Search results for: deep residual networks

Authors: M. A. Askari, M. A. Nazari, P. Perrier, Y. Payan

Abstract:

Growth and remodeling of biological structures have gained lots of attention over the past decades. Determining the response of living tissues to mechanical loads is necessary for a wide range of developing fields such as prosthetics design or computerassisted surgical interventions. It is a well-known fact that biological structures are never stress-free, even when externally unloaded. The exact origin of these residual stresses is not clear, but theoretically, growth is one of the main sources. Extracting body organ’s shapes from medical imaging does not produce any information regarding the existing residual stresses in that organ. The simplest cause of such stresses is gravity since an organ grows under its influence from birth. Ignoring such residual stresses might cause erroneous results in numerical simulations. Accounting for residual stresses due to tissue growth can improve the accuracy of mechanical analysis results. This paper presents an original computational framework based on gradual growth to determine the residual stresses due to growth. To illustrate the method, we apply it to a finite element model of a healthy human face reconstructed from medical images. The distribution of residual stress in facial tissues is computed, which can overcome the effect of gravity and maintain tissues firmness. Our assumption is that tissue wrinkles caused by aging could be a consequence of decreasing residual stress and thus not counteracting gravity. Taking into account these stresses seems therefore extremely important in maxillofacial surgery. It would indeed help surgeons to estimate tissues changes after surgery.

Keywords: finite element method, growth, residual stress, soft tissue

Procedia PDF Downloads 242

Authors: Xuan Sun, Mingbo Tong

Abstract:

In order to study the effect of hydrothermal environment on the fatigue properties of carbon fiber fabric composites, the experiments on fatigue and residual compressive strength with the center-hole laminates were carried out. For the experiments on fatigue in hydrothermal environment, an environmental chamber used for hydrothermal environment was designed, and the FLUENT was used to simulate the field of temperature in the environmental chamber, it proved that the design met the test requirements. In accordance with ASTM standard, the fatigue test fixture and compression test fixture were designed and produced. Then the tension-compression fatigue tests were carried out in conditions of standard environment (temperature of 23+2℃, relative humidity of 50+/-5%RH) and hydrothermal environment (temperature of 70 +2℃, relative humidity of 85+/-5%RH). After that, the residual compressive strength tests were carried out, respectively. The residual compressive strength after fatigue in condition of standard environment was set as a reference value, compared with the value in condition of hydrothermal environment, calculating the difference between them. According to the result of residual compressive strength tests, it shows that the residual compressive strength after fatigue in condition of hydrothermal environment was decreased by 13.5%,so the hydrothermal environment has little effect on the residual compressive strength of carbon fiber fabric composites laminates after fatigue under load spectrum in this research.

Keywords: carbon fiber, hydrothermal environment, fatigue, residual compressive strength

Procedia PDF Downloads 457

Authors: Jianhong Xiang, Rui Sun, Linyu Wang

Abstract:

In recent years, due to the continuous improvement of deep learning theory, Convolutional Neural Network (CNN) has played a great superior performance in the research of Hyperspectral Image (HSI) classification. Since HSI has rich spatial-spectral information, only utilizing a single dimensional or single size convolutional kernel will limit the detailed feature information received by CNN, which limits the classification accuracy of HSI. In this paper, we design a multi-scale CNN with MLP based on residual and attention modules (INRAM-3DCNN) for the HSI classification task. We propose to use multiple 3D convolutional kernels to extract the packet feature information and fully learn the spatial-spectral features of HSI while designing residual 3D convolutional branches to avoid the decline of classification accuracy due to network degradation. Secondly, we also design the 2D Inception module with a joint channel attention mechanism to quickly extract key spatial feature information at different scales of HSI and reduce the complexity of the 3D model. Due to the high parallel processing capability and nonlinear global action of the Multilayer Perceptron (MLP), we use it in combination with the previous CNN structure for the final classification process. The experimental results on two HSI datasets show that the proposed INRAM-3DCNN method has superior classification performance and can perform the classification task excellently.

Keywords: INRAM-3DCNN, residual, channel attention, hyperspectral image classification

Procedia PDF Downloads 41

Authors: Kimia Khoshdel Vajari, Saber Saffar

Abstract:

Reducing the residual stresses caused by welding is desirable for the industry. The effect of welding sequence, as well as the effect of yield stress on the number of residual stresses generated in Inconel X750 superalloy sheets and beams, have been investigated. The finite element model used in this research is a three-dimensional thermal and mechanical model, and the type of analysis is indirect coupling. This analysis is done in two stages. First, thermal analysis is performed, and then the thermal changes of the first analysis are used as the applied load in the second analysis. ABAQUS has been used for modeling, and the Dflux subroutine has been used in the Fortran programming environment to move the arc and the molten pool. The results of this study show that the amount of tensile residual stress in symmetric, discontinuous, and symmetric-discontinuous welds is reduced to a maximum of 27%, 54%, and 37% compared to direct welding, respectively. The results also show that the amount of residual stresses created by welding increases linearly with increasing yield stress with a slope of 40%.

Keywords: residual stress, X750 superalloy, finite element, welding, thermal analysis

Procedia PDF Downloads 82

Authors: Chaitanya Chawla, Divya Panwar, Gurneesh Singh Anand, M. P. S Bhatia

Abstract:

This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.

Keywords: image forensics, computer graphics, classification, deep learning, convolutional neural networks

Procedia PDF Downloads 304

Authors: Firas Gerges, Frank Y. Shih

Abstract:

Malignant melanoma, known simply as melanoma, is a type of skin cancer that appears as a mole on the skin. It is critical to detect this cancer at an early stage because it can spread across the body and may lead to the patient's death. When detected early, melanoma is curable. In this paper, we propose a deep learning model (convolutional neural networks) in order to automatically classify skin lesion images as malignant or benign. Images underwent certain pre-processing steps to diminish the effect of the normal skin region on the model. The result of the proposed model showed a significant improvement over previous work, achieving an accuracy of 97%.

Keywords: deep learning, skin cancer, image processing, melanoma

Procedia PDF Downloads 114

Authors: Xiang Jia, Zhijun Cheng

Abstract:

The residual lifetime of a product is the operation time between the current time and the time point when the failure happens. The residual lifetime estimation is rather important in reliability analysis. To predict the residual lifetime, it is necessary to assume or verify a particular distribution that the lifetime of the product follows. And the two-parameter Weibull distribution is frequently adopted to describe the lifetime in reliability engineering. Due to the time constraint and cost reduction, a life testing experiment is usually terminated before all the units have failed. Then the censored data is usually collected. In addition, other information could also be obtained for reliability analysis. The expert judgements are considered as it is common that the experts could present some useful information concerning the reliability. Therefore, the residual lifetime is estimated for Weibull distribution by fusing the censored data and expert judgements in this paper. First, the closed-forms concerning the point estimate and confidence interval for the residual lifetime under the Weibull distribution are both presented. Next, the expert judgements are regarded as the prior information and how to determine the prior distribution of Weibull parameters is developed. For completeness, the cases that there is only one, and there are more than two expert judgements are both focused on. Further, the posterior distribution of Weibull parameters is derived. Considering that it is difficult to derive the posterior distribution of residual lifetime, a sample-based method is proposed to generate the posterior samples of Weibull parameters based on the Monte Carlo Markov Chain (MCMC) method. And these samples are used to obtain the Bayes estimation and credible interval for the residual lifetime. Finally, an illustrative example is discussed to show the application. It demonstrates that the proposed method is rather simple, satisfactory, and robust.

Keywords: expert judgements, information fusion, residual lifetime, Weibull distribution

Procedia PDF Downloads 113

Authors: Teja Sai Puligadda

Abstract:

Satellite images in detail can serve an important role in the geographic study. Quantitative and qualitative information provided by the satellite and remote sensing images minimizes the complexity of work and time. Data/images are captured at regular intervals by satellite remote sensing systems, and the amount of data collected is often enormous, and it expands rapidly as technology develops. Interpreting remote sensing images, geographic data mining, and researching distinct vegetation types such as agricultural and forests are all part of satellite image categorization. One of the biggest challenge data scientists faces while classifying satellite images is finding the best suitable classification algorithms based on the available that could able to classify images with utmost accuracy. In order to categorize satellite images, which is difficult due to the sheer volume of data, many academics are turning to deep learning machine algorithms. As, the CNN algorithm gives high accuracy in image recognition problems and automatically detects the important features without any human supervision and the ANN algorithm stores information on the entire network (Abhishek Gupta., 2020), these two deep learning algorithms have been used for satellite image classification. This project focuses on remote sensing through Deep Neural Networks i.e., ANN and CNN with Deep Sat (SAT-4) Airborne dataset for classifying images. Thus, in this project of classifying satellite images, the algorithms ANN and CNN are implemented, evaluated & compared and the performance is analyzed through evaluation metrics such as Accuracy and Loss. Additionally, the Neural Network algorithm which gives the lowest bias and lowest variance in solving multi-class satellite image classification is analyzed.

Keywords: artificial neural network, convolutional neural network, remote sensing, accuracy, loss

Procedia PDF Downloads 126

Authors: Wajid Ali Khan

Abstract:

Extensive experimentation and numerical investigation are performed to predict the machining-induced residual stresses in the end milling of AISI 1045 steel, and an optimization code has been developed using the particle swarm optimization technique. Experiments were conducted using a single factor at a time and design of experiments approach. Regression analysis was done, and a mathematical model of the cutting process was developed, thus predicting the machining-induced residual stress with reasonable accuracy. The mathematical model served as the objective function to be optimized using particle swarm optimization. The relationship between the different cutting parameters and the output variables, force, and residual stresses has been studied. The combined effect of the process parameters, speed, feed, and depth of cut was examined, and it is understood that 85% of the variation of these variables can be attributed to these machining parameters under research. A 3D finite element model is developed to predict the cutting forces and the machining-induced residual stresses in end milling operation. The results were validated experimentally and against the Johnson-cook model available in the literature.

Keywords: residual stresses, end milling, 1045 steel, optimization

Procedia PDF Downloads 83

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 160

Authors: Roshani S. Golhar, Neerajkumar S. Sathawane, Snehal Dongre

Abstract:

Background and objectives: As the, cardiovascular illnesses increasing and becoming cause of mortality worldwide, killing around lot of people each year. Arrhythmia is a type of cardiac illness characterized by a change in the linearity of the heartbeat. The goal of this study is to develop novel deep learning algorithms for successfully interpreting arrhythmia using a single second segment. Because the ECG signal indicates unique electrical heart activity across time, considerable changes between time intervals are detected. Such variances, as well as the limited number of learning data available for each arrhythmia, make standard learning methods difficult, and so impede its exaggeration. Conclusions: The proposed method was able to outperform several state-of-the-art methods. Also proposed technique is an effective and convenient approach to deep learning for heartbeat interpretation, that could be probably used in real-time healthcare monitoring systems

Keywords: electrocardiogram, ECG classification, neural networks, convolutional neural networks, portable document format

Procedia PDF Downloads 45

Authors: Kamal KC, Zhendong Yin, Dasen Li, Zhilu Wu

Abstract:

Intra-plant disease classification based on leaf images is a challenging computer vision task due to similarities in texture, color, and shape of leaves with a slight variation of leaf spot; and external environmental changes such as lighting and background noises. Deep convolutional neural network (DCNN) has proven to be an effective tool for binary classification. In this paper, two methods for binary classification of diseased plant leaves using DCNN are presented; model created from scratch and transfer learning. Our main contribution is a thorough evaluation of 4 networks created from scratch and transfer learning of 5 pre-trained models. Training and testing of these models were performed on a plant leaf images dataset belonging to 16 distinct classes, containing a total of 22,265 images from 8 different plants, consisting of a pair of healthy and diseased leaves. We introduce a deep CNN model, Optimized MobileNet. This model with depthwise separable CNN as a building block attained an average test accuracy of 99.77%. We also present a fine-tuning method by introducing the concept of a convolutional block, which is a collection of different deep neural layers. Fine-tuned models proved to be efficient in terms of accuracy and computational cost. Fine-tuned MobileNet achieved an average test accuracy of 99.89% on 8 pairs of [healthy, diseased] leaf ImageSet.

Keywords: deep convolution neural network, depthwise separable convolution, fine-grained classification, MobileNet, plant disease, transfer learning

Procedia PDF Downloads 157

Authors: Farshid Hajati, Federico Girosi, Shima Ghassempour

Abstract:

We present a Deep Belief Network (DBN) method for clustering health trajectories. Deep Belief Network (DBN) is a deep architecture that consists of a stack of Restricted Boltzmann Machines (RBM). In a deep architecture, each layer learns more complex features than the past layers. The proposed method depends on DBN in clustering without using back propagation learning algorithm. The proposed DBN has a better a performance compared to the deep neural network due the initialization of the connecting weights. We use Contrastive Divergence (CD) method for training the RBMs which increases the performance of the network. The performance of the proposed method is evaluated extensively on the Health and Retirement Study (HRS) database. The University of Michigan Health and Retirement Study (HRS) is a nationally representative longitudinal study that has surveyed more than 27,000 elderly and near-elderly Americans since its inception in 1992. Participants are interviewed every two years and they collect data on physical and mental health, insurance coverage, financial status, family support systems, labor market status, and retirement planning. The dataset is publicly available and we use the RAND HRS version L, which is easy to use and cleaned up version of the data. The size of sample data set is 268 and the length of the trajectories is equal to 10. The trajectories do not stop when the patient dies and represent 10 different interviews of live patients. Compared to the state-of-the-art benchmarks, the experimental results show the effectiveness and superiority of the proposed method in clustering health trajectories.

Keywords: health trajectory, clustering, deep learning, DBN

Procedia PDF Downloads 342

Authors: Yong Zhao, Jian He, Cheng Zhang

Abstract:

Cardiovascular diseases caused by hypertension are extremely threatening to human health, and early diagnosis of hypertension can save a large number of lives. Traditional hypertension detection methods require special equipment and are difficult to detect continuous blood pressure changes. In this regard, this paper first analyzes the principle of heart rate variability (HRV) and introduces sliding window and power spectral density (PSD) to analyze the time domain features and frequency domain features of HRV, and secondly, designs an HRV-based hypertension prediction network by combining Resnet, attention mechanism, and multilayer perceptron, which extracts the frequency domain through the improved ResNet18 features through a modified ResNet18, its fusion with time-domain features through an attention mechanism, and the auxiliary prediction of hypertension through a multilayer perceptron. Finally, the network was trained and tested using the publicly available SHAREE dataset on PhysioNet, and the test results showed that this network achieved 92.06% prediction accuracy for hypertension and outperformed K Near Neighbor(KNN), Bayes, Logistic, and traditional Convolutional Neural Network(CNN) models in prediction performance.

Keywords: feature extraction, heart rate variability, hypertension, residual networks

Procedia PDF Downloads 67

Authors: Malik Muhammad Arslan, Muneeb Ullah, Dai Shihan, Daniyal Haider, Xiaodong Yang

Abstract:

Chest X-rays are instrumental in the detection and monitoring of a wide array of diseases, including viral infections such as COVID-19, tuberculosis, pneumonia, lung cancer, and various cardiac and pulmonary conditions. To enhance the accuracy of diagnosis, artificial intelligence (AI) algorithms, particularly deep learning models like Convolutional Neural Networks (CNNs), are employed. However, these deep learning models demand a substantial and varied dataset to attain optimal precision. Generative Adversarial Networks (GANs) can be employed to create new data, thereby supplementing the existing dataset and enhancing the accuracy of deep learning models. Nevertheless, GANs have their limitations, such as issues related to stability, convergence, and the ability to distinguish between authentic and fabricated data. In order to overcome these challenges and advance the detection and classification of CXR normal and abnormal images, this study introduces a distinctive technique known as DCWGAN (Diverse Conditional Wasserstein GAN) for generating synthetic chest X-ray (CXR) images. The study evaluates the effectiveness of this Idiosyncratic DCWGAN technique using the ResNet50 model and compares its results with those obtained using the traditional GAN approach. The findings reveal that the ResNet50 model trained on the DCWGAN-generated dataset outperformed the model trained on the classic GAN-generated dataset. Specifically, the ResNet50 model utilizing DCWGAN synthetic images achieved impressive performance metrics with an accuracy of 0.961, precision of 0.955, recall of 0.970, and F1-Measure of 0.963. These results indicate the promising potential for the early detection of diseases in CXR images using this Inimitable approach.

Keywords: CNN, classification, deep learning, GAN, Resnet50

Procedia PDF Downloads 47

Authors: Kazeem Adesina Dauda, Waheed Babatunde Yahya

Abstract:

To design a tree that maximizes within-node homogeneity, there is a need for a homogeneity measure that is appropriate for event history data with multiple risks. We consider the use of Deviance and Modified Cox-Snell residuals as a measure of impurity in Classification Regression Tree (CART) and compare our results with the results of Fiona (2008) in which homogeneity measures were based on Martingale Residual. Data structure approach was used to validate the performance of our proposed techniques via simulation and real life data. The results of univariate competing risk revealed that: using Deviance and Cox-Snell residuals as a response in within node homogeneity classification tree perform better than using other residuals irrespective of performance techniques. Bone marrow transplant data and double-blinded randomized clinical trial, conducted in other to compare two treatments for patients with prostate cancer were used to demonstrate the efficiency of our proposed method vis-à-vis the existing ones. Results from empirical studies of the bone marrow transplant data showed that the proposed model with Cox-Snell residual (Deviance=16.6498) performs better than both the Martingale residual (deviance=160.3592) and Deviance residual (Deviance=556.8822) in both event of interest and competing risks. Additionally, results from prostate cancer also reveal the performance of proposed model over the existing one in both causes, interestingly, Cox-Snell residual (MSE=0.01783563) outfit both the Martingale residual (MSE=0.1853148) and Deviance residual (MSE=0.8043366). Moreover, these results validate those obtained from the Monte-Carlo studies.

Keywords: within-node homogeneity, Martingale residual, modified Cox-Snell residual, classification and regression tree

Procedia PDF Downloads 242

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 60

Authors: Belkacem Chebil Sonia, Bensalem Wacef

Abstract:

The majority of ball end milling models includes only the influence of cutting parameters (cutting speed, feed rate, depth of cut). Furthermore, this influence is studied in most of works on cutting force. Therefore, this study proposes an accurate ball end milling process modeling which includes also the influence of tool workpiece inclination. In addition, a characterization of residual stresses resulting of thermo mechanical loading in the workpiece was also presented. Moreover, the study of the influence of tool workpiece inclination and cutting parameters was made on residual stresses distribution. In order to achieve the predetermination of cutting forces and residual stresses during a milling operation, a thermo mechanical three-dimensional numerical model of ball end milling was developed. Furthermore, an experimental companion of ball end milling tests was realized on a 5-axis machining center to determine the cutting forces and characterize the residual stresses. The simulation results are compared with the experiment to validate the Finite Element Model and subsequently identify the optimum inclination angle and cutting parameters.

Keywords: ball end milling, cutting forces, cutting parameters, residual stress, tool-workpiece inclination

Procedia PDF Downloads 279

Authors: Harold Mauricio Díaz-Vargas, Cristian Alfonso Jimenez-Castaño, David Augusto Cárdenas-Peña, Guillermo Alberto Ortiz-Gómez, Alvaro Angel Orozco-Gutierrez

Abstract:

Precise identification of the nerves is a crucial task performed by anesthesiologists for an effective Peripheral Nerve Blocking (PNB). Now, anesthesiologists use ultrasound imaging equipment to guide the PNB and detect nervous structures. However, visual identification of the nerves from ultrasound images is difficult, even for trained specialists, due to artifacts and low contrast. The recent advances in deep learning make neural networks a potential tool for accurate nerve segmentation systems, so addressing the above issues from raw data. The most widely spread U-Net network yields pixel-by-pixel segmentation by encoding the input image and decoding the attained feature vector into a semantic image. This work proposes a conditioning approach and encoder pre-training to enhance the nerve segmentation of traditional U-Nets. Conditioning is achieved by the one-hot encoding of the kind of target nerve a the network input, while the pre-training considers five well-known deep networks for image classification. The proposed approach is tested in a collection of 619 US images, where the best C-UNet architecture yields an 81% Dice coefficient, outperforming the 74% of the best traditional U-Net. Results prove that pre-trained models with the conditional approach outperform their equivalent baseline by supporting learning new features and enriching the discriminant capability of the tested networks.

Keywords: nerve segmentation, U-Net, deep learning, ultrasound imaging, peripheral nerve blocking

Procedia PDF Downloads 77

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 69

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 88

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 121

Authors: Khairani Binti Supyan, Fatimah Khalid, Mas Rina Mustaffa, Azreen Bin Azman, Amirul Azuani Romle

Abstract:

Perennial plant classification plays a significant role in various agricultural and environmental applications, assisting in plant identification, disease detection, and biodiversity monitoring. Nevertheless, attaining high accuracy in perennial plant image classification remains challenging due to the complex variations in plant appearance, the diverse range of environmental conditions under which images are captured, and the inherent variability in image quality stemming from various factors such as lighting conditions, camera settings, and focus. This paper proposes an adaptation approach to optimize perennial plant image classification by fine-tuning the pre-trained DNNs model. This paper explores the efficacy of fine-tuning prevalent architectures, namely VGG16, ResNet50, and InceptionV3, leveraging transfer learning to tailor the models to the specific characteristics of perennial plant datasets. A subset of the MYLPHerbs dataset consisted of 6 perennial plant species of 13481 images under various environmental conditions that were used in the experiments. Different strategies for fine-tuning, including adjusting learning rates, training set sizes, data augmentation, and architectural modifications, were investigated. The experimental outcomes underscore the effectiveness of fine-tuning deep neural networks for perennial plant image classification, with ResNet50 showcasing the highest accuracy of 99.78%. Despite ResNet50's superior performance, both VGG16 and InceptionV3 achieved commendable accuracy of 99.67% and 99.37%, respectively. The overall outcomes reaffirm the robustness of the fine-tuning approach across different deep neural network architectures, offering insights into strategies for optimizing model performance in the domain of perennial plant image classification.

Keywords: perennial plants, image classification, deep neural networks, fine-tuning, transfer learning, VGG16, ResNet50, InceptionV3

Procedia PDF Downloads 25

Authors: Paulo Cesar Pereira Junior, Alexandre Monteiro, Rafael da Luz Ribeiro, Antonio Carlos Sobieranski, Aldo von Wangenheim

Abstract:

In this paper, we present a comparison between convolutional neural networks and classical computer vision approaches, for the specific precision agriculture problem of weed mapping on sugarcane fields aerial images. A systematic literature review was conducted to find which computer vision methods are being used on this specific problem. The most cited methods were implemented, as well as four models of convolutional neural networks. All implemented approaches were tested using the same dataset, and their results were quantitatively and qualitatively analyzed. The obtained results were compared to a human expert made ground truth for validation. The results indicate that the convolutional neural networks present better precision and generalize better than the classical models.

Keywords: convolutional neural networks, deep learning, digital image processing, precision agriculture, semantic segmentation, unmanned aerial vehicles

Procedia PDF Downloads 219

Authors: Mohammed Abed, Rita Nemes, Salem Nehme

Abstract:

The present study experimentally investigated the impact of incorporating unprocessed waste fly ash (UWFA) on the residual mechanical properties of self-compacting concrete (SCC) after exposure to elevated temperature. Three mixtures of SCC have been produced by replacing the cement mass by 0%, 15% and 30% of UWFA. Generally, the fire resistance of SCC has been enhanced by replacing the cement up to 15% of UWFA, especially in case of residual modulus of elasticity which considers more sensitive than other mechanical properties at elevated temperature. However, a strong linear relationship has been observed between the residual flexural strength and modulus of elasticity, where both of them affected significantly by the cracks appearance and propagation as a result of elevated temperature. Sustainable products could be produced by incorporating unprocessed waste powder materials in the production of concrete, where the waste materials, CO₂ emissions, and the energy needed for processing are reduced.

Keywords: self-compacting high-performance concrete, unprocessed waste fly ash, fire resistance, residual modulus of elasticity

Procedia PDF Downloads 112

Authors: Jainendra Singh, Zaheeruddin

Abstract:

A typical wireless sensor networks (WSNs) consists of several tiny and low-power sensors which use radio frequency to perform distributed sensing tasks. The longevity of wireless sensor networks (WSNs) is a major issue that impacts the application of such networks. While routing protocols are striving to save energy by acting on sensor nodes, recent studies show that network lifetime can be enhanced by further involving sink mobility. A common approach for energy efficiency is partitioning the network into clusters with correlated data, where the representative nodes simply transmit or average measurements inside the cluster. In this paper, we propose an energy- efficient homogenous clustering (EHC) technique. In this technique, the decision of each sensor is based on their residual energy and an estimate of how many of its neighboring cluster heads (CHs) will benefit from it being a CH. We, also explore the routing algorithm in clustered WSNs. We show that the proposed schemes significantly outperform current approaches in terms of packet delay, hop count and energy consumption of WSNs.

Keywords: wireless sensor network, energy efficiency, clustering, routing

Procedia PDF Downloads 237

Authors: Yu-Ting Tsai, Chiun-Chieh Hsu, Yu-Chun Chu

Abstract:

In recent years, due to the development of wireless network technology, many researchers have devoted to the study of wireless sensor networks. The applications of wireless sensor network mainly use the sensor nodes to collect the required information, and send the information back to the users. Since the sensed area is difficult to reach, there are many restrictions on the design of the sensor nodes, where the most important restriction is the limited energy of sensor nodes. Because of the limited energy, researchers proposed a number of ways to reduce energy consumption and balance the load of sensor nodes in order to increase the network lifetime. In this paper, we proposed the Energy-Balanced Clustering method with Auxiliary Members on Wireless Sensor Networks（EBCAM）based on the cluster routing. The main purpose is to balance the energy consumption on the sensed area and average the distribution of dead nodes in order to avoid excessive energy consumption because of the increasing in transmission distance. In addition, we use the residual energy and average energy consumption of the nodes within the cluster to choose the cluster heads, use the multi hop transmission method to deliver the data, and dynamically adjust the transmission radius according to the load conditions. Finally, we use the auxiliary cluster members to change the delivering path according to the residual energy of the cluster head in order to its load. Finally, we compare the proposed method with the related algorithms via simulated experiments and then analyze the results. It reveals that the proposed method outperforms other algorithms in the numbers of used rounds and the average energy consumption.

Keywords: auxiliary nodes, cluster, load balance, routing algorithm, wireless sensor network

Procedia PDF Downloads 253

Authors: Qian Zhu, Shidong Nie, Bo Yang, Gang Xiong, Guoxin Dai

Abstract:

GJ steel is a new type of high-performance structural steel which has been increasingly adopted in practical engineering. Q460GJ structural steel has a nominal yield strength of 460 MPa, which does not decrease significantly with the increase of steel plate thickness like normal structural steel. Thus, Q460GJ structural steel is normally used in medium-walled welded sections. However, research works on the residual stress in GJ steel members are few though it is one of the vital factors that can affect the member and structural behavior. This article aims to investigate the residual stresses in welded I-shaped sections fabricated from Q460GJ structural steel plates by experimental tests. A total of four full scale welded medium-walled I-shaped sections were tested by sectioning method. Both circular curve correction method and straightening measurement method were adopted in this study to obtain the final magnitude and distribution of the longitudinal residual stresses. In addition, this paper also explores the interaction between flanges and webs. And based on the statistical evaluation of the experimental data, a multilayer residual stress model is proposed.

Keywords: Q460GJ structural steel, residual stresses, sectioning method, welded medium-walled I-shaped sections

Procedia PDF Downloads 289

Authors: Yahia. Kourd, N. Guersi D. Lefebvre

Abstract:

In this paper we propose to study the faults diagnosis in squirrel-cage induction motor using MLP neural networks. We use neural healthy and faulty models of the behavior in order to detect and isolate some faults in machine. In the first part of this work, we have created a neural model for the healthy state using Matlab and a motor located in LGEB by acquirins data inputs and outputs of this engine. Then we detected the faults in the machine by residual generation. These residuals are not sufficient to isolate the existing faults. For this reason, we proposed additive neural networks to represent the faulty behaviors. From the analysis of these residuals and the choice of a threshold we propose a method capable of performing the detection and diagnosis of some faults in asynchronous machines with squirrel cage rotor.

Keywords: faults diagnosis, neural networks, multi-models, squirrel-cage induction motor

Procedia PDF Downloads 603

Authors: Nubwimana Rachel, Mugabowindekwe Maurice

Abstract:

Trees play a crucial role in maintaining biodiversity and providing various ecological services. Traditional methods of counting trees are time-consuming, and there is a need for more efficient techniques. However, deep learning makes it feasible to identify the multi-scale elements hidden in aerial imagery. This research focuses on the application of deep learning techniques for tree detection and counting in both forest and non-forest areas through the exploration of the deep learning application for automated tree detection and counting using satellite imagery. The objective is to identify the most effective model for automated tree counting. We used different deep learning models such as YOLOV7, SSD, and UNET, along with Generative Adversarial Networks to generate synthetic samples for training and other augmentation techniques, including Random Resized Crop, AutoAugment, and Linear Contrast Enhancement. These models were trained and fine-tuned using satellite imagery to identify and count trees. The performance of the models was assessed through multiple trials; after training and fine-tuning the models, UNET demonstrated the best performance with a validation loss of 0.1211, validation accuracy of 0.9509, and validation precision of 0.9799. This research showcases the success of deep learning in accurate tree counting through remote sensing, particularly with the UNET model. It represents a significant contribution to the field by offering an efficient and precise alternative to conventional tree-counting methods.

Keywords: remote sensing, deep learning, tree counting, image segmentation, object detection, visualization

Procedia PDF Downloads 29