• ETRI Journal
• /
• 제46권2호
• /
• pp.290-306
• /
• 2024

To treat the novel COronaVIrus Disease (COVID), comparatively fewer medicines have been approved. Due to the global pandemic status of COVID, several medicines are being developed to treat patients. The modern COVID medicines development process has various challenges, including predicting and detecting hazardous COVID medicine responses. Moreover, correctly predicting harmful COVID medicine reactions is essential for health safety. Significant developments in computational models in medicine development can make it possible to identify adverse COVID medicine reactions. Since the beginning of the COVID pandemic, there has been significant demand for developing COVID medicines. Therefore, this paper presents the transferlearning methodology and a multilabel convolutional neural network for COVID (MLCNN-COV) medicines development model to identify negative responses of COVID medicines. For analysis, a framework is proposed with five multilabel transfer-learning models, namely, MobileNetv2, ResNet50, VGG19, DenseNet201, and Inceptionv3, and an MLCNN-COV model is designed with an image augmentation (IA) technique and validated through experiments on the image of three-dimensional chemical conformer of 17 number of COVID medicines. The RGB color channel is utilized to represent the feature of the image, and image features are extracted by employing the Convolution2D and MaxPooling2D layer. The findings of the current MLCNN-COV are promising, and it can identify individual adverse reactions of medicines, with the accuracy ranging from 88.24% to 100%, which outperformed the transfer-learning model's performance. It shows that three-dimensional conformers adequately identify negative COVID medicine responses.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.399-401
• /
• 2022

유방 악성 상태를 분류하기 위한 최종 진단은 침습적 생검을 이용한 현미경 분석을 통해 확인이 가능하나, 분석을 위해 일정 시간과 비용이 부과되며, 병리학적 지식을 보유한 전문가가 필요하다. 이러한 문제를 극복하기 위해, 딥 러닝을 활용한 진단 기법은 조직병리학적 이미지에서 유방암을 양성 및 악성으로 분류에 효율적인 방법으로 고려된다. 본 연구는 유방암 조직병리학적 이미지를 40배 확대한 BreaKHIS 데이터 세트를 사용하여 양성 및 악성으로 분류하였으며, 100% 미세 조정 체계와 Adagrad를 이용한 최적화로 사전 훈련된 컨볼루션 신경망 모델 아키텍처를 사용하였다. 사전 훈련된 아키텍처는 InceptionResNetV2 모델을 사용하여 마지막 계층을 고밀도 계층과 드롭아웃 계층으로 대체하여 수정된 InceptionResNetV2를 생성하도록 구성되었다. 훈련 손실 0.25%, 훈련 정확도 99.96%, 검증 손실 3.10%, 검증 정확도 99.41%, 테스트 손실 8.46%와 테스트 정확도 98.75%를 입증한 결과는 수정된 InceptionResNetV2 모델이 조직병리학적 이미지에서 유방 악성 유형을 예측하는 데 신뢰할 수 있음을 보여주었다. 향후 연구는 k-폴드 교차 검증, 최적화, 모델, 초 매개 변수 최적화 및 100×, 200× 및 400× 배율에 대한 분류에 초점을 맞추어 추가실험이 필요하다.

• 문화기술의 융합
• /
• 제6권4호
• /
• pp.789-795
• /
• 2020

전 세계적으로 유행하는 코로나19로 인해 많은 사망자가 보고되고 있다. 코로나19의 추가 확산을 막기 위해서는 의심 환자에 대해 신속하고 정확한 영상판독을 한 후, 적절한 조치를 취해야 한다. 이를 위해 본 논문은 환자의 감염 여부를 의료진에게 제공해 영상판독을 보조할 수 있는 딥 러닝 기반 코로나19 흉부 X선 판독 기법을 소개한다. 우선 판독모델을 학습하기 위해서는 충분한 데이터셋이 확보되어야 하는데, 현재 제공하는 코로나19 오픈 데이터셋은 학습의 정확도를 보장하기에 그 영상 데이터 수가 충분하지 않다. 따라서 누적 적대적 생성 신경망(StackGAN++)을 사용해 인공지능 학습 성능을 저하하는 영상 데이터 수적 불균형 문제를 해결하였다. 다음으로 판독모델 개발을 위해 증강된 데이터셋을 사용하여 DenseNet 기반 분류모델 학습을 진행하였다. 해당 분류모델은 정상 흉부 X선과 코로나 19 흉부 X선 영상을 이진 분류하는 모델로, 실제 영상 데이터 일부를 테스트데이터로 사용하여 모델의 성능을 평가하였다. 마지막으로 설명 가능한 인공지능(eXplainable AI, XAI) 중 하나인 Grad-CAM을 사용해 입력 영상의 질환유무를 판단하는 근거를 제시하여 모델의 신뢰성을 확보하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2131-2153
• /
• 2022

To achieve accurate detection of tuberculosis (TB) areas in chest radiographs, we design a chest X-ray TB area detection algorithm. The algorithm consists of two stages: the chest X-ray TB classification network (CXTCNet) and the chest X-ray TB area detection network (CXTDNet). CXTCNet is used to judge the presence or absence of TB areas in chest X-ray images, thereby excluding the influence of other lung diseases on the detection of TB areas. It can reduce false positives in the detection network and improve the accuracy of detection results. In CXTCNet, we propose a channel attention mechanism (CAM) module and combine it with DenseNet. This module enables the network to learn more spatial and channel features information about chest X-ray images, thereby improving network performance. CXTDNet is a design based on a sparse object detection algorithm (Sparse R-CNN). A group of fixed learnable proposal boxes and learnable proposal features are using for classification and location. The predictions of the algorithm are output directly without non-maximal suppression post-processing. Furthermore, we use CLAHE to reduce image noise and improve image quality for data preprocessing. Experiments on dataset TBX11K show that the accuracy of the proposed CXTCNet is up to 99.10%, which is better than most current TB classification algorithms. Finally, our proposed chest X-ray TB detection algorithm could achieve AP of 45.35% and AP50 of 74.20%. We also establish a chest X-ray TB dataset with 304 sheets. And experiments on this dataset showed that the accuracy of the diagnosis was comparable to that of radiologists. We hope that our proposed algorithm and established dataset will advance the field of TB detection.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.613-626
• /
• 2022

Guaranteeing the quality and integrity of structural health monitoring (SHM) data is very important for an effective assessment of structural condition. However, sensory system may malfunction due to sensor fault or harsh operational environment, resulting in multiple types of data anomaly existing in the measured data. Efficiently and automatically identifying anomalies from the vast amounts of measured data is significant for assessing the structural conditions and early warning for structural failure in SHM. The major challenges of current automated data anomaly detection methods are the imbalance of dataset categories. In terms of the feature of actual anomalous data, this paper proposes a data anomaly detection method based on data-level and deep learning technique for SHM of civil engineering structures. The proposed method consists of a data balancing phase to prepare a comprehensive training dataset based on data-level technique, and an anomaly detection phase based on a sophisticatedly designed network. The advanced densely connected convolutional network (DenseNet) and Transformer encoder are embedded in the specific network to facilitate extraction of both detail and global features of response data, and to establish the mapping between the highest level of abstractive features and data anomaly class. Numerical studies on a steel frame model are conducted to evaluate the performance and noise immunity of using the proposed network for data anomaly detection. The applicability of the proposed method for data anomaly classification is validated with the measured data of a practical supertall structure. The proposed method presents a remarkable performance on data anomaly detection, which reaches a 95.7% overall accuracy with practical engineering structural monitoring data, which demonstrates the effectiveness of data balancing and the robust classification capability of the proposed network.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.628-631
• /
• 2014

최근 다양한 형태의 스마트 기기 출현과 대중적 보급으로 인해 고속 데이터 전송에 대한 수요가 나날이 증가하고 있다. 이런 요구사항을 수용하기 위해 셀룰러 사업자 및 이동통신 장비 제조업체는 많은 새로운 기술에 대한 연구를 진행하였으며 이에 대한 결과로 향후 셀룰러 네트워크에서 성능 및 커버리지 향상을 위해 소형셀 기술을 하나의 중요한 요소 기술로 고려하고 있다. 셀룰러 네트워크에서 소형셀 기술은 데이터 요구량이 많은 위치에 소형셀을 밀집 배치하고 매크로 기지국 및 소형셀 기지국의 밀접한 협력을 통해 무선 네트워크의 용량을 증가시키는 것을 의미한다. 따라서 본 논문에서는 매크로 셀과 소형 셀이 다층으로 배치된 셀룰러 이동통신 구조를 제시하고 다층셀간의 협력을 통해 성능을 향상시킬 수 있는 다양한 요소기술들에 대해서 기술한다. 또, 이들 요소기술들을 바탕으로 최근 3GPP에서 활발히 논의되고 있는 LTE 소형셀 향상 표준화 동향에 대해 기술한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.2924-2944
• /
• 2023

Alzheimer's disease (AD) is a neurological condition that is recognized as one of the primary causes of memory loss. AD currently has no cure. Therefore, the need to develop an efficient model with high precision for timely detection of the disease is very essential. When AD is detected early, treatment would be most likely successful. The most often utilized indicators for AD identification are the Mini-mental state examination (MMSE), and the clinical dementia. However, the use of these indicators as ground truth marking could be imprecise for AD detection. Researchers have proposed several computer-aided frameworks and lately, the supervised model is mostly used. In this study, we propose a novel 3D Convolutional Neural Network Multilayer Perceptron (3D CNN-MLP) based model for AD classification. The model uses Attention Mechanism to automatically extract relevant features from Magnetic Resonance Images (MRI) to generate probability maps which serves as input for the MLP classifier. Three MRI scan categories were considered, thus AD dementia patients, Mild Cognitive Impairment patients (MCI), and Normal Control (NC) or healthy patients. The performance of the model is assessed by comparing basic CNN, VGG16, DenseNet models, and other state of the art works. The models were adjusted to fit the 3D images before the comparison was done. Our model exhibited excellent classification performance, with an accuracy of 91.27% for AD and NC, 80.85% for MCI and NC, and 87.34% for AD and MCI.

• 지능정보연구
• /
• 제16권4호
• /
• pp.159-172
• /
• 2010

협업필터링 추천은 다양한 분야에서 활용되고 있지만 트랜잭션 데이터의 성격에 따라 추천 성능에 현저한 차이를 보이고 있다. 기존 연구에서는 이러한 추천 성능의 차이가 나타나는 이유에 대한 설명을 구체적으로 제시하지 못하고 있고 이에 따라 추천 성능의 예측 또한 연구된 바가 없다. 본 연구는 사회네트워크분석과 인공신경망 모형을 이용하여 협업필터링 추천시스템의 성능을 예측하고자 한다. 본 연구의 목적을 달성하기 위해 국내 백화점의 트랜잭션 데이터를 기반으로 형성되는 고객간 사회 네트워크의 구조적 지표를 측정한 후 이를 기반으로 인공신경망 모형을 구축하고 검증한다. 본 연구는 협업필터링 추천 성능을 예측할 수 있는 새로운 모형을 제시하였다는 점에서 그 의의가 있으며 이를 통해 기업들의 협업필터링 추천시스템 도입에 대한 의사결정에 도움을 줄 수 있을 것으로 기대된다.

• Korean Journal of Radiology
• /
• 제23권10호
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.131-138
• /
• 2022

Novel Coronavirus (COVID-19) is viewed as one of the main general wellbeing theaters on the worldwide level all over the planet. Because of the abrupt idea of the flare-up and the irresistible force of the infection, it causes individuals tension, melancholy, and other pressure responses. The avoidance and control of the novel Covid pneumonia have moved into an imperative stage. It is fundamental to early foresee and figure of infection episode during this troublesome opportunity to control of its grimness and mortality. The entire world is investing unimaginable amounts of energy to fight against the spread of this lethal infection. In this paper, we utilized machine learning and deep learning techniques for analyzing what is going on utilizing countries shared information and for detecting the climate factors that effect on spreading Covid-19, such as humidity, sunny hours, temperature and wind speed for understanding its regular dramatic way of behaving alongside the forecast of future reachability of the COVID-2019 around the world. We utilized data collected and produced by Kaggle and the Johns Hopkins Center for Systems Science. The dataset has 25 attributes and 9566 objects. Our Experiment consists of two phases. In phase one, we preprocessed dataset for DL model and features were decreased to four features humidity, sunny hours, temperature and wind speed by utilized the Pearson Correlation Coefficient technique (correlation attributes feature selection). In phase two, we utilized the traditional famous six machine learning techniques for numerical datasets, and Dense Net deep learning model to predict and detect the climatic factor that aide to disease outbreak. We validated the model by using confusion matrix (CM) and measured the performance by four different metrics: accuracy, f-measure, recall, and precision.