Dilated Convolutional Neural Network Research Articles

Multi-channel and multi-scale separable dilated convolutional neural network with attention mechanism for flue-cured tobacco classification

Multi-channel and multi-scale separable dilated convolutional neural network with attention mechanism for flue-cured tobacco classification

DCT-GAN: Dilated Convolutional Transformer-Based GAN for Time Series Anomaly Detection

Time series anomaly detection (TSAD) is an essential problem faced in several fields, e.g., fault detection, fraud detection, and intrusion detection, etc. Although TSAD is a crucial problem in anomaly detection, few solutions in anomaly detection are suitable for it at present. Recently, some researchers use GAN-based methods such as TAnoGAN and TadGAN to solve TSAD problem. However, problems such as model collapse, low generalization capability and poor accuracy still exist. In this article, we proposed a Dilated Convolutional Transformer-based GAN (DCT-GAN) to enhance accuracy and improve generalization capability of the model. Specifically, DCT-GAN utilize several generators and a single discriminator to alleviate the mode collapse problem. Each generator consists of a dilated convolutional neural network and a Transformer block to obtain fine-grained and coarse-grained information of the time series, which is a useful component to improve generalization capability. We also use weight-based mechanism to balance these generators. Experiments verify the effectiveness of our method and each part of DCT-GAN.

AAD-Net: Advanced end-to-end signal processing system for human emotion detection & recognition using attention-based deep echo state network

Speech signals are the most convenient way of communication between human beings and the eventual method of Human–Computer Interaction (HCI) to exchange emotions and information. Recognizing emotions from speech signals is a challenging task due to the sparse nature of emotional data and features. In this article, we proposed a Deep Echo-State-Network (DeepESN) system for emotion recognition with a dilated convolution neural network and multi-headed attention mechanism. To reduce the model complexity, we incorporate a DeepESN that combines reservoir computing for higher-dimensional mapping. We also used fine-tuned Sparse Random Projection (SRP) to reduce dimensionality and adopted an early fusion strategy to fuse the extracted cues and passed the joint feature vector via a classification layer to recognize emotions. Our proposed model is evaluated on two public speech corpora, EMO-DB and RAVDESS, and tested for subject/speaker-dependent/independent performance. The results show that our proposed system achieves a high recognition rate, 91.14, 85.57 for EMO-DB, and 82.01, 77.02 for RAVDESS, using speaker-dependent and independent experiments, respectively. Our proposed system outperforms the State-of-The-Art (SOTA) while requiring less computational time.

A Systematic Approach of Advanced Dilated Convolution Network for Speaker Identification

Over the years, the Speaker recognition area is facing various challenges in identifying the speakers accurately. Remarkable changes came into existence with the advent of deep learning algorithms. Deep learning made a remarkable impact on the speaker recognition approaches. This paper introduces a simple novel architectural approach to an advanced Dilated Convolution network. The novel idea is to induce the well-structured log-Melspectrum to the proposed dilated convolution neural network and reduce the number of layers to 11. The network utilizes the Global average pooling to accumulate the outputs from all layers to get the feature vector representation for classification. Only 13 coefficients are extracted per frame of each speech sample. This novel dilated convolution neural network exhibits an accuracy of 90.97%, Equal Error Rate(EER) of 3.75% and 207 Seconds training time outperforms the existing systems on the LibriSpeech corpus.

Performance evaluation of deep learning architectures for load and temperature forecasting under dataset size constraints and seasonality

Buildings and their energy systems have unique characteristics and temporally changing dynamics. Additionally, building data have strong seasonality. Therefore, a deep learning model with good adaptability (i.e., high performance with little data) is necessary for model predictive control of buildings. Considering the specificity of the building-energy field, we benchmarked six deep learning architectures: the multilayer perceptron, simple recurrent neural network (RNN), long short-term memory, gated recurrent unit (GRU), dilated convolutional neural network, and transformer. Moreover, the data similarity analysis method was developed to analyze the effect of data seasonality on forecasting performance. A publicly accessible data generator and the open-source Python library DeepTimeSeries were used to design a reproducible benchmark. The zone temperatures and thermal loads over a future 24-h period were the forecasting targets. The benchmark results, with varying training dataset sizes from 0.3 to 0.9 y, demonstrated that the transformer architecture performs best, especially on small training datasets. The GRU and RNN were the second- and third-best performers, whereas the rank of other architectures varied depending on the training dataset size and forecasting targets. The similarity analysis revealed that simply increasing the dataset size does not necessarily improve performance, indicating the importance of training with highly similar data for the forecasting period.

Enhancement in Speaker Identification through Feature Fusion using Advanced Dilated Convolution Neural Network

There are various challenges in identifying the speakers accurately. The Extraction of discriminative features is a vital task for accurate identification in the speaker identification task. Nowadays, speaker identification is widely investigated using deep learning. The complex and noisy speech data affects the performance of Mel Frequency Cepstral Coefficients (MFCC); hence, MFCC fails to represent the speaker characteristics accurately. In this proposed work, a novel text-independent speaker identification system is developed to enhance the performance by fusion of Log-MelSpectrum and excitation features. The excitation information is obtained due to the vibration of vocal folds, and it is represented using Linear Prediction (LP) residual. The various types of features extracted from the excitation are residual phase, sharpness, Energy of Excitation (EoE), and Strength of Excitation (SoE). The extracted features were processed with the dilated convolution neural network (dilated CNN) to fulfill the identification task. The extensive evaluation showed that the fusion of excitation features gives better results than the existing methods. The accuracy reaches 94.12% for 11 complex classes and 91.34% for 80 speakers, and Equal Error Rate (EER) is reduced to 1.16% for the proposed model. The proposed model is tested with the Librispeech corpus using Matlab 2021b tool, outperforming the existing baseline models. The proposed model achieves an accuracy improvement of 1.34% compared to the baseline system.

HARDC : A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN

Deep learning-based models have achieved significant success in detecting cardiac arrhythmia by analyzing ECG signals to categorize patient heartbeats. To improve the performance of such models, we have developed a novel hybrid hierarchical attention-based bidirectional recurrent neural network with dilated CNN (HARDC) method for arrhythmia classification. This solves problems that arise when traditional dilated convolutional neural network (CNN) models disregard the correlation between contexts and gradient dispersion. The proposed HARDC fully exploits the dilated CNN and bidirectional recurrent neural network unit (BiGRU–BiLSTM) architecture to generate fusion features. As a result of incorporating both local and global feature information and an attention mechanism, the model’s performance for prediction is improved. By combining the fusion features with a dilated CNN and a hierarchical attention mechanism, the trained HARDC model showed significantly improved classification results and interpretability of feature extraction on the PhysioNet 2017 challenge dataset. Sequential Z-Score normalization, filtering, denoising, and segmentation are used to prepare the raw data for analysis. CGAN (Conditional Generative Adversarial Network) is then used to generate synthetic signals from the processed data. The experimental results demonstrate that the proposed HARDC model significantly outperforms other existing models, achieving an accuracy of 99.60%, F1 score of 98.21%, a precision of 97.66%, and recall of 99.60% using MIT-BIH generated ECG. In addition, this approach significantly reduces run time when using dilated CNN compared to normal convolution. Overall, this hybrid model demonstrates an innovative and cost-effective strategy for ECG signal compression and high-performance ECG recognition. Our results indicate that an automated and highly computed method to classify multiple types of arrhythmia signals holds considerable promise.

On Bayesian Optimization-Based Residual CNN for Estimation of Inter-Turn Short Circuit Fault in PMSM

Interturn short circuit (ITSC) fault diagnosis at its early stage is very essential to improve the security of permanent magnet synchronous motors. In this article, a Bayesian optimization (BO) based residual convolutional neural network (CNN) algorithm for ITSC fault diagnosis was proposed. There are mainly two aspects of the contributions. First, it is a challenge to apply a conventional CNN on time-series signal tasks as they can only look back on history with a liner size, which will limit the network depth. Moreover, to obtain enough characteristics from acquired signals, the proposed algorithm requires adequate network depth, which may result in degradation difficulties. To solve these problems, a residual connection is embedded into the dilated CNN. Second, with the increase of network depth, the possible combination of hyperparameters will grow geometrically, thus the hyperparameters tuning will cost considerable time. To overcome this, the BO algorithm is adopted to select the optimal hyperparameter combination automatically. To demonstrate the effectiveness of the proposed algorithm, a motor fault experiment with various operating conditions was conducted on the motor that can be set for 17 fault severity levels. The test results and comparisons with other five algorithms show the advantage of the proposed algorithm.

High-precision demodulation method for the cobweb FBG sensor network.

To improve the demodulation accuracy and speed of the cobweb fiber Bragg grating (FBG) sensor network, a demodulation algorithm based on a one-dimensional (1D) dilated convolutional neural network (CNN) combined with improved wavelet adaptive threshold de-noising is proposed. The improved wavelet adaptive threshold de-noising algorithm is used to de-noise several highly overlapping sensing signals for accurately measuring optical fiber sensing signals. Using a well-trained 1D dilated CNN model achieves extremely low signal demodulation errors, even with highly overlapping signals. Experiments show that the demodulation scheme improves the detection accuracy of the cobweb FBG sensor network and shortens detection time. Determination of the peak wavelengths of the four highly overlapping sensing signals achieves a root-mean-square error of better than 0.10pm and an average demodulation time of 15.2ms.

A Minority Class Balanced Approach Using the DCNN-LSTM Method to Detect Human Wrist Fracture.

The emergency department of hospitals receives a massive number of patients with wrist fracture. For the clinical diagnosis of a suspected fracture, X-ray imaging is the major screening tool. A wrist fracture is a significant global health concern for children, adolescents, and the elderly. A missed diagnosis of wrist fracture on medical imaging can have significant consequences for patients, resulting in delayed treatment and poor functional recovery. Therefore, an intelligent method is needed in the medical department to precisely diagnose wrist fracture via an automated diagnosing tool by considering it a second option for doctors. In this research, a fused model of the deep learning method, a convolutional neural network (CNN), and long short-term memory (LSTM) is proposed to detect wrist fractures from X-ray images. It gives a second option to doctors to diagnose wrist facture using the computer vision method to lessen the number of missed fractures. The dataset acquired from Mendeley comprises 192 wrist X-ray images. In this framework, image pre-processing is applied, then the data augmentation approach is used to solve the class imbalance problem by generating rotated oversamples of images for minority classes during the training process, and pre-processed images and augmented normalized images are fed into a 28-layer dilated CNN (DCNN) to extract deep valuable features. Deep features are then fed to the proposed LSTM network to distinguish wrist fractures from normal ones. The experimental results of the DCNN-LSTM with and without augmentation is compared with other deep learning models. The proposed work is also compared to existing algorithms in terms of accuracy, sensitivity, specificity, precision, the F1-score, and kappa. The results show that the DCNN-LSTM fusion achieves higher accuracy and has high potential for medical applications to use as a second option.

Reducing Moisture Effects on Soil Organic Carbon Content Estimation in Vis-NIR Spectra With a Deep Learning Algorithm

When estimating soil organic carbon (SOC) using visible and near-infrared (Vis-NIR) spectra measured in situ, the interference of soil moisture content (SMC) needs to be eliminated. The existing SMC removal methods are mainly based on spectral transformation, but they change the original form of the soil spectrum. In this paper, a new deep learning-based SMC influence removal network (MIRNet) is proposed to establish the relationship between the spectra of moist soil and that of dry soil. This method constructs a spectral extraction module (SEM) with two one-dimensional (1-D) ghost modules to extract soil spectral characteristics and a context extraction module (CEM) with a two-layer dilated convolutional neural network (DiCNN) to extract the context information of the spectra. Then these extracted features are combined to reconstruct the SMC influence with a two-layer deconvolution using residual learning (Res). Finally, a new loss function that combining spectral distance and spectral shape measurement (D-S loss) is proposed. The input of MIRNet is the moist soil spectra, and the output is the dry soil spectra. Black soil collected from Harbin and yellow-brown soil collected from Nanjing are selected as the research objects. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$R^{2}$</tex-math></inline-formula> reaches 0.703, 0.747, 0.907, 0.892, 0.866, 0.907, and 0.926, respectively, when using spectra processed by external parameter orthogonalization (EPO), orthogonal signal correction (OSC), support vector regression (SVR), convolutional neural network (CNN), deep neural network (DNN), denoising convolutional neural network (DnCNN), and MIRNet. Therefore, the proposed MIRNet achieves competitive results compared with these state-of-the-art methods.

Hybrid Multi-Strategy Aquila Optimization with Deep Learning Driven Crop Type Classification on Hyperspectral Images

Hyperspectral imaging instruments could capture detailed spatial information and rich spectral signs of observed scenes. Much spatial information and spectral signatures of hyperspectral images (HSIs) present greater potential for detecting and classifying fine crops. The accurate classification of crop kinds utilizing hyperspectral remote sensing imaging (RSI) has become an indispensable application in the agricultural domain. It is significant for the prediction and growth monitoring of crop yields. Amongst the deep learning (DL) techniques, Convolution Neural Network (CNN) was the best method for classifying HSI for their incredible local contextual modeling ability, enabling spectral and spatial feature extraction. This article designs a Hybrid Multi-Strategy Aquila Optimization with a Deep Learning-Driven Crop Type Classification (HMAODL-CTC) algorithm on HSI. The proposed HMAODL-CTC model mainly intends to categorize different types of crops on HSI. To accomplish this, the presented HMAODL-CTC model initially carries out image preprocessing to improve image quality. In addition, the presented HMAODL-CTC model develops dilated convolutional neural network (CNN) for feature extraction. For hyperparameter tuning of the dilated CNN model, the HMAO algorithm is utilized. Eventually, the presented HMAODL-CTC model uses an extreme learning machine (ELM) model for crop type classification. A comprehensive set of simulations were performed to illustrate the enhanced performance of the presented HMAODL-CTC algorithm. Extensive comparison studies reported the improved performance of the presented HMAODL-CTC algorithm over other compared methods.

Solid waste mapping based on very high resolution remote sensing imagery and a novel deep learning approach

The urbanization worldwide leads to the rapid increase of solid waste, posing a threat to environment and people’s wellbeing. However, it is challenging to detect solid waste sites with high accuracy due to complex landscape, and very few studies considered solid waste mapping across multi-cities and in large areas. To tackle this issue, this study proposes a novel deep learning model for solid waste mapping from very high resolution remote sensing imagery. By integrating a multi-scale dilated convolutional neural network (CNN) and a Swin-Transformer, both local and global features are aggregated. Experiments in China, India and Mexico indicate that the proposed model achieves high performance with an average accuracy of 90.62%. The novelty lies in the fusion of CNN and Transformer for solid waste mapping in multi-cities without the need for pixel-wise labelled data. Future work would consider more sophisticated methods such as semantic segmentation for fine-grained solid waste classification.

A Hybrid Residential Short-Term Load Forecasting Method Using Attention Mechanism and Deep Learning

Development in economics and social society has led to rapid growth in electricity demand. Accurate residential electricity load forecasting is helpful for the transformation of residential energy consumption structure and can also curb global climate warming. This paper proposes a hybrid residential short-term load forecasting framework (DCNN-LSTM-AE-AM) based on deep learning, which combines dilated convolutional neural network (DCNN), long short-term memory network (LSTM), autoencoder (AE), and attention mechanism (AM) to improve the prediction results. First, we design a T-nearest neighbors (TNN) algorithm to preprocess the original data. Further, a DCNN is introduced to extract the long-term feature. Secondly, we combine the LSTM with the AE (LSTM-AE) to learn the sequence features hidden in the extracted features and decode them into output features. Finally, the AM is further introduced to extract and fuse the high-level stage features to achieve the prediction results. Experiments on two real-world datasets show that the proposed method is good at capturing the oscillation characteristics of low-load data and outperforms other methods.

Root cause diagnosis for process faults based on multisensor time-series causality discovery

Root cause diagnosis (RCD) focuses on locating the critical root causes and identifying the propagation paths of the industrial process faults, which is superior to conventional fault diagnosis methods and has attracted extensive attention. However, RCD is challenging in terms of dense sensor layout and diversified interconnected subsystems in complex industrial processes, since a fault originating in one unit can propagate throughout the entire plant along with the flow of information and material, obscuring its root causes. Moreover, the previous RCD methods ignore the more crucial temporal information between multisensor time-series, suffering from the disadvantages of requiring expert knowledge and responding untimely. Therefore, a novel data-driven RCD methodology named multisensor time-series causality discovery (MTCD) is proposed for industrial processes fault diagnosis. Firstly, a temporal registration network (TRN) based on the dilated convolutional neural network (DCNN) is proposed to extract the temporal correlation between time-series and implement the time-series prediction. Ulteriorly, a permutation importance causality validation (PICV) is designed to verify the causality between time-series based on the TRN prediction results without prior knowledge or expert experience. Besides, a causal time delay discovery approach based on layerwise relevance propagation (LRP) is presented by interpreting the weights of the trained TRN. Finally, we demonstrate the effectiveness of the proposed method with a stochastic synthesis process and the Tennessee Eastman process. The experimental results show that the proposed method has better performance in both root cause localization and propagation path identification.

DDCNet: Deep dilated convolutional neural network for dense prediction

Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently larger effective receptive field (ERF) and a higher resolution of spatial features within a network are essential for providing higher-resolution dense estimates. In this work, we present a systemic approach to design network architectures that can provide a larger receptive field while maintaining a higher spatial feature resolution. To achieve a larger ERF, we utilized dilated convolutional layers. By aggressively increasing dilation rates in the deeper layers, we were able to achieve a sufficiently larger ERF with a significantly fewer number of trainable parameters. We used optical flow estimation problem as the primary benchmark to illustrate our network design strategy. The benchmark results (Sintel, KITTI, and Middlebury) indicate that our compact networks can achieve comparable performance in the class of lightweight networks.

A multiscale dilated convolution and mixed-order attention-based deep neural network for monocular depth prediction

Recovering precise depth information from different scenes has become a popular subject in the semantic segmentation and virtual reality fields. This study presents a multiscale dilated convolution and mixed-order attention-based deep neural network for monocular depth recovery. Specifically, we design a multilevel feature enhancement scheme to enhance and fuse high-resolution and low-resolution features on the basis of mixed-order attention. Moreover, a multiscale dilated convolution module that combines four different dilated convolutions is explored for deriving multiscale information and increasing the receptive field. Recent studies have shown that the design of loss terms is crucial to depth prediction. Therefore, an efficient loss function that combines the ℓ1 loss, gradient loss, and classification loss is also designed to promote rich details. Experiments on three public datasets show that the presented approach achieves better performance than state-of-the-art depth prediction methods.

Simple dilated convolutional neural network for quantitative modeling based on near infrared spectroscopy techniques

A simple deep convolutional neural network architecture had been developed and applied to the establishment of a quantitative model based on near infrared spectroscopy techniques. The network architecture only contained general convolutional layers and dilated convolutional layers. The determination coefficient was used as a criterion to stop the training process of the neural network. Three data sets were used to test the performance of the neural network. The major results are (1) quantitative model can be established within one million iterations; (2) the quantitative model established on one spectrometer can be applied to other spectrometers of same manufacturer and even the same kind of spectrometer of different manufacturer; (3) simultaneous quantitative analysis of four components in grain samples. This study provided a new strategy to apply techniques of deep neural network in quantitative analysis.

A dual-branch hybrid dilated CNN model for the AI-assisted segmentation of meningiomas in MR images

Background and objective:Treatment for meningiomas usually includes surgical removal, radiation therapy, and chemotherapy. Accurate segmentation of tumors significantly facilitates complete surgical resection and precise radiotherapy, thereby improving patient survival. In this paper, a deep learning model is constructed for magnetic resonance T1-weighted Contrast Enhancement (T1CE) images to develop an automatic processing scheme for accurate tumor segmentation. Methods:In this paper, a novel Convolutional Neural Network (CNN) model is proposed for the accurate meningioma segmentation in MR images. It can extract fused features in multi-scale receptive fields of the same feature map based on MR image characteristics of meningiomas. The attention mechanism is added as a helpful addition to the model to optimize the feature information transmission. Results and conclusions:The results were evaluated on two internal testing sets and one external testing set. Mean Dice Similarity Coefficient (DSC) values of 0.886, 0.851, and 0.874 are demonstrated, respectively. In this paper, a deep learning approach is proposed to segment tumors in T1CE images. Multi-center testing sets validated the effectiveness and generalization of the method. The proposed model demonstrates state-of-the-art tumor segmentation performance.

A Method for Predicting the Remaining Life of Rolling Bearings Based on Multi-Scale Feature Extraction and Attention Mechanism

In response to the problems of difficult identification of degradation stage start points and inadequate extraction of degradation features in the current rolling bearing remaining life prediction method, a rolling bearing remaining life prediction method based on multi-scale feature extraction and attention mechanism is proposed. Firstly, this paper takes the normalized bearing vibration signal as input and adopts a quadratic function as the RUL prediction label, avoiding identifying the degradation stage start point. Secondly, the spatial and temporal features of the bearing vibration signal are extracted using the dilated convolutional neural network and LSTM network, respectively, and the channel attention mechanism is used to assign weights to each degradation feature to effectively use multi-scale information. Finally, the mapping of bearing degradation features to remaining life labels is achieved through a fully connected layer for the RUL prediction of bearings. The proposed method is validated using the PHM 2012 Challenge bearing dataset, and the experimental results show that the predictive performance of the proposed method is superior to that of other RUL prediction methods.