• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.416-418
• /
• 2022

Glioma is a type of brain tumor that occurs in glial cells and is classified into two types: high hrade hlioma with a poor prognosis and low grade glioma. Magnetic resonance imaging (MRI) as a non-invasive method is widely used in glioma diagnosis research. Studies to obtain complementary information by combining multiple modalities to overcome the incomplete information limitation of single modality are being conducted. In this study, we developed a 3D CNN-based model that applied input-level fusion to MRI of four modalities (T1, T1Gd, T2, T2-FLAIR). The trained model showed classification performance of 0.8926 accuracy, 0.9688 sensitivity, 0.6400 specificity, and 0.9467 AUC on the validation data. Through this, it was confirmed that the grade of glioma was effectively classified by learning the internal relationship between various modalities.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.729-748
• /
• 2021

Vocal detection is one of the fundamental steps in musical information retrieval. Typically, the detection process consists of feature extraction and classification steps. Recently, neural networks are shown to outperform traditional classifiers. In this paper, we report our study on how to improve detection accuracy further by carefully choosing the parameters of the deep network model. Through experiments, we conclude that a feature-classifier model is still better than an end-to-end model. The recommended model uses a spectrogram as the input plane and the classifier is an 18-layer convolutional neural network (CNN). With this arrangement, when compared with existing literature, the proposed model improves the accuracy from 91.8% to 94.1% in Jamendo dataset. As the dataset has an accuracy of more than 90%, the improvement of 2.3% is difficult and valuable. If even higher accuracy is required, the ensemble learning may be used. The recommend setting is a majority vote with seven proposed models. Doing so, the accuracy increases by about 1.1% in Jamendo dataset.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.399-408
• /
• 2020

The construction industry is suffering from aging workers, frequent accidents, as well as low productivity. With the rapid development of information technologies in recent years, automatic construction, especially automatic cranes, is regarded as a promising solution for the above problems and attracting more and more attention. However, in practice, limited by the complexity and dynamics of construction environment, manual inspection which is time-consuming and error-prone is still the only way to recognize the search object for the operation of crane. To solve this problem, an image-processing-based automated object recognition approach is proposed in this paper, which is a fusion of Convolutional-Neutral-Network (CNN)-based and traditional object detections. The search object is firstly extracted from the background by the trained Faster R-CNN. And then through a series of image processing including Canny, Hough and Endpoints clustering analysis, the vertices of the search object can be determined to locate it in 3D space uniquely. Finally, the features (e.g., centroid coordinate, size, and color) of the search object are extracted for further recognition. The approach presented in this paper was implemented in OpenCV, and the prototype was written in Microsoft Visual C++. This proposed approach shows great potential for the automatic operation of crane. Further researches and more extensive field experiments will follow in the future.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.86-93
• /
• 2024

The development of functional magnetic resonance imaging (fMRI) has significantly contributed to mapping brain functions and understanding brain networks during rest. This paper proposes a CNN-LSTM-based classification model to classify the progression stages of Alzheimer's disease. Firstly, four preprocessing steps are performed to remove noise from the fMRI data before feature extraction. Secondly, the U-Net architecture is utilized to extract spatial features once preprocessing is completed. Thirdly, the extracted spatial features undergo LSTM processing to extract temporal features, ultimately leading to classification. Experiments were conducted by adjusting the temporal dimension of the data. Using 5-fold cross-validation, an average accuracy of 96.4% was achieved, indicating that the proposed method has high potential for identifying the progression of Alzheimer's disease by analyzing fMRI data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.5
• /
• pp.871-876
• /
• 2006

In this thesis, to accurately measure 3D face information using the spatial encoding patterns, the new algorithm to segment the pattern images from initial face pattern image is proposed. If the obtained images is non-homogeneous texture and ambiguous boundary pattern, the pattern segmentation is very difficult. Furthermore. the non-encoded areas by accumulated error are occurred. In this thesis, the FCM(fuzzy c-means) clustering method is proposed to enhance the robust encoding and segmentation rate under non-homogeneous texture and ambiguous boundary pattern. The initial parameters for experiment such as clustering class number, maximum repetition number, and error tolerance are set with 2, 100, 0.0001 respectively. The proposed pattern segmentation method increased 8-20% segmentation rate with conventional binary segmentation methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2042-2059
• /
• 2019

Digital shadow puppet has traditionally relied on expensive motion capture equipments and complex design. In this paper, a low-cost driven technique is presented, that captures human pose estimation data with simple camera from real scenarios, and use them to drive virtual Chinese shadow play in a 2.5D scene. We propose a special method for extracting human pose data for driving virtual Chinese shadow play, which is called 2.5D human pose estimation. Firstly, we use the 3D human pose estimation method to obtain the initial data. In the process of the following transformation, we treat the depth feature as an implicit feature, and map body joints to the range of constraints. We call the obtain pose data as 2.5D pose data. However, the 2.5D pose data can not better control the shadow puppet directly, due to the difference in motion pattern and composition structure between real pose and shadow puppet. To this end, the 2.5D pose data transformation is carried out in the implicit pose mapping space based on self-network and the final 2.5D pose expression data is produced for animating shadow puppets. Experimental results have demonstrated the effectiveness of our new method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.685-691
• /
• 2020

In this study, an algorithm that recognizes numbers from 0 to 9 was developed using the data obtained after tracking hand movements using the echo signal of a millimeter-wave radar sensor at 77 GHz. The echo signals obtained from the radar sensor by detecting the motion of a hand gesture revealed a cluster of irregular dots due to the difference in scattering cross-sectional area. A valid center point was obtained from them by applying a K-Means algorithm using 3D coordinate values. In addition, the obtained center points were connected to produce a numeric image. The recognition rate was compared by inputting the obtained image and an image similar to human handwriting by applying the smoothing technique to a CNN (Convolutional Neural Network) model trained with MNIST (Modified National Institute of Standards and Technology database). The experiment was conducted in two ways. First, in the recognition experiments using images with and without smoothing, average recognition rates of 77.0% and 81.0% were obtained, respectively. In the experiment of the CNN model with augmentation of learning data, a recognition rate of 97.5% and 99.0% on average was obtained in the recognition experiment using the image with and without smoothing technique, respectively. This study can be applied to various non-contact recognition technologies using radar sensors.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.31-38
• /
• 2017

In this paper, we propose a system which estimates Manhattan coordinate systems for urban scene images using a convolutional neural network (CNN). Estimating the Manhattan coordinate system from an image under the Manhattan world assumption is the basis for solving computer graphics and vision problems such as image adjustment and 3D scene reconstruction. We construct a CNN that estimates Manhattan coordinate systems based on GoogLeNet [1]. To train the CNN, we collect about 155,000 images under the Manhattan world assumption by using the Google Street View APIs and calculate Manhattan coordinate systems using existing calibration methods to generate dataset. In contrast to PoseNet [2] that trains per-scene CNNs, our method learns from images under the Manhattan world assumption and thus estimates Manhattan coordinate systems for new images that have not been learned. Experimental results show that our method estimates Manhattan coordinate systems with the median error of $3.157^{\circ}$ for the Google Street View images of non-trained scenes, as test set. In addition, compared to an existing calibration method [3], the proposed method shows lower intermediate errors for the test set.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.