Artificial neuro-fuzzy logic system for detecting human emotions

مقدم أطروحة جامعية

Murad, Umaiyah Mansur

مشرف أطروحة جامعية

al-Khasawinah, Muhammad

أعضاء اللجنة

al-Malkawi, Muhammad
Naum, Riyad S.

الجامعة

جامعة الشرق الأوسط

الكلية

كلية تكنولوجيا المعلومات

القسم الأكاديمي

قسم علم الحاسوب

دولة الجامعة

الأردن

الدرجة العلمية

ماجستير

تاريخ الدرجة العلمية

2011

الملخص الإنجليزي

This thesis presents a combined neural fuzzy model for detecting human emotions using physical measurable and physiological human responses.

The model has fourteen input variables representing human responses, twenty two types of human emotions represented at the output of the model, and the model has the ability to learn through successive training.

The purpose of this thesis is to build an adaptive neuro-fuzzy system, which can be trained to detect the current human emotions from a set of measured responses such as human body temperature, skin variations, heart beat rates and others.

The training will be based on synthetic hypothetical data, although real life data collected by experts in the field is required to train the final model.

After training the model with proper data, the emotion of a person can be detected by applying his/her current measurements of the input factors to the model.

The model developed in this thesis can be utilized effectively in social networks, health organizations, national security systems, and gaming industries.

The hybrid neuro-fuzzy model developed in this thesis is superior to either the fuzzy logic model or the artificial neural network model when built individually.

The hybrid neuro-fuzzy model benefits form the advantages provided by both models and overcome their constraints.

We have developed six models with different types of input/output membership functions and trained by different kinds of input arrays.

The models are compared based on their ability to train with lowest error values.

Many factors impact the error values such as input/output membership functions, the training data arrays, and the number of epochs required for training.

التخصصات الرئيسية

تكنولوجيا المعلومات وعلم الحاسوب

الموضوعات

• العواطف
• الشبكات العصبية(الحاسبات الإلكترونية)
• المنطق الضبابي

عدد الصفحات

135

قائمة المحتويات

• APA
• MLA
• AMA

لغة النص

الإنجليزية

نوع البيانات

رسائل جامعية

رقم السجل

BIM-698545