Learning Convolutional Neural Network Research Articles

Encoding temporal information in deep convolution neural network.

A recent development in deep learning techniques has attracted attention to the decoding and classification of electroencephalogram (EEG) signals. Despite several efforts to utilize different features in EEG signals, a significant research challenge is using time-dependent features in combination with local and global features. Several attempts have been made to remodel the deep learning convolution neural networks (CNNs) to capture time-dependency information. These features are usually either handcrafted features, such as power ratios, or splitting data into smaller-sized windows related to specific properties, such as a peak at 300 ms. However, these approaches partially solve the problem but simultaneously hinder CNNs' capability to learn from unknown information that might be present in the data. Other approaches, like recurrent neural networks, are very suitable for learning time-dependent information from EEG signals in the presence of unrelated sequential data. To solve this, we have proposed an encoding kernel (EnK), a novel time-encoding approach, which uniquely introduces time decomposition information during the vertical convolution operation in CNNs. The encoded information lets CNNs learn time-dependent features in addition to local and global features. We performed extensive experiments on several EEG data sets-physical human-robot collaborations, P300 visual-evoked potentials, motor imagery, movement-related cortical potentials, and the Dataset for Emotion Analysis Using Physiological Signals. The EnK outperforms the state of the art with an up to 6.5% reduction in mean squared error (MSE) and a 9.5% improvement in F1-scores compared to the average for all data sets together compared to base models. These results support our approach and show a high potential to improve the performance of physiological and non-physiological data. Moreover, the EnK can be applied to virtually any deep learning architecture with minimal effort.

Comparative analysis of convolutional neural network and DenseNet121 transfer learning in agriculture focusing on crop leaf disease identification

PurposePlant cultivation holds a pivotal role in agriculture, necessitating precise disease identification for the overall health of plants. This research conducts a comprehensive comparative analysis between two prominent deep learning algorithms, convolutional neural network (CNN) and DenseNet121, with the goal of enhancing disease identification in tomato plant leaves.Design/methodology/approachThe dataset employed in this investigation is a fusion of primary data and publicly available data, covering 13 distinct disease labels and a total of 18,815 images for model training. The data pre-processing workflow prioritized activities such as normalizing pixel dimensions, implementing data augmentation and achieving dataset balance, which were subsequently followed by the modeling and testing phases.FindingsExperimental findings elucidated the superior performance of the DenseNet121 model over the CNN model in disease classification on tomato leaves. The DenseNet121 model attained a training accuracy of 98.27%, a validation accuracy of 87.47% and average recall, precision and F1-score metrics of 87, 88 and 87%, respectively. The ultimate aim was to implement the optimal classifier for a mobile application, namely Tanamin.id, and, therefore, DenseNet121 was the preferred choice.Originality/valueThe integration of private and public data significantly contributes to determining the optimal method. The CNN method achieves a training accuracy of 90.41% and a validation accuracy of 83.33%, whereas the DenseNet121 method excels with a training accuracy of 98.27% and a validation accuracy of 87.47%. The DenseNet121 architecture, comprising 121 layers, a global average pooling (GAP) layer and a dropout layer, showcases its effectiveness. Leveraging categorical_crossentropy as the loss function and utilizing the stochastic gradien descent (SGD) Optimizer with a learning rate of 0.001 guides the course of the training process. The experimental results unequivocally demonstrate the superior performance of DenseNet121 over CNN.

Study on automatic lithology identification based on convolutional neural network and deep transfer learning

Automatic and fast rock classification identification is an important part of geotechnical intelligent survey system. Image based supervised deep learning analysis, especially for convolutional neural networks (CNN), has potential in optimizing lithologic classification and interpretation using borehole core images. However, the accuracy and efficiency of lithology identification models are low at present. In this work, a systematic and enormous rock data framework based on the geological rock classification system is firstly established to provide rock learning datasets. The dataset is composed of approximately 150,000 images of rock samples, which covers igneous rocks, sedimentary rocks, and metamorphic rocks. Secondly, based on CNN-deep transfer learning algorithm, an end-to-end, image-to-label rock lithology identification is established. Finally, the generalization of the proposed model and the field drilling core verification test show that the constructed intelligent rock recognition model has an ability to identify rocks quickly and accurately, and the recognition accuracy of 12 kinds of common engineering rocks is more than 95%. The proposed rock intelligent classification model provides a convenient and fast tool for field geologists and scientific researchers.

Preliminary study on AI-assisted diagnosis of bone remodeling in chronic maxillary sinusitis

ObjectiveTo construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary sinusitis (CMS) based on CT image data to improve the accuracy of image diagnosis.MethodsMaxillary sinus CT data of 1000 samples in 500 patients from January 2018 to December 2021 in our hospital was collected. The first part is the establishment and testing of chronic maxillary sinusitis detection model by 461 images. The second part is the establishment and testing of the detection model of chronic maxillary sinusitis with bone remodeling by 802 images. The sensitivity, specificity and accuracy and area under the curve (AUC) value of the test set were recorded, respectively.ResultsPreliminary application results of CT based AI in the diagnosis of chronic maxillary sinusitis and bone remodeling. The sensitivity, specificity and accuracy of the test set of 93 samples of CMS, were 0.9796, 0.8636 and 0.9247, respectively. Simultaneously, the value of AUC was 0.94. And the sensitivity, specificity and accuracy of the test set of 161 samples of CMS with bone remodeling were 0.7353, 0.9685 and 0.9193, respectively. Simultaneously, the value of AUC was 0.89.ConclusionIt is feasible to use artificial intelligence research methods such as deep learning and machine learning to automatically identify CMS and bone remodeling in MSCT images of paranasal sinuses, which is helpful to standardize imaging diagnosis and meet the needs of clinical application.

Multi‐model deep learning system for screening human monkeypox using skin images

AbstractPurposeHuman monkeypox (MPX) is a viral infection that transmits between individuals via direct contact with animals, bodily fluids, respiratory droplets, and contaminated objects like bedding. Traditional manual screening for the MPX infection is a time‐consuming process prone to human error. Therefore, a computer‐aided MPX screening approach utilizing skin lesion images to enhance clinical performance and alleviate the workload of healthcare providers is needed. The primary objective of this work is to devise an expert system that accurately classifies MPX images for the automatic detection of MPX subjects.MethodsThis work presents a multi‐modal deep learning system through the fusion of convolutional neural network (CNN) and machine learning algorithms, which effectively and autonomously detect MPX‐infected subjects using skin lesion images. The proposed framework, termed MPXCN‐Net is developed by fusing deep features of three pre‐trained CNNs: MobileNetV2, DarkNet19, and ResNet18. Three classifiers—K‐nearest neighbour, support vector machine (SVM), and ensemble classifier—with various kernel functions, are used to identify infected patients. To validate the efficacy of our proposed system, we employ a publicly accessible MPX skin lesion dataset.ResultsBy amalgamating features extracted from all three CNNs and utilizing the medium Gaussian kernel of the SVM classifier, our proposed system achieves an outstanding average classification accuracy of 90.4%.ConclusionsDeveloped MPXCN‐Net is suitable for testing with a large diversified dataset before being used in clinical settings.

A CNN-based spline active surface method with an after-balancing step for 3D medical image segmentation

Over the past few years, tasks such as automatic information extraction and object surface detection from 3D medical images have become increasingly popular, providing clinicians with numerous new opportunities for exploration and diagnostic assistance. Nonetheless, the segmentation process can present various challenges. This paper introduces an automatic 3D deep parametric active surface model (3D B-snake) approximated by bivariate Unified and Extended spline (UE-spline) functions with a parameter controlling the shape of the snake. We introduce an energy term that enables to separate the different textures present in an image using a Convolutional Neural Network (CNN) learning model, namely U-Net. After balancing our snake surface to align it with the complex parts of the object to be segmented, an object snake alignment strategy is proposed using an interpolation scheme that exploits some geometric properties of the object. Experiments performed on the BraTS21 dataset show that our model is very powerful to deal with various difficulties encountered in medical image segmentation.

MEGANET: Improved framework with nature inspired approach for colorectal cancer polyp classification

BACKGROUND: Polyps are tumorous growths in the colon or rectal area which can turn into cancer at later stages, thus detection of polyps is very important for timely prevention of colorectal cancer. The aim of the study is to develop a framework to accurately detect polyp images in colonoscopy images. OBJECTIVE: Development of an intelligent framework for classification of colorectal cancer from colon and rectal images. The standard machine learning, convolutional neural networks and ensemble models with nature inspired approach were implemented for this study. Model optimization was performed by varying hyper parameters. The main objective was to find an optimal model with high accuracy, optimized weights and less parameters. METHODS: The deep learning Convolutional Neural Network (CNN) models such as VGG19, ResNet50, EfficientNet, Ensemble Model (EM), and Modified Ensemble CNN with Genetic Algorithm (MEGANET) were implemented for the classification of colon images. RESULTS: Ensemble model was also created with two best performing deep learning models to further achieve higher accuracy of 96%. The ensemble model outperformed the other models in terms of accuracy, precision, recall, and F1 score. But this model has more complexity. The MEGANET, nature inspired evolutionary ensemble CNN model was implemented with transfer learning and genetic algorithms for weights optimization and parameter reduction. It achieved accuracy of 95%, on training data. CONCLUSION: The MEGANET performed similar to EM with less number of parameters on training, validation and test dataset. In future different methods will be implemented to further reduce the parameters and attain reasonable accuracy using MEGANET.

SandSnap: Measuring and mapping beach grain size using crowd-sourced smartphone images

Sediment grain size is a critical parameter for sediment mobilization and transport, but often has the highest uncertainty of any coastal sediment transport model input parameter. SandSnap is an initiative to engage the public to amass a beach grain size database by taking photos of the beach sand with a coin in the image for scale and uploading the image to a web application. Images are analyzed with two deep learning convolutional neural networks one to detect the coin and the second to measure the grain size, which is trained on sediment samples within the sand regime. The results for nine gradation metrics are returned to the user within 2 min of image upload. Results from 263 test images have a mean percent error of −6.5% and median absolute error of 22.4% for the median grain size (d50) with a small fine bias of −0.042 mm. The use of the database is highlighted by applying SandSnap output as an input to the AeoLiS aeolian sediment transport model to predict coastal dune growth at a nearly national scale using the full eight grain size classes (d10 – d90) from the SandSnap database. These outputs are used to inform the potential value of having spatially comprehensive grain size distribution information as part of coastal engineering design and planning. Education and outreach techniques for the SandSnap initiative are described in the manuscript. Though some challenges remain, the spatially and temporally robust beach grain size database being developed by SandSnap will help to improve numerous coastal engineering analyses including coastal resilience and vulnerability quantification, beach nourishment life cycle and uncertainty analysis, beach compatibility for the beneficial use of dredged sediment, and large-scale coastal morphology modeling.

Array Nulling Synthesis Based on Hyper-Parameter Optimized Self-Paced Learning Convolutional Neural Networks

Array Nulling Synthesis Based on Hyper-Parameter Optimized Self-Paced Learning Convolutional Neural Networks

Enhancing Diagnostic: Machine Learning in Medical Image Analysis

Medical image analysis is critical for accurate diagnosis and treatment in modern healthcare. This paper focuses on application of machine learning (ML) approaches in context of medical image classification. Aim is to develop robust ML models capable of automatically analyzing. Then classifying medical images. These models should possess high accuracy. Traditional methods of image analysis rely heavily on human interpretation. This reliance can be time-consuming and prone to variability. Moreover the increasing complexity of medical data further challenge these traditional approaches. In contrast ML algorithms offer potential to efficiently handle large datasets. They can extract meaningful patterns from images This supports more precise clinical decision making This research investigates various ML techniques such as deep learning convolutional neural networks (CNNs) and ensemble methods for their effectiveness in medical image classification tasks. By harnessing these techniques. Project seeks to advance field. Providing automated tools that can assist healthcare professionals in interpreting medical images more effectively. Ultimate goal is to improve patient outcomes. By accelerating diagnostic process. Facilitating early intervention strategies based on reliable image analysis. Significance of this study lies in its potential to overcome current limitations in medical image analysis. It paves way for enhanced diagnostic accuracy. Leading to more efficient healthcare delivery. Findings contribute to broader goal of integrating ML into clinical practice. Thereby realizing promise of personalized medicine. Optimized patient care. Key Words: Machine Learning, Convolutional Neural Networks (CNNs), Diagnostic Imaging, Radiology, Computer-Aided Diagnosis (CAD), Clinical Decision Support, Accuracy, Image Classification, Deep Learning, Feature Extraction.

Cervical Spine Fracture Detection Using Deep Learning

We've been looking into different disease detection models that use deep learning algorithms to look at medical radiograph images. Most of the studies have been done on lumbar spine diseases, but most of the studies were done on cervical spine diseases. Cervical radiculopathy is usually diagnosed based on MRI data, but it can be hard to diagnose even with an X-ray. MRI tests are expensive, so it can be hard for patients to get the right diagnosis. Cervical spine fractures are a medical emergency, and they can lead to permanent paralysis or even death. To make sure patients get the right diagnosis, it's important to use CT scans to check for fractures. We've come up with a Convolutional Neural Network (CNN) and Transfer Learning Model that can automatically detect cervical spine fractures from CT axial images, and we've trained and validated it using 4000 CT scans. We can even fine tune the transfer learning models to make it even more accurate. Keywords Convolutional Neural Networks, Computed tomography ,Deep learning , CT image , x ray , medical image , Spine disease , cervical spine fracture , Graphical user interface , Cervical radiculopathy.

Deep Learning Voigt Profiles. I. Single-Cloud Doublets

Voigt profile (VP) decomposition of quasar absorption lines is key to studying intergalactic gas and the baryon cycle governing the formation and evolution of galaxies. The VP velocities, column densities, and Doppler b parameters inform us of the kinematic, chemical, and ionization conditions of these astrophysical environments. A drawback of traditional VP fitting is that it can be human-time intensive. With the coming next generation of large all-sky survey telescopes with multiobject high-resolution spectrographs, the time demands will significantly outstrip our resources. Deep learning pipelines hold the promise to keep pace and deliver science-digestible data products. We explore the application of deep learning convolutional neural networks (CNNs) for predicting VP-fitted parameters directly from the normalized pixel flux values in quasar absorption line profiles. A CNN was applied to 56 single-component Mg ii λ λ2796, 2803 doublet absorption line systems observed with HIRES and UVES (R = 45,000). The CNN predictions were statistically indistinct from those of a traditional VP fitter. The advantage is that, once trained, the CNN processes systems ∼105 times faster than a human expert fitting VP profiles by hand. Our pilot study shows that CNNs hold promise to perform bulk analysis of quasar absorption line systems in the future.

A Knowledge-Guided Approach for Landslide Susceptibility Mapping Using Convolutional Neural Network and Graph Contrastive Learning

Landslide susceptibility mapping (LSM) constitutes a valuable analytical instrument for estimating the likelihood of landslide occurrence, thereby furnishing a scientific foundation for the prevention of natural hazards, land-use planning, and economic development in landslide-prone areas. Existing LSM methods are predominantly data-driven, allowing for significantly enhanced monitoring accuracy. However, these methods often overlook the consideration of landslide mechanisms and uncertainties associated with non-landslide samples, resulting in lower model reliability. To effectively address this issue, a knowledge-guided landslide susceptibility assessment framework is proposed in this study to enhance the interpretability and monitoring accuracy of LSM. First, a landslide knowledge graph is constructed to model the relationships between landslide entities and summarize landslide susceptibility rules. Next, combining the obtained landslide rules with geographic similarity principles, high-confidence non-landslide samples are selected to optimize the quality of the samples. Subsequently, a Landslide Knowledge Fusion Cell (LKF-Cell) is utilized to couple landslide data with landslide knowledge, resulting in the acquisition of informative and semantically rich landslide event features. Finally, a precise and credible landslide susceptibility assessment model is built based on a convolutional neural network (CNN), and landslide susceptibility spatial distribution levels are mapped. The research findings indicate that the CNN-based model outperforms traditional machine learning algorithms in predicting landslide probability; in particular, the Area Under the Curve (AUC) of the model was improved by 3–6% after sample optimization, and the AUC value of the LKF-Cell method was 6–11% higher than the baseline method.

Enhancing oral squamous cell carcinoma detection: a novel approach using improved EfficientNet architecture

ProblemOral squamous cell carcinoma (OSCC) is the eighth most prevalent cancer globally, leading to the loss of structural integrity within the oral cavity layers and membranes. Despite its high prevalence, early diagnosis is crucial for effective treatment.AimThis study aimed to utilize recent advancements in deep learning for medical image classification to automate the early diagnosis of oral histopathology images, thereby facilitating prompt and accurate detection of oral cancer.MethodsA deep learning convolutional neural network (CNN) model categorizes benign and malignant oral biopsy histopathological images. By leveraging 17 pretrained DL-CNN models, a two-step statistical analysis identified the pretrained EfficientNetB0 model as the most superior. Further enhancement of EfficientNetB0 was achieved by incorporating a dual attention network (DAN) into the model architecture.ResultsThe improved EfficientNetB0 model demonstrated impressive performance metrics, including an accuracy of 91.1%, sensitivity of 92.2%, specificity of 91.0%, precision of 91.3%, false-positive rate (FPR) of 1.12%, F1 score of 92.3%, Matthews correlation coefficient (MCC) of 90.1%, kappa of 88.8%, and computational time of 66.41%. Notably, this model surpasses the performance of state-of-the-art approaches in the field.ConclusionIntegrating deep learning techniques, specifically the enhanced EfficientNetB0 model with DAN, shows promising results for the automated early diagnosis of oral cancer through oral histopathology image analysis. This advancement has significant potential for improving the efficacy of oral cancer treatment strategies.

A deep learning based approach for image retrieval extraction in mobile edge computing

AbstractDeep learning has been widely explored in 5G applications, including computer vision, the Internet of Things (IoT), and intermedia classification. However, applying the deep learning approach in limited-resource mobile devices is one of the most challenging issues. At the same time, users’ experience in terms of Quality of Service (QoS) (e.g., service latency, outcome accuracy, and achievable data rate) performs poorly while interacting with machine learning applications. Mobile edge computing (MEC) has been introduced as a cooperative approach to bring computation resources in proximity to end-user devices to overcome these limitations. This article aims to design a novel image reiterative extraction algorithm based on convolution neural network (CNN) learning and computational task offloading to support machine learning-based mobile applications in resource-limited and uncertain environments. Accordingly, we leverage the framework of image retrieval extraction and introduce three approaches. First, privacy preservation is strict and aims to protect personal data. Second, network traffic reduction. Third, minimizing feature matching time. Our simulation results associated with real-time experiments on a small-scale MEC server have shown the effectiveness of the proposed deep learning-based approach over existing schemes. The source code is available here: https://github.com/jamalalasadi/CNN_Image_retrieval.

Improving the Concrete Crack Detection Process via a Hybrid Visual Transformer Algorithm.

Inspections of concrete bridges across the United States represent a significant commitment of resources, given their biannual mandate for many structures. With a notable number of aging bridges, there is an imperative need to enhance the efficiency of these inspections. This study harnessed the power of computer vision to streamline the inspection process. Our experiment examined the efficacy of a state-of-the-art Visual Transformer (ViT) model combined with distinct image enhancement detector algorithms. We benchmarked against a deep learning Convolutional Neural Network (CNN) model. These models were applied to over 20,000 high-quality images from the Concrete Images for Classification dataset. Traditional crack detection methods often fall short due to their heavy reliance on time and resources. This research pioneers bridge inspection by integrating ViT with diverse image enhancement detectors, significantly improving concrete crack detection accuracy. Notably, a custom-built CNN achieves over 99% accuracy with substantially lower training time than ViT, making it an efficient solution for enhancing safety and resource conservation in infrastructure management. These advancements enhance safety by enabling reliable detection and timely maintenance, but they also align with Industry 4.0 objectives, automating manual inspections, reducing costs, and advancing technological integration in public infrastructure management.

Artificial Intelligence Approach for Classifying Images of Upper-Atmospheric Transient Luminous Events.

Transient Luminous Events (TLEs) are short-lived, upper-atmospheric optical phenomena associated with thunderstorms. Their rapid and random occurrence makes manual classification laborious and time-consuming. This study presents an effective approach to automating the classification of TLEs using state-of-the-art Convolutional Neural Networks (CNNs) and a Vision Transformer (ViT). The ViT architecture and four different CNN architectures, namely, ResNet50, ResNet18, GoogLeNet, and SqueezeNet, are employed and their performance is evaluated based on their accuracy and execution time. The models are trained on a dataset that was augmented using rotation, translation, and flipping techniques to increase its size and diversity. Additionally, the images are preprocessed using bilateral filtering to enhance their quality. The results show high classification accuracy across all models, with ResNet50 achieving the highest accuracy. However, a trade-off is observed between accuracy and execution time, which should be considered based on the specific requirements of the task. This study demonstrates the feasibility and effectiveness of using transfer learning and pre-trained CNNs for the automated classification of TLEs.

Human Emotion Detection Using CNN and Transfer Learning

Facial emotion detection is a critical component in human-computer interaction, mental health assessment, and security systems. In this project, we propose a robust facial emotion detection system leveraging state-of-the-art deep learning techniques. Our system utilizes Convolutional Neural Networks (CNNs) to extract meaningful features from facial images and classify them into five distinct emotional categories: neutral, surprise, sad, happy, and angry. We conducted extensive experiments on a diverse dataset consisting of over 10,000 annotated facial images collected from various sources. Through data augmentation techniques such as rotation, translation, and flipping, we expanded the dataset to enhance model training. Additionally, we employed transfer learning by fine-tuning a pre-trained CNN model, ResNet50, on our dataset to leverage its learned features. This project presents a system for real-time emotion monitoring using computer vision techniques. The system utilizes the Haar Cascade Classifier for face detection in live webcam video streams. Furthermore, we evaluated the system's performance across different lighting conditions, poses, and facial occlusions to assess its robustness in real-world scenarios. Our results indicate that the system maintains consistent performance across diverse conditions, making it suitable for deployment in applications requiring real-time facial emotion recognition.

Research on sound quality of roller chain transmission system based on multi-source transfer learning

To establish the sound quality evaluation model of roller chain transmission system, we collect the running noise under different working conditions. After the noise samples are preprocessed, a group of experienced testers are organized to evaluate them subjectively. Mel frequency cepstral coefficient (MFCC) of each noise sample is calculated, and the MFCC feature map is used as an objective evaluation. Combining with the subjective and objective evaluation results of the roller chain system noise, we can get the original dataset of its sound quality research. However, the number of high-quality noise samples is relatively small. Based on the sound quality research of various chain transmission systems, a novel method called multi-source transfer learning convolutional neural network (MSTL-CNN) is proposed. By transferring knowledge from multiple source tasks to target task, the difficulty of small sample sound quality prediction is solved. Compared with the problem that single source task transfer learning has too much error on some samples, MSTL-CNN can give full play to the advantages of all transfer learning models. The results also show that the MSTL-CNN proposed in this paper is significantly better than the traditional sound quality evaluation methods.

Traffic Flow Optimization at Toll Plaza Using Proactive Deep Learning Strategies

Global urbanization and increasing traffic volume have intensified traffic congestion throughout transportation infrastructure, particularly at toll plazas, highlighting the critical need to implement proactive transportation infrastructure solutions. Traditional toll plaza management approaches, often relying on manual interventions, suffer from inefficiencies that fail to adapt to dynamic traffic flow and are unable to produce preemptive control strategies, resulting in prolonged queues, extended travel times, and adverse environmental effects. This study proposes a proactive traffic control strategy using advanced technologies to combat toll plaza congestion and optimize traffic management. The approach involves deep learning convolutional neural network models (YOLOv7–Deep SORT) for vehicle counting and an extended short-term memory model for short-term arrival rate prediction. When projected arrival rates exceed a threshold, the strategy proactively activates variable speed limits (VSLs) and ramp metering (RM) strategies during peak hours. The novelty of this study lies in its predictive and adaptive capabilities, ensuring efficient traffic flow management. Validated through a case study at Ravi Toll Plaza Lahore using PTV VISSIMv7, the proposed method reduces queue length by 57% and vehicle delays by 47% while cutting fuel consumption and pollutant emissions by 28.4% and 34%, respectively. Additionally, by identifying the limitations of conventional approaches, this study presents a novel framework alongside the proposed strategy to bridge the gap between theory and practice, making it easier for toll plaza operators and transportation authorities to adopt and benefit from advanced traffic management techniques. Ultimately, this study underscores the importance of integrated and proactive traffic control strategies in enhancing traffic management, minimizing congestion, and fostering a more sustainable transportation system.