• 대한의용생체공학회:의공학회지
• /
• 제28권2호
• /
• pp.271-279
• /
• 2007

We suggest a novel method for the evaluation of cochlear implant (CI) speech processing strategy based on neural spike train decoding. From formant trajectories of input speech and auditory nerve responses responding to the electrical pulse trains generated from a specific CI speech processing strategy, optimal linear decoding filter was obtained, and used to estimate formant trajectory of incoming speech. Performance of a specific strategy is evaluated by comparing true and estimated formant trajectories. We compared a newly-developed strategy rooted from a closer mimicking of auditory periphery using nonlinear time-varying filter, with a conventional linear-filter-based strategy. It was shown that the formant trajectories could be estimated more exactly in the case of the nonlinear time-varying strategy. The superiority was more prominent when background noise level is high, and the spectral characteristic of the background noise was close to that of speech signals. This confirms the superiority observed from other evaluation methods, such as acoustic simulation and spectral analysis.

• 대한인간공학회지
• /
• 제32권3호
• /
• pp.245-252
• /
• 2013

Objective: This paper analyzes the changes on stride parameters, joint angles, and trajectories of the body parts due to high heels during walking and explains the causal relationship between the changes and high heels. Background: This study aims to indicate the comprehensive gait changes by high heels on the whole body for women wearing high heels and researchers interested in high-heeled walking. Method: The experiment was designed in which two different shoe heel heights were used for walking (1cm, 9.8cm), and twelve women participated in the test. In the experiment, 35 points on the body were tracked to extract the stride parameters, joint angles, and trajectories of the body parts. Results: Double support time increased, but stride length decreased in high-heeled walking. The knee inflexed more at stance phase and the spine rotation became more severe. The trajectories of the pelvis, the trunk and the head presented outstanding fluctuations in the vertical direction. Conclusion: The double support time and the spine rotation were changed to compensate instability by high heels. Reduced range of motion of the ankle joint influenced on the stride length, the knee flexion, and fluctuations of the body parts. Application: This study can provide an insight of the gait changes by high heels through the entire body.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• 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.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권4호
• /
• pp.256-266
• /
• 2016

Concurrently detected and annotated abnormal events can have a significant impact on surveillance systems. By considering the specific domain of pedestrian trajectories, this paper presents two main contributions. First, as introduced in much of the work on trajectory-based anomaly detection in the literature, only information about pedestrian paths, such as direction and speed, is considered. Differing from previous work, this paper proposes a framework that deals with additional types of trajectory-based anomalies. These abnormal events take places when a person enters prohibited areas. Those restricted regions are constructed by an online learning algorithm that uses surrounding information, including detected pedestrians and background scenes. Second, a simple data-boosting technique is introduced to overcome a lack of training data; such a problem particularly challenges all previous work, owing to the significantly low frequency of abnormal events. This technique only requires normal trajectories and fundamental information about scenes to increase the amount of training data for both normal and abnormal trajectories. With the increased amount of training data, the conventional abnormal trajectory classifier is able to achieve better prediction accuracy without falling into the over-fitting problem caused by complex learning models. Finally, the proposed framework (which annotates tracks that enter prohibited areas) and a conventional abnormal trajectory detector (using the data-boosting technique) are integrated to form a united detector. Such a detector deals with different types of anomalous trajectories in a hierarchical order. The experimental results show that all proposed detectors can effectively detect anomalous trajectories in the test phase.

• 정보과학회 논문지
• /
• 제43권4호
• /
• pp.404-410
• /
• 2016

대부분의 차량에서 GPS 기반의 내비게이션을 사용함에 따라, 도로 지도를 자동적으로 생성하는 것은 중요한 연구 문제이다. 본 논문에서는 지도 정보 없이 GPS 궤적을 이용한 교차로 검출 기법을 제안한다. 이 기법은 궤적이 교차로에서 여러 갈래로 나누어지는 것을 이용한다. 이전의 교차로 검출 연구에서는 정차 빈도나 회전방향을 이용하였다. 그러나 제안하는 교차로 검출 기법은 이러한 복잡한 정보를 이용하지 않는다. 이 기법은 주어진 궤적에 대한 부분 궤적 매칭 결과를 이용하여 교차로에 진입한 궤적들이 서로 다른 도로로 나뉘어 이동하는 것을 이용한다. 강남구에서 수집된 실제 차량 궤적 1266개를 대상으로 실험하였다. 실험 결과 제안한 기법은 일반적인 십자 모양의 교차로에서 좋은 성능을 보였다. 제안 시스템은 선정한 교차로에 대해 재현율 75%, 민감도 78%의 성능을 보였다. 더 많은 궤적을 이용하면 더 신뢰할 수 있는 검출 결과를 낼 수 있을 것으로 예상된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권12호
• /
• pp.2355-2373
• /
• 2011

Vision-based vehicle detector systems are becoming increasingly important in ITS applications. Real-time operation, robustness, precision, accurate estimation of traffic parameters, and ease of setup are important features to be considered in developing such systems. Further, accurate vehicle detection is difficult in varied complex traffic environments. These environments include changes in weather as well as challenging traffic conditions, such as shadow effects and jams. To meet real-time requirements, the proposed system first applies a color background to extract moving objects, which are then tracked by considering their relative distances and directions. To achieve robustness and precision, the color background is regularly updated by the proposed algorithm to overcome luminance variations. This paper also proposes a scheme of feedback compensation to resolve background convergence errors, which occur when vehicles temporarily park on the roadside while the background image is being converged. Next, vehicle occlusion is resolved using the proposed prior split approach and through reasoning for rule-based tracking. This approach can automatically detect straight lanes. Following this step, trajectories are applied to derive traffic parameters; finally, to facilitate easy setup, we propose a means to automate the setting of the system parameters. Experimental results show that the system can operate well under various complex traffic conditions in real time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권10호
• /
• pp.4092-4107
• /
• 2015

We propose a background subtraction method for moving cameras based on trajectory classification, image segmentation and label inference. In the trajectory classification process, PCA-based outlier detection strategy is used to remove the outliers in the foreground trajectories. Combining optical flow trajectory with watershed algorithm, we propose a trajectory-controlled watershed segmentation algorithm which effectively improves the edge-preserving performance and prevents the over-smooth problem. Finally, label inference based on Markov Random field is conducted for labeling the unlabeled pixels. Experimental results on the motionseg database demonstrate the promising performance of the proposed approach compared with other competing methods.

• 대기
• /
• 제20권3호
• /
• pp.307-318
• /
• 2010

This study investigates the generation and movement of low-concentration $CO_2$ observed in Gosan during summer from 2002 to 2006. For analysis, additional $CO_2$ data in Anmyeondo, Ryori, Barrow, and Minamitorishima as well as NOAA/ESRL daily global $CO_2$ fields, background trajectories data, and 850 hPa wind fields are also used. Based on analyses using various observed data, we classified three types of low-concentration $CO_2$ in Gosan according to its origin: i) the origin of the Siberian continental, in which the consumption of $CO_2$ is active due to photosynthesis from broad forests, ii) the origin of Okhotsh and Artic seas, in which the low-concentration $CO_2$ is dominant due to high primary productivity by a plankton bloom, and iii) the origin of the Northwestern Pacific which is related to the entry of air mass from high latitudes. These results show that the low-concentration $CO_2$ observed in Gosan during summer is not originated from the Pacific oceans as known in previous studies, but originated from high latitude regions such as the Siberian continental and the Okhotsh and Artic seas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3328-3349
• /
• 2020

With rapid development of ubiquitous computing and location-based services (LBSs), human trajectory data and associated activities are increasingly easily recorded. Inappropriately publishing trajectory data may leak users' privacy. Therefore, we study publishing trajectory data while preserving privacy, denoted privacy-preserving activity trajectories publishing (PPATP). We propose S-PPATP to solve this problem. S-PPATP comprises three steps: modeling, algorithm design and algorithm adjustment. During modeling, two user models describe users' behaviors: one based on a Markov chain and the other based on the hidden Markov model. We assume a potential adversary who intends to infer users' privacy, defined as a set of sensitive information. An adversary model is then proposed to define the adversary's background knowledge and inference method. Additionally, privacy requirements and a data quality metric are defined for assessment. During algorithm design, we propose two publishing algorithms corresponding to the user models and prove that both algorithms satisfy the privacy requirement. Then, we perform a comparative analysis on utility, efficiency and speedup techniques. Finally, we evaluate our algorithms through experiments on several datasets. The experiment results verify that our proposed algorithms preserve users' privay. We also test utility and discuss the privacy-utility tradeoff that real-world data publishers may face.

• 한국환경과학회지
• /
• 제11권6호
• /
• pp.507-517
• /
• 2002

Cheeka Peak is a unique site for monitoring the background chemistry and aerosol contents of pristine marine air at mid-latitude. During long-range onshore winds that occur frequently throughout the year, it is predicted to have the cleanest air in the northern hemisphere. Measurements of CO and O$_3$were conducted at Cheeka Peak Observatory(CPO) on the northwestern tip of Washington state, USA during March 6 ∼May 29, 2001. The data have been segregated to quantify the mixing ratio of these species in the Pacific marine atmosphere. Also the marine air masses were further classified into four categories based on 10-day backward isentropic trajectories; high, mid, and low latitude and those which had crossed over the Asian industrial region. The diurnal variation of CO and O$_3$at CPO showed a similar to tendency of background measurement site. When marine air mass flowed to CPO, CO concentration was lower and O$_3$was similar or higher than those of total data. The westerly flow from ocean, not easterly from continent occurred the high concentration of CO and O$_3$at CPO. Using the trajectory segregation of marine air mass, the comparison of concentration according to latitude calculated. the CO concentration of Asian trajectory was lower than other latitudes, O$_3$concentration was higher.