scholarly journals Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study

2021 ◽  
Vol 7 ◽  
pp. e715
Author(s):  
Laith Alzubaidi ◽  
Ye Duan ◽  
Ayad Al-Dujaili ◽  
Ibraheem Kasim Ibraheem ◽  
Ahmed H. Alkenani ◽  
...  
Keyword(s):  
Neural Network ◽  
Experimental Study ◽  
Medical Imaging ◽  
Convolutional Neural Network ◽  
Natural Images ◽  
Training Data ◽  
Learning Models ◽  
Computational Tools ◽  
Effective Performance ◽  
Learned Features

Transfer learning (TL) has been widely utilized to address the lack of training data for deep learning models. Specifically, one of the most popular uses of TL has been for the pre-trained models of the ImageNet dataset. Nevertheless, although these pre-trained models have shown an effective performance in several domains of application, those models may not offer significant benefits in all instances when dealing with medical imaging scenarios. Such models were designed to classify a thousand classes of natural images. There are fundamental differences between these models and those dealing with medical imaging tasks regarding learned features. Most medical imaging applications range from two to ten different classes, where we suspect that it would not be necessary to employ deeper learning models. This paper investigates such a hypothesis and develops an experimental study to examine the corresponding conclusions about this issue. The lightweight convolutional neural network (CNN) model and the pre-trained models have been evaluated using three different medical imaging datasets. We have trained the lightweight CNN model and the pre-trained models with two scenarios which are with a small number of images once and a large number of images once again. Surprisingly, it has been found that the lightweight model trained from scratch achieved a more competitive performance when compared to the pre-trained model. More importantly, the lightweight CNN model can be successfully trained and tested using basic computational tools and provide high-quality results, specifically when using medical imaging datasets.

Building-damage detection method based on machine learning utilizing aerial photographs of the Kumamoto earthquake

2020 ◽  
Vol 36 (3) ◽  
pp. 1166-1187 ◽  
Author(s):  
Shohei Naito ◽  
Hiromitsu Tomozawa ◽  
Yuji Mori ◽  
Takeshi Nagata ◽  
Naokazu Monma ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Training Data ◽  
Aerial Photographs ◽  
Learning Models ◽  
Visual Interpretation ◽  
Damage Classification ◽  
Kumamoto Earthquake ◽  
Machine Learning Models

This article presents a method for detecting damaged buildings in the event of an earthquake using machine learning models and aerial photographs. We initially created training data for machine learning models using aerial photographs captured around the town of Mashiki immediately after the main shock of the 2016 Kumamoto earthquake. All buildings are classified into one of the four damage levels by visual interpretation. Subsequently, two damage discrimination models are developed: a bag-of-visual-words model and a model based on a convolutional neural network. Results are compared and validated in terms of accuracy, revealing that the latter model is preferable. Moreover, for the convolutional neural network model, the target areas are expanded and the recalls of damage classification at the four levels range approximately from 66% to 81%.

scholarly journals Convolutional Neural Networks for Challenges in Automated Nuclide Identification

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5238
Author(s):  
Anthony N. Turner ◽  
Carl Wheldon ◽  
Tzany Kokalova Wheldon ◽  
Mark R. Gilbert ◽  
Lee W. Packer ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Training Data ◽  
Significant Gain ◽  
Learning Models ◽  
Isotope Identification ◽  
Close Source ◽  
Machine Learning Models

Improvements in Radio-Isotope IDentification (RIID) algorithms have seen a resurgence in interest with the increased accessibility of machine learning models. Convolutional Neural Network (CNN)-based models have been developed to identify arbitrary mixtures of unstable nuclides from gamma spectra. In service of this, methods for the simulation and pre-processing of training data were also developed. The implementation of 1D multi-class, multi-label CNNs demonstrated good generalisation to real spectra with poor statistics and significant gain shifts. It is also shown that even basic CNN architectures prove reliable for RIID under the challenging conditions of heavy shielding and close source geometries, and may be extended to generalised solutions for pragmatic RIID.

scholarly journals Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1688
Author(s):  
Luqman Ali ◽  
Fady Alnajjar ◽  
Hamad Al Jassmi ◽  
Munkhjargal Gochoo ◽  
Wasif Khan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Crack Detection ◽  
Concrete Structures ◽  
Model Performance ◽  
Training Data ◽  
Computational Time ◽  
Data Heterogeneity ◽  
Public Datasets ◽  
Detection And Localization

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

scholarly journals Validating Deep Neural Networks for Online Decoding of Motor Imagery Movements from EEG Signals

Sensors ◽  
2019 ◽  
Vol 19 (1) ◽  
pp. 210 ◽  
Author(s):  
Zied Tayeb ◽  
Juri Fedjaev ◽  
Nejla Ghaboosi ◽  
Christoph Richter ◽  
Lukas Everding ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Classification Performance ◽  
Feature Engineering ◽  
Learning Models ◽  
Eeg Signals ◽  
Learning Methods

Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject’s motor intention into control signals through classifying the EEG patterns caused by different imagination tasks, e.g., hand movements. This type of BCI has been widely studied and used as an alternative mode of communication and environmental control for disabled patients, such as those suffering from a brainstem stroke or a spinal cord injury (SCI). Notwithstanding the success of traditional machine learning methods in classifying EEG signals, these methods still rely on hand-crafted features. The extraction of such features is a difficult task due to the high non-stationarity of EEG signals, which is a major cause by the stagnating progress in classification performance. Remarkable advances in deep learning methods allow end-to-end learning without any feature engineering, which could benefit BCI motor imagery applications. We developed three deep learning models: (1) A long short-term memory (LSTM); (2) a spectrogram-based convolutional neural network model (CNN); and (3) a recurrent convolutional neural network (RCNN), for decoding motor imagery movements directly from raw EEG signals without (any manual) feature engineering. Results were evaluated on our own publicly available, EEG data collected from 20 subjects and on an existing dataset known as 2b EEG dataset from “BCI Competition IV”. Overall, better classification performance was achieved with deep learning models compared to state-of-the art machine learning techniques, which could chart a route ahead for developing new robust techniques for EEG signal decoding. We underpin this point by demonstrating the successful real-time control of a robotic arm using our CNN based BCI.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

scholarly journals Efficient Facial Emotion Recognition Model using Deep Convolutional Neural Network and Modified Joint Trilateral Filter

2021 ◽  
Author(s):  
Naveen Kumari ◽  
Rekha Bhatia
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Emotion Recognition ◽  
Deep Convolutional Neural Network ◽  
Facial Emotion Recognition ◽  
Facial Emotion ◽  
Learning Models ◽  
Recognition Model ◽  
Trilateral Filter

Abstract Facial emotion recognition extracts the human emotions from the images and videos. As such, it requires an algorithm to understand and model the relationships between faces and facial expressions, and to recognize human emotions. Recently, deep learning models are extensively utilized enhance the facial emotion recognition rate. However, the deep learning models suffer from the overfitting issue. Moreover, deep learning models perform poorly for images which have poor visibility and noise. Therefore, in this paper, a novel deep learning based facial emotion recognition tool is proposed. Initially, a joint trilateral filter is applied to the obtained dataset to remove the noise. Thereafter, contrast-limited adaptive histogram equalization (CLAHE) is applied to the filtered images to improve the visibility of images. Finally, a deep convolutional neural network is trained. Nadam optimizer is also utilized to optimize the cost function of deep convolutional neural networks. Experiments are achieved by using the benchmark dataset and competitive human emotion recognition models. Comparative analysis demonstrates that the proposed facial emotion recognition model performs considerably better compared to the competitive models.

scholarly journals A Novel Convolutional Neural Network for Classifying Indian Coins by Denomination

2021 ◽  
Author(s):  
Yash Chauhan ◽  
Prateek Singh
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Academic Research ◽  
High Volume ◽  
Classification Problem ◽  
General Purpose ◽  
Training Data ◽  
Slot Machines ◽  
Validation Data ◽  
Starting Point

Coins recognition systems have humungous applications from vending and slot machines to banking and management firms which directly translate to a high volume of research regarding the development of methods for such classification. In recent years, academic research has shifted towards a computer vision approach for sorting coins due to the advancement in the field of deep learning. However, most of the documented work utilizes what is known as ‘Transfer Learning’ in which we reuse a pre-trained model of a fixed architecture as a starting point for our training. While such an approach saves us a lot of time and effort, the generic nature of the pre-trained model can often become a bottleneck for performance on a specialized problem such as coin classification. This study develops a convolutional neural network (CNN) model from scratch and tests it against a widely-used general-purpose architecture known as Googlenet. We have shown in this study by comparing the performance of our model with that of Googlenet (documented in various previous studies) that a more straightforward and specialized architecture is more optimal than a more complex general architecture for the coin classification problem. The model developed in this study is trained and tested on 720 and 180 images of Indian coins of different denominations, respectively. The final accuracy gained by the model is 91.62% on the training data, while the accuracy is 90.55% on the validation data.

Sign in / Sign up

Export Citation Format

Share Document