Search

Interactive classification aims at introducing user preferences in the learning process to produce individualized outcomes more adapted to each user’s behavior than the fully automatic approaches. The current interactive classification systems generally adopt a single-label classification paradigm that constrains items to span one label at a time and consequently limit the user’s expressiveness while he/she interacts with data that are inherently multi-label. Moreover, the experimental evaluations are mainly subjective and closely depend on the targeted use cases and the interface characteristics. This paper presents the first extensive study of the impact of the interactivity constraints on the performances of a large set of twelve well-established multi-label learning methods. We restrict ourselves to the evaluation of the classifier predictive and time-computation performances while the number of training examples regularly increases and we focus on the beginning of the classification task where few examples are available. The classifier performances are evaluated with an experimental protocol independent of any implementation environment on a set of twelve multi-label benchmarks of various sizes from different domains. Our comparison shows that four classifiers can be distinguished for the prediction quality: RF-PCT (Random Forest of Predictive Clustering Trees, (Kocev, 2011)), EBR (Ensemble of Binary Relevance, (Read et al., 2011)), CLR (Calibrated Label Ranking, (Fürnkranz et al., 2008)) and ML k NN (Multi-label k NN, (Zhang and Zhou, 2007)) with an advantage for the first two ensemble classifiers. Moreover, only RF-PCT competes with the fastest classifiers and is therefore considered as the most promising classifier for an interactive multi-label learning system. [ABSTRACT FROM AUTHOR]

Abstract: Interactive multiobjective optimization (IMO) is a subfield of multiple criteria decision making. In multiobjective optimization, the optimization problem is formulated with a mathematical model containing several conflicting objectives and constraints depending on decision variables. By using IMO methods, a decision maker progressively provides preference information in order to find the most satisfactory compromise between the conflicting objectives. In this paper, we consider implementation challenges of IMO methods. In particular, we consider what kind of interaction techniques can support the decision making process and information exchange between IMO methods and the decision maker. The implementation of an IMO method called Pareto Navigator is used as an example to demonstrate concrete challenges of interaction design. This paper focuses on describing the incremental development of the user interface for Pareto Navigator including empirical validation by user testing evaluation. [Copyright &y& Elsevier]

Abstract: This paper focuses on interactive decision making methods for random fuzzy two-level linear programming problems. Considering the probabilities that the decision makers’ objective function values are smaller than or equal to target variables, fuzzy goals of the decision makers are introduced. Using the fractile model to optimize the target variables under the condition that the degrees of possibility with respect to the attained probabilities are greater than or equal to certain permissible levels, the original random fuzzy two-level programming problems are reduced to deterministic ones. Interactive fuzzy nonlinear programming to obtain a satisfactory solution for the decision maker at the upper level in consideration of the cooperative relation between decision makers is presented. An illustrative numerical example demonstrates the feasibility and efficiency of the proposed method. [Copyright &y& Elsevier]

Abstract: In this paper, we focus on the difficulties of resource recycling problems relating to the used Iron and/or Aluminum cans. Based on the feedback control theory and combining with micro-chip processor, sensors, phonic chip, oil-compressor and mechanism technology, we design an interactive resource recycling Expert System –“Recycling Squeezed Cans Device” (RSCD) and the proposed interactive RSCD is an automaton device and achieves the following attractive functions: (1) Automatic guiding and detecting system, (2) Security protection system, (3) Automatic classification system, (4) Automatic squeezing system, (5) Automatic distributed collection system, (6) Automatic refund system. We design a heuristic feedback control algorithm imbedded in processor chip and the proposed interactive RSCD has the following special features: the Automatic guiding and detecting system using phonic chip associated with sensors and panel light indicator can easily lead users to operate the RSCD, the Security protection system using sensors associated with electromagnetic switches and safety mechanism designs can protect users harmless and the RSCD as well, the Automatic classification system using sensors associated with mechanic device and the design relating to rotating stepping motor can precisely discriminate whether the recycling used cans material belongs to metal or nonmetal type, and moreover, classify Iron or Aluminum type, the Automatic squeezing system using oil-compressor associated with sensors, and the design as to the compressing device can rapidly squeeze the recycling used cans into under about 1/5 of its original volume, the Automatic distributed collection system using sensors associated with stepping motor, micro-switches, and the design concerning the collection device can precisely distributed collect the recycling compressed cans into two different cans collection tanks, and the Automatic refund system using micro-switches associated with counter, and the design as to the rotating withdrawing device quickly give back the desired refunds. We install the proposed interactive RSCD in several different areas in public and make numerous simulations, the test results show that the proposed interactive RSCD is efficient for handling the resource recycling problems as to the recycling used Iron and/or Aluminum cans. [Copyright &y& Elsevier]

Abstract: This paper proposes an architecture for a pervasive negotiation support system that runs unobtrusively; that is, one in which users do not need to be aware of their current context. We apply context-aware computing technology to both acquire and manage the user''s current context, especially location. For pervasive and mobile transaction, one of our main ideas is to manage negotiation strategies so that they can be accessed and monitored by the transaction participants. We evaluate using a semantic web approach to realize this feature. We implement a prototype system, SmartGuide, and construct two examples to demonstrate the feasibility of the idea proposed in this paper and to evaluate the prototype system. [Copyright &y& Elsevier]

• Interactive, example-based pattern description for text extraction is feasible. • A modular framework accommodating many different options is described. • Many combinations of active learning schemes and string classifiers are assessed. • Experiments with 10 users on 10 tasks to be solved in 1 minute prove feasibility. We consider the problem of identifying within a given document all text items which follow a certain pattern to be specified by a user. In particular, we focus on scenarios in which the task is to be completed very quickly and the user is not able to specify the exact pattern of interest. The key use case corresponds to the interactive exploration of documents in search of snippets that do not fit Boolean, word-based search expressions. We propose an interactive framework in which the user provides examples of the items he is interested in, the system identifies items similar to those provided by the user and progressively refines the similarity criterion by submitting selected queries to the user, in an active learning fashion. The fact that the search is to be executed very quickly places severe requirements on the algorithms that can be used by the system, both for identifying the items and for constructing the queries. We propose and assess experimentally in detail a number of different design options for the components of the learning machinery. The results demonstrate the ability of our approach to achieve effectiveness close to state-of-the-art approaches based on regular expressions, while requiring an execution time which is orders of magnitude shorter. [ABSTRACT FROM AUTHOR]