KMITL

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

Browse

Search Results

Now showing 1 - 9 of 9

Some of the metrics are blocked by your
consent settings
Improving the Sound Classification Accuracy Using CNN-LSTM and MFCC with Audio Augmentation for Diagnosing Respiratory Disease
(2025-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
Audio is vital information data for understanding various situations. A multitude of sound features can be explained by analysis through the audio signals. Numerous classification methods have been developed to study audio classification. This work studies the improvement of audio classification for the diagnosis of respiratory disease through the integration of audio data augmentation and CNN in conjunction with LSTM (CNN-LSTM). Furthermore, this paper focuses on audio data augmentation and feature extraction in the deep learning approach. This study proposed the CNN-LSTM model to diagnose respiratory disease by learning from the different audio datasets. The results reveal that the CNN-LSTM model attained an accuracy of 81.48%, precision of 0.8340, sensitivity of 0.6948, and F1-score of 0.7225. Considering the achieved F1-score, the CNN-LSTM model demonstrates a high level of diagnotic accuracy. Therefore, all evaluation evaluation parameters collectively indicate the robust performance of the proposed disease classification model.
Some of the metrics are blocked by your
consent settings
Subcellular Protein Patterns Classification Using Extreme Gradient Boosting with Deep Transfer Learning as Feature Extractor
(2024-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
Proteins are essential structural and functional components of human cells. Understanding and identifying proteins can provide valuable insights into their structure, function and role in human body. Subcellular proteins provide the expression that characterizes the many proteins and their conditions across cell types. This work proposed a classification model for subcellular protein patterns using XGBoost with transfer learning of CNN as the feature extractor. In the model training process, we used ResNet50, VGG16, Xception, and MobileNet as the pre-trained models based on the transfer learning technique to extract different features. The proposed model was used to classify subcellular proteins into 28 patterns. The XGBoost with ResNet50, VGG16, MobileNet, and Xception model achieved an accuracy level of 92.20% 92.77%, 91.63%, and 91.44%, respectively. The XGBoost with ResNet50, VGG16, MobileNet, and Xception model obtained an F1 score of 0.9179, 0.9233, 0.9131, and 0.9152, respectively. Considering the F1 score, All XGBoost with transfer learning of CNN models gave a high score. Therefore, all evaluation parameters clearly demonstrate the high performance of the subcellular protein pattern classification model.
Some of the metrics are blocked by your
consent settings
Improving Classification Efficiency Based on Combination of Extreme Gradient Boosting and Deep Transfer Learning
(2023-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
The leading causes of blindness and low vision are ocular disease. Ocular disease such as glaucoma, cataract, diabetic retinopathy, and macular degeneration, which are diseases in which the risk of vision loss. Unfortunately, some ocular diseases have no symptoms until the late stages. Therefore, early-stage diagnosis of ocular disease is the best way to prevent vision loss. This work proposed the classification models for ocular disease classification using XGBoost in combination with deep transfer learning of CNN as the feature extractor. In the model training process, we used the pre-trained model including Xception and ResNet50 based on the transfer learning technique to extract different features. The proposed model was used to classify ocular disease into eight patterns. The XGBoost in combination with the ResNet50 model achieved an accuracy level of 87.82%, precision of 88.15%, sensitivity of 87.82%, and F1 score of 87.82%. The XGBoost in combination with the Xception model acquired an accuracy level of 87.02%, precision of 87.35%, sensitivity of 87.02%, and F1 score of 87.02%. By considering the F1 score, XGBoost in combination with transfer learning of CNN models gave a high score. Therefore, all evaluation parameters clearly indicate the high performance of the ocular disease classification model. The conclusion presents that the proposed method acquires more excellent performance than individual deep learning models.
Some of the metrics are blocked by your
consent settings
Stages of Progression Classification of Alzheimer's Disease Using Deep Transfer Learning Models with Over-Sampling
(2022-01-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
Alzheimer's disease is a chronic neurodegenerative disease that affected patients loss of memory, ability of thinking, reading, and cognitive decline. The Alzheimer's disease divided stages of progression into four general stages on the basis of their symptoms. The early diagnosis helps to slow down the disease and reduce the costs of treatment. Since Alzheimer's disease has four stages of progression, the classification problems are those where a stage must be predicted in the case of an unequal number of instances of each class. This study has proposed the classification the stages of progression of Alzheimer's disease using four transfer learning models such as VGG19, Xception, ResNet50, and MobileNetV2. The proposed models classify Alzheimer's disease into four stage of progression. The models gained an accuracy level of VGG19, Xception, ResNet50, and MobileNetV2 model of 77.73%, 82.46%, 76.28% and 79.29%, respectively. By considering the F1 score, the Xception, VGG19, and ResNet50, and MobileNetV2 models gave the high score of 0.7995, 0.8870, 0.8305, and 0.5993, respectively. Therefore, the VGG19 model is the best model by considering the F1 score that means the VGG19 model is the best model in overall performance. Finally, this study measures the AUC value that indicates the ability to classify between classes. The results show that AUC value of MobileNetV2, Xception, ResNet50, and VGG19 are 0.9290, 0.9539, 0.7937, and 0.8037, respectively. Therefore, the Xception model is the best model that has capable of distinguishing the stages of progression of the Alzheimer's disease.
Some of the metrics are blocked by your
consent settings
Evaluation of Deep Transfer Learning Models in Glaucoma Detection for Clinical Application
(2021-01-01)
Phankokkruad, Manop
The clinical information supports the doctors in diagnosing the diseases and making the right decisions. Glaucoma is the leading cause of irreversible blindness disease. Vision loss can be avoided by early stage detection and right treatment. This study has proposed the deep transfer learning of the CNN model for detecting the glaucoma using ResNet50V2, VGG16, InceptionV3, and Xception. The proposed models help in the diagnosis of the patients who have glaucoma. The model with CNN architecture was used to learn from training the Glaucoma image dataset. Since the existing dataset has a small number of images, this study uses the data augmentation techniques to increase the virtual number of images. The results reveal that the proposed models have performed the classification task for detecting glaucoma. The proposed model achieved an accuracy level of VGG16, RestNet50V2, InceptionV3, and Xception are 97.27%, 94.53%, 95.31%, and 94.92%, respectively. Furthermore, this study evaluates the models by considering the clinical performance parameters include accuracy, precision, specificity, sensitivity, and F1 score. All models provide the high confidence values. The evaluation reveals that the deep transfer learning model with VGG16 architecture is the highest performance in tests. The VGG16 model achieved the average AUC-ROC value of 98.94%.
Some of the metrics are blocked by your
consent settings
Cost-Sensitive Extreme Gradient Boosting for Imbalanced Classification of Breast Cancer Diagnosis
(2020-08-01)
Phankokkruad, Manop
The clinical information can enhance the doctors for predicting and diagnosing the diseases also making the right decisions. Breast cancer is the most dangerous disease, early diagnosis can improve a chance of survival and can support clinical treatment. Detecting breast cancer takes a lot of time and it is hard to classification. However, the problem of the classification occurs when there is an unequal distribution of classes the dataset. This is caused by the low performance in the traditional machine learning models. For this reason, this work proposed the cost-sensitive XGBoost model, which is an improved version of the XGBoost model in conjunction with cost-sensitive learning. The models were applied to classify the four breast cancer datasets that contained the imbalanced data. In the experiment, this work determined the best parameters on each dataset by the hyperparameters optimization technique before configuring the models. The results indicated that the cost-sensitive XGBoost model had been skillful, and could improve classification accuracy in four datasets. In addition, this work evaluated the model performance by accuracy, ROC AUC, and k-Fold cross-validation to ensure that the new models is accurate.
Some of the metrics are blocked by your
consent settings
COVID-19 Pneumonia detection in chest X-ray images using transfer learning of convolutional neural networks
(2020-07-24)
Phankokkruad, Manop
The COVID-19 pandemic is the defining global health crisis and the greatest challenge. Since its emergence and has spread rising daily worldwide. The early diagnosis of COVID-19 can improve a chance of survival and can support clinical treatment. An automatically COVID-19 pneumonia detection will support the medical diagnosis to examine the chest X-ray image. For this reason, this work intent to develop the CNN model by the process of transfer learning. The models will be created from the three pre-trained models include Xception, VGG16, and Inception-Resnet-V2 model. Then, these newly proposed models will be applied to detect COVID-19 pneumonia from the X-ray image dataset. The proposed models enhance to diagnose the chest X-ray images of patients who have pneumonia by COVID-19. Since the existing COVID-19 X-ray dataset has a small number of images containing 323 images, this work uses the data augmentation techniques to increase the virtual number of images. The results reveal that the proposed models have performed the classification task for detecting pneumonia. The proposed model achieved an accuracy level of Xception, VGG16, and Inception-Resnet-V2 is 97.19%, 95.42% and 93.87%, respectively. It reveals that the CNN model with the Xception has higher accuracy than VGG16 and Inception-ResNet-V2 model.
Some of the metrics are blocked by your
consent settings
An application of convolutional neural network-long short-term memory model for service demand forecasting
(2019-07-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
The medical services are very important requirement for being healthy human. In order to ensure the availability of resources for the medicine needed, the most hospital makes an service demand estimation by forecasting a number of patients to provide the sufficient medical services. Therefore, the accurately forecast a number of patients would be valuable knowledge for managing. This work proposed the CNN-LSTM model, which was a combination of CNN and LSTM, to forecast the number of patients who used hospital services. The CNN model was used to interpret, and extract the features from the input data. Then, it was provided this information to the LSTM model for interpreting and making a forecast. The CNN-LSTM models were applied to forecast on the two datasets. The results indicated that CNN-LSTM model made reliable forecasting. This work measured the model performnace by calculating RMSE and MAE value. The result showed RMSE and MAE of the models were very low in all experiments. Forecasting the number of patients can help the hospital to estimate the service demand, make a better policy for managing the medical resources on demand, and improve the efficiency of medical services for the future.
Some of the metrics are blocked by your
consent settings
A comparison of efficiency improvement for long short-term memory model using convolutional operations and convolutional neural network
(2019-07-01)
Phankokkruad, Manop
;
Wacharawichanant, Sirirat
This work studied the comparison of LSTM, ConvLSTM and CNN-LSTM model, that was applied for time series forecasting. We created the LSTM, CNN-LSTM, ConvLSTM model and configured the optimal parameters by using hyperparameters optimization techniques. All models were applied to two different datasets for forecasting the number of patients in the future. This work also applied the SeLu and ReLu activation function to avoid the problem of gradient vanishing and improve the self-normalizing. The results indicated that two models had skillful, and made the reliable forecasting in two datasets. This work benchmarked the model performance by calculating MAE, RMSE, and sMAPE, which was acceptable in all case study. The CNN-LSTM model with SeLu activation function gave highest forecasting efficiency for the data contain seasonal variation. LSTM model with SeLu activation function gave highest forecasting efficiency in the case of non-stationary data.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results