• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.263-278
• /
• 2022

With the recent advent of IoT technology, automatic pet feeders are being distributed so that owners can feed their companion animals while they are out. However, due to behaviors of pets, the method of measuring weight, which is important in automatic feeding, can be easily damaged and broken when using the scale. The 3D camera method has disadvantages due to its cost, and the 2D camera method has relatively poor accuracy when compared to 3D camera method. Hence, the purpose of this study is to propose a deep learning approach that can accurately estimate weight while simply using a 2D camera. For this, various convolutional neural networks were used, and among them, the ResNet101-based model showed the best performance: an average absolute error of 3.06 grams and an average absolute ratio error of 3.40%, which could be used commercially in terms of technical and financial viability. The result of this study can be useful for the practitioners to predict the weight of a standardized object such as feed only through an easy 2D image.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.4
• /
• pp.228-235
• /
• 2007

The main purpose of this paper is to manage the container property effectively at the container yard by applying the RTLS technology to the field of port logistics. Yet, many kinds of noises happen to be inputted with the distance value(between the reader and the tag) which is to be inputted into the location identification algorithm, which makes the distance value jumped due to the system noise of the ultrasonic sensor module and the measurement noise. The Kalman Filter is widely used to prevent this jump occurrence; the noises are eliminated by using the EKF(Extended Kalman Filter) while considering that the distance information of the ultrasonic sensor is non-linear. Also, the 3D RTLS system at the port container yard suggested in this research is designed not to be interrupted for its ultrasonic transmission by positioning the antenna at the front of each sector of the container where the active tags are installed. We positioned the readers, which function as antennas for location identification, to four places randomly in the absolute coordinate and let the positions of the active tags identified by using the distance data delivered from the active tags. For the location identification algorithm used in this paper, the triangulation measurement that is most used in general is applied and newly reorganized to calculate the position of the container. In the first experiment, we dealt with the error resulting in the angle and the distance of the ultrasonic sensor module, which is the most important in the hardware performance; in the second, we evaluated the performance of the location identification algorithm, which is the most important in the software performance, and tested the noise cancellation effects for the EKF. According to the experiment result, the ultrasonic sensor showed an average of 3 to 5cm error up to $45^{\circ}$ in case of $60^{\circ}$ or more, non-reliable linear distances were obtained. In addition, the evaluation of the algorithm performance showed an average of $4^{\circ}{\sim}5^{\circ}$ error due to the error of the linear distance-this error is negligible for most container location identifications. Lastly, the experiment results of noise cancellation and jump preservation by using the EKF showed that noises were removed in the distance information which was entered from the input of the ultrasonic sensor and as a result, only signal was extracted; thus, jumps were able to be removed and the exact distance information between the ultrasonic sensors could be obtained.

• Korean Journal of Applied Biomechanics
• /
• v.24 no.2
• /
• pp.181-187
• /
• 2014

In this study, a real-time evaluation system for quantitative dynamic fitting during pedaling was developed. The system is consisted of LED markers, a digital camera connected to a computer and a marker detecting program. LED markers are attached to hip, knee, ankle joint and fifth metatarsal in the sagittal plane. Playstation3 eye which is selected as a main digital camera in this paper has many merits for using motion capture, such as high FPS (Frame per second) about 180FPS, $320{\times}240$ resolution, and low-cost with easy to use. The maker detecting program was made by using Labview2010 with Vision builder. The program was made up of three parts, image acquisition & processing, marker detection & joint angle calculation, and output section. The digital camera's image was acquired in 95FPS, and the program was set-up to measure the lower-joint angle in real-time, providing the user as a graph, and allowing to save it as a test file. The system was verified by pedalling at three saddle heights (knee angle: 25, 35, $45^{\circ}$) and three cadences (30, 60, 90 rpm) at each saddle heights by using Holmes method, a method of measuring lower limbs angle, to determine the saddle height. The result has shown low average error and strong correlation of the system, respectively, $1.18{\pm}0.44^{\circ}$, $0.99{\pm}0.01^{\circ}$. There was little error due to the changes in the saddle height but absolute error occurred by cadence. Considering the average error is approximately $1^{\circ}$, it is a suitable system for quantitative dynamic fitting evaluation. It is necessary to decrease error by using two digital camera with frontal and sagittal plane in future study.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.52 no.5
• /
• pp.61-68
• /
• 2010

Jangchan reservoir is located in Okcheon county, Chungbuk province, of which watershed area is $29.4\;km^2$ from outside, and $5.1\;km^2$ from inside watershed, effective storage capacity is $392{\times}10^4\;m^3$, paddy area to be irrigated is 474 ha. To determine inflows from Keumcheon weir located in outside watershed on an optimum level, a repeated procedure which is composed of simulation of inflows to Keumcheon weir, setting of range of water taking at Keumcheon weir, simulation of inflows to Jangchan reservoir, estimation of paddy water from Jangchan reservoir, and simulation of water storages in Jangchan reservoir was selected. Parameters of DAWAST model for simulating inflows to Jangchan reservoir were determined to UMAX of 315 mm, LMAX of 21 mm, FC of 130 mm, CP of 0.018, and CE of 0.007 with absolute sum of errors in reservoir water storages minimized using unconstrained Simplex method because of no inflows data. Inflows to Keumcheon weir were simulated to $2,132{\times}10^4\;m^3$ on an annual average. Optimal range of water taking at Keumcheon weir to transfer to Jangchan reservoir were $0.81{\sim}50\;mm/km^2/d$, which were summed up to $1,397{\times}10^4\;m^3$ in 66% of total on an annual average. Inflows to Jangchan reservoir were simulated to $1,739{\times}10^4\;m^3$ on an annual average of which were 80 % from Keumcheon weir of outside watershed. Requirements to paddy water from Jangchan reservoir were estimated to $543{\times}10^4\;m^3$ on an annual average.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.2
• /
• pp.10-20
• /
• 2012

This study shows how to estimate AADT(Annual Average Daily Traffic) on temporary count data using new grouping method. This study deals with clustering permanent traffic counts using monthly adjustment factor, daily adjustment factor and a percentage of hourly volume. This study uses a percentage of hourly volume comparing with other studies. Cluster analysis is used and 5 groups is suitable. First, make average of monthly adjustment factor, average of daily adjustment factor, a percentage of hourly volume for each group. Next estimate AADT using 24 hour volume(not holiday) and two adjustment factors. Goodness of fit test is used to find what groups are applicable. MAPE(Mean Absolute Percentage Error) is 8.7% in this method. It is under 1.5% comparing with other method(using adjustment factors in same section). This method is better than other studies because it can apply all temporary counts data.

• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1193-1201
• /
• 2020

This study aims to develop a regression model that estimates a low-flow index that can be applied to ungauged basins. A total of 30 midsized basins in South Korea use long-term runoff data provided by the National Integrated Water Management System (NIWMS) to calculate average low-flow, average minimum streamflow, and low-flow index duration and frequency. This information is used in the correlation analysis with 18 basin factors and 3 climate change factors to identify the basin area, average basin altitude, average basin slope, water system density, runoff curve number, annual evapotranspiration, and annual precipitation in the low-flow index regression model. This study evaluates the model's accuracy by using the root-mean-square error (RMSE) and the mean absolute error (MAE) for 10 ungauged, verified basins and compares them with the previous model's low-flow calculations to determine the effectiveness of the newly developed model. Comparative analysis indicates that the new regression model produces average low-flow, attributed to the consideration of varied basin and hydrologic factors during the new model's development.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.25-30
• /
• 2016

It is critical to forecast the maximum daily and monthly demand for power with as little error as possible for our industry and national economy. In general, long-term forecasting of power demand has been studied from both the consumer's perspective and an econometrics model in the form of a generalized linear model with predictors. Time series techniques are used for short-term forecasting with no predictors as predictors must be predicted prior to forecasting response variables and containing estimation errors during this process is inevitable. In previous researches, seasonal exponential smoothing method, SARMA (Seasonal Auto Regressive Moving Average) with consideration to weekly pattern Neuron-Fuzzy model, SVR (Support Vector Regression) model with predictors explored through machine learning, and K-means clustering technique in the various approaches have been applied to short-term power supply forecasting. In this paper, SARMA and intervention model are fitted to forecast the maximum power load daily, weekly, and monthly by using the empirical data from 2011 through 2013. $ARMA(2,\;1,\;2)(1,\;1,\;1)_7$ and $ARMA(0,\;1,\;1)(1,\;1,\;0)_{12}$ are fitted respectively to the daily and monthly power demand, but the weekly power demand is not fitted by AREA because of unit root series. In our fitted intervention model, the factors of long holidays, summer and winter are significant in the form of indicator function. The SARMA with MAPE (Mean Absolute Percentage Error) of 2.45% and intervention model with MAPE of 2.44% are more efficient than the present seasonal exponential smoothing with MAPE of about 4%. Although the dynamic repression model with the predictors of humidity, temperature, and seasonal dummies was applied to foretaste the daily power demand, it lead to a high MAPE of 3.5% even though it has estimation error of predictors.

• Journal of the Korean Solar Energy Society
• /
• v.39 no.3
• /
• pp.59-66
• /
• 2019

New and renewable energy forecasts are key technology to reduce the annual operating cost of new and renewable facilities, and accuracy of forecasts is paramount. In this study, we intend to build a model for the prediction of short-term solar power generation for 1 hour to 3 hours. To this end, this study applied two time series technique, ARIMA model without considering seasonality and SARIMA model with considering seasonality, comparing which technique has better predictive accuracy. Comparing predicted errors by MAE measures of solar power generation for 1 hour to 3 hours at four locations, the solar power forecast model using ARIMA was better in terms of predictive accuracy than the solar power forecast model using SARIMA. On the other hand, a comparison of predicted error by RMSE measures resulted in a solar power forecast model using SARIMA being better in terms of predictive accuracy than a solar power forecast model using ARIMA.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.17-23
• /
• 2019

In this paper, quality control (QC) is applied to each meteorological element of weather data collected from seven IoT sensors such as temperature. In addition, we propose a method for estimating the data regarded as error by means of machine learning. The collected meteorological data was linearly interpolated based on the basic QC results, and then machine learning-based QC was performed. Support vector regression, decision table, and multilayer perceptron were used as machine learning techniques. We confirmed that the mean absolute error (MAE) of the machine learning models through the basic QC is 21% lower than that of models without basic QC. In addition, when the support vector regression model was compared with other machine learning methods, it was found that the MAE is 24% lower than that of the multilayer neural network and 58% lower than that of the decision table on average.

• Journal of Korean Society of Transportation
• /
• v.23 no.4 s.82
• /
• pp.71-79
• /
• 2005

Existing arterial link travel time estimation methods relying on either aggregate point-based or individual section-based traffic data have their inherent limitations. This paper demonstrates the utility of data fusion for improving arterial link travel time estimation. If the data describe traffic conditions, an operator wants to know whether the situations are going better or worse. In addition, some traffic information providing strategies require predictions of what would be the values of traffic variables during the next time period. In such situations, it is necessary to use a prediction algorithm in order to extract the average trends in traffic data or make short-term predictions of the control variables. In this research. a multi-step ahead prediction algorithm using Data fusion was developed to predict a link travel time. The algorithm performance were tested in terms of performance measures such as MAE (Mean Absolute Error), MARE(mean absolute relative error), RMSE (Root Mean Square Error), EC(equality coefficient). The performance of the proposed algorithm was superior to the current one-step ahead prediction algorithm.