• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.1D
• /
• pp.1-10
• /
• 2008

Recently, the Seoul Metropolitan Government (SMG) has initiated several urban redevelopment projects to revitalize the downtown well equipped for transit oriented development (TOD). Since, TOD should incur higher density development in our context, it has negative impacts on travel patterns, congestion, and urban environmental quality. The purpose of this study is to develop new transportation service index which can facilitate higher density TOD. This study includes relevant foreign case studies, the development of multimodal transportation index, and the impact analysis of TOD when it is applied in the downtown Seoul. In chapter III, it developed a so-called ITLOS, new multimodal transportation service index which shows the possibility of accommodating further development by integrating roadway service index with public transportation service index. The study sets ten policy scenarios by varying densities, and run the Seoul Congestion Management Model (SECOMM) to estimate the sustainable transportation impacts of TOD in the downtown. Travel speed index that only represents the availability of road capacity for development reveal that higher density development in the downtown can deteriorate traffic congestion while improving region-wide transportation level of service in Seoul. Also, it is proved that higher density development is more feasible when using ITLOS as the index because it considers not only available road capacity but subway capacity in the analysis area.

• BMB Reports
• /
• v.51 no.9
• /
• pp.427-428
• /
• 2018

Based on the piling reports of disruptions in the thalamus of patients with schizophrenia, the alteration in the thalamo-cortical system has been regarded as the core pathophysiology. As the thalamus is composed of distinctive nuclei with different cytoarchitecture and cortical connections, nuclei specific investigations have been actively conducted in post-mortem studies. In addition, the importance of early changes has been highlighted, which in turn has led to investigations of the thalamo-cortical system using non-invasive neuroimaging methods. From this perspective, the early structural changes in the thalamo-cortical system, such as the thalamo-cortical connection and nuclei specific microstructural changes (which are coherent with findings from post-mortem methods) will be briefly discussed. The main findings, which are the reduced thalamo-prefrontal connection and reduced microstructural complexity in the higher-order nuclei detected in first-episode psychosis patients, suggest the occurrence of early alterations within and between the communication hub of the brain and cortex. These findings suggest not only directions for further studies for unveiling the thalamo-cortical system related pathophysiology, but also the possibility of using the reduced microstructural complexity in the higher order nucleus as a biomarker for schizophrenia.

• Journal of Korean Society of Transportation
• /
• v.17 no.2
• /
• pp.137-147
• /
• 1999

This paper studies on the optimal bus network design in the framework of the set covering theory. The theory enables to cover passenger's loading and alighting areas as the set, and maximize the covering set as much as possible. In other words, it calculates the minimal set of the bus routes for covering whole bus passengers demand. After the optimal set of the bus routes is generated by the set covering theory, multimodal traffic equilibrium assignment is used for evaluating the generated set in terms of passenger's mode and route choice behavior. Whilst most previous works on it have been based on analyzing a specific route in a limited area, this study seeks to optimize the whole bus network.

• Journal of Navigation and Port Research
• /
• v.36 no.10
• /
• pp.883-888
• /
• 2012

Recently, the logistics industry in Asia is growing rapidly mostly with Chinese economic development. A variety of studies have been carried out to reduce the logistic cost under the situation that the global freight traffic continues to increasing. The Short Sea Shipping(SSS) system, a multi modal transport system centered around coastal shipping to realize high value-added logistics, achieved considerable success in EU. To implement the SSS system in Korea, it is necessary to develop the various essential technologies related to development of efficient ships and port facilities, including equipment for loading and unloading containers, operating and managing systems for freight terminals and technologies for tracking and securing containers. The present paper focuses on the survey of the current essential technologies available for implementation of the SSS system and suggests the direction of future development in the technologies.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.4
• /
• pp.1-13
• /
• 2018

The present study was conducted to analyze transport mode choice factors of shippers in Korea and to suggest policy implications and directions for future research. The findings showed that the research on freight mode choice factors in Korea is somewhat insufficient compared to that of other countries. In order to enhance the research, it is necessary to expand the number of studies and to strengthen the research to reflect characteristics of each transport mode. In particular, it is necessary to focus on identifying the characteristics of multimodal transport, including railway and shipping linked to truck. On the other hand, it was confirmed that the major factors influencing the choice of transport mode of shippers in Korea overlapped with foreign research cases. In addition, the implications for policy were derived when the analysis was separately conducted for Korea and other countries regarding individual transport mode and transport range. These results could be applied to various fields such as policy making to improve the efficiency of shippers' selection of transport mode and the estimation of transport mode choice model.

• Sleep Medicine and Psychophysiology
• /
• v.2 no.1
• /
• pp.23-30
• /
• 1995

Bedwetting is the most common urologic complaint among children. Wetting frequency decreases from birth to adolescence. Etiology is multifactorial : genetic, neuromuscular or urologic maturation, psychosocial stressors, toilet training, or biologic aspects. Treatment has been also multimodal : drugs to depress bladder activity, increase urethral resistance, or modulate sleep. and recently urine reduction modulation. All of these approaches reflect a lack of sufficient knowledge of the underlying pathophysiology of nocturnal enuresis. Recent researches have focused on sleep disturbances, bladder reservoir function, urine output, and a combination of the three. Sleep studies indicate that enuretic patients are normal sleepers, and enuresis can take place during any stage of sleep, but generally occurs when the bladder is filled to the equivalent of maximal daytime functional capacity. Bladder reservior capacity appears to be normal, and bladder instability is somewhat related with the pathology of nocturnal enuresis. However, enuretic patients have shown the lack of normal nocturnal increase in antidiuretic hormone levels, and nocturnal urine production increases up to 2-4 times volume of functional bladder capacity, which explains the need for bladder emptying. But behavioral approaches, especially Bell-alarm method, remain important in the treatment of primary enuresis.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.1
• /
• pp.15-26
• /
• 2014

This paper proposes a Modified Particle Swarm Optimization with Time Varying Acceleration Coefficients (MPSO-TVAC) for solving economic load dispatch (ELD) problem. Due to prohibited operating zones (POZ) and ramp rate limits of the practical generators, the ELD problems become nonlinear and nonconvex optimization problem. Furthermore, the ELD problem may be more complicated if transmission losses are considered. Particle swarm optimization (PSO) is one of the famous heuristic methods for solving nonconvex problems. However, this method may suffer to trap at local minima especially for multimodal problem. To improve the solution quality and robustness of PSO algorithm, a new best neighbour particle called 'rbest' is proposed. The rbest provides extra information for each particle that is randomly selected from other best particles in order to diversify the movement of particle and avoid premature convergence. The effectiveness of MPSO-TVAC algorithm is tested on different power systems with POZ, ramp-rate limits and transmission loss constraints. To validate the performances of the proposed algorithm, comparative studies have been carried out in terms of convergence characteristic, solution quality, computation time and robustness. Simulation results found that the proposed MPSO-TVAC algorithm has good solution quality and more robust than other methods reported in previous work.

• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.27-33
• /
• 2010

In this study, we conducted the classification experiments with GMM (Gaussian Mixture Model) from combining the extracted features by using microphone, Gyro sensor and Acceleration sensor in 9 different environment types. Existing studies of Context Aware wanted to recognize the Environment situation mainly using the Environment sound data with microphone, but there was limitation of reflecting recognition owing to structural characteristics of Environment sound which are composed of various noises combination. Hence we proposed the additional application methods which added Gyro sensor and Acceleration sensor data in order to reflect recognition agent's movement feature. According to the experimental results, the method combining Acceleration sensor data with the data of existing Environment sound feature improves the recognition performance by more than 5%, when compared with existing methods of getting only Environment sound feature data from the Microphone.

• Journal of Information Processing Systems
• /
• v.10 no.1
• /
• pp.1-22
• /
• 2014

Recent technological advances provide the opportunity to use large amounts of multimedia data from a multitude of sensors with different modalities (e.g., video, text) for the detection and characterization of criminal activity. Their integration can compensate for sensor and modality deficiencies by using data from other available sensors and modalities. However, building such an integrated system at the scale of neighborhood and cities is challenging due to the large amount of data to be considered and the need to ensure a short response time to potential criminal activity. In this paper, we present a system that enables multi-modal data collection at scale and automates the detection of events of interest for the surveillance and reconnaissance of criminal activity. The proposed system showcases novel analytical tools that fuse multimedia data streams to automatically detect and identify specific criminal events and activities. More specifically, the system detects and analyzes series of incidents (an incident is an occurrence or artifact relevant to a criminal activity extracted from a single media stream) in the spatiotemporal domain to extract events (actual instances of criminal events) while cross-referencing multimodal media streams and incidents in time and space to provide a comprehensive view to a human operator while avoiding information overload. We present several case studies that demonstrate how the proposed system can provide law enforcement personnel with forensic and real time tools to identify and track potential criminal activity.