• Journal of Information Processing Systems
• /
• v.13 no.2
• /
• pp.204-214
• /
• 2017

Artificial intelligence, especially deep learning technology, is penetrating the majority of research areas, including the field of bioinformatics. However, deep learning has some limitations, such as the complexity of parameter tuning, architecture design, and so forth. In this study, we analyze these issues and challenges in regards to its applications in bioinformatics, particularly genomic analysis and medical image analytics, and give the corresponding approaches and solutions. Although these solutions are mostly rule of thumb, they can effectively handle the issues connected to training learning machines. As such, we explore the tendency of deep learning technology by examining several directions, such as automation, scalability, individuality, mobility, integration, and intelligence warehousing.

• Journal of The Institute of Information and Telecommunication Facilities Engineering
• /
• v.3 no.1
• /
• pp.75-87
• /
• 2004

The mobile industry is waking up to the reality that customers buy 'services', not technology. Thekey is to deliver a variety of differentiated services today and improve them as the advanced technology becomes available. In the increasingly data centric world of the future, the emphasis will be on the provision of a range of services audio, video, data and multimedia and of course speech. As we move closer to the realization of these mobile services in the conglomeration of converged networks, new challenges are being faced by the technology and application developers as well as the service providers to design, test and integrate new products and services. Functionalities like availability, scalability, performance and compatibility have become more important. This paper discusses the new test paradigms in the mobile networks, both from the applications and the protocols perspective.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.395-397
• /
• 2013

MODIS는 기상, 대기, 해양, 그리고 육상 등의 지구전체에 대한 정보를 산출하기 위한 센서로서, 인공위성에 탑재되어 지구관측 데이터를 생산한다. 최초의 MODIS 위성 데이터는 많은 왜곡을 포함하고 있으므로 지형 및 광휘 보정작업은 분석 작업을 하기 위한 필수적인 전처리 작업이다. 위성 데이터 처리를 위해 개발된 SeaDAS는 단일노드/단일코어상에서 수행되기 적합하게 개발되었기 때문에, 대용량의 위성데이터를 전처리하기 위해 많은 시간을 소비해야 한다. 본 논문은 Sun Grid Engine 기반의 다중노드/다중코어를 이용하는 위성 데이터 분산 처리 방법을 제안하고 성능 및 확장성에 대한 평가를 수행한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.620-623
• /
• 2002

To cope with the challenge of competitive market, manufacturing system needs to be agile in terms of its reconfigurability and scalability. For a system to be adapted to changed requirements, decision support tools such as configurator have to be provided. This paper introduces the basic framework of a configurator for assembly system Based on the factory data model(FDM) depicting the overall structure of a manufacturing system, functions of the configurator are described, i.e., requirements analysis, module selection and configuration optimization.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.66-69
• /
• 2000

In this paper, we propose a progressive transmission of a video using a 2$\times$2$\times$2 DCT First of all, the video data is transformed into multiresolution represented video data using a 2$\times$2$\times$2 DCT. Then. it is represented by a 3-D EZT(Embedded Zero Tree) coding fur the progressive transmission with a bit-rate scalability. The proposed progressive transmission algorithm needs much less computations and buffer memories than the higher-order convolution based wavelet filter. Also, since the 2$\times$2$\times$2 DCT requires independent local computations, parallel processing can be applied.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2002.05a
• /
• pp.342-351
• /
• 2002

A personalized product recommendation is an enabling mechanism to overcome information overload occurred when shopping in an Internet marketplace. Collaborative filtering has been known to be one of the most successful recommendation methods, but its application to e-commerce has exposed well-known limitations such as sparsity and scalability, which would lead to poor recommendations. This paper suggests a personalized recommendation methodology by which we are able to get further effectiveness and quality of recommendations when applied to an Internet shopping mall. The suggested methodology is based on a variety of data mining techniques such as web usage mining, decision tree induction, association rule mining and the product taxonomy. For the evaluation of the methodology, we implement a recommender system using intelligent agent and data warehousing technologies.

• Journal of Information Processing Systems
• /
• v.7 no.1
• /
• pp.29-42
• /
• 2011

Wireless sensor networks are composed of a large number of sensor nodes with limited energy resources. One critical issue in wireless sensor networks is how to gather sensed information in an energy efficient way, since their energy is limited. The clustering algorithm is a technique used to reduce energy consumption. It can improve the scalability and lifetime of wireless sensor networks. In this paper, we introduce a clustering protocol with mode selection (CPMS) for wireless sensor networks. Our scheme improves the performance of BCDCP (Base Station Controlled Dynamic Clustering Protocol) and BIDRP (Base Station Initiated Dynamic Routing Protocol) routing protocol. In CPMS, the base station constructs clusters and makes the head node with the highest residual energy send data to the base station. Furthermore, we can save the energy of head nodes by using the modes selection method. The simulation results show that CPMS achieves longer lifetime and more data message transmissions than current important clustering protocols in wireless sensor networks.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.19 no.8
• /
• pp.138-143
• /
• 2005

A hierarchical tree structure of clusters has advantages for the network design due to its scalability and simple routing protocol. In this paper, the cluster tree routing protocol is studied for the wireless sensor network. From the numerical analysis results, the data aggregation in the intermediate nodes reduces the number of communication message and saves the energy of sensor nodes, but it may result in increased data traffic latency. And also the selection of cluster head can increase the relaying hops very high.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.1183-1186
• /
• 2014

Our research is different form traditional to have some large LED screen grouping together to constitute multi-vision technique. In this paper, we purpose a method of using k-path diffusion method to build connect between the devices and find an optimal data transmission path. In second half of this paper, through practical application, we using this technique transmitting data successfully and achieving a simple Multi-vision effect. This technique possess smart devices and Wifi P2P's features, these features improve system's dynamic and decentralized processing ability make our technique has high scalability.