arXiv subjects

Thien Nhan Vo

Publications and source records attributed to Thien Nhan Vo.

7 recordsLinked to original sources

arXiv2026

TinyCNNDeep: Lightweight Attention-Based CNN for EEG Classification of Eye States and Sleep Deprivation

Sleep deprivation impairs vigilance and cognitive function, yet jointly identifying the sleep condition (normal vs deprived) and the eye state (open vs closed) from electroencephalography (EEG) remains underexplored. We address this four-class problem with TinyCNNDeep, a lightweight convolutional neural network that combines residual learning with a Squeeze-and-Excitation (SE) attention module. We convert short multi-channel EEG segments from five physiologically relevant channels (Fp1, Fp2, O1, Oz, O2) into 224x224 grayscale images through per-channel Z-score normalization, min-max scaling, and center padding, enabling 2D convolutions to jointly model inter-channel and temporal structure. On a 35-subject dataset recorded under normal-sleep and sleep-deprivation sessions, TinyCNNDeep attains a subject-wise mean accuracy of 83.69%, outperforming the strongest baseline (Random Forest with combined time-frequency features, 47.66%) by 36.03 percentage points, while three established EEG architectures (EEGNet, ShallowConvNet, DeepConvNet) operate near chance. Per-subject analysis quantifies inter-subject variability, and confusion-matrix inspection shows that residual misclassifications concentrate between eyes-closed states across sleep conditions. These results indicate that an image-based EEG representation paired with residual feature extraction and channel attention provides an accurate and computationally efficient framework for multiclass sleep-related EEG classification under a minimal electrode configuration.

cs.HC↗

arXiv2025

Nonlinear Control of a Quadrotor UAV Using Backstepping-Based Sliding Mode Technique

This paper presents the development of a sliding mode controller using the backstepping approach. The controller is employed to synthesize tracking errors and Lyapunov functions. A novel state-space representation is formulated by incorporating the dynamics of the quadrotor and accounting for non-holonomic constraints. The proposed sliding mode controller effectively addresses system nonlinearities and improves tracking of predefined trajectories. Simulation results are presented graphically to demonstrate the controller's performance.

eess.SY↗

arXiv2025

Understand the Effect of Importance Weighting in Deep Learning on Dataset Shift

We evaluate the effectiveness of importance weighting in deep neural networks under label shift and covariate shift. On synthetic 2D data (linearly separable and moon-shaped) using logistic regression and MLPs, we observe that weighting strongly affects decision boundaries early in training but fades with prolonged optimization. On CIFAR-10 with various class imbalances, only L2 regularization (not dropout) helps preserve weighting effects. In a covariate-shift experiment, importance weighting yields no significant performance gain, highlighting challenges on complex data. Our results call into question the practical utility of importance weighting for real-world distribution shifts.

cs.LG↗

arXiv2025

3D Brain MRI Classification for Alzheimer Diagnosis Using CNN with Data Augmentation

A three-dimensional convolutional neural network was developed to classify T1-weighted brain MRI scans as healthy or Alzheimer. The network comprises 3D convolution, pooling, batch normalization, dense ReLU layers, and a sigmoid output. Using stochastic noise injection and five-fold cross-validation, the model achieved test set accuracy of 0.912 and area under the ROC curve of 0.961, an improvement of approximately 0.027 over resizing alone. Sensitivity and specificity both exceeded 0.90. These results align with prior work reporting up to 0.10 gain via synthetic augmentation. The findings demonstrate the effectiveness of simple augmentation for 3D MRI classification and motivate future exploration of advanced augmentation methods and architectures such as 3D U-Net and vision transformers.

eess.IV↗

arXiv2025

Heart Rate Classification in ECG Signals Using Machine Learning and Deep Learning

This study addresses the classification of heartbeats from ECG signals through two distinct approaches: traditional machine learning utilizing hand-crafted features and deep learning via transformed images of ECG beats. The dataset underwent preprocessing steps, including downsampling, filtering, and normalization, to ensure consistency and relevance for subsequent analysis. In the first approach, features such as heart rate variability (HRV), mean, variance, and RR intervals were extracted to train various classifiers, including SVM, Random Forest, AdaBoost, LSTM, Bi-directional LSTM, and LightGBM. The second approach involved transforming ECG signals into images using Gramian Angular Field (GAF), Markov Transition Field (MTF), and Recurrence Plots (RP), with these images subsequently classified using CNN architectures like VGG and Inception. Experimental results demonstrate that the LightGBM model achieved the highest performance, with an accuracy of 99% and an F1 score of 0.94, outperforming the image-based CNN approach (F1 score of 0.85). Models such as SVM and AdaBoost yielded significantly lower scores, indicating limited suitability for this task. The findings underscore the superior ability of hand-crafted features to capture temporal and morphological variations in ECG signals compared to image-based representations of individual beats. Future investigations may benefit from incorporating multi-lead ECG signals and temporal dependencies across successive beats to enhance classification accuracy further.

eess.SP↗

arXiv2025

Deep Learning for On-Street Parking Violation Prediction

Illegal parking along with the lack of available parking spaces are among the biggest issues faced in many large cities. These issues can have a significant impact on the quality of life of citizens. On-street parking systems have been designed to this end aiming at ensuring that parking spaces will be available for the local population, while also providing easy access to parking for people visiting the city center. However, these systems are often affected by illegal parking, providing incorrect information regarding the availability of parking spaces. Even though this can be mitigated using sensors for detecting the presence of cars in various parking sectors, the cost of these implementations is usually prohibiting large. In this paper, we investigate an indirect way of predicting parking violations at a fine-grained level, equipping such parking systems with a valuable tool for providing more accurate information to citizens. To this end, we employed a Deep Learning (DL)-based model to predict fine-grained parking violation rates for on-street parking systems. Moreover, we developed a data augmentation and smoothing technique for further improving the accuracy of DL models under the presence of missing and noisy data. We demonstrate, using experiments on real data collected in Thessaloniki, Greece, that the developed system can indeed provide accurate parking violation predictions.

cs.LG↗

arXiv2025

Active Learning for Multi-class Image Classification

A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting examples. Assigning values to image examples using different uncertainty metrics allows the model to identify and select high-value examples in a smaller training set size. We demonstrate results for digit recognition and fruit classification on the MNIST and Fruits360 data sets. We formally compare results for four different uncertainty metrics. Finally, we observe active learning is also effective on simpler (binary) classification tasks, but marked improvement from random sampling is more evident on more difficult tasks. We show active learning is a viable algorithm for image classification problems.

cs.CV↗