• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.388-393
• /
• 2024

The convergence of machine learning and smart farm is becoming more and more important. The purpose of this research is to quantitatively analyze machine learning and smart farm with bibliographic data from 2013 to 2023. This study analyzed the 251 articles, filtered from the Web of Science, with regard to the article publication trend, the article citation trend, the top 10 research area, and the top 10 keywords representing the articles. The quantitative analysis results reveal the four points: First, the number of article publications in machine learning and smart farm continued growing from 2016. Second, the article citations in machine learning and smart farm drastically increased since 2018. Third, Computer Science, Engineering, Agriculture, Telecommunications, Chemistry, Environmental Sciences Ecology, Material Science, Instruments Instrumentation, Science Technology Other Topics, and Physics are top 10 research areas. Fourth, it is 'machine learning', 'smart farming', 'internet of things', 'precision agriculture', 'deep learning', 'agriculture', 'big data', 'machine', 'smart' and 'smart agriculture' that are the top 10 keywords composing authors' keywords in the articles in machine learning and smart farm from 2013 to 2023.

• 한국생산제조학회지
• /
• 제24권1호
• /
• pp.7-14
• /
• 2015

The machine tools builders are trying to improve the efficiency and performance of the machine tools. The electro-mechanical driven broaching machine has many advantages such as lower noisy operating, higher energy efficiency, and smaller space of installation. This paper presents the structural and mechanical development of an electro-mechanical driven broaching machine that is replaced for traditional hydraulic one. The servo motor, ball screw and roller linear guide are used instead of hydraulic cylinder and translation frictional sliding guides. The simulation method based on FEM was applied to analyze the stress, deformation of the machine for static analysis. The dynamic analysis was carried out for verifying and assessing the mechanical behavior of the developed broaching machine. This work helps broaching machine developer make a better product at the early design stage with lower cost and development time.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제22권1호
• /
• pp.15-28
• /
• 2018

Recently Machine Learning algorithms are widely used to process Big Data in various applications and a lot of these applications are executed in run time. Therefore the speed of Machine Learning algorithms is a critical issue in these applications. However the most of modern iteration Machine Learning algorithms use a successive iteration technique well-known in Numerical Linear Algebra. But this technique has a very low convergence, needs a lot of iterations to get solution of considering problems and therefore a lot of time for processing even on modern multi-core computers and clusters. Tchebychev iteration technique is well-known in Numerical Linear Algebra as an attractive candidate to decrease the number of iterations in Machine Learning iteration algorithms and also to decrease the running time of these algorithms those is very important especially in run time applications. In this paper we consider the usage of Tchebychev iterations for acceleration of well-known K-Means and SVM (Support Vector Machine) clustering algorithms in Machine Leaning. Some examples of usage of our approach on modern multi-core computers under Apache Spark framework will be considered and discussed.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 추계학술대회
• /
• pp.1858-1863
• /
• 2003

The properties of a machine tool greatly affect machining quality since a machine tool has large variance in its features. Machine tool makers want to find best machining condition with the one that they have built. Machine builders need to develop test specimen since it helps finding characteristics of machine tools when the machining properties of the specimen are analyzed. This paper develops test specimen to identify features of the main spindle, the feeding device, and the frame of a machine tool. The specimen is machined with a high speed machine and the features of the machine are analyzed with test items. They are surface roughness, overshoot in axial movement, errors in circular movement, feeding with small movement, and compensational error. This work can improve usability for a machine tool in machining practice.

• 한국안전학회지
• /
• 제30권5호
• /
• pp.108-113
• /
• 2015

Plastic injection moulding machine is widely used for many industrial field. It is classified into mandatory safety certification machinery in Industrial Safety and Health Act because of its high hazard. In order to prevent industrial accidents by plastic injection moulding machine, it is necessary for designer to identify hazardous factors and assess the failure modes to mitigate them. This study tabulates the failure modes of main parts of plastic injection moulding machine and how their failure has affect on the machine being considered. Failure Mode & Effect Analysis(FMEA) method has been used to assess the hazard on plastic injection moulding machine. Risk and risk priority number(RPN) has been calculated in order to estimate the hazard of failures using severity, probability and detection. Accidents caused by plastic injection moulding machine is compared with the RPN which was estimated by main regions such as injection unit, clamping unit, hydraulic and system units to find out the most dangerous region. As the results, the order of RPN is injection unit, clamping unit, hydraulic unit and system units. Barrel is the most dangerous part in the plastic injection moulding machine.

• 한국수학교육학회지시리즈B:순수및응용수학
• /
• 제24권4호
• /
• pp.211-226
• /
• 2017

In this paper, machine learning models employed in various fields are discussed and applied to KOSPI200 stock index return forecasting. The results of hyperparameter analysis of the machine learning models are also reported and practical methods for each model are presented. As a result of the analysis, Support Vector Machine and Artificial Neural Network showed a better performance than k-Nearest Neighbor and Random Forest.

• 대한기계학회논문집
• /
• 제19권1호
• /
• pp.1-13
• /
• 1995

In order to investigate the effect of liquid balancer in washing machine, we identify the vibration characteristics of suspension system of washing machine and formulate the 4 D. O. F. system dynamic equations. As the washing machine rotates higher speed, it is emphasized to reduce the ecentric force due to unbalanced mass. Nowadays, the most effective cancelling method of eccentric force is known as the usage of liquid balancer. To determine the liquid distribution in liquid balancer, the fluid statics is considered. The system dynamic equations are solved by Runge-Kutta method and represent the good characteristics of real washing machine in X-Y plane. The accuracy of the numerical solution was examined by experiments. The simulation results show that the unbalanced mass has so much influence on vibration magnitude and the rotating shape of spin-basket. But the effect of mass reduction due to the dehydration of the spin-basket has little influence on transient vibration.

• Journal of Biosystems Engineering
• /
• 제40권2호
• /
• pp.137-144
• /
• 2015

Purpose: The high energy requirement of extraction of oil from jatropha seed and reduction of loss in oil content between whole seed and kernel of jatropha necessitate seed shelling. The purpose of this study is to develop and evaluate the performance of a jatropha seed shelling machine based on seed moisture content. Methods: A shelling machine was designed and constructed for jatropha seed. The components are frame, hopper, shelling chamber, concave, and blower with discharge units. The performance evaluation of the machine was carried out by determining parameters such as percentage of whole kernel recovered, percentage of broken kernel recovered, percentage of partially shelled seed, percentage of unshelled seed, machine capacity, machine efficiency, and shelling efficiency. All of the parameters were evaluated at five different moisture levels: 8.00%, 9.37%, 10.77%, 12.21%, and 13.68% w.b.). Results: The shelling efficiency of the machine increased with increase in seed moisture content; the percentage of whole kernel recovered and percentage of partially shelled seed decreased with increase in moisture content; and percentage of broken kernel, machine efficiency, and percentage of unshelled seed followed a sinusoidal trend with moisture content variation. Conclusion: The best operating condition for the shelling machine was at a moisture content of 8.00% w.b., at which the maximum percentage of whole kernel recovered was 23.23% at a shelling efficiency of 73.95%.

• 한국인공지능학회지
• /
• 제11권2호
• /
• pp.19-27
• /
• 2023

In recent times, an exponential increase in Internet traffic has been observed as a result of advancing development of the Internet of Things, mobile networks with sensors, and communication functions within various devices. Further, the COVID-19 pandemic has inevitably led to an explosion of social network traffic. Within this context, considerable attention has been drawn to research on network traffic analysis based on machine learning. In this paper, we design and develop a new machine learning framework for network traffic analysis whereby normal and abnormal traffic is distinguished from one another. To achieve this, we combine together well-known machine learning algorithms and network traffic analysis techniques. Using one of the most widely used datasets KDD CUP'99 in the Weka and Apache Spark environments, we compare and investigate results obtained from time series type analysis of various aspects including malicious codes, feature extraction, data formalization, network traffic measurement tool implementation. Experimental analysis showed that while both the logistic regression and the support vector machine algorithm were excellent for performance evaluation, among these, the logistic regression algorithm performs better. The quantitative analysis results of our proposed machine learning framework show that this approach is reliable and practical, and the performance of the proposed system and another paper is compared and analyzed. In addition, we determined that the framework developed in the Apache Spark environment exhibits a much faster processing speed in the Spark environment than in Weka as there are more datasets used to create and classify machine learning models.

• 한국컴퓨터정보학회논문지
• /
• 제27권5호
• /
• pp.11-19
• /
• 2022

본 논문에서는 전가상화 방식의 가상 머신 모니터를 기반으로 메모리 중복을 통한 고장 감내 기능을 적용한 임베디드 시스템을 제안한다. 제안된 가상 머신 모니터는 우선 효율적인 섀도우 페이지 테이블 기법을 사용하여 메모리를 가상화한다. 이를 기반으로 대상 임베디드 시스템을 하나의 가상 머신으로 동작하게 하는 한편, 동일한 시스템을 별도의 가상 머신에서 동작하도록 백업 시스템을 구축함으로써 대상 임베디드 시스템의 메모리 영역이 미리 정해진 시점과 대상에 따라 백업 시스템의 메모리 공간으로 복사되도록 하였다. 이렇게 중복이 이루어진 임베디드 시스템은 고장이 발생하면 백업 시스템으로 전환하여 정상적인 동작을 이어나가게 된다. 성능 평가를 통해 제안된 기법이 임베디드 시스템의 성능을 크게 저하시키지 않으면서도 시스템의 가용성을 크게 향상시킬 수 있음을 확인하였다.