Explore the vast range of titles available.

A second edition of the bestselling guide to exploring and mastering deep learning with Keras, updated to include TensorFlow 2.x with new chapters on object detection, semantic segmentation, and unsupervised learning using mutual information.

From the Internet to networks of friendship, disease transmission, and even terrorism, the concept--and the reality--of networks has come to pervade modern society. But what exactly is a network? What different types of networks are there? Why are they interesting, and what can they tell us? In recent years, scientists from a range of fields--including mathematics, physics, computer science, sociology, and biology--have been pursuing these questions and building a new \"science of networks.\" This book brings together for the first time a set of seminal articles representing research from across these disciplines. It is an ideal sourcebook for the key research in this fast-growing field. The book is organized into four sections, each preceded by an editors' introduction summarizing its contents and general theme. The first section sets the stage by discussing some of the historical antecedents of contemporary research in the area. From there the book moves to the empirical side of the science of networks before turning to the foundational modeling ideas that have been the focus of much subsequent activity. The book closes by taking the reader to the cutting edge of network science--the relationship between network structure and system dynamics. From network robustness to the spread of disease, this section offers a potpourri of topics on this rapidly expanding frontier of the new science.

The unprecedented hydraulic visibility of rivers surfaces deformation with SWOT satellite offers tremendous information for improving hydrological‐hydraulic models and discharge estimations for rivers worldwide. However, estimating the uncertain or unknown parameters of hydraulic models, such as inflow discharges, bathymetry, and friction parameters, poses a high‐dimensional inverse problem, which is ill‐posed if based solely on altimetry observations. To address this, we couple the hydraulic model with a semi‐distributed hydrological model, to constrain the ill‐posed inverse problem with sufficiently accurate initial estimates of inflows at the network upstreams. A robust variational data assimilation of water surface elevation (WSE) data into a 1D Saint‐Venant river network model, enables the inference of inflow hydrographs, effective bathymetry, and spatially distributed friction at network scale. The method is demonstrated on the large, complex, and poorly gauged Maroni basin in French Guiana. The pre‐processing chain enables (a) building an effective hydraulic model geometry from drifting ICESat‐2 WSE altimetry and Sentinel‐1 width; (b) filtering noisy SWOT Level 2 WSE data before assimilation. A systematic improvement is achieved in fitting the assimilated WSE (85% cost improvement), and in validating discharge at 5 gauges within the network. For assimilation of SWOT data alone, 70% of data‐model fit is in [−0.25;0.25m]$[-0.25;\\,0.25\\,\\mathrm{m}]$and the discharge NRMSE ranges between 0.05 and 0.18 (18%–71% improvement from prior). The high density of SWOT WSE enables the inferrence of detailed spatial variability in channel bottom elevation and friction, and inflows timeseries. The approach is transferable to other rivers networks worldwide.

The capillary pressure curve is essential for predicting multiphase flow processes in geological systems. At low saturations, wetting films form and become important, but how wetting films control this curve remains inadequately understood. In this study, we combine microfluidic experiments with pore‐network modeling to investigate the impact of corner‐bridge flow on the capillary pressure curve in porous media. Using a CMOS camera and a confocal laser scanning microscopy, we directly observe the corner‐bridge flow under quasi‐static drainage displacement, revealing that corner‐bridge flow serves as an additional flow path to drain trapped water. Consequently, the capillary pressure curve shifts toward lower saturations, resulting in a reduced water residual saturation. We establish a theoretical criterion for the occurrence of corner‐bridge flow and develop a pore‐network model to simulate quasi‐static drainage, taking into account this additional flow path. Pore‐network modeling results agree well with our experimental observation. On this basis, we employ our pore‐network model to systematically analyze the impact of corner‐bridge flow on capillary pressure curve across varying porosity, pore‐scale disorder, and system size. Results indicate that the impact of corner‐bridge flow becomes more pronounced as porosity decreases and shape factor increases. Our findings demonstrate that the maximum decrease of water residual saturation is 0.19 when porosity is at its minimum, and the shape factor is at its maximum. This work bridges the gap between the pore‐scale mechanism and capillary pressure behavior and has significant implications for estimating the amount of extractable water and the CO2 storage capacity. Key Points We directly observe the corner‐bridge flow serving as an additional flow path to drain the trapped water during quasi‐static drainage The corner‐bridge flow causes a shift of capillary pressure curve toward low saturation and reduces residual water saturation Sw,res The impact of corner‐bridge flow intensifies as porosity decreases and shape factor increases, with a maximum decrease in Sw,res of 0.19

In this research, our main goal was to improve power load forecasting accuracy by considering the impact of meteorological factors on the total power of the electrical system, examining existing load data, local weather, wind direction, and other parameters affecting total power load. We divided the data from the past three years into a training dataset, comprising 75% of the data, and a testing dataset with the remaining 25%. We employed a basic machine learning technique (Support Vector Machine) and three distinct neural network approaches (Artificial Neural Network, Convolutional Neural Network, and Long-Short Term Memory Network) to develop analytical models. Through experimentation, the LSTM model achieved a loss value of 0.0034 and required 1426.78 seconds of training time across 100 epochs. Considering the time expense and model complexity, we chose the LSTM model to forecast power load at 15-minute intervals for the subsequent ten days, achieving a satisfactory prediction and fitting outcome. Our results suggest that the LSTM model is a promising method for optimizing performance and reliability in electrical power systems.

Coal production often involves a substantial presence of gangue and foreign matter, which not only impacts the thermal properties of coal and but also leads to damage to transportation equipment. Selection robots for gangue removal have garnered attention in research. However, existing methods suffer from limitations, including slow selection speed and low recognition accuracy. To address these issues, this study proposes an improved method for detecting gangue and foreign matter in coal, utilizing a gangue selection robot with an enhanced YOLOv7 network model. The proposed approach entails the collection of coal, gangue, and foreign matter images using an industrial camera, which are then utilized to create an image dataset. The method involves reducing the number of convolution layers of the backbone, adding a small size detection layer to the head to enhance the small target detection, introducing a contextual transformer networks (COTN) module, employing a distance intersection over union (DIoU) loss border regression loss function to calculate the overlap between predicted and real frames, and incorporating a dual path attention mechanism. These enhancements culminate in the development of a novel YOLOv71 + COTN network model. Subsequently, the YOLOv71 + COTN network model was trained and evaluated using the prepared dataset. Experimental results demonstrated the superior performance of the proposed method compared to the original YOLOv7 network model. Specifically, the method exhibits a 3.97% increase in precision, a 4.4% increase in recall, and a 4.5% increase in mAP0.5. Additionally, the method reduced GPU memory consumption during runtime, enabling fast and accurate detection of gangue and foreign matter.

The growing demand for precise and reliable biomarkers in psychiatry is fueling research interest in the hope that identifying quantifiable indicators will improve diagnoses and treatment planning across a range of mental health conditions. The individual properties of brain networks at rest have been highlighted as a possible source for such biomarkers, with the added advantage that they are relatively straightforward to obtain. However, an important prerequisite for their consideration is their reproducibility. While the reliability of resting‐state (RS) measurements has often been studied at standard field strengths, they have rarely been investigated using ultrahigh‐field (UHF) magnetic resonance imaging (MRI) systems. We investigated the intersession stability of four functional MRI RS parameters—amplitude of low‐frequency fluctuations (ALFF) and fractional ALFF (fALFF; representing the spontaneous brain activity), regional homogeneity (ReHo; measure of local connectivity), and degree centrality (DC; measure of long‐range connectivity)—in three RS networks, previously shown to play an important role in several psychiatric diseases—the default mode network (DMN), the central executive network (CEN), and the salience network (SN). Our investigation at individual subject space revealed a strong stability for ALFF, ReHo, and DC in all three networks, and a moderate level of stability in fALFF. Furthermore, the internetwork connectivity between each network pair was strongly stable between CEN/SN and moderately stable between DMN/SN and DMN/SN. The high degree of reliability and reproducibility in capturing the properties of the three major RS networks by means of UHF‐MRI points to its applicability as a potentially useful tool in the search for disease‐relevant biomarkers. The growing demand for precise and reliable biomarkers in psychiatry is fueling research interest in the hope that identifying quantifiable indicators will improve diagnoses and treatment planning across a range of mental health conditions. In this work, we investigated the intersession stability of four functional magnetic resonance imaging (fMRI) resting‐state (RS) parameters—amplitude of low‐frequency fluctuations (ALFF) and fractional ALFF (fALFF, representing the spontaneous brain activity), regional homogeneity (ReHo; measure of local connectivity), and degree centrality (DC; measure of long‐range connectivity)—in three RS networks, previously shown to play an important role in several psychiatric diseases—the default mode network (DMN), the central executive network (CEN), and the salience network (SN). Our investigation at individual subject space revealed a strong stability for ALFF, ReHo, and DC in all three networks, and a moderate level of stability in fALFF. Furthermore, the internetwork connectivity between each network pair was strongly stable between CEN/SN and moderately stable between DMN/SN and DMN/SN.

We present a dual network model to simulate coupled single-phase flow and energy transport in porous media including conditions under which local thermal equilibrium cannot be assumed. The models target applications such as the simulation of catalytic reactors, micro-fluidic experiments, or micro-cooling devices. The new technique is based on a recently developed algorithm that extracts both the pore space and the solid grain matrix of a porous medium from CT images into an interconnected network representation. We simulate coupled heat and mass transfer in these networks simultaneously, allowing naturally to model scenarios with heterogeneous temperature distributions in both void space and solid matrix. The model is compared with 3D conjugate heat transfer simulations for both conduction- and convection-dominated scenarios. It is shown to reproduce effective thermal conductivities over a wide range of fluid to solid thermal conductivity ratios with a single parameter set. Morevoer, it captures local thermal nonequilibrium effects in a micro-cooling device scenario.

Effectively avoiding methane accidents is vital to the security of manufacturing minerals. Coal mine methane accidents are often caused by a methane concentration overrun, and accurately predicting methane emission quantity in a coal mine is key to solving this problem. To maintain the concentration of methane in a secure range, grey theory and neural network model are increasingly used to critically forecasting methane emission quantity in coal mines. A limitation of the grey neural network model is that researchers have merely combined the conventional neural network and grey theory. To enhance the accuracy of prediction, a modified grey GM (1,1) and radial basis function (RBF) neural network model is proposed, which combines the amended grey GM (1,1) model and RBF neural network model. In this article, the proposed model is put into a simulation experiment, which is built based on Matlab software (MathWorks.Inc, Natick, Masezius, U.S). Ultimately, the conclusion of the simulation experiment verified that the modified grey GM (1,1) and RBF neural network model not only boosts the precision of prediction, but also restricts relative error in a minimum range. This shows that the modified grey GM (1,1) and RBF neural network model can make more effective and precise predict the predicts, compared to the grey GM (1,1) model and RBF neural network model.

When the inlet flow velocity in the disc-type winding region of an oil-immersed transformer operates within a high Reynolds number range, it leads to an uneven distribution of oil flow. This phenomenon results in the abnormal occurrence of reverse oil flow in the bottom oil ducts, causing the hotspot temperature to rise instead of decrease. To address this issue, a three-node flow resistance module was introduced at the intersection of T-shaped oil ducts based on the flow paths of oil in the main and branch ducts within the disc-type winding region. A flow network model for the transformer winding region was subsequently constructed. The accuracy of the model was validated through CFD simulations and experiments conducted on a transformer winding region test platform, with a maximum relative error of 4.02%. The model successfully predicted the flow distribution of the cooling oil within the winding region. Furthermore, by considering the structural characteristics of the winding region and the principles of heat transfer, particular attention was given to variations in local Nusselt number correlations. This led to the development of a thermal network model tailored to the winding region experiencing reverse oil flow. Comparative analysis of the model’s calculation results yielded a maximum relative error of only 1.12%, demonstrating its ability to rapidly and accurately elucidate the reverse oil flow effect. This study provides a theoretical foundation for the identification and mitigation of reverse oil flow in future applications.