The way users manage access to their information and computers has a tremendous effect on the overall security and privacy of individuals and organizations. Usually, access management is conducted using a choice architecture , a behavioral economics concept that describes the way decisions are framed to users. Studies have consistently shown that the design of choice architectures, mainly the selection of default options, has a strong effect on the final decisions users make by nudging them toward certain behaviors. In this article, we propose a method for optimizing access control choice architectures in online social networks. We empirically evaluate the methodology on Facebook, the world's largest online social network, by measuring how well the default options cover the existing user choices and preferences and toward which outcome the choice architecture nudges users. The evaluation includes two parts: (a) collecting access control decisions made by 266 users of Facebook for a period of 3 months; and (b) surveying 533 participants who were asked to express their preferences regarding default options. We demonstrate how optimal defaults can be algorithmically identified from users’ decisions and preferences, and we measure how existing defaults address users’ preferences compared with the optimal ones. We analyze how access control defaults can better serve existing users, and we discuss how our method can be used to establish a common measuring tool when examining the effects of default options.

Cloud computing offers a compelling vision of computation, enabling an unprecedented level of data distribution and sharing. Beyond improving the computing infrastructure, cloud computing enables a higher level of interoperability between information systems, simplifying tasks such as sharing documents between coworkers or enabling collaboration between an organization and its suppliers. While these abilities may result in significant benefits to users and organizations, they also present privacy challenges due to unwanted exposure of sensitive information. As information-sharing processes in cloud computing are complex and domain specific, configuring these processes can be an overwhelming and burdensome task for users. This article investigates the feasibility of configuring sharing processes through a small and representative set of canonical configuration options. For this purpose, we present a generic method, named SCON-UP (Simplified CON-figuration of User Preferences). SCON-UP simplifies configuration interfaces by using a clustering algorithm that analyzes a massive set of sharing preferences and condenses them into a small number of discrete disclosure levels. Thus, the user is provided with a usable configuration model while guaranteeing adequate privacy control. We describe the algorithm and empirically evaluate our model using data collected in two user studies (n = 121 and n = 352). Our results show that when provided with three canonical configuration options, on average, 82% of the population can be covered by at least one option. We exemplify the feasibility of discretizing sharing levels and discuss the tradeoff between coverage and simplicity in discrete configuration options.

As technology advances we encounter more available data on moving objects, thus increasing our ability to mine spatio-temporal data. We can use this data for learning moving objects behavior and for predicting their locations at future times according to the extracted movement patterns.In this paper we cluster trajectories of a mobile object and utilize the accepted cluster centroids as the object's movement patterns. We use the obtained movement patterns for predicting the object location at specific future times. We evaluate our prediction results using precision and recall measures. We also remove exceptional data points from the moving patterns by optimizing the value of an exceptions threshold.

BACKGROUND: The definition of a distance measure plays a key role in the evaluation of different clustering solutions of gene expression profiles. In this empirical study we compare different clustering solutions when using the Mutual Information (MI) measure versus the use of the well known Euclidean distance and Pearson correlation coefficient. RESULTS: Relying on several public gene expression datasets, we evaluate the homogeneity and separation scores of different clustering solutions. It was found that the use of the MI measure yields a more significant differentiation among erroneous clustering solutions. The proposed measure was also used to analyze the performance of several known clustering algorithms. A comparative study of these algorithms reveals that their "best solutions" are ranked almost oppositely when using different distance measures, despite the found correspondence between these measures when analysing the averaged scores of groups of solutions. CONCLUSION: In view of the results, further attention should be paid to the selection of a proper distance measure for analyzing the clustering of gene expression data.

Feature selection is the process of identifying relevant features in the dataset and discarding everything else as irrelevant and redundant. Since feature selection reduces the dimensionality of the data, it enables the learning algorithms to operate more effectively and rapidly. In some cases, classification performance can be improved; in other instances, the obtained classifier is more compact and can be easily interpreted. There is much work done on feature selection methods for creating ensemble of classifiers. Thus, these works examine how feature selection can help ensemble of classifiers to gain diversity. This paper examines a different direction, i.e. whether ensemble methodology can be used for improving feature selection performance. In this paper we present a general framework for creating several feature subsets and then combine them into a single subset. Theoretical and empirical results presented in this paper validate the hypothesis that this approach can help to find a better feature subset.

Many real life problems are characterized by the structure of data derived from multiple sensors. The sensors may be independent, yet their information considers the same entities. Thus, there is a need to efficiently use the information rendered by numerous datasets emanating from different sensors. A novel methodology to deal with such problems is suggested in this work. Measures for evaluating probabilistic classification are used in a new efficient voting approach called "selective voting", which is designed to combine the classification of the models (sensor fusion). Using "selective voting", the number of sensors is decreased significantly while the performance of the integrated model's classification is increased. This method is compared to other methods designed for combining multiple models as well as demonstrated on a real-life problem from the field of human resources.

This paper introduces a new ensemble technique, cluster-based concurrent decomposition (CBCD) that induces an ensemble of classifiers by decomposing the training set into mutually exclusive sub-samples of equal-size. The CBCD algorithm first clusters the instance space by using the K-means clustering algorithm. Afterwards it produces disjoint sub-samples using the clusters in such a way that each sub-sample is comprised of tuples from all clusters and hence represents the entire dataset. An induction algorithm is applied in turn to each subset, followed by a voting mechanism that combines the classifier's predictions. The CBCD algorithm has two tuning parameters: the number of clusters and the number of subsets to create. Using a suitable meta-learning it is possible to tune these parameters properly. In the experimental study we conducted, the CBCD algorithm, using an embedded C4.5 algorithm, outperformed the bagging algorithm of the same computational complexity.

Decision trees are considered to be one of the most popular approaches for representing classifiers. Researchers from various disciplines such as statistics, machine learning, pattern recognition, and data mining considered the issue of growing a decision tree from available data. This paper presents an updated survey of current methods for constructing decision tree classifiers in a top-down manner. The paper suggests a unified algorithmic framework for presenting these algorithms and describes the various splitting criteria and pruning methodologies.

We describe and evaluate an information-theoretic algorithm for data-driven induction of classification models based on a minimal subset of available features. The relationship between input (predictive) features and the target (classification) attribute is modeled by a tree-like structure termed an information network (IN). Unlike other decision-tree models, the information network uses the same input attribute across the nodes of a given layer (level). The input attributes are selected incrementally by the algorithm to maximize a global decrease in the conditional entropy of the target attribute. We are using the prepruning approach: when no attribute causes a statistically significant decrease in the entropy, the network construction is stopped. The algorithm is shown empirically to produce much more compact models than other methods of decision-tree learning while preserving nearly the same level of classification accuracy.

Decision-tree algorithms are known to be unstable: small variations in the training set can result in different trees and different predictions for the same validation examples. Both accuracy and stability can be improved by learning multiple models from bootstrap samples of training data, but the "meta-learner" approach makes the extracted knowledge hardly interpretable. In the following paper, we present the Info-Fuzzy Network (IFN), a novel information-theoretic method for building stable and comprehensible decision-tree models. The stability of the IFN algorithm is ensured by restricting the tree structure to using the same feature for all nodes of the same tree level and by the built-in statistical significance tests. The IFN method is shown empirically to produce more compact and stable models than the "meta-learner" techniques, while preserving a reasonable level of predictive accuracy.

This paper examines the attribute decomposition approach with simple Bayesian combination for dealing with classification problems that contain high number of attributes and moderate numbers of records. According to the attribute decomposition approach, the set of input attributes is automatically decomposed into several subsets. A classification model is built for each subset, then all the models are combined using simple Bayesian combination. This paper presents theoretical and practical foundation for the attribute decomposition approach. A greedy procedure, called D-IFN, is developed to decompose the input attributes set into subsets and build a classification model for each subset separately. The results achieved in the empirical compart. son testing with well-known classification methods (like C4.5) indicate the superiority of the decomposition approach.

Engineering systems are developed through numerous modification cycles. Most of them arise from routine engineering processes such as optimization or by adopting new technologies. On occasion though, a system is modified through a qualitatively different process: a creative process. We call this type of modification a design invention. The paper presents an objective metric for the evaluation of the inventiveness of an engineering solution. This metric can be used not only to evaluate a known solution but also to guide the search toward new design inventions. The paper presents a formal treatment of the sufficient conditions with illustrative examples and case studies. An empirical study demonstrates that solutions which satisfy the conditions tend to score high on creativity evaluation by field experts.

When evaluation of terms such as "design complexity" and its "quality", it is often performed in an ad hoc manner. This paper attempts to remedy this situation by articulating two definitions of design complexity (structural complexity versus functional complexity), their associated value measures, and the relationships between them. The structural definition states that a design complexity is a function of its representation. Defining design complexity in the structural way provides quantitative techniques for evaluating vague terms. The functional definition states that a design complexity is a function of its probability of successfully achieving the required specifications (functional requirements and constraints). The proposed measurable metrics provide a proper basis for evaluating each step of the design process, and accordingly recommends the direction to follow for design modification and enhancement. It also provides a framework for comparing competing artifacts.

In this paper, we examine the logic and methodology of engineering design from the perspective of the philosophy of science. The fundamental characteristics of design problems and design processes are discussed and analyzed. These characteristics establish the framework within which different design paradigms are examined. Following the discussions on descriptive properties of design, and the prescriptive role of design paradigms, we advocate the plausible hypothesis that there is a direct resemblance between the structure of design processes and the problem solving of scientific communities. The scientific community metaphor has been useful in guiding the development of general purpose highly effective design process meta-tools.

A state of a discrete event stochastic system (DESS) can be represented by a tuple of time-varying discrete parameters. The authors have extended the theory of controlled discrete event systems developed by Ramadge, Wonham and other researchers to stochastic modeling and performance measurement. This work presents some important characteristics of the DESS model. The problem of making the most efficient use of information-processing resources (sensors, computer capacity, etc.) in a special class of controlled systems is stated in a new, two-stage format. The format is used to develop a heuristic solution procedure of the problem. Finally, we perform a brief discussion of the model applicability to real-life design of automatic supervisors.

Presents and analyzes a formal model of a design process, emphasizing the synthesis part. The design artifact description is identified as an algebraic structure. The desired function and constraints are mapped to the artifact description using an evolutionary process that can be visualized as a feedback loop of analysis, synthesis and evaluation. A special case of the synthesis activity, called the basic synthesis problem (BSP), is addressed. The BSP is shown to be NP-complete. As a consequence, tractability can be obtained by enforcing constraints on the artifact structure. As such, the authors present a model having an element of descriptive design theory that is also a framework for the future development of computational support systems and automatic design tools.

A method for robot program synthesis is developed. The conceptual graph-based approach is proposed for the development of a robot programming support system. The system provides a means toward automated conversion of a user's request expressed in natural language to the appropriate conceptual model of the required task. This approximate model of the dynamically changing real world of robotic assembly incorporates the information necessary for understanding, planning, and sensory-guided performance of the required robotic task. The overall framework of the system is defined, and the authors present the first phase of an assembly program synthesis: request specification, planning of valid assembly sequences, and required resources determination. A case study illustrates the approach on a large family of multi-axisymmetric components.>

The problem of how to utilize some robot task flexibility characteristics efficiently is addressed. For a given set of robots and a set of tasks which can be accomplished through several alternative sequences of motions and operations, the robot task-sequencing planning problem is to determine the optimal sequence of paths for each robot such that all the tasks are executed with a total minimum cost (e.g. time). A framework and a classification for such types of problems are provided, and one class of problems is studied. The problems are solved according to the proposed decomposition scheme. Special considerations, such as the capacity of the robot end effector and coordination planning among several robots, are included in the algorithms. An example illustrates the problem and the solution.>

This paper presents a method for real-time scheduling and routing of material in a Flexible Manufacturing System (FMS). It extends the earlier scheduling work of Kimemia and Gershwin. The FMS model includes machines that fail at random times and stay down for random lengths of time. The new element is the capability of different machines to perform some of the same operations. The times that different machines require to perform the same operation may differ. This paper includes a model, its analysis, a real-time algorithm, and examples.

The purpose of dynamic routing in FMS is to achieve real-time load balancing in a stochastic processing environment and thus to increase the performance of the system, in throughput, workload balance and reduced in-process queues. We formulate and develop a stationary policy based on the input buffer state of each station.

Integration of an automated manufacturing system is now recognized as one of the key issues for improving productivity. The separation of a large complex system into smaller subsystems that operate individually contributes to an efficient integration and control of the entire system. However, the overall performance of the system may be reduced if each subsystem operates independently and if no cooperation between the subsystems' resources exists. How the subsystems should cooperate to improve system performance is investigated.

This paper describes an experimental system that implemented the Activity Controller Theory presented in Maimon [8] pp. 48-70. The controller has the ability to coordinate any number of robots (and other automated machines) and to respond to the random arrival of components, so as to efficiently assemble different products. The work also briefly presents the structure of the coordination system, and a solution frame to the dynamic collision avoidance problem. The computer-controlled experimental system is used to simultaneously operate two robots sharing tasks and auxiliary devices in an assembly cell.