Indian Journal of Science and Technology
Year: 2016, Volume: 9, Issue: 38, Pages: 1-9
Hemanta Kumar Palo1 *, Jyoti Mohanty1 , Mihir Narayan Mohanty1 , Mahesh Chandra2
1 Department of Electronics and Communication Engineering, Siksha ‘O’ Anusandhan University, Bhubaneswar - 751030, Odisha, India; [email protected]
2 Department of Electronics and Communication Engineering, Birla Institute Technology, Ranchi - 835215, Jharkhand, India; [email protected]
*Author for correspondence
Hemanta Kumar Palo
Department of Electronics and Communication Engineering
Email: [email protected]
Background/Objectives: The objective of this paper is to distinguish similar and overlapped emotional states like disgust and irritation from the primary angry state based on similarity measures. Methods/Statistical Analysis: The similarity test among these emotions have been carried out using the signal waveform, frequency coherence, power spectral density, log-likelihood score and Dynamic Time Wrapping (DTW) technique. Findings: Disgust state has more number of frequency coherence peaks which are leaning more towards unity like angry state. Further the phase angle between irritation and anger state is larger than between anger and disgust state. The minimum cost path using dynamic time wrapping technique founds to be 147.5917 between disgust and angry state as compared to 184.2386 between angry and irritation samples. From these analyses, it is concluded that, the primary anger state is more closure to disgust state than irritation state. The results are promising and we are able to put a boundary among these emotional states with our chosen techniques. Application/Improvements: Anger detection can lead to an improvement in human relationship and social system refinement. Demarcation of subcategory emotions that leads to anger state prevents confusion and can improve its recogntion.
Keywords: Emotional States, Dynamic Type Wrapping, Short Time Fourier Transform, Similarity Measure, Spectral Coherence
Subscribe now for latest articles and news.