KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
FILTER PRUNING BASED ON LOCAL GRADIENT ACTIVATION MAPPING IN CONVOLUTIONAL NEURAL NETWORKS
(2023-12-01)
Intraraprasit, Monthon
;
Chitsobhuk, Orachat
Convolutional Neural Network (CNN) is a well-known Deep learning model utilized extensively in the field of computer vision. The structure of convolutional neural networks is quite complicated and necessitates a substantial amount of computational time and storage resources. As a result, it is difficult to adopt a CNN model on a resource-constraint device. Model pruning can help to reduce computation time and storage re-quirements. In this research, we propose a filter pruning technique based on Localized Gradient Activation heatmaP (LGAP) for the purpose of pruning CNNs. Analyzing a filter based on statistical criterion of single neuron can lead to a loss in spatial relations within the filter activation itself, the relationship to target prediction, as well as the relationship among filters in that specific layer. To minimize the limitations, we evaluate the significance of a filter through the spatial information of local gradient activation related to the target prediction in terms of the layer-wise loss of the investigated filter. The effect of loss of an investigated filter demonstrates the significance or insignificance of the filter. Our pruning criteria ensure that these significant filters are preserved, while maintaining the model accuracy. The performance of our pruning method was validated using VGG-16 and ResNet-50. With pruning ratio of 50%, VGG-16 tends to decrease 1.66% of its accuracy, 3.6× of FLOP and 3.9× of storage reduction. For ResNet-50, with 50% pruning ratio, the results show that Top-1 and Top-5 of our pruning techniques outperform all the baseline techniques with a reduction of top-1 accuracy by 3.56%, top-5 accuracy by 1.89%, Floating Point Operation by 2.3×, and storage by 2.05×.
Some of the metrics are blocked by your
consent settings
Classification of Adulterated Particle Images in Coconut Oil Using Deep Learning Approaches
(2022-01-01)
Palananda, Attapon
;
Kimpan, Warangkhana
In the production of coconut oil for consumption, cleanliness and safety are the first priorities for meeting the standard in Thailand. The presence of color, sediment, or impurities is an important element that affects consumers’ or buyers’ decision to buy coconut oil. Coconut oil contains impurities that are revealed during the process of compressing the coconut pulp to extract the oil. Therefore, the oil must be filtered by centrifugation and passed through a fine filter. When the oil filtration process is finished, staff inspect the turbidity of coconut oil by examining the color with the naked eye and should detect only the color of the coconut oil. However, this method cannot detect small impurities, suspended particles that take time to settle and become sediment. Studies have shown that the turbidity of coconut oil can be measured by passing light through the oil and applying image processing techniques. This method makes it possible to detect impurities using a microscopic camera that photographs the coconut oil. This study proposes a method for detecting impurities that cause the turbidity in coconut oil using a deep learning approach called a convolutional neural network (CNN) to solve the problem of impurity identification and image analysis. In the experiments, this paper used two coconut oil impurity datasets, PiCO_V1 and PiCO_V2, containing 1000 and 6861 images, respectively. A total of 10 CNN architectures were tested on these two datasets to determine the accuracy of the best architecture. The experimental results indicated that the MobileNetV2 architecture had the best performance, with the highest training accuracy rate, 94.05%, and testing accuracy rate, 80.20%.
Some of the metrics are blocked by your
consent settings
Sample and system parameter estimation from local speckle pattern by fully numerically trained deep convolution neural network
(2021-01-01)
Seesan, T.
;
Oida, D.
;
Oikawa, K.
;
Buranasiri, P.
;
Yasuno, Y.
Deep convolutional neural network (CNN) based estimators for optical coherence tomography (OCT) are presented. The CNN analyze local OCT speckle patterns and estimate the sample's scatterer density and OCT resolutions. This estimator is intensity invariant, i.e., it does not use the net signal strength of OCT even to estimate the scatterer density. The CNN is trained by a huge training dataset that was generated by a simple simulator of OCT imaging. And hence, the CNN is trained without experimental datasets. The performance of CNN was evaluated by numerically generated OCT images, and good accuracies of the estimation were shown.
Some of the metrics are blocked by your
consent settings
ADGAS: An Advanced Data Generation for Anomalous Signals
(2021-01-01)
Chalongvorachai, Thasorn
;
Woraratpanya, Kuntpong
Anomaly detection using deep learning approaches is still challenging, especially in the case of data limitations. A small number of samples for training deep learning models typically result in poor performance of detection and classification. Previously, data augmentation was one of the methods used to solve this problem. The data augmentation with rotation, permutation, time warping, and their combination can increase the performance of anomaly classification. However, this method is still limited and does not guarantee that the generated output data have adequate varieties and keep original characteristics of data. Our recent work, data augmentation and generation for anomalous time series signals (DAGAT) was proposed to expand the space of possible augmented data by implementing vanilla augmentation on various domains in conjunction with variational autoencoder (VAE). Nonetheless, the DAGAT still has barriers, which are an uncontrollable number of target results, a missed opportunity of integrating multiple augmentation characteristics in latent space, and a possibility of including any bad data for training in VAE. To overcome these limitations, this paper proposed an advanced data generation for anomalous signals (ADGAS). By focusing on the quality of generated data, one more quality classifier (QC) was added as a prepossessing step of VAE. In this way, the experimental results showed that convolutional neural networks (CNNs), used as a performance tester, trained with the generated datasets of ADGAS achieved better accuracy in classifying anomalous events when compared to models trained with a combination of rotation, permutation, and time warping data augmentation methods.
Some of the metrics are blocked by your
consent settings
Intensity-invariant scatterer density estimation for optical coherence tomography using deep convolutional neural network
(2020-01-01)
Seesan, Thitiya
;
Oida, Daisuke
;
Oikawa, Kensuke
;
Buranasiri, Prathan
;
Yasuno, Yoshiaki
A convolutional neural networks (CNN) based scatterer density estimator for optical coherence tomography (OCT) is presented. In order to train the OCT, small patches of OCT speckle image were numerically generated. In this numerical image generation, the imaging parameters including the resolutions, probe power, signal-to-noise ratio, and scatterer density were randomly defined. So, the CNN was trained to estimate the imaging parameters from the generated OCT image patch. The results showed that our CNN estimator can estimate the parameters from the OCT speckle images.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results