Multilayer Convolutional Neural Network Research Articles

CoATR: A Convolutional Autoregressive Tensor-Ring decomposition method for sparse spatio-temporal traffic data

Spatio-temporal traffic data collected by various sensing systems have chronic issues of missing and corruption, thus accurate data imputation and prediction have been extensively researched. Previous most methods can be divided into two categories: model-driven methods with physical explanations and data-driven deep learning methods. These methods all achieve promising results due to their respective advantages. However they have some limitations: model-driven methods are often linear and may not accurately model the spatio-temporal complexity, while deep learning methods often lack the physical reality making them probe to over-fitting. Inspired by both, we propose a new Convolutional-based generalized Autoregressive Tensor-Ring decomposition method (CoATR) for the completion of spatio-temporal data. CoATR not only retains the advantages of the tensor-ring (TR) decomposition model for global modeling of spatio-temporal data but also exploits the ability of deep networks to model nonlinear features. To be specific, we introduce TR decomposition to capture the global low-rankness and employ multilayer convolutional neural networks to model the global complex interactions among the TR factors for exploring the nonlinear features of the spatio-temporal data. Moreover, we design a new autoregressive network to further explore the local temporal variation in the data. Extensive experiments on a variety of common traffic datasets have validated the effectiveness and superiority of the CoATR over classical model-driven methods and other state-of-the-art data-driven deep learning methods.

Research on music genre recognition method based on deep learning

In this paper, we explore music genre recognition using deep learning methods, examining the application of feature extraction, model construction, and performance evaluation for different music genres. During the data preparation and preprocessing stages, data augmentation and normalization techniques were employed to enhance the model’s generalization capabilities. By constructing multilayer convolutional neural networks (CNNs) and recurrent neural networks (RNNs), we achieved automatic recognition of music genres. In the experimental results analysis, we compared the accuracy and training time of different models, validating the effectiveness of deep learning in the field of music genre recognition. The limitations of deep learning methods and future research directions are also discussed, providing a reference for further studies in music information processing. This study delves into the issue of music genre recognition and proposes a deep learning-based approach. This method leverages neural networks to extract features and learn from audio data, enabling accurate classification of different music genres. Extensive experiments have demonstrated that our method achieves highly satisfactory results in music genre recognition tasks. Furthermore, we optimized the deep learning models, improving their generalization capabilities and accuracy. Our research offers the music industry an efficient and accurate method for music genre recognition, providing new perspectives and technical support for research and applications in the music field.

Design of Chinese painting style classification model based on multi-layer aggregation CNN

This study delves deeply into exploring the artistic value of traditional Chinese painting (TCP) and aims to bridge the gap between its fundamental characteristics and the realm of human emotions. To achieve this, a novel convolutional neural network (CNN)-based classification model for TCP emotions is proposed. By thoroughly analyzing the distinct emotional mapping relationships inherent in TCP, a comprehensive framework is developed. Notably, emotional feature regions are accurately extracted using image saliency, and a multi-layer aggregation recalibrated emotional feature module is seamlessly integrated into the CNN network structure. This integration strengthens the activation of features that significantly influence TCP emotions. Moreover, a method of multi-category weighted activation localization is skillfully employed to classify Chinese painting emotions within the CMYK (cyan magenta yellow black) color space. The empirical results convincingly demonstrate that our algorithm surpasses existing approaches such as VGG-19, GoogLeNet, ResNet-50, and WSCNet in the task of TCP emotion recognition, achieving an impressive accuracy of 92.36%, the largest error is 0.191. This improvement signifies the advancements made by our model in accurately capturing and understanding the emotional nuances within TCP. By outperforming previous methods, our research contributes to the convergence of multimedia technology and cultural education.

TAWFN: a deep learning framework for protein function prediction.

Proteins play pivotal roles in biological systems, and precise prediction of their functions is indispensable for practical applications. Despite the surge in protein sequence data facilitated by high-throughput techniques, unraveling the exact functionalities of proteins still demands considerable time and resources. Currently, numerous methods rely on protein sequences for prediction, while methods targeting protein structures are scarce, often employing convolutional neural networks (CNN) or graph convolutional networks (GCNs) individually. To address these challenges, our approach starts from protein structures and proposes a method that combines CNN and GCN into a unified framework called the two-model adaptive weight fusion network (TAWFN) for protein function prediction. First, amino acid contact maps and sequences are extracted from the protein structure. Then, the sequence is used to generate one-hot encoded features and deep semantic features. These features, along with the constructed graph, are fed into the adaptive graph convolutional networks (AGCN) module and the multi-layer convolutional neural network (MCNN) module as needed, resulting in preliminary classification outcomes. Finally, the preliminary classification results are inputted into the adaptive weight computation network, where adaptive weights are calculated to fuse the initial predictions from both networks, yielding the final prediction result. To evaluate the effectiveness of our method, experiments were conducted on the PDBset and AFset datasets. For molecular function, biological process, and cellular component tasks, TAWFN achieved area under the precision-recall curve (AUPR) values of 0.718, 0.385, and 0.488 respectively, with corresponding Fmax scores of 0.762, 0.628, and 0.693, and Smin scores of 0.326, 0.483, and 0.454. The experimental results demonstrate that TAWFN exhibits promising performance, outperforming existing methods. The TAWFN source code can be found at: https://github.com/ss0830/TAWFN.

Advanced deepfake detection with enhanced Resnet-18 and multilayer CNN max pooling

Advanced deepfake detection with enhanced Resnet-18 and multilayer CNN max pooling

Phishing Website Detection Using Improved Multilayered Convolutional Neural Networks

Phishing Website Detection Using Improved Multilayered Convolutional Neural Networks

Translating Test Responses to Images for Test-termination Prediction via Multiple Machine Learning Strategies

Failure diagnosis is a software-based, data-driven procedure. Collecting an excessive amount of fail data not only increases the overall test cost but can also potentially reduce diagnostic resolution. Thus, test-termination prediction is proposed to dynamically determine the appropriate failing test pattern to terminate testing, producing an amount of test data that is sufficient for an accurate diagnosis analysis. In this work, we describe a set of novel methods utilizing advanced machine learning techniques for efficient test-termination prediction. To implement this approach, we first generate images representing failing test responses from failure-log files. These images are then used to train a multi-layer convolutional neural network (CNN) incorporating a residual block. The trained CNN model leverages the images and known diagnostic results to determine the optimal test-termination strategy within the testing process, ensuring efficient and high-quality diagnosis. In addition to the integration of test response-to-image translation, our approach harnesses two cutting-edge learning strategies to enhance fail data and boost performance in subsequent tasks. The first strategy is transfer learning, which utilizes sample-label information from one circuit to guide the decision of whether to continue or stop testing for another circuit lacking labels. The second strategy involves the use of a generative deep model to generate fail data in the form of synthetic images. This technique increases the modeling effectiveness by expanding the volume of training samples. Experimental results conducted on actual failing chips and standard benchmarks validate that our proposed method surpasses existing approaches. Our method creates opportunities to harness the power of recent advances in machine learning for improving test and diagnosis efficiency.

IMC-ResNet: Atrial fibrillation detection method based on interlayer multiscale coupling

Atrial fibrillation(AF) is one of the most common cardiac arrhythmias, and reliable detection of it is of significant importance. This study proposes a multilayer convolutional neural network for AF detection, which introduces the Multiscale Information Interaction module composed of a Detail Enhancer and a Context Information Extractor to achieve the extraction and coupling of multiscale information between layers. The Detail Enhancer is composed of multiscale transposed convolutions to encode waveform details in the electrocardiogram (ECG). The Context Information Extractor is composed of multiscale dilated convolutions to encode the morphological information of the ECG. Furthermore, the Multiscale Information Interaction module is used in conjunction with residual blocks to model the surface feature correlation and intrinsic abstract structure of AF signals. This approach extracts implicit information of AF from ECG signals, achieving high-precision and robust detection of AF. Five-fold cross-validation on the AFDB dataset resulted in an accuracy of 99.56% and an F1-score of 99.65%. Inter-patient testing on the clinical SPHDB database yielded an accuracy of 96.17% and an F1-score of 96.14%. In addition, this study conducted experiments to evaluate the model’s robustness against noise, yielding favorable results across four types of noise tests. The results indicate that the proposed method has great potential for application in clinical auxiliary diagnosis based on wearable devices.

Motor imagery electroencephalography channel selection based on deep learning: A shallow convolutional neural network

Electroencephalography (EEG) motor imagery (MI) signals have recently attracted much attention because of their potential to communicate with the surrounding environment in a specific way without the need for muscular and physical movement. Despite these advantages, these signals are difficult to detect due to their low signal to noise (SNR) rate and non-stationary and dynamic nature. Convolutional neural networks (CNN) can extract appropriate spatial and temporal features without the need for separate feature extraction and classification steps. Clean input data for CNN significantly improves its performance, but sometimes, common interference occurs between multi-channel signals. This challenge, along with the noisy EEG signals, degrades the performance of CNN networks. This paper presents a channel selection method based on convolutional neural networks to obviate these challenges. The proposed shallow convolutional neural network (SCNN) is designed with temporal convolution and pointwise convolution (using 1×1 convolution) to select the best channel with minimal computational load. Following the channel selection step, the multi-layer fusion CNN model was used to classify the signals. Choosing suitable and relevant EEG channels for motor imagery tasks makes it possible to create appropriate inputs for the classification model so that the model can be improved in the end. For High Gamma Dataset and Brian-Computer Interface (BCI) Competition IV-2a, the following accuracies were obtained: 81.15% and 72.01%, which are higher than when the other channel selections such as Mutual Information, Sequential Feature Forward Selection (SFFS) and wrapper methods are used.

[formula omitted][formula omitted]ave [formula omitted]earner: Predicting wave farms power output using effective meta-learner deep gradient boosting model: A case study from Australian coasts

Precise prediction of wave energy is indispensable and holds immense promise as ocean waves have a power capacity of 30–40 kW/m along the coast. Utilising this energy source does not generate harmful emissions, making it a superior substitute for fossil fuel-based energy. The computational expense associated with simulating and computing intricate hydrodynamic interactions in wave farms restricts optimisation methods to a few thousand evaluations and makes a challenging situation for training in deep neural prediction models. To address this issue, we propose a new solution: a Meta-learner gradient boosting method that employs four multi-layer convolutional dense neural network surrogate models combined with an optimised extreme gradient boosting. In order to train and validate the predictive model, we used four wave farm datasets, including the absorbed power outputs and 2D coordinates of wave energy converters (WECs) located along the southern coast of Australia, Adelaide, Sydney, Perth and Tasmania. Furthermore, the capability of the transfer learning strategy is evaluated. The WECs used in this study are of the fully submerged three-tether converter type, similar to the CETO prototype. The effectiveness of the proposed approach is assessed by comparing it with 15 well-established and effective machine learning (ML) methods. The experimental findings indicate that the proposed model is competitive with other ML and deep learning approaches, exhibiting considerable accuracy of 88.8%, 90.0%, 90.3%, and 84.4% in Adelaide, Perth, Sydney and Tasmania and improved robustness in predicting wave farm power output.

A short-term power load forecasting system based on data decomposition, deep learning and weighted linear error correction with feedback mechanism

Accurate power load forecasting enables Independent System Operators (ISOs) to precisely quantify the demand patterns of users and achieve efficient management of the smart grid. However, with the increasing variety of power consumption patterns, the power load data displays increasingly irregular characteristics, which posing great challenges for accurate load forecasting. In order to solve above problem, a novel power load forecasting system is proposed based on data denoising, customized deep learning and weighted linear error correction. Specifically, we first proposed an improved optimization algorithm IGWO-JAYA which enhanced the Grey Wolf Optimizer (GWO) algorithm by using Halton low-discrepancy sequence and the mechanism of JAYA algorithm. In data denoising, the proposed optimizer was employed to optimize the Variational Mode Decomposition (VMD), enabling data-driven intelligent denoising. The customized deep learning framework contained multi-layer Convolution Neural Network (CNN), Bi-directional Long Short-Term Memory (Bi-LSTM) and Multi-Head Attention mechanism. The effective integration of these layers can significantly improve the capacity for nonlinear fitting of deep learning. In weighted linear error correction, the IGWO-JAYA algorithm was employed to determine the appropriate weight for point forecasting values and residual forecasting values. By weighting them, the forecasting precision has been further enhanced. To verify the forecasting ability of the system, we conducted experiments on power load datasets from four states in Australia and found that it has the best performance compared with all rivals. In the discussion, we demonstrated the convergence efficiency of the IGWO-JAYA algorithm by CEC test function.

Ptychographic imaging with a fiber endoscope via wavelength scanning

Ptychography has become a popular computational imaging method for microscopy in recent years. In the present work we employ a wavelength scanning ptychography technique enhanced by neural networks for imaging with a fiber endoscope. Illumination of the object at various wavelengths is achieved using a single mode fiber, while a multicore fiber collects diffracted light from a distance. Using a U-Net multilayer convolutional neural network, the diffraction pattern is recovered at the far end of the multicore fiber from the recorded intensity pattern at the proximal end. With the recovered diffraction pattern in place, the phase object can be reconstructed using the ptychography algorithm. The quality of the object reconstruction improves with the number of wavelengths used. Comparison with an end-to-end neural network highlights the effectiveness and practicality of this two-step hybrid system. This alternative and simplified ptychographic endoscopy setup delivers noticeable improvements through neural networks and wavelength scanning.

Brain Tumor Recognition Using Artificial Intelligence Neural-Networks (BRAIN): A Cost-Effective Clean-Energy Platform

Brain tumors necessitate swift detection and classification for optimal patient outcomes. Deep learning has been extensively utilized to recognize complex tumor patterns in magnetic resonance imaging (MRI) images, aiding in tumor diagnosis, treatment, and prognostication. However, model complexity and limited generalizability with unfamiliar data hinder appropriate clinical integration. The objective of this study is to develop a clean-energy cloud-based deep learning platform to classify brain tumors. Three datasets of a total of 2611 axial MRI images were used to train our multi-layer convolutional neural network (CNN). Our platform automatically optimized every transfer learning and data augmentation feature combination to provide the highest predictive accuracy for our classification task. Our proposed system identified and classified brain tumors successfully and efficiently with an overall precision value of 96.8% [95% CI; 93.8–97.6]. Using clean energy supercomputing resources and cloud platforms cut our workflow to 103 min, $0 in total cost, and a negligible carbon footprint (0.0014 kg eq CO2). By leveraging automated optimized learning, we developed a cost-effective deep learning (DL) platform that accurately classified brain tumors from axial MRI images of different levels. Although studies have identified machine learning tools to overcome these obstacles, only some are cost-effective, generalizable, and usable regardless of experience.

IMAGE CAPTION GENERATOR USING DEEP LEARNING

Image Captioning is a task where each image must be understood properly and are able generate suitable caption with proper grammatical structure.Here it is a hybrid system which uses multilayer CNN (Convolutional Neural Network) for generating keywords which narrates given input images and Long Short Term Memory(LSTM) for precisely constructing the significant captions utilizing the obtained words .Convolution Neural Network (CNN) proven to be so effective that there is a way to get to any kind of estimating problem that includes image data as input. LSTM was developed to avoid the poor predictive problem which occurred while using traditional approaches. We used an encoder-decoder based model that is capable of generating grammatically correct captions for images. This model makes use of VGG16(Visual Geometry Group) as an encoder and LSTM as a decoder. The model will be trained like when an image is given model produces captions that almost describe the image. The efficiency is demonstrated for the given model using Flickr8K data sets which contains 8000 images and captions for each image but we use CNN and LSTM to capture dependencies and tell both the spatial relationships of images and contextual information of captions and generate contextually relevant captions. Keywords—CNN(Convolutional Neural Network),LSTM(Long Short Term Memory),VGG16(Visual Geometry Group),Deep Learning,Encoder-Decoder.

MT-MV-KDF: A novel Multi-Task Multi-View Knowledge Distillation Framework for myocardial infarction detection and localization

Myocardial infarction (MI) is a prevalent and life-threatening cardiovascular ailment, diagnosed primarily through the twelve-lead electrocardiogram (ECG). These leads provide unique insights into electrical activity across diverse heart regions, crucial for MI differentiation and assessment. However, prior studies predominantly focus on single-perspective 12-lead ECG analysis, overlooking inter-lead disparities. Moreover, prevailing methods often lack versatility, being tailored to specific tasks. Therefore, this paper presents the Multi-Task Multi-View Knowledge Distillation Framework (MT-MV-KDF) for MI detection and localization. The framework combines multi-view learning, multi-task learning, and knowledge distillation to enhance model performance and efficiency. Specifically, The introduction of multi-view learning aims to learn ECG feature representations from different views. Additionally, multi-task learning enables the model to learn the similarities and differences of multiple related tasks simultaneously. Finally, knowledge distillation is used to transfer latent knowledge from the complex teacher model to the simpler student model to improve efficiency. The MT-MV-KDF consists of MT-MVT-net and MT-SVS-net, which use a multi-layer CNN architecture to extract ECG different scale features. An attention module is used to capture inter-channel information and spatial cues. Through knowledge distillation, the MT-DSVS-net (0.40M) inherits insights from MT-MVT-net while achieving comparable performance with fewer parameters. Evaluation on the PTB-XL database demonstrates MT-DSVS-net has an Acc, AUC of 93.78% and 92.23% for MI detection and 83.45% and 78.26% for MI localization, respectively. Additionally, Robustness validation on CPSC2018 and Chapman datasets further confirms the efficacy of MT-MV-KDF. This study highlights the MT-MV-KDF effectiveness in MI detection and localization, particularly in improving inter-patient MI localization.

Intelligent waste classification approach based on improved multi-layered convolutional neural network

This study aims to improve the performance of organic to recyclable waste through deep learning techniques. Negative impacts on environmental and Social development have been observed relating to the poor waste segregation schemes. Separating organic waste from recyclable waste can lead to a faster and more effective recycling process. Manual waste classification is a time-consuming, costly, and less accurate recycling process. Automated segregation in the proposed work uses Improved Deep Convolutional Neural Network (DCNN). The dataset of 2 class category with 25077 images is divided into 70% training and 30% testing images. The performance metrics used are classification Accuracy, Missed Detection Rate (MDR), and False Detection Rate (FDR). The results of Improved DCNN are compared with VGG16, VGG19, MobileNetV2, DenseNet121, and EfficientNetB0 after transfer learning. Experimental results show that the image classification accuracy of the proposed model reaches 93.28%.

A sequence to sequence prediction model for remaining useful life of lithium-ion batteries with Bayesian optimisation process visualization

Accurate battery remaining useful life (RUL) prediction plays an important role in ensuring reliable operation of electric vehicles. In this paper, a hybrid model based on Bayesian optimization of deep convolutional neural network and long short-term memory neural network (BO-DCNN-LSTM) is proposed for battery RUL prediction. Feature extraction of raw charging characteristic curves is performed by the multilayer CNN and preliminary capacity prediction is performed by the multilayer LSTM. The model performance is explored with different training, validation and testing strategies and different prediction starting points. Validation using NASA battery aging data shows that the mean absolute error (MAE) and root mean square error (RMSE) of the RUL prediction are 0.0139 Ah and 0.0195 Ah, respectively, when the prediction starting point is the 50th cycle. In addition, this paper visualizes the process of how the Bayesian optimization (BO) algorithm searches for the global optimal combinations in the high-dimensional hyperparameter space and discusses the impact of these hyperparameters on the prediction, filling the gap in this part of the research.

Patch-Based Auxiliary Node Classification for Domain Adaptive Object Detection

Domain adaptive object detection (DAOD) aims to leverage labeled source domain data to train object detection models that can generalize well to unlabeled target domains. Recently, many researchers have considered implementing fine-grained pixel-level domain adaptation using graph representations. Existing methods construct semantically complete graphs and align them across domains via graph matching. This work introduced an auxiliary node classification task before domain alignment through graph matching, which utilizes the inherent information of graph nodes to classify them, in order to avoid suboptimal graph matching results caused by node class confusion. However, previous methods neglected the contextual information of graph nodes, leading to biased node classification and suboptimal graph matching. To solve this issue, we propose a novel patch-based auxiliary node classification method for DAOD. Unlike existing methods that use only the inherent information of nodes for node classification, our method exploits the local region information of nodes and employs multi-layer convolutional neural networks to learn the local region feature representation of nodes, enriching the node context information. Thus, accurate and robust node classification results are produced and the risk of class confusion is reduced. Moreover, we propose a progressive strategy to fuse the inherent features and the learned local region features of nodes, which ensures that the network can stably and reliably utilize local region features for accurate node classification. In this paper, we conduct abundant experiments on various DAOD scenarios and demonstrate that our proposed model outperforms existing works.

A Novel 3D Multi-Layer Convolutional Neural Networks for Lung Cancer Segmentation in CT Images

Background/Objectives: A novel three-dimensional efficient Multi-Layer Convolutional Neural Network (3D-MLCNN) is proposed for detecting lung tumors accurately using Computerized Tomography (CT) lung tumor images. The proposed K-means segmentation algorithm for labeling the tumor region automatically. This proposed K-means segmentation algorithm automatically labels the tumor regions to process with the 3D MLCNN model to predict tiny tumors and extract tumor regions accurately. Methods: The proposed 3DMLCNN network goal is to extract the tumor region in CT lung images to classify the lung tumor volume by pixel-wise segmentation model. Findings: The proposed 3D MLCNN segmentation model for detecting the segmenting tumors produces outperforming results for predicting even tiny tumors in the lung images. Experimental results demonstrated with lung cancer CT images in TCIA datasets show that the proposed model 3D-MLCNN achieved a dice coefficient (9.6%), Intersection over Union (IoU) (80%), F1-Score (9.33%), Sensitivity (17.11%), and Accuracy (98%) respectively. However, the proposed model 3D MLCNN was evaluated and compared with the existing state-of-the-art segmentation methods, which shows a 10% improvement in the segmentation process. Novelty: A novel 3D MLCNN model enhances the tumor region and predicts the tumor accurately by labeling the tumor using K-means labeling techniques. Keywords: 3D Convolutional Neural Networks, Lung Cancer CT Images, K - Means Labeling, Feature Visualization, Deep Learning

Integration of a CNN-based model and ensemble learning for detecting post-earthquake road cracks with deep features

A safe and healthy infrastructure is essential for humanity. Maintenance and repair of roads, which are of great importance, especially in transportation, is essential. Roads can sometimes be damaged due to natural disasters or human factors. In this study, roads damaged as a result of the natural disaster and the 6 February 2023 Gaziantep-Kahramanmaras earthquakes, which had devastating/fatal consequences, were studied. In recent years, the use of machine learning methods in the automatic detection process of road cracks has become widespread. Here, deep learning architectures generally based on multilayer convolutional neural networks have become a popular solution, mainly thanks to their high discrimination power in visual data. In this study, it was aimed to automatically detect cracks on the roads in Gaziantep (Nurdagi) and Adiyaman provinces after the earthquake. The data set used in the experimental process consists of two categories: uncracked and cracked, and was collected by the researchers. ResNet152 deep learning architecture, traditional machine learning algorithms, and an ensemble learning (EL) model were used to classify cracks. Among the machine learning algorithms used in the experiments are support vector machine (SVM), K-nearest neighbors, Adaptive Boosting, and Naive Bayes. In the experimental process, ResNet152 architecture was used for feature extraction, and classification was carried out with machine learning algorithms. In addition, the EL method has been used to improve the success of machine learning algorithms. According to experimental results, the SVM algorithm and EL method gave the most successful results with 98.68% accuracy values. The proposed method can benefit experts in the automatic classification of road cracks. The study can contribute to activating rapid coordination and transportation networks in natural disasters that cause fatal and destructive causes, such as earthquakes.