Convolutional Neural Network Classifier Research Articles

Research on Tool Wear Monitoring Based on Enhanced Convolutional Neural Networks

Abstract Identifying the wear status of cutting tools during the machining process is essential because failure to promptly replace severely worn tools can significantly impact the quality of workpiece machining. Presently, machine learning methods are predominantly utilized for monitoring cutting tool wear status. However, these methods rely on manual feature extraction and exhibit low accuracy. This study introduces a novel RRP-Net model, built upon the RepVgg and ResNet frameworks, integrating a parameter-free self-attention mechanism called SimAM to expedite the model’s solving speed without increasing parameters. Within the foundational module of the model, a structural reparameterization approach is employed to transform the multi-branch structure during training into a single-branch structure during validation. This method not only enhances model accuracy but also accelerates the model validation process. The publicly available cutting data from PHM2010 is employed for model training and validation. The findings demonstrate that RRP-Net surpasses classical convolutional neural network models in identifying cutting tool wear status within the PHM2010 dataset, achieving an average accuracy of 98.65% and enhancing recognition accuracy on relevant datasets by 2.41%. To verify the model’s practical applicability, specificity and recall during the Break stage are computed at 99.73% and 98.18%, respectively, affirming the model’s exceptional robustness and stability. The heightened accuracy and efficiency of RRP-Net further broaden its applicability within the industrial domain.

Detection of Encroachment in Civil Structure Using Dynamic Learning Techniques

Identifying cracks through visual inspection and automated surveys are both effective methods. While both approaches yield satisfactory distress analysis results, automated crack recognition technology stands out for its speed and cost-effectiveness compared to traditional human visual detection methods. This study introduces an innovative approach, namely "crack encroachment in concrete structures classified using DCNN" which employs a Deep Convolutional Neural Network. To enhance the precision of crack detection, the input image undergoes denoising through ADNLMF (Anisotropic Diffusion Non-Local Mean Filtering), preserving edges, textures, and features. Crack discrimination between crack and non-crack images was achieved using Yolo v3, and a deep convolutional neural network classifier was employed to identify specific crack types based on their widths, utilizing crack width transform. This method not only enhances accuracy but also reduces network complexity and processing time. A comprehensive performance comparison with existing crack identification techniques indicates that our proposed methodology for concrete structure crack recognition produces superior results.

Machine vision-based detection of forbidden elements in the high-speed automatic scrap sorting line

Highly efficient industrial sorting lines require fast and reliable classification methods. Various types of sensors are used to measure the features of an object to determine which output class it belongs to. One technique involves the use of an RGB camera and a machine learning classifier. The paper is focused on protecting the sorting process against prohibited and dangerous items potentially present in the sorted material that pose a threat to the sorting process or the subsequent metallurgical process. To achieve this, a convolutional neural network classifier was applied under real-life conditions to detect forbidden elements in copper-based metal scrap. A laboratory stand simulating the working conditions in a high-speed scrap sorting line was prepared. Using this custom stand, training and test sets for machine learning were gathered and labeled. An image preprocessing algorithm was designed to increase the robustness of the resulting forbidden element detector system. The performance of multiple neural network architectures and data set augmentations was analyzed. The highest accuracy of 98.03% and F1-score of 97.16% were achieved with a DenseNet-based classifier. The results of this paper show the feasibility of using the presented solution on a high-speed industrial line.

Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are vision related complications prominently found in diabetic patients. The early identification of DR/DME grades facilitates the devising of an appropriate treatment plan, which ultimately prevents the probability of visual impairment in more than 90% of diabetic patients. Thereby, an automatic DR/DME grade detection approach is proposed in this work by utilizing image processing. In this work, the retinal fundus image provided as input is pre-processed using Discrete Wavelet Transform (DWT) with the aim of enhancing its visual quality. The precise detection of DR/DME is supported further with the application of suitable Artificial Neural Network (ANN) based segmentation technique. The segmented images are subsequently subjected to feature extraction using Adaptive Gabor Filter (AGF) and the feature selection using Random Forest (RF) technique. The former has excellent retinal vein recognition capability, while the latter has exceptional generalization capability. The RF approach also assists with the improvement of classification accuracy of Deep Convolutional Neural Network (CNN) classifier. Moreover, Chicken Swarm Algorithm (CSA) is used for further enhancing the classifier performance by optimizing the weights of both convolution and fully connected layer. The entire approach is validated for its accuracy in determination of grades of DR/DME using MATLAB software. The proposed DR/DME grade detection approach displays an excellent accuracy of 97.91%.

Ultrasonic Assessment of Liver Fibrosis Using One-Dimensional Convolutional Neural Networks Based on Frequency Spectra of Radiofrequency Signals with Deep Learning Segmentation of Liver Regions in B-Mode Images: A Feasibility Study.

The early detection of liver fibrosis is of significant importance. Deep learning analysis of ultrasound backscattered radiofrequency (RF) signals is emerging for tissue characterization as the RF signals carry abundant information related to tissue microstructures. However, the existing methods only used the time-domain information of the RF signals for liver fibrosis assessment, and the liver region of interest (ROI) is outlined manually. In this study, we proposed an approach for liver fibrosis assessment using deep learning models on ultrasound RF signals. The proposed method consisted of two-dimensional (2D) convolutional neural networks (CNNs) for automatic liver ROI segmentation from reconstructed B-mode ultrasound images and one-dimensional (1D) CNNs for liver fibrosis stage classification based on the frequency spectra (amplitude, phase, and power) of the segmented ROI signals. The Fourier transform was used to obtain the three kinds of frequency spectra. Two classical 2D CNNs were employed for liver ROI segmentation: U-Net and Attention U-Net. ROI spectrum signals were normalized and augmented using a sliding window technique. Ultrasound RF signals collected (with a 3-MHz transducer) from 613 participants (Group A) were included for liver ROI segmentation and those from 237 participants (Group B) for liver fibrosis stage classification, with a liver biopsy as the reference standard (Fibrosis stage: F0 = 27, F1 = 49, F2 = 51, F3 = 49, F4 = 61). In the test set of Group A, U-Net and Attention U-Net yielded Dice similarity coefficients of 95.05% and 94.68%, respectively. In the test set of Group B, the 1D CNN performed the best when using ROI phase spectrum signals to evaluate liver fibrosis stages ≥F1 (area under the receive operating characteristic curve, AUC: 0.957; accuracy: 89.19%; sensitivity: 85.17%; specificity: 93.75%), ≥F2 (AUC: 0.808; accuracy: 83.34%; sensitivity: 87.50%; specificity: 78.57%), and ≥F4 (AUC: 0.876; accuracy: 85.71%; sensitivity: 77.78%; specificity: 94.12%), and when using the power spectrum signals to evaluate ≥F3 (AUC: 0.729; accuracy: 77.14%; sensitivity: 77.27%; specificity: 76.92%). The experimental results demonstrated the feasibility of both the 2D and 1D CNNs in liver parenchyma detection and liver fibrosis characterization. The proposed methods have provided a new strategy for liver fibrosis assessment based on ultrasound RF signals, especially for early fibrosis detection. The findings of this study shed light on deep learning analysis of ultrasound RF signals in the frequency domain with automatic ROI segmentation.

A CNNbased energy management strategy for a Hybrid energy storage system in electric vehicles

When approaching a large-scale performance, the choice, size, and administration of an Energy Storage System (ESS) for an Electric Vehicle (EV) are crucial. As the peak-to-average power demand ratio is relatively large, particularly for an urban ride that is frequently marked by rapid deceleration as well as acceleration, the complementary characteristics of the battery and Ultra-Capacitor (UC)render this arrangement a viable Hybrid energy storage system (HESS) for EV. Enhanced dynamic responsiveness, increased miles per charge, and extended battery life provided by the HESS increase the Electric Vehicle (EV’s) effectiveness. The primary objective of the study that has been suggested is to create a smart Energy Management Strategy (EMS) for EVs. A battery package and a properly sized Ultra-Capacitor (UC) together give the required high power along with energy density. This research proposes a CNN-based power management technique to aid in efficient EMS. Additionally, by adjusting the Convolution Neural Network (CNN) classifier’s weights through Improved Honey Badger Optimization (IHBO), the adaptive approach of the Standard HBO Algorithm, the performance of the classifier is improved. In MATLAB, the suggested CNN-based model for BESS EM is simulated and experimental assessment and analysis are done in terms of converter current and battery SoC. By contrasting the suggested approach against several standardized models, the performance analysis of the proposed work is assessed to validate its performance.

Research progress on colorectal cancer identification based on convolutional neural network

Colorectal cancer (CRC) is a common malignant tumor that seriously threatens human health. CRC presents a formidable challenge in terms of accurate identification due to its indistinct boundaries. With the widespread adoption of convolutional neural networks (CNNs) in image processing, leveraging CNNs for automatic classification and segmentation holds immense potential for enhancing the efficiency of colorectal cancer recognition and reducing treatment costs. This paper explores the imperative necessity for applying CNNs in clinical diagnosis of CRC. It provides an elaborate overview on research advancements pertaining to CNNs and their improved models in CRC classification and segmentation. Furthermore, this work summarizes the ideas and common methods for optimizing network performance and discusses the challenges faced by CNNs as well as future development trends in their application towards CRC classification and segmentation, thereby promoting their utilization within clinical diagnosis.

Detecting Voice Fatigue With Artificial Intelligence

Voice fatigue (VF) has many symptoms and can occur after extended or brief voice use, depending on the presence or absence of voice pathology, and other factors. However, fatigue is difficult to detect and quantify through current approaches. This study explores the use of artificial intelligence (AI) in the automatic detection and analysis of voice fatigue, presenting a novel approach to detect and monitor the condition. ObjectiveThis study aims to create an AI-based system for detecting voice fatigue. The AI model’s performance is evaluated against traditional methods of assessment conducted by speech-language pathologists (SLPs). MethodsVoice samples were collected from individuals experiencing varying levels of voice fatigue. To validate these samples, we calculated fo, increases which have been shown to be correlated with voice fatigue, at the beginning and end of the recordings. The samples were processed using a machine learning model trained to recognize patterns associated with voice fatigue. To build the model, we extracted embeddings from an ECAPA-TDNN model that has been shown to capture changes in the voice characteristics of a speaker over time and used a convolutional neural network for classification. To validate the model, the model’s accuracy in detecting voice fatigue was compared to assessments from SLPs. ResultsWe achieved an accuracy score of 93% on our dataset of English academic lectures and podcasts. As further validation, we asked 3 experienced SLPs to classify audio segments from our dataset and compared their responses to the classifications from our model, and achieved an accuracy of 86% as compared to their ratings. ConclusionThe application of AI in the detection of voice fatigue shows a generalizable approach for the analysis of voice fatigue. Future research will incorporate patient data to validate further the models that we created.

Improved Tunicate Swarm Optimization Based Hybrid Convolutional Neural Network for Classification of Leaf Diseases and Nutrient Deficiencies in Rice (Oryza)

Improved Tunicate Swarm Optimization Based Hybrid Convolutional Neural Network for Classification of Leaf Diseases and Nutrient Deficiencies in Rice (Oryza)

SF-ICNN: Spectral–Fractal Iterative Convolutional Neural Network for Classification of Hyperspectral Images

One primary concern in the field of remote-sensing image processing is the precise classification of hyperspectral images (HSIs). Lately, deep-learning models have demonstrated cutting-edge results in HSI classification. Despite this, researchers continue to study and propose simpler, more robust models. This study presents a novel deep-learning approach, the iterative convolutional neural network (ICNN), which combines spectral–fractal features and classifier probability maps iteratively, aiming to enhance the HSI classification accuracy. Experiments are conducted to prove the accuracy enhancement of the proposed method using HSI benchmark datasets of Indian pine (IP) and the University of Pavia (PU) to evaluate the performance of the proposed technique. The final results show that the proposed approach reaches overall accuracies of 99.16% and 95.5% on the IP and PU datasets, respectively, which are better than some basic methods. Additionally, the end findings demonstrate that greater accuracy levels might be achieved using a primary CNN network that employs the iteration loop than with certain current state-of-the-art spatial–spectral HSI classification techniques.

A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification

Music genre classification (MGC) is the basis for the efficient organization, retrieval, and recommendation of music resources, so it has important research value. Convolutional neural networks (CNNs) have been widely used in MGC and achieved excellent results. However, CNNs cannot model global features well due to the influence of the local receptive field; these global features are crucial for classifying music signals with temporal properties. Transformers can capture long-range dependencies within an image thanks to adopting the self-attention mechanism. Nevertheless, there are still performance and computational cost gaps between Transformers and existing CNNs. In this paper, we propose a hybrid architecture (CNN-TE) based on CNN and Transformer encoder for MGC. Specifically, we convert the audio signals into mel spectrograms and feed them into a hybrid model for training. Our model employs a CNN to initially capture low-level and localized features from the spectrogram. Subsequently, these features are processed by a Transformer encoder, which models them globally to extract high-level and abstract semantic information. This refined information is then classified using a multi-layer perceptron. Our experiments demonstrate that this approach surpasses many existing CNN architectures when tested on the GTZAN and FMA datasets. Notably, it achieves these results with fewer parameters and a faster inference speed.

Optimizing Corn Tar Spot Measurement: A Deep Learning Approach Using Red-Green-Blue Imaging and Stromata Contour Detection Algorithm for Leaf-Level Disease Severity Analysis.

Visual detection of stromata (brown-black, elevated fungal fruiting bodies) is a primary method for quantifying tar spot early in the season, as these structures are definitive signs of the disease and essential for effective disease monitoring and management. Here, we present Stromata Contour Detection Algorithm version 2 (SCDA v2), which addresses the limitations of the previously developed SCDA version 1 (SCDA v1) without the need for empirical search of the optimal Decision Making Input Parameters (DMIPs), while achieving higher and consistent accuracy in tar spot stromata detection. SCDA v2 operates in two components: (i) SCDA v1 producing tar-spot-like region proposals for a given input corn leaf Red-Green-Blue (RGB) image, and (ii) a pre-trained Convolutional Neural Network (CNN) classifier identifying true tar spot stromata from the region proposals. To demonstrate the enhanced performance of the SCDA v2, we utilized datasets of RGB images of corn leaves from field (low, middle, and upper canopies) and glasshouse conditions under variable environments, exhibiting different tar spot severities at various corn developmental stages. Various accuracy analyses (F1-score, linear regression, and Lin's concordance correlation), showed that SCDA v2 had a greater agreement with the reference data (human visual annotation) than SCDA v1. SCDA v2 achievd 73.7% mean Dice values (overall accuracy), compared to 30.8% for SCDA v1. The enhanced F1-score primarily resulted from eliminating overestimation cases using the CNN classifier. Our findings indicate the promising potential of SCDA v2 for glasshouse and field-scale applications, including tar spot phenotyping and surveillance projects.

A novel speaker verification approach featuring multidomain acoustics based on the weighted city block Minkowski distance

AbstractAccess control is vital in interconnected environments like the Internet of Things, Industry 4.0, and smart connectivity, ensuring authorized access for security. Biometric‐based access, particularly speaker verification (SV), enhances security with unique vocal features, offering nonintrusive authentication with continuous monitoring. Single‐domain features prove insufficient in distinguishing similar traits, prompting latest SV advancements to adopt multidomain‐based speech features. This paradigm addresses the limitations of single‐domain features by amalgamating the merits of individual domains, establishing a cutting‐edge approach. It utilizes cepstral–frequency–time domain feature fusion, achieved via cepstral mean‐variance normalization for generalizability. The weighted city block Minkowski distance is proposed to compare reference and test speech templates. Parameters are computed based on the confusion matrix, template matching distance functions, dynamic acoustic conditions, and additive white Gaussian noise. A deep convolutional neural network classifier is assessed on open‐source LibriSpeech and Speaker in the Wild corpora, surpassing the current methodologies.

System and method to diagnose conjunctivitis in the eye of a user

This Proposed work explores how machine learning can be used to diagnose conjunctivitis, a common eye ailment. The main goal of the study is to capture eye images using camera-based systems, perform image pre-processing, and employ image segmentation techniques, particularly the UNet++ and U-net models. Additionally, the study involves extracting features from the relevant areas within the segmented images and using Convolutional Neural Networks for classification. All this is carried out using TensorFlow, a well-known machine-learning platform. The research involves thorough training and assessment of both the UNet and U-net++ segmentation models. A comprehensive analysis is conducted, focusing on their accuracy and performance. The study goes further to evaluate these models using both the UBIRIS dataset and a custom dataset created for this specific research. The experimental results emphasize a substantial improvement in the quality of segmentation achieved by the U-net++ model, the model achieved an overall accuracy of 97.07. Furthermore, the UNet++ architecture displays better accuracy in comparison to the traditional U-net model. These outcomes highlight the potential of U-net++ as a valuable advancement in the field of machine learning-based conjunctivitis diagnosis.

Classification of melanocytic lesions using direct illumination multispectral imaging

With rising melanoma incidence and mortality, early detection and surgical removal of primary lesions is essential. Multispectral imaging is a new, non-invasive technique that can facilitate skin cancer detection by measuring the reflectance spectra of biological tissues. Currently, incident illumination allows little light to be reflected from deeper skin layers due to high surface reflectance. A pilot study was conducted at the University Hospital Basel to evaluate, whether multispectral imaging with direct light coupling could extract more information from deeper skin layers for more accurate dignity classification of melanocytic lesions. 27 suspicious pigmented lesions from 23 patients were included (6 melanomas, 6 dysplastic nevi, 12 melanocytic nevi, 3 other). Lesions were imaged before excision using a prototype snapshot mosaic multispectral camera with incident and direct illumination with subsequent dignity classification by a pre-trained multispectral image analysis model. Using incident light, a sensitivity of 83.3% and a specificity of 58.8% were achieved compared to dignity as determined by histopathological examination. Direct light coupling resulted in a superior sensitivity of 100% and specificity of 82.4%. Convolutional neural network classification of corresponding red, green, and blue lesion images resulted in 16.7% lower sensitivity (83.3%, 5/6 malignant lesions detected) and 20.9% lower specificity (61.5%) compared to direct light coupling with multispectral image classification. Our results show that incorporating direct light multispectral imaging into the melanoma detection process could potentially increase the accuracy of dignity classification. This newly evaluated illumination method could improve multispectral applications in skin cancer detection. Further larger studies are needed to validate the camera prototype.

EfficientNet-Based Model for Automated Classification of Retinal Diseases Using Fundus Images

The automated classification of retinal diseases, such as diabetic retinopathy, cataract, glaucoma, and normal retinal conditions, is critical for early diagnosis and timely intervention. This study employs an EfficientNet-based convolutional neural network (CNN) to classify these diseases using a dataset of fundus images, achieving an accuracy of 93.8%. By leveraging transfer learning and fine-tuning techniques, our model is both computationally efficient and highly accurate, making it suitable for clinical applications. In comparison to other CNN-based approaches and ensemble methods, as explored in recent studies, EfficientNet offers a balanced performance in terms of precision, recall, and inference speed, which is crucial in ophthalmic diagnostics. Previous research on real-time object detection in medical imaging, such as Billah et al.’s studies on YOLO models and ensemble methods, has demonstrated the effectiveness of CNNs for accurate classification across various medical imaging tasks. This paper situates EfficientNet within these advancements, underscoring its potential for high-accuracy, multi-class classification in retinal disease detection. Our findings suggest that EfficientNet can play a significant role in automating retinal disease screening, contributing to improved patient outcomes and facilitating the integration of AI in ophthalmology.

Deep Learning Based Multi-Parameter Assistive System for COVID-19 Diagnosis

Epidemics like the COVID-19 epidemic are major global problems, some of which spread rapidly, causing high mortality rates. The rapid spread of such diseases leaves behind the production and global use of medical testing tools, and during this period, the undetected disease spreads quickly and becomes hard to control. Therefore, non-medical digital technologies with faster disease prediction are needed. The studies on deep learning, a subfield of artificial intelligence, reveal that it is possible to predict disease more quickly. It will be possible to stop the pandemic progress with minimal damage if the best predictive approach is used. Lives are saved when the disease is detected early. A dataset containing low-dose CT scan images, gender, age, weight, COVID-19 PCR test result, and symptoms including cough, fever, shortness of breath, chest pain, and fatigue were used in this study. The primary goal is developing an assistive system for diagnosing COVID-19 disease based on deep learning using this dataset. The deep learning technique used in this study has a multi-branch architecture consisting of both classical artificial neural networks and convolutional neural networks. As a result of this study, it was concluded that the developed technique can be used not only for COVID-19 but also for different diseases and is open to development with data from more patients.

An effective accurate lung nodule detection of CT images using extensible hunt optimization based deep CNN

Lung cancer patients’ chances of survival can increase with early detection. For the diagnosis of lung cancer, precise lung nodule identification in computed tomography (CT) images is crucial. The variety of the lung nodules and the complexity of the surroundings, however, have made robust nodule identification a challenging problem. To address this challenge, the Extensible Hunt Optimization-based deep Convolutional Neural Network classifier (EHO-deep CNN), is developed in this research for detecting the lung nodules present in the CT images. The proposed model in which the preprocessing is performed through the median filter to eliminate the artifacts in the image. Specifically, the images are segmented by adopting the centralized superpixels segmentation-based iterative clustering (CSSBIC) technique that enhances the accuracy of segmentation. The proposed approach relies on the GLCM and the VGG16-based feature extraction to explicate the discrimination of the lung nodule features. In addition, the retrieved features are combined and fed forwarded to the Deep CNN classifier that is optimally tuned via the EHO algorithm. The EHO algorithm is developed by fusing the fitness function of Border collie dogs with the hunting characteristics of Dingo to enhance convergence rate and performance. The proposed EHO-deep CNN is reported in terms of accuracy, sensitivity, and specificity values as 98.13%, 98.98%, and 97.28% when measuring TP 80 for the LIDC-IDRI dataset and 96.09%, 96.70%, and 95.48% for measuring k-fold 10. Further, implementing the suggested model obtains the values of 95.34%, 92.88%, and 97.80% for the LUNA 16 dataset when measuring TP 80 and 98.21%, 98.06%, 98.35% when measuring k-fold 10, which outperforms other existing techniques in effectiveness.

Attention improvement for data-driven analyzing fluorescence excitation-emission matrix spectra via interpretable attention mechanism

Analyzing three-dimensional excitation-emission matrix (3D-EEM) spectra through machine learning models has drawn increasing attention, whereas the reliability of these machine learning models remains unclear due to their “black box” nature. In this study, the convolutional neural network (CNN) for classifying numbers of fluorescent components in 3D-EEM spectra was interpreted by gradient-weighted class activation mapping (Grad-CAM), guided Grad-CAM, and structured attention graphs (SAGs). Results showed that the original CNN classifier with high classification accuracy may make a classification based on misleading attention to the non-fluorescence area in 3D-EEM spectra. By removing Rayleigh scatterings in 3D-EEM spectra and integrating convolutional block attention module (CBAM) in CNN classifiers, the correct attention of the trained CNN classifier with CBAM greatly increased from 17.6% to 57.2%. This work formulated strategies for improving CNN classifiers associated with environmental fields and would provide great help for water determination in both natural and artificial environments.

Correction to “Multi‐Branch Sustainable Convolutional Neural Network for Disease Classification”

Correction to “Multi‐Branch Sustainable Convolutional Neural Network for Disease Classification”