• KIISE Transactions on Computing Practices
• /
• v.24 no.2
• /
• pp.93-98
• /
• 2018

Recommendation systems are used to provide items of interests for users to maximize a company's profit. Matrix factorization is frequently used by recommendation systems, based on an incomplete user-item rating matrix. However, as the number of items and users increase, it becomes difficult to make accurate recommendations due to the sparsity of data. To overcome this drawback, the use of text data related to items was recently suggested for matrix factorization algorithms. Furthermore, a word-level convolutional neural network was shown to be effective in the process of extracting the word-level features from the text data among these kinds of matrix factorization algorithms. However, it involves a large number of parameters to learn in the word-level convolutional neural network. Thus, we propose a matrix factorization algorithm which utilizes a character-level convolutional neural network with which to extract the character-level features from the text data. We also conducted a performance study with real-life datasets to show the effectiveness of the proposed matrix factorization algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.6
• /
• pp.1211-1217
• /
• 2005

Current generation embedded systems are built around only a small number of SOCs, which are again based on general-purpose embedded micro-processors, such as ARM and MIPS. These RISC-based processors are not, however, designed for specific functions such as networking and multimedia processing, whose importances have increased dramatically in recent years. Network devices for small business and home networks, are especially dependent upon such SOCs based on general processors. Except for PHY and MAC layer functions, which are built with hardware, all the network functions are processed by the embedded micro-processor. Enabling technologies such as VDSL and FTTH promise Internet access with a much higher speed, while at the same time explore the limitations of general purpose microprocessors. In this paper we design a network processor, embed it into an SOC for Home gateway, evaluate the performance rigorously, and gauge a possibility for commercialization.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.3
• /
• pp.393-404
• /
• 2004

Recently, public home have used a more than two computer connected with network, and several home appliances using independently with internet or network are developing to be related closely with the network. Therefore, the home utilized for a simple terminal of the global network in the past is being expanded to another part of the sub network. For a variety of connecting home-area protocols with the existing existing network, we require a new Residential Gateway(RG) that does not only make the home-area network operating in the sub network but also connects to the external network. In this paper, RG has intrinsic limits against flexible service due to IP address assignment and hardware capacity. In order to solve this problem in the RG, we propose a Management Server(MS). The MS that offers the integrated managements and control services for a variety of devices connected the RG in the home-area. It can not only solve the dynamic IP address assigning problem but also assigns private IP addresses to the home network devices through the Network Address Translation(NAT). It also provides somewhat useful functions for the home network and the RG for other additional services. <중략> The MS is using a SNMP protocol for managing the RG in the domain, a polling method of the MS and the RG compose a sequence polling method, a polling method using a multi-process and a multi-thread. In this paper, we introduce a problem with polling method separately, show a polling method between the MS and the RG using a multi-thread.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.11
• /
• pp.44-52
• /
• 1998

In this paper, we proposed a node architecture and cell routing strategies for ATM applications in WDM multihop networks. The proposed node architecture employs the optical delay loop for storing the cell which is failed in out-link contention. This optical delay loop allows the delay of one cell without the electro-optic conversion. Therefore, we can get the advantages of S&F(Store-and-Forward) routing in Deflection-based all-optical networks. To support the ATM applications efficiently. we considered the transmission priority of ATM cell so that high priority cell can be transmitted with lower loss and shorter delay than low priority one. Two kinds of routing strategies are designed for this architecture: Scheme-Ⅰand Scheme-Ⅱ. Scheme-Ⅰapplies S&F routing to high cell and Deflection routing to low cell, i.e., high cells are routed along the shortest path based on S&F routing, but low cells are deflected or lost. Schem-Ⅱ is similar to Scheme-Ⅰexcept that low cells can occupy the optical loop if it is available. This Scheme-Ⅱ increases the utilization of network resources without decreasing the throughput of high cell by reducing the low cell loss rate when traffic load is low. Simulation results show that our routing strategies have better performance than conventional ones under non-uniform traffic as well as uniform traffic.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.3
• /
• pp.78-95
• /
• 2011

This study has developed various DEMs with different spatial resolutions using many different interpolation methods with the aid of a 1:5,000 digital map. In addition, this study has evaluated the vertical accuracy of various DEMs constructed by check point data obtained from the network RTK GPS survey. The obtained results suggest that a DEM developed from the TIN-based Terrain method performs well in evaluating height restriction of buildings in a flying safety area considering general RMSE values, land-type RMSE values and profile evaluation results, etc. And, it has been found that three meters is the right spatial resolution for a DEM in evaluating height restriction of buildings in a flying safety area. Meanwhile, elevation values obtained by the DEM are not point estimation values but interval estimation values. This can be used to check whether the height of buildings in the vicinity of an airfield violates height limitation values of the area. To check whether the height of buildings measured in interval estimation values violates height limitation values of the area, this study has adopted three steps: 1) high probability of violation, 2) low probability of violation, 3) inconclusiveness about the violation. The obtained results will provide an important basis for developing a GIS related to the evaluation of height restriction of buildings in the vicinity of an airfield. Furthermore, although results are limited to the study area, the vertical accuracy values of the DEM constructed from a two-dimensional digital map may provide useful information to researchers who try to use DEMs.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1252-1257
• /
• 2017

In dialogues, speakers' intentions can be represented by sets of an emotion, a speech act, and a predicator. Therefore, dialogue systems should capture and process these implied characteristics of utterances. Many previous studies have considered such determination as independent classification problems, but others have showed them to be associated with each other. In this paper, we propose an integrated model that simultaneously determines emotions, speech acts, and predicators using a convolution neural network. The proposed model consists of a particular abstraction layer, mutually independent informations of these characteristics are abstracted. In the shared abstraction layer, combinations of the independent information is abstracted. During training, errors of emotions, errors of speech acts, and errors of predicators are partially back-propagated through the layers. In the experiments, the proposed integrated model showed better performances (2%p in emotion determination, 11%p in speech act determination, and 3%p in predicator determination) than independent determination models.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.733-741
• /
• 2017

LPWAN(Low Power Wide Area Network) technology is M2M (Machine to Machine) networking technology for the Internet of Things. The technology is designed to support low-power, long-distance and low-speed communications that are typical of LoRaWAN(Long Range Wide Area Network). To exchange inter-object information using a LoRaWAN, the link performances for various environments must be known. however, active performance analysis research that is based on an empirical environment is nonexistent. Therefore, this paper empirically evaluates the performance of the LoRa (Long Range) link, a physical communication technology of the LoRaWAN for various variables that may affect the link quality in indoor and outdoor environments. To achieve this, a physical performance monitoring system was designed and implemented. A communication experiment environment was subsequently constructed based on the indoor and outdoor conditions. The SNR(Signal to Noise Ratio), RSSI(Received Signal Strength Indication), and the PDR(Packet Delivery Ratio) were evaluated.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.21 no.2
• /
• pp.119-129
• /
• 2011

TCP-related Flooding attacks still dominate Distributed Denial of Service Attack. It is a great challenge to accurately detect the TCP flood attack in hish speed network. In this paper, we propose the NIC_Cookie logic implementation, which is a kind of security offload engine against TCP-related DDoS attacks, on network interface card. NIC_Cookie has robustness against DDoS attack itself and it is independent on server OS and external network configuration. It supports not IP-based response method but packet-level response, therefore it can handle attacks of NAT-based user group. We evaluate that the latency time of NIC_Cookie logics is $7{\times}10^{-6}$ seconds and we show 2Gbps wire-speed performance through a benchmark test.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.1-7
• /
• 2023

In the fabrication of curved multi-display glass for automotive use, the surface roughness of the mold is a critical quality factor. However, the difficulty in detecting micro-cutting signals in a micro-machining environment and the absence of a standardized model for predicting micro-cutting forces make it challenging to intuitively infer the correlation between cutting variables and actual surface roughness under machining conditions. Consequently, current practices heavily rely on machining condition optimization through the utilization of cutting models and experimental research for force prediction. To overcome these limitations, this study employs a surface roughness prediction formula instead of a cutting force prediction model and converts the surface roughness prediction formula into experimental data. Additionally, to account for changes in surface roughness during machining runtime, the theory of position variables has been introduced. By leveraging artificial neural network technology, the accuracy of the surface roughness prediction formula model has improved by 98%. Through the application of artificial neural network technology, the surface roughness prediction formula model, with enhanced accuracy, is anticipated to reliably perform the derivation of optimal machining conditions and the prediction of surface roughness in various machining environments at the analytical stage.

• Journal of computational fluids engineering
• /
• v.17 no.4
• /
• pp.1-8
• /
• 2012

During a reactor normal operation, two parallel 50% capacity cooling pumps circulate primary coolant to remove the fission reaction heat of the reactor through heat exchangers cold by a cooling tower. When one pump is failure, the other pump shall continuously circulate the coolant to remove the residual heat generated by the fuels loaded in the reactor after reactor shutdown. It is necessary to estimate how much flow rate will be supplied to remove the residual heat. We carried out a flow network analysis for the parallel primary pumps based on the piping network of the primary cooling system in HANARO. As result, it is estimated that the flow rate of one pump increased about 1.33 times the rated flow of one pump and was maintained within the limit of the cavitation critical flow.