Many approaches and tools assist the various tasks required to develop a multi-agent system (MAS), yet there still remains a gap between the generation of MAS models and program code. The resulting popularity of Agent-Oriented Software Engineering (AOSE) thus demands a methodology that facilitates the development of robust, scalable MAS implementations that recognise real-world semantics. We de...

A common approach to handle computer-based model experimentation is to use scientific workflow management systems. Such systems are dataflow-oriented. To match this paradigm, the experimenter has to ”translate” the objectives of his experimentation into terms of tasks with their composition and inand output data. This challenge causes a significant effort, requires workflow expert knowledge and...

There have been two thrusts in the development of optical flow algorithms. One has emphasized higher accuracy; the other faster implementation. These two thrusts, however, have been independently pursued, without addressing the accuracy vs. efficiency trade-offs. Although the accuracy-efficiency characteristic is algorithm dependent, an understanding of a general pattern is crucial in evaluatin...

Recently advancements in deep learning allowed the development of endto-end trained goal-oriented dialog systems. Although these systems already achieve good performance, some simplifications limit their usage in real-life scenarios. In this work, we address two of these limitations: ignoring positional information and a fixed number of possible response candidates. We propose to use positional...

In process planning, determining feature’s machining precedence is an essential step. The task becomes more difficult if features interact with each other, in which case the feature precedence information may suggest multiple machining sequences of the features. This paper considers interacting features in a feature-based model for process planning tasks. For each feature, precedence informatio...

There is currently no human-computer interface specifically designed for the alternative interaction modes used on wearable systems for input and output. For a geographically oriented wearable computer system a graphical user interface (GUI) is indispensable, yet contemporary window systems using the desktop metaphor are unsuitable for wearable computing. In this paper we document and discuss t...

Text in natural images is of arbitrary orientations, requiring detection in terms of oriented bounding boxes. Normally, a multi-oriented text detector often involves two key tasks: 1) text presence detection, which is a classification problem disregarding text orientation; 2) oriented bounding box regression, which concerns about text orientation. Previous methods rely on shared features for bo...

This study investigated the effects of different output-based task repetition conditions on EFL learners’ speech act production. Three intact classes of English-major students constituted three instructional groups: (1) the explicit task-repetition (ETR) group, (2) the implicit task-repetition (ITR) group, and (3) the no-input task repetition (NTR) group. All the three groups engaged in t...