeneous model remains dominant in clinical applications. Rigorous in vivo comparison of these analytical models is lacking. We compare the performance of different analytical models to estimate a cerebral blood flow index (CBFi) with DCS in adults. Resting-state data were obtained on a cohort of 20 adult patients with subarachnoid hemorrhage. Data at 1 and 2.5cm source-detector separations were analyzed with the homogenous, two-layer, and three-layer models to estimate scalp blood flow index and CBFi. The performance of each model was quantified via fitting convergence, fit stability, brain-to-scalp flow ratio (BSR), and correlation with transcranial Doppler ultrasound (TCD) measurements of cerebral blood flow velocity in the middle cerebral artery (MCA). The homogeneous model has the highest pass rate (100%), lowest coefficient of variation (CV) at rest (median [IQR] at 1Hz of 0.18 [0.13, 0.22]), and most significant correlation with MCA blood flow velocities (, ) compared with both the two- and three-layer models. The multilayer model pass rate was significantly correlated with extracerebral layer thicknesses. Discarding datasets with non-physiological BSRs increased the correlation between DCS measured CBFi and TCD measured MCA velocities for all models. We found that the homogeneous model has the highest pass rate, lowest CV at rest, and most significant correlation with MCA blood flow velocities. Results from the multilayer models should be taken with caution because they suffer from lower pass rates and higher coefficients of variation at rest and can converge to non-physiological values for CBFi. Future work is needed to validate these models in vivo, and novel approaches are merited to improve the performance of the multimodel models.

Integrated multitrophic aquaculture supply chain fish traceability with blockchain technology, valorisation of fish waste and plastic pollution reduction by seaweed bioplastic: A study in tuna fish aquaculture industry

The high demand for tuna, coupled with unsustainable supply chain practices, has triggered illegal fishing, overfishing, and environmental damage, including bycatch, pollution, and climate change impacts. To address these issues, the world urgently needs sustainable alternatives to meet tuna demand while preserving our oceans, marine species, and the environment. In this paper, a sustainable three-layer tuna fish supply chain model consisting of a single farmer, processor, and retailer is developed for two different quality levels of tuna fish. Green technology and integrated multi-trophic aquaculture (IMTA) methods are implemented at the farmer stage to reduce emissions and ocean pollution. Fish waste utilization technology, seaweed bioplastic packaging technology, and green technologies are implemented at the processor stage to reduce fish waste, plastic pollution, and carbon emissions. Blockchain technology is implemented for the traceability and transparency of the whole supply chain in order to avoid illegal and unsustainable tuna fish entering the market. The optimal solutions of the average integrated total profit are found by using the particle swarm optimization (PSO) algorithm in Python platform. The farmer's and processor's emission costs are reduced by 80% by investing in green technology. The transportation cost is also reduced. The fish waste utilization and plastic waste minimization costs of processors are reduced by more than 95% by investing in fish waste utilization and seaweed bioplastic packaging technology. The concavity of the average integrated total profit function is shown in a 3D graph. The optimal solution, sensitivity analysis, numerical examples, and managerial implications are presented for the tuna fish supply industries. The proposed model is applicable to any food processing industry.

Differential interactions between natural clay minerals and dissolved organic matter affect reactive oxygen species formation

Naturally occurring reactive oxygen species (ROS) are widely involved in many environmental processes. Here we investigated the ROS generation associated with the interaction between complexed natural clay minerals (CMs) and dissolved organic matter (DOM). Our results showed that among the nine chemical-reduced CMs (CR-CMs), the light brown CR-CM (CR-CM 7) generated the highest ROS via oxygenation, relying on the reactive structural Fe(II) (Fe species that can transfer electrons to oxygen) instead of total structural Fe(II) as previously reported. Moreover, DOM affected the oxygenation of CR-CMs differently. The tight interaction between DOM and CR-CM 7 formed DOM-complexed Fe, while the weak interaction between DOM and the dark gold CR-CM (CR-CM 1) and the black CR-CM (CR-CM 5) exhibited decreased efficiencies. Mechanism studies revealed that ROS were generated through three pathways but all followed a similar one-electron transfer process in the presence of DOM. We further developed a three-layer geobattery model system and demonstrated that long electron transfer driven by CR-CMs/DOM could extend ROS generation to several centimetres across the oxic-anoxic interface, even without redox switching. These findings offer new insights into CMs-involved ROS generation and associated organic matter transformation in natural environments.

Q-compensated wavefield depth extrapolation-based migration using a viscoacoustic wave equation

In a viscoacoustic medium, intrinsic attenuation causes seismic wavefields to attenuate in amplitude and become dispersed in phase, leading to distorted structural imaging and inaccurate migrated amplitudes. To address this problem, viscoacoustic reverse time migration corrects for dispersion and amplitude attenuation effects in wavefield propagation in forward and backward directions. To provide a parallel alternative approach, the time fractional derivative viscoacoustic wave equation in the depth domain is solved and a Q-compensated wavefield depth extrapolation scheme is established to compensate for viscoacoustic effects during recursive wavefield depth extrapolation. This approach decouples the amplitude attenuation and phase dispersion effects from the viscoacoustic vertical wavenumber. To suppress high wavenumber components and address the problem of exponential amplitude growth during wavefield depth extrapolation, we limit the imaginary part of the vertical wavenumber in the frequency wavenumber domain and use an adaptive stabilization solution. Numerical experiments of impulse responses in a viscoacoustic isotropic medium demonstrate that our proposed scheme can observe calculated wavefields exhibiting amplitude attenuation and phase dispersion effects in comparison to wavefields of the acoustic medium, indicating good agreement with theoretical expectations. We also demonstrate the capability of our proposed scheme to recover imaging amplitudes through a variety of numerical experiments, such as imaging of three-layer, Marmousi, and BP gas reservoir models. The results indicate that our proposed scheme can recover amplitude attenuation and phase dispersion effects more accurately than acoustic migration. We also use marine seismic data featuring natural gas hydrates to indicate that our proposed Q-compensated scheme can generate an enhanced imaging result, especially for the bottom simulating reflectors, compared with the conventional imaging algorithm without Q-compensation.

Energy Management and Networking for Sensor-based Transmission Line State Monitoring

The transmission line condition monitoring sensor network is large in scale and difficult to maintain. Its long-chain network topology differs from general wireless sensor networks, so it is necessary to develop a self-organizing sensor network with self-energy harvesting. In this regard, a three-layer network model is designed. Three types of node models are constructed. The sensor nodes implement round-robin sleep/wake and energy management mechanisms, powered by self-harvested energy. Additionally, reliable routing between nodes is established. Simulation results show that the developed simulation model is suitable for the application of transmission line condition monitoring. The expected functions of each module have been realized, and the stable and reliable transmission of perceived data of key components of transmission lines has been achieved, thereby providing technical and data basis for the deployment of practical networks.

Ice ridge evolution: Investigation in-situ and computer simulations

The article presents a two-dimensional three-layer non-stationary thermodynamic model allowing to calculate the annual variation (thermodynamic evolution) of the ice ridge using external meteorological and hydrological parameters as well as the information on the initial ice ridge porosity. For the test model simulation, the results of the study of morphometric characteristics of the ice ridge carried out in May-June 2011 and in April 2012 at « North Pole −38» and «North Pole −39» drifting stations were used. These studies were conducted using electric thermal drilling with computer recording of the penetration rate. Boreholes were drilled along the cross-section of the ridge crest at 0.5 m intervals. Cross-sectional profiles of ice ridge are illustrated. Applying the proposed model, it was possible to adequately reproduce the observed evolutionary changes in the main morphometric parameters (sail height, keel depth, thickness of the consolidated layer) of the investigated ice ridge.

Modeling the lane-changing behavior of non-motorized vehicles on road segments via social force model

Using traffic marking to separate non-motorized lane from the adjacent motorized lane is a common traffic design method for urban road segments. With the increase in non-motorized vehicle flow, illegal lane-changing occurs frequently, which leads to more serious conflict among road users. The study of the behavior characteristics of non-motorized illegal lane-changing on road segments, and establishing a microscopic simulation model can be used as a theoretical support and analysis tool for the design of non-motorized lane. This paper takes non-motorized vehicles as the research object to study lane-changing behavior characteristics. Then, the K-means clustering algorithm is used to classify riding styles into three types: risker, opportunist, and prudent. The micro-behavioral characteristics of riders with different riding styles are analyzed. Next, a three-layer model framework composed of perceptual, decision-making, and social force model is established. The logit model is used in the decision-making model to predict the probability of non-motorized vehicles crossing the line. Different riding styles are considered in the social force, and a virtual boundary force is introduced to describe lane-changing behavior. Subsequently, parameters are calibrated and the model is validated in various ways. Finally, the proposed model is used to conduct simulation experiments to explore the renovation scheme of the non-motorized lane. The results show that the proposed model can reproduce the traffic operation in the real scenario.

The effects of precipitation change on urban meadows in different design models and substrates

Climate change, such as temperature and precipitation changes, is becoming increasingly obvious, and in this context, planting designs need to urgently consider future climate change in advance. A field experiment was conducted in Beijing, China, where the future precipitation is predicted to increase, and extra irrigation was used to simulate the future precipitation increase. The species richness of sown meadows, including spontaneous plants and sown plants, and the adaptive strategies of the communities were recorded under different types of design models and substrates. The results showed that precipitation increased the diversity of sown plants and resource-demanding spontaneous plants but had no significant effect on the dry matter content of the entire community of species. Moreover, the interactions among precipitation and substrate, especially the design models, were significant. Of the models, the three-layer model had the highest species richness and least invasive plants. In addition, increased precipitation significantly changed the functional strategy of the plant community away from ruderals and towards competitor-stress tolerant species. This study provides guidance for the design and management of naturalistic plant communities under climate change.

LSTM time series NDVI prediction method incorporating climate elements: A case study of Yellow River Basin, China

Accurate prediction of the trend of Normalized Difference Vegetation Index (NDVI) time series in the Yellow River Basin (YRB) is crucial for the assessment of the hydrological and ecological environment in this region. Currently, the NDVI time series prediction model is primarily based on traditional models and single-variable neural network models. Nevertheless, these models present challenges in considering the limitations of multiple factors, causing the NDVI time series prediction results to lack reliability. To predict NDVI time-series in the YRB of China, this study constructed a multilayer multivariate Long-Short Term Memory (LSTM) neural network model including climatic components. The initial important climatic elements in this region were identified using GeoDetector. Then, the relationship between NDVI and climatic factors in the YRB of China is established. Finally, numerical scale data are used to train and predict a multilayer multivariate LSTM model with climatic components. According to the results, the three-layer multivariate LSTM neural network NDVI time series prediction model developed in this study has the best performance among the evaluated indices. When compared to existing time series prediction models, the proposed model in this study takes into account the common constraint effect of various climate factors on NDVI. This leads to a significantly improved prediction accuracy, presenting new opportunities for enhancing the prediction model. By analyzing the NDVI time series prediction outcomes for the YRB, it has been determined that the ecological environment of the area will continuously improve in the future. This study offers significant technological and theoretical backing for assessing the hydrological and ecological environment of the YRB and comparable ecologically vulnerable regions in China.

Absorption and reduced scattering coefficients in epidermis and dermis from a Swedish cohort study.

Knowledge of optical properties is important to accurately model light propagation in tissue, but in vivo reference data are sparse. The aim of our study was to present in vivo skin optical properties from a large Swedish cohort including 3809 subjects using a three-layered skin model and spatially resolved diffuse reflectance spectroscopy (Periflux PF6000 EPOS). Diffuse reflectance spectra (475 to 850nm) at 0.4 and 1.2mm source-detector separations were analyzed using an inverse Monte Carlo method. The model had one epidermis layer with variable thicknesses and melanin-related absorptions and two dermis layers with varying hemoglobin concentrations and equal oxygen saturations. The reduced scattering coefficient was equal across all layers. Median absorption coefficients () in the upper dermis ranged from 0.094 at 475nm to 0.0048 at 850nm and similarly in the lower dermis from 0.059 to 0.0035. The reduced scattering coefficient () ranged from 3.22 to 1.20, and the sampling depth (mm) ranged from 0.23 to 0.38 (0.4mm separation) and from 0.49 to 0.68 (1.2mm separation). There were differences in optical properties across sex, age groups, and BMI categories. Reference material for skin optical properties is presented.

A three-layer model of hydrodynamic processes in the Cyprus Eddy system

A three-layer model of hydrodynamic processes in the Cyprus Eddy system

Designing a Compact Dual-Band, Dual-Polarized Antenna for Biotelemetry Communications Using the Characteristic Mode Method.

A compact dual-band, dual-polarized, implantable antenna was designed using the characteristic mode method for operation in the wireless medical telemetry service (WMTS) band (1.4 GHz) and the industrial, scientific, and medical (ISM) band (2.45 GHz). By utilizing slotting techniques and materials with high dielectric constants, the antenna volume was minimized to 47.4 mm3, and circular polarization was gained in the WMTS band by using the characteristic mode method. A three-layer physical model of human tissues was constructed in a simulation, and a biogel and minced pork were used in the measurements. The measured peak gains are -20.85 dBi (1.4 GHz) and -22.15 dBi (2.45 GHz). The measured effective axis ratio bandwidth in the WMTS band is 170 MHz (1.33-1.50 GHz, 12.0%), and the impedance bandwidth in the ISM band is 390 MHz (2.21-2.60 GHz, 16.2%). At 1.4 GHz and 2.45 GHz, the largest 1 g average SAR values are 376 W/Kg and 318 W/Kg, which comply with IEEE C95.1-1999. Moreover, when the communication chain affinity exceeds 20 dB for 1.4 GHz and 2.4 GHz, the transceiver range reaches 8.2 m and 9.7 m. This antenna can be used for implantable wireless telemetry systems.

Light-Stimulated IGZO Transistors with Tunable Synaptic Plasticity Based on Casein Electrolyte Electric Double Layer for Neuromorphic Systems.

In this study, optoelectronic synaptic transistors based on indium-gallium-zinc oxide (IGZO) with a casein electrolyte-based electric double layer (EDL) were examined. The casein electrolyte played a crucial role in modulating synaptic plasticity through an internal proton-induced EDL effect. Thus, important synaptic behaviors, such as excitatory post-synaptic current, paired-pulse facilitation, and spike rate-dependent and spike number-dependent plasticity, were successfully implemented by utilizing the persistent photoconductivity effect of the IGZO channel stimulated by light. The synergy between the light stimulation and the EDL effect allowed the effective modulation of synaptic plasticity, enabling the control of memory levels, including the conversion of short-term memory to long-term memory. Furthermore, a Modified National Institute of Standards and Technology digit recognition simulation was performed using a three-layer artificial neural network model, achieving a high recognition rate of 90.5%. These results demonstrated a high application potential of the proposed optoelectronic synaptic transistors in neuromorphic visual systems.

Numerical modeling of vadose zone electrical resistivity to evaluate its hydraulic parameters

Studying and determining the physical properties and hydraulic parameters of vadose zone sediments is an important key to evaluate the infiltration rate into them and assessing the extent to which aquifer sediments benefit from rainwater harvesting in arid and semi-arid areas. Due to the lack of sufficient data on the characteristics of this zone depths, a numerical modeling was used to simulate the electrical resistivity of these sediments by applying the electrical resistivity method, because it is the most affected by the physical properties of dry and wet sediments. This study was applied as a proposal for application in northwestern KSA to calculate the vertical hydraulic conductivity and transmissivity for the vadose zone. This was implemented by assuming a three-layer model using COMSOL Multiphysics model with different electrical resistivity values depending on some in situ electrical resistivity measurements for shallow depths. Hence, the infiltration rate of sediments in this area can be predicted with depth and its effect on aquifer recharge. The focus was on calculating the vertical hydraulic parameters of the most widespread surface sediments with depth and comparing the results of calculating these parameters for some sediments laboratory-wise to ensure their accuracy. Then, their infiltration rate was inferred separately with depth, predicting their ability to aquifer recharge and make the most of rainwater harvesting. Finally, this study can be considered as a preliminary study to determine the expected forward model of electrical resistivity and hydraulic parameters values for the vadose zone sediments with depth along the area and in any other areas, and then apply them accurately in situ to estimate the extent of its usefulness in rainwater harvesting, especially aquifer recharge.

Fresh Water and Atmospheric Cooling Control on Density-Compensated Overturning in the Labrador Sea

Abstract As they rim the basin from the southern tip of Greenland to the southern Labrador coast, the waters in the Labrador Sea boundary current undergo a significant transformation in salinity and temperature, but much less so in density. Motivated by these observations, a previously developed simple three-layer model is adapted to understand the processes responsible for this density-compensated overturning in the Labrador Sea. From our model simulations, we find that the density-compensating water mass transformation in the boundary current can be largely attributed to the combined effect of 1) direct atmospheric cooling of the relatively warm boundary current and 2) freshening due to mixing with the shallower and fresh waters derived from Greenland meltwater discharge and Arctic Ocean inflow. Freshening of the boundary current waters due to the excess of precipitation over evaporation in the basin has an important, but less impactful, role in the density compensation. Studies examining the sensitivity of the density compensation to the freshwater entry location reveal a larger impact when the freshwater enters the boundary current on the Greenland side of the basin, compared to the Labrador side. These results yield insights into how increasing meltwater in the subpolar North Atlantic will affect the overturning.

Joint Inversion of Gravity and Magnetic Anomalies to Image Salt–Basement Structures Offshore Abu Dhabi, UAE, Using Deep Neural Networks

Summary By using a deep neural network (DNN), a novel technique is developed for a 2.5D joint inversion of gravity and magnetic anomalies to model subsurface salts and basement structures. The joint application of gravity and magnetic anomalies addresses the inherent nonuniqueness problem of geophysical inversions. Moreover, DNN is used to conduct the nonlinear inverse mapping of gravity and magnetic anomalies to depth-to-salt and depth-to-basement. To create the training data set, a three-layer forward model of the subsurface is designed indicating sediments, salts, and the basement. The length and height of the model are determined based on the dimensions of the target area to be investigated. Several random parameters are set to create different representations of the forward model by altering the depth and shape of the layers. Given the topography of the salts and basement layers as well as their predefined density and susceptibility values, the gravity and magnetic anomalies of the forward models are calculated. Using multiprocessing algorithms, thousands of training examples are simulated comprising gravity and magnetic anomalies as input features and depth-to-salt and depth-to-basement as labels. The application of the proposed technique is evaluated to interpret the salt–basement structures over hydrocarbon reservoirs in offshore United Arab Emirates (UAE). Correspondingly, a DNN model is trained using the simulated data set of the target region and is assessed by making predictions on the random actual and noise-added synthetic data. Finally, gravity-magnetic anomalies are fed into the DNN inverse model to estimate the salts and basement structures over three profiles. The results proved the capability of our technique in modeling the subsurface structures.

Obtaining extended insight into molecular systems by probing multiple pathways in second-order nonlinear spectroscopy.

Second-order nonlinear spectroscopy is becoming an increasingly important technique in the study of interfacial systems owing to its marked ability to study molecular structures and interactions. The properties of such a system under investigation are contained within their intrinsic second-order susceptibilities which are mapped onto the measured nonlinear signals (e.g. sum-frequency generation) through the applied experimental settings. Despite this yielding a plethora of information, many crucial aspects of molecular systems typically remain elusive, for example the depth distributions, molecular orientation and local dielectric properties of its constituent chromophores. Here, it is shown that this information is contained within the phase of the measured signal and, critically, can be extracted through measurement of multiple nonlinear pathways (both the sum-frequency and difference-frequency output signals). Furthermore, it is shown that this novel information can directly be correlated to the characteristic vibrational spectra, enabling a new type of advanced sample characterization and a profound analysis of interfacial molecular structures. The theory underlying the different contributions to the measured phase of distinct nonlinear pathways is derived, after which the presented phase disentanglement methodology is experimentally demonstrated for model systems of self-assembled monolayers on several metallic substrates. The obtained phases of the local fields are compared to the corresponding phases of the nonlinear Fresnel factors calculated through the commonly used theoretical model, the three-layer model. It is found that, despite its rather crude assumptions, the model yields remarkable similarity to the experimentally obtained values, thus providing validation of the model for many sample classes.

Stock price prediction on Australian companies under Chinas trade restriction based on the LSTM model

The volatility of Australian companies' stock prices in 2020, caused by China's trade restrictions, poses a significant challenge for predicting financial gain or loss. This research contributes to future scholarship in predicting stock prices under specific circumstances or during special time periods. The study proposes a novel approach to stock price prediction, incorporating news sentiment analysis into a deep learning model. The research collected news items potentially affecting the stock price, incorporating them into an analysis model to generate a new feature for the Long Short-Term Memory (LSTM) model. The LSTM model used in this study was bidirectional, with two sets of gates per layer, and a three-layer model with different units. Each layer employed a dropout layer and a dense layer in the final stage. The study also utilized the feature engineering of lookback, selecting a window of time in the past to predict the next day's stock prices. Following multiple hyperparameter tunings and feature engineering adjustments, the results and graphs demonstrate a successful prediction for all three of the chosen companies, even during an unstable stock market. The overall trend lines achieve optimal predictions for the stock prices, illustrating both upward and downward trends.