• Journal of the Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.37-49
• /
• 2008

Services are reusable units in business level. Ubiquitous computing provides computing services anytime and anywhere. The combination of both is becoming an important paradigm of computing environment. Fundamentals of services require flexibility and interoperability, and key elements of ubiquitous modeling require interoperability and context-awareness. There are two kinds of methods to identify services. The top-down approach is based on business process, and the bottom-up approach is based on components. The first approach depends on experts' intuitions, while the second approach suffers the incapability of expressing non-functional expression through components. Although a feature-based approach is capable of expressing non-functional expression and identifying services in ubiquitous environment, the research on this issue is not adequately addressed by far. To promote this research, this paper proposes a feature-based method to identify services in ubiquitous computing. The method extracts initial-candidate-services from a feature model. Then, the ultimate services are identified through optimizing and analyzing the candidate-services. The proposed method is expected to enhance the service reusability by effectively analyzing ubiquitous domain based on feature, and varying reusable service units.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3984-4005
• /
• 2017

Image recognition has become an increasingly important topic for its wide application. It is highly challenging when facing to large-scale database with large variance. The recognition systems rely on a key component, i.e. the low-level feature or the learned mid-level feature. The recognition performance can be potentially improved if the data distribution information is exploited using a more sophisticated way, which usually a function over hidden variable, model parameter and observed data. These methods are called generative score space. In this paper, we propose a discriminative extension for the existing generative score space methods, which exploits class label when deriving score functions for image recognition task. Specifically, we first extend the regular generative models to class conditional models over both observed variable and class label. Then, we derive the mid-level feature mapping from the extended models. At last, the derived feature mapping is embedded into a discriminative classifier for image recognition. The advantages of our proposed approach are two folds. First, the resulted methods take simple and intuitive forms which are weighted versions of existing methods, benefitting from the Bayesian inference of class label. Second, the probabilistic generative modeling allows us to exploit hidden information and is well adapt to data distribution. To validate the effectiveness of the proposed method, we cooperate our discriminative extension with three generative models for image recognition task. The experimental results validate the effectiveness of our proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.980-997
• /
• 2024

To improve the brightness of images and reveal hidden information in dark areas is the main objective of low-light image enhancement (LLIE). LLIE methods based on deep learning show good performance. However, there are some limitations to these methods, such as the complex network model requires highly configurable environments, and deficient enhancement of edge details leads to blurring of the target content. Single-scale feature extraction results in the insufficient recovery of the hidden content of the enhanced images. This paper proposed an edge detection-based multi-scale feature enhancement network for LLIE (EDMFEN). To reduce the loss of edge details in the enhanced images, an edge extraction module consisting of a Sobel operator is introduced to obtain edge information by computing gradients of images. In addition, a multi-scale feature enhancement module (MSFEM) consisting of multi-scale feature extraction block (MSFEB) and a spatial attention mechanism is proposed to thoroughly recover the hidden content of the enhanced images and obtain richer features. Since the fused features may contain some useless information, the MSFEB is introduced so as to obtain the image features with different perceptual fields. To use the multi-scale features more effectively, a spatial attention mechanism module is used to retain the key features and improve the model performance after fusing multi-scale features. Experimental results on two datasets and five baseline datasets show that EDMFEN has good performance when compared with the stateof-the-art LLIE methods.

• Bulletin of the Korean Chemical Society
• /
• v.34 no.3
• /
• pp.827-830
• /
• 2013

Investigation of an organic extract of the fruits Schisandra wilsoniana led to the isolation of two new highly oxygenated nortriterpenoids, named schilancidilactones V-W (1-2). Their structures were elucidated by spectroscopic evidence. Compounds 1-2 feature a double bond between C-7 and C-8 compared with related known nortriterpenoids isolated from the genus Schisandra. Compounds 1 and 2 were tested for their anti-HIV-1 activities and cytotoxicity. The results revealed that compounds 1 and 2 showed moderate anti-HIV-1 activities with $EC_{50}$ 3.05 and 2.87 ${\mu}g/mL$, respectively, and compound 1 showed high cytotoxicity against KB and MDA-MB-231 cell with $IC_{50}$ values of 3.18 and 5.22 ${\mu}M$, respectively.

• Journal of KIISE:Information Networking
• /
• v.33 no.3
• /
• pp.193-200
• /
• 2006

The security feature is essential in wireless sensor network such as intrusion detection or obstacle observation. Sensor nodes must have shared secret between nodes to support security such as privacy. Many methods which provide key pre-distribution need too many keys or support poor security. To solve this problem, probabilistic key pre-distribution is proposed. This method needs a few keys and use probabilistic method to share keys. However, this method does not guarantee key sharing between nodes, and neighbor nodes nay not communicate each other. It leads to waste of network resource such as inefficient routing, extra routing protocol. In this paper, we propose new key distribution method using quorum system which needs a few keys and guarantee key sharing between nodes. We also propose extension of the method which needs fewer keys and guarantee key sharing when node deployment knowledge is well known.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.997-1006
• /
• 2019

To overcome the difficulties and inefficiencies of the existing power analysis attack, we try to extract the secret key embedded in a cryptographic device using attack model based on MLP(Multi-Layer Perceptron) method. The target of our proposed power analysis attack is the AES-128 encryption module implemented on an 8-bit processor XMEGA128. We use the divide-and-conquer method in bytes to recover the whole 16 bytes secret key. As a result, the MLP-based power analysis attack can extract the secret key with the accuracy of 89.51%. Additionally, this MLP model has the 94.51% accuracy when the pre-processing method on power traces is applied. Compared to the machine leaning-based model SVM(Support Vector Machine), we show that the MLP can be a outstanding method in power analysis attacks due to excellent ability for feature extraction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1706-1725
• /
• 2024

The unique U-shaped structure of U-Net network makes it achieve good performance in image segmentation. This network is a lightweight network with a small number of parameters for small image segmentation datasets. However, when the medical image to be segmented contains a lot of detailed information, the segmentation results cannot fully meet the actual requirements. In order to achieve higher accuracy of medical image segmentation, a novel improved U-Net network architecture called multi-scale encoder-decoder U-Net+ (MEDU-Net+) is proposed in this paper. We design the GoogLeNet for achieving more information at the encoder of the proposed MEDU-Net+, and present the multi-scale feature extraction for fusing semantic information of different scales in the encoder and decoder. Meanwhile, we also introduce the layer-by-layer skip connection to connect the information of each layer, so that there is no need to encode the last layer and return the information. The proposed MEDU-Net+ divides the unknown depth network into each part of deconvolution layer to replace the direct connection of the encoder and decoder in U-Net. In addition, a new combined loss function is proposed to extract more edge information by combining the advantages of the generalized dice and the focal loss functions. Finally, we validate our proposed MEDU-Net+ MEDU-Net+ and other classic medical image segmentation networks on three medical image datasets. The experimental results show that our proposed MEDU-Net+ has prominent superior performance compared with other medical image segmentation networks.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.897-905
• /
• 2022

Research for video key frame detection has been actively conducted in the fields of computer vision. Recently with the advances on deep learning techniques, performance of key frame detection has been improved, but the various type of video content and complicated background are still a problem for efficient learning. In this paper, we propose a novel method for key frame detection, witch utilizes contrastive learning and memory bank module. The proposed method trains the feature extracting network based on the difference between neighboring frames and frames from separate videos. Founded on the contrastive learning, the method saves and updates key frames in the memory bank, witch efficiently reduce redundancy from the video. Experimental results on video dataset show the effectiveness of the proposed method for key frame detection.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.83-92
• /
• 2020

A recent study to determine the fall is focused on analyzing fall motions using a recurrent neural network (RNN), and uses a deep learning approach to get good results for detecting human poses in 2D from a mono color image. In this paper, we investigated the improved detection method to estimate the position of the head and shoulder key points and the acceleration of position change using the skeletal key points information extracted using PoseNet from the image obtained from the 2D RGB low-cost camera, and to increase the accuracy of the fall judgment. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion analysis method and on the velocity of human body skeleton key points change as well as the ratio change of body bounding box's width and height. The public data set was used to extract human skeletal features and to train deep learning, GRU, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than the conventional primitive skeletal data use method.

• Bulletin of the Korean Chemical Society
• /
• v.33 no.8
• /
• pp.2623-2626
• /
• 2012

A series of functionalized furans were synthesized by way of a palladium-catalyzed coupling reaction of 2,3,5-trisubstituted furans with aryl chlorides through C-H bond cleavages at C-4 position. The feature of the reaction was facilitative preparation of furan derivatives with good functional group tolerance. All reactions gave the desired products in moderate to good yields in the presences of $BuAd_2P$ and t-BuOK in DMF at $120^{\circ}C$ after 15 h.