• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권12호
• /
• pp.3135-3148
• /
• 2013

The popularization of streaming networks and mobile devices brings a new kind of network called mobile peer-assisted streaming network. In this network, service provider not only offers downloading services, but also pre-pushes resources to users for caching. Users can download their demanded resources while working as servers for uploading the cached data. Also the mobile characteristic makes high package losing probability in this network. So we study how the service provider pre-pushes or the user downloads resources efficiently and effectively while considering the package losing in this paper. We build utility models for service provider and user, and solve the models using Bellman's theory to achieve Nash Equilibrium which shows the service provider's optimal pre-pushing speed and user's optimal downloading speed. The numerical simulation demonstrates the efficiency and effectiveness of our proposed pre-pushing and downloading scheme by comparing to the traditional scheme.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권2호
• /
• pp.664-682
• /
• 2012

To improve the accuracy and enhance the applicability of existing models, this paper proposes a generalized Markov chain model for IEEE 802.11 Distributed Coordination Function (DCF) under the widely adopted assumption of ideal transmission channel. The IEEE 802.11 DCF is modeled by a two dimensional Markov chain, which takes into account unsaturated traffic, backoff freezing, retry limits, the difference between maximum retransmission count and maximum backoff exponent, and limited buffer size based on the M/G/1/K queuing model. We show that existing models can be treated as special cases of the proposed generalized model. Furthermore, simulation results validate the accuracy of the proposed model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권3호
• /
• pp.285-307
• /
• 2009

This paper introduces DICE, a Domain-Independent text Classification Engine. DICE is robust, efficient, and domain-independent in terms of software and architecture. Each module of the system is clearly modularized and encapsulated for extensibility. The clear modular architecture allows for simple and continuous verification and facilitates changes in multiple cycles, even after its major development period is complete. Those who want to make use of DICE can easily implement their ideas on this test bed and optimize it for a particular domain by simply adjusting the configuration file. Unlike other publically available tool kits or development environments targeted at general purpose classification models, DICE specializes in text classification with a number of useful functions specific to it. This paper focuses on the ways to locate the optimal states of a practical text classification framework by using various adaptation methods provided by the system such as feature selection, lemmatization, and classification models.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 춘계학술발표논문집 (하)
• /
• pp.1965-1968
• /
• 2003

The importance of Security measures by means of Physical Security, Network Security and Online/Internet Security. Lack of security is one of the primary obstacles in fielding many technologies in both commercial and DoD networks. Moreover, Internet censorship may be growing and is becoming increasingly sophisticated. In this paper, we will evaluate the Practice to Policy to Theory Approach for survivability by means of software rejuvenation models. These models would be assessed the effectiveness of proactive fault management in operational software systems and determined optimal times to perform rejuvenation.

• Journal of the Korean Data and Information Science Society
• /
• 제17권3호
• /
• pp.795-804
• /
• 2006

Most internet auction sites open to users the bid history with the ascending order of bid amounts. Whereas eBay.com presents second bid prices, auction.co.kr provides highest bid prices. In this paper, the bidhistory is arranged according to the passage of tim, which can help to understand the situations and trends of bid prices, especially for multiple auctions. This manipulated data can be visualized by using profile plots. The successful bid prices could be estimated based on some prediction models with appropriate prior informations. Both sellers and bidders can be provided useful informations with these statistical analyses, and then fair online auctions in Korea will grow actively and rapidly.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권1호
• /
• pp.47-53
• /
• 2019

The idea of ensemble learning is to train multiple models, each with the objective to predict or classify a set of results. Most of the errors from a model's learning are from three main factors: variance, noise, and bias. By using ensemble methods, we're able to increase the stability of the final model and reduce the errors mentioned previously. By combining many models, we're able to reduce the variance, even when they are individually not great. In this paper we propose an ensemble model and applied it to classification problem. In iris, Pima indian diabeit and semiconductor fault detection problem, proposed model classifies well compared to traditional single classifier that is logistic regression, SVM and random forest.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1738-1764
• /
• 2019

With the advent of big data, deep learning technology has become an important research direction in the field of machine learning, which has been widely applied in the image processing, natural language processing, speech recognition and online advertising and so on. This paper introduces deep learning techniques from various aspects, including common models of deep learning and their optimization methods, commonly used open source frameworks, existing problems and future research directions. Firstly, we introduce the applications of deep learning; Secondly, we introduce several common models of deep learning and optimization methods; Thirdly, we describe several common frameworks and platforms of deep learning; Finally, we introduce the latest acceleration technology of deep learning and highlight the future work of deep learning.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권2호
• /
• pp.173-178
• /
• 2021

In this paper, we find a suitable methodology for Korean Sentiment Analysis through a comparative experiment in which methods of embedding and natural network models are learned at the highest accuracy and fastest speed. The embedding method compares word embeddeding and Word2Vec. The model compares and experiments representative neural network models CNN, RNN, LSTM, GRU, Bi-LSTM and Bi-GRU with IKEA review data. Experiments show that Word2Vec and BiGRU had the highest accuracy and second fastest speed with 94.23% accuracy and 42.30 seconds speed. Word2Vec and GRU were found to have the third highest accuracy and fastest speed with 92.53% accuracy and 26.75 seconds speed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4557-4572
• /
• 2020

The Alaska competition provides an opportunity to study the practical problems of real-world steganalysis. Participants are required to solve steganalysis involving various embedding schemes, inconsistency JPEG Quality Factor and various processing pipelines. In this paper, we propose a method to ensemble multiple deep learning steganalyzers. We select SRNet and RESDET as our base models. Then we design a three-layers model ensemble network to fuse these base models and output the final prediction. By separating the three colors channels for base model training and feature replacement strategy instead of simply merging features, the performance of the model ensemble is greatly improved. The proposed method won second place in the Alaska 1 competition in the end.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.60-79
• /
• 2022

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.