Investigation of Human-Computer Task Markets: Methods and Prototype
نویسندگان
چکیده
We present research on task markets where automated planning procedures are used to enlist computational and human expertise to jointly contribute to the solution of problems, based on a consideration of the competencies, availabilities, and pricing of the different problem-solving resources. The methods meld the area of human computation with automated reasoning. We describe a prototype that creates plans for harnessing people and computation to perform translation among multiple languages. With the prototype, people with different skills are recruited to refine rough translations generated by a machine translation system. We present details about the hardness of plan generation, provide methods for solving them, and review experiences with the use of a prototype.
منابع مشابه
Control of a Robotic Wheel-Chair Prototype for People with Walking Disabilities
In this paper we present a system that could be used to help people with walking disabilities. A system consists of a prototype mobile robot platform equipped with a control board and a remote computer system, running with image processing algorithms, was used to develop a system for physically disabled human to move freely in an environment. We used a camera to get visual information by a huma...
متن کاملImproving Agent Performance for Multi-Resource Negotiation Using Learning Automata and Case-Based Reasoning
In electronic commerce markets, agents often should acquire multiple resources to fulfil a high-level task. In order to attain such resources they need to compete with each other. In multi-agent environments, in which competition is involved, negotiation would be an interaction between agents in order to reach an agreement on resource allocation and to be coordinated with each other. In recent ...
متن کاملGeneralized Task Markets for Human and Machine Computation
We discuss challenges and opportunities for developing generalized task markets where human and machine intelligence are enlisted to solve problems, based on a consideration of the competencies, availabilities, and pricing of different problemsolving resources. The approach couples human computation with machine learning and planning, and is aimed at optimizing the flow of subtasks to people an...
متن کاملInvestigation of human error by using THERP method in control room of incoiler department in a pipe manufacturing company
Background & Aims of the Study: Today, in many sensitive occupational environments, human error can lead to catastrophic events. Given that the sensitive task of a control area operator, which in the occurrence of malfunction or failure leads to irreparable events, it is important to predict human errors to reduce its adverse consequences. Therefore, the present study was perform by aiming to ...
متن کاملQuantitative Comparison of Analytical solution and Finite Element Method for investigation of Near-Infrared Light Propagation in Brain Tissue Model
Introduction: Functional Near-Infrared Spectroscopy (fNIRS) is an imaging method in which light source and detector are installed on the head; consequently, re-emission of light from human skin contains information about cerebral hemodynamic alteration. The spatial probability distribution profile of photons penetrating tissue at a source spot, scattering into the tissue, and being released at ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009