Application Of Convolutional Neural Networks Research Articles

Utilizing CNN to predict homogeneous thermo-mechanical properties of conductive layers for reliability numerical analysis in electronics

This study explores the application of Convolutional Neural Networks (CNN) in predicting the partitioned homogeneous properties (PHPs) of electronic product wiring structures, aiming to enhance the efficiency of reliability analysis through Finite Element Analysis (FEA). A systematic and novel method was developed to generate the input partitioned wiring diagram image sets that foster model generalization and universality. The performance of the CNN-based approach was assessed through regression analysis by employing a leave-one-out cross-validation (LOOCV) approach across three PCBs. Additionally, the predicted PHPs of one of the PCBs were applied in product-level FEA to validate their reliability, further demonstrating the practical applicability of the CNN-based method. The results demonstrate that a well-trained CNN model can accurately predict the properties of previously unencountered wiring structures, thereby facilitating direct application in product-level reliability FEA and improving the efficiency of reliability assessment. Furthermore, efficiency evaluation revealed that the CNN-based method offers significant advantages in terms of time and cost economy compared to the mesoscopic FEA method in determining, highlighting its potential for broader application in electronic product reliability analysis. The findings provide preliminary insights and propose strategies to enhance the applicability of CNN methods in this domain, ultimately aiming to improve the efficiency and reduce costs in reliability assessments, thereby streamlining the overall product development process.

Enhancing lung cancer diagnosis with data fusion and mobile edge computing using DenseNet and CNN

The recent advancements in automated lung cancer diagnosis through the application of Convolutional Neural Networks (CNN) on Computed Tomography (CT) scans have marked a significant leap in medical imaging and diagnostics. The precision of these CNN-based classifiers in detecting and analyzing lung cancer symptoms has opened new avenues in early detection and treatment planning. However, despite these technological strides, there are critical areas that require further exploration and development. In this landscape, computer-aided diagnostic systems and artificial intelligence, particularly deep learning methods like the region proposal network, the dual path network, and local binary patterns, have become pivotal. However, these methods face challenges such as limited interpretability, data variability handling issues, and insufficient generalization. Addressing these challenges is key to enhancing early detection and accurate diagnosis, fundamental for effective treatment planning and improving patient outcomes. This study introduces an advanced approach that combines a Convolutional Neural Network (CNN) with DenseNet, leveraging data fusion and mobile edge computing for lung cancer identification and classification. The integration of data fusion techniques enables the system to amalgamate information from multiple sources, enhancing the robustness and accuracy of the model. Mobile edge computing facilitates faster processing and analysis of CT scan images by bringing computational resources closer to the data source, crucial for real-time applications. The images undergo preprocessing, including resizing and rescaling, to optimize feature extraction. The DenseNet-CNN model, strengthened by data fusion and edge computing capabilities, excels in extracting and learning features from these CT scans, effectively distinguishing between healthy and cancerous lung tissues. The classification categories include Normal, Benign, and Malignant, with the latter further sub-categorized into adenocarcinoma, squamous cell carcinoma, and large cell carcinoma. In controlled experiments, this approach outperformed existing state-of-the-art methods, achieving an impressive accuracy of 99%. This indicates its potential as a powerful tool in the early detection and classification of lung cancer, a significant advancement in medical imaging and diagnostic technology.

GCN-Net: 3D Point Cloud Classification & Localization Using Graph-CNN

In this paper, we have demonstrated the application of a graph convolutional neural network for the purpose of object detection in a LiDAR point cloud. In order to encode the point cloud in the most time-effective manner, we make use of a near-neighbors graph with a defined radius. We create a graph convolutional neural network so that we can find out what kind of object and what class each vertex in a graph represents. We design a box merging and scoring operation to reliably combine detections from numerous vertices into a single score, and we offer an auto-registration strategy as a means of reducing the amount of translation errors that occur inside the system. According to the results of our tests using the KITTI benchmark, we are able to draw the conclusion that the method that was suggested achieves competitive accuracy with the point cloud, even beating fusion-based methods in some instances. According to the results of our research, the graph neural network has the potential to become an effective new tool for the detection of 3D objects.

Application of convolutional neural networks to detect damaged buildings

Application of convolutional neural networks to detect damaged buildings

Integrating convolutional neural networks for improved software engineering: A Collaborative and unbalanced data Perspective

This study pioneers the tailored application of Convolutional Neural Networks (CNNs) for addressing the challenge of unbalanced data in software engineering, a relatively unexplored domain for CNN utilization. Unlike conventional methods, our framework demonstrates a significant precision uplift of up to 15% in software classification tasks, specifically enhancing minority class sample accuracy. This research not only delineates a novel CNN-based approach that outperforms traditional data balancing techniques but also underscores the strategic integration of AI to bolster software engineering processes. By pinpointing the ethical implications, our findings advocate for a conscientious adoption of AI, ensuring software development advances equitably and efficiently.

BNVGLENET: Hypercomplex Bangla handwriting character recognition with hierarchical class expansion using Convolutional Neural Networks

Object recognition technology has made significant strides where recognizing handwritten Bangla characters including symbols, compounds form, etc. remains a challenging problem due to the prevalence of cursive writing and many ambiguous characters. The complexity and variability of the Bangla script, and individual’s unique handwriting styles make it difficult to achieve satisfactory performance for practical applications, and the best existing recognizers are far less effective than those developed for English alpha-numeric characters. In comparison to other major languages, there are limited options for recognizing handwritten Bangla characters. This study has the potential to improve the accuracy and effectiveness of handwriting recognition systems for the Bengali language, which is spoken by over 200 million people worldwide. This paper aims to investigate the application of Convolutional Neural Networks (CNNs) for recognizing Bangla handwritten characters, with a particular focus on enlarging the recognized character classes. To achieve this, a novel challenging dataset for handwriting recognition is introduced, which is collected from numerous students’ handwriting from two institutions. A novel convolutional neural network-based approach called BNVGLENET is proposed in this paper to recognize Bangla handwritten characters by modifying the LeNet-5 and combining it with the VGG architecture, which has the advantage of significantly identifying the characters from Bengali handwriting. This study systematically evaluated the performance of models not only on custom novel dataset but also on the publicly available Bangla handwritten character dataset called the Grapheme dataset. This research achieved a state-of-the-art recognition accuracy of 98.2% on our custom testing vowel-consonant class and 97.5% on the custom individual class. The improvements achieved in this study bridge a notable disparity between the practical needs and the actual performance of Bangla handwritten character recognition systems.

The application of convolutional neural networks in the diagnosis of Parkinson’s disease on the basis of handwriting samples

The application of convolutional neural networks in the diagnosis of Parkinson’s disease on the basis of handwriting samples

Research on the Application of Convolutional Neural Network in Stock Market Forecasting

With the continuous development and complexity of financial markets, stock market forecasting has become a hot topic of concern for investors and decision-makers. This study aims to explore the application of Convolutional Neural Networks (CNN) in stock market prediction, and evaluate their performance in stock index prediction by comparing them with traditional methods such as BP Neural Networks (BPNN) and Support Vector Machines (SVM). In order to further improve the performance of the model, we introduce a model that combines CNN and SVM(CNN-SVM). Experiments show that CNN-SVM model has achieved remarkable advantages in accuracy and robustness, showing the potential value of combining deep learning with traditional machine learning methods. In the empirical analysis, it is found that using CNN-SVM to predict the stock market can achieve relatively superior performance. CNN-SVM can better capture nonlinear relations and complex patterns in time series data through its excellent feature extraction ability. Compared with traditional methods, CNN-SVM shows higher accuracy, precision and recall rate, which verifies its effectiveness in the financial field. The results of this study not only provide investors with more accurate stock market forecasting tools, but also provide a new perspective for the academic research on the combination of deep learning technology in the financial field.

Assessing penmanship of Chinese handwriting: a deep learning-based approach

AbstractThe rise of the digital era has led to a decline in handwriting as the primary mode of communication, resulting in negative effects on handwriting literacy, particularly in complex writing systems such as Chinese. The marginalization of handwriting has contributed to the deterioration of penmanship, defined as the ability to write aesthetically and legibly. Despite penmanship being widely acknowledged as a crucial factor in predicting language literacy, research on its evaluation remains limited, with existing assessments primarily dependent on expert subjective ratings. Recent initiatives have started to explore the application of convolutional neural networks (CNN) for automated penmanship assessment. In this study, we adopted a similar approach, developing a CNN-based automatic assessment system for penmanship in traditional Chinese handwriting. Utilizing an existing database of 39,207 accurately handwritten characters (penscripts) from 40 handwriters, we had three human raters evaluate each penscript’s penmanship on a 10-point scale and calculated an average penmanship score. We trained a CNN on 90% of the penscripts and their corresponding penmanship scores. Upon testing the CNN model on the remaining 10% of penscripts, it achieved a remarkable performance (overall 9.82% normalized Mean Absolute Percentage Error) in predicting human penmanship scores, illustrating its potential for assessing handwriters’ penmanship. To enhance accessibility, we developed a mobile application based on the CNN model, allowing users to conveniently evaluate their penmanship.

Lightweight blueprint residual network for single image super-resolution

The application of deep convolutional neural networks (CNNs) makes the lightweight single image super-resolution (SISR) task develop rapidly in recent years. However, existing lightweight SISR networks for the terminals with limited computing resources are still not efficient enough. In order to further alleviate the model complexity while keeping remarkable reconstruction performance, in this paper, we propose a lightweight blueprint residual network (LBRN), which is a powerful CNN-based SR model while simultaneously maintaining extremely lightweight. Specifically, we design a novel lightweight blueprint residual block (LBRB) to learn the high-frequency information efficiently for lightweight SISR. The LBRB with fewer parameters consists of more efficient convolution operations to extract high-frequency information which helps recover more visual details. In addition, we propose an effective feature fusion residual block (EFFRB) which is composed of three LBRBs with convolutional kernels of different sizes. The EFFRB, which is designed with effective multi-scale receptive fields, can availably extract and fuse multi-scale high-frequency information to obtain discriminative feature, and it further improves model performance. Extensive experiments show that our LBRN achieves superior reconstruction performance quantitatively and visually compared with other lightweight state-of-the-art SR methods.

Application of Convolutional Neural Networks for Early Detection and Classification of Alzheimer's disease from MRI Images

This study investigates the application of convolutional neural networks (CNNs) and traditional machine learning algorithms for the early detection and classification of Alzheimer's disease (AD) using brain Magnetic Resonance Imaging (MRI) data. We compare the performance of CNNs with Support Vector Machines (SVM), Random Forest (RF), and Gradient Boosting Machines (GBM) on a dataset comprising MRI images from AD patients and healthy controls. Results show that CNNs achieved the highest accuracy (90.2%) and area under the receiver operating characteristic curve (AUC-ROC) of 0.95, outperforming SVM, RF, and GBM. The CNN model also exhibited high sensitivity (87.5%) and specificity (92.6%) in distinguishing between AD patients and healthy controls. These findings highlight the effectiveness of CNN-based approaches in leveraging raw MRI images for accurate and early detection of AD.

Application of convolutional neural network and evolutionary algorithm to predict the outcome of adverse drug interactions

Application of convolutional neural network and evolutionary algorithm to predict the outcome of adverse drug interactions

Review on Human Pose Estimation using AI Fitness Tracker

Human pose estimation, a fundamental computer vision task, has witnessed significant advancements with the advent of deep learning techniques. This paper provides an overview of recent developments in human pose estimation, focusing on the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). We explore the distinctions between 2D and 3D pose estimation, highlighting the challenges and solutions for each. The paper discusses the various techniques for single-person and multi-person pose estimation, as well as the trade-offs between part-based and holistic approaches. Additionally, we delve into the real-time and offline aspects of pose estimation and the significance of temporal analysis in videos. Lastly, we touch on the translation of 2D pose information into 3D space. This review underscores the practical implications of human pose estimation in diverse fields such as sports analysis, healthcare, surveillance, and entertainment. The dynamic nature of this field, fueled by ongoing research and technological advancements, promises to unlock new possibilities for human-computer interaction, augmented reality, and beyond. This abstract provides an overview of the paper's focus on deep learning in the context of human pose estimation and highlights the key aspects of the field. You can further tailor it to your specific paper or presentation needs. Keywords: Human pose estimation, camera, Artificial intelligence, Machine learning

Application of Convolutional Neural Networks in Weed Detection and Identification: A Systematic Review

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures used to detect and identify weeds in different crops; 61 articles applying CNN architectures were analyzed during the last five years (2019–2023). The results show the used of different devices to acquire the images for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

Plant Disease Detection Using Machine Learning

Agriculture plays a crucial role in sustaining societies worldwide, and effective crop management is paramount for food security. Plant diseases pose significant threats to agricultural productivity, making timely detection imperative. Leveraging advancements in deep learning and machine vision, this research explores the application of Convolutional Neural Networks (CNNs) to detect tomato leaf diseases. A novel dataset comprising images of diseased and healthy tomato leaves is introduced and utilized for model training. By employing the Inception V3 architecture and data augmentation techniques, the proposed CNN model demonstrates promising results in disease classification. This study presents a framework for leveraging AI/ML techniques to enhance plant disease diagnosis and contribute to global food security efforts. Keywords: Plant Disease Detection, Deep Learning, Convolutional Neural Networks, Inception V3, Agriculture, Tomato Leaf Diseases.

Padang Cuisine Classification using Deep Convolutional Neural Networks (CNN) and Transfer Learning

Padang cuisine, as an integral part of Indonesia's culinary wealth, challenges researchers to explore its potential through technological approaches. This article explores the application of Deep Convolutional Neural Networks (DCNN) and Transfer Learning for the classification of Padang cuisine. DCNN is used to understand and recognize unique visual patterns in food images, while Transfer Learning leverages existing knowledge to improve the model's performance in the specific task of classifying Padang cuisine. This process involves collecting a representative dataset, data preprocessing, and model training to create a system capable of accurately identifying various Padang dishes. Experimental results show that this approach achieves an accuracy rate of 92%, demonstrating its effectiveness in classifying different types of Padang cuisine. By engaging advanced technology, this article contributes to a deeper understanding of the integration between traditional culinary richness and innovation in the modern world of artificial intelligence. These findings indicate that AI implementation can be used to document and celebrate diverse culinary heritage, as well as support the culinary industry in managing and identifying dishes in real-time.

Optimization of Skin Cancer Detection to Improve Accuracy with the Application of Efficient Convolutional Neural Network and EfficientNetB2 Models

Skin cancer, related to ultraviolet light exposure, can be caused by genetic mutations in skin cells. Risk factors include family history, fair skin, moles, weak immunity and solar keratosis. Diagnosis involves skin examination and biopsy. Previous studies using Convolutional Neural Network (CNN) successfully classified skin cancer with an accuracy of up to 99%. The process of developing an image classification model involves structured steps. The dataset is divided into training, validation, testing. Data augmentation is performed with ImageDataGenerator to enrich the dataset. CNN model (EfficientNetB2) was customized, trained for 50 epochs. Evaluation of testing data model, metrics such as loss, accuracy, precision, recall, and F1-score. Visualization of Classification Reports, Confusion Matrix. The entire process ensured in-depth analysis of the model's performance and focused attention on prediction. The study used Kaggle's secondary data "HAM10000 Preprocessed Data" with 11644 data and three attributes, showing variations before normalization. The CNN model peaked at the 8th epoch with 86% accuracy, but there is a risk of overfitting. Evaluation using Classification Report and Confusion Matrix provides details of model performance on each skin cancer class, supporting diagnosis and treatment.This article highlights the positive impact of using the EfficientNetB2 Model on skin cancer detection through an efficient Convolutional Neural Network (CNN). The model is optimal in size and structure, resulting in superior feature representation. Evaluations including Classification Report and Confusion Matrix demonstrate the model's superiority in classifying skin cancer types, particularly in the ''akiec'' and ''bcc'' classes, with high accuracy, significantly improving detection performance.

A novel deep learning technique for medical image analysis using improved optimizer.

Application of Convolutional neural network in spectrum of Medical image analysis are providing benchmark outputs which converges the interest of many researchers to explore it in depth. Latest preprocessing technique Real ESRGAN (Enhanced super resolution generative adversarial network) and GFPGAN (Generative facial prior GAN) are proving their efficacy in providing high resolution dataset. Objective: Optimizer plays a vital role in upgrading the functioning of CNN model. Different optimizers like Gradient descent, Stochastic Gradient descent, Adagrad, Adadelta and Adam etc. are used for classification and segmentation of Medical image but they suffer from slow processing due to their large memory requirement. Stochastic Gradient descent suffers from high variance and is computationally expensive. Dead neuron problem also proves to detrimental to the performance of most of the optimizers. A new optimization technique Gradient Centralization is providing the unparalleled result in terms of generalization and execution time. Method: Our paper explores the next factor which is the employment of new optimization technique, Gradient centralization (GC) to our integrated framework (Model with advanced preprocessing technique). Result and conclusion: Integrated Framework of Real ESRGAN and GFPGAN with Gradient centralization provides an optimal solution for deep learning models in terms of Execution time and Loss factor improvement.

Application of Convolutional Neural Networks for Detecting Sea Ice Leads in the Laptev Sea with Landsat-8 Satellite Imagery

Application of Convolutional Neural Networks for Detecting Sea Ice Leads in the Laptev Sea with Landsat-8 Satellite Imagery

Application of convolutional neural networks trained on optical images for object detection in radar images

Due to the small number of annotated radar image datasets, the use of optical images for training neural networks designed to detect objects in radar images seems promising. However, optical images have some significant differences from radar images and an experimental investigation of this possibility is required. In this work we investigate the applicability of such an approach and show that in the case of detection of ships good results can be achieved. In addition, it is shown that preliminary filtering of speckle noise can improve the results.