• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.351-360
• /
• 2018

The LWR (Locally Weighted Regression) model, which is traditionally a lazy learning model, is designed to obtain the solution of the prediction according to the input variable, the query point, and it is a kind of the regression equation in the short interval obtained as a result of the learning that gives a higher weight value closer to the query point. We study on an incremental ensemble learning approach for LWR, a form of lazy learning and memory-based learning. The proposed incremental ensemble learning method of LWR is to sequentially generate and integrate LWR models over time using a genetic algorithm to obtain a solution of a specific query point. The weaknesses of existing LWR models are that multiple LWR models can be generated based on the indicator function and data sample selection, and the quality of the predictions can also vary depending on this model. However, no research has been conducted to solve the problem of selection or combination of multiple LWR models. In this study, after generating the initial LWR model according to the indicator function and the sample data set, we iterate evolution learning process to obtain the proper indicator function and assess the LWR models applied to the other sample data sets to overcome the data set bias. We adopt Eager learning method to generate and store LWR model gradually when data is generated for all sections. In order to obtain a prediction solution at a specific point in time, an LWR model is generated based on newly generated data within a predetermined interval and then combined with existing LWR models in a section using a genetic algorithm. The proposed method shows better results than the method of selecting multiple LWR models using the simple average method. The results of this study are compared with the predicted results using multiple regression analysis by applying the real data such as the amount of traffic per hour in a specific area and hourly sales of a resting place of the highway, etc.

• Journal of Korean Society of Forest Science
• /
• v.81 no.1
• /
• pp.30-39
• /
• 1992

Artificial acid rain(pH2.0, 3.0, 4.0 and 5.0) was treated on the seeded pots of 4 species to examine its effects on germination, leaf injury and seedling growth. Aluminum ammonium sulfate solution (0.5, 1.0 and 2.5mM) and artificial acid rain (pH3.0, 4.0 and 5.0) were treated on the seeded germinators of 3 species to examine its effects on germination and radicle growth. Artificial acid rain was prepared by diluting sulfuric acid with ground water and ground water(pH6.5) was used as control. Artificial acid rain was sprayed to seeded pots three times per week. About 5mm of artificial acid rain was treated each time from early April to early October, 1991. Germination, seedling establishment, radicle growth, leaf injury and seedling growth were measured and compared among the treatments. The results were summarized as follows 1. Germination, seedling establishment rate of Pinus densiflora were highest on the pH5.0 pot whereas those of Ailanthus altissima was highest on the control pot, and those of Magnolia sieboldii showed the highest value on the pH3.0 pot. 2. The differences in seedling height of Pinus densiflora and Pinus rigida were significant among the treatment levels of acid rain, whereas those of Magnolia sieboldii and Ailanthus altissima were not significant. Seedling heights of Pinus densiflora and Pinus rigida were highest on the pH3.0 pot, and that of Magnolia sieboldii was highest on the pH4.0 pot, and that of Ailanthus altissima was highest on the control pot. 3. Seedling dry weights of Pinus densiflora. Pinus rigida, and Ailanthus altissima differed significantly among the treatments, but that of Magnolia sieboldii did not differ. Highest seedling dry weights of Magnolia sieboldii and Ailanthus altissima were observed on the pH4.0 pot, and that of Pinus densiflora was observed on the pH3.0 pot, and that of Pinus rigida was observed on the pH5.0 pot. 4. With decrease of pH value of artificial acid rain, the number of injured needle and injured individual tended to be increased. 5. The differences in effects of soil acidity were highly significant among the treatments for all species. 6. Radicle growth of Pinus densiflora differed significantly among pH levels and aluminum concentrations.

• Ecology and Resilient Infrastructure
• /
• v.9 no.1
• /
• pp.68-76
• /
• 2022

In this study, the Habitat Suitability Index (HSI) was calculated in the Miho stream of the Geum river system, and the environmental ecological flow by point was evaluated. Two points (St.3 and St.8) representing the up and downstream of Miho Stream were selected, in order to calculate the Habitat Suitability Index, the depth and velocity at point where each species is appeared were investigated. The Habitat Suitability Index (HSI) was calculated by the Washington Department of Fish and Wildlife (WDFW) method using the number collected by water depth and velocity section and the results of the flow rate survey. Two target species were selected in this study; dominant species and swimming species sensitive to flow. In the case of a single species of Zacco platypus, the water depth was 0.1 - 0.5 m and the velocity was 0.2 - 0.5 m/s. For species of swimming fish, the water depth was 0.2 - 0.5 m and the velocity was 0.2 - 0.5 m/s. The discharge-Weighted Useable Area (WUA) relationship curve and habitat suitability distribution were simulated at the Miho Stream points St.3 and St.8. At the upstream St.3 of Miho Stream, the optimal discharge was simulated as 4.0 m³/s for swimming fishes and 2.7 m³/s for Zacco platypus. At the downstream point of St.8, species of swimming fish were simulated as 8.8 m³/s and Zacco platypus was simulated as 7.6 m³/s. In both points, the optimal discharge of swimming fish was over estimated. This is a result that the Habitat Suitability Index for swimming fish requires a faster flow rate than the habitat conditions of the Zacco platypus. In the calculation of the minimum discharge, the discharge of Zacco platypus is smaller and is evaluated to provide more Weighted Useable Area. In the case of swimming fishes, narrow range of depth and velocity increases the required discharge and relatively decreases the Weighted Useable Area. Therefore, when calculating the Habitat Suitability Index for swimming fishes, it is more advantageous to calculate the index including the habitat of all fish species than to narrow the range.

• Korean Journal of Soil Science and Fertilizer
• /
• v.37 no.1
• /
• pp.1-6
• /
• 2004

Agricultural recycling of livestock wastes by composting has lots of beneficial effects on crop production and soil fertility. Most of composts are made from pig manure and water content controller such as saw dust, bark, rice hulls etc. by aerobic processing. But the insufficient supply of saw dust, bark etc. cause the indiscreet use of industrial waste having heavy metals and toxic synthetic chemicals. This research investigated the present quality status of organic by-product fertilizers, and suggested the way of quality interpretation under the statistical approaches based on median, mean and weighted average value. Since the data of one hundred of samples for heavy metal contents (Cd, Pb, Cu, and Cr) and OM/N showed extremely left-skewed distribution, the median was more useful than the mean in representing the characteristics of distribiition for each items. The weighted average value will be a useful index for the quality based on the total amount of producing.

• Ecology and Resilient Infrastructure
• /
• v.1 no.1
• /
• pp.39-48
• /
• 2014

In order to establish fundamental data for stream restoration and environmental flow, we investigated optimal ecological flowrate (OEF) and riverine health condition in the Chogang Stream, a tributary to Geum River, Korea. The number of fish individuals sampled in this period were 4,669 in 36 species of 9 families. The most abundant species was Korean chub (Zacco koreanus, 34.0%) followed by pale chub (Z. platypus, 22.6%) and Korean shinner (Coreoleuciscus splendidus, 13.3%). Index of biological integrity (IBI) and qualitative habitat evaluation index (QHEI) values decreased from upstream to downstream along the stream. The estimated IBI value ranged from 27.9 to 38.6 with average 32.2 out of 50, rendering the site ecologically fair to good health conditions. OEF was estimated by the physical habitat simulation system (PHABSIM) using the habitat suitability indexes (HSI) of three fish species Z. koreanus, C. splendidus and Pseudopungtungia nigra selected as indicator species. In Z. koreanus, HSI for flow velocity and water depth were estimated at 0.1 to 0.4 m/s and 0.2 to 0.4 m, respectively. In P. nigra, HSI for flow velocity, water depth and substrate size were estimated at 0.2 to 0.5 m/s and 0.4 to 0.6 m and fine gravel to cobbles, respectively. OEF values increasing from up to downstream was found to increase, weighted usable area (WUA) values increased accordingly.

• Journal of the Korean Society for information Management
• /
• v.29 no.4
• /
• pp.191-208
• /
• 2012

Two fundamental aspects of speech summary generation are the extraction of key speech content and the style of presentation of the extracted speech synopses. We first investigated whether acoustic features (speaking rate, pitch pattern, and intensity) are equally important and, if not, which one can be effectively modeled to compute the significance of segments for lecture summarization. As a result, we found that the intensity (that is, difference between max DB and min DB) is the most efficient factor for speech summarization. We evaluated the intensity-based method of using the difference between max-DB and min-DB by comparing it to the keyword-based method in terms of which method produces better speech summaries and of how similar weight values assigned to segments by two methods are. Then, we investigated the way to present speech summaries to the viewers. As such, for speech summarization, we suggested how to extract key segments from a speech video efficiently using acoustic features and then present the extracted segments to the viewers.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.39 no.12
• /
• pp.529-538
• /
• 2002

Conventional method to reduce the handoff call blocking probability(PBH) in mobile communication system is to reserve a predetermined number of channels only for handoff calls. To determine the number of reserved channels, an optimization problem, which is generally computationally heavily involved, must be solved. In this Paper, we propose a call admission control (CAC) scheme that can be used to reduce the PBH without reserving channels in advance. For this, we define a new measure, gain, which depends on the state of the system upon the arrival of a new call. The proposed CAC decision rule relies on the gain computed when a new call arrives. SRN, an extended stochastic Petri nets, provides compact modeling facilities for system analysis can be calculated performance index by appropriate reward to the model. In this Paper, we develop SRN models which can perform the CAC with gain. The SRN models are 2 level hierarchical models. The upper layer models are the structure state model representing the CAC and channel allocation methods considering QoS with multimedia traffic The lower layer model Is to compute the gain under the state of the upper layer models.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.113-121
• /
• 2007

Commonly, in the Sensor Network that composed with multiple nodes uses Ad-hoc protocol to communicate each other. Each sensed data packets are collected by base node and processed by Host PC. But the Ad-hoc protocol is too vulnerable to Sinkhole attack, where the intruder attracts surrounding nodes with unfaithful routing information, and then performs selective forwarding or changes the data passing through it. The Sinkhole attack increases overhead over the network and boosts energy consumption speed to decrease network's life time. Since the other attacks can be easily adopted through sinkhole attack, the countermeasure must be considered carefully. In this paper, we proposed the Hop-depth algorithm that detects intruder in Sinkhole attack and colluded nodes. First, the proposed algorithm makes list of suspected nodes and identifies the real intruder in the suspected node list through the Hop-depth count value. And recalculates colluder's path information to find the real intruder. We evaluated the performance of the proposed algorithm using NS2. We compared and analyzed the success ratio of finding real intruder, false positive ratio, false negative ratio, and energy consumption.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.145-153
• /
• 2014

Several studies regarding drought indices and criteria have been widely studied in the literature. If one defines the onset, severity, and end of droughts, in general, a certain threshold needs to be set to assess the drought events. However, the uncertainty associated with the threshold is a critical problem in drought analysis. To take full advantage of the inherent features in the rainfall series, a Hidden Markov Model (HMM) based probabilistic drought analysis was proposed rather than using the existing threshold based analysis. As a result, the proposed HMM based probabilistic drought analysis scheme shows better performance in terms of defining drought state and understanding underlying characteristics of the drought. In addition, the HMM based approach is capable of quantifying the uncertainties associated with the classifying meteorological drought condition in a systematic way.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.2 no.1
• /
• pp.101-109
• /
• 1999

The objective of this research is to study effects of the residual stresses on the crack growth and the life of the structure, caused by cold working around the hole of the aircraft structure which will be jointed by rivets and bolts, etc. The compensated Morrow's equation, by experimental data from the materials AL7075-T6 and AL2024-T3, is suggested to calculate the values of the fatigue life prediction of the structure. Also, the compensated Forman's equation, by experimental data from a material AL7075-T6, is suggested to calculate the values of the crack growth prediction of the structure. It is founded that the calculated values from the suggested equations are almost close to the known values of the fatigue life prediction and the crack growth prediction. It is shown that this paper, associated with an initial research on the effects of residual stresses around hole, gives a direction to study the problem at the aircraft maintenance field.