Earticle

자율주행 시스템의 수용성 보장은 중요하다. 시스템 수용성 요소 중 하나인 자율주행 종방 향 제어기는 상위 제어기와 하위 제어기로 구성된다. 상위 제어기는 Cruise 제어와 Space 제어 를 상황에 맞는 제어를 결정하고 필요한 목표 속도를 만든다. 하위 제어기에서는 목표 속도를 추종하기 위한 가속도 신호를 만들어서 제어를 수행한다. 본 논문에서는 상위 제어기에서 Cruise 제어와 Space 제어전환 문제에서 발생하는 차간거리 변동을 개선하는 알고리즘을 제안 한다. 제안한 방법은 Cruise 제어에서 Space 제어로 전환되는 시점에 Cruise 제어에 Approach 알고리즘을 추가하여 전환 거리에서 Space 제어로 전환되도록 하는 것이다. 이를 통해서 ± 12m 초기 오차에서 ±4m까지 오차를 개선했으며 실차검증을 수행하였다.

Driver acceptance of autonomous driving is very important. The autonomous driving longitudinal controller, which is one of the factors affecting acceptability, consists of a high-level controller and a low-level controller. The host controller decides the cruise control and the space control according to the situation and creates the required target speed. The sub-controller performs control by creating an acceleration signal to follow the target speed. In this paper, we propose an algorithm to improve the inter-vehicle distance fluctuations that occur in the cruise control and space control switching problems in the host controller. The proposed method is to add an approach algorithm to the cruise control at the time of switching from cruise control to space control so that it is switched to space control at the correct switching distance. Through this, the error was improved from 12m error to 4m, and actual vehicle verification was performed.

In the recent years, non-preemptive job shop scheduling problems have been applied to a wide variety of academic and industrial fields. In comparison, preemptive job shop scheduling problems have received almost no attention in the both fields. Motivated by the needs of a specific application, we presented an algorithm for dealing with preemptive job shop scheduling problem. First, we considered constraint programming techniques to preemptive scheduling problems. Second, we applied genetic algorithm to these problems. In proposed genetic algorithm, we developed a new concept for representing of genetic algorithm. In case study, we applied the proposed algorithm to several job shop problems. Experiment results show that the proposed algorithm considered by preemptive problems outperforms non-preemptive case and other conventional algorithms.

The fact that signature is widely used means of person authentication emphasizes the need for automatic verification system. This paper presents a new approach for signature verification. The proposed system aims to collect representative and unique features to distinguish between digital signature images. The comparison process between testing signature and the stored signatures is optimized using Genetic Algorithm. Our experimental results give a good balance between False Acceptance Rate (FAR) and False Rejection Rate (FRR).

Note that k-anonymity algorithm has been widely discussed in the area of privacy protection. In this paper, a new search algorithm to achieve k-anonymity for database application is introduced. A lattice is introduced to form a solution space for a k-anonymity problem and then a hybrid search method composed of tabu search and genetic algorithm is proposed. In this algorithm, the tabu search plays the role of mutation in the genetic algorithm. The hybrid method with independent tabu search and genetic algorithm is compared, and the hybrid approach performs the best in average case.

비지도 방식의 클러스터링은 주로 각 데이터에 대한 유사도나 거리에 기반하여 수행되며, 기본적으로 NP (Non-deterministic polynomial) Hard의 영역으로 알려져 있다. 각 노드에 대한 계산은 매트릭스에 기반하여 수행되는데, 노드의 수가 많은 경우 다른 노드와 비교하는 계산 시간이 매우 많이 소요될 수 밖에 없으며, 이를 단시간 내에 계산하기 위해서는 동적프로그래밍과 같은 컴퓨터 알고리즘이 수반되어야 한다. 이러한 계산 복잡도와 구현의 어려움으로 인해 빅데이터의 클러스터링은 유클리드나 코사인 유사도 등 몇 가지 전통적인 컴퓨터 거리 계산 방식에 국한되어 적용되고 그 계산 방식을 제공하는 주요한 클러스터링 라이브러리에 종속적으로 의존되어 왔다. 따라서 이러한 보편적인 클러스터링으로 계산이 불가능한 특수한 데이터의 경우에는 적용이 아예 불가능하거나 어려운 점이 존재할 수 있다. 예를 들어 개인별 직무 경력과 같은 데이터는, 특정인의 경력 정보가 다른 인력의 경력 정보와 비교를 할 수 있는데, 이를 어떻게 비교를 하여 그 거리를 특정화하고, 여러가지 “career pathway”를 분류해내고 검토하기 위한 특수한 클러스터링 알고리즘이 요구된다. 본 연구에서는 IT 분야의 경력정보 데이터를 활용하여 생명공학 분야에서 DNA 시퀀스에 대한 분류를 위해 활용되는 Optimal Matching 알고리즘을 활용하여 경력 정보의 계산한 후 이를 활용하여 클러스터링하는 시스템을 소개한다.

The importance of recommendation algorithms is underscored by the advancement of AI technology and the growing demand for personalized services. However, there is a lack of empirical studies that analyze differences in algorithmic services across markets. The objective of this study is to draw attention to discrepancy in this field and develop a dual-path model to examine the factors that influence satisfaction with recommendations. By analyzing 641 respondents’ data through Partial Least Squares (PLS), it identifies differences in user attitudes towards algorithms across domains. e-commerce firms and content providers can improve personalized recommendations through the research, which highlights the importance of understanding consumer satisfaction and trust in technology to adapt to evolving AI innovations.

Korea professional baseball industry has grown to take the lion"s share of the domestic sports industry, but still does not make break even. The purpose of this study is to examine the financial impact of adopting the Customer Relation Management (CRM) approach on the profitability of Korea professional baseball industry. We use a measuring tool called entropy used in ID3 decision tree algorithm. In the paper, we specify five the most important factors that affect spectator satisfaction based on the previous literature, perform survey analysis, calculate entropy values, and find the results. We predicted the change in revenues when we adopt CRM by checking the spectators" willingness to pay more when the conditions of each factor are improved. We find that we can reap significant fruits of the effect of CRM introduction through enhancing "game content factor" and "game promotion factor" among the five factors. We also find that we can increase the revenues of domestic professional baseball teams to 2.4 times or 2.1 times the current level if we manage intensively those two factors. respectively. It is very surprising to see that the improvement in total revenues makes both ends meet for domestic professional baseball teams. This clearly demonstrates the effectiveness of CRM approach in improving the profitability of organizations.

전력은 모든 나라에서 사회 발전과 경제 성장에 가장 기본적인 자원이다. 산업이 고도화 되고 경제의 규모가 발전하면서 전력의 소비량은 점점 증가하고 있다. 전력을 공급하는 쪽에서는 전력을 생산할 때 자원의 낭비 를 줄이기 위해 전력 사용량을 예측하는 것은 중요한 일이다. 또한 전력 수요 예측을 통해 여름과 겨울의 피크 타임 에서의 전력 수요를 분산하는 것이 가능하다. 그리고 소비 전력의 예측은 국내에서 수요자원 거래시장(Negawatt market)이 본격화되면서 더욱 중요하게 되었다. 더구나 전력 소비량 예측은 소비자가 전력 시장에 직간접적으로 참여하는 수요관리 방법을 제공해준다. 본 연구에서는 1999년부터 2011년까지의 국내총생산, 1인당 국민총소득, 부 가세, 국내전력소비량을 이용하여 제주도의 어업 전력 사용량을 예측하는데 유전자 알고리즘을 사용하고 있다. 유전 자 알고리즘은 다양한 조합 최적화 분야에서 최적해를 찾는데 유용하게 사용되는 알고리즘이다. 본 논문에서 유전 자 알고리즘에서 최적의 동작을 위한 파라미터들을 찾는다. 그리고 실제 전력 소비량 예측을 위해 사용되는 계수 (coefficient)들의 최적값을 찾아 예측값과 실제 전력 소비량의 오차를 최소화하는데 목적이 있다.

Energy is a vital resource for the economic growth and the social development for any country. As the industry becomes more sophisticated and the economy more grows, the electricity demand is increasing. So forecasting electricity demand is an important for electricity suppliers. Forecasting electricity demand makes it possible to distribute electricity demand. As the market for Negawatt market began to grow in Korea from 2014, the prediction of electricity consumption demand becomes more important. Moreover, power consumption forecasting provides a way for demand management to be directly or indirectly participated by consumers in the electricity market. We use Genetic Algorithms to predict the energy demand of the fishing industry in Jeju Island by using GDP, per capita gross national income, value add, and domestic electricity consumption from 1999 to 2011. Genetic Algorithm is useful for finding optimal solutions in various fields. In this paper, genetic algorithm finds optimal parameters. The objective is to find the optimal value of the coefficients used to predict the electricity demand and to minimize the error rate between the predicted value and the actual power consumption values.

정보보호는 기업의 운영과 고객의 신뢰를 보장하는 필수요소이며 침해사고 예방을 통해 불확실한 피해를 완화시킬 수 있기 때문에 적절한 정보보호 대책의 선택과 적정투자 수준을 결정하는 것이 중요하다. 본 연구는 다양한 산업군에 속해있는 기업에서 정보보호 대책 투자에 활용할 수 있는 예산 범위에서 구성할 수 있는 최적의 정보보호 대책 포트폴리오 구성뿐만 아니라, 각 대책의 적절한 투자 수준에 대한 의사결정 지원 모델을 제시한다. 이를 위하여 산업군별 침해사고 유형 통계를 분석하고 유전자 알고리즘을 활용하여 최적 정보보호 대책 투자 포트폴리오를 도출한다. 도출된 모델을 기존 유전자 알고리즘을 이용한 정보보호 대책 투자 최적화 모델과 비교하고 기업 대상 설문 조사를 통하여 실제 사례를 분석한다.

Information security is an essential element not only to ensure the operation of the company and trust with customers but also to mitigate uncertain damage by preventing information data breach. Therefore, It is important to select appropriate information security countermeasures and determine the appropriate level of investment. This study presents a decision support model for the appropriate investment amount for each countermeasure as well as an optimal portfolio of information countermeasures within a limited budget. We analyze statistics on the types of information security breach by industry and derive an optimal portfolio of information security countermeasures by using genetic algorithms. The results of this study suggest guidelines for investing in information security countermeasures in various industries and help to support objective information security investment decisions.

This paper considers the sequencing of products in mixed model assembly lines under Just-In-Time (JIT) systems. Under JIT systems, the most important goal for the sequencing problem is to keep a constant rate of usage every part used by the systems. The sequencing problem is solved using Genetic Algorithm Genetic Algorithm is a heuristic method which can provide a near optimal solution in real time. The performance of proposed technique is compared with existing heuristic methods in terms of solution quality. Various examples are presented and experimental results are reported to demonstrate the efficiency of the technique.

IoT 디바이스로부터 수집된 위치정보를 활용한 실시간 위치센싱 기술은 항만 등 다양한 산 업현장에서 활용되고 있다. 그러나 GPS 센서의 특성상 오차는 항상 존재하며, 이를 활용하는 사고위험 검지 알고리즘은 오차의 고려가 필수적이다. 본 연구는 GPS 오차를 고려한 항만 내 낙하물 사고위험 구역 접근검지 알고리즘의 보정 방법론을 제안한다. IoT 디바이스로부터 수 집된 GPS 오차 데이터를 확률변수로 하는 확률밀도함수를 추정하였으며 알고리즘의 검증을 위해 미시적 시뮬레이션을 활용하였다. 검증 결과 알고리즘은 디바이스의 위치오차 1m, 5m에 따라 검지 정확도가 각각 93%, 77%로 나타났다. 본 연구는 향후 디바이스의 성능을 고려한 유효 위험범위 설정 및 안전관리에 중요한 역할을 할 수 있을 것으로 기대된다.

Real-time location-sensing technology using location information collected from IoT devices is being applied for safety management purposes in many industries, such as ports. On the other hand, positional error is always present owing to the characteristics of GPS. Therefore, accident-risk detection algorithms must consider positional error. This paper proposes an methodology of calibration for falling object accident-risk-zone approach detection algorithm considering GPS errors. A probability density function was estimated, with positional error data collected from IoT devices as a probability variable. As a result of the verification, the algorithm showed a detection accuracy of 93% and 77%. Overall, the analysis results derived according to the GPS error level will be an important criterion for upgrading algorithms and real-time risk managements in the future.

그동안 차두시간분포를 나타내는 확률분포로 음지수분포, Erlang 분포, 정규분포 등 다양한 단일확률분포들이 사용되어져 왔다. 그러나, 실제 도로에서 차두시간분포의 조사결과는 단일 확률분포로서 설명하기 어려운 경우가 있었다. 본 연구는 차량의 차두시간에 대해 두 개의 정 규분포가 일정한 관련성을 가지고 결합된 복합확률분포의 파라메타에 대해 최우추정법 중 하 나인 EM 알고리즘을 이용하여 추정하는 접근방법을 시도하였다. 이에 대한 분석결과 기존에 알려진 단일확률분포로서 잘 설명되기 어려웠던 차량도착 차두시간 분포를 EM 알고리즘을 이 용하여 복합확률분포의 파라메타를 추정하여 설명하였다. χ2 test 적합도 검정결과, 유의수준 1%에서 통계학적으로 유의성이 확보되어 EM 알고리즘을 이용한 복합확률분포의 파라메타 추 정의 신뢰성이 입증되는 것으로 분석되었다

Various single probability distributions have been used to represent time headway distributions. However, it has often been difficult to explain the time headway distribution as a single probability distribution on site. This study used the EM algorithm, which is one of the maximum likelihood estimations, for the parameters of combined mixture distributions with a certain relationship between two normal distributions for the time headway of vehicles. The time headway distribution of vehicle arrival is difficult to represent well with previously known single probability distributions. But as a result of this analysis, it can be represented by estimating the parameters of the mixture probability distribution using the EM algorithm. The result of a goodness-of-fit test was statistically significant at a significance level of 1%, which proves the reliability of parameter estimation of the mixture probability distribution using the EM algorithm.

We frequently use search engines to find relevant information in the Web but still end up with too much information. In order to solve this problem of information overload, ranking algorithms have been applied to various domains. As more information will be available in the future, effectively and efficiently ranking search results will become more critical. In this paper, we propose a ranking algorithm for the Semantic Web resources, specifically RDF resources.Traditionally, the importance of a particular Web page is estimated based on the number of key words found in the page, which is subject to manipulation. In contrast, link analysis methods such as Google’s PageRank capitalize on the information which is inherent in the link structure of the Web graph. PageRank considers a certain page highly important if it is referred to by many other pages. The degree of the importance also increases if the importance of the referring pages is high.Kleinberg’s algorithm is another link-structure based ranking algorithm for Web pages. Unlike PageRank, Kleinberg’s algorithm utilizes two kinds of scores: the authority score and the hub score. If a page has a high authority score, it is an authority on a given topic and many pages refer to it. A page with a high hub score links to many authoritative pages.As mentioned above, the link-structure based ranking method has been playing an essential role in World Wide Web (WWW), and nowadays, many people recognize the effectiveness and efficiency of it. On the other hand, as Resource Description Framework (RDF) data model forms the foundation of the Semantic Web, any information in the Semantic Web can be expressed with RDF graph, making the ranking algorithm for RDF knowledge bases greatly important. The RDF graph consists of nodes and directional links similar to the Web graph. As a result, the link-structure based ranking method seems to be highly applicable to ranking the Semantic Web resources. However, the information space of the Semantic Web is more complex than that of WWW. For instance, WWW can be considered as one huge class, i.e., a collection of Web pages, which has only a recursive property, i.e., a ‘refers to’ property corresponding to the hyperlinks. However, the Semantic Web encompasses various kinds of classes and properties, and consequently, ranking methods used in WWW should be modified to reflect the complexity of the information space in the Semantic Web.Previous research addressed the ranking problem of query results retrieved from RDF knowledge bases. Mukherjea and Bamba modified Kleinberg’s algorithm in order to apply their algorithm to rank the Semantic Web resources. They defined the objectivity score and the subjectivity score of a resource, which correspond to the authority score and the hub score of Kleinberg’s, respectively. They concentrated on the diversity of properties and introduced property weights to control the influence of a resource on another resource depending on the characteristic of the property linking the two resources. A node with a high objectivity score becomes the object of many RDF triples, and a node with a high subjectivity score becomes the subject of many RDF triples. They developed several kinds of Semantic Web systems in order to validate their technique and showed some experimental results verifying the applicability of their method to the Semantic Web. Despite their efforts, however, there remained some limitations which they reported in their paper. First, their algorithm is useful only when a Semantic Web system represents most of the knowledge pertaining to a certain domain. In other words, the ratio of links to nodes should be high, or overall resources should be described in detail, to a certain degree for their algorithm to properly work. Second, a Tightly-Knit Community (TKC) effect, the phenomenon that pages which are less important but yet densely connected have higher scores than the ones that are more important but sparsely connected, remains as problematic. Third, a resource may have a high score, not because it is actually important, but simply because it is very common and as a consequence it has many links pointing to it.In this paper, we examine such ranking problems from a novel perspective and propose a new algorithm which can solve the problems under the previous studies. Our proposed method is based on a class-oriented approach. In contrast to the predicate-oriented approach entertained by the previous research, a user, under our approach, determines the weights of a property by comparing its relative significance to the other properties when evaluating the importance of resources in a specific class. This approach stems from the idea that most queries are supposed to find resources belonging to the same class in the Semantic Web, which consists of many heterogeneous classes in RDF Schema. This approach closely reflects the way that people, in the real world, evaluate something, and will turn out to be superior to the predi-cate-oriented approach for the Semantic Web. Our proposed algorithm can resolve the TKC (Tightly Knit Community) effect, and further can shed lights on other limitations posed by the previous research. In addition, we propose two ways to incorporate data-type properties which have not been employed even in the case when they have some significance on the resource importance. We designed an experiment to show the effectiveness of our proposed algorithm and the validity of ranking results, which was not tried ever in previous research. We also conducted a comprehensive mathematical analysis, which was overlooked in previous research. The mathematical analysis enabled us to simplify the calculation procedure. Finally, we summarize our experimental results and discuss further research issues.

본 연구에서는 제품의 공급지, 유통센터 및 수요지의 3 계층으로 이루어진 공급사슬 상에서 각 공급지와 각 유통센터간의 1단계 수송비용, 각 유통센터와 각수요지 사이의 2단계 수송비용 및 유통센터의 운영비용의 합을 최소화할 수 있는 제품의 수송계획 문제를 대상으로 한다. 본 연구에서는 유전 알고리즘의 선행 연구를 바탕으로 이 문제에 대하여 우수한 해를 생성할 수 있는 협력적 공진화 알고리즘을 다음과 같이 설계한다. 먼저 이 문제를 2개의 부분문제로 분할하고, 각 부분문제에 대하여 우선순위 기반의 표현을 사용한 염색체 개체들로써 모집단을 구성한다. 그리고 두 모집단내 각 개체에 대한 적합도의 평가 원리를 소개하고, 사용할 적합도 함수를 설정하고, 각 개체에 대한 적합도 평가 알고리즘을 제시한다. 마지막으로 두 모집단의 세대교체에 사용될 선택, 교배 및 돌연변이 연산자를 선정한다. 이러한 설계를 기반으로 만들어진 협력적 공진화 알고리즘을 기존의 유전 알고리즘과 그 성능을 비교해 보기 위하여 여러 개의 테스트 문제에 대하여 반복 실험한다. 그 결과, 협력적 공진화 알고리즘은 문제의 크기가 커짐에 따라 기존의 유전 알고리즘에 비해 해의 평균적인 품질이나 해의 변동성 면에서 상대적으로 더 우수한 해를 얻을 수 있었다. 본 연구에서 제시한 협력적 공진화 알고리즘 기반의 해법은 현실적인 다단계 수송문제에도 확장 적용될 수 있다.

We consider a two stage transportation problem in which the objective is to minimize the total cost including shipping cost from plants to distribution centers, shipping cost from distribution centers to customers, and the opening costs of distribution centers in a three tiers of supply chain consisting of plants, distribution centers and customers. We design a cooperative coevolutionary algorithm to solve the problem as follows. First, the problem is decomposed into two different subproblems. In each subproblem we construct a population of chromosome individuals, each of which is denoting a priority and is represented as a permutation. Then we introduce the evaluation principle for a given individual, set the evaluation function, and suggest the evaluation algorithm. Finally we set selection operator, crossover operator, and mutation operator, each of which is used to generate individuals to be included in the next generation. An experiment study is carried out to compare the performance of our cooperative coevolutionary algorithm with that of the genetic algorithm from previous study. In this experiment we obtained the result that in general our coevolutionary algorithm generates better solution than genetic algorithm as the problem size get larger, in term of both the average quality of solutions and the variance of solutions.

A genetic algorithm (GA) is a search algorithm for solving optimization problems due to it is robustness; it offers benefits over optimization techniques in searching n-dimensional surface. In today's information age, information transfer has increased exponentially. Hence, security, confidentiality and authentication have become important factors in multimedia communications. Encryption is an effective technique that is preserving the confidentiality of data in Internet applications. Cryptanalysis is a technique of encoding and decoding ciphertext in such way it cannot be interpreted by anyone expects sender and receiver. In this paper, GA with an improved crossover operator was used for the cryptanalysis of Simplified data encryption standard problem (S-DES). Results have shown that GA performance is better than brute force search technique in breaking S-DES key.

In this application of artificial intelligence to a real-world problem, the constrained scheduling of employee resourcing for a mall type shop is solved by means of a genetic algorithm. hromosomes encode a one-week schedule and a constraint matrix handles all requirements for the population. The genetic operators are purposely designed to preserve all constraints and the objective function assures an imposed coverage, this is for people on both sections of the mall. The results demonstrate that the genetic algorithm approach can provide acceptable solutions to this type of employee scheduling problem with constrains.

Tracking the maximum power point is an appropriate solution against climatic changes like the irradiance and temperature. The classic incremental conductance algorithm is one of the most widely used methods in commercial photovoltaic MPPT’s (Maximum Power Point Tracking). A wide variation of climatic condition can degrade the produced energy. In this work we present our new approach based on fuzzy logic which can guarantee better performance. The studied system used to prove the efficiency of the proposed method is composed by a photovoltaic panel Kaneka K60 connected to a Sepic Converter which fed a resistive load. The All results quoted in this work are found using MATLAB-Simulink. We put the system in different working condition to highlight our new approach. All presented results are discussed.

In recent years, the use of cloud services has been significantly expanded. The providers of software as a service employ multi-tenant architectures to deliver services to their users. In these multi-tenant applications the resource allocation would suffer from over-utilization or under-utilization issues. Considering the significant effects of resource allocation on the service performance and cost, in this paper we have proposed an approach based on genetic algorithm for resource allocation which guarantees service quality through providing adequate resources. The proposed approach also improves system performance, meets the requirements of users and provides maximum resource efficiency. Simulation results show that the proposed approach has better response rate and availability comparing to other approaches, while provides an efficient resource usage.