| Proposed Title :|
FPGA Implementation of Low Power Detection of Symptomatic pattern Audio Biological SignalProposed System:
The Kids Health Monitoring System (KiMS) proposed uses wearable sensors and acoustic signal processing in order to provide health monitoring in children. Using the neural network-based processing, the KiMS classifies various symptoms and activities and, subsequently, transmits the record to a parent or doctor for further analysis. The use of an artificial neural network ensures a good classification rate. However, it also leads to a higher computational load on the implemented hardware and, hence, higher power consumption. Apart from that, complex training methodology is required in order to train the KiMS system for high efficacy. The high power consumption also implies that the limited energy source, that is the battery, is drained of its energy in a shorter period of time. In the case of wearable products, such draining of battery will lead to functional failures, which are undesirable. Although the power consumption of the system can be reduced by reducing the complexity of computation, this may lead to a reduced efficacy of the system. Reduced efficacy can render the primary function of the product redundant. Hence, there is need for the algorithm used in the wearable system and its corresponding hardware implementation to be designed in tandem, so that it is possible to maintain a high algorithmic efficacy and acceptable hardware power efficiency. The system should be scalable to detect patterns in a large variety of signals over a wide array of users. Programmability of the system to user desired function is another desirable feature.
- Performance is low
- High power and More Area
We have proposed an algorithm and its corresponding circuit to detect symptomatic patterns in human acoustic non-speech signals. These include audio recordings of cough, sneeze, belch, wheeze, and vomit patterns. These five human non-speech audio tracks are selected, because they are the most commonly observed signals. They are also known to be symptoms for diseases ranging from influenza, ear infection to serious conditions, such as asthma, bronchitis, stomach flu, and so on. It should be noted that apart from the identified five acoustic symptoms, the proposed system is scalable to other human non-speech audio as well. In order to correctly classify the type of symptom, the acoustic signal needs to be processed efficiently to cause detection. Complexity of this processing is directly translated into equivalent power consumption of corresponding hardware implemented. In order to design an effective and long lasting wearable system for symptomatic pattern detection, it is necessary to reduce its power consumption without degrading the efficacy of detection. This puts stringent design constraint on the power consumed. Therefore, a successful design can be achieved by optimizing algorithmic efficacy and hardware power efficiency during the design process.
Our primary contribution, in this paper, is to address two important issues. First, using a single input (human audio recording), multiple symptomatic patterns have been identified with a high efficacy. Second, the implemented hardware has been made scalable over variety of signals and power efficient. This methodology can be extended to efficaciously detect other symptomatic patterns using power-efficient circuits. We have used the wavelet transform as a mathematical tool to resolve the acoustic signals into their spectral components. Each component can be subsequently identified for specific pattern. In order to reduce the effect of sporadic spikes and noise in the signal, we have utilized the statistical nature of mathematical metrics, such as average, coastline (CL), and so on. Using such methods, the dominant patterns can be detected and classified efficaciously. Fig. 1 shows the block diagram of the system. These blocks are discussed below.
Discrete Wavelet Transform Block:
The wavelet transform block is the most computationally intensive block in the system and consumes a significant amount of power. There are various methods available in the literature to implement the DWT block. In this paper, we use Mallat’s algorithm. The DWT block consists of consecutive stages of low-pass (H) and high-pass (G) filters. These cascading stages are separated by intermediate subsampling (Fig. 2), which is achieved by appropriate clocking of the filters in successive stages. The number of filter stages in the DWT block depends on the number of coefficients of interest in the system. Hence, six cascading stages of H and G are needed. Since the five acoustic patterns are detected using the wavelet coefficients D3 through D6, we need to have five H filters and four G filters. All these filters are of the eighth order due to the use of the Daubechies fourth-order mother wavelet. A standard implementation of nine filters of the eighth order would be computationally intensive in terms of number of multiplication. We utilize multiplier-less technique of computation sharing multiplier (CSHM) and common sub-expression elimination (CSE) to reduce power consumption.
Mathematical Metric Blocks:
The block diagrams for the mathematical metric blocks are shown in Fig. 3. The energy parameter is computed according to (3). The block diagram for computation of energy is shown in Fig. 3(a). It consists of a multiply and accumulate operation, which adds the squared value of the input viz., D6 coefficient. TheD6 window size is chosen in the training phase and corresponds to 1024 samples of the digitized input data. The average energy value is then compared against the threshold to detect acoustics pertaining to vomiting sound. Energy parameter captures the continuous increase in the amplitude of the low-frequency component in human auditory signal to correctly detect this symptom. The CL parameter block diagram is shown in Fig. 3(b). The CL parameter is calculated based on (2). TheD5 coefficient is the input to the CL block. The input is delayed by a clock cycle in order to calculate the difference between two adjacent samples. The magnitude of the difference is accumulated over a prefixed window in order to calculate the trace length of the signal. This accumulated value is then compared with the threshold for detecting wheezing. Since wheezing signal is periodic signal for time duration without any significant increase in amplitude, the CL parameter captures this pattern accurately.
- Better performance
- Low Power and less area
- Xilinx ISE