• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1777-1783
• /
• 2021

The use of drones is gradually increasing for the efficient maintenance of large-scale renewable energy power generation complexes. For a long time, photovoltaic panels have been photographed with drones to manage panel loss and contamination. Various approaches using artificial intelligence are being tried for efficient maintenance of large-scale photovoltaic complexes. Recently, semantic segmentation-based application techniques have been developed to solve the image classification problem. In this paper, we propose a classification model using semantic segmentation to determine the presence or absence of failures such as arcs, disconnections, and cracks in solar panel images obtained using a drone equipped with a thermal imaging camera. In addition, an efficient classification model was implemented by tuning several factors such as data size and type and loss function customization in U-Net, which shows robust classification performance even with a small dataset.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.213-219
• /
• 2023

In recent years, popularity of deep learning (DL) is increased due to its ability to extract features from Hyperspectral images. A lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It's also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study.EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy.

• Proceedings of the Korea Institutes of Information Security and Cryptology Conference
• /
• 1998.12a
• /
• pp.443-453
• /
• 1998

본 논문에서는 Petri-net 형태로 침입탐지 규칙을 구성한다. 이것은 실시간 침입탐지가 가능하고 지연공격과 다중공격을 방어할 수 있다. 그리고, Petri-net의 플레이스에 퍼지값을 적용한다. 이 값은 침입의 진행에 따라 변경되며 침입을 판정하는 기준이 된다. 또한, 변형공격에 대응할 수 있도록 한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.9
• /
• pp.148-157
• /
• 2007

A new method which uses distance fields scheme and marching cube algorithm is proposed in order to get an accurate offset model of arbitrary shapes composed of triangular net. In the method, the space bounding the triangular net is divided into smaller cells. For the efficient calculation of distance fields, valid cells which will generate a portion of offset model are selected previously by the suggested detection algorithm. These valid cells are divided again into much smaller voxels which assure required accuracy. At each voxel distance fields are created by calculating the minimum distances between corner points of voxels and triangular net. After generating the whole distance fields, the offset surface were constructed by using the conventional marching cube algorithm together with mesh smoothing scheme. The effectiveness and validity of this new offset method was demonstrated by performing numerical experiments for the various types of triangular net.

• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.1273-1276
• /
• 1998

The HMM-Net is an architecture for a neural network that implements a hidden Markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria used for learning HMM-Net classifiers are maximum likelihood (ML), maximum mutual information (MMI), and minimization of mean squared error(MMSE). In this paper we propose an efficient learning method of HMM-Net classifiers using hybrid criteria, ML/MMSE and MMI/MMSE, and report the results of an experimental study comparing the performance of HMM-Net classifiers trained by the gradient descent algorithm with the above criteria. Experimental results for the isolated numeric digits from /0/ to /9/ show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.41 no.3
• /
• pp.71-82
• /
• 2004

Recently, network model inspired by social insect behavior attracts the public attention. The AntNet is an adaptive and distributed routing algorithm using mobile agents, called ants, that mimic the activities of social insect. In this paper. we present a new hardware architecture to realize an AntNet-based routing in practical system on a chip application. The modified AntNet algorithm for hardware implementation is compared with the original algorithm on the various traffic patterns and topologies. Implementation results show that the proposed architecture is suitable and efficient to realize adaptive routing based on the AntNet.

• Journal of Korean Academy of Nursing Administration
• /
• v.16 no.4
• /
• pp.409-418
• /
• 2010

Purpose: The purpose of this study was to compare the costs and benefits of home nursing care services between public health centers (PHC) and private hospitals. Method: Participants were 105 patients who had received home nursing care services from a private hospital or public health center. From a societal perspective, the researcher identified the costs and benefits of the services using performance data and calculated the net benefit and benefit/cost ratio. Result: The net benefit of the home nursing care service based in the PHC was 165.9 million won and benefit/cost ratio was 2.0, while the net benefit of the home nursing care services by the private hospital was 141.1 million won and benefit/cost ratio was 1.7. Both types of programs were economically validated. Conclusion: Home nursing care services were basically efficient as the results showed a positive net benefit. A cost-benefit analysis indicated that the PHC-based home nursing care services were more efficient than that of the private hospital. With limited human resources and management standards in public health centers, results suggest the need for a more systematic management of the home nursing care service to improve the health of this vulnerable community population.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.394-396
• /
• 2021

Additional pathological tests using imaging equipment are essential before diagnosing cancer cells. Recently, in order to reduce the need for time and human resources in these fields, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, in both previous studies, there were relatively limited deep learning algorithms and cell types, and limitations existed with low accuracy at the same time. In this study, a method of performing 4class Classification on four types of cancer cells through the Convolution Neral Network, a type of in-depth learning. EfficientNet, ResNet, and Inception were used, and finally Resnet was used to obtain an accuracy of 96.11 on average for k-fold.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.169-176
• /
• 2020

Recently, deep neural networks (DNNs) have brought revolutions to many mobile and embedded devices by providing human-level machine intelligence for various applications. However, high inference accuracy of such DNNs comes at high computational costs, and, hence, there have been significant efforts to reduce computational overheads of DNNs either by compressing off-the-shelf models or by designing a new small footprint DNN architecture tailored to resource constrained devices. One notable recent paradigm in designing small footprint DNN models is sharing parameters in several layers. However, in previous approaches, the parameter-sharing techniques have been applied to large deep networks, such as ResNet, that are known to have high redundancy. In this paper, we propose a parameter-sharing method for already parameter-efficient small networks such as ShuffleNetV2. In our approach, small templates are combined with small layer-specific parameters to generate weights. Our experiment results on ImageNet and CIFAR100 datasets show that our approach can reduce the size of parameters by 15%-35% of ShuffleNetV2 while achieving smaller drops in accuracies compared to previous parameter-sharing and pruning approaches. We further show that the proposed approach is efficient in terms of latency and energy consumption on modern embedded devices.