• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.317-326
• /
• 2024

생체 인식은 사람의 생체적, 행동적 특징 정보를 특정 장치로 추출하여 본인 여부를 판별하는 기술이다. 생체 인식 분야에서 생체 특성 위조, 복제, 해킹 등 사이버 위협이 증가하고 있다. 이에 대응하여 보안 시스템이 강화되고 복잡해지며, 개인이 사용하기 어려워지고 있다. 이를 위해 다중 생체 인식 모델이 연구되고 있다. 기존 연구들은 특징 융합 방법을 제시하고 있으나, 특징 융합 방법 간의 비교는 부족하다. 이에 본 논문에서는 지문, 얼굴, 홍채 영상을 이용한 다중 생체 인식 모델의 융합 방법을 비교 평가했다. 특징 추출을 위해VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, Inception-v3를 사용했으며, 특성융합을 위해 'Sensor-Level', 'Feature-Level', 'Score-Level', 'Rank-Level' 융합 방법을 비교 평가했다. 비교평가결과 'Feature-Level' 융합 방법에서 EfficientNet-B7 모델이 98.51%의 정확도를 보이며 높은 안정성을 보였다. 그러나 EfficietnNet-B7모델의 크기가 크기 때문에 생체 특성 융합을 위한 모델 경량화 연구가 필요하다.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.374-383
• /
• 2024

Objective: To evaluate the diagnostic performance and image quality of 1.5-mm slice thickness MRI with deep learningbased image reconstruction (1.5-mm MRI + DLR) compared to routine 3-mm slice thickness MRI (routine MRI) and 1.5-mm slice thickness MRI without DLR (1.5-mm MRI without DLR) for evaluating temporal lobe epilepsy (TLE). Materials and Methods: This retrospective study included 117 MR image sets comprising 1.5-mm MRI + DLR, 1.5-mm MRI without DLR, and routine MRI from 117 consecutive patients (mean age, 41 years; 61 female; 34 patients with TLE and 83 without TLE). Two neuroradiologists evaluated the presence of hippocampal or temporal lobe lesions, volume loss, signal abnormalities, loss of internal structure of the hippocampus, and lesion conspicuity in the temporal lobe. Reference standards for TLE were independently constructed by neurologists using clinical and radiological findings. Subjective image quality, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were analyzed. Performance in diagnosing TLE, lesion findings, and image quality were compared among the three protocols. Results: The pooled sensitivity of 1.5-mm MRI + DLR (91.2%) for diagnosing TLE was higher than that of routine MRI (72.1%, P < 0.001). In the subgroup analysis, 1.5-mm MRI + DLR showed higher sensitivity for hippocampal lesions than routine MRI (92.7% vs. 75.0%, P = 0.001), with improved depiction of hippocampal T2 high signal intensity change (P = 0.016) and loss of internal structure (P < 0.001). However, the pooled specificity of 1.5-mm MRI + DLR (76.5%) was lower than that of routine MRI (89.2%, P = 0.004). Compared with 1.5-mm MRI without DLR, 1.5-mm MRI + DLR resulted in significantly improved pooled accuracy (91.2% vs. 73.1%, P = 0.010), image quality, SNR, and CNR (all, P < 0.001). Conclusion: The use of 1.5-mm MRI + DLR enhanced the performance of MRI in diagnosing TLE, particularly in hippocampal evaluation, because of improved depiction of hippocampal abnormalities and enhanced image quality.

• Korean Journal of Radiology
• /
• 제23권2호
• /
• pp.264-270
• /
• 2022

Objective: This study aimed to investigate the usefulness of bone single-positron emission tomography/computed tomography (SPECT/CT) of the hip in predicting the later occurrence of avascular necrosis (AVN) after slipped capital femoral epiphysis (SCFE) or femoral neck fracture in pediatric patients. The quantitative parameters of SPECT/CT useful in predicting AVN were identified. Materials and Methods: Twenty-one (male:female, 10:11) consecutive patients aged < 18 years (mean age ± standard deviation [SD], 11.0 ± 2.7 years) who underwent surgery for SCFE or femoral neck fracture and postoperative bone SPECT/CT were included. The maximum standardized uptake value (SUV), mean SUV, and minimum SUV of the femoral head were measured. The ratios of the maximum SUV, mean SUV, and minimum SUV of the affected femoral head to the contralateral side were determined. Patients were followed up for > 1 year after the surgery. The SPECT/CT parameters were compared between patients who developed AVN and those who did not. The accuracy of SPECT/CT parameters for predicting AVN was assessed. Results: Six patients developed AVN. There was a significant difference in the ratio of the mean SUV among patients who developed AVN (mean ± SD, 0.8 ± 0.3) and those who did not (1.1 ± 0.2, p = 0.018). However, there were no significant differences in the ratios of the maximum and minimum SUV between the groups (all p = 0.205). For the maximum, mean, and minimum SUVs, no significant differences were observed between the groups (p = 0.519, 0.733, and 0.470, respectively). The cutoff mean SUV ratio of 0.87 yielded a 66.7% sensitivity and 93.2% specificity for predicting AVN. Conclusion: Quantitative bone SPECT/CT is useful for evaluating femoral head viability in pediatric patients with SCFE or femoral neck fractures. Clinicians should consider the high possibility of later AVN development in patients with a decreased mean SUV ratio.

• Korean Journal of Radiology
• /
• 제20권5호
• /
• pp.791-800
• /
• 2019

Objective: To compare various models of diffusion-weighted imaging including monoexponential apparent diffusion coefficient (ADC), biexponential (fast diffusion coefficient [D_f], slow diffusion coefficient [D_s], and fraction of fast diffusion), stretched-exponential (distributed diffusion coefficient and anomalous exponent term [α]), and kurtosis (mean diffusivity and mean kurtosis [MK]) models in the differentiation of renal solid masses. Materials and Methods: A total of 81 patients (56 men and 25 women; mean age, 57 years; age range, 30-69 years) with 18 benign and 63 malignant lesions were imaged using 3T diffusion-weighted MRI. Diffusion model selection was investigated in each lesion using the Akaike information criteria. Mann-Whitney U test and receiver operating characteristic (ROC) analysis were used for statistical evaluations. Results: Goodness-of-fit analysis showed that the stretched-exponential model had the highest voxel percentages in benign and malignant lesions (90.7% and 51.4%, respectively). ADC, D_s, and MK showed significant differences between benign and malignant lesions (p < 0.05) and between low- and high-grade clear cell renal cell carcinoma (ccRCC) (p < 0.05). α was significantly lower in the benign group than in the malignant group (p < 0.05). All diffusion measures showed significant differences between ccRCC and non-ccRCC (p < 0.05) except D_f and α (p = 0.143 and 0.112, respectively). α showed the highest diagnostic accuracy in differentiating benign and malignant lesions with an area under the ROC curve of 0.923, but none of the parameters from these advanced models revealed significantly better performance over ADC in discriminating subtypes or grades of renal cell carcinoma (RCC) (p > 0.05). Conclusion: Compared with conventional diffusion parameters, α may provide additional information for differentiating benign and malignant renal masses, while ADC remains the most valuable parameter for differentiation of RCC subtypes and for ccRCC grading.

• Korean Journal of Radiology
• /
• 제20권1호
• /
• pp.114-125
• /
• 2019

Objective: Segmented cardiac cine magnetic resonance imaging (MRI) is the gold standard for cardiac ventricular volumetric assessment. In patients with difficulty in breath-holding or arrhythmia, this technique may generate images with inadequate quality for diagnosis. Real-time cardiac cine MRI has been developed to address this limitation. We aimed to assess the performance of retrospective electrocardiography-gated real-time cine MRI at 3T for left ventricular (LV) volume and mass measurement. Materials and Methods: Fifty-one patients were consecutively enrolled. A series of short-axis cine images covering the entire left ventricle using both segmented and real-time balanced steady-state free precession cardiac cine MRI were obtained. End-diastolic volume (EDV), end-systolic volume (ESV), stroke volume (SV), ejection fraction (EF), and LV mass were measured. The agreement and correlation of the parameters were assessed. Additionally, image quality was evaluated using European CMR Registry (Euro-CMR) score and structure visibility rating. Results: In patients without difficulty in breath-holding or arrhythmia, no significant difference was found in Euro-CMR score between the two techniques (0.3 ± 0.7 vs. 0.3 ± 0.5, p > 0.05). Good agreements and correlations were found between the techniques for measuring EDV, ESV, EF, SV, and LV mass. In patients with difficulty in breath-holding or arrhythmia, segmented cine MRI had a significant higher Euro-CMR score (2.3 ± 1.2 vs. 0.4 ± 0.5, p < 0.001). Conclusion: Real-time cine MRI at 3T allowed the assessment of LV volume with high accuracy and showed a significantly better image quality compared to that of segmented cine MRI in patients with difficulty in breath-holding and arrhythmia.

• Korean Journal of Radiology
• /
• 제1권1호
• /
• pp.25-32
• /
• 2000

Objective: The purpose of our study was to determine the ability of H-1 MR spectroscopy (MRS) to lateralize the lesion in patients with hippocampal sclerosis. Materials and Methods: Twenty healthy volunteers and 25 patients with intractable temporal lobe epilepsy whose MR imaging diagnosis was unilateral hippocampal sclerosis were included. This diagnosis was based on the presence of unilateral atrophy and/or high T2 signal intensity of the hippocampus. Single-voxel H-1 MRS was carried out on a 1.5-T unit using PRESS sequence (TE, 136 msec). Spectra were obtained from hippocampal areas bilaterally with volumes of interest (VOIs) of 6.0 cm³ and 2.25 cm³ in healthy volunteers, and of either 6.0 cm³ (n = 14) or 2.25 cm³ (n = 11) in patients. Metabolite ratios of NAA/Cho and NAA/Cr were calculated from relative peak height measurements. The capability of MRS to lateralize the lesion and to detect bilateral abnormalities was compared with MR imaging diagnosis as a standard of reference. Results: In healthy volunteers, NAA/Cho and NAA/Cr ratios were greater than 0.8 and 1.0, respectively. In patients, the mean values of these ratios were significantly lower on the lesion side than on the contralateral side, and lower than those of healthy volunteers (p < .05). The overall correct lateralization rate of MRS was 72% (18/25); this rate was lower with a VOI of 6.0 cm³ than of 2.25 cm³ (64% versus 82%, p < .05). Bilateral abnormalities on MRS were found in 24% (6/25) of cases. Conclusion: Although its rate of correct lateralization is low, single-voxel H-1 MRS is a useful and promising diagnostic tool in the evaluation of hippocampal sclerosis, particularly for the detection of bilateral abnormalities. To improve the diagnostic accuracy of H-1 MRS, further investigation, including the use of a smaller VOI and measurement of the absolute amount of metabolites, are needed.

• 한국음향학회지
• /
• 제43권1호
• /
• pp.29-38
• /
• 2024

정합장처리(Matched Field Processing, MFP)는 음파전달 예측을 기반으로 음원의 거리와 심도를 추정하는 기법이다. 그러나 주파수가 높아지면 음파전달 예측의 부정확성이 증가하여 음원위치 추정이 어렵다. 최근에 제안된 차주파수 정합장처리(Frequency-difference Matched Field Processing, FD-MFP)는 고주파 신호의 자기상관으로부터 추출한 차주파수 곱을 적용함으로써 음속의 오정합 등이 있어도 강인하다고 알려졌다. 본 논문에서는 수평선배열센서에서 차주파수 정합장처리의 성능을 알아보기 위하여, 동해의 환경에서 시뮬레이션을 수행하였다. 장거리 탐지가 가능한 해저면반사(Bottom Bounce, BB)와 수렴구역(Convergence Zone, CZ)이 발생하는 영역에서 위치추정 결과를 분석하였다. 수평선배열센서의 차주파수 정합장처리의 위치추정 정확도는 회절음장과 음속의 오정합에 의해 기존의 정합장처리에 비해 유사하거나 낮아졌다. 시뮬레이션으로부터 차주파수 정합장처리가 기존의 정합장처리보다 오정합에 강인하다는 명확한 결과는 볼 수 없었다.

• 한국수자원학회논문집
• /
• 제57권2호
• /
• pp.73-85
• /
• 2024

하천과 저수지의 수질을 예측하는 것은 수자원관리를 위해 필요하다. 높은 정확도의 수질 예측을 위해 많은 연구들에서 인공신경망이 활용되었다. 기존 연구들은 매개변수를 탐색하는 인공신경망의 연산자인 옵티마이저로 경사하강법 기반 옵티마이저를 사용하였다. 그러나 경사하강법 기반 옵티마이저는 지역 최적값으로의 수렴 가능성과 해의 저장 및 비교구조가 없다는 단점이 있다. 본 연구에서는 인공신경망을 이용한 수질 예측성능을 향상시키기 위해 개량형 옵티마이저를 개발하여 경사하강법 기반 옵티마이저의 단점을 개선하였다. 본 연구에서 제안한 옵티마이저는 경사하강법 기반 옵티마이저 중 학습오차가 낮은 Adaptive moments (Adam)과 Nesterov-accelerated adaptive moments (Nadam)를 Harmony Search(HS) 또는 Novel Self-adaptive Harmony Search (NSHS)와 결합한 옵티마이저이다. 개량형 옵티마이저의 학습 및 예측성능 평가를 위해 개량형 옵티마이저를 Long Short-Term Memory (LSTM)에 적용하여 국내의 다산 수질관측소의 수질인자인 수온, 용존산소량, 수소이온농도 및 엽록소-a를 학습 및 예측하였다. 학습결과를 비교하면, Nadam combined with NSHS (NadamNSHS)를 사용한 LSTM의 Mean Squared Error (MSE)가 0.002921로 가장 낮았다. 또한, 각 옵티마이저별 4개 수질인자에 대한 MSE 및 R²에 따른 예측순위를 비교하였다. 각 옵티마이저의 평균 순위를 비교하면, NadamNSHS를 사용한 LSTM이 2.25로 가장 높은 것을 확인하였다.

• 한국수자원학회논문집
• /
• 제57권2호
• /
• pp.87-97
• /
• 2024

본 연구에서는 국가물관리기본계획의 2030년 물부족량 전망자료를 이용하여 공간군집특성을 고려한 우리나라 물부족 핫스팟 지역을 분석하였다. 물부족 최심 군집지역 도출을 위하여 표준유역 기준의 과거 최대 가뭄(약 50년 빈도)에 대한 물부족량 자료를 이용하여, Local Moran's I와 Getis-Ord Gi* 통계량으로 공간군집분석을 수행하였다. 클러스터맵(Cluster Map)을 통해 물부족 공간군집 대상지역을 선정하고, 공간적 군집 특성은 p-값 및 모란 산점도를 통해 적정성을 검증하였다. 분석 결과, 한강권역 내 1개 군집[임진강하류(#1023) 및 주변]과 낙동강권역 내 2개 군집 [대종천(#2403) 및 주변, 가화천(#2501) 및 주변] 지역이 물부족이 심각한 핫스팟 지역으로 나타났으며, 한강권역 내 1개 군집[남한강하류 (#1007) 및 주변]과 낙동강권역 내 1개 군집[병성천(#2006) 및 주변] 지역이 물부족 HL (해당지역은 물부족량이 많고 주변지역은 물부족량이 적은) 지역으로 나타났다. 표준유역단위 공간군집분석을 수행할 경우 물부족 공간군집지역 전체가 통계량 기준을 100% 만족하여 통계적으로 유의미한 결과가 도출되었다. 이는 표준유역 단위로 공간군집분석을 할 경우 가변적 공간단위 문제를 일정 부분 해결한 것으로 공간군집분석의 정확성이 상대적으로 높아졌다.

• 한국지반신소재학회논문집
• /
• 제23권1호
• /
• pp.39-47
• /
• 2024

본 연구에서는 부산항 신항 및 부산항 북항의 해성점토, 김해와 양산을 포함한 낙동강 중·하류, 울산지역에 분포하고 있는 연약한 점토층에 대하여 물성 시험 및 표준압밀시험을 실시한 후 결과를 활용하여 물성 특성 중 시료의 교란 여부와 관계없고 개인별 시험오차 발생이 작은 물성인 함수비를 이용하여 압축지수, 처녀압축지수, 압밀계수, 팽창지수, 2차압축지수 등을 회귀분석하여 상관성과 정확도를 평가하여 함수비로 압밀정수를 평가 및 산정할 수 있는 방안을 검토하였다. 압축지수를 산정하기 위해 물성 시험 중 가장 많이 활용되는 함수비 및 간극비, 액성한계와 상관성을 분석한 결과 액성한계가 가장 낮은 상관성을 가지는 것으로 확인되었다. 현재 자연상태의 함수비를 활용하여 압밀정수를 선형회귀분석한 결과 높은 상관성을 보여 침하량 및 침하시간을 결정할 수 있는 관계식을 제시하였다. 본 연구결과 부산, 경남지역에 분포하고 있는 퇴적 점토층의 지반침하 검토 시 함수비를 이용하여 압밀정수를 평가 및 산정할 수 있는 대안으로 활용할 수 있다.