• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.773-778
• /
• 2009

This paper studied the training methods less affected by the emotional variation for the development of the robust speech recognition system. For this purpose, the effect of emotional variations on the speech signal were studied using speech database containing various emotions. The performance of the speech recognition system trained by using the speech signal containing no emotion is deteriorated if the test speech signal contains the emotions because of the emotional difference between the test and training data. In this study, it is observed that vocal tract length of the speaker is affected by the emotional variation and this effect is one of the reasons that makes the performance of the speech recognition system worse. In this paper, vocal tract normalization method is used to develop the robust speech recognition system for emotional variations. Experimental results from the isolated word recognition using HMM showed that the vocal tract normalization method reduced the error rate of the conventional recognition system by 41.9% when emotional test data was used.

• Journal of the Korean Society of Safety
• /
• v.34 no.1
• /
• pp.82-89
• /
• 2019

The importance of aviation safety has been emphasized recently due to the development of aviation industry. Despite the efforts of each country and the improvement of screening equipment, screening tasks are still difficult and detection failures are frequent. The purpose of this study was to examine the effect of feedback on improving signal detection performance applying a Simulated Baggage Screening Program(SBSP) for improving aviation safety. SBSP consists of three parts: image combination, option setting and experiment. The experimental images were color-coded to reflect the items' transmittance of the x-rays and could be combined as researchers' need. In the option, the researcher could set up the information, incentive, and comments needed for training to be delivered on a number of tasks and times. Experiment was conducted using SBSP and participant's performance information (hit, missed, false alarms, correct rejection, reaction time, etc.) was automatically calculated and stored. A total of 50 participants participated and each participant was randomly assigned to feedback and non-feedback group. Participants performed a total of 200 tasks and 20(10%) contained target object(gun and knife). The results showed that when the feedback was provided, the hit, correct rejection ratio and d′ were increased, however, the false alarms and miss decreased. However, there was no significant difference in response criteria(${\beta}$). In addition, implications, limitations of this study and future research were discussed.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.6 no.1
• /
• pp.7-17
• /
• 1997

During the past decade, there were many well-established theories for the adaptive control of linear systems, but there exists relatively little general theory for the adaptive control of nonlinear systems. Adaptive control technique is essential for providing a stable and robust performance for application of industrial robot control. Neural network computing methods provide one approach to the development of adaptive and learning behavior in robotic system for manufacturing. Computational neural networks have been demonstrated which exhibit capabilities for supervised learning, matching, and generalization for problems on an experimental scale. Supervised learning could improve the efficiency of training and development of robotic systems. In this paper, a new scheme of adaptive-neuro control system to implement real-time control of robot manipulator using digital signal processors is proposed. Digital signal processors, DSPs, are micro-processors that are developed particularly for fast numerical computations involving sums and products of variables. The proposed neuro control algorithm is one of learning a model based error back-propagation scheme using Lyapunov stability analysis method. The proposed adaptive-neuro control scheme is illustrated to be an efficient control scheme for implementation of real-time control for SCARA robot with four-axes by experiment.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.32A no.1
• /
• pp.14-25
• /
• 1995

The main contribution of this paper can be summarized in two items as follws. Firstly, a modelling of mobile communication channel with Rayleigh fading characteristics is presented. Actual signal environments can be approximated as being real measurements by a proper mathematical representation of fluctuation of channel parameters due to Doppler effect, that is determined by the relative speed between transmitter and receiver, and noises, that vary at each sampling time. Secondly, an alternative procedure of synthesizing an adaptive equalizers is presented for recovering original signals that have been corrupted through the modelled channel. In order to compute the optimal tap coefficients for a high speed data(512 k symbol/sec) on a real-time basis, the CGM that guarantees fast and stable convergency is adopted during the training period of each frame. The coefficients obtained by the CGM are used as initial values for the LMS algorithm to trace the optimal coefficients during the data period that vary at each sampling time due to the mobility and noise at the receiver. Using the modelling presented in this paper, distributions of received signal power in various signal environments are demonstrated. The performance of the eqalizer proposed in this paper is shown as a function of BER under the various signal circumstances of mobile communications.

• The Journal of the Acoustical Society of Korea
• /
• v.43 no.1
• /
• pp.9-18
• /
• 2024

The importance of active sonar systems is emerging due to the quietness of underwater targets and the increase in ambient noise due to the increase in maritime traffic. However, the low signal-to-noise ratio of the echo signal due to multipath propagation of the signal, various clutter, ambient noise and reverberation makes it difficult to identify underwater targets using active sonar. Attempts have been made to apply data-based methods such as machine learning or deep learning to improve the performance of underwater target recognition systems, but it is difficult to collect enough data for training due to the nature of sonar datasets. Methods based on mathematical modeling have been mainly used to compensate for insufficient active sonar data. However, methodologies based on mathematical modeling have limitations in accurately simulating complex underwater phenomena. Therefore, in this paper, we propose a sonar signal synthesis method based on a deep neural network. In order to apply the neural network model to the field of sonar signal synthesis, the proposed method appropriately corrects the attention-based encoder and decoder to the sonar signal, which is the main module of the Tacotron model mainly used in the field of speech synthesis. It is possible to synthesize a signal more similar to the actual signal by training the proposed model using the dataset collected by arranging a simulated target in an actual marine environment. In order to verify the performance of the proposed method, Perceptual evaluation of audio quality test was conducted and within score difference -2.3 was shown compared to actual signal in a total of four different environments. These results prove that the active sonar signal generated by the proposed method approximates the actual signal.

• Clinics in Shoulder and Elbow
• /
• v.26 no.3
• /
• pp.260-266
• /
• 2023

Background: Knowledge of the base rate of signal changes consistent with distal biceps tendinopathy on magnetic resonance imaging (MRI) has the potential to influence strategies for diagnosis and treatment of people that present with elbow pain. The aim of this study is to measure the prevalence of distal biceps tendon signal changes on MRIs of the elbow by indication for imaging. Methods: MRI data for 1,306 elbows were retrospectively reviewed for mention of signal change in distal biceps tendon. The reports were sorted by indication. Results: Signal changes consistent with distal biceps tendinopathy were noted in 197 of 1,306 (15%) patients, including 34% of patients with biceps pain, 14% of patients with unspecified pain, and 8% of patients with a specific non-biceps indication. Distal biceps tendon changes noted on radiology reports were associated with older age, male sex, and radiologists with musculoskeletal fellowship training. Conclusions: The finding that distal biceps MRI signal changes consistent with tendinopathy are common even in asymptomatic elbows reduces the probability that symptoms correlate with pathology on imaging. The accumulation of signal changes with age, also independent of symptoms, suggests that tendon pathology persists after symptoms resolve, that some degree of distal biceps tendinopathy is common in a human lifetime, and that tendinopathy may often be accommodated without seeking care. Level of evidence: IV.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.171-178
• /
• 2016

An aircraft in flight and ATC(: Air Traffic Controllers) working in the Ground Control Center carry out a voice communication using the radio. Voice signal to be transmitted from the aircraft is received to a plurality of terrestrial sites around the country at the same time. The ATC receives the various quality of voice signal from the aircraft depending on the distance, speed, weather conditions and adjusted condition of the antenna and the radio. The ATC carries out a voice communication with aircraft in the optimal conditions finding the best voice signal. However, the present system chooses the values of the CD(: Carrier Dectect) which is determined to be superior to, based on the input voice level, as optimal channel. Thus this system can not be seen to select the optimal channel because it doesn't consider the effect of the noise which influences on the communication quality. In this paper, after removing the noise in the voice signal, we could give the digitized information and an improved voice signal quality, so that users can select an optimal channel. By using it, when operating the training eavesdropping system or the aircraft control, we can expect prevention accident and improvement of training performance by selecting the improved quality channel.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.13-20
• /
• 2022

IEEE 802.11ay Wi-Fi is the next generation wireless technology and operates in mmWave band. It supports the MU-MIMO (Multiple User Multiple Input Multiple Output) transmission in which an AP (Access Point) can transmit multiple data streams simultaneously to multiple STAs (Stations). To this end, the AP should perform MU-MIMO beamforming training with the STAs. For efficient MU-MIMO beamforming training, it is important for the AP to estimate signal strength measured at each STA at which multiple beams are used simultaneously. Therefore, in the paper, we propose a deep learning-based link quality estimation scheme. Our proposed scheme estimates the signal strength with high accuracy by utilizing a deep learning model pre-trained for a certain indoor or outdoor propagation scenario. Specifically, to estimate the signal strength of the multiple concurrent beams, our scheme uses the signal strengths of the respective single beams, which can be obtained without additional signaling overhead, as the input of the deep learning model. For performance evaluation, we utilized a Q-D (Quasi-Deterministic) Channel Realization open source software and extensive channel measurement campaigns were conducted with NIST (National Institute of Standards and Technology) to implement the millimeter wave (mmWave) channel. Our simulation results demonstrate that our proposed scheme outperforms comparison schemes in terms of the accuracy of the signal strength estimation.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2004.05a
• /
• pp.24-29
• /
• 2004

A small, highly-trained crew working on the ship's automation has contributed to the improvement of operation efficiency and the labor environment on board ship. However, at the same time, having a small crew adds more responsibility to the ship's officers to safely operate and manage the ship. Recently, development on the system to concentrate important information being scattered at the various pieces of navigational equipment has been actively studied, using information and computer technology. The purpose of this study is to set up and implement an integrated marine data networking and communication system on the training-research ship. Information relating to navigation, engine and office automation were investigated and analyzed, and implementation methods associated with navigation, engine and the management information system were designed and presented. In addition, the networking system and navigational signal interface unit for the integrated communication system, and the data communication method between the ship and land are also discussed.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1511-1516
• /
• 2011

The maintenance of the turnout is composed of signal field and track field on business, the electrical and mechanical field on system. adjustment and maintenance carry forward through coordination with these fields. In the case of turnout equipment used in a first phase of Seoul-Busan high-speed train, it is treated by classifying as mechanical adjustments and electrical adjustments. Mechanical adjustment is conducted with focus on fine adjustment to meet maintenance standards limits(1mm or less) about interval of basic rail and tongue rail about each part of track transition equipment. This refers to mechanical adjustments performed mainly with physical changes and movement characteristics between basic rail and tongue rail by considering the overall environment surrounding track side of section installed track transition equipment. However, these series of maintenance are conducted in state that high-speed train is not in the process from 1 am to 4 am at night, but common workers for maintenance are not familiar with the operation and checking about various situation, and the workers are even insufficient. Maintenance training using mixed reality is conducted in the place of business, we tried to overcome several problems of safety and time reduction through this training.