Abstract:
An automated system is proposed to recognize the distressed situation form the daily living activity of human sounds. The data used in this study is captured in special purpose smart home to depict the daily life of elderly humans. Elderly people are living as dependents in various countries but somehow this trends is much deviated now and people started living on their own. Due to illness or other medical occupations they prefer to stay at home rather than doing an office based job. The automated system will help in raising the living standard of such individuals along with those who are caretakers and can’t monitor them 24/7. The sound activity detection model is proposed which captures the sound of the entire day activity of an individual. As, sound is the plethora of information and carries huge knowledge of its surroundings. This recognition system basically classifies the proposed sounds. The comparison and contrast of already available data, technique and classification strategy discussed already. Our contribution is the collection of a set of acoustic features used for detection of SAD system. 2 Benchmark datasets 1 on-request dataset was used to test this model. Sound-db comprised of self-recorded and internet downloaded sounds. Noise of life was extended model of sound-db. The other dataset was Real World Computing Partnership Sound Database in Real Acoustical Environment (RWCP-DB). Our methodology was to estimate features from temporal, spectral or Spectro-temporal domains and then classified on Multi-class Support Vector Machine. The classifier performed well on different combinations for the improvement of classification accuracy. Our system performed well in comparison with the other methods reported in literature.
