• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.201-209
• /
• 2017

This paper is a smartphone object recognition system using hierarchical convolutional neural network. The overall configuration is a method of communicating object information to the smartphone by matching the collected data by connecting the smartphone and the server and recognizing the object to the convergence neural network in the server. It is also compared to a hierarchical convolutional neural network and a fractional convolutional neural network. Hierarchical convolutional neural networks have 88% accuracy, fractional convolutional neural networks have 73% accuracy and 15%p performance improvement. Based on this, it shows possibility of expansion of T-Commerce market connected with smartphone and broadcasting media.

• Journal of Korea Multimedia Society
• /
• v.21 no.9
• /
• pp.1062-1067
• /
• 2018

Conventional active sonar technology has relied heavily on the hearing of sonar operator, but recently, many techniques for automatic detection and classification have been studied. In this paper, we extract the image data from the spectrogram of the active sonar signal and classify the extracted data using CNN(convolutional neural networks), which has recently presented excellent performance improvement in the field of pattern recognition. First, we divided entire data set into eight classes depending on the ratio containing the target. Then, experiments were conducted to classify the eight classes data using proposed CNN structure, and the results were analyzed.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.45-54
• /
• 2018

This paper presents a vision-based fall detection system to automatically monitor and detect people's fall accidents, particularly those of elderly people or patients. For video analysis, the system should be able to extract both spatial and temporal features so that the model captures appearance and motion information simultaneously. Our approach is based on 3-dimensional convolutional neural networks, which can learn spatiotemporal features. In addition, we adopts a thermal camera in order to handle several issues regarding usability, day and night surveillance and privacy concerns. We design a pan-tilt camera with two actuators to extend the range of view. Performance is evaluated on our thermal dataset: TCL Fall Detection Dataset. The proposed model achieves 90.2% average clip accuracy which is better than other approaches.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.352-368
• /
• 2021

Sign-in point of interest (POI) are extremely sparse in location-based social networks, hindering recommendation systems from capturing users' deep-level preferences. To solve this problem, we propose a content-aware POI recommendation algorithm based on a convolutional neural network. First, using convolutional neural networks to process comment text information, we model location POI and user latent factors. Subsequently, the objective function is constructed by fusing users' geographical information and obtaining the emotional category information. In addition, the objective function comprises matrix decomposition and maximisation of the probability objective function. Finally, we solve the objective function efficiently. The prediction rate and F1 value on the Instagram-NewYork dataset are 78.32% and 76.37%, respectively, and those on the Instagram-Chicago dataset are 85.16% and 83.29%, respectively. Comparative experiments show that the proposed method can obtain a higher precision rate than several other newer recommended methods.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.803-816
• /
• 2023

Explainable artificial intelligence is a method that explains how a complex model (e.g., a deep neural network) yields its output from a given input. Recently, graph-type data have been widely used in various fields, and diverse graph neural networks (GNNs) have been developed for graph-type data. However, methods to explain the behavior of GNNs have not been studied much, and only a limited understanding of GNNs is currently available. Therefore, in this paper, we propose an explanation method for node classification using graph convolutional networks (GCNs), which is a representative type of GNN. The proposed method finds out which features of each node have the greatest influence on the classification of that node using GCN. The proposed method identifies influential features by backtracking the layers of the GCN from the output layer to the input layer using the gradients. The experimental results on both synthetic and real datasets demonstrate that the proposed explanation method accurately identifies the features of each node that have the greatest influence on its classification.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.194-198
• /
• 2017

In this paper, we propose a revised Deep Convolutional Neural Network (DCNN) model to extract Protein-Protein Interaction (PPIs) from the scientific literature. The proposed method has the merit of improving performance by applying various global features in addition to the simple lexical features used in conventional relation extraction approaches. In the experiments using AIMed, which is the most famous collection used for PPI extraction, the proposed model shows state-of-the art scores (78.0 F-score) revealing the best performance so far in this domain. Also, the paper shows that, without conducting feature engineering using complicated language processing, convolutional neural networks with embedding can achieve superior PPIE performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.11a
• /
• pp.17-18
• /
• 2016

본 논문에서는 딥러닝 기술 중의 하나인 CNN(Convolutional Neural Network) 기반의 얼굴 표정 인식 기법을 제안한다. 제안한 기법에서는 획득한 여섯 가지 주요 표정의 얼굴영상들을 학습 데이터로 이용할 때 분류 성능을 저해시키는 과적합(over-fitting) 문제를 해결하기 위해서 데이터 증대 기법(data augmentation)을 적용한다. 또한 기존의 CNN 구조에서 convolutional layer 및 node의 수를 변경하여 학습 파라미터 수를 대폭 감소시킬 수 있다. 실험 결과 제안하는 데이터 증대 기법 및 개선한 구조가 높은 얼굴 표정 분류 성능을 보여준다는 것을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.21 no.11
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.573-591
• /
• 2019

Classification criteria for Korean alphabet (Hangul) fonts are undeveloped in comparison to numerical classification systems for Roman alphabet fonts. This study finds important features that distinguish typeface styles in order to help develop numerical criteria for Hangul font classification. We find features that determine the characteristics of the two different styles using a convolutional neural network to create a model that analyzes the learned filters as well as distinguishes between serif and sans-serif styles.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2826-2840
• /
• 2018

Traditional methods based active contours or region merging are powerless in processing images with blurring border or hair occlusion. In this paper, a structure based convolutional neural networks is proposed to solve segmentation of skin lesion image. The structure mainly consists of two networks which are segmentation net and discrimination net. The segmentation net is designed based U-net that used to generate the mask of lesion, while the discrimination net is designed with only convolutional layers that used to determine whether input image is from ground truth labels or generated images. Images were obtained from "Skin Lesion Analysis Toward Melanoma Detection" challenge which was hosted by ISBI 2016 conference. We achieved segmentation average accuracy of 0.97, dice coefficient of 0.94 and Jaccard index of 0.89 which outperform the other existed state-of-the-art segmentation networks, including winner of ISBI 2016 challenge for skin melanoma segmentation.