• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.24-29
• /
• 2023

In this paper, we propose a real-time bus arrival notification system using deep learning to guarantee movement rights for the visually impaired. In modern society, by using location information of public transportation, users can quickly obtain information about public transportation and use public transportation easily. However, since the existing public transportation information system is a visual system, the visually impaired cannot use it. In Korea, various laws have been amended since the 'Act on the Promotion of Transportation for the Vulnerable' was enacted in June 2012 as the Act on the Movement Rights of the Blind, but the visually impaired are experiencing inconvenience in using public transportation. In particular, from the standpoint of the visually impaired, it is impossible to determine whether the bus is coming soon, is coming now, or has already arrived with the current system. In this paper, we use deep learning technology to learn bus numbers and identify upcoming bus numbers. Finally, we propose a method to notify the visually impaired by voice that the bus is coming by using TTS technology.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.9-14
• /
• 2002

We propose a new algorithm for blind source separation (BSS), in which frequency-domain independent component analysis (FDICA) and time-domain ICA (TDICA) are combined to achieve a superior source-separation performance under reverberant conditions. Generally speaking, conventional TDICA fails to separate source signals under heavily reverberant conditions because of the low convergence in the iterative learning of the inverse of the mixing system. On the other hand, the separation performance of conventional FDICA also degrades significantly because the independence assumption of narrow-band signals collapses when the number of subbands increases. In the proposed method, the separated signals of FDICA are regarded as the input signals for TDICA, and we can remove the residual crosstalk components of FDICA by using TDICA. The experimental results obtained under the reverberant condition reveal that the separation performance of the proposed method is superior to that of conventional ICA-based BSS methods.

• Journal of Convergence for Information Technology
• /
• v.10 no.5
• /
• pp.111-116
• /
• 2020

Recently, many safety accidents involving children shuttle buses take place. Without a teacher for help, a safety accident occurs when the driver can't see a child who is getting off in the blind spot of both frontside and backside. A deep learning-based smart mirror allows user authentication and provides various services. Especially, It can be a role of helper for children, and prevent accidents that can occur when drivers or assistant teachers do not see them. User authentication is carried out with children's face registered in advance. Safety accidents can be prevented by an approximate sensor and a camera in frontside and backside of the bus. This study suggests a way of checking out whether children are missed in the process of getting in and out of the bus, designs a system that reduce blind spots in the front and back of the vehicle, and builds a safety system that provide various services using GPS.

• Nuclear Engineering and Technology
• /
• v.53 no.4
• /
• pp.1199-1209
• /
• 2021

The detection of unexpected loose parts in the primary coolant system in a nuclear power plant remains an extremely important issue. It is essential to develop a methodology for the localization and mass estimation of loose parts owing to the high prediction error of conventional methods. An effective approach is presented for the localization and mass estimation of a loose part using machine-learning and deep-learning algorithms. First, a methodology was developed to estimate both the impact location and the mass of a loose part at the same times in a real structure in which geometric changes exist. Second, an impact database was constructed through a series of impact finite-element analyses (FEAs). Then, impact parameter prediction modes were generated for localization and mass estimation of a simulated metallic loose part using machine-learning algorithms (artificial neural network, Gaussian process, and support vector machine) and a deep-learning algorithm (convolutional neural network). The usefulness of the methodology was validated through blind tests, and the noise effect of the training data was also investigated. The high performance obtained in this study shows that the proposed methodology using an FEA-based database and deep learning is useful for localization and mass estimation of loose parts on site.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.336-338
• /
• 1998

This paper presents a novel neural network structure to the blind deconvolution task where the input (source) to a system is not available and the source has any type of distribution including sparse distribution. We employ multiple sensors so that spatial information plays a important role. The resulting learning algorithm is linear so that it works for both sub-and super-Gaussian source. Moreover, we can successfully deconvolve the mixture of a sparse source, while most existing algorithms [5] have difficulties in this task. Computer simulations confirm the validity and high performance of the proposed algorithm.

• Toxicological Research
• /
• v.17
• /
• pp.257-261
• /
• 2001

Recently, a traditional medicine called Gouteng-san, which consists of eleven herbs, was reported to be effective in treating vascular dementia with a double-blind, placebo-controlled study. Gout-eng-san is also used for patients with vascular dementia in combination with Si-Wu-Tang. The effect of Gouteng-san and Si-Wu-Tang on deficit of learning behavior was investigated using step-down passive avoidance task in mice. Hot-water extract of Gouteng-san (1.5 and 6 g/kg, p.o.) significantly prolonged the step-down latency shortened by scopolamine. The extract of Uncaria hook (150 mg/kg, p.o.), one of the component herb of Gouteng-san, significantly prevented the decrease in the latency after scopolamine. Hot-water extract of Si-Wu-Tang (1.5 and 6 g/kg of dried herbs, p.o.) prevented dose-dependently scopola-mine-induced disruption qf learning behavior. Si-Wu-Tang also prevented the ischemia-induced deficit of learning behavior. Both hot water extract of peony and angelica (1.5 g/kg, p.o.), which are component herbs qf Si-Wu-Tang, prevented the scopolamine-induced learning behavior deficit. Scopolamine (10 uM) suppressed long-term potentiation (LTP) of population spike in the CA1 region of the rat hippocampal slices. Peoniflorin (0.1~ 1uM) extracted from paeony root significantly ameliorated scopolamine-induced inhibition of LTR These results suggest that improvement of deficit of learning behavior by Gouteng-san and Si-Wu-Tang is mediated by direct and/or indirect activation of the cholinergic system in the brain.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.15 no.5
• /
• pp.19-24
• /
• 1978

In this paper, the functional propertied of vibrotactile sense of skin were studied by means of psycophysical experiments with respect to frequency and waveform of mechanical vibration, two-point threshold, contactor size of stimulators. Furthermore, leased on the experimental result, a small vibrotactile stimulator made of piezoelectrc ireed vibrator array was proposed for a aid blind to recognition of the Korean letters. A tactile output image is presented by an 8 row$\times$1 column array of samall vibrator reeds with 200 Hz rectangular wave, the array fitting on a fore-finger. Under the control of the NOVA mini-computer, the bimorph reeds array could represent any of one of the 24 characters of the Korean vowel and consonant at the 8 positions from left to right on the array. Without learning effect, the identification test of the Korean characters by the designed experimental system was carried out. The average rate of correct response was 90%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.10
• /
• pp.5095-5111
• /
• 2019

A multi-rotor Unmanned Aerial Vehicle (UAV) system is developed to solve the manhole cover detection problem for the infrastructure maintenance in the suburbs of big city. The visible light sensor is employed to collect the ground image data and a series of image processing and machine learning methods are used to detect the manhole cover. First, the image enhancement technique is employed to improve the imaging effect of visible light camera. An imaging environment perception method is used to increase the computation robustness: the blind Image Quality Evaluation Metrics (IQEMs) are used to percept the imaging environment and select the images which have a high imaging definition for the following computation. Because of its excellent processing effect the adaptive Multiple Scale Retinex (MSR) is used to enhance the imaging quality. Second, the Single Shot multi-box Detector (SSD) method is utilized to identify the manhole cover for its stable processing effect. Third, the spatial coordinate of manhole cover is also estimated from the ground image. The practical applications have verified the outdoor environment adaptability of proposed algorithm and the target detection correctness of proposed system. The detection accuracy can reach 99% and the positioning accuracy is about 0.7 meters.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.258-268
• /
• 2021

Online learning systems are becoming an effective educational medium for many universities. The accessibility of online learning system in universities means that every student, including the visually impaired, is able use all the site's services. This research focuses on investigating the accessibility of online learning systems for visually impaired users. The paper purpose is to understand the perception of visually impaired undergraduate students towards Blackboard's accessibility and to make recommendations for a new Blackboard design with accessible features that support their needs. Impact of a new Blackboard design with accessible features on visually impaired students, using Taif University students as a case study is evaluated in this paper, as it is similar to most learning systems used by Saudi universities. A study on Taif University's utilization of Blackboard was conducted using mixed method approaches (an automatic tool and a user study). In the first phase, Taif's use of Blackboard was evaluated by the web accessibility tool called AChecker. In the second phase, we conducted a user study to verify previously discovered accessibility challenges to fully assess them according to the accessibility and usability guidelines. In this study, the accessibility of Taif University's Blackboard was evaluated by thirteen visually impaired undergraduate students. The results of the study show that Blackboard has accessibility issues, which are confusing navigation, incompatibility with assistive technologies, untitled pages or parts, unclear identification for visual elements, and inaccessible PDF files. This paper also introduces a set of recommendations that aim to improve the accessibility of Blackboard and other educational websites developed for this population. It also highlights the serious need for universities to enhance web accessibility for online learning systems for students with disabilities.