• Asia pacific journal of information systems
• /
• 제20권2호
• /
• pp.23-37
• /
• 2010

Conventional Support Vector Machines (SVMs) have been utilized as classifiers for binary classification problems. However, certain real world problems, including corporate bond rating, cannot be addressed by binary classifiers because these are multi-class problems. For this reason, numerous studies have attempted to transform the original SVM into a multiclass classifier. These studies, however, have only considered nominal classification problems. Thus, these approaches have been limited by the existence of multiclass classification problems where classes are not nominal but ordinal in real world, such as corporate bond rating and multiclass customer classification. In this study, we adopt a novel multiclass SVM which can address ordinal classification problems using ordinal pairwise partitioning (OPP). The proposed model in our study may use fewer classifiers, but it classifies more accurately because it considers the characteristics of the order of the classes. Although it can be applied to all kinds of ordinal multiclass classification problems, most prior studies have applied it to finance area like bond rating. Thus, this study applies it to a real world customer level classification case for implementing customer relationship management. The result shows that the ordinal multiclass SVM model may also be effective for customer level classification.

• International journal of advanced smart convergence
• /
• 제11권3호
• /
• pp.56-63
• /
• 2022

Cyber-physical systems (CPSs) can solve real problems by utilizing closely connected resources in the cyber world. Most problems arise because the physical world is uncertain and unpredictable. To address this uncertainty, information pouring from numerous devices must be collected in real-time, and each interconnected device must share the information. At this time, CPS must meet timing-related techniques and strict timing constraints that can deliver accurate information within predefined deadlines in order to interact closely beyond simply connecting the cyber and physical worlds. Timing errors in safety-critical systems, such as automobiles, aviation, and medical systems, can lead to catastrophic disasters. In this paper, we classify timing problems into two types: real-time delay and synchronization problems. The results of this study can be used in the entire process of CPS system design, implementation, operation, verification, and maintenance. As a result, it can contribute to securing the safety and reliability of CPS.

• 한국학교수학회논문집
• /
• 제6권2호
• /
• pp.117-126
• /
• 2003

본 논문에서는 실생활문제에서 Skemp의 수학학습이론을 토대로 학생들이 나타내는 분수 개념에 대한 유형을 연구하였다. 4-6학년을 대상으로 학생들의 분수 개념에 대한 개념적 이해도를 조사하기 위해 3개의 문항에 대한 학생들의 반응을 분석하였고, 이를 바탕으로 바람직한 몇 가지 교수-학습 방법을 함께 제안하였다.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제11권4호
• /
• pp.247-263
• /
• 2007

Problem solving takes place not only in mathematics classes but also in real-world. For this reason, a problem and the structure of problem solving, and the enhancing of success in problem solving is a subject which has been studied by any educators. In this direction, the aim of this study is that the strategy used by students in Turkey when solving oral problems and their achievements of choosing operations when solving oral problems has been researched. In the research, the students have been asked three types of questions made up groups of 5. In the first category, S-problems (standard problems not requiring to determine any strategy but can be easily solved with only the applications of arithmetical operations), in the second category, AS-SA problems (problems that can be solved with the key word of additive operation despite to its being a subtractive operation, and containing the key word of subtractive operation despite to its being an additive operation), and in the third category P-problems (problematic problem) take place. It is seen that students did not have so much difficulty in S-problems, mistakes were made in determining operations for problem solving because of memorizing certain essential concepts, and the succession rate of students is very low in P-problems. The reasons of these mistakes as a summary are given below: $\cdot$ Because of memorizing some certain key concepts about operations mistakes have been done in choosing operations. $\cdot$ Not giving place to problems which has no solution and with incomplete information in mathematics. $\cdot$ Thinking of students that every problem has a solution since they don't encounter every type of problems in mathematics classes and course books.

• 전자통신동향분석
• /
• 제36권2호
• /
• pp.22-31
• /
• 2021

This report introduces a definition for robot task intelligence and explains the basis of the challenges associated with implementing robot task intelligence in real-world problems. Two fundamental elements of this intelligence, robot manipulation and navigation, are introduced herein. We describe the existing trends and industrial applications of the robot task intelligence in logistics and agricultural automation. Furthermore, as an underpinning technology for this intelligence, we review the existing three-dimensional position estimation techniques and summarize the difficulties associated with applying pure SLAM technology to real-world applications. Finally, we discuss the prospects of the robot task intelligence research and its potential for solving real-world problems.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.1248-1251
• /
• 2002

Logistics optimization problems related with vehicle routing such as warehouse locating, track scheduling, customer order delivery, wastage pickup etc. are very interesting and important issues to date. Many Vehicle Routing and Scheduling Systems (VRSS) have been developed/proposed to optimize the logistics problems. But majority of them are dedicated to a particular problem and are unable to handle the real world spatial data directly. The system developed for one problem may not be suitable for others due to inter-problem constraint variations. The constraints may include geographical, environmental and road traffic nature of the working region along with other constraints related with the problem. So the developer always needs to modify the original routing algorithm in order to fulfill the purpose. In our study, we propose a general-purpose platform by combining GIS road map and Database Management System (DBMS), so that VRSS can interact with real world spatial data directly to solve different kinds of vehicle routing problems. Using the features of our developed system, the developer can frequently modify the existing algorithm or create a new one to serve the purpose.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.195-204
• /
• 2003

Network optimization is being increasingly important and fundamental issue in the fields such as engineering, computer science, operations research, transportation, telecommunication, decision support systems, manufacturing, and airline scheduling. Networks provide a useful way to modeling real world problems and are extensively used in practice. Many real world applications impose on more complex issues, such as, complex structure, complex constraints, and multiple objects to be handled simultaneously and make the problem intractable to the traditional approaches. Recent advances in evolutionary computation have made it possible to solve such practical network optimization problems. The invited talk introduces a thorough treatment of evolutionary approaches, i.e., hybrid genetic algorithms approach to network optimization problems, such as, fixed charge transportation problem, minimum cost and maximum flow problem, minimum spanning tree problem, multiple project scheduling problems, scheduling problem in FMS.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.268-281
• /
• 2022

The development of information technology is bringing many changes to everyday life, and machine learning can be used as a technique to solve a wide range of real-world problems. Analysis and utilization of data are essential processes in applying machine learning to real-world problems. As a method of processing data in machine learning, we propose an approach based on applying multiple linear regression models by interlacing data to the task of classifying similar software. Linear regression is widely used in estimation problems to model the relationship between input and output data. In our approach, multiple linear regression models are generated by training on interlaced feature data. A combination of these multiple models is then used as the prediction model for classifying similar software. Experiments are performed to evaluate the proposed approach as compared to conventional linear regression, and the experimental results show that the proposed method classifies similar software more accurately than the conventional model. We anticipate the proposed approach to be applied to various kinds of classification problems to improve the accuracy of conventional linear regression.

• 대한산업공학회지
• /
• 제22권2호
• /
• pp.209-229
• /
• 1996

Scheduling problems which determine the sequence of jobs are one of the Important issues to many industries. This paper deals with a single-machine job sequencing problem which has complex constraints and an objective function. To solve the problem, an expressive constraint description language and an automatic code generator are developed for our scheduling system. The user just needs to describe the scheduling problem using the constraint description language that allows to express both quantitative and qualitative constraints as well as an objective function in real world semantics. Then, a complete scheduling program based on constraint satisfaction technique is automatically generated through the code generator. Advantage of this approach is that models of the scheduling problems are easily developed and maintained because models ore formulated by using the language which reflects real world semantics.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권3호
• /
• pp.263-267
• /
• 2005

Building classifiers for financial real-world classification problems is often plagued by severely overlapping and highly skewed class distribution. New performance measures such as receiver operating characteristic (ROC) curve and area under ROC curve (AUC) have been recently introduced in evaluating and building classifiers for those kind of problems. They are, however, in-effective to evaluation of classifier's discrimination performance in a particular class of the classification problems that interests lie in only a local operating range of the classifier, In this paper, a new method is proposed that enables us to directly improve classifier's discrimination performance at a desired local operating range by defining and optimizing a partial area under ROC curve or domain-specific curve, which is difficult to achieve with conventional classification accuracy based learning methods. The effectiveness of the proposed approach is demonstrated in terms of fraud detection capability in a real-world fraud detection problem compared with the MSE-based approach.