Simple Network Research Articles

On inequalities of shear modulus contributions in disordered elastic bodies

Abstract We investigate generic inequalities of various contributions to the shear modulus $\mu$ in ensembles of amorphous elastic bodies. We focus first on a simple elastic network model with connectivity matrices (CMs) which are either annealed or quenched, at or out of equilibrium. The stress-fluctuation formalism relation for $\mu$ is rewritten as $\mu = \mu_1 + \mu_a$ with $\mu_1 \ge 0$ characterizing the variance of the quenched shear stresses and $\mu_a$ being a simple average over all states and CMs. For equilibrium CM-distributions $\mu_a$ becomes equivalent to the shear modulus of annealed systems, i.e. $\mu_a \ge 0$, while more generally $\mu_a$ may become strongly negative as shown by considering a temperature quench and a scalar active two-temperature model. Consistent relations are also found for glass-forming colloids where $\mu-\mu_1=\mu_a=0$ for equilibrium ensembles, i.e. $\mu$ is set by the quenched shear stresses, while $\mu_a$ becomes again negative otherwise.

Joint extented Kalman filter-based parameter estimation in networked SEIR models with stochastic variability: analysis using COVID-19 daily data from southern India

Graph Laplacian diffusion is utilised to augment the susceptible-infected-removed (SEIR) epidemic model by integrating a weighted network and introducing variability in the transmission rate parameter to simulate population movement across network nodes. Employing the Joint Extended Kalman filter (JEKF), our objective is to derive three critical parameters: the transmission rate (β), recovery rate (γ), and latent period rate (α). The JEKF's iterative approach continuously anticipates and updates the system state based on current parameter estimations, making it adaptable for parameter estimation in dynamic systems. Integration of model predictions with observed data further enhances accuracy. Subsequently, we offer visual insights and demonstrate our methodology through experiments conducted on a simple tree network and a small-world Watts-Strogatz graph. Our ultimate aim is to precisely determine optimal parameter values to formulate effective COVID-19 management plans tailored for South India.

Simplification of Linear Beam-Forming Networks by Applying a Novel Phase Interpolation Technique

Simplification of Linear Beam-Forming Networks by Applying a Novel Phase Interpolation Technique

Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition.

Vision Transformers have been the most popular network architecture in visual recognition recently due to the strong ability of encode global information. However, its high computational cost when processing high-resolution images limits the applications in downstream tasks. In this paper, we take a deep look at the internal structure of self-attention and present a simple Transformer style convolutional neural network (ConvNet) for visual recognition. By comparing the design principles of the recent ConvNets and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels ( ≥ 7×7) nested in convolutional layers and we observe a consistent performance improvement when gradually increasing the kernel size from 5×5 to 21×21. We build a family of hierarchical ConvNets using the proposed convolutional modulation, termed Conv2Former. Our network is simple and easy to follow. Experiments show that our Conv2Former outperforms existent popular ConvNets and vision Transformers, like Swin Transformer and ConvNeXt in all ImageNet classification, COCO object detection and ADE20 k semantic segmentation.

Revitalizing Convolutional Network for Image Restoration.

Image restoration aims to reconstruct a high-quality image from its corrupted version, playing essential roles in many scenarios. Recent years have witnessed a paradigm shift in image restoration from convolutional neural networks (CNNs) to Transformer-based models due to their powerful ability to model long-range pixel interactions. In this paper, we explore the potential of CNNs for image restoration and show that the proposed simple convolutional network architecture, termed ConvIR, can perform on par with or better than the Transformer counterparts. By re-examing the characteristics of advanced image restoration algorithms, we discover several key factors leading to the performance improvement of restoration models. This motivates us to develop a novel network for image restoration based on cheap convolution operators. Comprehensive experiments demonstrate that our ConvIR delivers state-of-the-art performance with low computation complexity among 20 benchmark datasets on five representative image restoration tasks, including image dehazing, image motion/defocus deblurring, image deraining, and image desnowing.

Automated MRI quantification of pediatric abdominal adipose tissue using convolutional neural networks and novel total intensity maps

ObjectiveChildhood obesity is a significant global health concern. Visceral adipose tissue (VAT) is more closely linked to the development of metabolic and cardiovascular diseases than abdominal subcutaneous adipose tissue (ASAT). This study aimed to develop a straightforward and automated method to quantify both ASAT and VAT in children from MRI. MethodsDixon-based 3 T-MRI scans were conducted on Mexican boys aged 7–9 years. Novel Total Intensity Maps were generated from these scans for input into simple 2D Convolutional Neural Networks (CNNs) for automatic prediction/quantification of ASAT and VAT. The results were compared with the commercial semi-automated quantification and validated method provided by AMRA® Researcher which is the gold standard. ResultsThe CNN-based method produced ASAT and VAT quantifications comparable to those obtained by AMRA® Researcher (ASAT, p = 0.1765; VAT, p = 0.7757), with a high correlation between the two methods for ASAT (R2 = 0.98, p < 10−14) and VAT (R2 = 0.95, p < 10−11). The reproducibility coefficients (RPC) were 0.32 L for ASAT and 0.17 L for VAT with our novel methodology. ConclusionThis study presents a simple automated method for quantifying ASAT and VAT in children from MRI data using 2D-CNN analysis of novel inputs, Total Intensity Maps. The new method produced measurements comparable to those obtained by AMRA® Researcher on the same dataset. SignificanceThe proposed automatic and straightforward quantification method, with minimal computational resource requirements, may serve as an accessible tool for researchers and clinicians in the diagnosis, follow-up, and prevention of childhood obesity.

Neural network modelling of kinematic and dynamic features for signature verification

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm and forearm torques remains challenging. We present two approaches for estimating angular velocities, angular positions, and force torques. The first approach involves using a physical UR5e robotic arm to reproduce a signature while capturing those parameters over time. The second method, a cost-effective approach, uses a neural network to estimate the same parameters. Our findings demonstrate that a simple neural network model can extract effective parameters for signature verification. Training the neural network with the MCYT300 dataset and cross-validating with other databases, namely, BiosecurID, Visual, Blind, OnOffSigDevanagari-75 and OnOffSigBengali-75 confirm the model’s generalization capability. The trained model is available at: https://github.com/gvessio/SignatureKinematics.

The risk of shortcutting in deep learning algorithms for medical imaging research

While deep learning (DL) offers the compelling ability to detect details beyond human vision, its black-box nature makes it prone to misinterpretation. A key problem is algorithmic shortcutting, where DL models inform their predictions with patterns in the data that are easy to detect algorithmically but potentially misleading. Shortcutting makes it trivial to create models with surprisingly accurate predictions that lack all face validity. This case study shows how easily shortcut learning happens, its danger, how complex it can be, and how hard it is to counter. We use simple ResNet18 convolutional neural networks (CNN) to train models to do two things they should not be able to do: predict which patients avoid consuming refried beans or beer purely by examining their knee X-rays (AUC of 0.63 for refried beans and 0.73 for beer). We then show how these models’ abilities are tied to several confounding and latent variables in the image. Moreover, the image features the models use to shortcut cannot merely be removed or adjusted through pre-processing. The end result is that we must raise the threshold for evaluating research using CNNs to proclaim new medical attributes that are present in medical images.

GWO-elman based composite detection of transformer oil flow temperature

This paper addresses the issue of nonlinear coupling error caused by cross-sensitivity of strain and temperature in the composite detection of flow rate and temperature in transformer oil using a Fiber Bragg Grating (FBG) sensor. This paper focuses on the FBG sensor as the research object, elucidating the underlying principles of composite detection. Subsequently, a composite detection experimental platform is established for the purpose of analyzing the coupling error of flow rate and temperature. Ultimately, a nonlinear decoupling algorithm based on the Grey Wolf Optimizer (GWO) is proposed to enhance the nonlinear decoupling algorithm of the Elman neural network (simple recurrent neural network, Elman). The findings demonstrate that within the flow rate range of 0–5 m/s and the temperature range of 30 °C–150 °C, the maximum error is reduced by 72.0 % and 81.3 %, and the average error is reduced by 74.4 % and 79.4 %. This significantly enhances the precision and reliability of the sensor’s detection capabilities.

Quad ports dielectric resonator antenna with simple feed network and high gain performance

This paper presents a quad-port multiple-input multiple-output (MIMO) single cylindrical dielectric resonator antenna (CDRA) for X-band applications. This approach is mainly based on selecting the proper feeding structure for each port as well as implanting vertical metallic vias (VMVs) to diminish the mutual coupling over a wide bandwidth. Two orthogonal apertures and two vertical probes are utilized as feeding structures to realize good isolation between all port combinations. For coupling mitigation between port1 and port2 that is due to the field distribution of the excited modes at these ports, four VMVs are inserted between them in appropriate positions to produce field orthogonality along wide bandwidth. The excited modes inside the proposed CDRA are HE52δ+2x,HE52δ+2y, HE32δ + 2, and TM12δ + 2. Isolation better than -15 dB is attained across the overlapping band of 340 MHz (4 %); from 8.2 to 8.54 GHz. Moreover, the proposed DRA provides a gain of 5.17, 7.21, 7.77, and 7.78 dBi for the four ports at 8.45 GHz and the total efficiencies at all ports are from 65 to 85 % across the operating band. The MIMO performance of the proposed design shows a good envelope correlation coefficient (ECC), diversity gain (DG), total active reflection coefficient (TARC), channel capacity loss (CCL) and mean effective gain (MEG) through the whole band for all ports.

Point spread function deconvolution using a convolutional autoencoder

A major issue in optical astronomical image analysis is the combined effect of the instrument’s point spread function (PSF) and the atmospheric seeing that blurs images and changes their shape in a way that is band and time-of-observation dependent. In this work we present a very simple neural network based approach to nonblind image deconvolution that relies on feeding a convolutional autoencoder (CAE) input images that have been preprocessed by convolution with the corresponding PSF and its regularized inverse, a method which is both conceptually simple and computationally less intensive. We also present here, a new approach for dealing with limited input dynamic range of neural networks compared to the dynamic range present in astronomical images. Published by the American Physical Society 2024

Predicting leishmaniasis outbreaks in Brazil using machine learning models based on disease surveillance and meteorological data

Leishmaniasis poses a significant global health concern due to the absence of vaccines for humans and high infection rates in some countries. It is classified as a neglected tropical disease. In 2022, roughly 85% of global visceral leishmaniasis cases were reported in seven countries: Brazil, Ethiopia, India, Kenya, Somalia, South Sudan, and Sudan. Despite Brazil’s advanced medical capabilities compared to other affected regions, certain areas still witness a significant number of cases, prompting increased attention from researchers and raising concerns within the healthcare system. This study explores the application of artificial intelligence algorithms, particularly machine learning (ML) models to predict leishmaniasis outbreaks in selected Brazilian cities based on accumulated cases from 2007 to 2022, leveraging available meteorological data to enhance model accuracy. Our investigation concentrated on the following cities in Brazil: Fortaleza/CE, Teresina/PI, and São Luís/MA were chosen for the study of visceral leishmaniasis, whereas Manaus/AM, Rio Branco/AC, and Macapá/AP were selected for the study of tegumentary leishmaniasis, encompassing both cutaneous and mucocutaneous forms. Several Artificial Neural Network (ANN) architectures were evaluated, including a Simple Feedforward Neural Network (SFNN), a Deep Feedforward Neural Network (DFNN), and a Long Short-Term Memory (LSTM) recurrent neural network. Additionally, the Support Vector Machine (SVM), specifically the Support Vector Regression (SVR), was tested. Various metrics were used to identify the most effective models, in which the Root Mean Squared Error (RMSE) was the primary one. The results highlight the significance of meteorological data as a crucial factor in ML models for predicting leishmaniasis outbreaks, while also emphasizing the importance of fine-tuning these models to achieve greater accuracy. Finally, data and the pseudo-code of the models are accessible through an open repository to encourage further studies in this area.

DC-DC Buck Converters with Quasi-Online Estimation of Filter Capacitor Equivalent Parameters

The article focuses on devising solutions for monitoring the condition of the filter capacitors of DC-DC converters. The article introduces two novel DC-DC buck converter designs that monitor the equivalent series resistance (ESR) and the capacitance of capacitors using a parameter observer (PO) and simple variable electrical networks (VEN). For the first scheme, the PO processes in real time the voltage at the capacitor terminals during a discharge-charge cycle. For the second scheme, the filtering is performed with two or more capacitors in parallel, and the PO processes the voltage at the terminals of each capacitor during two discharge processes without interrupting the filtering operation of the converter. The paper presents the principles and theoretical support on which the two schemes of DC-DC buck converters are based, design details regarding PO and VEN, as well as experiments performed with each of the schemes. In the experimental schemes, the PO is implemented with a microcontroller, and the parameters of some aluminum electrolytic filter capacitors are calculated in a real-time manner of about . The calculation accuracy of the equivalent capacity is very good. Regarding the calculation accuracy of the ESR, it is shown that it depends on the fulfillment of certain ratios between the VEN resistances, on the one hand, as well as between them and the ESR, on the other hand.

SimSANet: a simple sequential attention-aided deep neural network for vehicle make and model recognition

SimSANet: a simple sequential attention-aided deep neural network for vehicle make and model recognition

The HYBRID CONTENT-BASED FILTERING AND CLASSIFICATION RNN WITH PARTICLE SWARM OPTIMIZATION FOR TOURISM RECOMMENDATION SYSTEM

Economic recovery in the tourism sector after the COVID-19 pandemic is one of the main focuses of the Indonesian government at the moment, especially in Bandung City. This research aims to develop a personalized tourist spot recommendation system, by addressing the gaps in the existing literature through the integration of Content-Based Filtering (CBF) and Simple Recurrent Neural Network (RNN) methods that aim to improve recommendation accuracy. This study uses a hybrid approach that combines Term Frequency - Inverse Document Frequency (TF-IDF) and word embedding with the Robustly Optimized BERT (RoBERTa) model to identify similarities between tourist destinations based on their content characteristics. Simple RNN is used to analyze user preference patterns over time, which is then further optimized using Particle Swarm Optimization (PSO). As a result, the Simple RNN model that has been optimized with PSO shows an increased accuracy of up to 94.37%, outperforming other optimizations such as Adam and SGD. This research makes a novel contribution by applying advanced machine learning techniques to improve personalization in travel recommendation systems.

Enhanced Tomato Disease Classification Using Hybrid Deep Learning Approach

Tomato disease classification is important for agricultural productivity and food security, yet achieving high accuracy stays challenging due to the complexity of disease symptoms. This study proposed a model classification utilizing DenseNet121 combined with an Autoencoder for feature extraction and Simple neural network (SNN) for classifier. The dataset contains 10 classes of tomato diseases. Experimental results shows that the proposed approach achieved a high accuracy of 99%, outperforming the performance of several approaches. The integration of the Autoencoder enhances feature extraction and dimensionality reduction, important for improved classification outcomes. This study highlights the efficacy of the proposed work in achieving state-of-the-art accuracy in tomato disease detection. Future work may focus on refining the model using advanced augmentation techniques and expanding the dataset to enhance its applicability across diverse agricultural conditions.

The spectrum of experimentally accessible states for melting and freezing transitions in mesoporous materials.

Structural disorder in mesoporous solids gives rise to complex phase behavior for materials confined within their pore spaces. As a result, a wide spectrum of possible phase configurations associated with spatial distributions of thermodynamic phases throughout the pore networks can be realized in experiments. Despite their importance, quantifying these states remains largely unaddressed. By considering solid-liquid equilibria as a representative example and using a simple random network model, we investigate the spectrum of such states accessible in real experiments and relate this spectrum to the structural characteristics of porous solids. We classify these states by their free energies and demonstrate how network effects break degeneracies for specific phase compositions and temperatures. Furthermore, we identify the experimental conditions that delineate boundary free energy states, differentiating accessible from inaccessible states. The insights from this study on solid-liquid equilibria are also equally applicable to gas-liquid equilibria in confined spaces and contribute to a deeper understanding of relaxation dynamics associated with hysteresis.

Prediction and evaluation of key parameters in coalbed methane pre-extraction based on transformer and inversion model

Accurate parameter prediction in the coalbed methane (CBM) pre-extraction process is crucial for formulating effective control measures and preventing CBM-related accidents. Traditional prediction methods rely on feature extraction or complex physical model parameter calculations, which require extensive manual intervention and have limited practical applicability. Additionally, simple neural network methods are prone to overfitting and gradient vanishing when handling parameters, and they lack the capability to dynamically monitor gas pressure during extraction, leading to inefficient and blind extraction operations. This study proposes a CBM pre-extraction parameter and completion time prediction method based on the Transformer model. By integrating autoregressive models and wavelet denoising techniques, the approach effectively captures temporal features and long-term dependencies in CBM data. Experimental results demonstrate that the proposed model outperforms traditional methods in short-, medium-, and long-term predictions, with a median R2 value of 0.99072, and 76% of the training results exceeding 0.9. Furthermore, a CBM pressure inversion model was developed, combining dimensional analysis and physical similarity principles with the Transformer model, enabling the dynamic detection of high- and low-pressure regions in coal seams. In single borehole compliance time predictions, the median compliance time for the first stage is 4 days, with an average of 49 days and a maximum of 277 days, providing adjustment guidance for boreholes with extended compliance times. The proposed model significantly improves prediction accuracy and stability, offering critical support for developing scientifically sustainable pre-extraction plans and advancing intelligent CBM management.

Evolution of avian foot morphology through anatomical network analysis

Avian evolution led to morphological adaptive variations in feet. Diverse foot types are accompanied by a diverse muscle system, allowing birds to adopt different primary lifestyles, and to display various locomotor and manipulative skills. We provide insights of evolutionary and functional significance on the avian foot architecture through Anatomical Network Analysis, a methodology focused on connectivity patterns of anatomical parts. Here, we show that: (1) anatomical parts largely conserved in living birds and already present in ancestral dinosaurs exhibit the highest connectivity degree, (2) there is no link between the more complex foot networks and the ability to perform more specialized skills or a higher number of different tasks, (3) there is a trend towards the simplification of foot networks on a macroevolutionary scale within birds, and (4) foot networks are phylogenetically constrained and conserved in all birds despite their foot type diversity, probably due to stabilizing selection.

Simple Recurrent Networks are Interactive.

There is disagreement among cognitive scientists as to whether a key computational framework - the Simple Recurrent Network (SRN; Elman, Machine Learning, 7(2), 195-225, 1991; Elman, Cognitive Science, 14(2), 179-211, 1990) - is a feedforward system. SRNs have been essential tools in advancing theories of learning, development, and processing in cognitive science for more than three decades. If SRNs were feedforward systems, there would be pervasive theoretical implications: Anything an SRN can do would therefore be explainable without interaction (feedback). However, despite claims that SRNs (and by extension recurrent neural networks more generally) are feedforward (Norris, 1993), this is not the case. Feedforward networks by definition are acyclic graphs - they contain no loops. SRNs contain loops - from hidden units back to hidden units with a time delay - and are therefore cyclic graphs. As we demonstrate, they are interactive in the sense normally implied for networks with feedback connections between layers: In an SRN, bottom-up inputs are inextricably mixed with previous model-internal computations. Inputs are transmitted to hidden units by multiplying them by input-to-hidden weights. However, hidden units simultaneously receive their own previous activations as input via hidden-to-hidden connections with a one-step time delay (typically via context units). These are added to the input-to-hidden values, and the sums are transformed by an activation function. Thus, bottom-up inputs are mixed with the products of potentially many preceding transformations of inputs and model-internal states. We discuss theoretical implications through a key example from psycholinguistics where the status of SRNs as feedforward or interactive has crucial ramifications.