• 한국멀티미디어학회논문지
• /
• 제22권3호
• /
• pp.335-348
• /
• 2019

Cell segmentation and counting represent one of the most important tasks required in order to provide an exhaustive understanding of biological images. Conventional features suffer the lack of spatial consistency by causing the joining of the cells and, thus, complicating the cell counting task. We propose, in this work, a cascade of networks that take as inputs different versions of the original image. After constructing a Gaussian pyramid representation of the microscopy data, the inputs of different size and spatial resolution are given to a cascade of deep convolutional autoencoders whose task is to reconstruct the segmentation mask. The coarse masks obtained from the different networks are summed up in order to provide the final mask. The principal and main contribution of this work is to propose a novel method for the cell counting. Unlike the majority of the methods that use the obtained segmentation mask as the prior information for counting, we propose to utilize the hidden latent representations, often called the high-level features, as the inputs of a neural network based regressor. While the segmentation part of our method performs as good as the conventional deep learning methods, the proposed cell counting approach outperforms the state-of-the-art methods.

• 대한원격탐사학회지
• /
• 제33권4호
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• Nuclear Engineering and Technology
• /
• 제53권3호
• /
• pp.888-893
• /
• 2021

The International Atomic Energy Agency has developed a tomographic imaging system for accomplishing the total fuel rod-by-rod verification time of fuel assemblies within the order of 1-2 h, however, there are still limitations for some fuel types. The aim of this study is to develop a deep learning-based denoising process resulting in increasing the tomographic image acquisition speed of fuel assembly compared to the conventional techniques. Convolutional AutoEncoder (CAE) was employed for denoising the low-quality images reconstructed by filtered back-projection (FBP) algorithm. The image data set was constructed by the Monte Carlo method with the FBP and ground truth (GT) images for 511 patterns of missing fuel rods. The de-noising performance of the CAE model was evaluated by comparing the pixel-by-pixel subtracted images between the GT and FBP images and the GT and CAE images; the average differences of the pixel values for the sample image 1, 2, and 3 were 7.7%, 28.0% and 44.7% for the FBP images, and 0.5%, 1.4% and 1.9% for the predicted image, respectively. Even for the FBP images not discriminable the source patterns, the CAE model could successfully estimate the patterns similarly with the GT image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• Smart Structures and Systems
• /
• 제29권6호
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• 전기전자학회논문지
• /
• 제24권2호
• /
• pp.632-637
• /
• 2020

비간섭적 개별 전기 기기 부하 식별(NILM)은 단일 미터기에서 측정한 총 소비 전력을 사용하여 가정이나 회사에서 개별 전기 기기의 소비 전력과 사용 시간을 효율적으로 모니터링할 수 있는 방법이다. 본 논문에서는 스마트팜의 소비 전력 데이터 취득 시스템에서 LTE 모뎀을 통해 서버로 수집된 총 소비 전력량, 개별 전기 기기의 전력량을 HDF5 형태로 변환하고 NILM 분석을 수행하였다. NILM 분석은 오픈소스를 사용하여 잡음제거 오토인코더(Denoising Autoencoder), 장단기 메모리(Long Short-Term Memory), 게이트 순환 유닛(Gated Recurrent Unit), 시퀀스-투-포인트(sequence-to-point) 학습 방법을 사용하였다.

• 전기전자학회논문지
• /
• 제24권2호
• /
• pp.475-485
• /
• 2020

최근, 별도의 센서를 설치하지 않고 센서가 포함된 사용자의 기기로부터 제공되는 실시간 센싱 데이터를 가지고 새로운 센싱 서비스를 제공하는 크라우드센싱(Crowdsensing) 시스템이 주목받고 있다. 크라우드센싱 시스템에서는 사용자의 조작실수나 통신 문제로 인해 의미 없는 데이터가 제공되거나 보상을 얻기 위해 거짓 데이터를 제공할 수 있어 해당 이상 데이터의 탐지 및 제거가 크라우드센싱 서비스의 질을 결정짓는다. 이러한 이상데이터를 탐지하기 위해 제안되었던 방법들은 크라우드센싱의 빠른 변화 환경에 효율적이지 않다. 본 논문은 머신러닝 기술을 활용하여 지속적이고 빠르게 변화하는 센싱 데이터의 특징을 추출하고 적절한 알고리즘을 통해 모델링하여 이상데이터를 탐지하는 방법을 제안한다. 지도학습의 딥러닝 이진 분류 모델과 비지도학습의 오토인코더 모델을 사용하여 제안 시스템의 성능 및 실현 가능성을 보인다.

• 한국멀티미디어학회논문지
• /
• 제23권1호
• /
• pp.1-7
• /
• 2020

Clustering methods essentially take a two-step approach; extracting feature vectors for dimensionality reduction and then employing clustering algorithm on the extracted feature vectors. However, for clustering images, the traditional clustering methods such as stacked auto-encoder based k-means are not effective since they tend to ignore the local information. In this paper, we propose a method first to effectively reduce data dimensionality using convolutional auto-encoder to capture and reflect the local information and then to accurately cluster similar data samples by using a hierarchical clustering approach. The experimental results confirm that the clustering results are improved by using the proposed model in terms of clustering accuracy and normalized mutual information.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.59-70
• /
• 2020

This paper presents a fully automatic tool to recognize the liver region from CT images based on a deep learning model, namely Multiple Filter U-net, MFUnet. The advantages of both U-net and Multiple Filters were utilized to construct an autoencoder model, called MFUnet for segmenting the liver region from computed tomograph. The MFUnet architecture includes the autoencoding model which is used for regenerating the liver region, the backbone model for extracting features which is trained on ImageNet, and the predicting model used for liver segmentation. The LiTS dataset and Chaos dataset were used for the evaluation of our research. This result shows that the integration of Multiple Filter to U-net improves the performance of liver segmentation and it opens up many research directions in medical imaging processing field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.