Number Of Epochs Research Articles

Deep learning-based prediction of major arrhythmic events in dilated cardiomyopathy: A proof of concept study.

Prediction of major arrhythmic events (MAEs) in dilated cardiomyopathy represents an unmet clinical goal. Computational models and artificial intelligence (AI) are new technological tools that could offer a significant improvement in our ability to predict MAEs. In this proof-of-concept study, we propose a deep learning (DL)-based model, which we termed Deep ARrhythmic Prevention in dilated cardiomyopathy (DARP-D), built using multidimensional cardiac magnetic resonance data (cine videos and hypervideos and LGE images and hyperimages) and clinical covariates, aimed at predicting and tracking an individual patient's risk curve of MAEs (including sudden cardiac death, cardiac arrest due to ventricular fibrillation, sustained ventricular tachycardia lasting ≥30 s or causing haemodynamic collapse in <30 s, appropriate implantable cardiac defibrillator intervention) over time. The model was trained and validated in 70% of a sample of 154 patients with dilated cardiomyopathy and tested in the remaining 30%. DARP-D achieved a 95% CI in Harrell's C concordance indices of 0.12-0.68 on the test set. We demonstrate that our DL approach is feasible and represents a novelty in the field of arrhythmic risk prediction in dilated cardiomyopathy, able to analyze cardiac motion, tissue characteristics, and baseline covariates to predict an individual patient's risk curve of major arrhythmic events. However, the low number of patients, MAEs and epoch of training make the model a promising prototype but not ready for clinical usage. Further research is needed to improve, stabilize and validate the performance of the DARP-D to convert it from an AI experiment to a daily used tool.

Analyzing and Improving Existing Neural Network-Based Approaches to Identify AI Generated Images

Images produced by AI software, particularly human faces, have the potential to spread misinformation, thus detection tools are essential to tell facts from fiction. However, current neural network-based tools misclassify images with extreme photography conditions, facial obstructions, or post-processing. This project aimed to address the limitations of existing detection models, especially regarding poorly-photographed or edited images. A MobileNet-v2-based neural network to identify synthetic images was analyzed for possible shortcomings. After obtaining its baseline accuracy, it was stress tested on validation data with brightness, contrast, hue, and saturation edited by set increments. The model performed poorly on processed images and faces with glasses or shadows. Possible limitations were insufficient data augmentation, the Global Average Pooling Layer, too few epochs trained, and inadequate regularization strength or dropout rate. The model was then modified to address these shortcomings by altering the brightness, contrast, hue, and saturation of training data, adding Gaussian noise to training images, implementing a Global Max Pooling Layer, augmenting the number of epochs trained, and changing the regularization strength and dropout rate. The modified model was evaluated on augmented and non-augmented images. Overall, the model improved when Gaussian noise was added with standard deviation 0.1, it was trained for 15 epochs, and there were no dropout layers. This was because the Gaussian noise layer approximated degraded image quality, and the model was too simple to learn image features when trained for fewer epochs or when neurons were disabled. This research could be expanded by testing multiple modifications at once.

Synthetic Brain Images: Bridging the Gap in Brain Mapping With Generative Adversarial Model

Magnetic Resonance Imaging (MRI) is a vital modality for gaining precise anatomical information, and it plays a significant role in medical imaging for diagnosis and therapy planning. Image synthesis problems have seen a revolution in recent years due to the introduction of deep learning techniques, specifically Generative Adversarial Networks (GANs). This work investigates the use of Deep Convolutional Generative Adversarial Networks (DCGAN) for producing high-fidelity and realistic MRI image slices. The suggested approach uses a dataset with a variety of brain MRI scans to train a DCGAN architecture. While the discriminator network discerns between created and real slices, the generator network learns to synthesise realistic MRI image slices. The generator refines its capacity to generate slices that closely mimic real MRI data through an adversarial training approach. The outcomes demonstrate that the DCGAN promise for a range of uses in medical imaging research, since they show that it can effectively produce MRI image slices if we train them for a consequent number of epochs. This work adds to the expanding corpus of research on the application of deep learning techniques for medical image synthesis. The slices that are could be produced possess the capability to enhance datasets, provide data augmentation in the training of deep learning models, as well as a number of functions are made available to make MRI data cleaning easier, and a three ready to use and clean dataset on the major anatomical plans.

Comparative Analysis of Deep Learning Models for Olive Detection on the Branch

The future of deep learning integration in agriculture holds great potential for advancing sustainable agricultural practices, precision agriculture and improved decision-making. With the rapid development of image processing and artificial intelligence technologies in recent years, deep learning has begun to play a major role in identifying agricultural pests and optimizing agricultural product marketing. However, there are challenges related to data quality, model scalability, and geographical limitations for widespread adoption of deep learning in agriculture. This study on Olive was conducted to improve the quality of the data set and to ensure more reliable training of object detection models. According to the result of the training process of YOLOv7 used in the study, it was concluded that it was characterized by decreasing loss values and showed an increase in the model's ability to detect objects correctly. It was observed that the other model, YOLOv8l, had a more effective learning capacity and a tendency to learn faster. The performance of both models was evaluated with various metrics, and it was determined that YOLOv8l had higher Precision, Recall, and mAP values. It was emphasized that YOLOv8l showed high performance even in low epoch numbers and can be preferred especially in cases where time and computational resources were limited. It was determined that YOLOv7 made detections in a wide confidence range, but had difficulty in detections with low confidence scores. It was observed that YOLOv8l made more stable and reliable detections with higher confidence scores. The metric data of the "YOLOv8l" model was found to be higher compared to other models. The F1 score of the YOLOv5l model was 92.337%, precision 96.568%, recall %88,462,mAP@0.5:0.65 value gave the highest score with 94.608%. This research on deep learning-based object detection models indicated that YOLOv8l showed superior performance compared to YOLOv7 and was a more reliable option for agricultural applications.

A comparison of deep transfer learning backbone architecture techniques for printed text detection of different font styles from unstructured documents.

Object detection methods based on deep learning have been used in a variety of sectors including banking, healthcare, e-governance, and academia. In recent years, there has been a lot of attention paid to research endeavors made towards text detection and recognition from different scenesor images of unstructured document processing. The article's novelty lies in the detailed discussion and implementation of the various transfer learning-based different backbone architectures for printed text recognition. In this research article, the authors compared the ResNet50, ResNet50V2, ResNet152V2, Inception, Xception, and VGG19 backbone architectures with preprocessing techniques as data resizing, normalization, and noise removal on a standard OCR Kaggle dataset. Further, the top three backbone architectures selected based on the accuracy achieved and then hyper parameter tunning has been performed to achieve more accurate results. Xception performed well compared with the ResNet, Inception, VGG19, MobileNet architectures by achieving high evaluation scores with accuracy (98.90%) and min loss (0.19). As per existing research in this domain, until now, transfer learning-based backbone architectures that have been used on printed or handwritten data recognition are not well represented in literature. We split the total dataset into 80 percent for training and 20 percent for testing purpose and then into different backbone architecture models with the same number of epochs, and found that the Xception architecture achieved higher accuracy than the others. In addition, the ResNet50V2 model gave us higher accuracy (96.92%) than the ResNet152V2 model (96.34%).

CNN-based image style transformation--Using VGG19

eural Style Transfer is a widely used approach in the field of computer vision, which aims to generate visual effects by integrating the information contained in one image into another. In this paper, this work presents an implementation of neural style transfer using TensorFlow and the VGG19 model. The proposed method involves loading and preprocessing the content and style images, extracting features from both images using the VGG19 model, and computing Gram matrices to capture the style information. A StyleContentModel class is introduced to encapsulate the style and content extraction process. The optimization process is performed using the Adam optimizer, where gradients are applied to iteratively update the generated image. The number of epochs and steps per epoch can be adjusted to control the optimization process and achieve desired results. Experiments show that we are effective in generating an image that is able to integrate the content of one image into the other. The generated images exhibit visually appealing characteristics and showcase the potential of neural style transfer as a creative tool in image synthesis. Future work may involve exploring different variations of the style transfer algorithm, optimizing hyperparameters, and evaluating the performance on a wider range of image datasets. Additionally, the integration of other deep learning architectures and techniques could further enhance the capabilities of neural style transfer.

Low-Cost Training of Image-to-Image Diffusion Models with Incremental Learning and Task/Domain Adaptation

Diffusion models specialized in image-to-image translation tasks, like inpainting and colorization, have outperformed the state of the art, yet their computational requirements are exceptionally demanding. This study analyzes different strategies to train image-to-image diffusion models in a low-resource setting. The studied strategies include incremental learning and task/domain transfer learning. First, a base model for human face inpainting is trained from scratch with an incremental learning strategy. The resulting model achieves an FID score almost equivalent to that of its batch learning equivalent while significantly reducing the training time. Second, the base model is fine-tuned to perform a different task, image colorization, and, in a different domain, landscape images. The resulting colorization models showcase exceptional performances with a minimal number of training epochs. We examine the impact of different configurations and provide insights into the ability of image-to-image diffusion models for transfer learning across tasks and domains.

Evaluation of the astrometric capability of Multi-Channel Imager and simulated calculation of proper motion of M31

Introduction: The Multi-Channel Imager (MCI), one of the back-end modules of the future China Space Station Telescope (CSST), is designed for high-precision spacebased astronomical observations. This paper evaluates the astrometric capability of the MCI based on simulated observational images and Gaia data: the M31 galaxy is selected as a representative case to validate the astrometric capability by calculating the proper motions (PMs) of the M31 member stars.Method: We analyze the stellar centroids of the simulated images in the R, I and G bands, positional uncertainty of 2.5 mas for brighter foreground reference stars from the Gaia DR3 catalog and of 7.5 mas for the fainter M31 member stars, are adopted respectively. The theoretical PMs are generated from the adopted velocity field model, rotation curve, and stellar surface density profile. And the simulated observed PMs are generated from the aforementioned position uncertainties and theoretical PMs.Result: We conclude that the precision of the MCI derived PMs strongly depends on the number of astrometric epochs per year. Specifically, uncertainty of 10 μas/yr is achievable with 10 epochs per year, and of 5 μas/yr with 50 epochs ignoring possible systematic effects. And symmetrically distributed observed fields yield better M31 kinematic parameters.Discussion: Unknown systematic errors, space environment effects on detectors, dithering strategies, and observation schedules can affect the PMs of M31, the above issues need further analysis and validation in future work.

Recognition of Daily Activities in Adults With Wearable Inertial Sensors: Deep Learning Methods Study.

Activities of daily living (ADL) are essential for independence and personal well-being, reflecting an individual's functional status. Impairment in executing these tasks can limit autonomy and negatively affect quality of life. The assessment of physical function during ADL is crucial for the prevention and rehabilitation of movement limitations. Still, its traditional evaluation based on subjective observation has limitations in precision and objectivity. The primary objective of this study is to use innovative technology, specifically wearable inertial sensors combined with artificial intelligence techniques, to objectively and accurately evaluate human performance in ADL. It is proposed to overcome the limitations of traditional methods by implementing systems that allow dynamic and noninvasive monitoring of movements during daily activities. The approach seeks to provide an effective tool for the early detection of dysfunctions and the personalization of treatment and rehabilitation plans, thus promoting an improvement in the quality of life of individuals. To monitor movements, wearable inertial sensors were developed, which include accelerometers and triaxial gyroscopes. The developed sensors were used to create a proprietary database with 6 movements related to the shoulder and 3 related to the back. We registered 53,165 activity records in the database (consisting of accelerometer and gyroscope measurements), which were reduced to 52,600 after processing to remove null or abnormal values. Finally, 4 deep learning (DL) models were created by combining various processing layers to explore different approaches in ADL recognition. The results revealed high performance of the 4 proposed models, with levels of accuracy, precision, recall, and F1-score ranging between 95% and 97% for all classes and an average loss of 0.10. These results indicate the great capacity of the models to accurately identify a variety of activities, with a good balance between precision and recall. Both the convolutional and bidirectional approaches achieved slightly superior results, although the bidirectional model reached convergence in a smaller number of epochs. The DL models implemented have demonstrated solid performance, indicating an effective ability to identify and classify various daily activities related to the shoulder and lumbar region. These results were achieved with minimal sensorization-being noninvasive and practically imperceptible to the user-which does not affect their daily routine and promotes acceptance and adherence to continuous monitoring, thus improving the reliability of the data collected. This research has the potential to have a significant impact on the clinical evaluation and rehabilitation of patients with movement limitations, by providing an objective and advanced tool to detect key movement patterns and joint dysfunctions.

The Implementation of a Deep Neural Network (DNN) Approach in a Case Study Predicting the Distribution of Carbon Dioxide (CO2) Gas Saturation

Predicting the distribution of CO2 gas saturation is one example of how multiphase flow might be evaluated in Carbon Capture and Storage (CCS). The TOUGH2 simulator is one of the numerical simulations commonly used for multiphase flow simulation. Ordinary numerical simulations have several issues, including high grid spatial resolution and high processing costs. One of the most effective deep learning approaches to predicting the distribution of CO2 gas saturation is the deep neural network (DNN). A deep neural network is a network with three interconnected layers, there are input, hidden, and output layers. DNN learns about the previously constructed architecture from the input data. DNN requires a large quantity of data as input. Thus, in this study, we use 700 data points for each of the train_a and train_b variables. The distribution of CO2 gas saturation will be predicted automatically by the trained DNN model. This technique can handle complex data patterns, such as gas saturation in multiphase flow problems. The reconstruction loss findings show that the loss value decreases as the number of epochs increases. Furthermore, we used 3 and 4 epochs to determine the difference in results between the two. As a result, the model with 4 epochs and 10−3 regularization weight obtained the lowest error value of 0.4305. In summary, this model is capable of predicting CO2 gas saturation distribution, but more research is needed to produce more optimal results. This research hopes to help monitor multiphase flow in CCS systems in the future by forecasting the distribution of CO2 gas saturation.

Time-Sensitive Learning for Heterogeneous Federated Edge Intelligence

Real-time machine learning (ML) has recently attracted significant interest due to its potential to support instantaneous learning, adaptation, and decision making in a wide range of application domains, including self-driving vehicles, intelligent transportation, and industry automation. In this paper, we investigate real-time ML in a federated edge intelligence (FEI) system, an edge computing system that implements federated learning (FL) solutions based on data samples collected and uploaded from decentralized data networks, e.g., Internet-of-Things (IoT) and/or wireless sensor networks. FEI systems often exhibit heterogenous communication and computational resource distribution, as well as non-i.i.d. data samples arrived at different edge servers, resulting in long model training time and inefficient resource utilization. Motivated by this fact, we propose a time-sensitive federated learning (TS-FL) framework to minimize the overall run-time for collaboratively training a shared ML model with desirable accuracy. Training acceleration solutions for both TS-FL with synchronous coordination (TS-FL-SC) and asynchronous coordination (TS-FL-ASC) are investigated. To address the straggler effect in TS-FL-SC, we develop an analytical solution to characterize the impact of selecting different subsets of edge servers on the overall model training time. A server dropping-based solution is proposed to allow some slow-performance edge servers to be removed from participating in the model training if their impact on the resulting model accuracy is limited. A joint optimization algorithm is proposed to minimize the overall time consumption of model training by selecting participating edge servers, the local epoch number (the number of model training iterations per coordination), and the data batch size (the number of data samples for each model training iteration). Motivated by the fact that data samples at the slowest edge server may exhibit special characteristics that cannot be removed from model training, we develop an analytical expression to characterize the impact of both staleness effect of asynchronous coordination and straggler effect of FL on the time consumption of TS-FL-ASC. We propose a load forwarding-based solution that allows a slow edge server to offload part of its training samples to trusted edge servers with higher processing capability. We develop a hardware prototype to evaluate the model training time of a heterogeneous FEI system. Experimental results show that our proposed TS-FL-SC and TS-FL-ASC can provide up to 63% and 28% of reduction, in the overall model training time, respectively, compared with traditional FL solutions.

Survey of image classification models for transfer learning

Training models for image classification is a very time-consuming task. It has always been a challenge for researchers and practitioners to train a model partly because of the large dataset required, which is complex and sometimes almost impossible to source. This has recently led to the use of pre-trained models for image classifications. Pre-trained models have gained popularity because they initialize the model with appropriate weight and significantly reduce the training time and dataset required. There are many image classification pre-trained models in use today, and this paper will focus on investigating the performance of the ten top models (ConvNext, DenseNet, EfficientNet, InceptionResNet, Inception, mobileNet, ResNet, VGG, Xception, NasNet) using caltech101 dataset containing 101 object classes and caltech256 dataset containing 256 object classes. The models are all trained on the ImageNet-1k dataset. Tensorflow and Keras were used as the frameworks for developing the experiments. The accuracy, precision, recall, and f1-score were used as metrics for model performance evaluation. The findings and analysis underscore the significance of training time, number of epochs, and choice of model in image classification.

NN‐mCRE: A modified constitutive relation error framework for unsupervised learning of nonlinear state laws with physics‐augmented neural networks

AbstractThis article proposes a new approach to train physics‐augmented neural networks with observable data to represent mechanical constitutive laws. To train the neural network and learn thermodynamics potentials, the proposed method does not rely on strain‐stress or strain‐free energy pairs but needs only partial strain or displacement measurements inside the structure. The neural network is trained thanks to an unsupervised procedure in which the modified constitutive relation error (mCRE) is minimized. The mCRE functional provides a bias‐aware data assimilation framework with a rich physical sense as the constitutive relation error (CRE) part can be interpreted as a modeling error continuously defined over the structure, and can be used as a prediction quality in the inference phase. This article also extends previous works on the mCRE by introducing a new minimization procedure in the case of nonlinear state laws. As typical structural health monitoring applications may require that the neural networks should be trained online, an important focus is thus made on automatic and adaptive tuning of sensitive hyperparameters (learning rate, weighting between losses, number of epochs and initialization). It is shown that when the training database is rich enough with respect to the loading cases, the proposed method achieves remarkable performance regarding the quality of the learned model, noise robustness, and low sensitivity to user‐defined hyperparameters. The method is evaluated on two test cases: a non‐quadratic potential in the small strain regime with synthetic optic fiber measurements, and a Mooney–Rivlin model in the hyperelastic case with synthetic digital image correlation observations.

AMDDLmodel: Android smartphones malware detection using deep learning model.

Android is the most popular operating system of the latest mobile smart devices. With this operating system, many Android applications have been developed and become an essential part of our daily lives. Unfortunately, different kinds of Android malware have also been generated with these applications' endless stream and somehow installed during the API calls, permission granted and extra packages installation and badly affected the system security rules to harm the system. Therefore, it is compulsory to detect and classify the android malware to save the user's privacy to avoid maximum damages. Many research has already been developed on the different techniques related to android malware detection and classification. In this work, we present AMDDLmodel a deep learning technique that consists of a convolutional neural network. This model works based on different parameters, filter sizes, number of epochs, learning rates, and layers to detect and classify the android malware. The Drebin dataset consisting of 215 features was used for this model evaluation. The model shows an accuracy value of 99.92%. The other statistical values are precision, recall, and F1-score. AMDDLmodel introduces innovative deep learning for Android malware detection, enhancing accuracy and practical user security through inventive feature engineering and comprehensive performance evaluation. The AMDDLmodel shows the highest accuracy values as compared to the existing techniques.

FACE DETECTION AND RECOGNITION USING GOOGLE-NET ARCHITECTURE

Using face detection to secure places is an important application merging with machine vision. This paper reposed a system to do face detection and recognition using existing architecture google-net and transfer learning to let the network learn images based on pre-trained architecture, The design of a network leads to an architecture that leads to maximizing the accuracy of the system and accurately detecting faces that are saved to the database and specifying the effect of weights used within the nodes of the hidden layer which consider the most time-consuming task within the architecture. The main characteristics are explained and the architecture used as well as the used data set in detail with the design of a network which provides an architecture that leads to maximizing the accuracy of the system and accurately detecting faces that are saved to the database and specifying the effect of weights used within the nodes of the hidden layer which consider the most time-consuming task within the architecture. Experimental results show using epochs 10 and 100 samples imply 98.37% training accuracy whereas other numbers of epochs either provide less accuracy or consume more time, and the number of epochs and training samples can be modified according to the system requirements. Other factors like illumination, the color of the background, and face rotation or scale were discussed as impact factors.

Algorithm Optimizer in GA-LSTM for Stock Price Forecasting

Fluctuating stock prices make it difficult for investors to see investment opportunities. One tool that can help investors overcome this is represented by forecasting techniques. Long Short-Term Memory (LSTM) is one of deep learning methods used in forecasting time series. The training and success of deep learning is strongly influenced by the selection of hyperparameters. This research uses a hybrid method between the Genetic Algorithm (GA) and LSTM to find a suitable model for predicting stock prices. GA is used in optimizing the architecture such as the number of epochs, window size, and the number of LSTM units in the hidden layer. Tuning optimizer is also carried out using several optimizers to achieve the best value. From method that has been applied, it shows that the method has a good level of accuracy with MAPE values below 10% in every optimizer used. The error rate generated is quite low, in case-1 with a minimum RMSE value of 93.03 and 94.40, &amp; in case-2 with an RMSE value of 104.99 and 150.06 during training and testing. A fairly stable and small value is generated by setting it using the Adam Optimizer.

Refinement bounds for the expected number of renewal epochs over a finite interval

ABSTRACT Primary quantities of interest in renewal theory are the expected number of renewals in ( 0 , t ] , known as renewal function (denoted by U ( t ) ), and the expected number of renewals in ( t , t + h ] , given by the difference U ( t + h ) − U ( t ) .One of the most known bounds for the expected number of renewals over a finite interval is the one delivered by Barlow and Proschan [Statistical theory of reliability and life testing. MD: Silver Spring; 1981. Reprint Edition. To begin with]. The essential quantity of this bound is the difference U ( t + h ) − U ( t ) − U ( h ) . In this paper, initially, we offer bounds for the conditional tails of the backward and forward recurrence times, and we give a renewal-type equation for the difference U ( t + h ) − U ( t ) − U ( h ) . Employing those results, we refine the provided bound by Barlow and Proschan [Statistical theory of reliability and life testing. MD: Silver Spring; 1981. Reprint Edition. To begin with]. The results are illustrated with numerical examples.

An approach to optimization of Gated Recurrent Unit with Greedy Algorithm

This study focuses on enhancing the performance of Stacked Gated Recurrent Unit (GRU) model in time series data processing, specifically in stock price prediction. The most significant innovation occurs in the integration of a Greedy Algorithm for optimizing hyperparameters such as look-back period, number of epochs, batch size, and units in each GRU layer. Historical stock data from Apple Inc. is utilized for the model's application, emphasizing the model's effectiveness in predicting stock prices. The study methodology involves a sequence of steps, such as data loading, preprocessing, dataset splitting, model construction, and evaluation. The role of the Greedy Algorithm is to iteratively adjust hyperparameters to minimize the Root Mean Squared Error (RMSE) metric, resulting in refining the model's predictive accuracy. The outcomes reveal that the integrated Greedy Algorithm significantly enhances the model's accuracy in predicting stock prices, indicating its potential application in various scenarios requiring precise time series forecasting.

Implementation of Neural Network for Classification of Diabetes Mellitus through Finger Nail Image

This study aims to obtain accuracy for classification of diabetes mellitus based on fingernail images using neural network. The data is fingernail images with fasting conditions and non-fasting conditions. In each condition, data is divided into three namely diabetes, prediabetes and normal data. Images in each data are 100 images. Methods were preprocessing, GLCM, neural network (NN) and accuracy. Preprocessing were cropping and grayscaling. GLCM were contrast, entropy, homogeneity, energy and correlation features. In NN, number of epochs used is 1000. Images in the training data is 240. The accuracy were 100% for fasting condition and 85% for non-fasting condition.

Analysis of Optimization Techniques in 6D Pose Estimation Approaches using RGB Images on Multiple Objects with Occlusion

6D pose estimation is very important for supporting future smart technologies. The previous methods show optimal performance on RGB-D images or single objects. However, the problem still occurs in RGB images or multiple objects with occlusion. This study focuses on solving the problem using a deep learning approach. One of the key components of deep learning is the optimization process, which we research to determine its effect on solving the problem. The research methodology includes implementing the optimization techniques in the methods, measuring loss value, measuring performance, observing experimental results, analyzing statistical significance, and comparing the performance of optimizers. We implement Adam, RMSprop, Adagrad, Adadelta, and SGD optimizers and analyze their effects on the EfficientPose and DPOD methods. We use the LineMod-Occluded dataset to measure the performance of the methods using the ADD metric. According to the experiment, the loss value is low and stable in the experimental scenarios with a number of epochs between 200 and 500. The performance is relatively high in those scenarios, where Adadelta's performance outperforms other optimizers on both methods. Based on the analysis of variance, the effect of optimizers on the performance of the methods is low, but the slight performance increase is significant in this case.