Difference between revisions of "ISSS608 2017-18 T3 Assign Chan En Ying Grace Methodology"
(11 intermediate revisions by the same user not shown) | |||
Line 32: | Line 32: | ||
R was the primary tool used in this analysis. SAS JMP Pro, Tableau and QGIS were also used to supplement the initial stage of the exploratory analysis. | R was the primary tool used in this analysis. SAS JMP Pro, Tableau and QGIS were also used to supplement the initial stage of the exploratory analysis. | ||
− | <br>The following lists the packages used for the project’s scope - for data cleaning, data visualisation, geospatial analysis and audio processing. | + | <br>The following lists the packages used for the project’s scope - for data cleaning, data visualisation, geospatial analysis and audio processing/classification. |
{| class="wikitable" style="background-color:#FFFFFF;" width="100%" | {| class="wikitable" style="background-color:#FFFFFF;" width="100%" | ||
|- | |- | ||
Line 61: | Line 61: | ||
**phonTools | **phonTools | ||
**seewave | **seewave | ||
+ | **randomForest | ||
+ | **rpart | ||
+ | **caret | ||
+ | **e1071 | ||
|- | |- | ||
|} | |} | ||
Line 67: | Line 71: | ||
==<font size="5"><font color="#000000">'''Approach Taken'''</font></font>== | ==<font size="5"><font color="#000000">'''Approach Taken'''</font></font>== | ||
− | The following outlines the | + | The following outlines the 7 key steps used for the analysis - Data Cleaning, Data Preparation, Geospatial Visualisation, Statistical Confirmation, Audio Processing, Audio Visualisation and Audio Classification. For the full codes, the R notebook is uploaded in the assignment folder. |
<div style="margin:0px; padding: 2px; background: #E6E6FA; font-family: Arial; border-radius: 1px; text-align:left"> | <div style="margin:0px; padding: 2px; background: #E6E6FA; font-family: Arial; border-radius: 1px; text-align:left"> | ||
Line 143: | Line 147: | ||
<b>v. Data Overview & Exploration</b> | <b>v. Data Overview & Exploration</b> | ||
− | * Overlay 2081 Birds, Raster Map & Dumping Site, for an integrated overview using | + | * Overlay 2081 Birds, Raster Map & Dumping Site, for an integrated overview using plot() |
− | * Use | + | * Use facet_wrap() to visualise location of clustering across species, across time, and across season, and by call/song in a trellis plot |
− | <b>vi. | + | <b>vi. Selection of Treatment & Control Groups</b> |
− | * Use ‘Rose Pipits’ as Treatment Group | + | * Use ‘Rose Pipits’ as Treatment Group |
− | * Use ‘Ordinary Snape’ and | + | * Use ‘Ordinary Snape’ and ‘Lesser Birchbeere’ as Control Groups to see if dumping were the cause |
− | * Use ‘All Birds’ as third control | + | * Use ‘All Birds’ as third control to see if external factors were the cause |
|- | |- | ||
Line 162: | Line 166: | ||
<b>i. Prepare polygon layer </b> | <b>i. Prepare polygon layer </b> | ||
* Create a 200x200 spatial polygon to depict the boundaries of Lekagul raster map | * Create a 200x200 spatial polygon to depict the boundaries of Lekagul raster map | ||
− | * Merge Raster Polygon with Rose Pipit Layer, using | + | * Merge Raster Polygon with Rose Pipit Layer, using owin() from spatstat package |
<b>ii. Kernel Density Plot </b> | <b>ii. Kernel Density Plot </b> | ||
− | * First, set sigma=bw.diggle | + | * First, set sigma=bw.diggle (Uses cross-validation to select a smoothing bandwidth for the kernel estimation of point process intensity) |
* Apply the Kernel Density Plot (By Year; 2012-2017) | * Apply the Kernel Density Plot (By Year; 2012-2017) | ||
** For All Birds | ** For All Birds | ||
Line 201: | Line 205: | ||
<b>iii. K-Function (Distance Based Measure) </b> | <b>iii. K-Function (Distance Based Measure) </b> | ||
* Apply Monti-Carlo simulation | * Apply Monti-Carlo simulation | ||
− | * Visualise significance based on | + | * Visualise significance based on confidence envelope |
+ | |||
+ | |||
+ | <b>iv. K-Cross (for bivariate analysis) </b> | ||
+ | * Apply Monti-Carlo simulation | ||
+ | * Visualise spatial dependence (significance) based on confidence envelope | ||
|- | |- | ||
Line 209: | Line 218: | ||
<b>Audio Processing</b> | <b>Audio Processing</b> | ||
|| | || | ||
− | <b>i. Data Preparation | + | <b>i. Data Preparation </b> |
* Read in MP3 Files (Training & Testing Data) | * Read in MP3 Files (Training & Testing Data) | ||
− | * Convert to .wav format using | + | * Convert to .wav format using writeWav() |
− | * Convert .wav files to data frame using | + | * Convert .wav files to data frame using analyzeFolder() |
* Read in data frame | * Read in data frame | ||
Line 237: | Line 246: | ||
|| | || | ||
<b>i. Amplitude Envelope Plot</b> | <b>i. Amplitude Envelope Plot</b> | ||
− | * Use | + | * Use env() to plot the envelopes of the amplitude plots |
* Do this for all the 15 test birds | * Do this for all the 15 test birds | ||
− | * Do this for 5 training birds per species and select most representative plot as | + | * Do this for 5 training birds per species and select most representative plot as ‘dictionary’ |
<b>ii. Oscillogram Plot</b> | <b>ii. Oscillogram Plot</b> | ||
− | * Use seewave package to plot | + | * Use seewave package to plot oscillogram |
* Do this for all the 15 test birds | * Do this for all the 15 test birds | ||
− | * Do this for 5 of the training birds, per species and select most representative plot as | + | * Do this for 5 of the training birds, per species and select most representative plot as ‘dictionary’ |
<b>iii. Distribution of audio parameters, using Trellis Plot</b> | <b>iii. Distribution of audio parameters, using Trellis Plot</b> | ||
− | * Out of the 15 attributes available after extracting the dataframe | + | * Run analyzeFolder() from soundgen library to the entire collections to extract dataframe from .wav files |
+ | * Find the acoustic parameters that are particularly relevant i.e. mean>standard deviation | ||
+ | * Out of the 15 <b>median</b> (mean and sd not used) attributes available after extracting the dataframe, the following 7 will be used for analysis as they produced greatest variation across species: | ||
** dom_median,HNR_median, meanFreq_median, peakFreq_median, pitch_median, pitchAutocor_median, pitchSpec_median | ** dom_median,HNR_median, meanFreq_median, peakFreq_median, pitch_median, pitchAutocor_median, pitchSpec_median | ||
* These were selected as they vary across the species more, than the other of the 8 variables | * These were selected as they vary across the species more, than the other of the 8 variables | ||
* Use ggplot() to plot a trellis plot using the 19 training species | * Use ggplot() to plot a trellis plot using the 19 training species | ||
− | * Label the mean | + | * Label the mean using black solid line |
− | * Use ggplot() to insert the 15 testing birds | + | * Use ggplot() to insert the 15 testing birds, with blue dotted line as the testing bird's mean |
− | * Visualise and identify the top 3 closest species, | + | * Visualise and identify the top 3 closest species to the mean, by parameter |
− | * Select the species based on no. of parameters closest to the | + | * Select the species based on most no. of parameters selected as closest |
+ | |- | ||
+ | | | ||
+ | 7. | ||
+ | || | ||
+ | <b>Audio Classification</b> | ||
+ | || | ||
+ | <b>i. Decision Tree</b> | ||
+ | * Use rpart, caret and e1071 libraries | ||
+ | * Using the extracted dataframe with analyzeFolder(), out of the 2081 birds, set 70% as training data, 30% as validation data | ||
+ | * Build decision tree model using training data. Evaluate misclassification rate. | ||
+ | * Apply model to 15 testing birds to predict the species | ||
+ | |||
+ | |||
+ | <b>ii. Random Forest</b> | ||
+ | * Use randomForest library to create a Random Forest model with default parameters | ||
+ | * Then we will fine tune the model by changing 'mtry' | ||
+ | * We can tune the random forest model by changing the number of trees (ntree) and the number of variables randomly sampled at each stage (mtry). | ||
+ | ** Ntree: Number of trees to grow. This should not be set to too small a number, to ensure that every input row gets predicted at least a few times. | ||
+ | ** Mtry: Number of variables randomly sampled as candidates at each split. Default value for classification is sqrt(p) where p is number of variables in x. | ||
+ | * Evaluate the RF's misclassification rate, with the Decision Tree | ||
+ | * Compare with visualisation plots, to see if the prediction matches | ||
|} | |} | ||
</div> | </div> | ||
− | Note: Frequency Analysis using the Fourier Transformation for a Spectrogram Plot comparison was attempted but did not produce good variation across the species. Pitch contour and pitch tracking with identified peaks also produced little variation in visualisations. These methods were hence dropped from this analysis | + | Note: Frequency Analysis using the Fourier Transformation, for a Spectrogram Plot comparison, was attempted but did not produce good variation across the species. Pitch contour and pitch tracking with identified peaks also produced little variation in visualisations. These methods were hence dropped from this analysis but the visualisations are made available in the R notebook for reference. |
<br> | <br> |
Latest revision as of 19:16, 30 June 2018
|
|
|
|
|
Tools
R was the primary tool used in this analysis. SAS JMP Pro, Tableau and QGIS were also used to supplement the initial stage of the exploratory analysis.
The following lists the packages used for the project’s scope - for data cleaning, data visualisation, geospatial analysis and audio processing/classification.
|
Approach Taken
The following outlines the 7 key steps used for the analysis - Data Cleaning, Data Preparation, Geospatial Visualisation, Statistical Confirmation, Audio Processing, Audio Visualisation and Audio Classification. For the full codes, the R notebook is uploaded in the assignment folder.
Step |
Approach |
Description |
1. |
Data Understanding |
i. Read in Raster Layer (Lekagul Roadways Map)
class : RasterLayer
|
2. |
Data Cleaning |
i. Import two CSV Files (Birds)
iii. Data Manipulation
|
3. |
Geospatial Visualisation |
Spatial Point Pattern Visualisation i. Prepare polygon layer
|
4. |
Statistical Confirmation |
Spatial Point Pattern Analysis & Cluster Confirmation i. Quadrat Analysis (Density Based Measure)
|
5. |
Audio Processing |
i. Data Preparation
|
6. |
Audio Visualisation |
i. Amplitude Envelope Plot
|
7. |
Audio Classification |
i. Decision Tree
|
Note: Frequency Analysis using the Fourier Transformation, for a Spectrogram Plot comparison, was attempted but did not produce good variation across the species. Pitch contour and pitch tracking with identified peaks also produced little variation in visualisations. These methods were hence dropped from this analysis but the visualisations are made available in the R notebook for reference.