Earticle

Failure modes and effects analysis (FMEA) is a widely used engineering tool in the fields of the design of a product or a process to improve its quality or performance by prioritizing potential failure modes in terms of three risk factors―severity, occurrence, and detection. In a classical FMEA, the risk priority number is obtained by multiplying the three values in 10 score scales which are evaluated for the three risk factors. However, the drawbacks of the classical FMEA have been mentioned by many previous researchers. As a way to overcome these difficulties, this paper suggests the ELECTRE III that is a representative technique among outranking models. Furthermore, fuzzy linguistic variables are included to deal with ambiguous and imperfect evaluation process. In addition, when the importances for the three risk factors are obtained, the entropy method is applied. The numerical example which was previously studied by Kutlu and Ekmek‡ioğlu(2012), who suggested the fuzzy TOPSIS method along with fuzzy AHP, is also adopted so as to be compared with the results of their research. Finally, after comparing the results of this study with that of Kutlu and Ekmek‡ioğlu(2012), further possible researches are mentioned.

Decision analysis has becomes an important technique for decision making in the face of uncertainty. It is characterized by enumerating all the available courses of action, identifying the payoffs for all possible outcomes, and quantifying the subjective probabilities for the all possible random events. When the data are available, decision analysis becomes a powerful tool for determining an optimal course of action. We study the multi-attribute decision making in a compensatory models. In this paper, we use the entropy methods in weights calculating. For the purpose of making optimal decision, the data of five different car models are used. For computing, we used Visual Numerica Version 1.0 software package.

In this paper, we investigates the asymmetry effect of information flow for the 31 daily international foreign exchange rates and also observes the relationship between the difference in the degree of market efficiency and the degree of asymmetry in the information flow. We utilize the symbolic transfer entropy (STE), widely acknowledged in econophysics literature, to estimate the information flows between foreign exchange rates and use the Approximate entropy (ApEn) method which can measure the randomness in the time series. We have find that the information for the 31 daily international foreign exchange rates streams from European to Asian continents, In other words, there is the asymmetry behavior of information flow. We then consider the difference in the degree of market efficiency as driving force of information flow and calculate the ApEn value in all foreign exchange rates used in this paper. We find that the degree of asymmetry in information flows between foreign exchange rates shows the strong positive correlation with the difference in the degree of market efficiency. Our finding suggest that for the international foreign exchange markets the difference in the degree of market efficiency plays an important role as driving force that can determine the direction of information flow.

A quantified reasoning and description of the perplexity for evaluating language models by using the concept of information entropy is discussed in this article: The smaller the entropy of the language estimated by the language model is, the more precise the language model is; an interpolated model based on two (n‐1)‐gram models is better than the (n‐1)‐gram component models, but not a n‐gram model. We also explore the methods to estimating the entropy of Chinese using language models.

본 연구는 전문가 설문 및 엔트로피 가중치 기법을 이용하여 전국의 지진 위험성을 평가하였다. 연구에 사용된 지표는 정부간 기후변화 패널에서 분류하고 있는 4개의 상위 지표 중 위해성, 노출성, 취약성 3개 지표에 따라 10개의 하위지표를 선정하여 전문가 설문조사에 활용하였다. 설문 결과를 엔트로피 가중치 기법을 활용하여 위험점수를 산정하였으며, 위해성, 노출성, 취약성을 단순 합산하여 일정 비율에 따라 위험도를 5개로 등급화하였 다. 연구 결과 최근 대규모 지진이 발생한 경주 및 포항이 위치한 동남권 지역에 5등급으로 국내에서 지진이 가장 위험한 지역으로 나타났다. 또한 동남권 지역 인근에 원자력발전소, 대규모 산업단지 등이 밀집되어있어, 2차, 3차 연쇄 재난의 가능성이 클 것으로 나타났다. 따라서 동남권 지역의 지진재난 대응 역량 강화를 위해 구조 및 비구 조적 대책 마련이 필요하다고 판단된다.

This study evaluated the national earthquake risk using expert questionnaire and entropy weighting technique. As for the indicators used in the study, 10 sub-indices were selected according to the 3 indicators of risk, exposure, and vulnerability among the 4 top indicators classified by the Intergovernmental Panel on Climate Change and used in the expert survey. Then, the risk score was calculated using the entropy weighting technique for the survey results, and the risk, exposure, and vulnerability were simply summed up, and the risk was graded into 5 levels according to a certain ratio. As a result, Gyeongju and Pohang, where large-scale earthquakes occurred recently, were ranked as the 5th grade in the southeastern region where earthquakes were most dangerous in Korea. In addition, since nuclear power plants and large-scale industrial complexes are concentrated near the southeastern region, the possibility of secondary and tertiary chain disasters is high. Therefore, it is urgently required to prepare structural and non-structural countermeasures to strengthen the earthquake disaster response capacity in the southeast region.

기존에 제안된 대부분의 스펙트럼 센싱 기법은 해당 시간에 센싱 된 우선사용자의 신호만을 다루고 있다. 하지만 해당 시간 이전의 우선사용자의 상태를 이용하게 되면 조건부 확률을 사용하여 검출기의 신뢰성을 증가시킬 수 있다. 따라서 크로스 엔트로피(Cross Entropy) 기반의 스펙트럼 센싱 기법에서는 해당 시간 이전의 우선사용자의 상태도 함께 이용하는 기법을 제안하였으며 이를 통해 우선사용자 신호 검출 성능을 향상시키고 잡음에 강인한 성능을 갖도록 하였다. 그러나 이러한 크로스 엔트로피 기반의 스펙트럼 센싱 기법은 모두 실제 이상적인 센싱 환경만을 고려하였다. 다시 말해, 우선사용자의 채널 점유 시간이 항상 일정하다고 가정한 상태에서 센싱을 수행하였다. 하지만 실제 상황에서는 우선사용자가 채널을 점유하는 시간이 이상적인 상황보다 길어질 수도, 반대로 짧아질 수도 있으며 이로 인해 스펙트럼 센싱 성능이 변화 할 수 있다. 따라서 본 논문에서는 이러한 실제 상황에서도 센싱 성능을 일정하게 유지할 수 있는 기법을 제안하였으며 이를 시뮬레이션을 통해 확인하였다.

Most of the traditional spectrum sensing methods consider only the current detected data sets of Primary User (PU). However previous state of PU is a kind of conditional probability that strengthens the reliability of the detector. Therefore, in the cross entropy spectrum sensing method, relationship of the previous and current spectrum sensing is considered to detect PU signal more effectively. But these cross entropy spectrum sensing methods only consider the ideal system. In other words, PU always occupy the channel during the same period. However, PU can occupy the channel either for a longer or a shorter period than the ideal case in the real system. For this reason, the spectrum sensing performance can be varied. In this paper, we propose the method that can maintain the performance of spectrum sensing in the real system and we confirm the results with the help of simulation.

Because of its lower density and plenty of availability, Magnesium alloy is a good choice material in automobile and aerospace industry. There are more and more materials available in the market to serve the common sake. Material selection plays an important role in the process of designing any physical product. A better methodology is required to help the organizations for selecting the best material. Multi Criterion Decision Making (MCDM) methods provide a ranking of the available alternatives thereby, decision of critical thinking become easier. A branch of MCDM methods named Vlse Kriterijumska Optimizacija I Kompromisno Resenje in Serbian (VIKOR) is used in the present work. The work presents the selection of a Magnesium alloy material, where eight materials and ten properties are considered to identify the best material. The influence of weightage factors by three different methods was also discussed.

As a new learning framework, Multi-Instance learning is labeled recently and has successfully found application in vision classification. A novel Multi-instance bag generating method is presented in this paper on basis of Gaussian Mixed Model. The generated GMM model composes not only color but also the locally stable unchangeable components. It is frequently named as MI bag by researchers. Besides, another method called Agglomerative Information Bottleneck clustering is applied to replace the MIL problem with the help of single-instance learning ones. Meanwhile, single-instance classifiers are employed for classification. Finally, ensemble learning is adopted to strengthen classifiers’ generalization ability of RBM (Restricted Boltzmann Machine) as the base classifier. On the basis of large-scale datasets, this method is tested and the corresponding result shows that our method provides high accuracy and good performance for image annotation, feature matching and example-based object-classification.

Internet public opinion response assessment is a very important part of the internet public opinion. This assessment can summarize the works of public opinion response processing, and identify the strengths and weaknesses in response process to provide the basis for the future response processing. In this paper, according to the characteristics of the internet public opinion response work, we proposed a fuzzy comprehensive assessment scheme of internet public opinion based AHP and entropy method and verified the effectiveness of the scheme through the case study. This method not only can reduce subjectivity in the evaluation process and make the assessment more reasonable and accurate. , but also can provide a reference for improving the internet public opinion response works of government.

Since the Internet enters in China, the phenomenon of network public opinion has received the wide range of the attention. The network public opinion has also played the important role in the formation and the spread of the social opinion. At the same time, due to the special nature of the network public opinion, this phenomenon brings the impact on the management mode of the traditional network public opinion. Then, it also leads to the public social events and the false information. Therefore, it is necessary to evaluate the network public opinion. It makes the relevant departments adopt appropriate measures to reduce the risk of the network public opinion. In this paper, we consider to use the combination weight. At the same time, we propose an improved AHP-Entropy method. Aiming at the characteristics of the network public opinion, the method not only considers the subjective weight, but also the objective weight. Then, we get the comprehensive weight. Finally, we use the method to evaluate the risk of the network public opinion. The evaluation results show that the method is reliable and validity.

The green products in manufacture industry still differ from each other in terms of economics, technology, environmental friendliness, though they all reach the criteria of limitation. This paper expounds the necessity for product choice optimization and provides a model based on information entropy to judge different advantages of product groups. According to Entropy Weight Method and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), the basic theory of green product evaluation model is established. The index system includes selected evaluation indicators of green products, considering about the evaluation index of the critical values to construct a hierarchy criterion, which uses entropy to objectively determine the weight vector of each evaluation index. Then, combined with TOPSIS analysis approach and calculates the pros and cons of green products. It is concluded that the evaluation results based on the Entropy-TOPSIS evaluation model are consistent with the actual results, and the results are consistent with the evaluation results of fuzzy mathematics. The method comprehensively considered many influential factors of the green products, to avoid the limitation of single criterion, and the importance of various factors are analyzed and compared, the prediction result is more scientific, as the theoretical basis of green products, and provide a reliable guidance method for product improvement. This is objective to empower the law, which also fully embodies the idea of variable weights and overcome the past green products that exist in the evaluation process homogeneity empowering. That means fixed weights lead to the limitation of a lack of flexible evaluation.

The aim of this paper is to propose a new multi-sensor target recognition method base on relative entropy evaluation theory. There are several influencing factors in the target recognition problem, which needs several sensors to work together. Then the multi-sensor target recognition problem can be regarded as a multi-attribute decision making problem. Relative entropy measure can depict the closeness of the two systems, and then this paper will use it to develop an improved TOPSIS method for the multi-sensor target recognition problem. A new characteristic index weights method is proposed, which can avoid the subjectivity of the weight of characteristic indexes. Finally, an application example is used to illustrate the effectiveness and feasibility of the proposed method.

Determining when software testing should begin and the number of resources that may be required in order to find and fix defects are complicated decisions. If we can predict the number of defects for an upcoming software product given the current development team, it will enable us to make better decisions. A majority of reported defects are managed and tracked using a defect life cycle, which tracks a defect throughout its lifetime. The process starts when the defect is found and ends when the resolution is verified and the defect is closed. Defects transition through different states according to the evolution of the project, which involves testing, debugging, verification. In paper, we presents defect prediction model for consecutive software products that is based on entropy.

Traditional affinity propagation algorithm has inefficient results when conducting clustering analysis of high dimensional data because "dimension effect" lead to difficult find the proper class structure .In view of this, the author proposes an improved algorithm on the basis of Entropy Weight Method and Principal Component Analysis (EWPCA-AP). EWPCA-AP algorithm empowers the sample data by Entropy Weight Method, eliminate data irrelevant attributes by Principal Component Analysis, and travel with neighbor clustering algorithm, realization of high-dimensional data clustering in low dimension space. The numerical result of simulation experiment shows that the new EWPCA-AP algorithm can effectively eliminate the redundancy and irrelevant attributes of data and improve the performance of clustering. In addition, the proposed algorithm is applied in the area of the economy in our country and the clustering result is consistent with the real one. This algorithm provides a new intelligent evaluation method for Chinese economy.

There are several factors influencing the slope stability of open pit mine, and the common methods can be divided into the subjective weighting method and the objective weighting method. In this paper, we make comprehensive evaluation of slope stability by using AHP method and entropy weight method. First of all, we make evaluation of the first level indicators, using AHP method to determine the weight of factors and then use the entropy weight method to calculate the influence factors, the conclusion has certain reliability and scientific nature. Through field monitoring, we get the membership function of each influence index by using assignment method and trapezoid distribution. Following the principle of maximum membership, slope II is the most stable, followed by slope V and slope I, slope III and slope IV are poor stability. This result is consistent with the on-site inspection, and then we proposed treatment measures according to the engineering practice.

CHI statistical text feature selection method based on information entropy optimization is presented in this paper. In the text categorization process of feature selection, considering the results of effect of the distribution within categories and among categories, we introduce the frequency of features information entropy among categories, the information entropy within categories, information within category to optimize the CHI statistical methods. The experimental results show that the classification accuracy of the optimized CHI method is significantly higher than that the traditional CHI statistical methods.

Enterprise risk management (ERM) has raised increasing concern in the field of risk management, and brought practical revenues to enterprises in today’s complex interrelated global business environment. It is a valuable question for China enterprises how to improve the ERM performance. Based upon ERM implemental goals published by COSO, we user elevant data from non-financial listed corporations in SSE, from the perspectives of strategic effectiveness, operational efficiency, reporting reliability and corporate compliance. The data of 509 Chinese enterprises is validly interpreted by entropy weight/TOPSIS method to assess the ERM performance, and to analyze the status of ERM in China. Such models provide means quantitatively improve decision making with respect to the ERM performance.

Based on Fujian industrial enterprises’ technological innovation survey, this established evaluation index system of enterprise’s innovation capabilities. Then, it presented an improved grey clustering model with entropy, and used the model to systematically evaluate the innovation capabilities of enterprises. Empirical study of Fujian enterprises’ innovation capabilities evaluation showed that the improved grey clustering method had a trait of simple, objective, easy to operating, easy to using and so on, and it was practical for assessment enterprises’s innovation capabilities in little information, small sample condition.

Information entropy features are often used for radiation source signal recognition, but due to the information entropy is very sensitive to noise, so this method has greater recognition rate changes with the SNR. This paper putting forward a viable recognition based on Entropy and cloud model. using cloud model to extract secondary features of signals, build radiation source signal’s entropy and cloud feature vector. The method uses cloud model description and processing interval fuzzy and observation noise data, better solve the low SNR cases of radiation source signal feature extraction problem. At the same time, putting forward the similar cloud classification recognition algorithm based on cloud model. The simulation results show that Entropy and cloud model has better recognition effect under low SNR, which can improve the signals’ recognition rate under low SNR.