Multi-channel Convolutional Neural Network Research Articles

Diabetic retinopathy detection via deep learning based dual features integrated classification model

Background The primary recognition of diabetic retinopathy (DR) is a pivotal requirement to prevent blindness and vision impairment. This deadly condition is identified by highly qualified professionals by examining colored retinal images. Objective The physical diagnostics for this condition was time-consuming and prone to fault. The development of computer-vision based intelligent systems has develop a main research area to effectually diagnosis the pathologies from an image. Methods In this research, a novel Deep learning based Dual Features Integrated classification (DD-FIC) framework is designed to detect the DR from a color retinal image. Initially, the fundus images are denoised by Wavelet integrated Retinex (WIR) algorithm to remove the noise artifacts which provide high contrast image. This DD-FIC model contains two phases of feature extraction module to evaluation of several retinal areas. Initially, global features of the fundus image are retrieved by the assist of attention fused efficient model, whereas the attention module dynamically highlights the important features. Afterwards, the segmented retinal vessels data is converted into features for learning the local features. Results Finally, the collective of features is processed into the Random Forest based feature selection model for the optimal prediction with five different classes using multi-class support vector machine (MCSVM). The efficacy of the proposed DD-FIC framework is estimated by Kaggle dataset with the detection accuracy of 98.6%. Conclusions The proposed framework rises the accuracy of 1.54%, 3.65%, 13.79% and 6.28% for Multi-channel CNN, CNN, VGG NiN and Shallow CNN respectively.

Fault diagnosis of HVCB via the subtraction average based optimizer algorithm optimized multi channel CNN-SABO-SVM network

The mechanical fault diagnosis of HVCB is important to ensure the stability of electric power systems. Aiming at the problem of poor diagnostic performance of deep learning methods under limited samples, this paper proposes an HVCB operating mechanism fault diagnosis model (multi-channel CNN-SABO-SVM, MCCSS) based on multimodal data fusion features and Subtraction-Average-Based Optimizer (SABO). This model extracts and fuses features from the input two-dimensional data using a multi-channel CNN network and then uses the multimodal data fusion features to diagnose HVCB faults. Additionally, the SVM is used instead of the Softmax classifier to classify the fused features of vibration and sound, compensating for the poor diagnostic performance and generalization ability of the CNN network in small sample data scenarios. To further enhance the fault diagnosis performance of the SVM, the SABO is introduced for hyperparameter optimization of the SVM classifier. An HVCB fault test platform was established to train and test the model with limited data. The experimental results show that, compared with the multi-channel CNN-SVM and the CNN model based on unimodal signals, the proposed multi-channel CNN-SABO-SVM model improves the accuracy by 2.66% and 10.66%, respectively, and effectively addresses the challenge of circuit breaker fault diagnosis with limited samples.

Multi-channel convolutional neural network with attention mechanism using dual-band WiFi signals for indoor positioning systems in smart buildings

Multi-channel convolutional neural network with attention mechanism using dual-band WiFi signals for indoor positioning systems in smart buildings

CIR-DFENet: Incorporating cross-modal image representation and dual-stream feature enhanced network for activity recognition

Human activity recognition (HAR) based on wearable sensors has been widely used in various fields such as health monitoring, healthcare, and fitness due to its portability, accuracy, and real-time capabilities. Currently, advanced technologies involve converting time-series into images and deep learning for recognition, which addresses issues of subjectivity and dependence on data quality inherent in traditional processing methods. However, each of the current methods for converting time-series data into images only focuses on one type of feature representation such that one of these methods is insufficient to fully characterize the data, which results in lower accuracy in activity recognition. To address the above problems, we propose a novel method for cross-modal image representation of time-series and a dual-stream feature enhanced network model, which enables HAR based on a single-node wearable sensor. Firstly, three methods including Markov Transition Field (MTF), Recurrence Plot (RP), and Gramian Angular Field (GAF), are employed to encode the time-series into three channels (R, G, B) of color images, facilitating the fusion of features such as amplitude variation, nonlinearity, and local temporal relationship. Then, a multi-channel CNN with a Global Attention Mechanism (GAM) is employed in the model to process images, which captures both channel and spatial information. A network combining CNN and Long Short-Term Memory (LSTM) with Self-Attention Mechanism (SA) is utilized to process time-series, which captures temporal features. Simultaneously, the introduction of residual structures makes the network easy to train, thereby enhancing overall performance. The experimental results demonstrate that the proposed model can accurately identify six different gymnastic activities, achieving an accuracy rate of 99.40%. This study provides a new direction for processing time-series and offers better applications in the field of HAR based on wearable sensors.

Joint intent detection and slot filling with syntactic and semantic features using multichannel CNN-BiLSTM

Understanding spoken language is crucial for conversational agents, with intent detection and slot filling being the primary tasks in natural language understanding (NLU). Enhancing the NLU tasks can lead to an accurate and efficient virtual assistant thereby reducing the need for human intervention and expanding their applicability in other domains. Traditionally, these tasks have been addressed individually, but recent studies have highlighted their interconnection, suggesting better results when solved together. Recent advances in natural language processing have shown that pretrained word embeddings can enhance text representation and improve the generalization capabilities of models. However, the challenge of poor generalization in joint learning models for intent detection and slot filling remains due to limited annotated datasets. Additionally, traditional models face difficulties in capturing both the semantic and syntactic nuances of language, which are vital for accurate intent detection and slot filling. This study proposes a hybridized text representation method using a multichannel convolutional neural network with three embedding channels: non-contextual embeddings for semantic information, part-of-speech (POS) tag embeddings for syntactic features, and contextual embeddings for deeper contextual understanding. Specifically, we utilized word2vec for non-contextual embeddings, one-hot vectors for POS tags, and bidirectional encoder representations from transformers (BERT) for contextual embeddings. These embeddings are processed through a convolutional layer and a shared bidirectional long short-term memory (BiLSTM) network, followed by two softmax functions for intent detection and slot filling. Experiments on the air travel information system (ATIS) and SNIPS datasets demonstrated that our model significantly outperformed the baseline models, achieving an intent accuracy of 97.90% and slot filling F1-score of 98.86% on the ATIS dataset, and an intent accuracy of 98.88% and slot filling F1-score of 97.07% on the SNIPS dataset. These results highlight the effectiveness of our proposed approach in advancing dialogue systems, and paving the way for more accurate and efficient natural language understanding in real-world applications.

Intelligent Gesture Recognition Based on Screen Reflectance Multi-Band Spectral Features.

Human-computer interaction (HCI) with screens through gestures is a pivotal method amidst the digitalization trend. In this work, a gesture recognition method is proposed that combines multi-band spectral features with spatial characteristics of screen-reflected light. Based on the method, a red-green-blue (RGB) three-channel spectral gesture recognition system has been developed, composed of a display screen integrated with narrowband spectral receivers as the hardware setup. During system operation, emitted light from the screen is reflected by gestures and received by the narrowband spectral receivers. These receivers at various locations are tasked with capturing multiple narrowband spectra and converting them into light-intensity series. The availability of multi-narrowband spectral data integrates multidimensional features from frequency and spatial domains, enhancing classification capabilities. Based on the RGB three-channel spectral features, this work formulates an RGB multi-channel convolutional neural network long short-term memory (CNN-LSTM) gesture recognition model. It achieves accuracies of 99.93% in darkness and 99.89% in illuminated conditions. This indicates the system's capability for stable operation across different lighting conditions and accurate interaction. The intelligent gesture recognition method can be widely applied for interactive purposes on various screens such as computers and mobile phones, facilitating more convenient and precise HCI.

MetalTrans: A Biological Language Model-Based Approach for Predicting Disease-Associated Mutations in Protein Metal-Binding Sites.

The critical importance of accurately predicting mutations in protein metal-binding sites for advancing drug discovery and enhancing disease diagnostic processes cannot be overstated. In response to this imperative, MetalTrans emerges as an accurate predictor for disease-associated mutations in protein metal-binding sites. The core innovation of MetalTrans lies in its seamless integration of multifeature splicing with the Transformer framework, a strategy that ensures exhaustive feature extraction. Central to MetalTrans's effectiveness is its deep feature combination strategy, which merges evolutionary-scale modeling amino acid embeddings with ProtTrans embeddings, thus shedding light on the biochemical properties of proteins. Employing the Transformer component, MetalTrans leverages the self-attention mechanism to delve into higher-level representations. Utilizing mutation site information for feature fusion not only enriches the feature set but also sidesteps the common pitfall of overestimation linked to protein sequence-based predictions. This nuanced approach to feature fusion is a key differentiator, enabling MetalTrans to outperform existing methods significantly, as evidenced by comparative analyses. Our evaluations across varied metal binding site data sets (specifically Zn, Ca, Mg, and Mix) underscore MetalTrans's superior performance, which achieved the average AUC values of 0.971, 0.965, 0.980, and 0.945 on multiple 5-fold cross-validation, respectively. Remarkably, against the multichannel convolutional neural network method on a benchmark independent test set, MetalTrans demonstrated unparalleled robustness and superiority, boasting the AUC score of 0.998 on multiple 5-fold cross-validation. Our comprehensive examination of the predicted outcomes further confirms the effectiveness of the model. The source codes, data sets, and prediction results for MetalTrans can be accessed for academic usage at https://github.com/EduardWang/MetalTrans.

Identification and diagnosis of schizophrenia based on multichannel EEG and CNN deep learning model

This paper proposes a high-accuracy EEG-based schizophrenia (SZ) detection approach. Unlike comparable literature studies employing conventional machine learning algorithms, our method autonomously extracts the necessary features for network training from EEG recordings. The proposed model is a ten-layered CNN that contains a max pooling layer, a Global Average Pooling layer, four convolution layers, two dropout layers for overfitting prevention, and two fully connected layers. The efficiency of the suggested method was assessed using the ten-fold-cross validation technique and the EEG records of 14 healthy subjects and 14 SZ patients. The obtained mean accuracy score was 99.18 %. To confirm the high mean accuracy attained, we tested the model on unseen data with a near-perfect accuracy score (almost 100 %). In addition, the results we obtained outperform numerous other comparable works.

Multi-Shared-Task Self-Supervised CNN-LSTM for Monitoring Free-Body Movement UPDRS-III Using Wearable Sensors.

The Unified Parkinson's Disease Rating Scale (UPDRS) is used to recognize patients with Parkinson's disease (PD) and rate its severity. The rating is crucial for disease progression monitoring and treatment adjustment. This study aims to advance the capabilities of PD management by developing an innovative framework that integrates deep learning with wearable sensor technology to enhance the precision of UPDRS assessments. We introduce a series of deep learning models to estimate UPDRS Part III scores, utilizing motion data from wearable sensors. Our approach leverages a novel Multi-shared-task Self-supervised Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) framework that processes raw gyroscope signals and their spectrogram representations. This technique aims to refine the estimation accuracy of PD severity during naturalistic human activities. Utilizing 526 min of data from 24 PD patients engaged in everyday activities, our methodology demonstrates a strong correlation of 0.89 between estimated and clinically assessed UPDRS-III scores. This model outperforms the benchmark set by single and multichannel CNN, LSTM, and CNN-LSTM models and establishes a new standard in UPDRS-III score estimation for free-body movements compared to recent state-of-the-art methods. These results signify a substantial step forward in bioengineering applications for PD monitoring, providing a robust framework for reliable and continuous assessment of PD symptoms in daily living settings.

Modeling Source and System Features Through Multi-channel Convolutional Neural Network for Improving Intelligibility Assessment of Dysarthric Speech

Modeling Source and System Features Through Multi-channel Convolutional Neural Network for Improving Intelligibility Assessment of Dysarthric Speech

An artificial intelligence-assisted microfluidic colorimetric wearable sensor system for monitoring of key tear biomarkers

The precise, simultaneous, and rapid detection of essential biomarkers in human tears is imperative for monitoring both ocular and systemic health. The utilization of a wearable colorimetric biochemical sensor exhibits potential in achieving swift and concurrent detection of pivotal biomarkers in tears. Nevertheless, challenges arise in the collection, interpretation, and sharing of data from the colorimetric sensor, thereby restricting the practical implementation of this technology. To overcome these challenges, this research introduces an artificial intelligence-assisted wearable microfluidic colorimetric sensor system (AI-WMCS) for rapid, non-invasive, and simultaneous detection of key biomarkers in human tears, including vitamin C, H+(pH), Ca2+, and proteins. The sensor consists of a flexible microfluidic epidermal patch that collects tears and facilitates the colorimetric reaction, and a deep-learning neural network-based cloud server data analysis system (CSDAS) embedded in a smartphone enabling color data acquisition, interpretation, auto-correction, and display. To enhance accuracy, a well-trained multichannel convolutional recurrent neural network (CNN-GRU) corrects errors in the interpreted concentration data caused by varying pH and color temperature in different measurements. The test set determination coefficients (R2) of 1D-CNN-GRU for predicting pH and 3D-CNN-GRU for predicting the other three biomarkers were as high as 0.998 and 0.994, respectively. This correction significantly improves the accuracy of the predicted concentration, enabling accurate, simultaneous, and quick detection of four critical tear biomarkers using only minute amounts of tears ( ~ 20 μL). This research demonstrates the powerful integration of a flexible microfluidic colorimetric biosensor and deep-learning algorithm, which holds immense potential to revolutionize the fields of health monitoring.

A computational clinical decision-supporting system to suggest effective anti-epileptic drugs for pediatric epilepsy patients based on deep learning models using patient’s medical history

BackgroundEpilepsy, a chronic brain disorder characterized by abnormal brain activity that causes seizures and other symptoms, is typically treated using anti-epileptic drugs (AEDs) as the first-line therapy. However, due to the variations in their modes of action, identification of effective AEDs often relies on ad hoc trials, which is particularly challenging for pediatric patients. Thus, there is significant value in computational methods capable of assisting in the selection of AEDs, aiming to minimize unnecessary medication and improve treatment efficacy.ResultsIn this study, we collected 7,507 medical records from 1,000 pediatric epilepsy patients and developed a computational clinical decision-supporting system for AED selection. This system leverages three multi-channel convolutional neural network (CNN) models tailored to three specific AEDs (vigabatrin, prednisolone, and clobazam). Each CNN model predicts whether a respective AED is effective on a given patient or not. The CNN models showed AUROCs of 0.90, 0.80, and 0.92 in 10-fold cross-validation, respectively. Evaluation on a hold-out test dataset further revealed positive predictive values (PPVs) of 0.92, 0.97, and 0.91 for the three respective CNN models, representing that suggested AEDs by our models would be effective in controlling epilepsy with a high accuracy and thereby reducing unnecessary medications for pediatric patients.ConclusionOur CNN models in the system demonstrated high PPVs for the three AEDs, which signifies the potential of our approach to support the clinical decision-making by assisting doctors in recommending effective AEDs within the three AEDs for patients based on their medical history. This would result in a reduction in the number of unnecessary ad hoc attempts to find an effective AED for pediatric epilepsy patients.

A multi-scale multi-channel CNN introducing a channel-spatial attention mechanism hyperspectral remote sensing image classification method

ABSTRACT Aiming the problems that the classification performance of hyperspectral images in existing classification algorithms is highly dependent on spatial-spectral information and that detailed features are ignored in single convolutional channel feature extraction, resulting in poor generalization performance of the feature extraction model, a multi-scale multi-channel convolutional neural network (MMC-CNN) model is proposed in this paper. First, the data set is divided into two kinds of pixel module, and then different channels are used for feature extraction. A channel-space attention mechanism module is also introduced, and a multi-scale multichannel convolutional neural network (CSAM-MMC) model with the introduction of channel-space attention mechanism is proposed for deeper spatial-spectral feature extraction of hyperspectral image elements while reducing the redundancy of convolutional pooling parameters to achieve better HSI classification. To evaluate the effectiveness of the proposed model, experiments were conducted on Indian Pines, Pavia Center and KSC datasets respectively, and the overall classification accuracies of this paper’s MMC-CNN model in the HSI dataset were 97.23%, 98.50%, and 97.85%, thus verifying the model’s high feature extraction accuracy. The CSAM-MMC model in this paper further improves 0.13%, 0.35%, and 0.71% relative to the MMC-CNN model, which provides higher overall accuracies relative to other state-of-the-art algorithms.

Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation

Accurate and timely structural damage diagnosis is crucial to efficient disaster response and city renovation in post-earthquake events. The scarcity of labeled data hinders the powerful deep learning techniques from in-domain damage detection on target structures. Cross-domain transfer learning has emerged as a captivating strategy through digging knowledge from the abundant source domain to detect the damage in the target domain. However, the heterogeneity among multi-domain structures poses the challenge in seismic damage diagnosis. This study proposes a novel zero-shot knowledge transfer approach for seismic damage diagnosis through multi-channel one-dimensional convolutional neural networks (1D CNN) integrated with deep autoencoder (DAE)-based domain adaptation (DA). The framework consists of three modules, namely, data preprocessor adaptive to seismic vibration signals, DAE-based DA module, and damage diagnosis via multi-channel 1D CNN. The DA module is customized to seamlessly translate the unseen target-domain data to mimic latent representation via a DAE pretrained on the source data, thus realizing rigorous zero-shot learning. Imbalanced data distribution is also considered during the network training and testing. Two representative phases of knowledge transfer are performed to substantiate the knowledge transferability of the proposed method. The first phase involves multi-class damage quantification on two ASCE benchmark models from the simplified model to the refined one, and the second phase conducts binary damage detection on a three-story reinforced frame structure from the finite element numerical model to the laboratory-tested physical model. Both examples show that the proposed method exhibits high prediction accuracy and a lower false negative rate in achieving zero-shot knowledge transfer for cross-domain structural damage diagnosis. With a delicate network design for diverse data, the proposed knowledge transfer framework can be further extended from the present zero-shot approach to the few-shot learning paradigm, thus suggesting a feasible algorithm adaptability and promising engineering applicability.

Aspect based hotel recommendation system using dilated multichannel CNN and BiGRU with hyperbolic linear unit

Aspect based hotel recommendation system using dilated multichannel CNN and BiGRU with hyperbolic linear unit

Scalable deep learning framework for sentiment analysis prediction for online movie reviews

Sentiment analysis has broad use in diverse real-world contexts, particularly in the online movie industry and other e-commerce platforms. The main objective of our work is to examine the word information order and analyze the content of texts by exploring the hidden meanings of words in online movie text reviews. This study presents an enhanced method of representing text and computationally feasible deep learning models, namely the PEW-MCAB model. The methodology categorizes sentiments by considering the full written text as a unified piece. The feature vector representation is processed using an enhanced text representation called Positional embedding and pretrained Glove Embedding Vector (PEW). The learning of these features is achieved by inculcating a multichannel convolutional neural network (MCNN), which is subsequently integrated into an Attention-based Bidirectional Long Short-Term Memory (AB) model. This experiment examines the positive and negative of online movie textual reviews. Four datasets were used to evaluate the model. When tested on the IMDB, MR (2002), MRC (2004), and MR (2005) datasets, the (PEW-MCAB) algorithm attained accuracy rates of 90.3%, 84.1%, 85.9%, and 87.1%, respectively, in the experimental setting. When implemented in practical settings, the proposed structure shows a great deal of promise for efficacy and competitiveness.

Structural Damage Identification Based on Preprocessing Samples Mixed Training of Multi-Channel and Multi-Source Dynamic Response Data

Previous studies have shown that sampling processing and identification methods for neural networks damage identification in multi-channel and multi-source structural dynamic response data exhibit diversity, and the robustness and generalization issues of the model have not been effectively solved. This paper proposes a sample preprocessing technique and mixed training method suitable for multi-channel and multi-source dynamic response data to optimize the current structural damage identification methods based on neural networks. Through multi-dimensional discrete autocorrelation processing and Fourier transform, the preprocessed datasets from multiple sensors with multi-channel can access multi-channel CNN. Furthermore, the measured datasets from the actual structures are mixed with numerical simulation datasets before being used for neural network model training to address the model calibration and the imbalanced sample size under each classification label. The results of extensive model experiments and finite element verification of specimens show that the method performs outstandingly in detecting and identifying damage to simply supported beam structures using multi-channel CNN. The neural network model trained with preprocessed samples exhibits excellent robustness. The model using the mixed training method still performs well in identifying the accuracy of damage location and degree in simply supported beam structures after changing beam section and initial excitation. The method has certain generalization ability in detecting unknown damage in simply supported beam structures.

A multi-output fault diagnosis framework for hydraulic system using a CNN-SVM hierarchical learning strategy

Achieving asymptotic and concurrent fault diagnosis in hydraulic system remains a challenging endeavor due to the inherent attributes of the hidden occurrence, simultaneous manifestation, coupling, and limited sample size. To address the above issues, this paper proposes a hierarchical multi-output fault detection and diagnosis framework, namely, HMDF, based on a hierarchical learning strategy to leverage an improved convolutional neural network (CNN) and support vector machine (SVM). Both a multi-channel CNN and a multi-branch CNN are employed to extract and downscale features collected by the sensors at diverse sampling frequencies first, and then, such features are subsequently subjected to classification using SVM. The hierarchical learning strategy enables the identification of different fault states, both at the component and the intra-component level. Additionally, a modified whale optimization algorithm is also utilized to optimize the classification process of SVM. Extensive experiments are conducted to test the proposed HMDF with the hydraulic system datasets. Results show that HMDF achieves a diagnostic accuracy of up to 98.9% for the dataset, surpassing traditional methods reliant on manual extraction of time–frequency features, and it also exhibits superior classification performances with a small sample size. The HMDF is expected to offer a generalized framework for the multi-output fault detection and diagnosis in hydraulic systems and other complex components.

Intelligent fault diagnosis of roller bearing based on dual-flow convolutional neural network

Deep learning (DL) has inaugurated new approaches to implement fault diagnosis of roller bearings, which is essential to deal with the current industrial big data era. Unfortunately, many existing deep learning models, particularly convolutional neural network (CNN) models, have the following drawbacks. Single-channel convolution neural network in pooling layer has the problem of data loss. The feature information extracted by CNN is not integrated due to lack of feature learning ability, which will induce unsatisfactory diagnostic results and poor generalization ability. To deal with the above issues, a dual-flow convolutional neural network (DFCNN) is proposed for intelligent diagnosis the faults of roller bearings. The multi-channel convolutional neural network is used for feature extraction to solve the problem of data loss in the pooling layer. More comprehensive fault features can be extracted by multiple feature fusion after the input of two dimensions. Network parameters are adjusted using model optimization. The proposed method is demonstrated by the bearing experiment and collected vibration data including different types of faults. The results show that the accuracy rate is more superior than other six different neural network, and it is suitable for roller bearing fault diagnosis.

Prediction and Elucidation of Physical Properties of Polycrystalline Materials Using Multichannel Machine Learning of Electron Backscattering Diffraction

AbstractThe application of machine learning in materials science has yielded several benefits, including the prediction of physical properties and the improvement of experimental efficiency. However, with complex models, such as convolutional neural networks (CNN), learning has become a black box, from which no universal physical knowledge can be obtained. In this study, a highly accurate prediction of the electrical properties of polycrystalline semiconductor thin films is achieved by learning multichannel CNN models from electron backscattering diffraction (EBSD) data, that is band contrasts, grain boundaries, and inverse pole figures. In addition, it examines how the CNN model learned the correlation between the crystallinity, grain boundaries, crystallographic orientation, and carrier mobility by polarizing certain EBSD data and checking the predicted changes in carrier mobility. Physical parameters affecting carrier mobility can be extracted, which is challenging via human image recognition. The methods proposed in this study will not only enable the prediction of electrical properties from EBSD data for all materials but also will contribute to the discovery of complex physical phenomena beyond the limits of human analysis.