International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 6, No. 5, 8 Apr. 2014
Cover page and Table of Contents: PDF (size: 277KB)
A New Architecture for Making Moral Agents Based on C4.5 Decision Tree Algorithm
Full Text (PDF, 277KB), PP.50-57
Views: 0 Downloads: 0
Author(s)
Index Terms
Moral Agent, Beauchamp and Childress’s Principles of Biomedical Ethics, C4.5 Decision Tree Algorithm, Machine Ethics
Abstract
Regarding to the influence of robots in the various fields of life, the issue of trusting to them is important, especially when a robot deals with people directly. One of the possible ways to get this confidence is adding a moral dimension to the robots. Therefore, we present a new architecture in order to build moral agents that learn from demonstrations. This agent is based on Beauchamp and Childress’s principles of biomedical ethics (a type of deontological theory) and uses decision tree algorithm to abstract relationships between ethical principles and morality of actions. We apply this architecture to build an agent that provides guidance to health care workers faced with ethical dilemmas. Our results show that the agent is able to learn ethic well.
Cite This Paper
Meisam Azad-Manjiri, "A New Architecture for Making Moral Agents Based on C4.5 Decision Tree Algorithm", International Journal of Information Technology and Computer Science(IJITCS), vol.6, no.5, pp.50-57, 2014. DOI:10.5815/ijitcs.2014.05.07
Reference
[1]Anderson, M., Anderson, S., Armen, C.: Toward Machine Ethics: Implementing Two Action-Based Ethical Theories. In: AAAI 2005 Fall Symp. Machine Ethics, pp. 1–16. AAAI Press, Menlo Park, 2005.
[2]Anderson, M. and Anderson, S. L. Machine Ethics, published by Kluwer Academic , V. 17 , Issue 1 ,Pages: 1–10, 2006.
[3]Robbins R,Wallace W., Decision Support for ethical problem solving: A multi-agent approach. published on elsevier journal of Decision Support Systems, 2007.
[4]Kavathatzopoulos, I., & Asai, R. Can Machines Make Ethical Decisions?. In Artificial Intelligence Applications and Innovations (pp. 693-699). Springer Berlin Heidelberg, 2013.
[5]Anderson, M.; Anderson, S.; and Armen, C.. MedEthEx: A Prototype Medical Ethics Advisor. Eighteenth Conference on Innovative Applications of Artificial Intelligence. Menlo Park, CA: AAAI Press, 2006.
[6]Powers T.M . On the Moral Agency of Computers. IEEE Robot Autom 18(1):51–58, 2013.
[7]Allen, C., Wallach, W., and Smit, I.. Why Machine Ethics?. IEEE Intelligent Systems 21, 4 . 12-17, 2006.
[8]Lawrence, W., & Sankaranarayanan, S Smart Agent Learning based Hotel Search System-Android Environment. International Journal of Information Technology and Computer Science (IJITCS), 4(9), 9, 2012.
[9]Floridi, L., Sanders, J.W.: On the Morality of Artificial Agents. Minds and Machines 14(3), 349–379, 2004.
[10]Elichmann D. , ethical web agents, Computer network and ISDN system, Elsevier, 1995.
[11]Gips, J.Towards the ethical robot. In android Epistemology, K. M. Ford, C.Glymour, and P. J. Hayes, Eds. MIT Press, Cambridge, MA, 243-252, 1995.
[12]Allen, C., Smit, I., and Wallach, W. Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches. Ethics and Information Technology.springer. 149-155, 2005.
[13]Moor, J. H.. The Nature, Importance, and Difficulty of Machine Ethics. IEEE Intelligent Systems 21, 4 . 18-21, 2006.
[14]Ganascia J.G, using non-monotonic logic to model machine ethics, Seventh International Computer Ethics Conference,University of San Diego, USA, 2007.
[15]Rzepka, R. and Araki, What Statistics Could Do for Ethics? – The Idea of Common Sense Processing Based Safety Valve. In: Technical report—machine ethics: papers from the AAAI fall symposium, Technical Report FS-05-06, 85–87, American Association of Artificial Intelligence, Menlo Park, CA, 2005.
[16]Sabah S. Al-Fedaghi, Typification-Based Ethics for Artificial Agents, Second IEEE International Conference on Digital Ecosystems and Technologies, 2008.
[17]Wiegel, V. et. al.,. Privacy, deontic epistemic action logic and software agents, in Ethics and information technology forthcoming, 2006a.
[18]Kurzweil, machine intelligence with the full range of human intelligence.. p. 260, 2005.
[19]Mitchell T. M., Machine learning. Published by McGraw-Hill, Maidenhead, U.K., International Student Edition. ISBN: 0-07-115467-1, 414 pages. , 1997.
[20]Quinlan, J. R. Induction of Decision Trees. Machine Learning 1: 81-106, Kluwer Academic Publishers, 1986.
[21]Sahoo, G. Study of Parametric Performance Evaluation of Machine Learning and Statistical Classifiers. International Journal of Information Technology and Computer Science (IJITCS), 5(6), 57, 2013.
[22]Anderson, M., Anderson, S.: Ethical Healthcare Agents. Studies in Computational Intelligence, V. 107, pp. 233–257. Springer, Heidelberg, 2008.
[23]Anderson, M., and Anderson, S., eds, Machine Ethics: Creating an Ethical Intelligent Agent. IEEE Intelligent Systems, 2007.
[24]McLaren B., Lessons in Machine Ethics from the Prespective of Two Computational Models of Ethical Reasoning. AAAI Fall Symposium,70-77, 2005.
[25]Honarvar A.R., ghasem-Aghaee N., Casuist BDI-Agent: A New Extended BDI Architecture with the Capability of Ethical Reasoning, Artificial Intelligence and Computational Intelligence: International Conference, AICI 2009, Shanghai, China, Springer Verlag, 2009.
[26]Lin, P., Abney, K., Bekey, G.: Robot Ethics: Mapping the Issues for a Mechanized World. Artificial Intelligence,2011.
[27]Guarini M., Particularism and the Classification and Reclassification of Moral Cases, IEEE Intelligent Systems, V. 21, N. 4, 2006.
[28]van den Hoven,J and Lokhorst,G Deontic Logic and Computer- Supported Computer Ethics, Cyberphilosophy: The Intersection of Computing and Philosophy, 2002.
[29]Arkoudas K, Bringsjord, Toward ethical robots via mechanized deontic logic. In: Technical report—machine ethics: papers from the AAAI fall symposium, Technical Report FS–05–06, American Association of Artificial Intelligence, Menlo Park, CA, 2005.
[30]Bentham, J. Introduction to the Principles of Morals and Legislation, W. Harrison, ed., Hafner Press, 1948.
[31]Wallach, W., Allen, C.: Moral Machines: Teaching Robot Right from Wrong. Oxford University Press, Oxford ,2009.