• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3599-3619
• /
• 2019

In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video features and unable to investigate the level of contribution of both (Static and Motion) components. Our work highlights this problem and proposes Static-Motion fused features descriptor (SMFD), which intelligently leverages both static and motion features in the form of descriptor. First, static features are learned by two-stream 3D convolutional neural network. Second, trajectories are extracted by tracking key points and only those trajectories have been selected which are located in central region of the original video frame in order to to reduce irrelevant background trajectories as well computational complexity. Then, shape and motion descriptors are obtained along with key points by using SIFT flow. Next, cholesky transformation is introduced to fuse static and motion feature vectors to guarantee the equal contribution of all descriptors. Finally, Long Short-Term Memory (LSTM) network is utilized to discover long-term temporal dependencies and final prediction. To confirm the effectiveness of the proposed approach, extensive experiments have been conducted on three well-known datasets i.e. UCF101, HMDB51 and YouTube. Findings shows that the resulting recognition system is on par with state-of-the-art methods.

• Proceedings of the KIEE Conference
• /
• 2008.04a
• /
• pp.209-210
• /
• 2008

본 논문에서는 제어기에 승산형 섭동을 가지는 제어기와 이산시간 특이시스템을 안정화시키는 비약성 제어기 설계방법을 제시한다. 강인 비약성 제어기가 존재할 조건과 제어기 설계방법을 블록최적화가 가능한 선형 행렬부등식 접근방법으로 제안한다. 또한, 제어기의 약성 성도를 표시하는 비약성 척도를 동시에 계산함으로 승산형 섭동의 제어기 최대 변동정도를 제시한다. 제안한 비약성 제어기는 제어기의 이득 변동에도 불구하고 이산 시간 특이시스템의 강인 안정성을 보장한다.

• Journal of Intelligence and Information Systems
• /
• v.12 no.3
• /
• pp.67-82
• /
• 2006

We propose the HBEM(Hybrid Behavior Evolution Model) composed of rule classification and evolutionary neural network using rule descriptor and link descriptor for evolutionary behavior of virtual robots. In our model, two levels of the knowledge of behaviors were represented. In the upper level, the representation was improved using rule and link descriptors together. And then in the lower level, behavior knowledge was represented in form of bit string and learned adapting their chromosomes by the genetic operators. A virtual robot was composed by the learned chromosome which had the best fitness. The composed virtual robot perceives the surrounding situations and they were classifying the pattern through rules and processing the result in neural network and behaving. To evaluate our proposed model, we developed HBES(Hybrid Behavior Evolution System) and adapted the problem of gathering food of the virtual robots. In the results of testing our system, the learning time was fewer than the evolution neural network of the condition which was same. And then, to evaluate the effect improving the fitness by the rules we respectively measured the fitness adapted or not about the chromosomes where the learning was completed. In the results of evaluating, if the rules were not adapted the fitness was lowered. It showed that our proposed model was better in the learning performance and more regular than the evolutionary neural network in the behavior evolution of the virtual robots.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.2
• /
• pp.192-196
• /
• 2004

A combined optimal design problem is discussed taking a 3-D truss structure as a design object. We use descriptor forms for a controlled object and a generalized plant because the structural parameters appear naturally in these forms. We consider not only the minimum weight design problem for the structure, but also the suppression problem of the effect of disturbances for the control system as the purpose of the design. A numerical example shows the validity of combined optimal design of the structure and control systems. We also consider the validity of the sensor-actuator collocation for the control system design in this paper.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.637-644
• /
• 2011

Being digitalized, the music can be easily purchased and delivered to the users. However, there is still some difficulty to find the music which fits to someone's taste using traditional music information search based on musician, genre, tittle, album title and so on. In order to reduce the difficulty, the contents-based or the emotion-based music retrieval has been proposed and developed. In this paper, we propose new method to determine the importance of MPEG-7 low-level audio descriptors which are multi-dimensional vectors for the emotion-based music retrieval. We measured the mutual similarities of musics which represent a pair of emotions expressed by opposite meaning in terms of each multi-dimensional descriptor. Then rough approximation, and inter- and intra similarity ratio from the similarity relation are used for determining the importance of a descriptor, respectively. The set of weights based on the importance decides the aggregated similarity measure, by which emotion-based music retrieval can be achieved. The proposed method shows better result than previous method in terms of the average number of satisfactory musics in the experiment emotion-based retrieval based on content-based search.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.4
• /
• pp.293-298
• /
• 2011

In this paper, we propose a new image descriptor, that is, a rotation invariant histogram of oriented gradients (RIHOG). RIHOG overcomes a disadvantage of the histogram of oriented gradients (HOG), which is very sensitive to image rotation. The HOG only uses magnitude values of a pixel without considering neighboring pixels. The RIHOG uses the accumulated relative magnitude values of corresponding relative orientation calculated with neighboring pixels, which has an effect on reducing the sensitivity to image rotation. The performance of RIHOG is verified via the index of classification and classification of Brodatz texture data.

• Journal of Korea Society of Industrial Information Systems
• /
• v.4 no.3
• /
• pp.90-94
• /
• 1999

To prevent the congruent output of the digital psuedo-random transformation from giving the same randomness, a transformation of seemingly random deterministic process, called Chaotic transformation, is introduced. Passing through a Chaotic transformation, each event(descriptor) will produce chaotic random sequences. haotic transformation is designed on the basis of deterministic chaos function and also can be realized by simple hardware like shift registers. The circuit of chaotic transformation implemented with the shift registers is presented and the chaotic behavior of suggested circuit is explained with the characteristics of saw-tooth function with the chaotic behavior.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.1
• /
• pp.111-119
• /
• 2009

For daily life interaction with human, robots need the capability of encoding and storing cognitive information and retrieving it contextually. In this paper, spatiotemporal grounding of cognitive information for a language based cognitive system is presented. The cognitive information of the event occurred at a robot is described with a sentence, stored in a memory, and retrieved contextually. Each sentence is parsed, discriminated with the functional type of it, and analyzed with argument structure for connecting to cognitive information. With the proposed grounding, the cognitive information is encoded to sentence form and stored in sentence memory with object descriptor. Sentences are retrieved for answering questions of human by searching temporal information from the sentence memory and doing spatial reasoning in schematic imagery. An experiment shows the feasibility and efficiency of the spatiotemporal grounding for advanced service robot.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.240-248
• /
• 2014

We present a robust speaker identification algorithm that uses novel features based on soft bag-of-word representation and a simple Naive Bayes classifier. The bag-of-words (BoW) based histogram feature descriptor is typically constructed by summarizing and identifying representative prototypes from low-level spectral features extracted from training data. In this paper, we define a generalization of the standard BoW. In particular, we define three types of BoW that are based on crisp voting, fuzzy memberships, and possibilistic memberships. We analyze our mapping with three common classifiers: Naive Bayes classifier (NB); K-nearest neighbor classifier (KNN); and support vector machines (SVM). The proposed algorithms are evaluated using large datasets that simulate medical crises. We show that the proposed soft bag-of-words feature representation approach achieves a significant improvement when compared to the state-of-art methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.1
• /
• pp.33-39
• /
• 2010

The interaction of emotion is an important factor in Human-Robot Interaction(HRI). This requires a contextual appraisal of emotion extracting the emotional information according to the events happened from past to present. In this paper an emotion appraisal system based on the cognitive context is presented. Firstly, a conventional emotion appraisal model is simplified to model a contextual emotion appraisal which defines the types of emotion appraisal, the target of the emotion induced from analyzing emotional verbs, and the transition of emotions in the context. We employ a language based cognitive system and its sentential memory and object descriptor to define the type and target of emotion and to evaluate the emotion varying with the process of time with the a priori emotional evaluation of targets. In a experimentation, we simulate the proposed emotion appraisal system with a scenario and show the feasibility of the system to HRI.