Claims:1. A device for detection of wheezing in a patient, wherein said device comprises of a
a display unit for indicating parameters of wheezing;
a power source;
a breathing sound detection unit configured to detect a breathing sound of a measurement subject and acquire a breathing sound signal in a time series expressing the breathing sound;
tubes and wires for sending signals from sensing section to a processing chamber;
wherein said processing chamber can process and detect the parameters of wheezing to be displayed on the display unit.

2. The device as claimed in claim 1, wherein the processing chamber evaluates parameters of wheezing by following process steps:
(i) developing a short-time Fourier transform (STFT) to acquire a spectrogram containing a time-frequency relationship of the wheezing sound;
(ii) forming an mage Mask from the Spectrogram;
(iii) parameters are extracted and classified using a support vector machine (SVM).

3. The device as claimed in claim 2, wherein in step (ii) noise is filtered using a bilateral filter and image processing methods to pin point wheezing.

4. The device as claimed in claim 3, wherein the image processing methods are selected from edge detection method, multi-threshold image segmentation, or image morphological processing.

5. The device as claimed in claim 3, wherein a sifting process using two rules based on CORSA standards is also applied to ensure that objects in the image mask are wheezes.

6. The device as claimed in any of the preceding claims, wherein bilateral filtering is used to both smooth the image by removing outliers, and preserve strong image edge components by giving both spatial and photometric domains weighted coefficients.

7. The device as claimed in claim 1, wherein edge detection and multi threshold segmentation are combined to preserve image edges and retain high and isolated peaks during analysis.
, Description:Field of Invention:
Present invention relates to a device for detecting respiratory problems. More particularly, the invention relates to a device for detecting wheezing in a patient.

Background of Invention:
Wheezing is a high-pitched whistling sound made while breathing. It's often associated with difficulty breathing. Wheezing may occur during breathing out (expiration) or breathing in (inspiration). Many people with respiratory allergies know that bouts of wheezing often come with the arrival of hay fever season. Wheezing may also accompany respiratory infections such as acute bronchitis and may be experienced by patients in heart failure and by some with emphysema (or chronic obstructive pulmonary disease, COPD). But the characteristic whistling sound of wheezing is a primary symptom of the chronic respiratory disease asthma.
A variety of treatments are available to help alleviate wheezing. You should be regularly monitored by a doctor if you have asthma, severe allergies, chronic bronchitis, emphysema, or COPD. Evaluation by a specialist such as an allergist or pulmonologist may also be recommended in some cases.
Wheeze monitoring is an important aspect of chronic respiratory disease management, such as asthma management. Wheezes are adventitious lung sounds that are superimposed on normal breath sounds and indicate constricted breathing. A wheeze is generally characterized by a high pitch sound lasting a predetermined duration, and can be detected by evaluating time and frequency components of a respiratory signal.
Up to now, there have been several methods of automatic lung sound diagnosis and analysis put forth sequentially, such as the disclosures in U.S. Pat. Nos. 6,139,505 and 6,261,238. Regarding these techniques, a plurality of microphones, collecting acoustic signals, are attached to the chest of a patient. Afterwards, the collected acoustic signals are analyzed to recognize what illnesses the patient suffers from, such as pneumonia, emphysema, bronchitis and asthma. In this regard, such a diagnosis system is appropriate to be used in general clinical diagnosis because the patient who is bedridden or sleeping feels uncomfortable with the attached microphones over a long term. On the other hand, specific acoustic signals characterizing each kind of lung illness must be collected in advance so that unrecognized acoustic signals can have a spectrum analysis and be compared with the database consisting of the collected specific acoustic signals. Therefore, the diagnosis system is very complicated.
US20170325777 discloses a wheezing detection apparatus includes a breathing sound detection unit that detects a breathing sound of a measurement subject and acquires a breathing sound signal in a time series expressing the breathing sound. The wheezing detection apparatus includes a determination processing unit that, in each pre-determined processing unit period, converts the breathing sound signal into a frequency space to acquire a frequency spectrum of the breathing sound, and based on a height and a width of a peak in the frequency spectrum, determines whether or not the peak indicates wheezing. The lightweight wheeze detection method comprises the steps of receiving by a respiratory data processing system a respiratory signal; calculating by the processing system noncontiguous lines of a STFT image of the respiratory signal until a start line conforming to one or more wheeze peak criteria is identified; once a start line conforming to the wheeze peak criteria is identified, calculating by the processing system contiguous lines of the STFT image preceding the start line and contiguous lines of the STFT image following the start line until both a preceding line and a following line not conforming to the wheeze peak criteria are identified; and, once both a preceding line and a following line not conforming to the wheeze peak criteria are identified, determining by the processing system using a total count of calculated lines of the STFT image conforming to the wheeze peak criteria whether a duration of a peak conforms to one or more wheeze duration criteria.
Patent Document US 2011/0125044 A1 discloses an automated system for observing a respiratory disease such as asthma. The system provides a summary of data and a warning when the severity of symptoms reaches a threshold value based on data from a microphone and an accelerometer. In particular, for wheezing, peaks of a frequency spectrum in a frequency range of about 200 to 800 Hz is measured, the peaks of the frequency spectrum and a predetermined value that is associated with wheezing and is stored in the memory are compared, and the result of the comparison is used as an element for determining the severity.
US8506501 discloses a lightweight wheeze detection methods and systems for portable respiratory health monitoring devices conserve computing resources in portable respiratory health monitoring devices by employing lightweight algorithm that calculates a partial STFT image of a respiratory signal that includes all data points necessary for wheeze detection but excludes many data points that are unnecessary for wheeze detection. The methods and systems provide substantial savings in computing resources while still ensuring every wheeze in a respiratory signal is detected.
US 20060077063A discloses a portable monitoring system for recognizing wheeze in lung sounds can detect the occurrence of wheeze from the neck of an asthmatic. The portable monitoring system comprises an acoustic sensor, a signal processor and a wireless signal transmission module, a remote analyzer and an alarm generator. The acoustic sensor is placed next to the windpipe of the asthmatic to collect the acoustic signals when he breathes. The signal processor and remote analyzer analyze the acoustic signals to recognize whether the wheeze, in the form of specified signals, exists. If the wheeze is found, the wireless signal transmission module or the remote analyzer directly instructs the alarm generator to generate an alarm so as to notify someone to give medical treatment to the asthmatic.
PCT (patent convention treatment) patent publication No. 01/19243 discloses an asthma inspection apparatus. Even though the apparatus is simplified as a microphone-shaped device, sampled signals and corresponding statistical data are still necessarily obtained and stored in the memory components of the apparatus for comparison with unrecognized acoustic signals in advance. Apparently, whether the apparatus can exactly recognize an asthma attack is completely dependent on what acoustic signals are sampled.
In conclusion, the medical equipment industry currently desires to develop an asthma detector that is portable and convenient for a bedridden patient to use. Such an asthma detector is suitable for an asthmatic to wear for a long term. The beginning of an asthma attack, especially, should be actually sensed by the detector.
However, with the above-described system, since only the magnitudes of the peaks of the frequency spectrum and the reference value (value stored in the memory) are compared for wheezing, there is a problem in that the accuracy of detecting wheezing is not good.
WIPO Patent Application WO/2016/136049, discloses a wheezing detection device is provided with a breathing sound detection unit that detects the breathing sounds of a subject and acquires a chronological breathing sound signal representing the breathing sounds. The wheezing detection device is also provided with a determination processing unit that, for each of preset processing unit periods, converts the breathing sound signal into a frequency space, acquires the frequency spectrum of the breathing sounds, and determines whether a peak (Pd) in the frequency spectrum indicates wheezing on the basis of the height (L) and the width (D) of the peak (Pd).
In view of this, the present invention aims to provide a wheezing detection apparatus that can accurately detect whether or not wheezing is included in a breathing sound of a measurement subject.
The whistling sound that characterizes wheezing occurs when air moves through airways that are narrowed, much like the way a whistle or flute makes music. In asthma, this airway narrowing is due to inflammation, mucus, and muscle spasms in the wall of the airways.
In this world mostly people live and die from, respiratory disorders. It doesn’t matter who suffer, may be young or old. This respiratory problem people have from birth or develop in certain environmental condition or few from dust allergy. Wheezes are more respiratory sounds as compared to normal respiratory sound, which a usually due to pathological condition of the respiratory system especially irregularities in pulmonary obstruction, such as asthma and chronic obstructive pulmonary disease. Identification of the Wheeze sound is the first step in controlling the asthma. Using that easy to understand the disease progress, and how close research to developing new test and treatments and what still needs to be done. Although many studies have addressed the problem of wheeze detection, a limited number of scientific works has focused on real time detection of wheeze sound. As day to day increasing number of asthmatic patient there is a need of automatic monitoring of the wheeze sound to assist the physicians in diagnosing and monitoring the patient. This is the invention that makes automatic wheeze detection systems with spectral power estimation in real time to assist the physicians in diagnosing and monitoring the patient.
Summary of Invention:
In this disclosure, whenever a composition, an element or a group of elements is preceded with the transitional phrase "comprising", it is understood that we also contemplate the same composition, element or group of elements with transitional phrases "consisting essentially of, "consisting", "selected from the group of consisting of, "including", or "is" preceding the recitation of the composition, element or group of elements and vice versa.

According to an embodiment of the invention, there is provided a device for detection of wheezing in a patient, wherein said device comprises of:
a display unit for indicating parameters of wheezing;
a power source;
a breathing sound detection unit configured to detect a breathing sound of a measurement subject and acquire a breathing sound signal in a time series expressing the breathing sound;
tubes and wires for sending signals from sensing section to a processing chamber;
wherein said processing chamber can process and detect the parameters of wheezing to be displayed on the display unit.

Yet according to another aspect of the invention, there is provided a device, wherein the processing chamber evaluates parameters of wheezing by following process steps:
(i) developing a short-time Fourier transform (STFT) to acquire a spectrogram containing a time-frequency relationship of the wheezing sound;
(ii) forming an image Mask from the Spectrogram;
(iii) parameters are extracted and classified using a support vector machine (SVM).

Yet according to another aspect of the invention, there is provided a device, wherein in step (ii) noise is filtered using a bilateral filter and image processing methods to pin point wheezing.

Yet according to another aspect of the invention, there is provided a device, wherein the image processing methods are selected from edge detection method, multi-threshold image segmentation, or image morphological processing.

Yet according to another aspect of the invention, there is provided a device, wherein a sifting process using two rules based on CORSA standards is also applied to ensure that objects in the image mask are wheezes.

Yet according to another aspect of the invention, there is provided a device, wherein bilateral filtering is used to both smooth the image by removing outliers, and preserve strong image edge components by giving both spatial and photometric domains weighted coefficients.

Yet according to another aspect of the invention, there is provided a device, whereinedge detection and multi threshold segmentation are combined to preserve image edges and retain high and isolated peaks during analysis.

Description of Drawings:
So that the manner in which the above recited features of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting of its scope, for the invention may admit to other equally effective embodiments.
Figure 1 discloses a line diagram of arrangement of sections of the device, according to a preferred embodiment.
Figure 2 detailed diagram of the architecture of the system platform is shown.
Figure 3 shows operational timing diagram for the WDSIP.

Detailed description of Invention:
Asthma and chronic obstructive pulmonary disease (COPD) are common around the World. Because of air pollution and other environmental factors, the prevalence of asthma and COPD continues to grow. In 2009, approximately 25 million people in US had asthma, and there were approximately 300 million asthma sufferers worldwide in 2007. Analyzing the spectral density and power of respiratory sounds such as wheezing can yield valuable information. Lung BRAM I/O and Data memory control IP FFT, IP Image Processing IP, FLASH/SRAM Memory UART GPIO Controller, wheeze detection SIP bus bridge arbiter D-Cache, BRAM I-Cache BRAM MicroBlaze Support Vector Machine (SVMs) classifier, Arbiter processor, local bus processor, local bus parenchyma and pathological modifications have often been treated as a crucial indicator of asthma and COPD. Current methods of diagnosing asthma include auscultation, spirometers, and determining peak expiratory flow to ascertain pulmonary conditions. Conventional stethoscope auscultation is safe and convenient, but also extremely subjective, and cannot be generalized; thus, using auscultation to recognize wheezing is dependent on how experienced the practicing physician is. Although spirometers are used to measure lungs, spirometers induce patient discomfort and are inappropriate for long-term monitoring. In contrast to traditional manual wheezing detection methods, the use of recording devices to collect and analyze lung sound have been extensively studied in recent years. The identification of abnormal lung sound characteristics using signal processing methods could help physicians to identify physiological mechanisms generated by lung sounds and their associated pathological links. However, these signal processing methods are objective, their use may also help to establish a classification system to accurately quantify normal and abnormal breath sounds. It has been medically proven that asthma is a chronic disease from which recovery is not possible. Asthma sufferers have a high risk of suffocation when their asthma is acute, and 250,000 annual deaths are attributed to the disease. Although, asthma can be controlled effectively by long-term medication and monitoring, most asthma sufferers are unaware of the condition of their own asthma, and often stop treatment by themselves, causing repeated inflammation and fibrosis in their respiratory tracts, and worsening their lung function. Therefore, the establishment of a portable system for rapid wheezing detection, able to send out a warning during acute asthma attacks, is necessary. Moreover, such a portable system could also be used in home care. Wheezes are abnormal respiratory sounds that occur for certain duration of time. According to computerized respiratory sound analysis (CORSA) standards, wheezing is characterized by its dominant frequency (more than 100 Hz) and duration (more than 100 ms). Most researchers have analyzed wheezing based on spectrograms, this is straightforward, and implementation is simple. However, spectrograms are vulnerable to noise disturbances, and can lack wheezing detection sensitivity. Certain approaches have thus been used to extract wheezing features, for example, classification models have been combined with algorithms, but this requires a large number of coefficients determined through training. This requires immense computational resources, which are not available on portable devices. Another method identified wheezing episodes using image processing to analyze the edges of spectrograms. However, this method is severely dependent on the resolution of the spectrogram in question. High-resolution spectrograms can be used to improve the sensitivity of this detection system, but also require substantial computational resources. Improving recognition accuracy thus often requires an immense number of computational resources, and is difficult to implement on portable devices. Therefore, most conventional automatic wheezing detection systems have been built using desktop computers. To implement an automatic wheezing detection system on a portable device, digital signal processors (DSPs) are commonly used. Although DSP has a high clock rate, DSP is inappropriate for wheezing detection because its computation process is based on sequential steps. Another method used a customized integrated circuit (IC) as a DSP coprocessor to detect rapid wheezing; this facilitated hardware acceleration and achieved real-time processing, but involved an immense number of computations. However, a customized IC for rapid wheezing detection is expensive, lacks flexibility, and is unable to be modified or integrated with other systems. Thus, the field-programmable gate array (FPGA) is ideally suited for building a portable rapid wheezing detection system. Such a portable system can be accelerated by applying an image processing algorithm using parallel computing hardware. The characteristics of wheezes in spectrogram can be treated as quasihorizontal lines with strong amplitude. Thus, there are many image processing techniques combined to preserve these characteristics and filter out unwanted noises. In order to achieve quick response to wheezing events, the frame blocking technique, which divides a spectrogram into sections of two seconds, can reduce responding time and demands of computing resources. Simultaneously, an optimal parameter set for support vector machine (SVM) model proposed in this research shows good accuracy and sensitivity of wheezing recognition. The proposed system is built as an independent wheezing detection silicon intellectual property (WDSIP), able to be integrated with other functional silicon intellectual properties (SIPs), e.g., universal asynchronous receiver/transmitter (UART), direct memory access (DMA), on system-on-programmable-chips (SoPCs) using the peripheral local bus (PLB) and MicroBlaze processor provided by Xilinx. This allows for greater portability and reduced system volume. In contrast to a customized IC, an FPGA can be modified repeatedly, and can be flexibly integrated with other SIPs.
Present invention provides a device for detection of wheezing in a patient, wherein said device comprises of a a display unit for indicating parameters of wheezing;a power source;a breathing sound detection unit configured to detect a breathing sound of a measurement subject and acquire a breathing sound signal in a time series expressing the breathing sound; tubes and wires for sending signals from sensing section to a processing chamber;wherein said processing chamber can process and detect the parameters of wheezing to be displayed on the display unit.

The device 100 of this invention shows the wheezing percentage. An end of the breathing sound detection unit 1is place inside the mouth to calculate the wheezing problem, which can be seen through the display2. The power and charging unit3is placed for providing power to the device 100.Tubes and wires 4are used to send signal from the breathing sound detection unit 1 to the processing chamber 5. Processing chamber 5is the system where the processing of the spectrogram for evaluation of the wheezing happens.
The processing flow of our wheezing recognition system is shown in Figure 2, and has following main steps:
• Preprocessing: A short-time Fourier transform (STFT) is used to acquire an image containing the time-frequency relationship of the wheezing sound (spectrogram).
• Forming an image mask from the spectrogram: noise is filtered using a bilateral filter and image processing methods such as edge detection, multi-threshold image segmentation, image morphological processing methods are used to detect wheezing. A sifting process using two rules based on CORSA standards is also applied to ensure that objects in the image mask are wheezes.
•Feature extraction and classification: features which represent the wheezing components on the masked spectrogram are extracted and classified using an SVM. Image processing of the spectrogram is the most crucial part of this process. Traditional methods directly analyze the edge of the spectrogram to detect wheezes, or check peak continuity using rules after the application of image processing techniques (e.g., mean filter).
The proposed system uses a combination of these two methods. Bilateral filtering is used to both smooth the image by removing outliers, and preserve strong image edge components by giving both spatial and photometric domains weighted coefficients. Edge detection and multi threshold segmentation are combined to preserve image edges and retain high and isolated peaks during analysis.

A WDSIP was designed to be able to communicate with other cores through the PLB. As shown in Figure 2, the number of read/write operations necessary during bilateral filtering and image mask formation was determined to be massive. Thus, in the proposed WDSIP, on-chip memory is used to store intermediate data to avoid overusing PLB bandwidth and slowing the processing speed. The WDSIP Sound Source FFT Spectrogram Limitor Bilateral Filter Multi-thresholds image segmentation forming masks by image close and open Sobel edge detector SVM classifier Features extraction Masking and labelling the image was designed to use a single PLB slave. MicroBlaze is used only to write the sound data to the WDSIP and read the recognized result from the control register on the memory map. The memory management and function of each register are shown in Figure 2. Using these control registers, the WDSIP can be controlled using the calling function to read/write the corresponding address on the memory map. MicroBlaze controls the WDSIP using only the reset register, therefore, a finite state machine (FSM) was designed to control the internal processing flow. MicroBlaze can only scan the “STATE” register to check whether the FSM has entered the SVM state, and determine whether the current value in the “RESULT” register is valid. After reading a valid value from the “RESULT” register, MicroBlaze clears the “RESULT” register to prevent the future reading of wrong values. According to the present invention, the FSM is based on the concept of the Moore machine, and its processing flow is shown in Figure 2. The red arrows represent the registers, which are mapped and controlled by using MicroBlaze, and other arrows represent the internal control signals of the WDSIP. When the external reset signal is set to “low,” the FSM will enter the Rcv_sound state, and the input FIFO receives external data sent from MicroBlaze. The FSM jumps to the next state only when the WDSIP has received a total data packets. The input FIFO was designed to be constantly able to receive data, because incoming data may be input at any time to the UART input buffer.
The operational timing diagram for the WDSIP is shown in Figure 3.

While the embodiments of the present invention have been disclosed above, but its use is not limited to the description set forth and described embodiments, which can be applied to various fields suitable for the present invention, for the person skilled in the art, can be easily realized a further modification, thus without departing from the generic concept claims and equivalents as defined by the scope of the present invention is not limited to the specific details shown and described herein with legend.