• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.4
• /
• pp.847-857
• /
• 2018

As the number of malicious code increases steeply, cyber attack victims targeting corporations, public institutions, financial institutions, hospitals are also increasing. Accordingly, academia and security industry are conducting various researches on malicious code detection. In recent years, there have been a lot of researches using machine learning techniques including deep learning. In the case of research using Convolutional Neural Network, ResNet, etc. for classification of malicious code, it can be confirmed that the performance improvement is higher than the existing classification method. However, one of the characteristics of the target attack is that it is custom malicious code that makes it operate only for a specific company, so it is not a form spreading widely to a large number of users. Since there are not many malicious codes of this kind, it is difficult to apply the previously studied machine learning or deep learning techniques. In this paper, we propose a method to classify malicious codes when the amount of samples is insufficient such as targeting type malicious code. As a result of the study, we confirmed that the accuracy of 97% can be achieved even with a small amount of data by applying the Memory Augmented Neural Networks model.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.777-783
• /
• 2022

Even though several deep learning-based methods have been applied in the field of acoustic source localization, the previous works have only been conducted using the two-dimensional representation of the beamforming maps, particularly with the planar array system. While the acoustic sources are more required to be localized in a spherical microphone array system considering that we live and hear in the 3D world, the conventional 2D equirectangular map of the spherical beamforming map is highly vulnerable to the distortion that occurs when the 3D map is projected to the 2D space. In this study, a 3D deep learning approach is proposed to fulfill accurate source localization via distortion-free 3D representation. A target function is first proposed to obtain 3D source distribution maps that can represent multiple sources' positional and strength information. While the proposed target map expands the source localization task into a point-wise prediction task, a PointNet-based deep neural network is developed to precisely estimate the multiple sources' positions and strength information. While the proposed model's localization performance is evaluated, it is shown that the proposed method can achieve improved localization results from both quantitative and qualitative perspectives.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.979-995
• /
• 2023

As wildfires are difficult to predict, real-time monitoring is crucial for a timely response. Geostationary satellite images are very useful for active fire detection because they can monitor a vast area with high temporal resolution (e.g., 2 min). Existing satellite-based active fire detection algorithms detect thermal outliers using threshold values based on the statistical analysis of brightness temperature. However, the difficulty in establishing suitable thresholds for such threshold-based methods hinders their ability to detect fires with low intensity and achieve generalized performance. In light of these challenges, machine learning has emerged as a potential-solution. Until now, relatively simple techniques such as random forest, Vanilla convolutional neural network (CNN), and U-net have been applied for active fire detection. Therefore, this study proposed an active fire detection algorithm using state-of-the-art (SOTA) deep learning techniques using data from the Advanced Himawari Imager and evaluated it over East Asia and Australia. The SOTA model was developed by applying EfficientNet and lion optimizer, and the results were compared with the model using the Vanilla CNN structure. EfficientNet outperformed CNN with F1-scores of 0.88 and 0.83 in East Asia and Australia, respectively. The performance was better after using weighted loss, equal sampling, and image augmentation techniques to fix data imbalance issues compared to before the techniques were used, resulting in F1-scores of 0.92 in East Asia and 0.84 in Australia. It is anticipated that timely responses facilitated by the SOTA deep learning-based approach for active fire detection will effectively mitigate the damage caused by wildfires.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.201-202
• /
• 2018

In this paper, a dog breed image provided by Dataset of existing ImageNet and Oxford-IIIT Pet Image is combined with a dog breed image obtained through data mining on Internet and a random-label is added. this paper introduces to recognize 122 classes of dog breeds and 1 class that is not dog breeds. The recognition rate of dog breeds using both conventional DB and collection DB was improved 1.5% over Top-1 compared to recognition rate of dog breeds using only existing DB. The image recognition rate about non-dog image, was 93% recognition rate in case of 10000 random DBs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.252-255
• /
• 2020

Unsupervised deep learning methods have shown impressive results for the challenging monocular depth estimation task, a field of study that has gained attention in recent years. A common approach for this task is to train a deep convolutional neural network (DCNN) via an image synthesis sub-task, where additional views are utilized during training to minimize a photometric reconstruction error. Previous unsupervised depth estimation networks are trained within a fixed depth estimation range, irrespective of its possible range for a given image, leading to suboptimal estimates. To overcome this suboptimal limitation, we first propose an unsupervised adaptive depth estimation method guided by minimum and maximum (min-max) depth priors for a given input image. The incorporation of min-max depth priors can drastically reduce the depth estimation complexity and produce depth estimates with higher accuracy. Moreover, we propose a novel network architecture for adaptive depth estimation, called the AdaMM-DepthNet, which adopts the min-max depth estimation in its front side. Intensive experimental results demonstrate that the adaptive depth estimation can significantly boost up the accuracy with a fewer number of parameters over the conventional approaches with a fixed minimum and maximum depth range.

• Annual Conference of KIPS
• /
• 2018.10a
• /
• pp.680-682
• /
• 2018

기후변화에 따라 매개 질병의 발병 빈도가 증가하고 있으며 모기와 같은 매개체에 의해 전염되는 매개 질병은 인구집단에 대한 중요한 위협 요인이다. 이러한 질병 관리를 위해 지역별 모기 서식 현황을 모니터링 하는 시스템의 필요성이 강조되고 있다. 하지만 현재의 모기 모니터링은 개체 파악을 위한 분류와 동정을 사람이 직접 수행하기에 오랜 시간이 소요된다. 이 연구는 그러한 문제점을 해결하고 미래 매개곤충 서식 현황 파악 시스템의 기반을 마련하기 위해 심층 신경망(Deep Neural Networks)을 활용하여 한국 주요 매개모기 종 분류를 수행하고 결과를 분석하였다. 종 분류를 위한 모델은 잘 알려진 신경망 모델인 DenseNet(Densely Connected Networks)을 사용하였고 이를 직접 촬영한 모기 데이터와 약간의 변형을 가한 모기 데이터를 사용하여 학습시켰다. 학습 데이터를 각각 5배, 20배, 100배로 증강하여 실제 데이터의 부족을 보완하였으며, 이를 통해 최대 99.48%의 정확도를 달성하였다.

• Nuclear Engineering and Technology
• /
• v.51 no.7
• /
• pp.1784-1790
• /
• 2019

Accurate and consistent characterization of defects in steam generator tubes (SGT) in nuclear power plants is one of the key issues in the field of nondestructive testing since the large number of signals to be analyzed in a time-limited in-service inspection causes a serious problem in practice. This paper presents an effective approach to this difficult task of automated classification of motorized rotating pancake coil (MRPC) eddy current flaw acquired from tube specimens with deliberated defects using deep neural networks (DNN). This approach consists of five steps, namely, the data acquisition using the MRPC probe in the tube, the signal preprocessing to make data more suitable for training DNN, the data augmentation for boosting a training performance, the training of DNN, and finally demonstration of the trained DNN for discriminating the axial and circumferential defects. The high performance obtained in this study shows that DNN is useful for classification of defects in tubes from the MRPC eddy current signals even though the number of signals is very large.

• Journal of information and communication convergence engineering
• /
• v.19 no.2
• /
• pp.79-83
• /
• 2021

This paper proposes a novel image classification method based on few-shot learning, which is mainly used to solve model overfitting and non-convergence in image classification tasks of small datasets and improve the accuracy of classification. This method uses model structure optimization to extend the basic convolutional neural network (CNN) model and extracts more image features by adding convolutional layers, thereby improving the classification accuracy. We incorporated certain measures to improve the performance of the model. First, we used general methods such as setting a lower learning rate and shuffling to promote the rapid convergence of the model. Second, we used the data expansion technology to preprocess small datasets to increase the number of training data sets and suppress over-fitting. We applied the model to 10 monkey species and achieved outstanding performances. Experiments indicated that our proposed method achieved an accuracy of 87.92%, which is 26.1% higher than that of the traditional CNN method and 1.1% higher than that of the deep convolutional neural network ResNet50.

• Journal of Animal Science and Technology
• /
• v.66 no.4
• /
• pp.846-858
• /
• 2024

In a duck cage, ducks are placed in various states. In particular, if a duck is overturned and falls or dies, it will adversely affect the growing environment. In order to prevent the foregoing, it was necessary to continuously manage the cage for duck growth. This study proposes a method using an object detection algorithm to improve the foregoing. Object detection refers to the work to perform classification and localization of all objects present in the image when an input image is given. To use an object detection algorithm in a duck cage, data to be used for learning should be made and the data should be augmented to secure enough data to learn from. In addition, the time required for object detection and the accuracy of object detection are important. The study collected, processed, and augmented image data for a total of two years in 2021 and 2022 from the duck cage. Based on the objects that must be detected, the data collected as such were divided at a ratio of 9 : 1, and learning and verification were performed. The final results were visually confirmed using images different from the images used for learning. The proposed method is expected to be used for minimizing human resources in the growing process in duck cages and making the duck cages into smart farms.