• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.4
• /
• pp.383-390
• /
• 2016

Remote sensing data has been widely used in the estimation of crop yields by employing statistical methods such as regression model. Machine learning, which is an efficient empirical method for classification and prediction, is another approach to crop yield estimation. This paper described the corn yield estimation in Iowa State using four machine learning approaches such as SVM (Support Vector Machine), RF (Random Forest), ERT (Extremely Randomized Trees) and DL (Deep Learning). Also, comparisons of the validation statistics among them were presented. To examine the seasonal sensitivities of the corn yields, three period groups were set up: (1) MJJAS (May to September), (2) JA (July and August) and (3) OC (optimal combination of month). In overall, the DL method showed the highest accuracies in terms of the correlation coefficient for the three period groups. The accuracies were relatively favorable in the OC group, which indicates the optimal combination of month can be significant in statistical modeling of crop yields. The differences between our predictions and USDA (United States Department of Agriculture) statistics were about 6-8 %, which shows the machine learning approaches can be a viable option for crop yield modeling. In particular, the DL showed more stable results by overcoming the overfitting problem of generic machine learning methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.28 no.3
• /
• pp.337-345
• /
• 2010

In general, Digital Photogrammetry is based on independent workstation system, which is costly and has complex process. In this research, a new approach method regarding Digital Photogrammetry procedure is suggested using Web Processing Service, which is a GIS standard proposed by Open Geospatial Consortium. For the experiment, many Generic Processes were defined through WPS profiling procedure which defines standard unit for Photogrammetry, and with the defined process each server and client S/W module was implemented based on WPS standards. In this paper, many users can be expected to share and reuse unit process in WPS server through the web.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2821-2823
• /
• 2002

In this paper we propose the Multi-FNN (Fuzzy-Neural Networks) for optimal identification modeling of complex system. The proposed Multi-FNNs is based on a concept of FNNs and exploit linear inference being treated as generic inference mechanisms. In the networks learning, backpropagation(BP) algorithm of neural networks is used to updata the parameters of the network in order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM(Hard C-Means)clustering algorithm which carry out the input-output dat a preprocessing function and Genetic Algorithm which carry out optimization of model The HCM clustering method is utilized to determine the structure of Multi-FNNs. The parameters of Multi-FNN model such as apexes of membership function, learning rates, and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization abilities of the model. NOx emission process data of gas turbine power plant is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Smart Structures and Systems
• /
• v.6 no.3
• /
• pp.239-262
• /
• 2010

Tube Lines has carried out a "knowledge and investigation programme" on the deep tube tunnels comprising the Jubilee, Northern and Piccadilly lines, as required by the PPP contract with London Underground. Many of the tunnels have been in use for over 100 years, so this assessment was considered essential to the future safe functioning of the system. This programme has involved a number of generic investigations which guide the assessment methodology and the analysis of some 5,000 individual structures. A significant amount of investigation has been carried out, including ultrasonic thickness measurement, detection of brickwork laminations using radar, stress measurement using magnetic techniques, determination of soil parameters using CPT, pressuremeter and laboratory testing, installation of piezometers, material and tunnel segment testing, and trialling of remote photographic techniques for inspection of large tunnels and shafts. Vibrating wire, potentiometer, electro level, optical and fibre-optic monitoring has been used, and laser measurement and laser scanning has been employed to measure tunnel circularity. It is considered that there is scope for considerable improvements in non-destructive testing technology for structural assessment in particular, and some ideas are offered as a "wish-list". Assessment reports have now been produced for all assets forming Tube Lines' deep tube tunnel network. For assets which are non-compliant with London Underground standards, the risk to the operating railway has to be maintained as low as reasonably practicable (ALARP) using enhanced inspection and monitoring, or repair where required. Monitoring techniques have developed greatly during recent years and further advances will continue to support the economic whole life asset management of infrastructure networks.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1590-1599
• /
• 2015

As a variety of personal medical devices appear, it is possible to acquire a large number of diverse medical contexts from the devices. There have been efforts to analyze the medical contexts via software applications. In this paper, we propose a generic model of medical analytics schemes that are used by medical experts, identify inference methods for realizing each medical analytics scheme, and present guidelines for applying the inference methods to the medical analytics schemes. Additionally, we develop a PoC inference system and analyze real medical contexts to diagnose relevant diseases so that we can validate the feasibility and effectiveness of the proposed medical analytics schemes and guidelines of applying inference methods.

• Nuclear Engineering and Technology
• /
• v.44 no.4
• /
• pp.379-386
• /
• 2012

A symptom-based procedure with a critical safety function monitoring system has been established to reduce the operator's diagnosis and cognitive burden since the Three-Mile Island (TMI) accident. However, it has been reported that a symptom-based procedure also requires an operator's cognitive efforts to cope with off-normal events. This can be caused by mismatches between a static model, an emergency operating procedure (EOP), and a dynamic process, the nature of an ongoing situation. The purpose of this study is to share the evidence of mismatches that may result in an excessive cognitive burden in conducting EOPs. For this purpose, we analyzed simulated emergency operation records and observed some operator behaviors during the EOP operation: continuous steps, improper description, parameter check at a fixed time, decision by information previously obtained, execution complexity, operation by the operator's knowledge, notes and cautions, and a foldout page. Since observations in this study are comparable to the results of an existing study, it is expected that the operational behaviors observed in this study are generic features of operators who have to cope with a dynamic situation using a static procedure.

• Journal of Convergence Society for SMB
• /
• v.5 no.1
• /
• pp.13-18
• /
• 2015

The malware, as hackers generic name of executable code that is created for malicious purposes, depending on the presence or absence of a self-replicating ability infected subjects, and are classified as viruses, worms, such as the Trojan horse. Mainly Web page search and P2P use, such as when you use a shareware, has become penetration is more likely to occur in such a situation. If you receive a malware attack, whether the e-mail is sent it is automatically, or will suffer damage such as reduced system performance, personal information leaks. While introducing the current malware, let us examine the measures and describes the contents related to the malicious code.

• ETRI Journal
• /
• v.28 no.5
• /
• pp.593-606
• /
• 2006

Thanks to the great possibilities of providing different types of telecommunication traffic to a large geographical area, satellite networks are expected to be an essential component of the next-generation internet. As a result, issues concerning the designing and testing of efficient connection-admission-control (CAC) strategies in order to increase the quality of service (QoS) for multimedia traffic sources, are attractive and at the cutting edge of research. This paper investigates the potential strengths of a generic digital-video-broadcasting return-channel-via-satellite (DVB-RCS) system architecture, proposing a new CAC algorithm with the aim of efficiently managing real-time multimedia video sources, both with constant and high variable data rate transmission; moreover, the proposed admission strategy is compared with a well-known iterative CAC mainly designed for the managing of real-time bursty traffic sources in order to demonstrate that the new algorithm is also well suited for those traffic sources. Performance analysis shows that, both algorithms guarantee the agreed QoS to real-time bursty connections that are more sensitive to delay jitter; however, our proposed algorithm can also manage interactive real-time multimedia traffic sources in high load and mixed traffic conditions.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.20 no.6
• /
• pp.498-508
• /
• 2015

In the simulation of photovoltaic (PV) power conditioning systems, PSIM is a widely accepted circuit simulation platform because of its fast speed and C-code support. PSIM provides two kinds of generic PV panel models: functional model and physical model. Whereas the functional model simulates PV in the standard test condition (STC) only, the physical model can emulate changing PV characteristics under varying temperatures and irradiation conditions and is thus more suitable for system simulation. However, the physical model requires complicated parameters from users, and thus it is prone to errors and is difficult to use. In this study, a new PSIM model for PV is presented to solve these problems. The proposed model utilizes manufacturers' datasheet values specified under STC only and excludes user-defined information from input parameters. To achieve good accuracy even in varying environmental conditions, single-diode model parameters are successively tuned to a time-varying virtual datasheet. Comparison with a conventional physical model shows that the proposed model provides more accurate simulation according to error analysis based on the EN50530 standard.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.1
• /
• pp.43-50
• /
• 2001

In this paper, we propose the design procedure of advance Polynomial Neural Networks(PNN) architecture for optimal model identification of complex and nonlinear system. The proposed PNN architecture is presented as the generic and advanced type. The essence of the design procedure dwells on the Group Method of Data Handling(GMDH). PNN is a flexible neural architecture whose structure is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated in a dynamic way. In this sense, PNN is a self-organizing network. With the aid of three representative numerical examples, compari-sons show that the proposed advanced PNN algorithm can produce the model with higher accuracy than previous other works. And performance index related to approximation and generalization capabilities of model is evaluated and also discussed.