• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.249-251
• /
• 2022

In this paper, we present machine learning to control drone flight using EEG signals. We defined takeoff, forward, backward, left movement and right movement as control targets and measured EEG signals from the frontal lobe for controlling using Fp1. Fp2 Fp2 two-channel dry electrode (NeuroNicle FX2) measuring at 250Hz sampling rate. And the collected data were filtered at 6~20Hz cutoff frequency. We measured the motion image of the action associated with each control target open for 5.19 seconds. Using Matlab's classification learner for the measured EEG signal, the triple layer neural network, logistic regression kernel, nonlinear polynomial Support Vector Machine(SVM) learning was performed, logistic regression kernel was confirmed as the highest accuracy for takeoff and forward, backward, left movement and right movement of the drone in learning by class True Positive Rate(TPR).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.413-415
• /
• 2022

Since human joints can be used as useful information for analyzing human behavior as a component of the human body, many studies have been conducted on human action recognition using joint information. However, it is a very complex problem to recognize human action that changes every moment using only each independent joint information. Therefore, an additional information extraction method to be used for learning and an algorithm that considers the current state based on the past state are needed. In this paper, we propose a human action recognition technique considering the positional relationship of connected joints and the change of the position of each joint over time. Using the pre-trained joint extraction model, position information of each joint is obtained, and bone information is extracted using the difference vector between the connected joints. In addition, a simplified neural network is constructed according to the two types of inputs, and spatio-temporal features are extracted by adding LSTM. As a result of the experiment using a dataset consisting of 9 behaviors, it was confirmed that when the action recognition accuracy was measured considering the temporal and spatial relationship features of each joint, it showed superior performance compared to the result using only single joint information.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.329-332
• /
• 2023

3D Object Detection using deep neural network has been developed a lot for obstacle detection in autonomous vehicles because it can recognize not only the class of target object but also the distance from the object. But in the case of 3D Object Detection models, the detection performance for distant objects is lower than that for nearby objects, which is a critical issue for autonomous vehicles. In this paper, we introduce a technique that increases the performance of 3D object detection models, particularly in recognizing distant objects, by generating virtual 3D vehicle data and adding it to the dataset used for model training. We used a spherical point tracing method that leverages the characteristics of 3D LiDAR sensor data to create virtual vehicles that closely resemble real ones, and we demonstrated the validity of the virtual data by using it to improve recognition performance for objects at all distances in model training.

• Journal of Sensor Science and Technology
• /
• v.32 no.2
• /
• pp.88-94
• /
• 2023

Recently, piezoelectric tactile sensors have garnered considerable attention in the field of texture recognition owing to their high sensitivity and high-frequency detection capability. Despite their remarkable potential, improving their mechanical flexibility to attach to complex surfaces remains challenging. In this study, we present a flexible piezoelectric sensor that can be bent to an extremely small radius of up to 2.5 mm and still maintain good electrical performance. The proposed sensor was fabricated by controlling the thickness that induces internal stress under external deformation. The fabricated piezoelectric sensor exhibited a high sensitivity of 9.3 nA/kPa ranging from 0 to 10 kPa and a wide frequency range of up to 1 kHz. To demonstrate real-time texture recognition by rubbing the surface of an object with our sensor, nine sets of fabric plates were prepared to reflect their material properties and surface roughness. To extract features of the objects from the detected sensing data, we converted the analog dataset to short-term Fourier transform images. Subsequently, texture recognition was performed using a convolutional neural network with a classification accuracy of 97%.

• Journal of Korean Neurosurgical Society
• /
• v.66 no.1
• /
• pp.53-62
• /
• 2023

Objective : Deep learning is a machine learning approach based on artificial neural network training, and object detection algorithm using deep learning is used as the most powerful tool in image analysis. We analyzed and evaluated the diagnostic performance of a deep learning algorithm to identify skull fractures in plain radiographic images and investigated its clinical applicability. Methods : A total of 2026 plain radiographic images of the skull (fracture, 991; normal, 1035) were obtained from 741 patients. The RetinaNet architecture was used as a deep learning model. Precision, recall, and average precision were measured to evaluate the deep learning algorithm's diagnostic performance. Results : In ResNet-152, the average precision for intersection over union (IOU) 0.1, 0.3, and 0.5, were 0.7240, 0.6698, and 0.3687, respectively. When the intersection over union (IOU) and confidence threshold were 0.1, the precision was 0.7292, and the recall was 0.7650. When the IOU threshold was 0.1, and the confidence threshold was 0.6, the true and false rates were 82.9% and 17.1%, respectively. There were significant differences in the true/false and false-positive/false-negative ratios between the anterior-posterior, towne, and both lateral views (p=0.032 and p=0.003). Objects detected in false positives had vascular grooves and suture lines. In false negatives, the detection performance of the diastatic fractures, fractures crossing the suture line, and fractures around the vascular grooves and orbit was poor. Conclusion : The object detection algorithm applied with deep learning is expected to be a valuable tool in diagnosing skull fractures.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.150-159
• /
• 2022

This paper presents an implementation of detecting whether a helmet is worn and there is a fall accident through individual image analysis in real-time from extracting the image objects of several workers active in the industrial field. In order to detect image objects of workers, YOLO, a deep learning-based computer vision model, was used, and for whether a helmet is worn or not, the extracted images with 5,000 different helmet learning data images were applied. For whether a fall accident occurred, the position of the head was checked using the Pose real-time body tracking algorithm of Mediapipe, and the movement speed was calculated to determine whether the person fell. In addition, to give reliability to the result of a falling accident, a method to infer the posture of an object by obtaining the size of YOLO's bounding box was proposed and implemented. Finally, Telegram API Bot and Firebase DB server were implemented for notification service to administrators.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.2
• /
• pp.94-101
• /
• 2023

A deep neural network composed of encoders and decoders, such as U-Net, used for speech enhancement, concatenates the encoder to the decoder through skip-connection. Skip-connection helps reconstruct the enhanced spectrum and complement the lost information. The features of the encoder and the decoder connected by the skip-connection are incompatible with each other. In this paper, for complex-valued spectrum based speech enhancement, Self-Attention (SA) method is applied to skip-connection to transform the feature of encoder to be compatible with the features of decoder. SA is a technique in which when generating an output sequence in a sequence-to-sequence tasks the weighted average of input is used to put attention on subsets of input, showing that noise can be effectively eliminated by being applied in speech enhancement. The three models using encoder and decoder features to apply SA to skip-connection are studied. As experimental results using TIMIT database, the proposed methods show improvements in all evaluation metrics compared to the Deep Complex U-Net (DCUNET) with skip-connection only.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.167-173
• /
• 2023

As research has been published to predict future data using regression analysis or artificial intelligence as a method of analyzing economic indicators. In this study, we designed a system that predicts prospective futures prices using artificial intelligence that utilizes topic probability data obtained from past news articles using topic modeling. Topic probability distribution data for each news article were obtained using the Latent Dirichlet Allocation (LDA) method that can extract the topic of a document from past news articles via unsupervised learning. Further, the topic probability distribution data were used as the input for a Long Short-Term Memory (LSTM) network, a derivative of Recurrent Neural Networks (RNN) in artificial intelligence, in order to predict prospective futures prices. The method proposed in this study was able to predict the trend of futures prices. Later, this method will also be able to predict the trend of prices for derivative products like options. However, because statistical errors occurred for certain data; further research is required to improve accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.413-420
• /
• 2023

For a long time, researchers have presented excellent results in the field of image retrieval due to many studies on CBIR. However, there is still a semantic gap between these search results for images and human perception. It is still a difficult problem to classify images with a level of human perception using a small number of images. Therefore, this paper proposes an image classification model using deep learning-based transfer learning to minimize the semantic gap between images of people and search systems in image retrieval. As a result of the experiment, the loss rate of the learning model was 0.2451% and the accuracy was 0.8922%. The implementation of the proposed image classification method was able to achieve the desired goal. And in deep learning, it was confirmed that the CNN's transfer learning model method was effective in creating an image database by adding new data.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.8
• /
• pp.117-127
• /
• 2007

Slope stability analysis is a geotechnical engineering problem characterized by many sources of uncertainty. Some of them are connected to the uncertainties of soil properties involved in the analysis. In this paper, a numerical procedure for integrating commercial finite difference method into probabilistic analysis of slope stability is presented. Since the limit-state function cannot be expressed in an explicit form, the ANN-based response surface method is adopted to approximate the limit-state function and the first-, second-order reliability method and the Monte Carlo simulation technique are used to calculate the probability of failure. Probabilistic stability assessments for a hypothetical two-layer slope and the Sugar Creek embankment were performed to verify the application potential to the slope stability problems. The examples show the successful implementation and the possibility of the extension of the proposed procedure to the variety of geotechnical engineering problems.