• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.361-367
• /
• 1998

The main two applications of the Genetic Algorithms(GA) are the optimization and the machine learning. Machine Learning has two objectives that make the complex system learn its environment and produce the proper output of a system. The machine learning using the Genetic Algorithms is called GA machine learning or genetic-based machine learning (GBML). The machine learning is different from the optimization problems in finding the rule set. In optimization problems, the population of GA should converge into the best individual because optimization problems, the population of GA should converge into the best individual because their objective is the production of the individual near the optimal solution. On the contrary, the machine learning systems need to find the set of cooperative rules. There are two methods in GBML, Michigan method and Pittsburgh method. The former is that each rule is expressed with a string, the latter is that the set of rules is coded into a string. Th classifier system of Holland is the representative model of the Michigan method. The classifier systems arrange the strength of classifiers of classifier list using the message list. In this method, the real time process and on-line learning is possible because a set of rule is adjusted on-line. A classifier system has three major components: Performance system, apportionment of credit system, rule discovery system. In this paper, we solve the food search problem with the learning and evolution of an artificial ant using the learning classifier system.

• Journal of Korean Society for Atmospheric Environment
• /
• v.32 no.2
• /
• pp.158-166
• /
• 2016

To characterize the features of particle apparent density, continuous measurements of particle number size distributions from optical particle sizer (OPS) and 24 hr integrated particle mass concentrations from filter based sampler were conducted at the National institute of environmental research NamBu Supersite (NNBS, $35.22^{\circ}N$, $126.84^{\circ}E$) in Gwangju for 16 days from Nov. 4 in 2014. Source apportionment model was carried out by applying Positive Matrix Factorization (PMF) to particle size distribution data. Three different distributions related to primary and secondary sources were investigated by the diurnal patterns of identified factors. Density estimated by gaussian model has been calculated as $1.69g/cm^3$ with 95% confidence bounds ($1.57{\sim}1.81g/cm^3$).

• Journal of Forest and Environmental Science
• /
• v.27 no.1
• /
• pp.1-15
• /
• 2011

The present study was undertaken in middle altitudinal (1500 to 2500 masl) moist temperate forest of Mandal-Chopta area in the Garhwal region of Uttarakhand, India. The aim of the present study was to assess the variation in species composition and diversity in different vegetation layers viz. herb, shrub and tree, at different altitudes. Shannon-Wiener diversity index ($\bar{H}$), $Nha^{-1}$, total basal cover per hectare (G), Simpson concentration of dominance, Pielou Equitability, species richness (SR), Margalef index, Menheink index of species richness and ${\beta}$-diversity were calculated to understand community composition. Tree G ranged from 84.25 to 35.08 $m^2ha^{-1}$ and total stem density varied from 990 to 1470 Nha-1. Total SR (herb, shrub and trees) among different forest types ranged between 31 and 58. Maximum G of herb and shrub layers was recorded at lower altitudes between 1500 and 1650 masl. ${\beta}$-diversity was higher in herb layers as compared to tree and shrub layers. Dominance-diversity curves were also drawn to ascertain resource apportionment among various species in different forest types. Values of species diversity, $\bar{H}$, $Nha^{-1}$ and G were higher in the study area as compared to similar forests growing in other parts of Uttarakhand Himalaya.

• Advances in environmental research
• /
• v.10 no.1
• /
• pp.43-57
• /
• 2021

Evaluation of groundwater quality is vital due to its diverse use for several purposes. In the present study, groundwater quality and suitability from the Peshawar basin, Pakistan, were evaluated for drinking and irrigation purposes. The water samples were analysed for major cations (Ca, Mg, Na and K) and anions (chloride, bicarbonate and sulphate) along with other physicochemical parameters (pH, electrical conductivity, total dissolved solids, and total hardness). About 95% of the water samples were found to be within the WHO, US-EPA and Pak-EPA permissible levels for drinking purposes. Seventy percent (70%) of the water samples belonged to the hard water category. Irrigation water quality parameters, such as, chloride, residual sodium bicarbonate, sodium adsorption ratio, percent sodium, magnesium adsorption ratio, Kelly's ration and permeability index were evaluated which demonstrated that the groundwater was highly to moderately suitable for irrigation. A correlation study was conducted to find out the mutual associations among the variables. Piper diagram indicated the overall chemical nature of the study area was calcium-magnesium bicarbonate type. Cluster analysis revealed mutual apportionment of various parameters in the groundwater of the Peshawar basin, Pakistan.

• Journal of Soil and Groundwater Environment
• /
• v.27 no.2
• /
• pp.87-98
• /
• 2022

This study aims to prepare a technical protocol for identifying the source of nitrate in water using nitrogen (δ¹⁵N) and oxygen (δ¹⁸O) stable isotope ratios. The technical processes for nitrate sources identification are composed of site investigation, sample collection and analysis, isotope analysis, source identification using isotope characteristics, and source apportionment for multiple potential sources with the Bayesian isotope mixing model. Characteristics of various nitrate potential sources are reviewed, and their typical ranges of δ¹⁵N and δ¹⁸O are comparatively analyzed and summarized. This study also summarizes the current knowledge on the dual-isotope approach and how to correlate the field-relevant information such as land use and hydrochemical data to the nitrate source identification.

• Asian Journal of Atmospheric Environment
• /
• v.6 no.2
• /
• pp.118-126
• /
• 2012

To investigate the effect of aircraft traffic emissions on soil pollution, metal levels were analyzed for 8 metals (Fe, Cr, Pb, Zn, Cu, Ni, Mn and Cd) from the vicinity of the Indira Gandhi International (IGI) airport in Delhi, India. The texture of the airport soil was observed to be sandy. Among the metals, Cd showed minimum concentration ($2.07{\mu}g\;g^{-1}$), while Fe showed maximum concentration ($4379{\mu}g\;g^{-1}$). The highest metal accumulation was observed at the landing site. Significant correlations were observed between metals and different textures (sand, silt, and clay) as well as with organic carbon (OC). The results indicate that grain size play a major role in OC retention in soil and subsequently helps in adsorption of metals in soil. M$\ddot{u}$ller's geoaccumulation index (I-geo) showed that airport soil was contaminated due to Cd and Pb with the pollution class 2 and 1, respectively. Pollution load index of the airport site was 1.34-3 times higher than the background site. The results of factor analysis suggested that source of the soil metal is mainly from natural weathering of soil, aircraft exhaust, and automobile exhaust from near by area. With respect to Dutch target values, the airport soils showed ~3 times higher Cd concentration. The study highlighted the future risk of enhanced metal pollution with respect to Cd and Pb due to aircraft trafficking.

• Journal of Environmental Impact Assessment
• /
• v.14 no.4
• /
• pp.227-235
• /
• 2005

Source contribution for VOCs collected in Seoul metropolitan area was conducted using PAMs (Photochemical assessment monitoring system) data and CMB(Chemical Mass Balance) model8.0, in order to estimate spatial and temporal variations of VOCs source contribution in that area, and also to compare with corresponding emission inventory. VOCs data used in model calculation were collected at 6 different sites of PAMs(Seokmori, Guwoldong, Simgokdong, Bulgwangdong, Jeongdong and Yangpyeong) and 22 out of 56 VOCs species were analyzed from June 2002 to march 2003 and used for CMB model estimation. The result showed that vehicle exhaust, coating and energy combustion were important sources of VOCs in Seoul metropolitan area, averaging 32.6%, 25.5% and 25.1%, respectively. In this study as well as other references, it was revealed that vehicle exhaust is the main contributor of urban area VOCs, but there is remarkable contrast between emission inventory and model estimation. Vehicle exhaust portion is seriously underestimated while coating is usually overestimated in emission estimates, compared to CMB results. Therefore, it is considered to assert and confirm the uncertainty of emission estimates and clarify the distinction between two other source apportionment methods.

• Journal of Korean Society for Atmospheric Environment
• /
• v.19 no.4
• /
• pp.387-396
• /
• 2003

A field study was conducted during the summer time of 2002 to determine compositions of volatile organic compounds (VOCs) emitted from vehicles and to develop source emission profiles that is applied to CMB model to estimate the source contribution of certain area. Source emission profile is widely used for the estimation of source contribution by the chemical mass balance model and have to be developed applicable for the target area of estimation. This study was aimed to develop source emission profile and estimation of source contribution of VOCs after application of the chemical mass balance (CMB) receptor model. After considering the emission inventory and other research results for the VOCs in Seoul, Korea, the sources like vehicle emission (tunnel), gas station (gasoline, diesel), solvent usage (painting operation, dry cleaning, graphic art), and gas fuels were selected for the major VOCs sources. Furthermore, ambient air samples were simultaneously collected from 09:00 to 11:00 for four days at eight different official air quality monitoring sites as receptors in Seoul during summer of 2001. Source samples were collected by canisters, and then about seventy volatile organic compounds were analyzed by gas chromatography with flame ionization detector (GC/FID). Based on both the developed source profiles and the database of the receptors, CMB model was intensively applied to estimate mass contribution of VOCs sources. Examining the source profile from the vehicle, the portion of alkanes of VOCs was highest, and then the portion of aromatics such toluene, m/p-xylene were followed. In case of gas fuel. they have their own components; the content of butane, propane, ethane was higher than any other component according to the fuel usage. The average of the source apportionment on VOCs for 8 sites showed that the major sources were vehicle emission and gas fuels. The vehicle emission source was revealed as having the highest contribution with an average of 49.6%, and followed by solvent with 21.3%, gas fuel with 16.1%, gasoline with 13.1%.

• Journal of Korean Society for Atmospheric Environment
• /
• v.25 no.3
• /
• pp.219-236
• /
• 2009

Particle-phase organic tracers (molecular markers) have been shown to be an effective method to assess and quantify the impact of sources of carbonaceous aerosols. These molecular markers have been used in chemical mass balance (CMB) models to apportion primary sources of organic aerosols in regions where the major organic aerosol source categories have been identified. As in the case of all CMB models, all important sources of the tracer compounds must be included in a Molecular Marker CMB (MM-CMB) model or the MMCMB model can be subject to biases. To this end, the application of the MM-CMB models to locations where reasonably accurate emissions inventory of organic aerosols are not available, should be performed with extreme caution. Of great concern is the potential presence of industrial point sources that emit carbonaceous aerosols and have not been well characterized or inventoried. The current study demonstrates that emissions from industrial point sources in the St. Louis, Missouri area can greatly bias molecular marker CMB models if their emissions are not correctly addressed. At a sampling site in the greater St. Louis Area, carbonaceous aerosols from industrial point sources were found to be important source of carbonaceous aerosols during specific time periods in addition to common urban sources (i.e. mobile sources, wood burning, and road dust). Since source profiles for these industrial sources have not been properly characterized, method to identify time periods when point sources are impacting a sampling site, needs to avoid obtaining biases source apportionment results. The use of real time air pollution measurements, along with molecular marker measurements, as a screening tool to identify when point sources are impacting a receptor site is presented.

• Journal of Korean Society for Atmospheric Environment
• /
• v.19 no.6
• /
• pp.719-731
• /
• 2003

In order to maintain and manage ambient air quality, it is necessary to identify sources and to apportion its sources for ambient particulate matters. The receptor methods were one of the statistical methods to achieve reasonable air pollution strategies. Also, receptor methods, a field of chemometrics, is based on manifold applied statistics and is a statistical methodology that analyzes the physicochemical properties of gaseous and particulate pollutant on various atmospheric receptors, identifies the sources of air pollutants, and quantifies the apportionment of the sources to the receptors. The objective of this study was 1) after obtaining results from the PMF modeling, the existing sources of air at the study area were qualitatively identified and the contributions of each source were quantitatively estimated as well. 2) finally efficient air pollution management and control strategies of each source were suggested. The PMF model was intensively applied to estimate the quantitative contribution of air pollution sources based on the chemical information (128 samples and 25 chemical species). Through a case study of the PMF modeling for the PM-10 aerosols, the total of 11 factors were determined. The multiple linear regression analysis between the observed PM-10 mass concentration and the estimated G matrix had been performed following the FPEAK test. Finally the regression analysis provided quantitative source contributions (scaled G matrix) and source profiles (scaled F matrix). The results of the PMF modeling showed that the sources were apportioned by secondary aerosol related source 28.8 ％, soil related source 16.8％, waste incineration source 11.5%, field burning source 11.0%, fossil fuel combustion source 10%, industry related source 8.3％, motor vehicle source 7.9%, oil/coal combustion source 4.4％, non-ferrous metal source 0.3％. and aged sea- salt source 0.2％, respectively.