• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.2
• /
• pp.29-34
• /
• 2024

Since the outbreak of COVID-19, there has been a surge in sports conducted through online platforms due to the increase in remote and non-contact activities. Billiards, being suitable for online platforms, has received much attention, leading to research on detecting the position and trajectory of balls. In this paper, we propose a new method utilizing machine vision to detect the position of the balls accurately. The proposed method detects the outline of the ball using the Canny edge detection and then employs simple correlation to determine its position. This correlation-based approach offers satisfactory system performance and is easily applicable in practical systems due to its low implementation complexity and robustness to noise.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2082-2102
• /
• 2024

Accurate segmentation of magnetic resonance (MR) images is crucial for providing doctors with effective quantitative information for diagnosis. However, the presence of weak boundaries, intensity inhomogeneity, and noise in the images poses challenges for segmentation models to achieve optimal results. While deep learning models can offer relatively accurate results, the scarcity of labeled medical imaging data increases the risk of overfitting. To tackle this issue, this paper proposes a novel fuzzy c-means (FCM) model that integrates a deep learning approach. To address the limited accuracy of traditional FCM models, which employ Euclidean distance as a distance measure, we introduce a measurement function based on the skewed normal distribution. This function enables us to capture more precise information about the distribution of the image. Additionally, we construct a regularization term based on the Kullback-Leibler (KL) divergence of high-confidence deep learning results. This regularization term helps enhance the final segmentation accuracy of the model. Moreover, we incorporate orthogonal basis functions to estimate the bias field and integrate it into the improved FCM method. This integration allows our method to simultaneously segment the image and estimate the bias field. The experimental results on both simulated and real brain MR images demonstrate the robustness of our method, highlighting its superiority over other advanced segmentation algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2199-2213
• /
• 2024

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3914-3924
• /
• 2024

The release source term of radioactivity becomes a critical foundation for emergency response and accident consequence assessment after a nuclear accident Rapidly and accurately inverting the source term remains an urgent scientific challenge. Today source term inversion based on meteorological data and gamma dose rate measurements is a common method. But gamma dose rate actually includes all nuclides information, and the composition of radioactive nuclides is generally uncertain. This paper introduces a novel nuclear accident source term inversion model, which is Improve Snow Ablation Optimizer-Sensitivity Analysis Pruning Extreme Learning Machine (ISAO-SAELM) model. The model inverts the release rates of 11 radioactive nuclides (I-131, Xe-133, Cs-137, Kr-88, Sr-91, Te-132, Mo-99, Ba-140, La-140, Ce-144, Sb-129). It does not require the use of the physical field of the reactor to obtain prior information and establish a dispersion model. And the robustness is validated through noise analysis test. The mean absolute errors of the release rates of 11 nuclides are 15.52 %, 15.28 %, 15.70 %, 14.99 %, 14.85 %, 15.61 %, 15.96 %, 15.42 %, 15.84 %, 15.13 %, 17.72 %, which show the significant superiority of ISAO-SAELM. ISAO-SAELM model not only achieves notable advancements in accuracy but also receives validation in terms of practicality and feasibility.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.137-142
• /
• 2010

Although multi-model speech recognizer has been shown to be quite successful in noisy speech recognition, the results were based on general speech front-ends which do not take into account noise adaptation techniques. In this paper, for the accurate evaluation of the multi-model based speech recognizer, we adopted a quite noise-robust speech front-end, AFE, which was proposed by the ETSI for the noisy DSR environment. For the performance comparison, the MTR which is known to give good results in the DSR environment has been used. Also, we modified the structure of the multi-model based speech recognizer to improve the recognition performance. N reference HMMs which are most similar to the input noisy speech are used as the acoustic models for recognition to cope with the errors in the selection of the reference HMMs and the noise signal variability. In addition, multiple SNR levels are used to train each of the reference HMMs to improve the robustness of the acoustic models. From the experimental results on the Aurora 2 databases, we could see better recognition rates using the modified multi-model based speech recognizer compared with the previous method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.74-86
• /
• 2006

This paper proposes a robust and computationally efficient algorithm for automatic video object segmentation. For implementing the spatio-temporal segmentation, which aims for efficient combination of the motion segmentation and the color segmentation, an SOM-based hierarchical clustering method in which the segmentation process is regarded as clustering of feature vectors is employed. As results, problems of high computational complexity which required for obtaining exact segmentation results in conventional video object segmentation methods, and the performance degradation due to noise are significantly reduced. A measure of motion vector reliability which employs MRF-based MAP estimation scheme has been introduced to minimize the influence from the motion estimation error. In addition, a noise elimination scheme based on the motion reliability histogram and a clustering validity index for automatically identifying the number of objects in the scene have been applied. A cross projection method for effective object tracking and a dynamic memory to maintain temporal coherency have been introduced as well. A set of experiments has been conducted over several video sequences to evaluate the proposed algorithm, and the efficiency in terms of computational complexity, robustness from noise, and higher segmentation accuracy of the proposed algorithm have been proved.

• Journal of Navigation and Port Research
• /
• v.30 no.5 s.111
• /
• pp.343-349
• /
• 2006

In order to enhance the robustness against noisy environment, the previous GPS initial synchronization method of DGPS reference stations adopts not only the coherent integration method but also the non-coherent integration method. However the previous GPS initial synchronization method muses the non-coherent integration loss, which is a dominant factor among the signal acquisition losses in noisy environment. And the non-coherent integration loss increases with the strength of noise signal. In this paper, a novel GPS initial synchronization method is proposed for robust DGPS reference stations in noisy environment. This paper presents that the proposed GPS initial synchronization method suppresses the non-coherent acquisition loss. Furthermore, with regard to the mean acquisition time, it is shown that the number of the search cells of the proposed GPS initial synchronization method is much smaller than that of the previous GPS initial synchronization method Finally, through the simulation by the GPS simulator, it is seen that the GPS signal of nigh signal-to-noise ratio can be acquired under increased noise floor using the proposed GPS initial synchronization method.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.4
• /
• pp.95-103
• /
• 2009

In this paper, a generation method of transmit and receive beamforming vectors based on base station cooperation is proposed which maximizes the user SINR in mobile cellular multi-user MIMO systems. There are two main sources of interference which deteriorate the performance of the system, i.e. the inter-user interference caused by the usage of the same radio resource for multiple users in the system, and the inter-cluster interference from neighboring base stations which are not participating in cooperative transmission. The proposed scheme cancels out the inter-user interference by using the block diagonalization(BD) method, and mitigate the inter-cluster interference by using optimal transmit and receive beamforming vectors based on optimal combining(OC) with the statistic information of inter-cluster interference. We perform computer simulations to verify the performance of the proposed scheme, and compare the result to the conventional performance obtained from utilizing the receiver side information only or utilizing the information from neither sides. The performance evaluations are conducted not only over the independent MIMO channels, but over correlated MIMO channels to demonstrate the robustness of the proposed scheme over the channels with correlation among antennas.