• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1203-1211
• /
• 2022

Melanoma is a skin cancer that starts in pigment-producing cells (melanocytes). The death rates of skin cancer like melanoma can be reduced by early detection and diagnosis of diseases. It is common for doctors to spend a lot of time trying to distinguish between skin lesions and healthy cells because of their striking similarities. The detection of melanoma lesions can be made easier for doctors with the help of an automated classification system that uses deep learning. This study presents a new approach for melanoma classification based on an ensemble of deep convolution neural networks and a Log-Gabor filter. First, we create the Log-Gabor representation of the original image. Then, we input the Log-Gabor representation into a new ensemble of deep convolution neural networks. We evaluated the proposed method on the melanoma dataset collected at Yonsei University and Dongsan Clinic. Based on our numerical results, the proposed framework achieves more accuracy than other approaches.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1212-1223
• /
• 2022

Skin lesions are common diseases that range from skin rashes to skin cancer, which can lead to death. Note that early diagnosis of skin diseases can be important because early diagnosis of skin diseases considerably can reduce the course of treatment and the harmful effect of the disease. Recently, the development of computer-aided diagnosis (CAD) systems based on artificial intelligence has been actively made for the early diagnosis of skin diseases. In a typical CAD system, the accurate classification of skin lesion types is of great importance for improving the diagnosis performance. Motivated by this, we propose a novel deep ensemble classification with multi-scale attention networks. The proposed deep ensemble networks are jointly trained using a single loss function in an end-to-end manner. In addition, the proposed deep ensemble network is equipped with a multi-scale attention mechanism and segmentation information of the original skin input image, which improves the classification performance. To demonstrate our method, the publicly available human skin disease dataset (HAM 10000) and the private animal skin lesion dataset were used for the evaluation. Experiment results showed that the proposed methods can achieve 97.8% and 81% accuracy on each HAM10000 and animal skin lesion dataset. This research work would be useful for developing a more reliable CAD system which helps doctors early diagnose skin diseases.

• 한국멀티미디어학회논문지
• /
• 제22권6호
• /
• pp.665-675
• /
• 2019

In this paper, we compare and analyze the classification performance of deep learning algorithm Convolutional Neural Network(CNN) ac cording to ensemble generation and combining techniques. We used several CNN models(VGG16, VGG19, DenseNet121, DenseNet169, DenseNet201, ResNet18, ResNet34, ResNet50, ResNet101, ResNet152, GoogLeNet) to create 10 ensemble generation combinations and applied 6 combine techniques(average, weighted average, maximum, minimum, median, product) to the optimal combination. Experimental results, DenseNet169-VGG16-GoogLeNet combination in ensemble generation, and the product rule in ensemble combination showed the best performance. Based on this, it was concluded that ensemble in different models of high benchmarking scores is another way to get good results.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.

• 한국컴퓨터정보학회논문지
• /
• 제26권1호
• /
• pp.27-35
• /
• 2021

본 연구에서는 레이블 임베딩의 분포를 반영하는 딥러닝 모형을 위한 새로운 스태킹 앙상블 방법론을 제안하였다. 제안된 앙상블 방법론은 기본 딥러닝 분류기를 학습하는 과정과 학습된 모형으로 부터 얻어진 레이블 임베딩을 이용한 군집화 결과로부터 소분류기들을 학습하는 과정으로 이루어져 있다. 본 방법론은 주어진 다중 분류 문제를 군집화 결과를 활용하여 소 문제들로 나누는 것을 기본으로 한다. 군집화에 사용되는 레이블 임베딩은 처음 학습한 기본 딥러닝 분류기의 마지막 층의 가중치로부터 얻어질 수 있다. 군집화 결과를 기반으로 군집화 내의 클래스들을 분류하는 소분류기들을 군집의 수만큼 구축하여 학습한다. 실험 결과 기본 분류기로부터의 레이블 임베딩이 클래스 간의 관계를 잘 반영한다는 것을 확인하였고, 이를 기반으로 한 앙상블 방법론이 CIFAR 100 데이터에 대해서 분류 성능을 향상시킬 수 있다는 것을 확인할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제27권11호
• /
• pp.29-38
• /
• 2022

본 논문에서는 멀티 센서가 장착된 스마트 인솔로 측정한 보행 데이터에 대해 앙상블 딥러닝 네트워크를 이용하여 보행의 타입을 분류하는 시스템을 제안한다. 보행 타입 분류 시스템은 인솔에 의해 측정된 데이터를 정규화하는 부분과 딥러닝 네트워크를 이용하여 보행의 특징을 추출하는 부분, 그리고 추출된 특징을 입력으로 보행의 타입을 분류하는 부분으로 구성되어 있다. 서로 다른 특성을 가지는 CNN과 LSTM을 기반으로 하는 네트워크를 독립적으로 학습하여 두 종류의 보행 특징 맵을 추출하였으며, 각각의 분류 결과를 결합하여 최종적인 앙상블 네트워크의 분류 결과를 도출하였다. 20~30대 성인의 걷기, 뛰기, 빠르게 걷기, 계단 오르기와 내려가기, 언덕 오르기와 내려가기의 7종류의 보행에 대해, 스마트 인솔을 이용하여 실측한 멀티 센서 데이터를 제안한 앙상블 네트워크로 분류해 본 결과 90% 이상의 높은 분류율을 보이는 것을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.39-51
• /
• 2022

Image-based gender classification and age estimation of human are classic problems in computer vision. Most of researches in this field focus just only one task of either gender classification or age estimation and most of the reported methods for each task focus on accuracy performance and are not computationally light. Thus, running both tasks together simultaneously on low cost mobile or embedded systems with limited cpu processing speed and memory capacity are practically prohibited. In this paper, we propose a novel light-weight gender classification and age estimation method based on ensemble multitasking deep learning with light-weight processing neural network architecture, which processes both gender classification and age estimation simultaneously and in real-time even for embedded systems. Through experiments over various well-known datasets, it is shown that the proposed method performs comparably to the state-of-the-art gender classification and/or age estimation methods with respect to accuracy and runs fast enough (average 14fps) on a Jestson Nano embedded board.

• 한국컴퓨터정보학회논문지
• /
• 제26권7호
• /
• pp.37-44
• /
• 2021

뇌 MRI 영상의 자동 분류는 뇌종양의 조기 진단을 하는 데 있어 중요한 역할을 한다. 본 연구에서 우리는 심층 특징 앙상블을 사용한 MRI 영상에서의 딥 러닝 기반 뇌종양 분류 모델을 제안한다. 우선 사전 학습된 3개의 합성 곱 신경망을 사용하여 입력 MRI 영상에 대한 심층 특징들을 추출한다. 그 이후 추출된 심층 특징들은 완전 연결 계층들로 구성된 분류 모듈의 입력 값으로 들어간다. 분류 모듈에서는 우선 3개의 서로 다른 심층 특징들 각각에 대해 먼저 완전 연결 계층을 거쳐 특징 차원을 줄인다. 그 이후 3개의 차원이 준 특징들을 결합하여 하나의 특징 벡터를 생성한 뒤 다시 완전 연결 계층의 입력값으로 들어가서 최종적인 분류 결과를 예측한다. 우리가 제안한 모델을 평가하기 위해 웹상에 공개된 뇌 MRI 데이터 셋을 사용하였다. 실험 결과 우리가 제안한 모델이 다른 기계학습 기반 모델보다 더 좋은 성능을 나타냄을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.632-657
• /
• 2022

Detecting web attacks is a major challenge, and it is observed that the use of simple models leads to low sensitivity or high false positive problems. In this study, we aim to develop a robust two-stage deep learning based stacked ensemble web application firewall. Normal and abnormal classification is carried out in the first stage of the proposed WAF model. The classification process of the types of abnormal traffics is postponed to the second stage and carried out using an integrated stacked ensemble model. By this way, clients' requests can be served without time delay, and attack types can be detected with high sensitivity. In addition to the high accuracy of the proposed model, by using the statistical similarity and diversity analyses in the study, high generalization for the ensemble model is achieved. Within the study, a comprehensive, up-to-date, and robust multi-class web anomaly dataset named GAZI-HTTP is created in accordance with the real-world situations. The performance of the proposed WAF model is compared to state-of-the-art deep learning models and previous studies using the benchmark dataset. The proposed two-stage model achieved multi-class detection rates of 97.43% and 94.77% for GAZI-HTTP and ECML-PKDD, respectively.

• 한국BIM학회 논문집
• /
• 제12권2호
• /
• pp.12-25
• /
• 2022

To increase the usability of Building Information Modeling (BIM) in construction projects, it is critical to ensure the interoperability of data between heterogeneous BIM software. The Industry Foundation Classes (IFC), an international ISO format, has been established for this purpose, but due to its structural complexity, geometric information and properties are not always transmitted correctly. Recently, deep learning approaches have been used to learn the shapes of the BIM elements and thereby verify the mapping between BIM elements and IFC entities. These models performed well for elements with distinct shapes but were limited when their shapes were highly similar. This study proposed a method to improve the performance of the element type classification by using an Ensemble model that leverages not only shapes characteristics but also the relational information between individual BIM elements. The accuracy of the Ensemble model, which merges MVCNN and MLP, was improved 0.03 compared to the existing deep learning model that only learned shape information.