• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.23-29
• /
• 2011

We try to build the base for implementation of smart water treatment plant through identifying status by data acquisition such as temperature, humidity, flow, level, pump status and CCTV by using USN terminal such as Zigbee, Wi-Fi, UHF at the center of the flowmeter calibration center in K-water institute. The data obtained from various sensors is transmitted to data processing device through different types of USN network, the processed data is implemented to monitor by smart phone and we try to perform low cost and high efficient USN-based pilot project by implementing remote monitoring system using network performance analysis and mobile devices.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.294-297
• /
• 2004

The purpose of this study was to develop landslide susceptibility analysis techniques using artificial neural networks and then to apply these to the selected study area of Janghung in Korea. We aimed to verify the effect of data selection on training sites. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use was constructed. Thirteen landslide-related factors were extracted from the spatial database. Using these factors, landslide susceptibility was analyzed using an artificial neural network. The weights of each factor were determined by the back-propagation training method. Five different training datasets were applied to analyze and verify the effect of training. Then, the landslide susceptibility indices were calculated using the trained back-propagation weights and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. The results of the landslide susceptibility maps were verified and compared using landslide location data. GIS data were used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool to analyze landslide susceptibility.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.3876-3895
• /
• 2014

Recently, Heterogeneous Network (HetNet) with Coordinated Multi-Point (CoMP) scheme is introduced into Long Term Evolution-Advanced (LTE-A) systems to improve digital services for User Equipments (UEs), especially for cell-edge UEs. However, Radio Resource Management (RRM), including Resource Block (RB) scheduling and Power Allocation (PA), in this scenario becomes challenging, due to the intercell cooperation. In this paper, we investigate the RRM problem for downlink transmission of HetNet system with Joint Processing (JP) CoMP (both joint transmission and dynamic cell selection schemes), aiming at maximizing weighted sum data rate under the constraints of both transmission power and backhaul capacity. First, joint RB scheduling and PA problem is formulated as a constrained Mixed Integer Programming (MIP) which is NP-hard. To simplify the formulation problem, we decompose it into two problems of RB scheduling and PA. For RB scheduling, we propose an algorithm with less computational complexity to achieve a suboptimal solution. Then, according to the obtained scheduling results, we present an iterative Karush-Kuhn-Tucker (KKT) method to solve the PA problem. Extensive simulations are conducted to verify the effectiveness and efficiency of the proposed algorithms. Two kinds of JP CoMP schemes are compared with a non-CoMP greedy scheme (max capacity scheme). Simulation results prove that the CoMP schemes with the proposed RRM algorithms dramatically enhance data rate of cell-edge UEs, thereby improving UEs' fairness of data rate. Also, it is shown that the proposed PA algorithms can decrease power consumption of transmission antennas without loss of transmission performance.

• Genomics & Informatics
• /
• v.6 no.3
• /
• pp.153-156
• /
• 2008

Complex diseases such as stroke and cancer have two or more genetic loci and are affected by environmental factors that contribute to the diseases. Due to the complex characteristics of these diseases, identifying candidate genes requires a system-level analysis of the following: gene ontology, pathway, and interactions. A database and user interface, termed StrokeBase, was developed; StrokeBase provides queries that search for pathways, candidate genes, candidate SNPs, and gene networks. The database was developed by using in silico data mining of HGNC, ENSEMBL, STRING, RefSeq, UCSC, GO, HPRD, KEGG, GAD, and OMIM. Forty candidate genes that are associated with cerebrovascular disease were selected by human experts and public databases. The networked cerebrovascular disease gene maps also were developed; these maps describe genegene interactions and biological pathways. We identified 1127 genes, related indirectly to cerebrovascular disease but directly to the etiology of cerebrovascular disease. We found that a protein-protein interaction (PPI) network that was associated with cerebrovascular disease follows the power-law degree distribution that is evident in other biological networks. Not only was in silico data mining utilized, but also 250K Affymetrix SNP chips were utilized in the 320 control/disease association study to generate associated markers that were pertinent to the cerebrovascular disease as a genome-wide search. The associated genes and the genes that were retrieved from the in silico data mining system were compared and analyzed. We developed a well-curated cerebrovascular disease-associated gene network and provided bioinformatic resources to cerebrovascular disease researchers. This cerebrovascular disease network can be used as a frame of systematic genomic research, applicable to other complex diseases. Therefore, the ongoing database efficiently supports medical and genetic research in order to overcome cerebrovascular disease.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.58-64
• /
• 1996

This paper was proposed the recognition method by using parameters which was estimated from the data on the estimated plane and a neural network. After the LPC estimated in each frame algorithm was mapped to the estimated plane by the optimum feature mapping function, we estimated the C-LPC and the maximum and minimum value and 3 divided power from the mapping data on the estimated plane. As a result of the experiment of the speech recognition that those parameters were applied to the input of a neural network, it was found that those parameters estimated from the estimated plane have the features of the original speech for a change in the time scale and that the recongnition rate by the proposed methods was 96.3 percent.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.431-434
• /
• 2001

Knowledge discovery in databases(KDD) is the process for extracting valid, novel, potentially useful and understandable knowledge form real data. There are many academic and industrial activities with new technologies and application areas. Particularly, data mining is the core step in the KDD process, consisting of many algorithms to perform clustering, pattern recognition and rule induction functions. The main goal of these algorithms is prediction and description. Prediction means the assessment of unknown variables. Description is concerned with providing understandable results in a compatible format to human users. We introduce an efficient data mining algorithm considering predictive and descriptive capability. Reasonable pattern is derived from real world data by a revised neural network model and a proposed fuzzy rule extraction technique is applied to obtain understandable knowledge. The proposed neural network model is a hierarchical self-organizing system. The rule base is compatible to decision makers perception because the generated fuzzy rule set reflects the human information process. Results from real world application are analyzed to evaluate the system\`s performance.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.71-76
• /
• 2021

Education is one of the pillars of sustainable development. For this reason, the discovery of useful information in its process of adaptation to new challenges is treated with care. This paper aims to present the initiation of a process of exploring the data collected from the results obtained by Romanian students at the BBaccalaureate (the Romanian high school graduation) exam, through data mining methods, in order to try an in-depth analysis to find and remedy some of the causes that lead to unsatisfactory results. Specifically, a set of public data was collected from the website of the Ministry of Education, on which several classification methods were tested in order to find the most efficient modeling algorithm. It is the first time that this type of data is subjected to such interests.

• International Journal of Computer Science & Network Security
• /
• v.21 no.3
• /
• pp.275-286
• /
• 2021

As a result of the vast amount of data that is geographically found in different locations. Distributed data mining (DDM) has taken a center stage in data mining. The use of mobile agents to enhance efficiency in DDM has gained the attention of industries, commerce and academia because it offers serious suggestions on how to solve inherent problems associated with DDM. In this paper, a novel DDM model has been proposed by using a mobile agent to enhance efficiency. The main idea behind the model is to use the Naive Bayes algorithm to give the mobile agent the ability to learn, compare, get and store the results on it from each server which has different datasets and we found that the accuracy increased roughly by 0.9% which is our main target.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2191-2208
• /
• 2022

Motion blur in PET (Positron emission tomography) images induced by respiratory motion will reduce the quality of imaging. Although exiting methods have positive performance for respiratory motion correction in medical practice, there are still many aspects that can be improved. In this paper, an improved 3D unsupervised framework, Res-Voxel based on U-Net network was proposed for the motion correction. The Res-Voxel with multiple residual structure may improve the ability of predicting deformation field, and use a smaller convolution kernel to reduce the parameters of the model and decrease the amount of computation required. The proposed is tested on the simulated PET imaging data and the clinical data. Experimental results demonstrate that the proposed achieved Dice indices 93.81%, 81.75% and 75.10% on the simulated geometric phantom data, voxel phantom data and the clinical data respectively. It is demonstrated that the proposed method can improve the registration and correction performance of PET image.

• Asia pacific journal of information systems
• /
• v.31 no.1
• /
• pp.121-140
• /
• 2021

The main purpose of this research is to understand the strongest predictors of wearable adoption among athletes with an emphasis on the perceived ethics of biometric data. We performed a word co-occurrence study of biometrics research to determine the ethical constructs of biometric data. A questionnaire incorporating the Unified Theory of Acceptance and Use of Technology (UTAUT), Health Belief Model and Biometric Data Ethics was then designed to develop a neural network model to predict the adoption of wearable sensors among athletes. Our model shows that wearable adoption's strongest predictors are perceived ethics, perceived profit, and perceived threat; which can be categorized as professional stressors. The key theoretical contribution of this paper is to extend the literature on UTAUT by developing a predictive modeling of factors affecting acceptance of wearables by athletes, and highlighting the ethical implications of athlete's adoption of wearables.