SCT 2017 Abstracts


Full Papers
Paper Nr: 2
Title:

A Neuro-Fuzzy Sugeno-Style HVAC Control System for Balancing Thermal Comfort and Energy Consumption

Authors:

Hoba H. Bakr, Nawzad K. Al-Salihi and Oussama H. Hamid

Abstract: Thermal comfort is an environmental state, in which humans enjoy calefactory conditions while being indoor and wearing a normal amount of clothing. To achieve this, the indoor environment's temperature should be adjusted in accordance with the temperature variations of the outdoor space, taking into account the resulting energy costs. We studied this problem by designing a neuro-fuzzy HVAC control system that provides a higher indoor environment comfort while decreasing the corresponding energy consumption. Our controller utilizes a Sugeno-style fuzzy inference system with two sensory inputs: one for temperature and another for occupants' motion. It outputs a signal that represents the mode of the air conditioner and the compressor speed. Simulation results showed that the air conditioner turns off automatically after 10 minutes of the last detected motion. Furthermore, running the simulations for the energy consumption and resulting costs, both variables were shown to fall in the absence of occupants' motion.

Short Papers
Paper Nr: 1
Title:

The Relative Importance of Perception, Embodiment, Metaphors, and Ethics for Cooperative Human-Machine Coexistence

Authors:

Norris Lee Smith and Oussama H. Hamid

Abstract: In applications of soft computing, one question raised is the extent to which artificial intelligence (AI) and human intelligence (HI) share similar quantitative or qualitative properties or both. Recently, we have argued that phenomenology emphasizes first-person experience as one of the central differences between AI and HI. Presently, we expand this argument to include perception, embodiment, metaphors and ethics. For experience to occur, the experiencing entity needs a body, which contributes to the development of the first-person perspective. The work of Gibson and Merleau-Ponty supports this view by providing alternatives to information processing and behavioral models in the study of perception. Similarly, Lakoff’s central metaphors are compelling in the field of linguistics. In case of AI, however, embodiment seems not to be apparent. As a result, AI has difficulty understanding natural language because perception and many metaphors are expressed and learned in terms of the body. The implication is AI can thrive as long as long as there is HI, which corroborates our view of human-machine coexistence. Furthermore, and not necessarily paradoxical, the humanistic endeavor of ethics may be more suitable for AI in the case of war robots that successfully adhere to universal laws. The integration of AI and HI is accomplished by having humans as the source for first-person experiences, whereas machines are the extended minds of humans.

Paper Nr: 3
Title:

Facial Emotion Recognition in Presence of Speech using a Default ARTMAP Classifier

Authors:

Sheir Afgen Zaheer and Jong-Hwan Kim

Abstract: This paper proposes a scheme for facial emotion recognition in the presence of speech, i.e. the interacting subjects are also speaking. We propose the usage of default ARTMAP, a variant of fuzzy ARTMAP, as a classifier for facial emotions using feature vectors derived from facial animation parameters (FAP). The proposed scheme is tested on Interactive Emotional Dyadic Motion Capture (IEMOCAP) database. The results show the effectiveness of the approach as a standalone facial emotion classifier as well as its relatively superior performance on IEMOCAP in comparison to the existing similar approaches.

Posters
Paper Nr: 4
Title:

Using Artificial Neural Networks in Dialect Identification in Less-resourced Languages - The Case of Kurdish Dialects Identification

Authors:

Hossein Hassani and Oussama H. Hamid

Abstract: Dialect identification/classification is an important step in many language processing activities particularly with regard to multi-dialect languages. Kurdish is a multi-dialect language which is spoken by a large population in different countries. Some of the Kurdish dialects, for example, Kurmanji and Sorani, have significant grammatical differences and are also mutually unintelligible. In addition, Kurdish is considered a less-resourced language. The classification techniques based on machine learning approaches usually require a considerable amount of data. In this research, we are interested in using approaches based on Artificial Neural Network (ANN) in order to be able to identify the dialects of Kurdish texts without the need to have a large amount of data. We will also compare the outcomes of this approach with the previous work on Kurdish dialect identification to compare the performance of these methods. The results showed that the two approaches do not show a significant difference in their accuracy and performance with regard to long documents. However, they showed that the ANN approach performs better than traditional approach for the single sentence classification. The accuracy rate of the ANN sentence classifier was 99% for Kurmanji and 96% for Sorani.