• Korean Journal of Radiology
• /
• v.22 no.4
• /
• pp.513-524
• /
• 2021

Objective: To assess the noncontrast two-dimensional single-shot balanced turbo-field-echo magnetic resonance angiography (b-TFE MRA) features of the abdominal aortic aneurysm (AAA) status following endovascular aneurysm repair (EVAR) and evaluate to detect endoleaks (ELs). Materials and Methods: We examined four aortic stent-grafts in a phantom study to assess the degree of metallic artifacts. We enrolled 46 EVAR-treated patients with AAA and/or common iliac artery aneurysm who underwent both computed tomography angiography (CTA) and b-TFE MRA after EVAR. Vascular measurements on CTA and b-TFE MRA were compared, and signal intensity ratios (SIRs) of the aneurysmal sac were correlated with the size changes in the AAA after EVAR (AAA prognoses). Furthermore, we examined six feasible b-TFE MRA features for the assessment of ELs. Results: There were robust intermodality (r = 0.92-0.99) correlations and interobserver (intraclass correlation coefficient = 0.97-0.99) agreement. No significant differences were noted between SIRs and aneurysm prognoses. Moreover, "mottled high-intensity" and "creeping high-intensity with the low-band rim" were recognized as significant imaging findings suspicious for the presence of ELs (p < 0.001), whereas "no signal black spot" and "layered high-intensity area" were determined as significant for the absence of ELs (p < 0.03). Based on the two positive features, sensitivity, specificity, and accuracy for the detection of ELs were 77.3%, 91.7%, and 84.8%, respectively. Furthermore, the k values (0.40-0.88) displayed moderate-to-almost perfect agreement. Conclusion: Noncontrast MRA could be a promising imaging modality for ascertaining patient follow-up after EVAR.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1743-1747
• /
• 2022

Sentinel-2 can be used as proxy data for the Korean Compact Advanced Satellite 500-4 (CAS500-4), also known as Agriculture and Forestry Satellite, in terms of spectral wavelengths and spatial resolution. This letter examined cloud detection for later use in the CAS500-4 based on deep learning technologies. DeepLabV3+, a traditional Convolutional Neural Network (CNN) model, and Shifted Windows (Swin) Transformer, a state-of-the-art (SOTA) Transformer model, were compared using 22,728 images provided by Radiant Earth Foundation (REF). Swin Transformer showed a better performance with a precision of 0.886 and a recall of 0.875, which is a balanced result, unbiased between over- and under-estimation. Deep learning-based cloud detection is expected to be a future operational module for CAS500-4 through optimization for the Korean Peninsula.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.2
• /
• pp.61-66
• /
• 2005

This paper presents a refined protection algorithm of the unfused 22.9kV shunt capacitor banks in grounded wye connection to improve the existing algorithm using the voltage difference method. It is difficult to detect ground faults with arc near the input points or ground faults near the grounding point by the existing algorithm using only the voltage balanced relay. This paper shows that ground faults with arc near the input point can be detected by harmonics analysis of the differential voltage and that it has no impact of harmonics out of nonlinear loads which have the quantitative influence on capacitor banks. Thus the proposed method using harmonics analysis can be a proper detection method. In case of ground faults near the grounding point, an OVGR is being added recently and its validity is verified in this paper. The proposed method is applied to a 22.9kV example system and is verified that the proposed algorithm can detect clearly faults which are not easy to detect by the existing method.

• Journal of Power Electronics
• /
• v.18 no.1
• /
• pp.56-69
• /
• 2018

In this paper, an improved Space Vector Modulation (SVM) based fault tolerant operation on a nine-level Cascaded H-Bridge (CHB) inverter with an additional backup circuit is proposed. Any type of fault in a power converter may result in a power interruption and productivity loss. Three different faults on H-bridge modules in all three phases based on the SVM approach are investigated with diagrams. Any fault in an inverter phase creates an unbalanced output voltage, which can lead to instability in the system. An additional auxiliary unit is connected in series to the three phase cascaded H-bridge circuit. With the help of this and the redundant switching states in SVM, the CHB inverter produces a balanced output with low harmonic distortion. This ensures high DC bus utilization under numerous fault conditions in three phases, which improves the system reliability. Simulation results are presented on three phase nine-level inverter with the automatic fault detection algorithm in the MATLAB/SIMULINK software tool, and experimental results are presented with DSP on five-level inverter to validate the practicality of the proposed SVM fault tolerance strategy on a CHB inverter with an auxiliary circuit.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4105-4121
• /
• 2021

Recently, malware classification based on Deep Neural Networks (DNN) has gained significant attention due to the rise in popularity of artificial intelligence (AI). DNN-based malware classifiers are a novel solution to combat never-before-seen malware families because this approach is able to classify malwares based on structural characteristics rather than requiring particular signatures like traditional malware classifiers. However, these DNN-based classifiers have been found to lack robustness against malwares that are carefully crafted to evade detection. These specially crafted pieces of malware are referred to as adversarial examples. We consider a clever adversary who has a thorough knowledge of DNN-based malware classifiers and will exploit it to generate a crafty malware to fool DNN-based classifiers. In this paper, we propose a DNN-based malware classifier that becomes resilient to these kinds of attacks by exploiting Generative Adversarial Network (GAN) based data augmentation. The experimental results show that the proposed scheme classifies malware, including AEs, with a false positive rate (FPR) of 3.0% and a balanced accuracy of 70.16%. These are respective 26.1% and 18.5% enhancements when compared to a traditional DNN-based classifier that does not exploit GAN.

• Progress in Superconductivity
• /
• v.3 no.1
• /
• pp.56-59
• /
• 2001

We have constructed a multi-channel SQUID magnetometer system for localization and classification of magnetic targets. Ten SQUID magnetometers were arranged to measure 5 independent components of 3 $\times$ 3 magnetic field gradient tensor. To get gradient from the difference of magnetic field measurements, we carefully balanced magnetometers. SQUIDs with slotted washer were used for operation in an unshielded laboratory environment, and noise characteristic in the laboratory was measured. With the multi-channel SQUID magnetometer system, we have successfully traced the motion of a bar magnet moving around it at a distance of about 1 m. In the urban environment, the drift of uniform magnetic field due to the irregular motion of a large magnetic body at distance and earth field causes an error in the position calculation, and this results in the distortion of the calculated trajectory. In this paper, we present the architecture and the performance of the system.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.27-34
• /
• 2001

Utterance verification is used in variable vocabulary word recognition to reject the word that does not belong to in-vocabulary word or does not belong to correctly recognized word. Utterance verification is an important technology to design a user-friendly speech recognition system. We propose a new utterance verification algorithm for no-training utterance verification system based on the minimum verification error. First, using PBW (Phonetically Balanced Words) DB (445 words), we create no-training anti-phoneme models which include many PLUs(Phoneme Like Units), so anti-phoneme models have the minimum verification error. Then, for OOV (Out-Of-Vocabulary) rejection, the phoneme-based confidence measure which uses the likelihood between phoneme model (null hypothesis) and anti-phoneme model (alternative hypothesis) is normalized by null hypothesis, so the phoneme-based confidence measure tends to be more robust to OOV rejection. And, the word-based confidence measure which uses the phoneme-based confidence measure has been shown to provide improved detection of near-misses in speech recognition as well as better discrimination between in-vocabularys and OOVs. Using our proposed anti-model and confidence measure, we achieve significant performance improvement; CA (Correctly Accept for In-Vocabulary) is about 89％, and CR (Correctly Reject for OOV) is about 90％, improving about 15-21％ in ERR (Error Reduction Rate).

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.345-353
• /
• 2021

Cloud computing represent a new era of computing that's forms through the combination of service-oriented architecture (SOA), Internet and grid computing with virtualization technology. Virtualization is a concept through which every cloud is enable to provide on-demand services to the users. Most IT service provider adopt cloud based services for their users to meet the high demand of computation, as it is most flexible, reliable and scalable technology. Energy based performance tradeoff become the main challenge in cloud computing, as its acceptance and popularity increases day by day. Cloud data centers required a huge amount of power supply to the virtualization of servers for maintain on- demand high computing. High power demand increase the energy cost of service providers as well as it also harm the environment through the emission of CO₂. An optimization of cloud computing based on energy-performance tradeoff is required to obtain the balance between energy saving and QoS (quality of services) policies of cloud. A study about power usage of resources in cloud data centers based on workload assign to them, says that an idle server consume near about 50% of its peak utilization power [1]. Therefore, more number of underutilized servers in any cloud data center is responsible to reduce the energy performance tradeoff. To handle this issue, a lots of research proposed as energy efficient algorithms for minimize the consumption of energy and also maintain the SLA (service level agreement) at a satisfactory level. VM (virtual machine) consolidation is one such technique that ensured about the balance of energy based SLA. In the scope of this paper, we explore reinforcement with fuzzy logic (RFL) for VM consolidation to achieve energy based SLA. In this proposed RFL based active VM consolidation, the primary objective is to manage physical server (PS) nodes in order to avoid over-utilized and under-utilized, and to optimize the placement of VMs. A dynamic threshold (based on RFL) is proposed for over-utilized PS detection. For over-utilized PS, a VM selection policy based on fuzzy logic is proposed, which selects VM for migration to maintain the balance of SLA. Additionally, it incorporate VM placement policy through categorization of non-overutilized servers as- balanced, under-utilized and critical. CloudSim toolkit is used to simulate the proposed work on real-world work load traces of CoMon Project define by PlanetLab. Simulation results shows that the proposed policies is most energy efficient compared to others in terms of reduction in both electricity usage and SLA violation.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.453-462
• /
• 2021

A lot of license plate data is required for car number recognition. License plate data needs to be balanced from past license plates to the latest license plates. However, it is difficult to obtain data from the actual past license plate to the latest ones. In order to solve this problem, a license plate recognition study through deep learning is being conducted by creating a synthetic license plates. Since the synthetic data have differences from real data, and various data augmentation techniques are used to solve these problems. Existing data augmentation simply used methods such as brightness, rotation, affine transformation, blur, and noise. In this paper, we apply a style transformation method that transforms synthetic data into real-world data styles with data augmentation methods. In addition, real license plate data are noisy when it is captured from a distance and under the dark environment. If we simply recognize characters with input data, chances of misrecognition are high. To improve character recognition, in this paper, we applied the DeblurGANv2 method as a quality improvement method for character recognition, increasing the accuracy of license plate recognition. The method of deep learning for license plate detection and license plate number recognition used YOLO-V5. To determine the performance of the synthetic license plate data, we construct a test set by collecting our own secured license plates. License plate detection without style conversion recorded 0.614 mAP. As a result of applying the style transformation, we confirm that the license plate detection performance was improved by recording 0.679mAP. In addition, the successul detection rate without image enhancement was 0.872, and the detection rate was 0.915 after image enhancement, confirming that the performance improved.

• Korean Journal of Optics and Photonics
• /
• v.20 no.1
• /
• pp.29-33
• /
• 2009

We propose a new measuring technique based on optical low-coherence reflectometry that enables us to determine the refractive index and the geometrical thickness of a transparent sample by one-time scanning only. By passing a collimated beam having a finite size through the edge of the sample, the refractive index and the geometrical thickness can be determined simultaneously from the comparison of interferograms generated by two kinds of reflected beams. In this study, a refractive index could be determined with the accuracy of $10^{-3}$, and its accuracy would be enhanced by using a more precise translator and a thicker sample.