Low-Power System for Detection of Symptomatic Patterns in Audio Biological Signals
Abstract : In this paper, we present a low-power, efficacious, and scalable system for the detection of symptomatic patterns in biological audio signals. The digital audio recordings of various symptoms, such as cough, sneeze, and so on, are spectrally analyzed using a discrete wavelet transform. Subsequently, we use simple mathematical metrics, such as energy, quasi-average, and coastline parameter for various wavelet coefficients of interest depending on the type of pattern to be detected. Furthermore, a mel-frequency cepstrum-based analysis is applied to distinguish between signals, such as cough and sneeze, which have a similar frequency response and, hence, occur in common wavelet coefficients. Algorithm-circuit codesign methodology is utilized in order to optimize the system at algorithm and circuit levels of design abstraction. This helps in implementing a low-power system as well as maintaining the efficacy of detection. The system is scalable in terms of user specificity as well as the type of signal to be analyzed for an audio symptomatic pattern. We utilize multiplierless implementation circuit strategies and the algorithmic modification of mel cepstrum computation to implement lowpower system in the 65-nm bulk Si technology. It is observed that the pattern detection system achieves about 90% correct classification of five types of audio health symptoms. We also scale the supply voltage due to lower frequency of operation and report a total power consumption of ~184 µW at 700 mV supply.
? The existing system has been experimented for testing the emotions of the subject, type of sounds and their origin.
? In this paper, a design is proposed for the acquisition of audio signals and then process under a standard pattern values with the consideration of lower attributes such as power and system scalability for detection of symptomatic pattern.
? The outcomes of MelFilters are layered according to energy spectrum for avoiding internal anomalies of signal.
? Discrete Cosine Transformation is performed for energy spectrum for internal segregation of the signal strength and in general, the signals are appending with decision making approaches.
? If repetitive occurrence of these symptoms is detected in advance, it is possible for the patient or the healthcare personnel to commence remedial action prior to aggravation of the problem.
? These parameters, it is well known that acoustic symptoms, such as cough, sneeze, belching, and so on, are early markers of serious health issues, such as influenza, diarrhea, and whooping cough, especially among children.
? The order of the selected mother wavelet is an algorithmic design decision, which has a direct impact on the complexity of its hardware implementation.
? There are several health risks associated with snoring and leads to serious health problems.
• We have proposed an algorithm and its corresponding circuit to detect symptomatic patterns in human auditory no speech signals.
• It need to be referred to that aside from the recognized five acoustic symptoms, the proposed device is scalable to different human non-speech audio as well.
• In this paper, we have proposed a commonplace device primarily based on wavelet transform, mathematical metrics, and mel cepstrum based analysis, which can be used to notice odd human audio signals.
• The proposed system is more feasible with the user inputs and the Indian environment.
? In order to correctly classify the type of symptom, the acoustic signal needs to be processed efficiently to cause detection.
? However, to do that at a lower hardware cost, we make modification to filter coefficients (algorithm modification) and filter circuit topology (circuit modification) to achieve similar functionality without any degradation in quality at a much lower hardware cost (power).
? The acoustic signals in the form of wavelet coefficients have certain patterns corresponding to the symptom to be detected.
? Although the symptomatic patterns are frequency resolved into separate wavelet coefficients, there are several sporadic spikes in the wavelet processed data, which might trigger false detection.
|