Projects:2019s2-22702 Barkbusters 2.0 - Revision history

A1761292 at 00:00, 9 June 2020

2020-06-09T00:00:01Z

A1750914 at 10:48, 8 June 2020

2020-06-08T10:48:42Z

A1750914 at 10:45, 8 June 2020

2020-06-08T10:45:55Z

A1761292: /* Results conclusion */

2020-06-07T20:43:00Z

‎Results conclusion

A1761292 at 20:41, 7 June 2020

2020-06-07T20:41:49Z

A1750914 at 13:37, 7 June 2020

2020-06-07T13:37:07Z

A1750914 at 12:10, 7 June 2020

2020-06-07T12:10:47Z

A1750914 at 15:11, 5 June 2020

2020-06-05T15:11:45Z

A1750914 at 14:55, 5 June 2020

2020-06-05T14:55:34Z

A1750914 at 13:52, 5 June 2020

2020-06-05T13:52:02Z

@@ Line 159: / Line 159: @@
 The classifier can identify the dog barks from human speaks with the accuracy close to 100%.
-The time-domain and spectral-domain features are successfully extracted from Diagnostic Feature Designer App. The MATLAB generated Naive Bayes Classifier works with an accuracy of 78% of accuracy. The k-means Clustering algorithm clusters the data fairly good. The GMM Clustering did not work on the collected dataset.
+The time-domain and spectral-domain features are successfully extracted from Diagnostic Feature Designer App. The MATLAB generated Naive Bayes Classifier works with an accuracy of 78%. The k-means Clustering algorithm clusters the data fairly good. The GMM Clustering did not work on the collected data set.
 The device can save recordings with time labels which are identified as dog barks. It can upload recordings to a cloud disk at anytime. Users can get access to the dog bark recordings online and free to download.

@@ Line 68: / Line 68: @@
 K-means clustering is an unsupervised machine learning algorithm which looks for a fixed number of clusters(k) in the data like automatic speech recognition. K-means algorithm identifies k number of centroids and allocates each data point to the nearest cluster by an iteration process until the centroids meet a convergence criterion[9].
 === Software Development (Model Training) ===
@@ Line 142: / Line 143: @@
 <center> Figure 7. Confusion matrix of a Naive Bayes Classifier</center>
 === K-means Clustering ===
- Clustering is performed using k-means algorithm with both the datasets, one with the original extracted feature dataset and the other with the principal components from PCA.
 [[File:K-Means1.png|500px|Image:500pixels|center]]
 <center> Figure 8. Clustering using principal components with K-means Algorithm </center>

@@ Line 36: / Line 36: @@
 This section introduced the background theory, hardware implementation and software implementation of the project.
 === Background theory ===
@@ Line 49: / Line 57: @@
 A Gaussian Mixture Model (GMM) is a parametric probability density function represented as a weighted sum of Gaussian component densities. GMMs are commonly used as a parametric model of the probability distribution of continuous measurements or features in a biometric system, such as vocal tract related spectral features in a speaker recognition system. GMM parameters are estimated from training data using the iterative Expectation-Maximization (EM) algorithm or Maximum A Posteriori (MAP) estimation from a well-trained prior model. [7]
-=== '' Diagnostic Feature Designer App '' ===
+==== '' Diagnostic Feature Designer App '' ====
 The time domain and spectral domain features of the audio data samples are extracted using Diagnostic feature designer app in MATLAB. The features extracted include shape factor, clearance factor, kurtosis etc. The generated features can be exported to MATLAB workspace to be used as inputs for Classification algorithms.
-=== '' Naive Bayes Classifier '' ===
+==== '' Naive Bayes Classifier '' ====
 Naive Bayes Classifier is a type of supervised machine learning algorithm which assumes that the features are statistically independent. The probability of each class is estimated using Bayes rule and the class with highest probability is the outcome of the algorithm. This classifier can be used to  train large datasets within short computational time. This is the simplest algorithm used in speech recognition systems[8].
-=== '' K-Means Clustering '' ===
+==== '' K-Means Clustering '' ====
 K-means clustering is an unsupervised machine learning algorithm which looks for a fixed number of clusters(k) in the data like automatic speech recognition. K-means algorithm identifies k number of centroids and allocates each data point to the nearest cluster by an iteration process until the centroids meet a convergence criterion[9].
@@ Line 92: / Line 100: @@
 ==== '' Prototype photo '' ====
-[[File:PrototypePhoto.png|center|Figure 1. Prototype photo]]
+[[File:PrototypePhoto.png|700px|Image:700pixels|center]]
-<center>Figure 1. Prototype photo</center>
+<center>Figure 2. Prototype photo</center>
 == Results ==
@@ Line 102: / Line 110: @@
 === Automatically recording and records saving ===
-With the USB microphone plugged in, the python program can directly run for recording. For the test, we set the volume threshold to 4000. Two dog bark recoding samples and two human speaking recording samples are chosen to be used. One of the dog bark recording samples is from a small dog, the other one is from a large one. One of the human speaking recording samples is from myself (male), the other one is from my colleague Nityasri (female). The volumes of these recording samples are adjusted to the same level by human hearing. The test result is shown in Figure 2.
+With the USB microphone plugged in, the python program can directly run for recording. For the test, we set the volume threshold to 4000. Two dog bark recoding samples and two human speaking recording samples are chosen to be used. One of the dog bark recording samples is from a small dog, the other one is from a large one. One of the human speaking recording samples is from myself (male), the other one is from my colleague Nityasri (female). The volumes of these recording samples are adjusted to the same level by human hearing. The test result is shown in Figure 3.
 [[File:DistanceTest.png|700px|Image:700pixels|center]]
-<center>Figure 2. The test results for recording at different distances</center>
+<center>Figure 3. The test results for recording at different distances</center>
 === Sound classification ===
@@ Line 114: / Line 122: @@
 [[File:ConfusionMatrix.png|500px|Image:500pixels|center]]
-<center>Figure 3. Confusion matrix of classification tests</center>
+<center>Figure 4. Confusion matrix of classification tests</center>
 === Recordings saving and uploading ===
-If a sound sample is identified as a dog bark, it will be stored in a specific folder in the Raspbian system with time labels which is shown in Figure 4.
+If a sound sample is identified as a dog bark, it will be stored in a specific folder in the Raspbian system with time labels which is shown in Figure 5.
-[[File:LocalStorage.png|900px|Image:900pixels|center]]
+[[File:LocalStorage.png|700px|Image:700pixels|center]]
-<center>Figure 4. Recordings saved in local storage</center>
+<center>Figure 5. Recordings saved in local storage</center>
 It is set that to upload all files to the cloud disk at 10.05 am. The figure shows the file list in the cloud disk.
-[[File:CloudDiskStorage.png|500px|Image:500pixels|center]]
+[[File:CloudDiskStorage.png|700px|Image:700pixels|center]]
-<center>Figure 5. Recording saved in cloud disk</center>
+<center>Figure 6. Recording saved in cloud disk</center>
-== Naive Bayes Classifier==
+=== Naive Bayes Classifier===
-A data sample of 2000 sample is taken as the input of the Naïve Bayes classifier with one class consisting of 1000 dog bark sounds and another class with the rest 1000 samples which consists of other environmental sounds. The confusion matrix of Naïve Bayes classifier is shown in the figure 6 below.
+A data sample of 2000 sample is taken as the input of the Naïve Bayes classifier with one class consisting of 1000 dog bark sounds and another class with the rest 1000 samples which consists of other environmental sounds. The confusion matrix of Naïve Bayes classifier is shown in the figure 7 below.
-[[File:Confusionmatrix.png|26KBpx|center|900pixels]]
+[[File:Confusionmatrix.png|700px|Image:700pixels|center]]
-<center> Figure 6. Confusion matrix of a Naive Bayes Classifier</center>
+<center> Figure 7. Confusion matrix of a Naive Bayes Classifier</center>
-== K-means Clustering ==
+=== K-means Clustering ===
   Clustering is performed using k-means algorithm with both the datasets, one with the original extracted feature dataset and the other with the principal components from PCA.
-[[File:K-Means1.png|center|PCA]]
+[[File:K-Means1.png|500px|Image:500pixels|center]]
-<center> Figure 7. Clustering using principal components with K-means Algorithm </center>
+<center> Figure 8. Clustering using principal components with K-means Algorithm </center>
-[[File:K-Means2.png|center]]
+[[File:K-Means2.png|500px|Image:500pixels|center]]
-<center> Figure 8. Clustering using original features with K-means algorithm </Center>
+<center> Figure 9. Clustering using original features with K-means algorithm </Center>
 == Conclusion ==
@@ Line 154: / Line 162: @@
 === Future work ===
-==== ‘’Sound signal amplifier‘’ ====
+==== ''Sound signal amplifier'' ====
 From the results gained in the testing section, the device has no recording capability for sound far away. In the future development it may consider to add a sound amplifier. One of the methods of amplifying the sound volume is linear amplification. The linear sound signal amplifier is basically the volume amplifier. The function can be described as following steps.
@@ Line 160: / Line 168: @@
 The first step is to set the threshold to a very low value to assure a piece of voice with low volume (long distance away) can be recorded. The second step is to load the sound sample into the digital signal. The third step is to multiply the original signal by a amplification factor. It should be noticed that the amplication factor should be calculated based on the amplitude of the original signal to avoid the distortion of the sound. It is considered to calculate the factor using multiple of the amplitude.
-==== ‘’Identification of an individual dog‘’ ====
+==== ''Identification of an individual dog'' ====
 Since the model training is performed on board, the training sound database cannot be too large. The calculating speed is limited for the Raspberry Pi 4b, it will take more than 5 times of the calculating time of a PC. Thus, a better model can be trained on a PC by enlarging the database.

@@ Line 148: / Line 148: @@
 The classifier can identify the dog barks from human speaks with the accuracy close to 100%.
-The time-domain and spectral-domain features are successfully extracted from Diagnostic Feature Designer App. The MATLAB generated Naive Bayes Classifier works with an accuracy of 78% of accuracy. The k-means Clustering algorithm clusters the data fairly good. The GMM Clustering did not work on the system.
+The time-domain and spectral-domain features are successfully extracted from Diagnostic Feature Designer App. The MATLAB generated Naive Bayes Classifier works with an accuracy of 78% of accuracy. The k-means Clustering algorithm clusters the data fairly good. The GMM Clustering did not work on the collected dataset.
 The device can save recordings with time labels which are identified as dog barks. It can upload recordings to a cloud disk at anytime. Users can get access to the dog bark recordings online and free to download.
 === Future work ===

@@ Line 19: / Line 19: @@
 === Objectives ===
-This project aims to develop a small field deployable device.
+This project aims to develop a small field deployable device which automatically detects the an individual dog bark from other ambient sounds in the environment and stores it in the storage space of the device..
 == Background ==
@@ Line 35: / Line 35: @@
 == Method ==
-This section introduced the background theory and hardware implementation.
+This section introduced the background theory, hardware implementation and software implementation of the project.
 === Background theory ===
@@ Line 48: / Line 48: @@
 A Gaussian Mixture Model (GMM) is a parametric probability density function represented as a weighted sum of Gaussian component densities. GMMs are commonly used as a parametric model of the probability distribution of continuous measurements or features in a biometric system, such as vocal tract related spectral features in a speaker recognition system. GMM parameters are estimated from training data using the iterative Expectation-Maximization (EM) algorithm or Maximum A Posteriori (MAP) estimation from a well-trained prior model. [7]
 === Hardware selection ===
@@ Line 53: / Line 70: @@
 ==== '' Raspberry Pi 4b '' ====
-Raspberry Pi 4 Model B is the latest product in the popular Raspberry Pi range of computers. This version beats the Raspberry Pi in the following aspects [8]:
+Raspberry Pi 4 Model B is the latest product in the popular Raspberry Pi range of computers. This version beats the Raspberry Pi in the following aspects [10]:
 *Broadcom BCM2711, Quad-core Cortex-<u>A72</u> (ARM v8) 64-bit SoC @ <u>1.5GHz</u>.
@@ Line 112: / Line 129: @@
 <center>Figure 5. Recording saved in cloud disk</center>
 == Conclusion ==
@@ Line 120: / Line 148: @@
 The classifier can identify the dog barks from human speaks with the accuracy close to 100%.
 The device can save recordings with time labels which are identified as dog barks. It can upload recordings to a cloud disk at anytime. Users can get access to the dog bark recordings online and free to download.
 === Future work ===
@@ Line 150: / Line 180: @@
 [7] L. Baum er al., A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains, Ann. Math Srar., vol. 41, pp. 164-171, 1970.
-[8] “Raspberry Pi 4 vs Raspberry Pi 3B+”（https://magpi.raspberrypi.org/articles/raspberry-pi-4-vs-raspberry-pi-3b-plus）
+[8] S. B. Kotsiantis, “Supervised machine learning: a review of classification techniques,” informatica, vol. 31, no. 3, p. 249(20), october 2007

@@ Line 64: / Line 64: @@
 *5V DC via <u>USB-C</u> connector (minimum 3A*).
 ==== '' USB microphone '' ====
@@ Line 76: / Line 74: @@
 ==== '' Prototype photo '' ====
-[[File:PrototypePhoto.png|frame|none|Figure 1. Prototype photo]]
 == Results ==
-With the USB microphone plugged in, the python program can directly run for recording. For the test, we set the volume threshold to 4000. Two dog bark recoding samples and two human speaking recording samples are chosen to be used. One of the dog bark recording samples is from a small dog, the other one is from a large one. One of the human speaking recording samples is from myself (male), the other one is from my colleague Nityasri (female). The volumes of these recording samples are adjusted to the same level by human hearing. The test result is shown as Figure 2.
+This section shows the testing results of the product prototype. Functions such as automatically recording, identifying and saving are tested.
-[[File:DistanceTest.png|frame|none|Figure 2. The test results for recording at different distances]]
+=== Recordings saving and uploading ===
 == Conclusion ==
 == References ==

@@ Line 39: / Line 39: @@
 === Background theory ===
-====Mel Frequency Cepstral Coefficients (MFCCs)====
+==== '' Mel Frequency Cepstral Coefficients (MFCCs) '' ====
 MFCC is one of the methods for extracting speech feature parameters. Because of its unique cepstrum-based extraction method, it is more in line with human auditory principles, and thus is the most common and effective speech feature extraction algorithm. The MFCC is a cepstral coefficient extracted from the Mel scale frequency domain. Since humans have a very accurate sense of sound, they can distinguish between different sound sources by their timbre.
@@ Line 45: / Line 45: @@
 The Mel scale exactly describes the nonlinear characteristics of the human ear's perception of frequency to simulate the human's accurate discrimination of timbre [6].
-==== Gaussian Mixture Model (GMM) ====
+==== '' Gaussian Mixture Model (GMM) '' ====
 A Gaussian Mixture Model (GMM) is a parametric probability density function represented as a weighted sum of Gaussian component densities. GMMs are commonly used as a parametric model of the probability distribution of continuous measurements or features in a biometric system, such as vocal tract related spectral features in a speaker recognition system. GMM parameters are estimated from training data using the iterative Expectation-Maximization (EM) algorithm or Maximum A Posteriori (MAP) estimation from a well-trained prior model. [7]
@@ Line 51: / Line 51: @@
 === Hardware selection ===
 == Results ==
@@ Line 76: / Line 107: @@
 [7] L. Baum er al., A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains, Ann. Math Srar., vol. 41, pp. 164-171, 1970.
-[8]
+[8] “Raspberry Pi 4 vs Raspberry Pi 3B+”（https://magpi.raspberrypi.org/articles/raspberry-pi-4-vs-raspberry-pi-3b-plus）

@@ Line 4: / Line 4: @@
 == Introduction ==
-=== Project descroption ===
+=== Project description ===
 Bark busters 2.0 is designed not to control the barking of the dog but to log the barking activity of a specific animal. This can be used as proof by the person who is facing a nuisance due to a specific animal and make a complaint to the concerned officer. This is a simple solution to collect proof against a disturbing animal.
 When dealing with dogs, there are legal issues that need to be considered. Legally, the person owning the dog is solely responsible for the control of the dog is guilty of an offence if a dog” creates a noise, by barking or otherwise, which persistently occurs or continues to such a degree or extent that unreasonably interferes with the peace or convenience of a person.” Bark busters 2.0 helps the person facing inconvenience with a specific animal to collect proof against it and complaint to the concerned officer.
@@ Line 37: / Line 37: @@
 This section introduced the background theory and hardware implementation.
-==== Project students ====
+=== Background theory ===
-* Mingde Jiang
-* Nityasri Gallennagari
+====Mel Frequency Cepstral Coefficients (MFCCs)====
-==== Supervisors ====
-* Prof. Langford White
+MFCC is one of the methods for extracting speech feature parameters. Because of its unique cepstrum-based extraction method, it is more in line with human auditory principles, and thus is the most common and effective speech feature extraction algorithm. The MFCC is a cepstral coefficient extracted from the Mel scale frequency domain. Since humans have a very accurate sense of sound, they can distinguish between different sound sources by their timbre.
-* Dr. Brian Ng
@@ Line 65: / Line 71: @@
 [5] Online post: “Any Good Android Recorders to Prove a Barking Dog?” (https://www.ozbargain.com.au/node/373772)

@@ Line 26: / Line 26: @@
 The standard program of the Campbelltown City Council [3] dealing with complaints about the dog barks is to provide a Barking Dog pack which includes a diary for complainants to record the barking activity. The following action is once there is sufficient evidence in the diary, the council will contact the dog owner to rectifier the situation and perform a 14 days monitor. If the circumstances have not improved, the council will review information collected from nearby residents to determine whether a further action will be performed. If it can be established that the noise is persistent and is an unreasonable interference, the council will take action, however, civil action by those effected is also possible.
-However, the only solution currently available to the disturbed residents is to buy a recorder with enough storage space and power [4]. They are suggested to turn the recorder on and leave it in the yard under a shelter cover. “Just leave it under cover outside recording for whatever periods you want and download the audio files from it. Don't do more than a few hours at a time or it's just too big a file to easily deal with.”, said by Zambuck, a replier to this complaint.
+However, the only solution currently available to the disturbed residents is to buy a recorder with enough storage space and power [4]. They are suggested to turn the recorder on and leave it in the yard under a shelter cover. “Just leave it under cover outside recording for whatever periods you want and download the audio files from it. Don't do more than a few hours at a time or it's just too big a file to easily deal with.”, said by Zambuck, a replier to this complaint [5].
-[[Image:Wiki.png|中文维基]]
+This method has two main problems. The first one is that the recorder is way too expensive to be used only for complaint proof collecting. People maybe not willing to pay that much for others fault. The second defect is a recorder cannot identify whether the barking belongs to an individual dog. This gives the dog owner opportunity to argue that the barking recorded is not from his or her dog.
 == Method ==
@@ Line 40: / Line 42: @@
 == References ==
-[1] “Barking dogs, crowing roosters and screeching cats top noise complaints list in Brisbane” (https://www.abc.net.au/news/2017-10-19/most-common-noise-complaints-brisbane-and-what-to-do-about-it/9059182 Last access time 1/Jun/2020)
+[1] “Barking dogs, crowing roosters and screeching cats top noise complaints list in Brisbane” (https://www.abc.net.au/news/2017-10-19/most-common-noise-complaints-brisbane-and-what-to-do-about-it/9059182)
 [2] Dog and Cat Management Act 1995, 45A (5).
-[3] “Barking Dog Information Pack” (https://www.campbelltown.sa.gov.au/__data/assets/pdf_file/0027/236961/Barking-Dog-Information-Pack.pdf Last access time 1/Jun/2020)
-[4] Online post: “Any Good Android Recorders to Prove a Barking Dog?” (https://www.ozbargain.com.au/node/373772 Last access time 23/May/2020)
+[3] “Barking Dog Information Pack” (https://www.campbelltown.sa.gov.au/__data/assets/pdf_file/0027/236961/Barking-Dog-Information-Pack.pdf)