• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• 융합보안논문지
• /
• 제23권5호
• /
• pp.135-142
• /
• 2023

생활 폐기물 쓰레기는 기후 변화, 자원 부족, 환경 오염을 불러오는 대표적인 문제로서, 이러한 문제를 해결하기 위해 지능적으로 쓰레기를 분류하는 방식을 연구하였고, 전통적인 분류 알고리즘부터 기계학습, 신경망에 이르기까지 많은 연구가 진행되고 있다. 그러나, 다양한 환경과 조건에서 쓰레기를 분류하기에는 여전히 데이터셋이 부족하고, 신경망 네트워크 구성 복잡도가 증가하며, 성능 측면에서도 실생활에 적용하기에 아직 미흡하다. 따라서 본 논문에서는 신속한 분류와 정확도 향상을 위해 i-YOLOX를 제안하고, 네트워크 매개변수, 검출속도, 정확도 등을 평가한다. 이를 위해 17개의 폐기물 범주를 포함하는 10,000개의 가정용 쓰레기 대상 샘플로 데이터 세트를 구성하고, YOLOX 구조에 Involution 채널 컨볼루션 연산자와 CBAM(Convolution Branch Attention Module)을 도입하여 i-YOLOX를 구성하고, 기존의 YOLO 구조와 성능을 비교한다. 실험 결과 복잡한 장면에서 쓰레기 객체 검출 속도와 정확도가 기존의 신경망에 비해 향상되어, 제안한 i-YOLOX 구조가 생활 폐기물 다중 객체 검출과 분류에 효과적임을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권5호
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2008년도 추계학술대회 논문집 Vol.21
• /
• pp.82-82
• /
• 2008

One-dimensional (1D) nanowires have been received much attention due to their potential for applications in various field. Recently some logic applications fabricated on various nanowires, such as ZnO, CdS, Si, are reported. These logic circuits, which consist of two- or three field effect transistors(FETs), are basic components of computation machine such as central process unit (CPU). FETs fabricated on nanowire generally have surrounded shapes of gate structure, which improve the device performance. Highly integrated circuits can also be achieved by fabricating on nano-scaled nanowires. But the numerical and SPICE simulation about the logic circuitry have never been reported and analyses of detailed parameters related to performance, such as channel doping, gate shapes, souce/drain contact and etc., were strongly needed. In our study, NAND and NOT logic circuits were simulated and characterized using 2- and 3-dimensional numerical simulation (SILVACO ATLAS) and built-in spice module(mixed mode).

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권1호
• /
• pp.51-58
• /
• 2023

본 논문에서는 X-ray 영상에서 의료 진단지표를 자동으로 추출하기 위한 조직분할 기법을 제안한다. 척추질환이나 심장질환에 대한 진단지표로서, 흉추-심장 비율이나 콥 각도 등의 지표를 산출하기 위해서는 흉부 X-ray 영상으로부터 흉추, 용골 및 심장의 영역을 정확하게 분할하는 과정이 필요하다. 본 연구에서는 이를 위하여 계층별로 영상의 고해상도의 표현과 저해상도의 특징지도로 변환되는 구조가 병렬적으로 연결되는 형태의 심층신경망 모델을 채택하였다. 이러한 구조는 영상에서 세부 조직의 상대적인 위치정보가 분할 과정에 효과적으로 반영될 수 있게 한다. 또한 픽셀 정보와 객체 정보가 다단계의 과정으로 상호 작용되는 OCR 모듈과, 네트워크의 각 채널이 서로 다른 가중치 값으로 반영되도록 하는 채널 어텐션 모듈을 결합하여 학습 성능을 개선할 수 있음을 보인다. 부수적으로 X-ray 영상에서 피사체의 위치 변화, 형태의 변형 및 크기 변이 등에도 강인한 성능을 제공하기 위하여 학습데이터를 증강하는 방법을 제시하였다. 총 145개의 인체 흉부 X-ray 영상과, 총 118개의 동물 X-ray 영상을 사용한 실험을 통하여 제안된 이론의 타당성을 평가하였다.