• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.123-132
• /
• 2013

As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.

• Journal of Food Hygiene and Safety
• /
• v.24 no.3
• /
• pp.232-237
• /
• 2009

This study was conducted to develop a model for describing the effect of storage temperature (4, 10, 15, 20, 25, 30 and $35^{\circ}C$) on the growth of Escherichia coli O157 : H7 in ready-to-eat (RTE) lettuce treated with or without (control) alkaline electrolyzed water (AIEW). The growth curves were well fitted with the Gompertz equation, which was used to determine the specific growth rate (SGR) and lag time (LT) of E. coli O157 : H7 ($R^2$ = 0.994). Results showed that the obtained SGR and LT were dependent on the storage temperature. The growth rate increased with increasing temperature from 4 to $35^{\circ}C$. The square root models were used to evaluate the effect of storage temperature on the growth of E. coli O157 : H7 in lettuce samples treated without or with AIEW. The coefficient of determination ($R^2$), adjusted determination coefficient ($R^2_{Adj}$), and mean square error (MSE) were employed to validate the established models. It showed that $R^2$ and $R^_{Adj}$ were close to 1 (> 0.93), and MSE calculated from models of untreated and treated lettuce were 0.031 and 0.025, respectively. The results demonstrated that the overall predictions of the growth of E. coli O157: H7 agreed with the observed data.

• Journal of Environmental Science International
• /
• v.23 no.12
• /
• pp.2045-2056
• /
• 2014

In this study, pressure drop was measured in the pulse jet bag filter without venturi on which 16 numbers of filter bags (Ø$140{\times}850{\ell}$) are installed according to operation condition(filtration velocity, inlet dust concentration, pulse pressure, and pulse interval) using coke dust from steel mill. The obtained 180 pressure drop test data were used to predict pressure drop with multiple regression model so that pressure drop data can be used for effective operation condition and as basic data for economical design. The prediction results showed that when filtration velocity was increased by 1%, pressure drop was increased by 2.2% which indicated that filtration velocity among operation condition was attributed on the pressure drop the most. Pressure was dropped by 1.53% when pulse pressure was increased by 1% which also confirmed that pulse pressure was the major factor affecting on the pressure drop next to filtration velocity. Meanwhile, pressure drops were found increased by 0.3% and 0.37%, respectively when inlet dust concentration and pulse interval were increased by 1% implying that the effects of inlet dust concentration and pulse interval were less as compared with those changes of filtration velocity and pulse pressure. Therefore, the larger effect on the pressure drop the pulse jet bag filter was found in the order of filtration velocity($V_f$), pulse pressure($P_p$), inlet dust concentration($C_i$), pulse interval($P_i$). Also, the prediction result of filtration velocity, inlet dust concentration, pulse pressure, and pulse interval which showed the largest effect on the pressure drop indicated that stable operation can be executed with filtration velocity less than 1.5 m/min and inlet dust concentration less than $4g/m^3$. However, it was regarded that pulse pressure and pulse interval need to be adjusted when inlet dust concentration is higher than $4g/m^3$. When filtration velocity and pulse pressure were examined, operation was possible regardless of changes in pulse pressure if filtration velocity was at 1.5 m/min. If filtration velocity was increased to 2 m/min. operation would be possible only when pulse pressure was set at higher than $5.8kgf/cm^2$. Also, the prediction result of pressure drop with filtration velocity and pulse interval showed that operation with pulse interval less than 50 sec. should be carried out under filtration velocity at 1.5 m/min. While, pulse interval should be set at lower than 11 sec. if filtration velocity was set at 2 m/min. Under the conditions of filtration velocity lower than 1 m/min and high pulse pressure higher than $7kgf/cm^2$, though pressure drop would be less, in this case, economic feasibility would be low due to increased in installation and operation cost since scale of dust collection equipment becomes larger and life of filtration bag becomes shortened due to high pulse pressure.

• Ecology and Resilient Infrastructure
• /
• v.7 no.2
• /
• pp.126-133
• /
• 2020

In accordance with the implementation of the sunset provision to cancel the designations of urban park sites that remained unexecuted for a prolonged period until 2020, the park sites in the city center, which account for 90% of the long-term unexecuted urban facilities subjected to the provision, are currently on the verge of development. The total area of the 204 park sites that will disappear in Seoul as a result of this provision is 95 ㎢; moreover, 116 of these are privately-owned. It is expected that the possible changes in the use of these park sites could result in reckless development and reduction of green space, which would ultimately affect the ecosystem. This study applied the InVEST model to calculate the changes in the fixed carbon amount before and after the implementation of the sunset provision to estimate the economic value of these changes. The study focused on Jongno-gu in Seoul because it has the most unexecuted park sites subjected to the lifting of the designation. The research findings show that the fixed carbon amount provided by the unexecuted park sites in Jongno-gu was 374,448 mg, prior to the implementation of the sunset provision; however, the amount was estimated to decrease by 18% to 305,564 mg after its execution. When calculated in terms of average value of the real carbon price, this translated into a loss of approximately 700 million won. In addition, considering the social costs including both climate change and the impact on the ecosystem, an economic loss of approximately 98 billion won was projected. This study is meaningful because its predictions are based on the estimation of fixed carbon amount according to the implementation of the sunset provision in Jongno-gu and scientifically calculates the value of ecological services provided by the parks in the city. This study can serve not only as a basis during the decision-making process for policies related to ecosystem conservation and development, but also as an evidentiary material for the compensation of privately-owned land that is designated as urban park sites and was unexecuted for a prolonged period.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of the Korean GEO-environmental Society
• /
• v.15 no.1
• /
• pp.63-68
• /
• 2014

In this study, it was found that determined the photocatalytic degradation of antibiotics (lincomycin, LM) with various catalyst composite of titanium dioxide ($TiO_2$), hydroxyapatite (HAP) and germanium (Ge) under UV-A irradiation. At first, various type of complex catalysts were investigated to compare the enhanced photocatalytic potential. It was observed that in order to obtain the removal efficiencies were $TiO_2/HAP/Ge$ > $TiO_2/Ge$ > $TiO_2/HAP$. The composition of $TiO_2/HAP/Ge$ using a statistical approach based on mixture analysis design, one of response surface method was investigated. The independent variables of $TiO_2$ ($X_1$), HAP ($X_2$) and Ge ($X_3$) which consisted of 6 condition in each variables was set up to determine the effects on LM ($Y_1$) and TOC ($Y_2$) degradation. Regression analysis on analysis of variance (ANOVA) showed significant p-value (p < 0.05) and high coefficients for determination value ($R^2$ of $Y_1=99.28%$ and $R^2$ of $Y_2=98.91%$). Contour plot and response curve showed that the effects of $TiO_2/HAP/Ge$ composition for LM degradation under UV-A irradiation. And the estimated optimal composition for TOC removal ($Y_2$) were $X_1=0.6913$, $X_2=0.2313$ and $X_3=0.0756$ by coded value. By comparison with actual applications, the experimental results were found to be in good agreement with the model's predictions, with mean results for LM and TOC removal of 99.2% and 49.3%, respectively.

• Proceedings of the Korea Society of Poultry Science Conference
• /
• 2004.11a
• /
• pp.80-90
• /
• 2004

Three experiments were performed to test the assumption that imbalanced dietary amino acid mixtures must lead to increased heat production (HP). The first experiment was based on diets formulated to have a wide range of crude protein (CP) concentrations but a fixed concentration of lysine, formulated to be the first-limiting amino acid. In the second (converse) experiment, lysine concentration was varied over a wide range while CP content was kept constant. To prevent the masking of dietary effects by thermoregulatory demands, the third experiment was performed at 30 $^{\circ}C$ with the diets similar to the diets used in the second experiment. The detailed relationships among amino acid balance, nitrogen (N) metabolism and energy (E) metabolism were investigated in a computer-controlled chamber calorimetry system. The results of experiments were compared with the predictions of a computerised simulation model of E metabolism. In experiment 1. with constant lysine and varying CP, there was a 75 % increase in N intake as CP concentration increased. This led to a 150 % increase in N excretion. with no significant change in HP. Simulated HP agreed with the empirically determined results in not showing a trend with dietary CP. In experiment 2, with varying lysine but constant CP, there was a 3-fold difference in daily weight gain between the lowest and highest lysine diets. HP per bird increased significantly with dietary lysine concentration. There was still an effect when HP was adjusted for body weight differences, but it failed to maintain statistical significance. Simulated HP results agreed in showing little effect of varying lysine concentration and growth rate on HP. Based on the results of these two experiments, the third experiment was designed to test the response of birds to dietary lysine in high ambient temperature. In experiment 3 which performed at high ambient temperature (30 $^{\circ}C$), HP per bird increased significantly with dietary lysine content, whether or not adjusted for body-weight. The trend was greater than in the previous experiment (20 $^{\circ}C$).

• Journal of the Korean Geotechnical Society
• /
• v.21 no.2
• /
• pp.113-120
• /
• 2005

An understanding of soil-structure interaction is the key to rational and economical design for laterally loaded drilled shafts. It is very difficult to formulate the ultimate lateral capacity into a general equation because of the inherent soil nonlincarity, nonhomogeneity, and complexity enhanced by the three dimensional and asymmetric nature of the problem though extensive research works on the behavior of deep foundations subjected to lateral loads have been conducted for several decades. This study reviews the four most well known methods (i.e., Reese, Broms, Hansen, and Davidson) among many design methods according to the specific site conditions, the drilled shaft geometric characteristics (D/B ratios), and the loading conditions. And the hyperbolic lateral capacities (H$_h$) interpreted by the hyperbolic transformation of the load-displacement curves obtained from model tests carried out as a part of this research have been compared with the ultimate lateral capacities (Hu) predicted by the four methods. The H$_u$ / H$_h$ ratios from Reese's and Hansen's methods are 0.966 and 1.015, respectively, which shows both the two methods yield results very close to the test results. Whereas the H$_u$ predicted by Davidson's method is larger than H$_h$ by about $30\%$, the C.0.V. of the predicted lateral capacities by Davidson is the smallest among the four. Broms' method, the simplest among the few methods, gives H$_u$ / H$_h$ : 0.896, which estimates the ultimate lateral capacity smaller than the others because some other resisting sources against lateral loading are neglected in this method. But it results in one of the most reliable methods with the smallest S.D. in predicting the ultimate lateral capacity. Conclusively, none of the four can be superior to the others in a sense of the accuracy of predicting the ultimate lateral capacity. Also, regardless of how sophisticated or complicated the calculating procedures are, the reliability in the lateral capacity predictions seems to be a different issue.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.3
• /
• pp.149-155
• /
• 2021

Early warning systems for weather risk management in the agricultural sector have been developed to predict potential wind damage to crops. These systems take into account the daily maximum wind speed to determine the critical wind speed that causes fruit drops and provide the weather risk information to farmers. In an effort to increase the accuracy of wind risk predictions, an artificial neural network for binary classification was implemented. In the present study, the daily wind speed and other weather data, which were measured at weather stations at sites of interest in Jeollabuk-do and Jeollanam-do as well as Gyeongsangbuk- do and part of Gyeongsangnam- do provinces in 2019, were used for training the neural network. These weather stations include 210 synoptic and automated weather stations operated by the Korean Meteorological Administration (KMA). The wind speed data collected at the same locations between January 1 and December 12, 2020 were used to validate the neural network model. The data collected from December 13, 2020 to February 18, 2021 were used to evaluate the wind risk prediction performance before and after the use of the artificial neural network. The critical wind speed of damage risk was determined to be 11 m/s, which is the wind speed reported to cause fruit drops and damages. Furthermore, the maximum wind speeds were expressed using Weibull distribution probability density function for warning of wind damage. It was found that the accuracy of wind damage risk prediction was improved from 65.36% to 93.62% after re-classification using the artificial neural network. Nevertheless, the error rate also increased from 13.46% to 37.64%, as well. It is likely that the machine learning approach used in the present study would benefit case studies where no prediction by risk warning systems becomes a relatively serious issue.

• Journal of Bio-Environment Control
• /
• v.31 no.4
• /
• pp.376-383
• /
• 2022

The current study, which consisted of two independent studies (laboratory and greenhouse), was carried out to project the hypothesis fungi-spray scheduling for leaf mold and gray leaf spot in tomato, as well as to evaluate the effect of temperature and leaf wet duration on the effectiveness of different fungicides against these diseases. In the first experiment, tomato leaves were infected with 1 × 10⁴ conidia·mL^-1 and put in a dew chamber for 0 to 18 hours at 10 to 25℃ (Fulvia fulva) and 10 to 30℃ (Stemphylium lycopersici). In farm study, tomato plants were treated for 240 hours with diluted (1,000 times) 30% trimidazole, 50% polyoxin B, and 40% iminoctadine tris (Belkut) for protection of leaf mold, and 10% etridiazole + 55% thiophanate-methyl (Gajiran), and 15% tribasic copper sulfate (Sebinna) for protection of gray leaf spot. In laboratory test, leaf condensation on the leaves of tomato plants were emerged after 9 hrs. of incubation. In conclusion, the incidence degree of leaf mold and gray leaf spot disease on tomato plants shows that it is very closely related to formation of leaf condensation, therefore the incidence of leaf mold was greater at 20 and 15℃, while 25 and 20℃ enhanced the incidence of gray leaf spot. The incidence of leaf mold and gray leaf spot developed 20 days after inoculation, and the latency period was estimated to be 14-15 days. Trihumin fungicide had the maximum effectiveness up to 168 hours of fungicides at 12 hours of wet duration in leaf mold, whereas Gajiran fungicide had the highest control (93%) against gray leaf spot up to 144 hours. All the chemicals showed an around 30-50% decrease in effectiveness after 240 hours of treatment. The model predictions in present study could be help in timely, effective and ecofriendly management of leaf mold disease in tomato.