• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.455-457
• /
• 2019

In this paper we study the effect of decomposed spatiotemporal convolutions for action recognition in videos. Our motivation emerges from the empirical observation that spatial convolution applied on solo frames of the video provide good performance in action recognition. In this research we empirically show the accuracy of factorized convolution on individual frames of video for action classification. We take 3D ResNet-18 as base line model for our experiment, factorize its 3D convolution to 2D (Spatial) and 1D (Temporal) convolution. We train the model from scratch using Kinetics video dataset. We then fine-tune the model on UCF-101 dataset and evaluate the performance. Our results show good accuracy similar to that of the state of the art algorithms on Kinetics and UCF-101 datasets.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.67-70
• /
• 2018

Object detection and tracking is an exciting and interesting research area in the field of computer vision, and its technologies have been widely used in various application systems such as surveillance, military, and augmented reality. This paper proposes and implements a novel and more robust object recognition and tracking system to localize and track multiple objects from input images, which estimates target state using the likelihoods obtained from multiple CNNs. As the experimental result, the proposed algorithm is effective to handle multi-modal target appearances and other exceptions.

• Structural Monitoring and Maintenance
• /
• v.6 no.3
• /
• pp.173-190
• /
• 2019

Steel-confined reinforced concrete (SCRC) columns feature highly complex and invisible mechanisms that make damage evaluation and pattern recognition difficult. In the present article, the prevailing acoustic emission (AE) technique was applied to monitor and evaluate the damage process of steel-confined RC columns in a quasi-static test. AE energy-based indicators, such as index of damage and relax ratio, were proposed to trace the damage progress and quantitatively evaluate the damage state. The fuzzy C-means algorithm successfully discriminated the AE data of different patterns, validity analysis guaranteed cluster accuracy, and principal component analysis simplified the datasets. A detailed statistical investigation on typical AE features was conducted to relate the clustered AE signals to micro mechanisms and the observed damage patterns, and differences between steel-confined and unconfined RC columns were compared and illustrated.

• Proceedings of the KIEE Conference
• /
• 1988.11a
• /
• pp.111-114
• /
• 1988

With the increase of size and complicacy of power systems, distribution system need to operate effectively for high reliability. In order to achieve this purpose, the study which apply expert system to operating plan, restoration on fault and distribution system operating, has developing actively. The essential element of the study is system line state which make a system observe. The development of expert system on power system operation make a system be able to judge state of loading and looping system line, related current direction, substation, and distribution line, atomatically by breaker operation. Finally, this paper developed expert system which decides itself atomatically by rules for deciding system line state.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.777-782
• /
• 2011

Neural network technique is widely employed in the fields of signal processing, control systems, pattern recognition, etc. Learning of neural networks is an important procedure to accomplish dynamic system modeling. This paper presents a novel learning approach for differential neural network models based on the Kalman-Bucy filter theory. We construct an augmented state vector including original neural state and parameter vectors and derive a state estimation rule avoiding gradient function terms which involve to the conventional neural learning methods such as a back-propagation approach. We carry out numerical simulation to evaluate the proposed learning approach in nonlinear system modeling. By comparing to the well-known back-propagation approach and Kalman-Bucy filtering, its superiority is additionally proved under stochastic system environments.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.6
• /
• pp.87-93
• /
• 2017

In this paper, we design a small low power single channel ECG(Electrocardiogram) system of Chest Belt type with fiber-type electrodes to measure emotional state change of game addict. HRV(Heart Rate Variability) is analyzed through heart rate signal measurement and the psychological stress state is judged by using it. And it verifies its effectiveness through prototype. First, we design HR measurement module through low power MCU(Micro Controller Unit) and implement prototype level measurement system. The results showed that the difference between the addiction group and the general group was confirmed and that the system was effective. The result of this study can be used for health management such as reduction of stress of the user through music and breathing that lowers the stress by detecting the stress state of the general person or the chronic ill person.

• Journal of Sensor Science and Technology
• /
• v.22 no.1
• /
• pp.54-64
• /
• 2013

In this study, we developed a falling recognition system to transmit SMS data through CDMA communication using a three axises acceleration sensor and a two axises gyro sensor. 5 healthy men were selected into a control group, and the fall recognition system using the three axises acceleration sensor and the two axises gyro sensor was devised to conduct an experiment. The system was attached to the upper of their sternum. According to the experiment protocol, the experiment was carried out 3 times repeatedly divided into 3 specific protocols: falling during gait, falling in stopped state, and falling in everyday life. Data obtained in the falling recognition system and LabVIEW 8.5 were used to decide if falling corresponds to that regulated in an analysis program applying an algorithm proposed in this study. In addition, results from falling recognition were transmitted to designated cellular phone in a SMS (Shot Message Service) form. These research results show that an erroneous detection rate of falling reached 19% in applying an acceleration signal only; 6% in applying an angular velocity; and 2% in applying a proposed algorithm. Such finding suggests that an erroneous detection rate of falling is improved when the proposed algorithm is applied incorporated with acceleration and angular velocity. In this study therefore, we proposed that a falling recognition system implemented in this study can make a contribution to the recognition of falling of the aged or the disabled.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.924-942
• /
• 2020

The facial expression is diverse and various among persons due to the impact of the psychology factor. Whilst the facial action is comparatively steady because of the fixedness of the anatomic structure. Therefore, to improve performance of the action unit recognition will facilitate the facial expression recognition and provide profound basis for the mental state analysis, etc. However, it still a challenge job and recognition accuracy rate is limited, because the muscle movements around the face are tiny and the facial actions are not obvious accordingly. Taking account of the moving of muscles impact each other when person express their emotion, we propose to make full use of co-occurrence relationship among action units (AUs) in this paper. Considering the dynamic characteristic of AUs as well, we adopt the 3D Convolutional Neural Network(3DCNN) as base framework and proposed to recognize multiple action units around brows, nose and mouth specially contributing in the emotion expression with putting their co-occurrence relationships as constrain. The experiments have been conducted on a typical public dataset CASME and its variant CASME2 dataset. The experiment results show that our proposed AU co-occurrence constraint 3DCNN based AU recognition approach outperforms current approaches and demonstrate the effectiveness of taking use of AUs relationship in AU recognition.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.67-77
• /
• 2004

The recent research has been focused on fusion of audio and visual features for reliable speech recognition in noisy environments. In this paper, we propose a neural network based model of robust speech recognition by integrating audio, visual, and contextual information. Bimodal Neural Network(BMNN) is a multi-layer perception of 4 layers, each of which performs a certain level of abstraction of input features. In BMNN the third layer combines audio md visual features of speech to compensate loss of audio information caused by noise. In order to improve the accuracy of speech recognition in noisy environments, we also propose a post-processing based on contextual information which are sequential patterns of words spoken by a user. Our experimental results show that our model outperforms any single mode models. Particularly, when we use the contextual information, we can obtain over 90% recognition accuracy even in noisy environments, which is a significant improvement compared with the state of art in speech recognition. Our research demonstrates that diverse sources of information need to be integrated to improve the accuracy of speech recognition particularly in noisy environments.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.711-716
• /
• 2003

This paper proposes the method to select the number of optimal mixtures in each state in Continuous Density HMM (Hidden Markov Models), Previously, researchers used the same number of mixture components in each state of HMM regardless spectral characteristic of speaker, To model each speaker as accurately as possible, we propose to use a different number of mixture components for each state, Selection of mixture components considered the probability value of mixture by each state that affects much parameter estimation of continuous density HMM, Also, we use PCA (principal component analysis) to reduce the correlation and obtain the system' stability when it is reduced the number of mixture components, We experiment it when the proposed method used average 10% small mixture components than the conventional HMM, When experiment result is only applied selection of mixture components, the proposed method could get the similar performance, When we used principal component analysis, the feature vector of the 16 order could get the performance decrease of average 0,35% and the 25 order performance improvement of average 0.65%.