• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.4
• /
• pp.729-734
• /
• 2008

Vibroarthrographic(VAG) signals, emitted by human knee joints, are non-stationary and multi-component in nature and time-frequency distributions(TFD) provide powerful means to analyze such signals. The objective of this paper is to classify VAG signals, generated during joint movement, into two groups(normal and patient group) using the characteristic parameters extracted by time-frequency transform, and to evaluate the classification accuracy. Noise within TFD was reduced by singular value decomposition and back-propagation neural network(BPNN) was used for classifying VAG signals. The characteristic parameters consist of the energy parameter, energy spread parameter, frequency parameter, frequency spread parameter by Wigner-Ville distribution and the amplitude of frequency distribution, the mean and the median frequency by fast Fourier transform. Totally 1408 segments(normal 1031, patient 377) were used for training and evaluating BPNN. As a result, the average value of the classification accuracy was 92.3(standard deviation ${\pm}0.9$)%. The proposed method was independent of clinical information, and showed good potential for non-invasive diagnosis and monitoring of joint disorders such as osteoarthritis and chondromalacia patella.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.814-822
• /
• 2022

The deployment of sensors for Structural Health Monitoring requires a complicated network arrangement, ground truthing, and calibration for validating sensor performance periodically. Any conventional sensor on a structural element is also subjected to static and dynamic vertical loadings in conjunction with other environmental factors, such as brightness, noise, temperature, and humidity. A structural model with strain gauges was built and tested to get realistic sensory information. This paper investigates different deep learning architectures and algorithms, including unsupervised, autoencoder, and supervised methods, to benchmark blind drift calibration methods using deep learning. It involves a fully connected neural network (FCNN), a long short-term memory (LSTM), and a gated recurrent unit (GRU) to address the blind drift calibration problem (i.e., performing calibrations of installed sensors when ground truth is not available). The results show that the supervised methods perform much better than unsupervised methods, such as an autoencoder, when ground truths are available. Furthermore, taking advantage of time-series information, the GRU model generates the most precise predictions to remove the drift overall.

• Proceedings of the KSR Conference
• /
• 2000.05a
• /
• pp.344-351
• /
• 2000

Recently, the microprocessor with network function based-controlled systems instead of conventional microprocessors is widely used to industrial applications, and also those technologies are widely adopted for train control and monitoring in modern rapid transit systems such as railway vehicles. The purpose of this paper is to propose a high quality data transmission line of railway vehicle system controlled by a microprocessor, which was designed and realized through SMG 7＆8 and ISA project. Noise, distortion and attenuation are always present in data transmission system and strictly limit performance. This paper describes a method to calculate the propagation constant, attenuation constant, phase velocity and length of stub.

• Current Optics and Photonics
• /
• v.7 no.3
• /
• pp.237-247
• /
• 2023

In middle- and long-distance imaging systems, due to the atmospheric turbulence caused by temperature, wind speed, humidity, and so on, light waves propagating in the air are distorted, resulting in image-quality degradation such as geometric deformation and fuzziness. In remote sensing, astronomical observation, and traffic monitoring, image information loss due to degradation causes huge losses, so effective restoration of degraded images is very important. To restore images degraded by atmospheric turbulence, an image-restoration method based on improved compound multibranch feature fusion (CMFNetPro) was proposed. Based on the CMFNet network, an efficient channel-attention mechanism was used to replace the channel-attention mechanism to improve image quality and network efficiency. In the experiment, two-dimensional random distortion vector fields were used to construct two turbulent datasets with different degrees of distortion, based on the Google Landmarks Dataset v2 dataset. The experimental results showed that compared to the CMFNet, DeblurGAN-v2, and MIMO-UNet models, the proposed CMFNetPro network achieves better performance in both quality and training cost of turbulent-image restoration. In the mixed training, CMFNetPro was 1.2391 dB (weak turbulence), 0.8602 dB (strong turbulence) respectively higher in terms of peak signal-to-noise ratio and 0.0015 (weak turbulence), 0.0136 (strong turbulence) respectively higher in terms of structure similarity compared to CMFNet. CMFNetPro was 14.4 hours faster compared to the CMFNet. This provides a feasible scheme for turbulent-image restoration based on deep learning.

• Journal of Korean Society of societal Security
• /
• v.2 no.2
• /
• pp.49-54
• /
• 2009

High incident of accidents in construction jobsite became a social problem. According to the International Labour Organization (ILO), more than 60,000 fatal accidents occur each year in construction workplace worldwide. This number of accidents accounts for about 17 percent of all fatal workplace accidents. Especially, accidents from struck-by and falls comprise of over 60 percent of construction fatalities. This paper introduces a prototype of a received signal strength index (RSSI)-based safety monitoring to mitigate the potential accidents caused by falls and struck-by. Correlation between signal strength and noise index is examined to create the distance profile between a transmitter and a receiver. Throughout the distributed sensor nodes attached on potential hazardous objects, the proposed prototype envisions that construction workers with a tracker-tag can identify and monitor their current working environment in construction workplace, and early warning system can reduce the incidents of fatal accident in construction job site.

• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.552-562
• /
• 2018

With the advent of the information society, image restoration technology has aroused considerable interest. Guided image filtering is more effective in suppressing noise in homogeneous regions, but its edge-preserving property is poor. As such, the critical part of guided filtering lies in the selection of the guided image. The result of the Expected Patch Log Likelihood (EPLL) method maintains a good structure, but it is easy to produce the ladder effect in homogeneous areas. According to the complementarity of EPLL with guided filtering, we propose a method of coupling EPLL and guided filtering for image de-noising. The EPLL model is adopted to construct the guided image for the guided filtering, which can provide better structural information for the guided filtering. Meanwhile, with the secondary smoothing of guided image filtering in image homogenization areas, we can improve the noise suppression effect in those areas while reducing the ladder effect brought about by the EPLL. The experimental results show that it not only retains the excellent performance of EPLL, but also produces better visual effects and a higher peak signal-to-noise ratio by adopting the proposed method.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.10
• /
• pp.17-26
• /
• 2010

This is concerned with the technology to monitor the vehicle operation, failure and disorder by using WiBro portable device. More precisely, the technology makes it possible that the information collection device is connected to both ECU(Electronic Control Unit) which is the device for controlling engine, transmission, brake, air-bag, etc that are connected to in-vehicle network and OBD-II connector that is for data collection from various sensors. In addition, with a WiBro portable device (cell phone, PDA, PMP, UMPC, etc). equipped with a vehicle diagnostic programs, information for operation, failure and malfunction can be obtained and analyzed in real-time, and alarm is alerted when the vehicle is in abnormal status, which makes the early reactions to the status. Furthermore, the collected data can be sent through WiBro network to the server managed by the company specialized in managing the vehicles, thus the technology could help the drivers who have less knowledge about their auto-vehicles have safe and economic driving. There is always a possibility of malfunction due to various types of noise that are caused by wring-harness when the device is wired-connected. In this research, in order to overcome this problem, we propose a system configuration that can do monitoring and diagnosis with a device for collecting data from vehicle and a personal WiBro device. Also, we performed research on data acquisition and interlock for the system defined by the definition for information and data sharing platform.

• Journal of the Institute of Convergence Signal Processing
• /
• v.14 no.4
• /
• pp.243-248
• /
• 2013

In wireless sensor networks, consensus algorithms for dynamic systems may flexibly usable for their data fusion of a sensor network. In this paper, a distributed data fusion filter is implemented using an average consensus based on distributed sensor data, which is composed of some sensor nodes and a sink node to track the mean values of n sensors' data. The consensus filter resolve the problem of data fusion by a distribution Kalman filtering scheme. We showed that the consensus filter has an optimal convergence to decrease of noise propagation and fast tracking ability for input signals. In order to verify for the results of consensus filtering, we showed the output signals of sensor nodes and their filtering results, and then showed the result of the combined signal and the consensus filtering using zeegbee communication.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.673-686
• /
• 2022

Deep learning algorithms for Structural Health Monitoring (SHM) have been extracting the interest of researchers and engineers. These algorithms commonly used loss functions and evaluation indices like the mean square error (MSE) which were not originally designed for SHM problems. An updated loss function which was specifically constructed for deep-learning-based structural damage detection problems has been proposed in this study. By tuning the coefficients of the loss function, the weights for damage localization and quantification can be adapted to the real situation and the deep learning network can avoid unnecessary iterations on damage localization and focus on the damage severity identification. To prove efficiency of the proposed method, structural damage detection using convolutional neural networks (CNNs) was conducted on a truss bridge model. Results showed that the validation curve with the updated loss function converged faster than the traditional MSE. Data augmentation was conducted to improve the anti-noise ability of the proposed method. For reducing the training time, the normalized modal strain energy change (NMSEC) was extracted, and the principal component analysis (PCA) was adopted for dimension reduction. The results showed that the training time was reduced by 90% and the damage identification accuracy could also have a slight increase. Furthermore, the effect of different modes and elements on the training dataset was also analyzed. The proposed method could greatly improve the performance for structural damage detection on both the training time and detection accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.12
• /
• pp.11-21
• /
• 2011

An embedded sensor is significantly influenced by its spatial environment, such as barriers or distance, through low power and signal strength. Due to these causes, noise data frequently occur in an embedded sensor. Because the information acquired from the embedded sensor exists in a time series, it is hard to detect an error which continuously takes place in the time series information on a realtime basis. In this paper, we proposes an error detection method based on time-series prediction that detects error signals of embedded sensors in real time in consideration of the physical characteristics of embedded devices. The error detection method based on time-series prediction proposed in this paper determines errors in generated embedded device signals using a stable distance function. When detecting errors by monitoring signals from an embedded device, the stable distance function can detect error signals effectively by applying error weight to the latest signals. When detecting errors by monitoring signals from an embedded device, the stable distance function can detect error signals effectively by applying error weight to the latest signals.