Convolutional Neural Network Approach Research Articles

GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-Resolved EEG Motor Imagery Signals.

Toward the development of effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by an electroencephalogram (EEG) is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning (DL) framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected (FC) softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and groupwise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet dataset), 96.24% and 80.89% (high gamma dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step toward better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain MI. A DL library for EEG task classification including the code for this study is open source at https://github.com/SuperBruceJia/ EEG-DL for scientific research.

Mandatory age verification for pornography access: Why it can't and won't ‘save the children’

Age verification is currently gaining traction among some western democracies as a means to restrict minors’ access to online pornography. In this article we consider the ramifications of applying age estimation software to this task. We analyse a public dataset of 10,139 facial images processed through a commonly used high-performance convolutional neural network approach and find significant inconsistencies in classification performance. Notably, the software demonstrates racial bias, with highest accuracy for the Caucasian category and lowest accuracy for the African category. It also displays age and gender bias, with lower accuracy for young males compared to young females. In addition to underwhelming technical performance, we argue that the concept of employing automated processes to restrict access to pornography is not only problematic but fundamentally misconceived. The systems being proposed to automate age verification create greater user data privacy risks and divert resourcing that could be spent on strategies that are proven to support healthy sexual development. Ultimately, mandatory age verification systems create barriers to post-pubescent young people seeking information about sex online. Our study concludes that the underlying problem with age verification, therefore, is not only technical but more profoundly political: even if the system can be made to work, it should not be.

Nonlinear Analysis in Skin Cancer Detection: Customized Convolutional Neural Networks Approach

Nonlinear Analysis in Skin Cancer Detection: Customized Convolutional Neural Networks Approach

Drowsiness Detection in the Advanced Driver-Assistance System using YOLO V5 Detection Model

The development of Artificial Intelligence (AI) in the automobile industry, particularly in the Advanced Driver-Assistance System (ADAS), has been increasing rapidly in recent years. One of the essential features of ADAS is the drowsiness alert system, which monitors the state of the driver's eyes. This article presents a study on the development of ADAS that focuses on drowsiness detection using deep learning through a Convolutional Neural Network (CNN) approach. The study utilized the YOLO V5 model for object detection, which was trained using custom datasets containing images annotated with two labels: "Mengantuk" (Drowsy) and "Bangun" (Awake) The goal was to recognize whether the driver was drowsy or awake. The results of the study showed that the modified YOLO V5 CNN Model had high accuracy based on evaluation metrics in terms of accuracy, precision, and recall in detecting drowsiness around the area of the eyes, with a Mean Average Precision (mAP) of 99.5% and an F1-Score of 99.8%. For better understanding and visualization, the model was tested using real-time detection through a web camera, using Jetson Nano as the inference device. The model detected drowsiness in real time, with a confidence rate of 80% to 97%

BRAIN TUMOR DETECTION USING MACHINE LEARNING

A brain tumor is the cause of abnormal growth of cells in the brain. Magnetic resonance imaging (MRI) is the most practical method for detecting brain tumors. Through these MRIs, doctors analyze and identify abnormal tissue growth and can confirm whether the brain is affected by a tumor or not. Today, with the emergence of artificial intelligence techniques, the detection of brain tumors is done by applying the techniques and algorithms of machine learning and deep learning. The advantages of the application of these algorithms are the quick prediction of brain tumors, fewer errors, and greater precision, which help in decision-making and in choosing the most appropriate treatment for patients. In the proposed work, a convolution neural network (CNN) is applied with the aim of detecting the presence of a brain tumor and its performance is analyzed. The main purpose of this article is to adopt the approach of convolutional neural networks as a machine learning technique to perform brain tumor detection and classification. Based on training and testing results, the pre- trained architecture model reaches 96% in precision and classification accuracy rates. For the given dataset, CNN proves to be the better technique for predicting the presence of brain tumors. Keywords—Brain tumor; machine learning; convolutional neural network; MRI images

The powerful lens galaxy cluster PLCK G287.0+32.9 (θE ∼ 43″)

Aims. We present a new high-precision strong-lensing model of PLCK G287.0+32.9, a massive lens galaxy cluster at z = 0.383, with the aim of obtaining an accurate estimation of its effective Einstein radius and total mass distribution. We also present a spectroscopic catalog containing accurate redshift measurements for close to 500 objects up to redshift z = 6, including multiply lensed sources and cluster member galaxies. Methods. We exploited high-quality spectroscopic data from the Multi Unit Spectroscopic Explorer (MUSE), covering a central 3 arcmin2 region of the cluster. We supplemented the spectroscopic catalog by including redshift measurements from VIsible MultiObject Spectrograph (VIMOS) and DEep Imaging Multi-Object Spectrograph (DEIMOS). We identified 129 spectroscopic cluster member galaxies with redshift values of 0.360 ≤ z ≤ 0.405, and mF160W ≤ 21. We complemented this galaxy cluster member sample with 24 photometric members identified with a convolutional neural network (CNN) approach. We also identified 114 multiple images from 28 background sources, of which 84 images from 16 sources are new and the remaining ones have already been identified in previous works. From these, we extracted “golden sample” of 47 secure multiple images and used them, together with the selected cluster member, to build and optimize several strong-lensing models with the software lenstool. Results. The best-fitting lens model shows a root mean square (RMS) separation value between the predicted and observed positions of the multiple images of 0.″75. Using its predictive power, we found three new multiple images and we confirm the configuration of three systems of multiple images that were not used for the optimization of the model. For a source at a redshift of zs = 2, we found a cluster with an Einstein radius of θE = 43.4″ ± 0.1″. This value is in agreement with previous estimates and corresponds to a total mass enclosed in the critical curve of ME = 3.33−0.07+0.02 × 1014 M⊙. Conclusions. The combined application of ancillary Hubble Space Telescope (HST) imaging, VIMOS and DEIMOS data, and the new MUSE spectroscopic observations allowed us to build a new lens model of the galaxy cluster PLCK G287.0+32.9, with an improvement in terms of reconstructing the observed positions of the multiple images of a factor of 2.5 with respect to previous models. The derived total mass distribution confirms this cluster to be a very prominent gravitational lens, with an effective Einstein radius of θE ∼ 43″. We were also able to construct an extensive spectroscopic catalog containing 490 objects, of which 153 are bright cluster members with mF160W ≤ 21, and 114 are multiple images.

Stock Price Prediction Using Machine Learning

This project’s Researchers have been studying different methods to effectively predict the stock market price. Useful prediction systems allow traders to get better insights about data such as: future trends. Also, investors have a major benefit since the analysis give future conditions of the market. One such method is to use machine learning algorithms for forecasting. A number of researchers have come up with various ways to solve this problem, mainly there are traditional methods so far, such as artificial neural network is a way to get hidden patterns and classify the data which is used in predicting stock market. This project proposes a different method for prognosing stock market prices. It does not fit the data to a specific model; rather we are identifying the latent dynamics existing in the data using machine learning architectures. In this work we use Machine learning architectures Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Hybrid approach of LSTM + CNN for the price forecasting of NSE listed companies and differentiating their performance. On a long term basis, sling window approach has been applied and the performance was assessed by using root mean square error.

Demonstration of event position reconstruction based on diffusion in the NEXT-white detector

Noble element time projection chambers are a leading technology for rare event detection in physics, such as for dark matter and neutrinoless double beta decay searches. Time projection chambers typically assign event position in the drift direction using the relative timing of prompt scintillation and delayed charge collection signals, allowing for reconstruction of an absolute position in the drift direction. In this paper, alternate methods for assigning event drift distance via quantification of electron diffusion in a pure high pressure xenon gas time projection chamber are explored. Data from the NEXT-White detector demonstrate the ability to achieve good position assignment accuracy for both high- and low-energy events. Using point-like energy deposits from 83m\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{83\ extrm{m}}$$\\end{document}Kr calibration electron captures (E∼45\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$E\\sim 45$$\\end{document} keV), the position of origin of low-energy events is determined to 2 cm precision with bias <1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$< 1~$$\\end{document}mm. A convolutional neural network approach is then used to quantify diffusion for longer tracks (E≥1.5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$E\\ge ~1.5$$\\end{document} MeV), from radiogenic electrons, yielding a precision of 3 cm on the event barycenter. The precision achieved with these methods indicates the feasibility energy calibrations of better than 1% FWHM at Qββ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$_{\\beta \\beta }$$\\end{document} in pure xenon, as well as the potential for event fiducialization in large future detectors using an alternate method that does not rely on primary scintillation.

Classification of mango disease using ensemble convolutional neural network

Mango is a highly significant fruit crop that thrives in a variety of agro-ecologies around the world. Mangoes are rich in vitamins and minerals. However, its yield is currently severely constrained due to disease and pest infestations. Thus, in order to improve mango fruit quality and productivity, illnesses and insect pests must be detected early on. In this study, we conceived and constructed a mango leaf disease detection mechanism utilizing an ensemble convolutional neural network approach. Healthy and diseased mango leaf images were manually obtained from main producing locations in Amhara Region for Merawi fruit and vegetable research identification. To improve the datasets, several pre-processing procedures (such as image resizing, noise reduction, and image augmentation) were used. To improve classification performance and meet the study's purpose, various segmentation approaches such as k means and Mask R-CNN were applied. Furthermore, following pre-processing and segmentation, features of mango leaf images were retrieved using CNN to obtain important features. The classification model was then constructed using fully-connected layer classifiers on the retrieved features of mango leaf images. The ensemble proposed GoogLeNet and VGG16 based CNN model in the study encompasses various operations, including dataset collection, image preprocessing, noise removal, segmentation, data augmentation, feature extraction, and classification. Upon testing, the model demonstrated impressive performance with 99.87 % training classification accuracy, 99.72 % validation accuracy, and 99.21 % testing accuracy. This indicates the effectiveness of the ensemble approach in achieving high accuracy in image classification tasks.

An Effective Deep Learning Approach For Handwritten Ol-Chiki Character Recognition

In this paper, we propose a deep convolution neural network approach to recognize Ol-Chiki handwritten characters. Here we describe recognition of handwritten basic characters of Ol-Chiki script, used by more than 10 million tribal people in India mostly from Assam, Bengal, Bihar, Odisha and Jharkhand. There are 30 basic characters and 10 numeral digits in Ol-Chiki. We have used a dataset of 10000 handwritten isolated character samples written by 100 persons. Convolution Neural Network (CNN) architecture has been used for the recognition of handwritten isolated Ol-Chiki characters. Our system has been tested on Ol-Chiki isolated dataset and we have achieved 92% accuracy on almost on all Ol-Chiki characters.

An ergonomic evaluation using a deep learning approach for assessing postural risks in a virtual reality-based smart manufacturing context

This study proposes an integrated ergonomic evaluation designed to identify unsafe postures, whereby postural risks during industrial work are assessed in the context of virtual reality-based smart manufacturing. Unsafe postures were recognised by identifying the displacements of the centre of mass (COM) of body keypoints using a computer vision-based deep learning (DL) convolutional neural network approach. The risk levels for the identified unsafe postures were calculated using ergonomic risk assessment tools rapid upper limb assessment and rapid whole-body assessment. An analysis of variance was conducted to determine significant differences between the vertical and horizontal directions of postural movements associated with the most unsafe postures. The findings assess the ergonomic risk levels and identify the most unsafe postures during industrial work in smart manufacturing using DL method. The identified postural risks can help industry managers and researchers acquire a better understanding of unsafe postures.

Clusternets: a deep learning approach to probe clustering dark energy

ABSTRACT Machine learning (ML) algorithms are becoming popular in cosmology for extracting valuable information from cosmological data. In this paper, we evaluate the performance of a convolutional neural network (CNN) trained on matter density snapshots to distinguish clustering dark energy (DE) from the cosmological constant scenario and to detect the speed of sound (cs) associated with clustering DE. We compare the CNN results with those from a Random Forest (RF) algorithm trained on power spectra. Varying the DE equation of state parameter wDE within the range of −0.7 to −0.99 while keeping $c_s^2 = 1$, we find that the CNN approach results in a significant improvement in accuracy over the RF algorithm. The improvement in classification accuracy can be as high as 40 per cent depending on the physical scales involved. We also investigate the ML algorithms’ ability to detect the impact of the speed of sound by choosing $c_s^2$ from the set {1, 10−2, 10−4, 10−7} while maintaining a constant wDE for three different cases: wDE ∈ {−0.7, −0.8, −0.9}. Our results suggest that distinguishing between various values of $c_s^2$ and the case where $c_s^2=1$ is challenging, particularly at small scales and when wDE ≈ −1. However, as we consider larger scales, the accuracy of $c_s^2$ detection improves. Notably, the CNN algorithm consistently outperforms the RF algorithm, leading to an approximate 20 per cent enhancement in $c_s^2$ detection accuracy in some cases.

Currency Classification Using Deep Learning

Among the uses of machine learning is the recognition of facial expressions. Based on the features that are derived from an image, it assigns a facial expression to one of the classes of facial expressions. Convolutional Neural Network (CNN) is a classification technique that may also be used to identify patterns in an image. We used the CNN approach to identify facial expressions in our proposed study. To increase the precision of facial emotion recognition, the wavelet transform is used after CNN processing. Seven distinct facial expressions are included in the facial expression image dataset that was obtained from Kaggle. The findings of the face expression recognition experiment utilizing CNN and wavelet transform show that the accuracy is improved, and the output is audible. Index Terms: Facial and Convolutional Neural Nets

Metallurgical microstructure classification using CNN: A comprehensive study on heat treatment analysis for steel

Predicting metallurgical microstructures is challenging due to the intricate features that emerge during manufacturing. This research utilizes Convolutional Neural Networks (CNNs) to recognize microstructure images of mild steel alloys, representing diverse microstructures. The study focuses on forecasting steel microstructure properties, specifically identifying and predicting Pearlite (P) and Bainite (B) microstructures after steel heat treatment, using a CNN approach. This comprehensive workflow leads to robust microstructure classification, achieving a model training accuracy rate of 98.95 %. While its final validation accuracy of 98.8 %, highlighting its capability to generate precise predictions across both classes seamlessly. Valuable insights from confusion matrices highlight the model’s performance in distinguishing between “Bainite” and “Pearlite” microstructures. Additionally, the study underscores the significance of CNNs in metallurgical microstructure analysis, with insightful confusion matrices revealing the model’s capability to differentiate between microstructures. This is useful for innovative microstructure analysis in materials science, emphasizing the transformative potential of AI in enhancing our understanding of processing-microstructure relationships in industrial applications.

DraftFed: A Draft-Based Personalized Federated Learning Approach for Heterogeneous Convolutional Neural Networks

DraftFed: A Draft-Based Personalized Federated Learning Approach for Heterogeneous Convolutional Neural Networks

Development of Face Recognition System Using Support Vector Machine Algorithm

This research paper describes a face recognition system constructed with the Support Vector Machine (SVM) method. The technique implements the Convolutional Neural Network (CNN) approach for extracting features, which improves the accuracy of recognising faces. The method confirms an efficient and accurate facial recognition procedure by utilising SVM's ability to detect complex patterns within retrieved characteristics. The article explores how the system is implemented and optimised performance, with a focus on obtaining performance in real time. The experimental findings demonstrate the practical application of the SVM-based facial recognition system, emphasising its numerous potential applications in security, the authentication process, as well as interaction between humans and computers. The implementation of CNN for extracting features provides refinement to the system, proving its flexibility to complex face characteristics and confirming its feasibility in actual applications. The results indicate that the suggested system is an effective facial recognition technique. Furthermore, the system is computationally efficient, taking just a few seconds to evaluate an individual face for extracting features and recognition. The system for identifying faces uses modern approaches to enhance both speed and precision, making it a potential option for a variety of applications. Its capacity to swiftly and correctly detect faces in real-time circumstances is a substantial development in facial identification technologies. The system's capability has been comprehensively evaluated, and it satisfies the essential criteria for practical implementation in real-world situations, making it an important addition to the continued development of secure and efficient face recognition systems.

Enhancing breast cancer segmentation and classification: An Ensemble Deep Convolutional Neural Network and U-net approach on ultrasound images

Breast cancer is a condition where the irregular growth of breast cells occurs uncontrollably, leading to the formation of tumors. It poses a significant threat to women’s lives globally, emphasizing the need for enhanced methods of detecting and categorizing the disease. In this work, we propose an Ensemble Deep Convolutional Neural Network (EDCNN) model that exhibits superior accuracy compared to several transfer learning models and the Vision Transformer model. Our EDCNN model integrates the strengths of the MobileNet and Xception models to improve its performance in breast cancer detection and classification. We employ various preprocessing techniques, including image resizing, data normalization, and data augmentation, to prepare the data for analysis. By following these measures, the formatting is optimized, and the model’s capacity to make generalizations is improved. We trained and evaluated our proposed EDCNN model using ultrasound images, a widely available modality for breast cancer imaging. The outcomes of our experiments illustrate that the EDCNN model attains an exceptional accuracy of 87.82% on Dataset 1 and 85.69% on Dataset 2, surpassing the performance of several well-known transfer learning models and the Vision Transformer model. Furthermore, an AUC value of 0.91 on Dataset 1 highlights the robustness and effectiveness of our proposed model. Moreover, we highlight the incorporation of the Grad-CAM Explainable Artificial Intelligence (XAI) technique to improve the interpretability and transparency of our proposed model. Additionally, we performed image segmentation using the U-Net segmentation technique on the input ultrasound images. This segmentation process allowed for the identification and isolation of specific regions of interest, facilitating a more comprehensive analysis of breast cancer characteristics. In conclusion, the study presents a creative approach to detecting and categorizing breast cancer, demonstrating the superior performance of the EDCNN model compared to well-established transfer learning models. Through advanced deep learning techniques and image segmentation, this study contributes to improving diagnosis and treatment outcomes in breast cancer.

Development of A Palm-Vein Recognition System for Identification and Verification Systems using Enhanced Convolutional Neural Network

Biometric authentication systems have gained significant attention in access control applications due to their ability to provide enhanced security and convenience. Among various biometric modalities, palm-vein recognition has emerged as a promising approach, offering high accuracy, reliability, and resistance to forgery. However, existing palm-vein recognition systems often face challenges in implementation costs, computational efficiency, and performance limitations. This research aimed to develop an enhanced palm-vein recognition system for access control applications by optimizing a Convolutional Neural Network (CNN) architecture. A palm-vein dataset comprising 1000 images from 200 LAUTECH students was acquired, with 5 images per individual. The dataset was split into 700 training images and 300 testing images. The acquired images were pre-processed for quality enhancement and region of interest extraction. A Gravitational Search Algorithm (GSA) optimized CNN (GSA-CNN) was then employed to extract deep features from the pre-processed images, which were classified using a SoftMax layer. Experimental results revealed that the CNN technique achieved a specificity, sensitivity, False Positive Rate (FPR), accuracy of 74.60%, 79.89%, 25.40%, 77.67% at 117.52 seconds, respectively. In contrast, the proposed GSA-CNN technique demonstrated superior performance, achieving a specificity, sensitivity, FPR, accuracy of 92.06%, 92.53%, 7.94%, 92.33% at 97.14 seconds, respectively. The GSA-CNN system outperformed the conventional CNN approach in terms of accuracy, specificity, sensitivity, FPR, and processing time, demonstrating its potential for reliable and efficient palm-vein recognition in access control applications. The findings have significant implications for developing robust and secure access control systems, contributing to enhanced privacy and security across various domains.

Deep Neural Networks for Multimedia Forensics: Detection of Deepfake Content

Deep Neural Networks for Multimedia Forensics: Detection of Deepfake Content

A novel hybrid deep CNN model for breast cancer classification using Lipschitz-based image augmentation and recursive feature elimination

Breast cancer is the leading cause of death for women worldwide. Despite its difficulties, the histopathological diagnosis must be used because modern imaging techniques cannot differentiate between benign and malignant tumors. This article introduces a hybrid deep learning method with recursive feature elimination for categorizing histopathology images of breast lesions as benign or malignant, using standard datasets, to increase diagnostic accuracy. The proposed four-stage model includes several novel techniques. First, a modified Lipschitz-based image augmentation technique is utilized to ensure a proportionate representation of various sample classes. K-fold cross-validation is employed to mitigate the bias that emerges from the selection of training and testing datasets. Then, for efficient feature extraction, a hybrid convolutional neural network (CNN) approach is used by integrating three CNNs (PResNet-34, FE-VGG-16, and M-AlexNet). With the proposed universum twin support vector machine-based recursive feature elimination technique, the initial 1,000 features extracted by each deep model are further reduced to 100. Finally, the deep features are subsequently combined into a set of 300 features, which are then fed into machine learning classifiers such as decision tree, k-nearest neighborhood, linear discriminant analysis, linear regression, and support vector machine. The results demonstrate that the proposed hybrid CNN model outperforms state-of-the-art techniques in accurately classifying breast lesions as benign or malignant, with an accuracy of 99.99 %, sensitivity of 99.56 %, specificity of 99.53 %, precision of 99.55 %, and F1 score of 99.77 %.