• Annual Conference of KIPS
• /
• 2012.11a
• /
• pp.468-471
• /
• 2012

음성을 통한 자동화된 감정 인식은 편리하고 다양한 서비스를 제공할 수 있어 중요한 연구분야라고 할 수 있다. 기계학습의 다양한 알고리즘을 사용하여 감정을 인식하는 연구가 진행되어 왔지만 그 성능은 아직 초보적 단계를 벋어나지 못하고 있는 실정이다. 앞선 연구에서 우리는 비감독 학습 방법으로 감성을 그룹화 하고 이것을 이용하여 다시 감독 학습을 하는 시스템을 소개 하였다. 본 연구에서 우리는 감독 학습 방법에서 사용했던 오류 역전파 알고리즘을 support vector machine(SVM) 으로 변경하고 몇 가지 구조를 변경하여 기능을 개선하였다. 실험을 통하여 성능을 측정하였으며 어느 정도 개선된 결과를 얻을 수 있었다.

• Journal of Korean Clinical Health Science
• /
• v.6 no.2
• /
• pp.1097-1105
• /
• 2018

Purpose: Loneliness is an extremely subjective experience that is influenced by life experiences and circumstances. This study attempted to provide basic data for the development of nursing intervention strategies to understand the concept of loneliness and to reduce loneliness on various topics. Methods: The research analysis method is based on the framework of concept analysis proposed by Walker and Avant (1988). Results: The results of this study are as follows: 1) Self-alienation 2) Isolation of human beings 3) Psychological damage reaction 4) Pain 5) Loneliness is the loss of a comfortable "frame". The prerequisites can be divided into personal characteristics and situational characteristics. Empirical criteria include intimate others, lack of social relationships or problems, family and friendship, belonging, recognition or expression of loneliness, emotional state changes and changes in health behavior, and physical symptoms. Conclusions: Loneliness is an important indicator of well-being and a cause of physical and mental illnesses, so nurses facing various subjects should be able to recognize the signs and symptoms of loneliness. By promoting and sustaining their interest, they should be able to enjoy lonely people.

• Electronics and Telecommunications Trends
• /
• v.33 no.6
• /
• pp.107-117
• /
• 2018

In recent years, with the development of autonomous driving technology, high-performance artificial intelligence computing hardware platforms have been developed that can process multi-sensor data, object recognition, and vehicle control for autonomous vehicles. Most of these hardware platforms have been developed overseas, such as NVIDIA's DRIVE PX, Audi's zFAS, Intel GO, Mobile Eye's EyeQ, and BAIDU's Apollo Pilot. In Korea, however, ETRI's artificial intelligence computing platform has been developed. In this paper, we discuss the specifications, structure, performance, and development status centering on hardware platforms that support autonomous driving rather than the overall contents of autonomous driving technology.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.459-461
• /
• 2019

The location estimation algorithm in the existing wireless network uses a base station to estimate the absolute location of three or more in the state where the terminal is fixed. However, this paper suggests a location recognition algorithm that uses a mobile terminal to estimate the location of a mobile base station using a traverse technique using a three-way estimation.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.571-585
• /
• 2021

Applications for object detection are expanding as it is automated through artificial intelligence-based processing, such as deep learning, on a large volume of images and videos. High dependence on training data and a non-transparent way to find answers are the common characteristics of deep learning. Attacks on training data and training models have emerged, which are closely related to the nature of deep learning. Privacy, integrity, and robustness for the extracted information are important security issues because deep learning enables object recognition in images and videos. This paper summarizes the security issues that need to be addressed for future applications and analyzes the state-of-the-art security studies related to robustness, privacy, and integrity of object detection for images and videos.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.7-11
• /
• 2022

Object detection technology is one of the main research topics in the field of computer vision and has established itself as an essential base technology for implementing various vision systems. Recent DNN (Deep Neural Networks)-based algorithms achieve much higher recognition accuracy than traditional algorithms. However, it is well-known that the DNN model inference operation requires a relatively high computational power. In this paper, we analyze the inference time complexity of the state-of-the-art object detection architecture Yolov7 in various environments. Specifically, we compare and analyze the time complexity of four types of the Yolov7 model, YOLOv7-tiny, YOLOv7, YOLOv7-X, and YOLOv7-E6 when performing inference operations using CPU and GPU. Furthermore, we analyze the time complexity variation when inferring the same models using the Pytorch framework and the Onnxruntime engine.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• pp.524-543
• /
• 2022

Correct facade image parsing is essential to the semantic understanding of outdoor scenes. Unfortunately, there are often various occlusions in front of buildings, which fails many existing methods. In this paper, we propose an end-to-end deep network for facade parsing with occlusions. The network learns to decompose an input image into visible and invisible parts by occlusion reasoning. Then, a context aggregation module is proposed to collect nonlocal cues for semantic segmentation of the visible part. In addition, considering the regularity of man-made buildings, a repetitive pattern completion branch is designed to infer the contents in the invisible regions by referring to the visible part. Finally, the parsing map of the input facade image is generated by fusing the results of the visible and invisible results. Experiments on both synthetic and real datasets demonstrate that the proposed method outperforms state-of-the-art methods in parsing facades with occlusions. Moreover, we applied our method in applications of image inpainting and 3D semantic modeling.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.97-100
• /
• 2021

Light field (LF) superpixel segmentation aims to group the similar pixels not only in the single image but also in the other views to improve the computational efficiency of further applications like object detection and pattern recognition. Among the state-of-the-art methods, there is an approach to segment the LF images while enforcing the view consistency. However, it leaves too much noise and inaccuracy in the shape of superpixels. In this paper, we modify the process of the clustering step. Experimental results demonstrate that our proposed method outperforms the existing method in terms of view-consistency.