Recently, thanks to emerging ICT (Information and Communication Technology) such as IoT (Internet of Things), wireless telecommunication, and various sensor technologies, the concept of connected car has been highlighted in the automotive industry. In the connected car technology, one application is to diagnose and predict the car status in a real-time way based on gathered data. To this end, it is necessary to develop the diagnostics/prognostics algorithms for a specific part or component in a car. The results of diagnostics and prognostics could provide drivers with useful information used for advanced maintenance policy such as condition-based maintenance. In this study, we have reviewed the relevant previous research works before developing detailed algorithms.

식음료분야 전문의 글로벌 시장조사 기업인 Innova Market Insights (이노바 마켓 인사이트, 네덜란드 푸드밸리)는 글로벌 식품산업에서의 로봇 산업에 대한 인사이트를 소개한다. 4차 산업혁명의 키워드 중의 하나인 “인공지능과 지능형 로봇”은 전세계적으로 모든 산업에 영향을 미치고 있다. 식품산업도 예외는 아니며, 가정에서의 서비스 로봇의 개발도 이미 상업화 단계에 이르고 있다. 글로벌 식품산업과 소비자의 변화를 이끌고 있는 4차 산업혁명을 준비해야 하는 시점에서, 대표적인 사례들을 통해 인공지능과 식품 서비스 로봇의 개발 현황을 살펴본다. 1. Attraction for food & drink manufacturers in robotics 2. Ready to do cognitive cooking? Chef Watson 3. Robo Chef ? Moley Robotics robo chef 4. Bionic Bartender ? MakrShakr 5. AI advise Master brewer ? Intelligent X 6. Machine Learning Understand Consumer Preferences ? Graze 7. Opportunities in Service Robot Innova Market Insights (이노바 마켓 인사이트): 네덜란드의 FoodValley에 본사를 둔 Innova Market Insights b.v.(이노바 마켓 인사이트)는 글로벌 식품산업에 Innovadatabase(이노바 데이터베이스)를 제공하고 있다. 전세계에서 유일하고, 가장 앞선 식음료 관련분야의 전문적인 데이터베이스 플랫폼으로서, “새로운 기술”과 “신제품 정보”, “마케팅관점의 트렌드 보고서”, “혁신적인 패키지” 등을 하나의 플랫폼으로 제공하고 있다. 해외의 혁신적인 브랜드와 패키지, 새로운 제품들을 가장 먼저 만날 수 있다. 이미 국내외 많은 기업들이 Innovadatabase를 이용하고 있으며, 새로운 아이디어와 트렌드로 시장을 개척하고 있다.

This research focuses on a scheduling problem in the semiconductor probing facility. Probing facility is composed of identical parallel machines and the parallel machines form three workstations for the tests with different recipes. Each machine can be set to three different tests and sequence-dependent setup times are required between operations due to temperature and probe card loading/unloading. Precedence relationship exists between three tests of each wafer lot. The scheduling problem for the probing facility is a parallel machine scheduling problem with precedence relationship and sequence dependent setup time. We develop heuristic algorithm to minimize makespan for the scheduling problem and numerical experiments are conducted to evaluate the performance.

현대 사회에 들어서 점차 많은 기업들은 데이터의 대량 수집, 인터넷을 바탕으로 한 연결, 자동화된 알고리즘을 이용한 판매를 그들의 기존 공급망 및 판매기능과 결합시키고 있다. 즉 공급과 수요를 모니터링하는 가격 결정 알고리즘이 탑재된 소프트웨어 도구를 이용함으로써, 이러한 소프트 웨어 도구에 경쟁사에 대한 대응 및 가격 책정 업무를 넘기고 있는 것이다. 그런데 미국의 독점금지법인 셔먼법(Sherman Act)은 기업들 간의 가격 책정에 관한 ‘합의’가 있을 것을 요구하는바, 자동화된 알고리즘에 따른 가격 책정 및 공급량 책정이 이루어지는 경우 기업들은 상호 간의 의사소통 없이도 경쟁을 하였을 때 형성될 시장가격보다 높은 가격을 책정할 수 있게 되므로, 이러한 경우 현행 셔먼법에 의하면 처벌을 할 수 없다는 문제가 있다. 우리나라의 독점규제 및 공정거래에 관한 법률도 제19조의 ‘부당한 공동행위’의 요건으로서 ‘사업자 간 의사연결의 상호성’이 있을 것을 요구하므로, 마찬가지로 위와 같은 문제가 발생할 수 있다. 현대 사회에서 알고리즘의 필요성과 그 가치를 부정할 수 없는 만큼, 알고리즘을 이용한 판매를 독과점금지에 관한 법률과 조화시킬 수 있는 적절한 방안을 찾는 것이 현재 독과점금지제도의 가장 큰 과제라 할 것이다.

In order to implement the smart home environment, we need an intelligence service platform that learns the user’s life style and behavioral patterns, and recommends appropriate services to the user. The intelligence service platform should embed a couple of effective and efficient data mining algorithms for learning from the data that is gathered from the smart home environment. In this study, we evaluate the suitability of data mining algorithms for smart home intelligent service platforms. In order to do this, we first develop an intelligent service scenario for smart home environment, which is utilized to derive functional and technical requirements for data mining algorithms that is equipped in the smart home intelligent service platform. We then evaluate the suitability of several data mining algorithms by employing the analytic hierarchy process technique. Applying the analytical hierarchy process technique, we first score the importance of functional and technical requirements through a hierarchical structure of pairwise comparisons made by experts, and then assess the suitability of data mining algorithms for each functional and technical requirements. There are several studies for smart home service and platforms, but most of the study have focused on a certain smart home service or a certain service platform implementation. In this study, we focus on the general requirements and suitability of data mining algorithms themselves that are equipped in smart home intelligent service platform. As a result, we provide a general guideline to choose appropriate data mining techniques when building a smart home intelligent service platform.

PURPOSES:This study suggests a specific methodology for the prediction of road surface temperature using vehicular ambient temperature sensors. In addition, four kind of models is developed based on machine learning algorithms.METHODS:Thermal Mapping System is employed to collect road surface and vehicular ambient temperature data on the defined survey route in 2015 and 2016 year, respectively. For modelling, all types of collected temperature data should be classified into response and predictor before applying a machine learning tool such as MATLAB. In this study, collected road surface temperature are considered as response while vehicular ambient temperatures defied as predictor. Through data learning using machine learning tool, models were developed and finally compared predicted and actual temperature based on average absolute error.RESULTS:According to comparison results, model enables to estimate actual road surface temperature variation pattern along the roads very well. Model III is slightly better than the rest of models in terms of estimation performance.CONCLUSIONS :When correlation between response and predictor is high, when plenty of historical data exists, and when a lot of predictors are available, estimation performance of would be much better.

Distributed genetic algorithm (DGA), also known as island model or coarse-grained model, is a kind of parallel genetic algorithm, in which a population is partitioned into several sub-populations and each of them evolves with its own genetic operators to maintain diversity of individuals. It is known that DGA is superior to conventional genetic algorithm with a single population in terms of solution quality and computation time. Several researches have been conducted to evaluate effects of parameters on GAs, but there is no research work yet that deals with structure of DGA. In this study, we tried to evaluate performance of various genetic algorithms (GAs) for the famous symmetric traveling salesman problems. The considered GAs include a conventional serial GA (SGA) with IGX (Improved Greedy Crossover) and several DGAs with various combinations of crossover operators such as OX (Order Crossover), DPX (Distance Preserving Crossover), GX (Greedy Crossover), and IGX. Two distinct immigration policies, conventional noncompetitive policy and newly proposed competitive policy are also considered. To compare performance of GAs clearly, a series of analysis of variance (ANOVA) is conducted for several scenarios. The experimental results and ANOVAs show that DGAs outperform SGA in terms of computation time, while the solution quality is statistically the same. The most effective crossover operators are revealed as IGX and DPX, especially IGX is outstanding to improve solution quality regardless of type of GAs. In the perspective of immigration policy, the proposed competitive policy is slightly superior to the conventional policy when the problem size is large.

Efficient and sustainable sea transport is a key aspect to ensure cost competitive ship operation. The constant need to increase economic feasibility, energy efficiency and safety while complying with emission regulations motivates further developments and improvements in voyage optimization and weather routing systems. These systems optimize a voyage based on meteorological and oceanographic information taking into account ship characteristics and routing information. The quality of the provided route not only depends on the quality of this data, but also on the modeling of the optimization problem and the algorithm chosen to solve it. Due to the wide range of mathematical approaches and consequently challenges in decision making, this paper aims to give a comprehensive and comparative overview of the existing state-of-the-art methods by a thorough literature review and elaboration of different modeling approaches, optimization algorithms, and their application in weather routing systems. The research shows that approaches range from modeling the weather routing problem as a constrained graph problem, a constrained nonlinear optimization problem or as combination of both. Based on the formulation of the ship weather routing optimization problem different methods are used to solve it ranging from Dijkstra’s algorithm, dynamic programing and optimal control methods to isochrone methods or iterative approaches for solving nonlinear optimization problems. However, it can be concluded that the determination whether an approach is suitable, produces sufficient results and may be recommended, strongly depends on the specific requirements concerning optimization objectives, control variables and constraints as well as the implementation.

Megacities in Asia such as Seoul, Tokyo, Singapore is modern and historical at the same time. Although technologically developed and highly urbanized, these megacities’ urban fabric and life-style heavily rely on human scale – the software of the urban – as its main shaping force. This interesting mixture and contrast is what gives this city its unique characteristics. It is very motivating to find out how the software – human, community & social aspects of everyday life, rather than hardware of the city – built environment itself, drive the evolution of Seoul to such high degree. Through continuous research and workshops, the software part of the city is investigated and the lowest level elements in urban fabrication - human are looked at in two distinguish methods; computational and analogue. Differences and similarities between them are questioned, by investigating the contrast between digital and physical, virtual and actual in the thinking process. The study looks at the formation of urbanism and architecture on the level of local communities, mapping the social data, and trying to approach this idea in multiple level and perspectives.

As Internet has been wildly spreaded and it's technique is advanced, the use of computers has been routinized and almost data are stored in computers. Accordingly, many companies and researchers have tried to find the relations in these tremendous data and the one way is to use clustering algorithm which is used to find out similar data set in the entire data set and to discover the common properties. In early period, clustering algorithm was performed based on a main memory of a computer and PAM(Partitioning Around Medoids) was representative, which can be complemented k-means algorithm defeat. PAM performs clustering by using the medoid of data instead of means. PAM works well in small data set but it is difficult to apply it to large data set. Therefore, CLARA(Clutering LARge Application) shows up to be used in large data set. This algorithm samples data from large data set and applies PAM to the sample data. CLARA has limits caused by the fixed samples in each clustering stage and has a problem that if the good mediod is not sampled then the result of the clustering becomes not good. CLARANS(Clustering Large Application based upon Randomized Search) overcomes these problems by drawing a sample with some randomness. This algorithm executes clustering using k mediod set extracted in the processing of clustering in each stage. The main objective is to compare and analyze the algorithms which are popularly used for the clustering of big data.

This paper focuses on scheduling problems arising in the military. In planned artillery attack operations, a large number of threatening enemy targets should be destroyed to minimize fatal loss to the friendly forces. We consider a situation in which the

This study focuses on the problem of scheduling wafer lots of several recipe(operation condition) types in the photolithography workstation in a semiconductor wafer fabrication facility, and sequence-dependent recipe set up times may be required at the ph

This paper considers an economic design problem of a tree-based network which is a kind of computer network. This problem can be modeling to be an objective function to minimize installation costs, on the constraints of spanning tree and maximum traffic c

One of the most important objectives of post-marketing monitoring of dietary supplements is the early detection of unknown and unexpected adverse events (AEs). Several causality algorithms, such as the Naranjo scale, the RUCAM scale, and the M&V scale are available for the estimation of the likelihood of causation between a product and an AE. Based on the existing algorithms, the Korea Food & Drug Administration has developed a new algorithm tool to reflect the characteristics of dietary supplements in the causality analysis. However, additional work will be required to confirm if the newly developed algorithm tool has reasonable sensitivity and not to generate an unacceptable number of false positives signals.

In this study, a forecasting engine from the user perspective is studied and developed. Characteristics of forecasting engine can be divided into a few categories, an algorithms for predicting variety of situations and the depth of algorithms based on the

This dissertation focuses on scheduling problems arising in the military. In planned artillery attack operations, a large number of threatening enemy targets should be destroyed to minimize fatal loss to the friendly forces. We consider a situation in which the number of available weapons is smaller than the number of targets. Therefore it is required to develop a new sequencing algorithm for the unplanned artillery attack operation. The objective is to minimize the total loss of the targets, which is expressed as a function of the fire power potential, after artillery attack operations are finished. We develop a algorithm considering the fire power potential and the time required to destroy the targets. The algorithms suggested in this dissertation can be used in real artillery attack operations if they are modified slightly to cope with the practical situations.

Overhead facility design problem(OFDP) is one of the shortest rectilinear flow network problem(SRFNP)[4]. Genetic algorithm(GA), artificial immune system(AIS), population management genetic algorithm (PM) and greedy randomized adaptive search procedures (GRASP) were introduced to solve OFDP. A path matrix formed individual was designed to represent rectilinear path between each facility. An exchange crossover operator and an exchange mutation operator were introduced for OFDP. Computer programs for each algorithm were constructed to evaluate the performance of algorithms. Computation experiments were performed on the quality of solution and calculations time by using randomly generated test problems. The average object value of PM was the best of among four algorithms. The quality of solutions of AIS for the big sized problem were better than those of GA and GRASP. The solution quality of GRASP was the worst among four algorithms. Experimental results showed that the calculations time of GRASP was faster than any other algorithm. GA and PM had shown similar performance on calculation time and the calculation time of AIS was the worst.

This paper considers a 2-stage assembly flowshop scheduling problem where each job is completed by assembling multiple components. The problem has the objective measure of minimizing total completion time. The problem is shown to be NP-complete in the str