• 구강회복응용과학지
• /
• 제38권4호
• /
• pp.196-203
• /
• 2022

목적: 본 연구는 79종의 치과 임플란트에 대해 딥러닝을 이용한 식별 모델의 정확도와 임상적 유용성을 평가하는 것을 목적으로 하였다. 연구 재료 및 방법: 2001년부터 2020년까지 30개 치과에서 임플란트 치료를 받은 환자들의 파노라마 방사선 사진에서 총 45396개의 임플란트 고정체 이미지를 수집했다. 수집된 임플란트 이미지는 18개 제조사의 79개 유형이었다. 모델 학습을 위해 EfficientNet 및 Meta Pseudo Labels 알고리즘이 사용되었다. EfficientNet은 EfficientNet-B0 및 EfficientNet-B4가 하위 모델로 사용되었으며, Meta Pseudo Labels는 확장 계수에 따라 두 가지 모델을 적용했다. EfficientNet에 대해 Top 1 정확도를 측정하고 Meta Pseudo Labels에 대해 Top 1 및 Top 5 정확도를 측정하였다. 결과: EfficientNet-B0 및 EfficientNet-B4는 89.4의 Top 1 정확도를 보였다. Meta Pseudo Labels 1은 87.96의 Top 1 정확도를 보였고, 확장 계수가 증가한 Meta Pseudo Labels 2는 88.35를 나타냈다. Top 5 정확도에서 Meta Pseudo Labels 1의 점수는 97.90으로 Meta Pseudo Labels 2의 97.79보다 0.11% 높았다. 결론: 본 연구에서 임플란트 식별에 사용된 4가지 딥러닝 알고리즘은 모두 90%에 가까운 정확도를 보였다. 임플란트 식별을 위한 딥러닝의 임상적 적용 가능성을 높이려면 더 많은 데이터를 수집하고 임플란트에 적합한 미세 조정 알고리즘의 개발이 필요하다.

• 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.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.

• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.150-158
• /
• 2021

Intracranial hemorrhage (ICH) refers to acute bleeding inside the intracranial vault. Not only does this devastating disease record a very high mortality rate, but it can also cause serious chronic impairment of sensory, motor, and cognitive functions. Therefore, a prompt and professional diagnosis of the disease is highly critical. Noninvasive brain imaging data are essential for clinicians to efficiently diagnose the locus of brain lesion, volume of bleeding, and subsequent cortical damage, and to take clinical interventions. In particular, computed tomography (CT) images are used most often for the diagnosis of ICH. In order to diagnose ICH through CT images, not only medical specialists with a sufficient number of diagnosis experiences are required, but even when this condition is met, there are many cases where bleeding cannot be successfully detected due to factors such as low signal ratio and artifacts of the image itself. In addition, discrepancies between interpretations or even misinterpretations might exist causing critical clinical consequences. To resolve these clinical problems, we developed a diagnostic model predicting intracranial bleeding and its subtypes (intraparenchymal, intraventricular, subarachnoid, subdural, and epidural) by applying deep learning algorithms to CT images. We also constructed a visualization tool highlighting important regions in a CT image for predicting ICH. Specifically, 1) 27,758 CT brain images from RSNA were pre-processed to minimize the computational load. 2) Three different CNN-based models (ResNet, EfficientNet-B2, and EfficientNet-B7) were trained based on a training image data set. 3) Diagnosis performance of each of the three models was evaluated based on an independent test image data set: As a result of the model comparison, EfficientNet-B7's performance (classification accuracy = 91%) was a way greater than the other models. 4) Finally, based on the result of EfficientNet-B7, we visualized the lesions of internal bleeding using the Grad-CAM. Our research suggests that artificial intelligence-based diagnostic systems can help diagnose and treat brain diseases resolving various problems in clinical situations.

• Journal of electromagnetic engineering and science
• /
• 제6권2호
• /
• pp.103-109
• /
• 2006

This paper suggests an efficient and comprehensive algorithm of the protection ratio derivation and illustrates some calculated results applicable to the initial planning of frequency coordination in the fixed wireless access networks. The net filter discrimination associated with Tx spectrum mask and overall Rx filter characteristic has been also examined to show the effect of the adjacent channel interference. The calculations for co-channel and adjacent channel protection ratios are performed for the current microwave frequency band of 6.7 GHz including Tx spectrum mask and Rx filter response. According to results, fade margin and co-channel protection ratio reveal 41.4 and 75.2 dB, respectively, for 64-QAM and 60 km at BER $10^{-6}$. It is shown that the net filter discrimination with 40 MHz channel bandwidth provides 28.9 dB at the first adjacent channel, which yields 46.3 dB of adjacent channel protection ratio. In addition, the protection ratio of 38 GHz radio relay system is also reviewed for millimeter wave band applications. The proposed method gives some advantages of an easy and systematic extension for protection ratio calculation and is also applied to frequency coordination in fixed millimeter wave networks.

• 한국통신학회논문지
• /
• 제36권5B호
• /
• pp.437-442
• /
• 2011

6LoWPAN은 IETF Working Group으로 IEEE 802.15.4 상에서 IPv6 패킷을 전송하는 기술의 표준화를 진행하고 있다. 6LoWPAN WG은 현재 2개의 RFC 문서를 제정하였다. 이 중에 RFC 4944는 단편화, 재조립, 헤더 압축의 기술이 포함되어 있다. 본 논문은 6LoWPAN 노드가 외부 노드와 통신 할 경우에 효율적인 통신 메카니즘을 제안 한다. 이 통신 메카니즘은 6LoWPAN과 외부 네트워크 사이의 게이트웨이가 각 노드 사이에서 프락시 게이트웨이처럼 동작하는 방법을 사용 하였다. 성능 비교 및 분석을 위하여 QualNet으로 시뮬레이션을 하였다. 이를 통하여 제안한 메카니즘과 기존의 RFC 4944의 방법을 비교하여 성능이 향상되었음을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제42권4호
• /
• pp.167-174
• /
• 2021

The purpose of this study is to classify TIFF images, PNG images, and JPEG images using deep learning, and to compare the accuracy by verifying the classification performance. The TIFF, PNG, and JPEG images converted from chest X-ray DICOM images were applied to five deep neural network models performed in image recognition and classification to compare classification performance. The data consisted of a total of 4,000 X-ray images, which were converted from DICOM images into 16-bit TIFF images and 8-bit PNG and JPEG images. The learning models are CNN models - VGG16, ResNet50, InceptionV3, DenseNet121, and EfficientNetB0. The accuracy of the five convolutional neural network models of TIFF images is 99.86%, 99.86%, 99.99%, 100%, and 99.89%. The accuracy of PNG images is 99.88%, 100%, 99.97%, 99.87%, and 100%. The accuracy of JPEG images is 100%, 100%, 99.96%, 99.89%, and 100%. Validation of classification performance using test data showed 100% in accuracy, precision, recall and F1 score. Our classification results show that when DICOM images are converted to TIFF, PNG, and JPEG images and learned through preprocessing, the learning works well in all formats. In medical imaging research using deep learning, the classification performance is not affected by converting DICOM images into any format.

• Nuclear Engineering and Technology
• /
• 제55권10호
• /
• pp.3866-3873
• /
• 2023

In 4th^-generation storage rings, whether to operate the beam as round or flat is a critical question. A round beam has equal horizontal and vertical emittances, and is an efficient solution to reduce strong intra-beam scattering effects and lengthen the Touschek lifetimes, but a flat beam produces a brighter photon beam than a round beam. To provide both beams concurrently rather than bifurcating the beam time, this paper presents the exploitation of beam dynamics and the cutting-edge fast pulser that supports concurrent operation of round beam and flat beam.

• 한국음향학회지
• /
• 제20권4호
• /
• pp.29-34
• /
• 2001

본 논문에서는 고품질 음성 서비스를 가능하게 하는 광대역 음성 부호화기의 선 스펙트럼 주파수 (line spectral frequency: ISF) 계수 양자화기를 설계하였다. 광대역 음성 부호화기를 위한 효율적인 LSF 계수 양자화기를 설계하기 위하여, 인접 프레임간의 상관도를 이용하였으며, 각 해당 프레임의 ISF 계수에 대한 양자화를 인접 프레임간 상관도가 높은 프레임과 상관도가 낮은 프레임으로 나누어 독립적으로 수행하였다. 인접 프레임간 상관도가 높은 프레임의 LSF계수 양자화를 위하여 예측 피라미드형 벡터 양자화기 (predictive pyramid vector quantizer: PPVQ)를 사용하여 양자화하였고, 상관도가 낮은 프레임의 LSF 계수는 피라미드형 벡터 양자화기 (PVQ)를 사용하여 양자화 하였다. PPVQ에서 예측기로 1차 AR 예측기를 사용하였다. 광대역 음성 부호화기를 위해 본 논문에서 설계된 UF 계수양자화기를 평균스펙트럼 왜곡(spectral distortion: SD) 성능 관점에서 실험한 결과, LSF계수 양자화에 할당된 비트가 프레임당 40비트일 때, 평균 SD값이 1 dB 내외이고, 2 dB 이상 및 4 dB 이상 outlier가 각각 3.87%및 0.01%인 transparent한 성능을 얻을 수 있었다.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.175-181
• /
• 2022

COVID-19 is an acute respiratory syndrome that affects the host's breathing and respiratory system. The novel disease's first case was reported in 2019 and has created a state of emergency in the whole world and declared a global pandemic within months after the first case. The disease created elements of socioeconomic crisis globally. The emergency has made it imperative for professionals to take the necessary measures to make early diagnoses of the disease. The conventional diagnosis for COVID-19 is through Polymerase Chain Reaction (PCR) testing. However, in a lot of rural societies, these tests are not available or take a lot of time to provide results. Hence, we propose a COVID-19 classification system by means of machine learning and transfer learning models. The proposed approach identifies individuals with COVID-19 and distinguishes them from those who are healthy with the help of Deep Visual Embeddings (DVE). Five state-of-the-art models: VGG-19, ResNet50, Inceptionv3, MobileNetv3, and EfficientNetB7, were used in this study along with five different pooling schemes to perform deep feature extraction. In addition, the features are normalized using standard scaling, and 4-fold cross-validation is used to validate the performance over multiple versions of the validation data. The best results of 88.86% UAR, 88.27% Specificity, 89.44% Sensitivity, 88.62% Accuracy, 89.06% Precision, and 87.52% F1-score were obtained using ResNet-50 with Average Pooling and Logistic regression with class weight as the classifier.