RELAX:a language to address uncertainty in self-adaptive systems requirement

Self-adaptive systems have the capability to autonomously modify their behavior at run-time in response to changes in their environment. Self-adaptation is particularly necessary for applications that must run continuously, even under adverse conditions and changing requirements; sample domains include automotive systems, telecommunications, and environmental monitoring systems. While a few techniques have been developed to support the monitoring and analysis of requirements for adaptive systems, limited attention has been paid to the actual creation and specification of requirements of self-adaptive systems. As a result, self-adaptivity is often constructed in an ad-hoc manner. In order to support the rigorous specification of adaptive systems requirements, this paper introduces RELAX, a new requirements language for self-adaptive systems that explicitly addresses uncertainty inherent in adaptive systems. We present the formal semantics for RELAX in terms of fuzzy logic, thus enabling a rigorous treatment of requirements that include uncertainty. RELAX enables developers to identify uncertainty in the requirements, thereby facilitating the design of systems that are, by definition, more flexible and amenable to adaptation in a systematic fashion. We illustrate the use of RELAX on smart home applications, including an adaptive assisted living system.

Fuzzy data envelopment analysis:a discrete approach

Data envelopment analysis (DEA) as introduced by Charnes, Cooper, and Rhodes (1978) is a linear programming technique that has widely been used to evaluate the relative efficiency of a set of homogenous decision making units (DMUs). In many real applications, the input-output variables cannot be precisely measured. This is particularly important in assessing efficiency of DMUs using DEA, since the efficiency score of inefficient DMUs are very sensitive to possible data errors. Hence, several approaches have been proposed to deal with imprecise data. Perhaps the most popular fuzzy DEA model is based on a-cut. One drawback of the a-cut approach is that it cannot include all information about uncertainty. This paper aims to introduce an alternative linear programming model that can include some uncertainty information from the intervals within the a-cut approach. We introduce the concept of "local a-level" to develop a multi-objective linear programming to measure the efficiency of DMUs under uncertainty. An example is given to illustrate the use of this method.

Efficiency measurement in fuzzy additive data envelopment analysis

Performance evaluation in conventional data envelopment analysis (DEA) requires crisp numerical values. However, the observed values of the input and output data in real-world problems are often imprecise or vague. These imprecise and vague data can be represented by linguistic terms characterised by fuzzy numbers in DEA to reflect the decision-makers' intuition and subjective judgements. This paper extends the conventional DEA models to a fuzzy framework by proposing a new fuzzy additive DEA model for evaluating the efficiency of a set of decision-making units (DMUs) with fuzzy inputs and outputs. The contribution of this paper is threefold: (1) we consider ambiguous, uncertain and imprecise input and output data in DEA, (2) we propose a new fuzzy additive DEA model derived from the a-level approach and (3) we demonstrate the practical aspects of our model with two numerical examples and show its comparability with five different fuzzy DEA methods in the literature. Copyright © 2011 Inderscience Enterprises Ltd.

Aggregating preference ranking with fuzzy Data Envelopment Analysis

Selecting the best alternative in a group decision making is a subject of many recent studies. The most popular method proposed for ranking the alternatives is based on the distance of each alternative to the ideal alternative. The ideal alternative may never exist; hence the ranking results are biased to the ideal point. The main aim in this study is to calculate a fuzzy ideal point that is more realistic to the crisp ideal point. On the other hand, recently Data Envelopment Analysis (DEA) is used to find the optimum weights for ranking the alternatives. This paper proposes a four stage approach based on DEA in the Fuzzy environment to aggregate preference rankings. An application of preferential voting system shows how the new model can be applied to rank a set of alternatives. Other two examples indicate the priority of the proposed method compared to the some other suggested methods.

Fuzzy assessment of performance of a decision making units using DEA:a non-radical approach

Data Envelopment Analysis (DEA) is recognized as a modern approach to the assessment of performance of a set of homogeneous Decision Making Units (DMUs) that use similar sources to produce similar outputs. While DEA commonly is used with precise data, recently several approaches are introduced for evaluating DMUs with uncertain data. In the existing approaches many information on uncertainties are lost. For example in the defuzzification, the a-level and fuzzy ranking approaches are not considered. In the tolerance approach the inequality or equality signs are fuzzified but the fuzzy coefficients (inputs and outputs) are not treated directly. The purpose of this paper is to develop a new model to evaluate DMUs under uncertainty using Fuzzy DEA and to include a-level to the model under fuzzy environment. An example is given to illustrate this method in details.

Fuzzy knowledge-based approach to treating uncertainty in inventory control

Inventory control in complex manufacturing environments encounters various sources of uncertainity and imprecision. This paper presents one fuzzy knowledge-based approach to solving the problem of order quantity determination, in the presence of uncertain demand, lead time and actual inventory level. Uncertain data are represented by fuzzy numbers, and vaguely defined relations between them are modeled by fuzzy if-then rules. The proposed representation and inference mechanism are verified using a large numbers of examples. The results of three representative cases are summarized. Finally a comparison between the developed fuzzy knowledge-based and traditional, probabilistic approaches is discussed.

Unsupervised KDD to creatively support managers' decision making with fuzzy association rules:a distribution channel application

To be competitive in contemporary turbulent environments, firms must be capable of processing huge amounts of information, and effectively convert it into actionable knowledge. This is particularly the case in the marketing context, where problems are also usually highly complex, unstructured and ill-defined. In recent years, the development of marketing management support systems has paralleled this evolution in informational problems faced by managers, leading to a growth in the study (and use) of artificial intelligence and soft computing methodologies. Here, we present and implement a novel intelligent system that incorporates fuzzy logic and genetic algorithms to operate in an unsupervised manner. This approach allows the discovery of interesting association rules, which can be linguistically interpreted, in large scale databases (KDD or Knowledge Discovery in Databases.) We then demonstrate its application to a distribution channel problem. It is shown how the proposed system is able to return a number of novel and potentially-interesting associations among variables. Thus, it is argued that our method has significant potential to improve the analysis of marketing and business databases in practice, especially in non-programmed decisional scenarios, as well as to assist scholarly researchers in their exploratory analysis. © 2013 Elsevier Inc.

Reduction Measurements for Calculation in Fuzzy Experiment Scheme

The papers is dedicated to the questions of modeling and basing super-resolution measuring- calculating systems in the context of the conception “device + PC = new possibilities”. By the authors of the article the new mathematical method of solution of the multi-criteria optimization problems was developed. The method is based on physic-mathematical formalism of reduction of fuzzy disfigured measurements. It is shown, that determinative part is played by mathematical properties of physical models of the object, which is measured, surroundings, measuring components of measuring-calculating systems and theirs cooperation as well as the developed mathematical method of processing and interpretation of measurements problem solution.

The Cascade Neo-Fuzzy Architecture and its Online Learning Algorithm

In the paper learning algorithm for adjusting weight coefficients of the Cascade Neo-Fuzzy Neural Network (CNFNN) in sequential mode is introduced. Concerned architecture has the similar structure with the Cascade-Correlation Learning Architecture proposed by S.E. Fahlman and C. Lebiere, but differs from it in type of artificial neurons. CNFNN consists of neo-fuzzy neurons, which can be adjusted using high-speed linear learning procedures. Proposed CNFNN is characterized by high learning rate, low size of learning sample and its operations can be described by fuzzy linguistic “if-then” rules providing “transparency” of received results, as compared with conventional neural networks. Using of online learning algorithm allows to process input data sequentially in real time mode.

A fuzzy expected value approach under generalized data envelopment analysis

Fuzzy data envelopment analysis (DEA) models emerge as another class of DEA models to account for imprecise inputs and outputs for decision making units (DMUs). Although several approaches for solving fuzzy DEA models have been developed, there are some drawbacks, ranging from the inability to provide satisfactory discrimination power to simplistic numerical examples that handles only triangular fuzzy numbers or symmetrical fuzzy numbers. To address these drawbacks, this paper proposes using the concept of expected value in generalized DEA (GDEA) model. This allows the unification of three models - fuzzy expected CCR, fuzzy expected BCC, and fuzzy expected FDH models - and the ability of these models to handle both symmetrical and asymmetrical fuzzy numbers. We also explored the role of fuzzy GDEA model as a ranking method and compared it to existing super-efficiency evaluation models. Our proposed model is always feasible, while infeasibility problems remain in certain cases under existing super-efficiency models. In order to illustrate the performance of the proposed method, it is first tested using two established numerical examples and compared with the results obtained from alternative methods. A third example on energy dependency among 23 European Union (EU) member countries is further used to validate and describe the efficacy of our approach under asymmetric fuzzy numbers.

Ensemble fuzzy belief intrusion detection design

With the rapid growth of the Internet, computer attacks are increasing at a fast pace and can easily cause millions of dollar in damage to an organization. Detecting these attacks is an important issue of computer security. There are many types of attacks and they fall into four main categories, Denial of Service (DoS) attacks, Probe, User to Root (U2R) attacks, and Remote to Local (R2L) attacks. Within these categories, DoS and Probe attacks continuously show up with greater frequency in a short period of time when they attack systems. They are different from the normal traffic data and can be easily separated from normal activities. On the contrary, U2R and R2L attacks are embedded in the data portions of the packets and normally involve only a single connection. It becomes difficult to achieve satisfactory detection accuracy for detecting these two attacks. Therefore, we focus on studying the ambiguity problem between normal activities and U2R/R2L attacks. The goal is to build a detection system that can accurately and quickly detect these two attacks. In this dissertation, we design a two-phase intrusion detection approach. In the first phase, a correlation-based feature selection algorithm is proposed to advance the speed of detection. Features with poor prediction ability for the signatures of attacks and features inter-correlated with one or more other features are considered redundant. Such features are removed and only indispensable information about the original feature space remains. In the second phase, we develop an ensemble intrusion detection system to achieve accurate detection performance. The proposed method includes multiple feature selecting intrusion detectors and a data mining intrusion detector. The former ones consist of a set of detectors, and each of them uses a fuzzy clustering technique and belief theory to solve the ambiguity problem. The latter one applies data mining technique to automatically extract computer users’ normal behavior from training network traffic data. The final decision is a combination of the outputs of feature selecting and data mining detectors. The experimental results indicate that our ensemble approach not only significantly reduces the detection time but also effectively detect U2R and R2L attacks that contain degrees of ambiguous information.

An automatic tuning strategy for local fuzzy logic ramp metering algorithm using Particle Swarm Optimization (PSO)

Freeway systems are becoming more congested each day. One contribution to freeway traffic congestion comprises platoons of on-ramp traffic merging into freeway mainlines. As a relatively low-cost countermeasure to the problem, ramp meters are being deployed in both directions of an 11-mile section of I-95 in Miami-Dade County, Florida. The local Fuzzy Logic (FL) ramp metering algorithm implemented in Seattle, Washington, has been selected for deployment. The FL ramp metering algorithm is powered by the Fuzzy Logic Controller (FLC). The FLC depends on a series of parameters that can significantly alter the behavior of the controller, thus affecting the performance of ramp meters. However, the most suitable values for these parameters are often difficult to determine, as they vary with current traffic conditions. Thus, for optimum performance, the parameter values must be fine-tuned. This research presents a new method of fine tuning the FLC parameters using Particle Swarm Optimization (PSO). PSO attempts to optimize several important parameters of the FLC. The objective function of the optimization model incorporates the METANET macroscopic traffic flow model to minimize delay time, subject to the constraints of reasonable ranges of ramp metering rates and FLC parameters. To further improve the performance, a short-term traffic forecasting module using a discrete Kalman filter was incorporated to predict the downstream freeway mainline occupancy. This helps to detect the presence of downstream bottlenecks. The CORSIM microscopic simulation model was selected as the platform to evaluate the performance of the proposed PSO tuning strategy. The ramp-metering algorithm incorporating the tuning strategy was implemented using CORSIM's run-time extension (RTE) and was tested on the aforementioned I-95 corridor. The performance of the FLC with PSO tuning was compared with the performance of the existing FLC without PSO tuning. The results show that the FLC with PSO tuning outperforms the existing FL metering, fixed-time metering, and existing conditions without metering in terms of total travel time savings, average speed, and system-wide throughput.

Evaluating the Appropriateness of Project Delivery Systems for Different Trenchless Methods

Trenchless methods have been considered to be a viable solution for pipeline projects in urban areas. Their applicability in pipeline projects is expected to increase with the rapid advancements in technology and emerging concerns regarding social costs related to trenching methods. Selecting appropriate project delivery system (PDS) is a key to the success of trenchless projects. To ensure success of the project, the selected project delivery should be tailored to trenchless project specific characteristics and owner needs, since the effectiveness of project delivery systems differs based on different project characteristics and owners requirements. Since different trenchless methods have specific characteristics such rate of installation, lengths of installation, and accuracy, the same project delivery systems may not be equally effective for different methods. The intent of this paper is to evaluate the appropriateness of different PDS for different trenchless methods. PDS are examined through a structured decision-making process called Fuzzy Delivery System Selection Model (FDSSM). The process of incorporating the impacts of: (a) the characteristics of trenchless projects and (b) owners’ needs in the FDSSM is performed by collecting data using questionnaires deployed to professionals involved in the trenchless industry in order to determine the importance of delivery systems selection attributes for different trenchless methods, and then analyzing this data. The sensitivity of PDS rankings with respect to trenchless methods is considered in order to evaluate whether similar project delivery systems are equally effective in different trenchless methods. The effectiveness of PDS with respect to attributes is defined as follows: a project delivery system is most effective with respect to an attribute (e.g., ability to control growth in costs ) if there is no project delivery system that is more effective than that PDS. The results of this study may assist trenchless project owners to select the appropriate PDS for the trenchless method selected.

Fuzzy Modeling and Control Based Virtual Machine Resource Management

Virtual machines (VMs) are powerful platforms for building agile datacenters and emerging cloud systems. However, resource management for a VM-based system is still a challenging task. First, the complexity of application workloads as well as the interference among competing workloads makes it difficult to understand their VMs’ resource demands for meeting their Quality of Service (QoS) targets; Second, the dynamics in the applications and system makes it also difficult to maintain the desired QoS target while the environment changes; Third, the transparency of virtualization presents a hurdle for guest-layer application and host-layer VM scheduler to cooperate and improve application QoS and system efficiency. This dissertation proposes to address the above challenges through fuzzy modeling and control theory based VM resource management. First, a fuzzy-logic-based nonlinear modeling approach is proposed to accurately capture a VM’s complex demands of multiple types of resources automatically online based on the observed workload and resource usages. Second, to enable fast adaption for resource management, the fuzzy modeling approach is integrated with a predictive-control-based controller to form a new Fuzzy Modeling Predictive Control (FMPC) approach which can quickly track the applications’ QoS targets and optimize the resource allocations under dynamic changes in the system. Finally, to address the limitations of black-box-based resource management solutions, a cross-layer optimization approach is proposed to enable cooperation between a VM’s host and guest layers and further improve the application QoS and resource usage efficiency. The above proposed approaches are prototyped and evaluated on a Xen-based virtualized system and evaluated with representative benchmarks including TPC-H, RUBiS, and TerraFly. The results demonstrate that the fuzzy-modeling-based approach improves the accuracy in resource prediction by up to 31.4% compared to conventional regression approaches. The FMPC approach substantially outperforms the traditional linear-model-based predictive control approach in meeting application QoS targets for an oversubscribed system. It is able to manage dynamic VM resource allocations and migrations for over 100 concurrent VMs across multiple hosts with good efficiency. Finally, the cross-layer optimization approach further improves the performance of a virtualized application by up to 40% when the resources are contended by dynamic workloads.

Ensemble Fuzzy Belief Intrusion Detection Design

With the rapid growth of the Internet, computer attacks are increasing at a fast pace and can easily cause millions of dollar in damage to an organization. Detecting these attacks is an important issue of computer security. There are many types of attacks and they fall into four main categories, Denial of Service (DoS) attacks, Probe, User to Root (U2R) attacks, and Remote to Local (R2L) attacks. Within these categories, DoS and Probe attacks continuously show up with greater frequency in a short period of time when they attack systems. They are different from the normal traffic data and can be easily separated from normal activities. On the contrary, U2R and R2L attacks are embedded in the data portions of the packets and normally involve only a single connection. It becomes difficult to achieve satisfactory detection accuracy for detecting these two attacks. Therefore, we focus on studying the ambiguity problem between normal activities and U2R/R2L attacks. The goal is to build a detection system that can accurately and quickly detect these two attacks. In this dissertation, we design a two-phase intrusion detection approach. In the first phase, a correlation-based feature selection algorithm is proposed to advance the speed of detection. Features with poor prediction ability for the signatures of attacks and features inter-correlated with one or more other features are considered redundant. Such features are removed and only indispensable information about the original feature space remains. In the second phase, we develop an ensemble intrusion detection system to achieve accurate detection performance. The proposed method includes multiple feature selecting intrusion detectors and a data mining intrusion detector. The former ones consist of a set of detectors, and each of them uses a fuzzy clustering technique and belief theory to solve the ambiguity problem. The latter one applies data mining technique to automatically extract computer users’ normal behavior from training network traffic data. The final decision is a combination of the outputs of feature selecting and data mining detectors. The experimental results indicate that our ensemble approach not only significantly reduces the detection time but also effectively detect U2R and R2L attacks that contain degrees of ambiguous information.