• Journal of Biomedical Engineering Research
• /
• v.17 no.4
• /
• pp.449-458
• /
• 1996

Most of the conventional electrocardiowaphs foil to detect signals other than P-QRS-T due to the limited SNR and bandwidth. High-resolution electrocardiography(HRECG) provides better SNR and wider bandwidth for the detection of micro-potentials with higher frequency components such as vontricular late potentials(LP). We have developed a HRECG using uncorrected XYZ lead for the detection of LPs. The overall gain of the amplifier is 4000 and the bandwidth is 0.5-300Hz without using 60Hz notch filter. Three 16-bit A/D converters sample X, Y, and Z signals simultaneously with a sampling frequency of 2000Hz. Sampled data are transmitted to a PC via a DMA-controlled, optically-coupled serial communication channel. In order to further reduce the noise, we implemented a signal averaging algorithm that averaged many instances of aligned beats. The beat alignment was carried out through the use of a template matching technique that finds a location maximizing cross-correlation with a given beat tem- plate. Beat alignment error was reduced to $\pm$0.25ms. FIR high-pass filter with cut-off frequency of 40Hz was applied to remove the low frequency components of the averaged X, Y, and Z signals. QRS onset and end point were determined from the vector magnitude of the sigrlaIL and some parameters needed to detect the existence of LP were estimated. The entire system was designed for the easy application of the future research topics including the optimal lead system, filter design, new parameter extraction, etc. In the developed HRECG, without signal averaging, the noise level was less than 5$\mu$V$_rms RTI$. With signal averaging of at least 100 beats, the noise level was reduced to 0.5$\mu$V$_rms RTI$, which is low enough to detect LPs. The developed HRECG will provide a new advanced functionality to interpretive ECG analyzers.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.10
• /
• pp.955-961
• /
• 2010

In this paper, we describe a study of a vehicle detection method based on a Boosting Classifier which uses Histogram of Oriented Gradient (HOG) features and Image Segmentation techniques. An input image is segmented by means of a split and merge algorithm. Then, the two largest segmented regions are removed in order to reduce the search region and speed up processing time. The HOG features are then calculated for each pixel in the search region. In order to detect the vehicle region we used the AdaBoost (adaptive boost) method, which is well known for classifying samples with two classes. To evaluate the performance of the proposed method, 537 training images were used to train and learn the classifier, followed by 500 non-training images to provide the recognition rate. From these experiments we were able to detect the proper image 98.34% of the time for the 500 non-training images. In conclusion, the proposed method can be used for detecting the location of a vehicle in an intelligent vehicle control system.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.3
• /
• pp.345-352
• /
• 2000

Objective : The purpose of this study was to compare computed tomographic angiography(CTA) with conventional cerebral angiography(CCA) and to assess usefulness of CTA in detection and anatomic definition of intracranial aneurysms of the circle of Willis in subarachnoid hemorrhage. Patients and Methods : Fifty consecutive patients with known or suspected intracranial saccular aneurysms underwent CTA with preoperative CCA from 1997 to 1999. Using surface shaded display post-processing technique, CTA was interpreted for the presence, location of aneurysms and anatomic features. The image obtained with CTA was then compared with CCA image. Results : In 47 patients, CCA revealed 57 cerebral aneurysms and CTA revealed 54 aneurysms. Two of the 57 cerebral aneurysms were located outside of the imaging volume of CTA and one case was misdiagnosed. The sensitivity of CTA was 94.7% and the specificity was 100%. The results obtained with CTA were, compared with the results obtained with CCA, equal in determining dome shape, direction and lobularity. However, CTA provided a 3-dimensional representation of aneurysmal lesion very useful for surgical planning. Moreover, CTA was useful for rapid and relatively noninvasive detection of aneurysms in the circle of Willis. Conclusion : CTA can be a diagnostic tool for the patients with acute subarachnoid hemorrhage due to a ruptured aneurysm of the circle of Willis and provides adequate anatomic detail for surgical planning, especially to complex cerebral aneurysms. However, we think CCA is necessary because of CTA limitations including its difficulty in detecting unusually located aneurysms(including those in cavernous sinus or distal artery) and combined vascular lesion (including arteriovenous malformation) and acquiring dynamic flow information.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.6
• /
• pp.2781-2785
• /
• 2016

Background: Matric metalloproteinase (MMP) 13 gene expression is increased in esophageal squamous cell carcinomas (ESCCs) and associated with increasing tumor invasion, lymph node involvement and decreased survival rates. Levels of the circulating enzyme may be elevated and used as a marker of tumor progression. In this study, clinical application of MMP-13 serum levels was evaluated for early detection, prediction of prognosis and survival time of ESCC patients. Materials and Methods: Serum levels of MMP13 were determined by ELISA in 66 ESCC patients prior of any treatment and 54 healthy controls for comparison with clinicopathological data through statistical analysis with Man Whitney U and Log-Rank tests. In addition, clinical value of MMP13 levels for diagnosis was evaluated by receiver operating characteristic (ROC) test. Results: The serum level of MMP-13 in patients (>250 pg/ml) was significantly higher than in the control group (<100 pg/ml) (p value=0.004). Also the results showed a significant correlation between MMP-13 serum levels with tumor stage (p value = 0.003), depth of tumor invasion (p value=0.008), involvement of lymph nodes (p value = 0.011), tumor size (p value = 0.018) and survival time. While there were no significant correlation with grade and location of tumors. ROC analysis showed that MMP-13 level is an accurate diagnostic marker especially to differentiate pre-invasive/ invasive lesions from normal controls (sensitivity and specificity: 100%). Conclusions: These findings indicate a potential clinical significance of serum MMP13 measurement for early detection and prognostic assessment in ESCC patients.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.3
• /
• pp.332-336
• /
• 2010

There are so many successful applications to image processing systems in industries. In this study we propose a position detection system for used oil filter by using a line laser. We have been done on the development of line laser as interaction devices. A camera captures images of a display surface of a used oil filter and then a laser beam location is extracted from the captured image. This image is processed and used as a cursor position. We also discuss an algorithm that can distinguish the front part and rear part. In particular we present a robust and efficient linear detection algorithm that allows us to use our system under a variety lighting conditions, and allows us to reduce the amount of image parsing required to find a laser position by an order of magnitude.

• Geophysics and Geophysical Exploration
• /
• v.8 no.1
• /
• pp.97-103
• /
• 2005

Recent development of marine magnetic gradient systems, using arrays of sensors, has made it possible to survey large contaminated areas very quickly. However, underwater Unexploded Ordnances (UXO) can be moved by water currents. Because of this mobility, the cleanup process in such situations becomes dynamic rather than static. This implies that detection should occur in near real-time for successful remediation. Therefore, there is a need for a fast interpretation method to rapidly detect signatures of underwater objects in marine magnetic data. In this paper, we present a fast method for location and characterization of underwater UXOs. The approach utilises gradient interpretation techniques (analytic signal and Euler methods) to locate the objects precisely. Then, using an iterative linear least-squares technique, we obtain the magnetization characteristics of the sources. The approach was applied to a theoretical marine magnetic anomaly, with random errors, over a known source. We demonstrate the practical utility of the method using marine magnetic gradient data from Japan.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.707-709
• /
• 2014

The radiation sources leaked from large-scale radiation leak accident like the Fukushima nuclear power plant accident or nuclear explosions can cause to the very large damage for us. So that the damage can be minimized, we have being developed a detector that can providing information about the location of the source to remove dangerous substances quickly than the conventional single detector. In this paper, we designed and implemented the radiation shield and the collimator for the development of the stereo radiation detector to detect contamination things using MCNP Simulation. And we analysed the test results of the radiation shield and collimator using the radiation source. The results of this paper will be used as the basis for improving the efficiency of the stereo radiation detector being studied currently.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2168-2187
• /
• 2021

The smart grid replaces the traditional power structure with information inventiveness that contributes to a new physical structure. In such a field, malicious information injection can potentially lead to extreme results. Incorrect, FDI attacks will never be identified by typical residual techniques for false data identification. Most of the work on the detection of FDI attacks is based on the linearized power system model DC and does not detect attacks from the AC model. Also, the overwhelming majority of current FDIA recognition approaches focus on FDIA, whilst significant injection location data cannot be achieved. Building on the continuous developments in deep learning, we propose a Deep Learning based Locational Detection technique to continuously recognize the specific areas of FDIA. In the development area solver gap happiness is a False Data Detector (FDD) that incorporates a Convolutional Neural Network (CNN). The FDD is established enough to catch the fake information. As a multi-label classifier, the following CNN is utilized to evaluate the irregularity and cooccurrence dependency of power flow calculations due to the possible attacks. There are no earlier statistical assumptions in the architecture proposed, as they are "model-free." It is also "cost-accommodating" since it does not alter the current FDD framework and it is only several microseconds on a household computer during the identification procedure. We have shown that ANN-MLP, SVM-RBF, and CNN can conduct locational detection under different noise and attack circumstances through broad experience in IEEE 14, 30, 57, and 118 bus systems. Moreover, the multi-name classification method used successfully improves the precision of the present identification.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.27-37
• /
• 2021

In this paper, we propose Automatic detection system of underground pipe which automatically detects underground pipe to help experts. Actual location of underground pipe does not match with blueprint due to various factors such as ground changes over time, construction discrepancies, etc. So, various accidents occur during excavation or just by ageing. Locating underground utilities is done through GPR exploration to prevent these accidents but there are shortage of experts, because GPR data is enormous and takes long time to analyze. In this paper, To analyze 3D GPR data automatically, we use 3D image segmentation, one of deep learning technique, and propose proper data generation algorithm. We also propose data augmentation technique and pre-processing module that are adequate to GPR data. In experiment results, we found the possibility for pipe analysis using image segmentation through our system recorded the performance of F1 score 40.4%.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1188-1191
• /
• 2020

In this paper, automotive safety and convenience service is proposed based on bluetooth and smart watch. The proposed service performs accident detection, kidnapping detection, kid-left-alone-in-car detection, parking location recording, and smart key function. Conventional smartphone services often fails to precisely recognize accident and kidnapping situations since smartphone is located on the dashboard or in the bag. On the contrary, smartwatch recognizes accident and kidnapping situations more precisely since it is always worn on the wrist with hearbeat monitoring. The proposed service recognise various situations around drives and passengers using acceleration sensor, GPS sensor, heartbeat sensor and bluetooth link status. It also performs accident notice, sound recording, and other necessary actions. It also performs door opening, door closing, hazard light flickering, and other necessary actions using OBD-II connection to the vehicle.