Residual Convolutional Network Research Articles

Channel Estimation for Indoor Massive MIMO Visible Light Communication With Deep Residual Convolutional Blind Denoising Network

Massive multiple-input multiple-output (m-MIMO) visible light communication (VLC) has been considered as one of the promising components in the optical wireless communication system. However, the envisioned benefits may be limited due to the high computational complexity to estimate accurate channel state information (CSI). Besides, several propagation paths in the practical communication channels induces significant difficulties. In this paper, a deep residual convolutional blind denoising network (ResCBDNet) has been proposed to predict more realistic channels in indoor m-MIMO VLC communication system. Unlike the other convolutional networks which may overfit on the simplified additive white gaussian noise model, the ResCBDNet exploits noise level estimation subnetwork to improve the generalization ability to real noise as well as interactively reduce the noise in the channel matrix by adjusting the noise level map. More specifically, we have investigated to optimize the ResCBDNet over a large range of SNRs. During the simulation, the sparse channel matrix has been treated as a two dimensional natural image. Simulation results validate that the proposed network is very promising in practical channel estimation for the indoor m-MIMO VLC communication system and outperforms the state-of-the-art channel estimators in terms of normalized mean square error and peak signal-to-noise ratio.

PCRTAM-Net: A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation

PCRTAM-Net: A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation

Discerning Watershed Response to Hydroclimatic Extremes with a Deep Convolutional Residual Regressive Neural Network

The impact of climate change continues to manifest itself daily in the form of extreme events and conditions such as droughts, floods, heatwaves, and storms. Better forecasting tools are mandatory to calibrate our response to these hazards and help adapt to the planet’s dynamic environment. Here, we present a deep convolutional residual regressive neural network (dcrrnn) platform called Flux to Flow (F2F) for discerning the response of watersheds to water-cycle fluxes and their extremes. We examine four United States drainage basins of varying acreage from smaller to very large (Bear, Colorado, Connecticut, and Mississippi). F2F combines model and ground observations of water-cycle fluxes in the form of surface runoff, subsurface baseflow, and gauged streamflow. We use these time series datasets to simulate, visualize, and analyze the watershed basin response to the varying climates and magnitudes of hydroclimatic fluxes in each river basin. Experiments modulating the time lag between remotely sensed and ground-truth measurements are performed to assess the metrological limits of forecasting with this platform. The resultant mean Nash–Sutcliffe and Kling–Gupta efficiency values are both greater than 90%. Our results show that a hydrological machine learning platform such as F2F can become a powerful resource to simulate and forecast hydroclimatic extremes and the resulting watershed responses and natural hazards in a changing global climate.

Lightweight Implicit Blur Kernel Estimation Network for Blind Image Super-Resolution

Blind image super-resolution (Blind-SR) is the process of leveraging a low-resolution (LR) image, with unknown degradation, to generate its high-resolution (HR) version. Most of the existing blind SR techniques use a degradation estimator network to explicitly estimate the blur kernel to guide the SR network with the supervision of ground truth (GT) kernels. To solve this issue, it is necessary to design an implicit estimator network that can extract discriminative blur kernel representation without relying on the supervision of ground-truth blur kernels. We design a lightweight approach for blind super-resolution (Blind-SR) that estimates the blur kernel and restores the HR image based on a deep convolutional neural network (CNN) and a deep super-resolution residual convolutional generative adversarial network. Since the blur kernel for blind image SR is unknown, following the image formation model of blind super-resolution problem, we firstly introduce a neural network-based model to estimate the blur kernel. This is achieved by (i) a Super Resolver that, from a low-resolution input, generates the corresponding SR image; and (ii) an Estimator Network generating the blur kernel from the input datum. The output of both models is used in a novel loss formulation. The proposed network is end-to-end trainable. The methodology proposed is substantiated by both quantitative and qualitative experiments. Results on benchmarks demonstrate that our computationally efficient approach (12x fewer parameters than the state-of-the-art models) performs favorably with respect to existing approaches and can be used on devices with limited computational capabilities.

A residual convolution transfer framework based on slow feature for cross-domain machinery fault diagnosis

Intelligent fault diagnosis plays a vital role in ensuring the stable, reliable and safe operation of machinery equipment. However, data distribution doesn’t meet the assumption of the same distribution in the practical scene due to environmental changes. Traditional transfer learning methods can solve the situation of data distribution shift, but they encounter obstacles without adequately considering the possibility of introducing feature pre-extraction into deep learning and fusing pre-extracted low-dimensional feature with high-dimensional feature. In this study, a residual convolution transfer learning framework based on slow feature, which is an invariant or slowly varing signal learned from a vector signal, is presented to address this issue. Firstly, slow feature analysis is employed to implement preliminary feature extraction, which obtains latent variable that reflects the fundamental information of the equipment. Then, slow feature is sent to a residual convolution network for further abstraction and low-dimensional feature aggregates with high-dimensional feature by a bypass branch. Furthermore, maximum mean discrepancy is introduced to calculate the distance between two distributions in the Reproducing Kernel Hilbert Space (RKHS) and reduce the discrepancy of feature distribution. The proposed method is evaluated on Xi’an Jiao Tong University (XJTU) dataset and Case Western Reserve University (CWRU) dataset, and the average accuracy is higher than 99%. Experimental results show that the proposed framework has superior transferability and robustness under different working conditions.

Self-Attention Graph Convolution Residual Network for Traffic Data Completion

Complete and accurate traffic data is critical in urban traffic management, planning and operation. In fact, real-world traffic data contains missing values due to multiple factors, such as device outages and communication errors. For traffic data completion task, most of the existing methods are matrix/tensor completion methods, which usually enforce low rank constraint on traffic data matrix/tensor. But they neglect the graph structure of traffic data, resulting in low completion performance. Recently, graph convolutional networks have achieved remarkable results in traffic data forecasting due to their abilities of feature extraction and nonlinear fitting on arbitrarily graph-structured data. However, there are few studies based on graph neural networks for traffic data completion task. In this paper, we propose a traffic data completion model based on graph convolutional network model to impute missing values from the perspective of deep learning. This model utilizes graph convolution to model the local spatial dependency. As for global spatial dependency and temporal dependency, this model incorporates self-attention mechanism, which is applied in the spatial and temporal dimensions respectively. The experimental results on the two real-time datasets demonstrate that the proposed model outperforms the baseline methods significantly under arbitrarily missing scenarios.

Fine-grained Traffic Classification Based on Improved Residual Convolutional Network in Software Defined Networks

As Internet traffic becomes increasingly complex, a growing number of applications are carrying different services. To provides service-aware traffic classification, allowing network operators to better analyze network composition as well as manage and schedule efficiently network resources to facilitate sustainable development network, fine-grained traffic classification has become a crucial and challenging problem. Software defined networks has become the most promising new network architecture in the future with two major advantages of centralized control and programmability. Deep learning has also become a mainstream technology by its excellent feature extraction ability for large datasets. Thus the combination of software defined networks and deep learning can effectively solve the challenge of data set collection and feature extraction in the field of traffic classification. Inspired by research in computer vision, in this paper we propose an improved residual convolutional network approach to network traffic classification, which addresses the network degradation problem that occurs with increasing network depth in traditional deep learning methods for fine-grained network traffic identification, and can effectively learn deeper network features to achieve fine-grained network traffic classification. Experimental results show that the overall accuracy of the proposed method can reach 99.93%, which is about 4%, 13%, 7% and 2% higher than other state-of-the-art models such as classical residual networks ResNet-18, One-dimensional Convolutional Neural Networks (1D-CNN), Long Short-Term Memory (LSTM) and combined model CNN-LSTM respectively, thus verify the effectiveness of our method.

Transfer learning convolutional neural network with modified Lion optimization for multimodal biometric system

Recently, biometric verification systems have been widely used in security applications with multi-level authentication. Existing machine learning approaches were utilized to develop traditional multimodal biometric systems (MBS). However, they fail to guarantee optimal secrecy, security, and accuracy. Thus, this work adopted the transfer learning convolutional neural network (TL-CNN) approach for implementing the eight-class hybrid MBS. The multi-level security biometric verification systems are achieved by considering eight different types of biometric datasets, which are the retina, faces, ears, palm print, fingerprint, voice, gait, and DNA-based biometric data. Initially, the noise from these datasets is eliminated by using Multi-Kernel-Multi-Patch Bilateral Filtering (MK-MP-BF), which also enhances the regions of images. Further, a deep convolutional residual network (DCRN) is used to extract pattern-specific features from the pre-processed data, which also identifies the relationship between various features. Then, a bio-optimization-based modified Lion optimization algorithm (MLOA) is used to select the optimal feature, which also identifies the inter- and intra-dependencies among various biometrics. Finally, a TL-CNN-based GoogleNet classifier was utilized for recognizing the biometrics, which also performed the multi-class classification operation. From the simulations, it is proven that the proposed MLOA optimized TL-CNN resulted in outstanding recognition and authentication performance in comparison with conventional methods.

CRMSNet: a deep learning model that uses convolution and residual multi-head self-attention block to predict RBPs for RNA sequence.

RNA-binding proteins (RBPs) play significant roles in many biological life activities, many algorithms and tools are proposed to predict RBPs for researching biological mechanisms of RNA-protein binding sites. Deep learning algorithms based on traditional machine learning get better result for predicting RBPs. Recently, deep learning method fused with attention mechanism has attracted huge attention in many fields and gets competitive result. Thus, attention mechanism module may also improve model performance for predicting RNA-protein binding sites. In this study, we propose convolutional residual multi-head self-attention network (CRMSNet) that combines CNN, ResNet and multi-head self-attention blocks to find RBPs for RNA sequence. First, CRMSNet incorporates convolutional neural networks, recurrent neural networks and multi-head self-attention block. Second, CRMSNet can draw binding motif pictures from the convolutional layer parameters. Third, attention mechanism module combines the local and global RNA sequence information for capturing long sequence feature. CRMSNet gets competitive AUC (area under the ROC curve) result in a large-scale dataset RBP-24. And CRMSNet experiment result is also compared with other state-of-the-art methods. The source code of our proposed CRMSNet method can be found in https://github.com/biomg/CRMSNet. This article is protected by copyright. All rights reserved.

Deep learning based deep-sea automatic image enhancement and animal species classification

The automatic classification of marine species based on images is a challenging task for which multiple solutions have been increasingly provided in the past two decades. Oceans are complex ecosystems, difficult to access, and often the images obtained are of low quality. In such cases, animal classification becomes tedious. Therefore, it is often necessary to apply enhancement or pre-processing techniques to the images, before applying classification algorithms. In this work, we propose an image enhancement and classification pipeline that allows automated processing of images from benthic moving platforms. Deep-sea (870 m depth) fauna was targeted in footage taken by the crawler “Wally” (an Internet Operated Vehicle), within the Ocean Network Canada (ONC) area of Barkley Canyon (Vancouver, BC; Canada). The image enhancement process consists mainly of a convolutional residual network, capable of generating enhanced images from a set of raw images. The images generated by the trained convolutional residual network obtained high values in metrics for underwater imagery assessment such as UIQM (~ 2.585) and UCIQE (2.406). The highest SSIM and PSNR values were also obtained when compared to the original dataset. The entire process has shown good classification results on an independent test data set, with an accuracy value of 66.44% and an Area Under the ROC Curve (AUROC) value of 82.91%, which were subsequently improved to 79.44% and 88.64% for accuracy and AUROC respectively. These results obtained with the enhanced images are quite promising and superior to those obtained with the non-enhanced datasets, paving the strategy for the on-board real-time processing of crawler imaging, and outperforming those published in previous papers.

Epidemic efficacy of Covid-19 vaccination against Omicron: An innovative approach using enhanced residual recurrent neural network.

The outbreak of COVID-19 has engulfed the entire world since the end of 2019, causing tremendous loss of lives. It has also taken a toll on the healthcare sector due to the inability to accurately predict the spread of disease as the arrangements for the essential supply of medical items largely depend on prior predictions. The objective of the study is to train a reliable model for predicting the spread of Coronavirus. The prediction capabilities of various powerful models such as the Autoregression Model (AR), Global Autoregression (GAR), Stacked-LSTM (Long Short-Term Memory), ARIMA (Autoregressive Integrated Moving Average), Facebook Prophet (FBProphet), and Residual Recurrent Neural Network (Res-RNN) were taken into consideration for predicting COVID-19 using the historical data of daily confirmed cases along with Twitter data. The COVID-19 prediction results attained from these models were not up to the mark. To enhance the prediction results, a novel model is proposed that utilizes the power of Res-RNN with some modifications. Gated Recurrent Unit (GRU) and LSTM units are also introduced in the model to handle the long-term dependencies. Neural Networks being data-hungry, a merged layer was added before the linear layer to combine tweet volume as additional features to reach data augmentation. The residual links are used to handle the overfitting problem. The proposed model RNN Convolutional Residual Network (RNNCON-Res) showcases dominating capability in country-level prediction 20 days ahead with respect to existing State-Of-The-Art (SOTA) methods. Sufficient experimentation was performed to analyze the prediction capability of different models. It was found that the proposed model RNNCON-Res has achieved 91% accuracy, which is better than all other existing models.

A Novel Joint Time-Frequency Spectrum Resources Sustainable Risk Prediction Algorithm Based on TFBRL Network for the Electromagnetic Environment

To protect the electromagnetic environment and understand its current state in a timely manner, monitoring the electromagnetic environment has great practical significance, while massive amounts of data are generated. It is crucial to utilize data mining technology to extract valuable information from these massive amounts of data for effective spectrum management. Traditional spectrum prediction methods do not integrate the prior information of spectrum resource occupancy, so that the prediction of the channel state of a single frequency point is of limited significance. To address these issues, the paper describes a dynamic threshold algorithm which mines bottom noise and spectrum resource occupancy from massive electromagnetic environment data. Moreover, the paper describes a joint time-frequency spectrum resource prediction algorithm based on the time-frequency block residual LSTM (TFBRL) network, which utilizes hourly time closeness, daily period, and annual trend as prior knowledge of spectrum resources. The TFBRL network comprises three main parts: (1) a residual convolution network with a squeeze-and-excitation (SE) attention mechanism, (2) a long short term memory (LSTM) model with memory ability to capture sequence latent information, and (3) a feature fusion module based on a matrix to combine time closeness, daily period, and annual trend feature components. Experimental results demonstrate that the TFBRL network outperforms the baseline networks, improving by 31.37%, 16.00% and 13.06% compared with the best baseline for MSE, RMSE and MAE, respectively. Thus, the TFBRL network has good risk prediction performance and lays the foundation for subsequent frequency scheduling.

Estimating seabed properties with a residual convolutional network

Deep learning can assist in characterizing seabeds using sources of opportunity such as shipping noise. While previous work focused on seabed classification, this study uses a residual convolutional neural network to find individual seabed properties. The training data were labeled with sound speed, density, attenuation, and thickness of the layer values of the top sediment layer. A comparison was made between predictive capabilities of ResNet-18 networks when trained to learn a single parameter and those trained to simultaneously learn multiple parameters. For stiff parameters—those with high information content in the data—learning an individual parameter performed better. These single parameter predictions are fundamentally different from a geoacoustic inversion for one parameter. In geoacoustic inversion, all other parameters are held at a fixed value. In deep learning, variability in all other parameters is contained in the training data, but the network focuses on features in the data related to a single property. The trained networks are applied to ship noise measured during the 2017 Seabed Characterization Experiment. [Work supported by the Office of Naval Research and the National Science Foundation’s REU program.]

Editorial Issue 34.2

Editorial Issue 34.2

Tool wear condition monitoring based on multi-sensor integration and deep residual convolution network

In order to guarantee machining quality and production efficiency and as well as to reduce downtime and cost, it is essential to receive information about the cutting tool condition and change it in time if necessary. To this end, tool condition monitoring systems are of great significance. Based on the data fusion technology of multi-sensor integration and the learning ability of deep residual network, a tool wear monitoring system is proposed in this paper. For data acquisition, multiple sensors are used to collect vibration, noise and acoustic emission signals in the machining process. For signal processing, the data fusion method of angular summation of matrices is used, so that the multi-source data are fused into two-dimensional pictures. Then, the feature extraction module of the proposed system uses the pictures as input and takes advantage of the deep residual convolutional network in extracting the deep features from the pictures, and finally the identification module completes the recognition of the tool wear type. To verify its feasibility, a testing bed is built on a CNC milling machine, and multi-sensor data are collected during the machining process of a simple workpiece with one of the two selected cutting tools each time. The proposed system is trained using the collected data and then is used to monitor the wear condition of a new cutting tool by collecting real-time data under similar condition. The results show that the accuracy of wear state recognition is as high as 90%, which verifies the feasibility of the proposed tool wear monitoring system.

Unconstrained vocal pattern recognition algorithm based on attention mechanism

Deep learning-based voiceprint recognition methods rely heavily on adequate datasets, especially those closer to the natural environment and more complex under unconstrained conditions. Yet, the data types of open-source speech datasets are too homogeneous nowadays, and there are some differences with the address collected in natural application environments. For few Chinese datasets used, this paper proposes and produces an unconstrained Chinese speech dataset with richer data types closer to those collected in a natural environment. To address the inadequate extraction of acoustic features in the unconstrained speech dataset, a new two-dimensional convolutional residual network structure based on the attention mechanism is designed and applied to acoustic feature extraction. The residual block structure in the residual network is improved by the SE module and the CBAM module to obtain the SE-Cov2d and CSA-Cov2d models respectively. Finally, it is experimentally demonstrated that the attention mechanism can help the network focus on more critical feature information and fuse more differentiated features in feature extraction.

LIRNet: A Lightweight Inception Residual Convolutional Network for Solar Panel Defect Classification

Solar-cell panels use sunlight as a source of energy to generate electricity. However, the performances of solar panels decline when they degrade, owing to defects. Some common defects in solar-cell panels include hot spots, cracking, and dust. Hence, it is important to efficiently detect defects in solar-cell panels and repair them. In this study, we propose a lightweight inception residual convolutional network (LIRNet) to detect defects in solar-cell panels. LIRNet is a neural network model that utilizes deep learning techniques. To achieve high model performance on solar panels, including high fault detection accuracy and processing speed, LIRNet draws on hierarchical learning, which is a two-phase solar-panel-defect classification method. The first phase is the data-preprocessing stage. We use the K-means clustering algorithm to refine the dataset. The second phase is the training of the model. We designed a powerful and lightweight neural network model to enhance accuracy and speed up the training time. In the experiment, LIRNet improved the accuracy by approximately 8% and performed ten times faster than EfficientNet.

Pavement Roughness Grade Recognition Based on One-dimensional Residual Convolutional Neural Network.

A pavement's roughness seriously affects its service life and driving comfort. Considering the complexity and low accuracy of the current recognition algorithms for the roughness grade of pavements, this paper proposes a real-time pavement roughness recognition method with a lightweight residual convolutional network and time-series acceleration. Firstly, a random input pavement model is established by the white noise method, and the pavement roughness of a 1/4 vehicle vibration model is simulated to obtain the vehicle vibration response data. Then, the residual convolutional network is used to learn the deep-level information of the sample signal. The residual convolutional neural network recognizes the pavement roughness grade quickly and accurately. The experimental results show that the residual convolutional neural network has a robust feature-capturing ability for vehicle vibration signals, and the classification features can be obtained quickly. The accuracy of pavement roughness classification is as high as 98.7%, which significantly improves the accuracy and reduces the computational effort of the recognition algorithm, and is suitable for pavement roughness grade classification.

MSRConvNet: Classification of railway track defects using multi-scale residual convolutional neural network

The development of an automated rail line defect classification system is of great benefit, as railway tracks must be periodically monitored and inspected to guarantee the safety of rail transportation. In this paper, an effective multi-scale residual convolutional network (MSRConvNet) model is proposed to classify the different types of railway track defects. The skip connections with residual learning blocks are used to increase the effectiveness of the network. The multi-scale convolutions are connected with parallel and two skip connections in the structure to distribute detailed feature maps with each other. Therefore, different scale feature maps can be extracted. The data augmentation method is performed to ensure a balanced class distribution and to eliminate the negative effect of the imbalanced dataset. The proposed model is compared with both benchmark deep learning models and the different variations of the designed network. The results verify that the proposed model can reach superior classification fulfillment, and the MSRConvNet provides an overall accuracy of 99.83%, precision of 99.83%, sensitivity of 99.83%, specificity of 99.94%, F1-score of 99.83%, and Matthew’s correlation coefficient of 99.78% for four defect classes.

Weakly supervised semantic segmentation of histological tissue via attention accumulation and pixel-level contrast learning

Objective. Histopathology image segmentation can assist medical professionals in identifying and diagnosing diseased tissue more efficiently. Although fully supervised segmentation models have excellent performance, the annotation cost is extremely expensive. Weakly supervised models are widely used in medical image segmentation due to their low annotation cost. Nevertheless, these weakly supervised models have difficulty in accurately locating the boundaries between different classes of regions in pathological images, resulting in a high rate of false alarms Our objective is to design a weakly supervised segmentation model to resolve the above problems. Approach. The segmentation model is divided into two main stages, the generation of pseudo labels based on class residual attention accumulation network (CRAANet) and the semantic segmentation based on pixel feature space construction network (PFSCNet). CRAANet provides attention scores for each class through the class residual attention module, while the Attention Accumulation (AA) module overlays the attention feature maps generated in each training epoch. PFSCNet employs a network model containing an inflated convolutional residual neural network and a multi-scale feature-aware module as the segmentation backbone, and proposes dense energy loss and pixel clustering modules are based on contrast learning to solve the pseudo-labeling-inaccuracy problem. Main results. We validate our method using the lung adenocarcinoma (LUAD-HistoSeg) dataset and the breast cancer (BCSS) dataset. The results of the experiments show that our proposed method outperforms other state-of-the-art methods on both datasets in several metrics. This suggests that it is capable of performing well in a wide variety of histopathological image segmentation tasks. Significance. We propose a weakly supervised semantic segmentation network that achieves approximate fully supervised segmentation performance even in the case of incomplete labels. The proposed AA and pixel-level contrast learning also make the edges more accurate and can well assist pathologists in their research.