Input To Network Research Articles

Spectrum Sensing Method Based on STFT-RADN in Cognitive Radio Networks.

To address the common issues in traditional convolutional neural network (CNN)-based spectrum sensing algorithms in cognitive radio networks (CRNs), including inadequate signal feature representation, inefficient utilization of feature map information, and limited feature extraction capabilities due to shallow network structures, this paper proposes a spectrum sensing algorithm based on a short-time Fourier transform (STFT) and residual attention dense network (RADN). Specifically, the RADN model improves the basic residual block and introduces the convolutional block attention module (CBAM), combining residual connections and dense connections to form a powerful deep feature extraction structure known as residual in dense (RID). This significantly enhances the network's feature extraction capabilities. By performing STFT on the received signals and normalizing them, the signals are converted into time-frequency spectrograms as network inputs, better capturing signal features. The RADN is trained to extract abstract features from the time-frequency images, and the trained RADN serves as the final classifier for spectrum sensing. Experimental results demonstrate that the STFT-RADN spectrum sensing method significantly improves performance under low signal-to-noise ratio (SNR) conditions compared to traditional deep-learning-based methods. This method not only adapts to various modulation schemes but also exhibits high detection probability and strong robustness.

Multi-objective QoS optimization in swarm robotics

The “Internet of Robotic Things” (IoRT) is a concept that connects sensors and robotic objects. One of the practical applications of IoRT is swarm robotics, where multiple robots collaborate in a shared workspace to accomplish assigned tasks that may be challenging or impossible for a single robot to conquer. Swarm robots are particularly useful in critical situations, such as post-earthquake scenarios, where they can locate survivors and provide assistance in areas inaccessible to humans. In these life-saving situations, reliable and prompt communication among swarm robots is of utmost importance. To address the need for highly dependable and low-latency communication in swarm robotics, this research introduces a novel hybrid approach called Multi-objective QoS optimization based on Support vector regression and Genetic algorithm (MQSG). The MQSG method consists of two main phases: Parameter Relationship Identification and Parameter Optimization. In the Parameter Relationship Identification phase, the relationship between network inputs (Packet inter-arrival time, Packet size, Transmission power, Distance between sender and receiver) and outputs (quality of service (QoS) parameters) is established using support vector regression. In the parameter optimization phase, a multi-objective function is created based on the obtained relationships from the Parameter Relationship Identification phase. By solving this multi-objective function, optimal values for each QoS parameter are determined, leading to enhanced network performance. Simulation results demonstrate that the MQSG method outperforms other similar algorithms in terms of transmission latency, packet delivery rate, and the number of retransmitted packets.

Sink location problems in dynamic flow grid networks

A dynamic flow network consists of a directed graph, where nodes called sources represent locations of evacuees, and nodes called sinks represent locations of evacuation facilities. Each source and each sink are given supply representing the number of evacuees and demand representing the maximum number of acceptable evacuees, respectively. Each edge is given capacity and transit time. Here, the capacity of an edge bounds the rate at which evacuees can enter the edge per unit time, and the transit time represents the time which evacuees take to travel across the edge. The evacuation completion time is the minimum time at which each evacuee can arrive at one of the evacuation facilities. Given a dynamic flow network without sinks, once sinks are located on some nodes or edges, the evacuation completion time for this sink location is determined. We then consider the problem of locating sinks to minimize the evacuation completion time, called the sink location problem. The problems have been given polynomial-time algorithms only for limited networks such as paths [1–3], cycles [1], and trees [4–6], but no polynomial-time algorithms are known for more complex network classes. In this paper, we prove that the 1-sink location problem can be solved in polynomial-time when an input network is a grid with uniform edge capacity and transit time.

Centrality of Information Sources in Agricultural Input Networks: Insights from Social Network Analysis

Input dealers being credible localite sources of information for farmers have huge potential of aiding faster diffusion of innovations. Under this context, understanding how the input dealers’ access and exchange information is essential for enriching them with updated information and improving the agricultural value chain. This study employs Social Network Analysis (SNA) to explore the centrality measures—degree centrality, closeness centrality, and betweenness centrality—of various information sources utilized by input dealers in Nagar Kurnool and Wanaparthy districts of Telangana during 2020. The analysis reveals that traditional sources, such as extension agents and other input dealers, are highly central to the network, with both scoring the highest in degree and closeness centrality (0.733 and 0.698, respectively). These sources are not only frequently accessed but also serve as key bridges within the network, facilitating the flow of information. Digital platforms like smartphones show growing importance, with significant degree centrality (0.667), yet they play a less critical bridging role. In contrast, social media and print media exhibit lower centrality scores, indicating their peripheral influence. The findings suggest that while traditional information sources remain dominant, digital platforms are emerging as valuable tools for information dissemination highlighting the need for strategies that strengthen traditional channels while integrating digital tools to enhance the efficiency and reach of agricultural information networks. This research contributes to a deeper understanding of the complex information ecosystem in agriculture, offering insights for policymakers and stakeholders aiming to optimize information flows within the sector.

Predicting stroke volume variation using central venous pressure waveform: a deep learning approach

Objective. This study evaluated the predictive performance of a deep learning approach to predict stroke volume variation (SVV) from central venous pressure (CVP) waveforms.Approach. Long short-term memory (LSTM) and the feed-forward neural network were sequenced to predict SVV using CVP waveforms obtained from the VitalDB database, an open-source registry. The input for the LSTM consisted of 10 s CVP waveforms sampled at 2 s intervals throughout the anesthesia duration. Inputs of the feed-forward network were the outputs of LSTM and demographic data such as age, sex, weight, and height. The final output of the feed-forward network was the SVV. The performance of SVV predicted by the deep learning model was compared to SVV estimated derived from arterial pulse waveform analysis using a commercialized model, EV1000.Main results. The model hyperparameters consisted of 12 memory cells in the LSTM layer and 32 nodes in the hidden layer of the feed-forward network. A total of 224 cases comprising 1717 978 CVP waveforms and EV1000/SVV data were used to construct and test the deep learning models. The concordance correlation coefficient between estimated SVV from the deep learning model were 0.993 (95% confidence interval, 0.992-0.993) for SVV measured by EV1000.Significance. Using a deep learning approach, CVP waveforms can accurately approximate SVV values close to those estimated using commercial arterial pulse waveform analysis.

Reimagining otitis media diagnosis: A fusion of nested U-Net segmentation with graph theory-inspired feature set

Otitis media (OM) is a common infection or inflammation of the middle ear causing conductive hearing loss that primarily affects children and may delay speech, language, and cognitive development. OM can manifest itself in different forms, and can be diagnosed using (video) otoscopy (visualizing the tympanic membrane) or (video) pneumatic otoscopy and tympanometry. Accurate diagnosis of OM is challenging due to subtle differences in otoscopic features. This research aims to develop an automated computer-aided design (CAD) system to assist clinicians in diagnosing OM using otoscopy images. The ground truths, generated manually and validated by otolaryngologists, are utilized to train the proposed nested U-Net++ model. Ten clinically relevant gray level co-occurrence matrix (GLCM) and morphological features were extracted from the segmented Region of Interest (ROI) and validated for OM classification based on a statistical significance test. These features serve as input for a Graph Neural Network (GNN) model, the base model in our research. An optimized GNN model is proposed after ablation study of the base model. Three datasets, one private dataset, and two public ones have been used, where the private dataset is utilized for both training and testing, and the public datasets are used to test the robustness of the proposed GNN model only. The proposed GNN model obtained the highest accuracy in diagnosing OM: 99.38 %, 93.51 %, and 91.38 % for the private dataset, public dataset1, and public dataset2, respectively. The proposed methodology and results of this research might enhance clinicians' effectiveness in diagnosing OM.

Backpropagation-Based Learning Techniques for Deep Spiking Neural Networks: A Survey.

With the adoption of smart systems, artificial neural networks (ANNs) have become ubiquitous. Conventional ANN implementations have high energy consumption, limiting their use in embedded and mobile applications. Spiking neural networks (SNNs) mimic the dynamics of biological neural networks by distributing information over time through binary spikes. Neuromorphic hardware has emerged to leverage the characteristics of SNNs, such as asynchronous processing and high activation sparsity. Therefore, SNNs have recently gained interest in the machine learning community as a brain-inspired alternative to ANNs for low-power applications. However, the discrete representation of the information makes the training of SNNs by backpropagation-based techniques challenging. In this survey, we review training strategies for deep SNNs targeting deep learning applications such as image processing. We start with methods based on the conversion from an ANN to an SNN and compare these with backpropagation-based techniques. We propose a new taxonomy of spiking backpropagation algorithms into three categories, namely, spatial, spatiotemporal, and single-spike approaches. In addition, we analyze different strategies to improve accuracy, latency, and sparsity, such as regularization methods, training hybridization, and tuning of the parameters specific to the SNN neuron model. We highlight the impact of input encoding, network architecture, and training strategy on the accuracy-latency tradeoff. Finally, in light of the remaining challenges for accurate and efficient SNN solutions, we emphasize the importance of joint hardware-software codevelopment.

Spatial–temporal prediction model for unsteady near-wall flow around cylinder based on hybrid neural network

A hybrid neural network based on Densely Connected Convolutional Networks (DenseNet), Convolutional Long Short-Term Memory Neural Network (ConvLSTM), and Deconvolutional Neural Network (DeCNN) is employed to predict unsteady flow fields. The utilization of DenseNet makes the model more compact and makes the prediction of three-dimensional flow affordable. The ConvLSTM is implemented to predict multiple future time steps which improves prediction efficiency. The proposed model transforms the time sequences of velocity and pressure fields into uniform spatial–temporal topology as input and captures nonlinear feature information in the spatial–temporal domain. Numerical simulations are conducted for the flow around cylinder at different Reynolds numbers and the near-wall flow around cylinder with different gap ratios, and training samples for the neural network inputs are established. The predicted results are compared with the numerical simulation results, showing good agreement. From the prediction cycle, it can be seen that good prediction results can be maintained in the first three prediction cycles. The prediction results of the three-dimensional unsteady flow around a cylinder near a plane wall, exhibit remarkable accuracy, successfully capturing the evolution of turbulent vortex structures. This signifies that the prediction model is highly effective in capturing the spatial–temporal variations of complex unsteady flows.

Developing new electrocatalysts for oxygen evolution reaction via high throughput experiments and artificial intelligence

The development of non-noble metal electrocatalysts for the Oxygen Evolution Reaction (OER) is advancing towards the use of multi-element materials. To reveal the complex correlations of multi-element OER electrocatalysts, we developed an iterative workflow combining high-throughput experiments and AI-generated content (AIGC) processes. An increased number of 909 (compared to 145 in previous literature) universal descriptors for inorganic materials science were constructed and used as Artificial Neural Network (ANN) input. A large number of statistical ensembles with each ANN individual ensemble having a reduced number of descriptors were integrated with a new Hierarchical Neural Network (HNN) algorithm. This algorithm addresses the longstanding challenge of balancing overwhelming descriptor numbers with insufficient datasets in traditional ANN approaches to materials science problems. As a result, the combination of AIGC and experimental validation significantly enhanced prediction accuracy, increase the R2 values from 0.7 to 0.98 for Tafel slopes.

Physics-informed machine-learning solution to log-layer mismatch in wall-modeled large-eddy simulation

This study proposes a physics-informed machine learning to enable using the erroneous flow data at near-wall grid points as the input to the wall model in a wall-modeled large-eddy simulation (LES). The proposed neural network predicts the amount of numerical error in the near-wall grid-point data and inputs the physically correct flow variables into the wall model by correcting the near-wall error. The input and output features of the neural networks are selected based on the physical relations of the turbulent boundary layer for robustness against various Reynolds and Mach number conditions. The proposed neural networks allow the wall model to accurately predict the wall shear stress from the erroneous near-wall information and yields accurate predictions of the turbulence statistics. Additionally, the proposed physics-informed machine-learning approach reproduces the asymmetry in the probability density functions of the predicted wall shear stress observed in direct numerical simulations, while the conventional wall model with input away from the wall does not. The results suggest that using the near-wall information for wall modeling may increase the fidelity of the wall-modeled LES. Published by the American Physical Society 2024

An Interpretable Target-Aware Vision Transformer for Polarimetric HRRP Target Recognition with a Novel Attention Loss

Polarimetric high-resolution range profile (HRRP), with its rich polarimetric and spatial information, has become increasingly important in radar automatic target recognition (RATR). This study proposes an interpretable target-aware vision Transformer (ITAViT) for polarimetric HRRP target recognition with a novel attention loss. In ITAViT, we initially fuse the polarimetric features and the amplitude of polarimetric HRRP with a polarimetric preprocessing layer (PPL) to obtain the feature map as the input of the subsequent network. The vision Transformer (ViT) is then used as the backbone to automatically extract both local and global features. Most importantly, we introduce a novel attention loss to optimize the alignment between the attention map and the HRRP span. Thus, it can improve the difference between the target and the background, and enable the model to more effectively focus on real target areas. Experiments on a simulated X-band dataset demonstrate that our proposed ITAViT outperforms comparative models under various experimental conditions. Ablation studies highlight the effectiveness of polarimetric preprocessing and attention loss. Furthermore, the visualization of the self-attention mechanism suggests that attention loss enhances the interpretability of the network.

Generalized load modeling approach considering multiple distributed generation integration

To solve the problem of node characteristic uncertainty caused by the connection of multiple distributed generations to the original load node, a new method for modeling the steady-state characteristics of generalized load nodes based on scene clustering was proposed. Scenario clustering takes into account three factors: wind farm output fluctuation, photovoltaic output fluctuation, and demand-side power load fluctuation, and extracts typical scenarios of generalized load data. According to the uncertainty change of node characteristics in different scenarios, the clustering data is segmented and refined, and its probability distribution is counted. Clustering information, probability information, and maximum value are used as three types of features of generalized load and are custom encoded as 12-dimensional feature vectors as neural network inputs. To improve the identification performance of generalized load features, the back propagation (BP) dichotomy neural network is used to build a unified model of node features. The simulation results show that the proposed method can not only model accurately but also introduce probability information through statistical data samples, which can provide an auxiliary reference for the prediction and regulation of generalized loads.

3D Positioning of Drones through Images.

Drones traditionally rely on satellite signals for positioning and altitude. However, when in a special denial environment, satellite communication is interrupted, and the traditional positioning and height determination methods face challenges. We made a dataset at the height of 80-200 m and proposed a multi-scale input network. The positioning index RDS achieved 76.3 points, and the positioning accuracy within 20 m was 81.7%. This paper proposes a method to judge the height by image alone, without the support of other sensor data. One height judgment can be made per single image. Based on the UAV image-satellite image matching positioning technology, by calculating the actual area represented by the UAV image in real space, combined with the fixed parameters of the optical camera, the actual height of the UAV flight is calculated, which is 80-200 m, and the relative error rate of height is 18.1%.

Manifold-based approach for neural network robustness analysis

It is important to understand the mathematical foundations of neural networks and to include robustness in model evaluation. Here, we introduce algorithms based on manifold curvature estimation to assess neural network robustness. These algorithms rely solely on training data and do not require regular or adversarial test data. Initially, a metric is proposed to measure the curvature of discrete data manifolds by introducing weighted angles concept between subspaces. Following this, a robustness measure is introduced that is independent of network architecture or model parameters. Lastly, two additional methods are introduced, utilizing curvature estimation of special manifolds formed by using gradient vectors between output and input network layers, alongside manifold curvature estimation. A comprehensive evaluation is provided on multiple network models using the CIFAR-10 dataset. Manifold geometry-based robustness analysis may lead to the development of not only accurate but also robust neural network models.

Soft computing-driven infrared and visible image fusion network for security application service

The high-level visual tasks (HLVT)-specific infrared and visible image fusion networks aim to guide the fusion network to focus on specific feature regions. The resulting fused images enhance the performance of HLVT in adverse conditions. However, cross-layer visual task fusion may diminish the fusion network’s adaptability to diverse data. This deficiency results in a lack of robustness and security in the fusion network. Consequently, the fusion network is rendered insufficient to fulfill the requirements of HLVT security applications, including object detection and security systems. To address these challenges, we propose a soft computing-driven infrared and visible image fusion network based on layer separation and dual-stream adversarial learning, referred to as LsDSGFuse. Firstly, we employ a layer segmentation network based on a high-resolution network to create salient object segmentation masks for the original image. This helps mitigate the impact of task-specific guidance on the fusion network learning process, preventing overfitting to HLVT. Secondly, we use the original image after information separation as the input of the generator. The separated network inputs clearly define foreground objects and background environments, aiding the generator in better fusing foreground and background. Lastly, we adopt a no-loading training strategy to balance adversarial learning, prevent discriminator overfitting, and reduce resource waste. Experimental results demonstrate the outstanding performance of our proposed image fusion method in terms of fusion quality, surpassing several representative approaches. Furthermore, experiments in HLVT indicate that our method facilitates HLVT in better responding to potential threats and unknown variables. This improvement significantly enhances HLVT’s security performance.

Prediction of wear properties of CaO and MgO doped stabilized zirconia ceramics produced with different pressing methods using adaptive neuro fuzzy inference systems

AbstractThe present paper describes the fabrication and wear behaviour of CaO and MgO added stabilized zirconia (ZrO2) ceramics produced by powder metallurgy method were examined and modelling with artificial neural networks was studied using the experimental data obtained. CaO/MgO added stabilized zirconia ceramics were fabricated by using a combined method of ball milling, cold pressing ‐ cold isostatic pressing and sintering. CaO and MgO in different amounts (0–8 %mole) were mixed with zirconia. These mixtures were prepared by mechanical alloying method. The green compacts were sintered at 1600 °C. The wear experimental results obtained were converted into data suitable for modelling with artificial neural networks. Wear Load, wear time, CaO and MgO data were used as artificial neural networks input variables. The amount of wear according to the pressing method was taken as the output variables of artificial neural networks. An artificial neural networks was established for the prediction of wear properties of zirconia pressed using the adaptive neuro fuzzy inference systems (ANFIS) learning technique. As a result, a high R2 value of 0.9187 for cold pressing samples and 0,9449 for cold isostatic pressing samples was achieved based on the approach of comparing the success of the model with the test data set and the result produced.

Interlayer information fusion-based and dual-attention improved U-Net for ABVS image sequence intelligent tumor segmentation

Breast cancer is the most common cancer among women. Accurate and intelligent ultrasound image tumor segmentation can help physicians efficiently determine the location, shape and features of tumors and then develop appropriate treatment plans. To this end, we propose a deep learning method combining interlayer information and dual attention improvement for accurate and intelligent segmentation of breast tumors in ABVS image sequences. We extracted the slices containing tumors in ABVS images and formed a three-channel image input network with the current frame and the corresponding before and after frames. The network combines interlayer information during computation, and the before and after frames can guide the current frame image for more accurate tumor segmentation. In addition, we improved the channel attention module by replacing the full connection with a one-dimensional convolution and applying global max pooling on the basis of the original channel attention module, which improved the segmentation performance of the module while reducing the number of parameters. The improved channel attention module was added to the U-Net skip-connection section to assign different weight coefficients to each feature channel according to the characteristics of the input three-channel image. Our method outperformed other mainstream tumor segmentation methods on the dataset in both centers, achieving a Dice similarity coefficient (DSC) of 84.97 %, a Jaccard coefficient (JC) of 74.63 %, a 95 % Hausdorff distance (95HD) of 6.22 mm on the inner center, and DSC of 80.79 %, JC of 69.74 %, 95HD of 9.82 mm on the outer dataset.

Frequency Modulation Recognition for Radar Signal based on Resnet-LSTM Network

In order to satisfy the modulation recognition requirements for radar signal with large scale changes in pulse-width and bandwidth, the Resnet-LSTM network is proposed in this paper. First, the waveform is preprocessed by self-correlation, and then the I/Q waveform and self-correlation result are as the network input. Secondly, the local characteristics were extracted by Resnet network; and lastly the LSTM network is adopted to extract the serialization representation. The proposed algorithm avoids the flaw of CNN network cannot adapt to variable length, and problem of memory forgetting of the LSTM network for long sequence is reduced. The simulation shows that the modulation recognition accuracy is more than 96.1% over the detection sensitivity for LFM, Parabolic-NLFM, Triangular-NLFM, Sine-NLFM, Sawtooth-NLFM and FSK signals.

Deep Neural Network-Based Temperature Mapping Technique for Heat Sink on Electronic Devices Using Local Thermocouple Sensors

ABSTRACT Heat generated by electronic devices can lead to thermal deformation, damage, and fatigue failure, underscoring the importance of monitoring heat distribution. This study introduces an artificial neural network using two thermocouples for cost-effective temperature distribution prediction. Experimental data from heated systems on chip with attached heat sinks were used for training and validation, integrating thermocouple measurements and infrared camera data. The method’s applicability was verified across four different heat sinks. Additionally, finite element analysis compared stress and strain based on predicted and actual temperature distributions, addressing conventional limitations that focus solely on temperature validation. Furthermore, the temperature of any coordinate could be output by including the coordinate as an input of neural networks, eliminating the hassle of re-constructing or learning the DNN to obtain the temperature of the desired coordinate. Results showed that the temperature distribution could be predicted with high accuracy (over 0.95), and the maximum error rate for stress and strain predictions was 7% in the worst case. This confirmed the feasibility of artificial neural networks to predict the temperature distribution using a minimal number of sensors and ensure robust performance even if the heat sink changes.

CFRP-RC fracture strength prediction: A novel approach using deep learning

Externally bonded carbon fiber-reinforced polymer (CFRP) composites have been widely adopted for strengthening and repairing aging concrete structures. However, premature fracture at the CFRP-concrete interface remains a significant concern, necessitating a better understanding of the interfacial bond behavior and fracture mechanisms. Traditional experimental studies and numerical simulations have limitations in accurately capturing the complex nonlinear factors influencing this fracture behavior. This paper explores the novel application of machine learning (ML), specifically artificial neural networks (ANNs), for predicting the fracture strength of CFRP-reinforced concrete (CFRP-RC) members. ANNs enable mapping the intricate relationships between input parameters (e.g., CFRP/concrete properties, geometric configurations) and fracture responses through iterative training on experimental data. Key aspects include comprehensive data collection, preprocessing techniques, feature selection methods like mean impact value (MIV) analysis, and neural network architecture design. The paper highlights successful ANN applications in predicting CFRP-RC bond strength, shear capacity, and overall fracture behavior. A systematic approach is proposed for developing robust ANN models tailored to CFRP-RC fracture prediction, encompassing data curation, input variable screening, network training/validation, and model interpretability analyses. By leveraging ML’s ability to handle multifaceted nonlinearities, this data-driven framework offers a powerful alternative to traditional methods, potentially enhancing the design, analysis, and performance evaluation of CFRP-strengthened concrete structures.