http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Study of Model Selection for Electric Data using Cross Validation Approach
Saraswathi Sivamani,Saravana Kumar,신창선,박장우,조용윤 한국지식정보기술학회 2017 한국지식정보기술학회 논문지 Vol.12 No.6
In this paper, the appropriate model is selected for the risk assessment of the electric utility pole data with the help of cheat sheets and k-fold cross validation. In order to analyze, predict and forecast the data, the appropriate model has to be selected. The major issue is the declination of the accuracy in the model fitting, which may result in poor model selection. There are different type of machine learning algorithm, which makes it difficult to conclude the model selection. To ensure the proper selection of the model, we undergo a two-step process. Firstly, the basic model is selected with the existing model selection cheat sheets named as Scikit learn and Microsoft azure, by understanding the available input and required output of the data. After getting through the multiple question, the respective models such as Generalized Additive Model, Generalized Linear Model, Linear Regression and Support Vector Machine are obtained. In order to attain the appropriate model, we perform k-fold cross validation to estimate the risk of the algorithms, by comparing 2-fold, 8-fold and 10-fold cross validation. Between the three set, the 10-cross fold validation of generalized additive model is selected with the least risk error. Using k-fold cross validation, we estimate the accuracy of the model that is suitable for the data, by using the electric power data set.
An Ontology Model for Smart Service in Vertical Farms – An OWL-S Approach
Saraswathi Sivamani,Hong-geun Kim,Myeongbae Lee,Jangwoo Park,Changsun Shin,Yongyun Cho 보안공학연구지원센터 2016 International Journal of u- and e- Service, Scienc Vol.9 No.1
Recently, the evolution of ubiquitous computing has brought a breakthrough in network access and web based services including the agricultural field, which is integral to human living. In a ubiquitous vertical farm environment, context aware services display the context information in selecting the appropriate web service by identifying the state of the user and its surroundings. In this web enabled environment, establishing a context aware system for the vertical farm without the understanding of domains gets complicated especially when shaping with the avails. The semantic web should enable users to locate, select, compose and monitor web-based services automatically. For a successful execution of such services in semantic web, the service needs to be grounded with the corresponding WSDL. To resolve these issues, our work includes the development of an OWL-S based ontology model to define the relationship between the domains and add classes needed for the model in every aspect of the service oriented system. Compared with any other semantic web service, OWL-S is more suitable for the Vertical Farming System in the ubiquitous computing.
Towards an Intelligent Livestock Farm Management using OWL-based Ontology Model
Saraswathi Sivamani,Jangwoo Park,Changsun Shin,Kyungryong Cho,Dongguk Park,Yongyun Cho 보안공학연구지원센터 2015 International Journal of Smart Home Vol.9 No.4
In this paper, we have designed the ontology model to achieve a cost effective livestock farm environment by maintaining safety and quality. The proposed model is built with the situational context aware data by making use of the wireless sensor network (WSN). The concepts of the proposed model are identified after considering all the possibilities with respect to the control services that help to increase the productivity and automation in the livestock farm environment. The health and diet management along with the environmental services are considered as a main service, which is a deniable fact. In addition to these services, uprising and downsizing of stock prices can affect the management behavior in regard to the production services. In order to solve the issue, both the health and diet management plans are monitored and modified automatically with respect to the changes in the stock market. With the proposed ontology model, the information from Internet of Things (IoT) is recomposed as context information, which helps in the understanding of the relationship between the livestock environmental factors.
Peak Hour Identification for Traffic Congestion Based on IoT Environments
Vasanth Ragu,Saraswathi Sivamani,이명배,조현욱,조용윤,박장우,신창선 한국지식정보기술학회 2018 한국지식정보기술학회 논문지 Vol.13 No.3
This study deals with the analysis of traffic congestion and the peak hour identification by using Kalman Filter and Ensemble Model. There are different types of traffic congestion, Roadway Traffic congestion, Airways Traffic congestion, Network Traffic congestion, and so on. This study focuses on Roadway Traffic congestion. The peak hour identification is essential to prevent roadway traffic congestion. In roadway traffic congestion, there are two categories in traffic data, namely Roadside Equipment (RSE) data and Video Detection System (VDS) data. Both data were collected from RSE devices and VDS devices, which are located in roadways signals, toll plaza, private sectors, and etc. In traffic data, it may contain error values. So, this paper applies the Kalman Filter for the purpose of removing the error values or inaccurate values and providing the cleaned Traffic data. The suggested study also uses the Ensemble Model to average the traffic data at corresponding hours easily to analyse the traffic data. To identify peak hour, it defines four different models by considering numbers, average times, and average speeds of vehicles. With the suggested method, the perfect peak hour in the traffic data can be easily and exactly obtained. In the tests and results, this paper showed the detailed process of peak hour identification in traffic congestion.
An Optimal Model Prediction for Fruits Diseases with Weather Conditions
Vasanth Gagu,이명배,Saraswathi Sivamani,조용윤,박장우,조경룡,조성은,홍기정,오수열,신창선 (사)한국스마트미디어학회 2019 스마트미디어저널 Vol.8 No.1
This study provides the analysis and prediction of fruits diseases related to weather conditions(temperature, wind speed, solar power, rainfall and humidity) using Linear Model and Poisson Regression. The main goal of the research is to control the method of fruits diseases and also to prevent diseases usingless agricultural pesticides. So, it is needed to predict the fruits diseases with weather data. Initially, fruitdata is used to detect the fruit diseases. If diseases are found, we move to the next process and verify thecondition of the fruits including their size. We identify the growth of fruit and evidence of diseases withLinear Model. Then, Poisson Regression used in this study to fit the model of fruits diseases with weatherconditions as an input provides the predicted diseases as an output. Finally, the residuals plot, Q-Q plotand other plots help to validate the fitness of Linear Model and provide correlation between the actual andthe predicted diseases as a result of the conducted experiment in this study.