• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.326-328
• /
• 2021

The use of shared electric kickboards that can move quickly within a short distance at a relatively low price is increasing significantly. In this paper, we propose a system for recognizing incorrect parking of an abandoned shared kickboard by applying deep learning-based object recognition technology. In this paper, a model similar to CNN was created separately considering the characteristics of the experimental data, and it was shown that a recognition rate of 60% was obtained through the experiment.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.171-176
• /
• 2023

This study is about a speech recognition error correction system designed to detect and correct speech recognition errors before natural language processing to increase the success rate of intent analysis in natural language processing with optimal efficiency in various service domains. An encoder is constructed to embedded the correct speech token and one or more error speech tokens corresponding to the correct speech token so that they are all located in a dense vector space for each correct token with similar vector values. One or more utterance tokens within a preset Manhattan distance based on the correct utterance token in the dense vector space for each embedded correct utterance token are detected through an error detector, and the correct answer closest to the detected error utterance token is based on the Manhattan distance. Errors are corrected by extracting the utterance token as the correct answer.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.253-254
• /
• 2023

We this study investiged the level of perception such as construction quality-related systems according to the subject of construction work. The results of the recognition moisture survey showed a high response rate in the order of construction companies and supervisors. The result of the system's level of understanding was low at 3.6 points for the orderer and contractor. In addition, in recognition of the effectiveness of the quality management system, the contractor showed a somewhat negative perception than other targets.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.33-38
• /
• 2024

In this paper, we propose the implementation of a drone delivery system using artificial intelligence in a situation where the use of drones is rapidly increasing and human errors are occurring. This system requires the implementation of an accurate control algorithm, assuming that last-mile delivery is delivered to the apartment veranda. To recognize the delivery location, a recognition system using the YOLO algorithm was implemented, and a delivery system was installed on the drone to measure the distance to the object and increase the delivery distance to ensure stable delivery even at long distances. As a result of the experiment, it was confirmed that the recognition system recognized the marker with a match rate of more than 60% at a distance of less than 10m while the drone hovered stably. In addition, the drone carrying a 500g package was able to withstand the torque applied as the rail lengthened, extending to 1.5m and then stably placing the package down on the veranda at the end of the rail.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.5
• /
• pp.51-57
• /
• 1995

In this paper, we study a noise-robust feature extraction method of speech signal based on auditory modeling. The auditory model consists of a basilar membrane, a hair cell model and spectrum output stage. Basilar membrane model describes a response characteristic of membrane according to vibration in speech wave, and is represented as a band-pass filter bank. Hair cell model describes a neural transduction according to displacements of the basilar membrane. It responds adaptively to relative values of input and plays an important role for noise-robustness. Spectrum output stage constructs a mean rate spectrum using the average firing rate of each channel. And we extract feature vectors using a mean rate spectrum. Simulation results show that when auditory-based feature extraction is used, the speech recognition performance in noisy environments is improved compared to other feature extraction methods.

• Phonetics and Speech Sciences
• /
• v.9 no.3
• /
• pp.67-74
• /
• 2017

An increase in speech intelligibility has been found in Clear Speech compared to conversational speech. Clear Speech is defined by decreased articulation rates and increased frequency and length of pauses. The objective of the present study was to investigate improvement in immediate speech intelligibility in 10 patients with Parkinson's disease (age range: 46 to 75 years) using Clear Speech. This experiment has been performed using the Phonatory Aerodynamic System 6600 after the participants read the first sentence of a Sanchaek passage and the "List for Adults 1" in the Sentence Recognition Test (SRT) using casual speech and Clear Speech. Acoustic and aerodynamic parameters that affect speech intelligibility were measured, including mean F0, F0 range, intensity, speaking rate, mean airflow rate, and respiratory rate. In the Sanchaek passage, use of Clear Speech resulted in significant differences in mean F0, F0 range, speaking rate, and respiratory rate, compared with the use of casual speech. In the SRT list, significant differences were seen in mean F0, F0 range, and speaking rate. Based on these findings, it is claimed that speech intelligibility can be affected by adjusting breathing and tone in Clear Speech. Future studies should identify the benefits of Clear Speech through auditory-perceptual studies and evaluate programs that use Clear Speech to increase intelligibility.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.529-540
• /
• 2000

This is paper presents the semantic based rate-control method which is based on very low bit rate video coding standards H.263 plus, applied on very low bit rate applications. Previous rate control methods control the generated bit rates by setting the optimum quantization parameters per macro block unit on frame. But, in this paper, we added the pre-processing algorithm, semantic region recognition and assignment of priority algorithm, to obtain the subjective quality enhancement. This work aims to improve the subjective quality of skin color region or face by using unimportant background region's bit resources.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.4
• /
• pp.1136-1142
• /
• 1999

A difficulty of the visual inspection for translated, magnified and rotated objects exists owing to the limitation of recognition rate. In this paper, we perform to define Integral Logarithm Transform(ILT), to consider its characteristic for implementation of Translation-, Magnification- and Rotation-invariant inspection system, and to compare with other methods in inspection error rate. By using magnification and rotation invariance properties of ILT, it makes easier than other methods to extract the rotation degree. The new method employs the ILT for the good/bad inspection of translated, magnified and rotated objects and experiment is performed to achieve translation, magnification and rotation invariance. In other methods both magnification and rotation invariance can't be available. As the result of he experiment, it is not better than the self-organizing map in the improvement of recognition rate, but it shows us the possibility to be used as a tool for the good/bad inspection system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.5
• /
• pp.458-467
• /
• 1991

In this paper, the cause of linear prediction error is analysed and the theoretical basis for nomalizing the format bandwidth to 0is given and its validity is verified. The formant and bandwidth in relation to the position of the poles of AR filter are measured for an alaysis of the relation between the pole position and the formant bandwidth. By changing the glottis reflection coefficient to 1. the pole position and the formant bandwidth. By changing the glottis reflection coefficient to 1. the effect of the glottis is eliminated and as the result a new linear preiction coefficients are obtained by normalizing the formant bandwidth of the signal to 0. since these coefficients are symmetrical, the standard deviation is larger than the coefficients with fixed glottis reflection coefficient. The bit rate for speech coding can be reduced by a factor of 2 without any loss of information. Through computer simulation, recognition rate of 96.7% is botained by using the proposed algorithm in recognizing 5 Korean vowels in noisy environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.5
• /
• pp.425-430
• /
• 2015

This paper is a study to improve the classification efficiency of rotating objects by using deep neural networks to which a deep learning algorithm was applied. For the classification experiment of rotating objects, COIL-20 is used as data and total 3 types of classifiers are compared and analyzed. 3 types of classifiers used in the study include PCA classifier to derive a feature value while reducing the dimension of data by using Principal Component Analysis and classify by using euclidean distance, MLP classifier of the way of reducing the error energy by using error back-propagation algorithm and finally, deep learning applied DBN classifier of the way of increasing the probability of observing learning data through pre-training and reducing the error energy through fine-tuning. In order to identify the structure-specific error rate of the deep neural networks, the experiment is carried out while changing the number of hidden layers and number of hidden neurons. The classifier using DBN showed the lowest error rate. Its structure of deep neural networks with 2 hidden layers showed a high recognition rate by moving parameters to a location helpful for recognition.