KMITL

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

Browse

Search Results

Now showing 1 - 10 of 16

Some of the metrics are blocked by your
consent settings
Optimized CNN-based channel estimation for zero-padded uplink OFDMA in 5G new radio over fast-fading channels
(2026-07-01)
Mata, Tanairat
;
Boonsrimuang, Pisit
This paper addresses a pilot-assisted channel estimation applicable to the uplink orthogonal frequency-division multiple-access with zero-padding in a 5G new radio. The adjacent uplink subchannels in the frequency domain are allocated separately for each user, and each subchannel assigns the pilot signal independently. This paper proposes a convolutional neural network-based channel estimation, including one-dimensional and two-dimensional architectures, designed to optimize the handling of rapid fading channel variations encountered in high-mobility scenarios. The estimation process leverages the subchannels of each user to enhance accuracy. Simulation results demonstrate the effectiveness of the proposed method in offering a better bit-error rate and a higher transmission data rate than the conventional channel estimation methods under challenging conditions. Finally, this paper discusses the considerable computational complexity of aspects of the lightweight two convolutional neural network architectures.
Some of the metrics are blocked by your
consent settings
Time Series-Based Fault Detection and Classification in IEEE 9-Bus Transmission Lines Using Deep Learning
(2025-01-01)
Jiriwibhakorn, Somchat
;
Kanwal, Shazia
Transmission line faults present a significant threat to the stability of power systems, potentially causing widespread outages. Timely detection of these faults is essential to prevent substantial disruptions in the power supply. This paper explores a time series-based deep learning technique for fault detection and classification in the IEEE 9-bus system. Post asymmetrical fault current and voltage time series data have been used to train a convolutional neural network (CNN), representing normal and faulty conditions, with convolutional and ReLU layers. A fully connected layer is used to detect features without missing critical information of the signal, achieving MSE as zero for fault detection and 0.0149 for fault classification. This demonstrates the effectiveness of CNNs for real-time fault detection and classification in complex power grids. The robustness of the CNN model indicates its potential for deployment in practical applications, enhancing the reliability and resilience of the transmission network. Using deep learning techniques opens opportunities for further improvements in fault detection and location strategies within the power grid.
Some of the metrics are blocked by your
consent settings
Quality Classification of Sunglasses Lens by Deep Learning
(2025-01-01)
Theskham, Charin
;
Jearanaitanakij, Kietikul
Sunglasses lens are medical devices designed to correct human vision while also providing protection against ultraviolet (UV) radiation. Sunglasses lenses come in various colors, each offering different light-filtering properties. Currently, the quality classification of sunglasses lenses during the production process still relies on human vision. Therefore, this research aims to study the design and quality classification of sunglasses lens with both evenness and unevenness colors using machine vision and deep learning techniques. However, from the review of existing studies on sunglasses lens quality inspection, informal research has been conducted in this area. This work is considered a new contribution with potential for practical application in the industry. In this study, a Convolutional Neural Network (CNN) will be used. To save research time, the researchers employed transfer learning techniques using models such as VGG16, VGG19, InceptionV3, Xception, DenseNet121, ResNet50, EfficientNetB0, EfficientNet -B7, and EfficientNetV2L. The classification results are divided into 2 categories for evenness colors lens and unevenness colors lens. The dataset used real photos of sunglasses lens from Hoya Lens Thailand as the data source. A dataset of 1,250 real images of sunglasses lens was used, comprising 625 images of evenness colors lens and 625 images of unevenness colors lens. Data augmentation was performed by rotating the images 90, 180, and 270 degrees, as well as vertically flipping the sunglasses lens images. This process yielded a total of 10,000 images, with 5,000 images each for lenses with evenness and unevenness colors. The results of applying Transfer Learning of each model for classifying the quality of sunglasses lens that the DenseNet121 model achieved the highest performance, with an accuracy of 82.23 % and precision of 82.32 %
Some of the metrics are blocked by your
consent settings
Applying Convolutional Neural Network with Candlestick Images to Predict Corn Price Movement
(2025-01-01)
Chaiwuttisak, Pornpimol
The objective of this research is to study the effect of hyperparameters on corn price movement prediction models, namely batch size and learning rate, and create a model to predict the corn price movement in the Chicago Board of Trade (CBOT) based on candlestick images at 5-day and 20-day timeframes. The data are split into three sets, namely, training set, validation set, and test set, with a ratio of 70:10:20. The models presented in this research are CNN, VGG-16, and Efficientnet-B0, which must be fine-tuned. The study’s findings on hyperparameter values within a 5-day timeframe revealed that the optimal batch size and learning rates for all three models were a batch size of 16 with a learning rate of 0.001 and a timeframe of 20 days with a dataset size of 16. However, the suitable learning rate for the CNN model was 0.001, while for the VGG-16 and EfficientNet-B0 models, it was 0.0001. Subsequently, the hyperparameter values were fine-tuned for each model and tested the model with the test set. The study findings revealed that at the 5-day timeframe, the customized CNN model outperformed other models in predicting corn price movement, with an accuracy of 55.39%, while at a 20- day timeframe, the model with the highest accuracy was EfficientNet-B0, with an accuracy of 55.03%.
Some of the metrics are blocked by your
consent settings
Classification of the equatorial plasma bubbles using convolutional neural network and support vector machine techniques
(2023-12-01)
Thanakulketsarat, Thananphat
;
Supnithi, Pornchai
;
Myint, Lin Min Min
;
Hozumi, Kornyanat
;
Nishioka, Michi
Equatorial plasma bubble (EPB) is a phenomenon characterized by depletions in ionospheric plasma density being formed during post-sunset hours. The ionospheric irregularities can lead to disruptions in trans-ionospheric radio systems, navigation systems and satellite communications. Real-time detection and classification of EPBs are crucial for the space weather community. Since 2020, the Prachomklao radar station, a very high frequency (VHF) radar station, has been installed at Chumphon station (Geographic: 10.72° N, 99.73° E and Geomagnetic: 1.33° N) and started to produce radar images ever since. In this work, we propose two real-time plasma bubble detection systems based on support vector machine techniques. Two designs are made with the convolutional neural network (CNN) and singular value decomposition (SVD) used for feature extraction, the connected to the support vector machine (SVM) for EPB classification. The proposed models are trained using quick look (QL) plot images from the VHF radar system at the Chumphon station, Thailand, in 2017. The experimental results show that the combined CNN-SVM model, using the RBF kernel, achieves the highest accuracy of 93.08% while the model using the polynomial kernel achieved an accuracy of 92.14%. On the other hand, the combined SVD-SVM models yield the accuracies of 88.37% and 85.00% for RBF and polynomial kernels of SVM, respectively. Graphical Abstract: [Figure not available: see fulltext.].
Some of the metrics are blocked by your
consent settings
FACE SPOOFING DETECTION BASED ON DEEP FEATURE EXTRACTION AND INSTANCE-BASED CLASSIFICATION
(2023-02-01)
Claypo, Niphat
;
Jaiyen, Saichon
;
Hanskunatai, Anantaporn
Face recognition is an important task in smart home security for detecting a face or monitoring a person in a live video and verifying the identity of an authentic user. However, there have been spoofing face methods that can trick a face recognition algorithm into wrongly verifying the identity of the person. In this paper, we propose a new hybrid framework for spoofing face detection based on Convolutional Neural Network and Long Short-Term Memory (CNNLSTM) and instance-based learning algorithm. In addition, a new dataset called FSA-CCTV is proposed, which contains face images from CCTV video clips with many types of spoofing attacks. The performance of our method was compared to several other anti-spoofing methods: CNN and RI-LBP, SLRNN, HSV+YCbCr, ResNet50, YCbCr+SVM and YCbCr+KNN. The experimental results show that our method yielded 93.2% of Accuracy, 96.8% of Recall, 94% of Precision, 94.8% of F<inf>1</inf>-score and 0.93 of AUC on the FSA-CCTV dataset. From the experimental results we can conclude that the proposed algorithm outperforms other approaches and yielded the most stable classification accuracy on the proposed dataset.
Some of the metrics are blocked by your
consent settings
Rice Diseases Recognition Using Transfer Learning from Pre-trained CNN Model
(2023-01-01)
Hamhongsa, Wittawat
;
Wiangsripanawan, Rungrat
;
Thorncharoensri, Pairat
This research aims at applying the well-known pre-trained convolutional neural network (CNN) image classification algorithms such as InceptionV3, Xception, ResNetV2, InceptionResNetV2, and DenseNet to classify the five diseases of rice's leaves in Thailand. Data sets used are from 3 sources: UCI database, Rice Leaf Disease Image Samples dataset and images collected by authors in Thailand between 2018–2020. Our initial experimental result shows that using the pre-trained CNN models to classify the rice leaves disease seems to be possible with a greater number of images required. Therefore, the image data augmentation technique is used to add the number of images into the dataset. The experimental result with data augmentation shows that it could increase rice disease classification efficiency up to 16.533% (especially for the ResNet50V2 model).
Some of the metrics are blocked by your
consent settings
Seven Segment Display Detection and Recognition via Deep Learning Technique
(2022-01-01)
Suttapakti, Ungsumalee
;
Titijaroonroj, Taravichet
;
Nunsong, Walairach
;
Kakanopas, Donyarut
Seven segment display detection and recognition play an important role in determining the status of manufacturing machines. However, in some industrial factories, employees are still assigned to manually record the status of the seven segment displays. This is not real-Time tracking status and it is easy to make the typos or mistakes while collecting data. Hence, image processing and machine vision are used to automatically detect and recognize images from the seven segment displays. In this paper, the Cascade R-CNN is applied to automatically detect and recognize seven-segment displays in a single model-End-To-end learning because this method is efficient and flexible. The Cascade R-CNN method achieves precision, recall, and F1-score of 0.999 which are higher than conventional methods and the state-of-The-Art methods, including Faster R-CNN, RetinaNet, NAS-FPN, CornerNet, and CenterNet. Although the recognition accuracy of Cascade R-CNN is slightly lower than those of YOLOv3 and CornerNet, its accuracy is still higher than the Faster R-CNN, SSD, RetinaNet, NAS-FPN, and CenterNet. This method can automatically detect and recognize the digits on seven-segment display in a single model, thus improving the effectiveness for detecting and recognizing seven-segment display images.
Some of the metrics are blocked by your
consent settings
A CNN-BASED MULTI-MODEL ENSEMBLE METHOD FOR INDOOR AND OUTDOOR MULTI-VIEW STEREO RECONSTRUCTION
(2022-01-01)
Wattanacheep, Bhattarabhorn
;
Chitsobhuk, Orachat
Camera poses estimation is a critical process that ensures the success of Three-Dimensional (3D) modelling. We present a Convolutional Neural Network (CNN)-based multi-model ensemble method for indoor and outdoor multi-view stereo reconstruction capable of learning across multiple domains, including images from both indoor and outdoor environments. Each domain’s images have distinct properties and shooting view-points, which leads to difficulty in efficient learning such a large difference and requires large amount of computational resources. In order to reduce complexity of the end-to-end single model, the proposed model is divided into multiple learning agents consisting of domain-specific agents and domain relationship agent. The domain-specific agent is trained independently on its own set of unique image characteristics, for example, one for indoor datasets and another for outdoor datasets. The domain relationship agent then ensembles and analyzes the multiple domain features and finalizes the estimation. In terms of average root mean square error, we compare the performance of the combined domain single model with the suggested ensemble CNN model. The experimental results indicate that the proposed model outperforms the others, with rotation and translation prediction errors of 0.112012266.
Some of the metrics are blocked by your
consent settings
Transformer-based decoder designs for semantic segmentation on remotely sensed images
(2021-12-01)
Panboonyuen, Teerapong
;
Jitkajornwanich, Kulsawasd
;
Lawawirojwong, Siam
;
Srestasathiern, Panu
;
Vateekul, Peerapon
Transformers have demonstrated remarkable accomplishments in several natural language processing (NLP) tasks as well as image processing tasks. Herein, we present a deep-learning (DL) model that is capable of improving the semantic segmentation network in two ways. First, utilizing the pre-training Swin Transformer (SwinTF) under Vision Transformer (ViT) as a backbone, the model weights downstream tasks by joining task layers upon the pretrained encoder. Secondly, decoder designs are applied to our DL network with three decoder designs, U-Net, pyramid scene parsing (PSP) network, and feature pyramid network (FPN), to perform pixel-level segmentation. The results are compared with other image labeling state of the art (SOTA) methods, such as global convolutional network (GCN) and ViT. Extensive experiments show that our Swin Transformer (SwinTF) with decoder designs reached a new state of the art on the Thailand Isan Landsat-8 corpus (89.8% F1 score), Thailand North Landsat-8 corpus (63.12% F1 score), and competitive results on ISPRS Vaihingen. Moreover, both our best-proposed methods (SwinTF-PSP and SwinTF-FPN) even outperformed SwinTF with supervised pre-training ViT on the ImageNet-1K in the Thailand, Landsat-8, and ISPRS Vaihingen corpora.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results