Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
11
datasets available to search
ShareScore release 0.9.0
Dataset results
11 results for “Fourier Process”
2012_2024_VIIRS_Fourier Processed_1k_ER
<h4>Overview:</h4> <p>This is a set of images produced by Temporal Fourier Analysis (TFA) of VIIRS data <strong>(New version updated until 2024)</strong>:</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p>The imagery summarises some key environmental indicators, incorporating seasonal dynamics, for the European and North African extent.<br>This series of VIIRS data, processed according to Scharlemann et al (2008), has been updated to include imagery from 2012 to 2024. </p> <h4>Process:</h4> <p>Image values were extracted from VIRRS imagery from 2012 to 2024. The day and night land temperature came from the 8-day VNP21A2 data, whilst the vegetation indices and Middle Infra Red values were extracted from the VNP13A2 16-day datasets. Each parameter extract dataset was then processed by a temporal Fourier processing algorithm. A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other outputs recorded the time series's mean, minimum, and maximum and the error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (<a href="https://doi.org/10.1371/journal.pone.0001408">https://doi.org/10.1371/journal.pone.0001408</a>)<br>Sea pixels were masked with a VIIRS land/sea layer, and the images were projected from sinusoidal to geographic. The E4warning study region was a subset of global images. Idrisi rasters were converted to GeoTIFF format in order to give data users more flexibility.</p> <p>This new VIIRS Dataset is used as an update and continuation of our MODIS TFA product and can be utilised similarly. </p> <p> </p> <p>Projection + EPSG code:<br>Latitude-Longitude/WGS84 (EPSG: 4326)</p> <p>Extent -32.0000000000000000,10.0000000000000000 : 68.9999999999999574,81.9999999999999716<br><br><br><strong>File names:</strong></p> <p><br>The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the E4warning study area and is in geographic projection. 24 refers to the year timeline of 2012-2024.<br><br>The next two characters identify the channel:<br>03 - middle infra-red<br>07 - daytime land surface temperature<br>08 - nighttime land surface temperature<br>14 - NDVI: Normalised Difference Vegetation Index<br>15 - EVI: Enhanced Vegetation Index<br><br>The last two characters of each file name denote the output from the Fourier processing:<br>a0 - mean<br>mn - minimum<br>mx - maximum<br>a1 - amplitude of annual cycle<br>a2 - amplitude of bi-annual cycle<br>a3 - amplitude of tri-annual cycle<br>p1 - phase of annual cycle<br>p2 - phase of bi-annual cycle<br>p3 - phase of tri-annual cycle<br>d1 - variance in annual cycle<br>d2 - variance in bi-annual cycle<br>d3 - variance in tri-annual cycle<br>da - combined variance in annual, bi-annual, and tri-annual cycles<br>vr - variance in raw data<br><br>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <h4>Global Files can be accessed <a title="VIIRS_TFA_1224" href="https://drive.google.com/drive/folders/117aWsu-Dy83Q4yRBCxWcTqnug-pRy8za?usp=sharing" target="_blank" rel="noopener">here</a>.</h4>
2001_2021_MODIS_Fourier Processed_1k_ER
<h4>Overview:</h4> <p>This is a set of images produced by Temporal Fourier Analysis (TFA) of MODIS data:</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p>The imagery summarises some key environmental indicators, incorporating seasonal dynamics, for The European and North African extent.<br>This series of version 6 MODIS data, processed according to Scharlemann et al (2008), has been updated to include imagery from 2001 to 2021. </p> <h4>Process:</h4> <p>Image values were extracted from MODIS imagery form 2001 to 2021. The day and night land temperature came from the 8 day MOD11A2 data whilst the vegetation indices and Middle Infra Red values were extracted from the MOD13A2 16 day datasets. Each parameter extract dataset was then processed by a temporal Fourier processing algorithm. A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other output recorded the mean, minimum, and maximum of the time series, and error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (<a href="https://doi.org/10.1371/journal.pone.0001408">https://doi.org/10.1371/journal.pone.0001408</a>)<br>Sea pixels were masked with a MODIS land/sea layer and the images were projected from sinusoidal to geographic. The E4warning study region was subset from global images. Idrisi rasters were converted to GeoTIFF format in order to give data users more flexibility.</p> <p>Projection + EPSG code:<br>Latitude-Longitude/WGS84 (EPSG: 4326)</p> <h4>File names:</h4> <p><br>The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the E4warning study area and is in geographic projection. 21 refers to the year timeline of 2001-2021.<br><br>The next two characters identify the channel:<br>03 - middle infra-red<br>07 - daytime land surface temperature<br>08 - nighttime land surface temperature<br>14 - NDVI: Normalised Difference Vegetation Index<br>15 - EVI: Enhanced Vegetation Index<br><br>The last two characters of each file name denote the output from Fourier processing:<br>a0 - mean<br>mn - minimum<br>mx - maximum<br>a1 - amplitude of annual cycle<br>a2 - amplitude of bi-annual cycle<br>a3 - amplitude of tri-annual cycle<br>p1 - phase of annual cycle<br>p2 - phase of bi-annual cycle<br>p3 - phase of tri-annual cycle<br>d1 - variance in annual cycle<br>d2 - variance in bi-annual cycle<br>d3 - variance in tri-annual cycle<br>da - combined variance in annual, bi-annual, and tri-annual cycles<br>vr - variance in raw data<br><br>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <h4>Global Files can be accessed <a href="https://tinyurl.com/tfamodis0121">here</a>. </h4>
2016_2018_VIIRS_Fourier Processed_1k_ER
<h4>Overview:</h4> <p>This is a set of images produced by Temporal Fourier Analysis (TFA) of VIIRS data:</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p>The imagery summarises some key environmental indicators, incorporating seasonal dynamics, for The European and North African extent.<br>This series of VIIRS data, processed according to Scharlemann et al (2008), has been updated to include imagery from 2016 to 2018 and was produced to compare with next three years' time series.</p> <h4>Process:</h4> <p>Image values were extracted from VIRRS imagery from 2016 to 2018. The day and night land temperature came from the 8 day VNP21A2 data whilst the vegetation indices and Middle Infra Red values were extracted from the VNP13A2 16-day datasets. Each parameter extract dataset was then processed by a temporal Fourier processing algorithm. A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other output recorded the time series's mean, minimum, and maximum, and error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (<a href="https://doi.org/10.1371/journal.pone.0001408">https://doi.org/10.1371/journal.pone.0001408</a>)<br>Sea pixels were masked with a VIIRS land/sea layer and the images were projected from sinusoidal to geographic. The E4warning study region was a subset of global images. Idrisi rasters were converted to GeoTIFF format in order to give data users more flexibility.</p> <p>This new VIIRS Dataset is used as an update and continuation of our MODIS TFA product and can be utilised in the same way. </p> <p> </p> <p>Projection + EPSG code:<br>Latitude-Longitude/WGS84 (EPSG: 4326)</p> <p><br><br><br><strong>File names:</strong></p> <p><br>The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the E4warning study area and is in geographic projection. 19 refers to the year timeline of 2016-2018.<br><br>The next two characters identify the channel:<br>03 - middle infra-red<br>07 - daytime land surface temperature<br>08 - nighttime land surface temperature<br>14 - NDVI: Normalised Difference Vegetation Index<br>15 - EVI: Enhanced Vegetation Index<br><br>The last two characters of each file name denote the output from Fourier processing:<br>a0 - mean<br>mn - minimum<br>mx - maximum<br>a1 - amplitude of annual cycle<br>a2 - amplitude of bi-annual cycle<br>a3 - amplitude of tri-annual cycle<br>p1 - phase of annual cycle<br>p2 - phase of bi-annual cycle<br>p3 - phase of tri-annual cycle<br>d1 - variance in annual cycle<br>d2 - variance in bi-annual cycle<br>d3 - variance in tri-annual cycle<br>da - combined variance in annual, bi-annual, and tri-annual cycles<br>vr - variance in raw data<br><br>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <h4> </h4>
2020_2022_VIIRS_Fourier Processed_1k_ER
<h4>Overview:</h4> <p>This is a set of images produced by Temporal Fourier Analysis (TFA) of VIIRS data:</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p>The imagery summarises some key environmental indicators, incorporating seasonal dynamics, for The European and North African extent.<br>This series of VIIRS data, processed according to Scharlemann et al (2008), has been updated to include imagery from 2020 to 2022 and was produced to compare with previous three years' time series.</p> <h4>Process:</h4> <p>Image values were extracted from VIRRS imagery form 2020 to 2022. The day and night land temperature came from the 8 day VNP21A2 data whilst the vegetation indices and Middle Infra Red values were extracted from the VNP13A2 16-day datasets. Each parameter extract dataset was then processed by a temporal Fourier processing algorithm. A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other output recorded the time series's mean, minimum, and maximum, and error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (<a href="https://doi.org/10.1371/journal.pone.0001408">https://doi.org/10.1371/journal.pone.0001408</a>)<br>Sea pixels were masked with a VIIRS land/sea layer and the images were projected from sinusoidal to geographic. The E4warning study region was a subset of global images. Idrisi rasters were converted to GeoTIFF format in order to give data users more flexibility.</p> <p>This new VIIRS Dataset is used as an update and continuation of our MODIS TFA product and can be utilised in the same way. </p> <p> </p> <p>Projection + EPSG code:<br>Latitude-Longitude/WGS84 (EPSG: 4326)</p> <p><br><br><br><strong>File names:</strong></p> <p><br>The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the E4warning study area and is in geographic projection. 19 refers to the year timeline of 2020</p> <p>-2022.<br><br>The next two characters identify the channel:<br>03 - middle infra-red<br>07 - daytime land surface temperature<br>08 - nighttime land surface temperature<br>14 - NDVI: Normalised Difference Vegetation Index<br>15 - EVI: Enhanced Vegetation Index<br><br>The last two characters of each file name denote the output from Fourier processing:<br>a0 - mean<br>mn - minimum<br>mx - maximum<br>a1 - amplitude of annual cycle<br>a2 - amplitude of bi-annual cycle<br>a3 - amplitude of tri-annual cycle<br>p1 - phase of annual cycle<br>p2 - phase of bi-annual cycle<br>p3 - phase of tri-annual cycle<br>d1 - variance in annual cycle<br>d2 - variance in bi-annual cycle<br>d3 - variance in tri-annual cycle<br>da - combined variance in annual, bi-annual, and tri-annual cycles<br>vr - variance in raw data<br><br>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <h4>Files can be accessed here as well. </h4>
2012_2014_VIIRS_Fourier Processed_1k_ER
<h4>Overview:</h4> <p>This is a set of images produced by Temporal Fourier Analysis (TFA) of VIIRS data:</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p>The imagery summarises some key environmental indicators, incorporating seasonal dynamics, for The European and North African extent.<br>This series of VIIRS data processed according to Scharlemann et al (2008), has been updated to include imagery from 2012 to 2014, and was produced to compare with next three years' time series,</p> <h4>Process:</h4> <p>Image values were extracted from VIRRS imagery from 2012 to 2014. The day and night land temperature came from the 8 day VNP21A2 data whilst the vegetation indices and Middle Infra Red values were extracted from the VNP13A2 16-day datasets. Each parameter extract dataset was then processed by a temporal Fourier processing algorithm. A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other output recorded the time series's mean, minimum, and maximum, and error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (<a href="https://doi.org/10.1371/journal.pone.0001408">https://doi.org/10.1371/journal.pone.0001408</a>)<br>Sea pixels were masked with a VIIRS land/sea layer and the images were projected from sinusoidal to geographic. The E4warning study region was a subset of global images. Idrisi rasters were converted to GeoTIFF format in order to give data users more flexibility.</p> <p>This new VIIRS Dataset is used as an update and continuation of our MODIS TFA product and can be utilised in the same way. </p> <p> </p> <p>Projection + EPSG code:<br>Latitude-Longitude/WGS84 (EPSG: 4326)</p> <p><br><br><br><strong>File names:</strong></p> <p><br>The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the E4warning study area and is in geographic projection. 14 refers to the year timeline of 2012-2014.<br><br>The next two characters identify the channel:<br>03 - middle infra-red<br>07 - daytime land surface temperature<br>08 - nighttime land surface temperature<br>14 - NDVI: Normalised Difference Vegetation Index<br>15 - EVI: Enhanced Vegetation Index<br><br>The last two characters of each file name denote the output from Fourier processing:<br>a0 - mean<br>mn - minimum<br>mx - maximum<br>a1 - amplitude of annual cycle<br>a2 - amplitude of bi-annual cycle<br>a3 - amplitude of tri-annual cycle<br>p1 - phase of annual cycle<br>p2 - phase of bi-annual cycle<br>p3 - phase of tri-annual cycle<br>d1 - variance in annual cycle<br>d2 - variance in bi-annual cycle<br>d3 - variance in tri-annual cycle<br>da - combined variance in annual, bi-annual, and tri-annual cycles<br>vr - variance in raw data<br><br>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <h4> </h4>
2001_2019_MODIS_Fourier Processed_1k_ER
<p><strong>Overview:</strong></p> <p>This is a set of images produced by Temporal Fourier Analysis of global MODIS data</p> <p>NDVI: Normalised Difference Vegetation Index</p> <p>EVI: Enhanced Vegetation Index</p> <p>MIR: Middle Infra-Red</p> <p>DLST: Day-time Land Surface Temperature</p> <p>NLST: Night-time Land Surface Temperature</p> <p> </p> <p><strong>Abstract: </strong></p> <p>MODIS is a sensor on board two NASA satellites, providing near-daily coverage of the entire Earth. The MOD11A2 product contains an 8-day average of land surface temperature at 1-kilometre resolution. Reflectance values have been adjusted to remove the distortion caused by the view angle and land surface texture. The MOD13A2 Product used for NDVI, EVI, and Middle Infra-red from USGS. The imagery summarises key environmental indicators, incorporating seasonal dynamics, for the MOOD study area.</p> <p>This is the original version of the 2001-2019 series, which was then processed by a temporal Fourier processing algorithm.</p> <p>A stepwise system of thresholds and interpolations screened erroneous values and bridged gaps in the time series. The smoothed series was sampled at 5-day intervals and transformed into a set of sine curves describing annual, bi-annual, and tri-annual fluctuations. For each of these curves, the Fourier algorithm generated images expressing the amplitude, phase, and variance. Other outputs recorded the mean, minimum, and maximum of the time series, and error measured during the Fourier transform. For a detailed description of the Fourier algorithm and its output, please see the article by Scharlemann et al., 2008 (https://doi.org/10.1371/journal.pone.0001408)<br> Sea pixels were masked with a MODIS land/sea layer and the images were projected from sinusoidal to geographic. The MOOD study region was a subset of global images. Idrisi rasters were converted to Geotiff format to give data users more flexibility<br> </p> <p><strong>File naming scheme:</strong></p> <p><br> The er at the start of each file name indicates that the image covers the wider Europe and North Africa region included in the MOOD study area and is in geographic projection. 19 refers to the year timeline of 2001-2019.<br> <br> The next two characters identify the channel:<br> 03 - middle infra-red<br> 07 - daytime land surface temperature<br> 08 - nighttime land surface temperature<br> 14 - NDVI: Normalised Difference Vegetation Index<br> 15 - EVI: Enhanced Vegetation Index<br> <br> The last two characters of each file name denote the output from Fourier processing:<br> a0 - mean<br> mn - minimum<br> mx - maximum<br> a1 - amplitude of annual cycle<br> a2 - amplitude of bi-annual cycle<br> a3 - amplitude of tri-annual cycle<br> p1 - phase of annual cycle<br> p2 - phase of bi-annual cycle<br> p3 - phase of tri-annual cycle<br> d1 - variance in annual cycle<br> d2 - variance in bi-annual cycle<br> d3 - variance in tri-annual cycle<br> da - combined variance in annual, bi-annual, and tri-annual cycles<br> vr - variance in raw data</p> <p><br><strong>Projection + EPSG code:</strong><br>Latitude-Longitude/WGS84 (EPSG: 4326)<br><strong>Spatial extent:</strong><br>Extent -32.0000000000000000,10.0000000000000000 : 68.9999999999999574,81.9999999999999716<br><strong>Spatial resolution:</strong><br>0.0083333 deg (approx. 1000 m) <br><strong>Temporal resolution:</strong><br> 8-day and 16-day from 2001 to 2019</p> <p><br><strong>Pixel values</strong></p> <p>Parameter Fourier Variable Image values are<br>MIR (03) A0, A1, A2, A3, Min, Max, Vr Reflectance values * 10000<br>LST (07 day,08 night) A0, A1, A2, A3, Min, Max, Vr (Degrees Centigrade+273)*50<br>NDVI (14) and EVI (15) A0, A1, A2, A3, Index Value * 1000<br>NDVI (14) and EVI (15) A0, Min, Max, Index Value * 1000 + 10000<br>NDVI (14) and EVI (15) VR Value * 10000<br>ALL D1,D2,D3,Da Percentages<br>ALL E1,E2,E3 Percentages<br>ALL P1,P2.P3 Months*100. (Jan=100)</p> <p><br><strong>Source: </strong><br>MODIS NASA :MOD11A2 and MOD13A2</p> <p><br><strong>Software used:</strong><br>Codes for modelling are in Python and C++<br>The software used for map production is ESRI ArcMap 10.8</p> <p><br><strong>License: </strong>CC-BY-SA 4.0<br><strong>Processed by:</strong><br>ERGO (Environmental Research Group Oxford) https://ergoonline.co.uk/ for the H2020 MOOD project</p>
BRAIN Journal-ANNSVM: A Novel Method for Graph-Type Classification by Utilization of Fourier Transformation, Wavelet Transformation, and Hough Transformation-Figure 3. Demonstrating the process of classification by applying the ANN, then the SVM
<p>Essentially, if the number of nodes in the hidden layers increases, processing time increases, and the resultant ANN will suffer from over-fitting. Conversely, too small of a number of hidden layers will cause under-fitting for the ANN. In our setting, the number of hidden layers and the number of nodes in each hidden layer were fixed at five. Concerning the learning rate and momentum settings, these impact sensitive training performances are set to optimal values obtained via a grid search technique. The number of nodes in the output layer was three because there are three different class labels (i.e., 2Dchart, bar, and pie) in our datasets. We used the ANN here because our datasets have nonlinear separation, and the ANN is also highly applicable to nonlinear modeling. Thus the ANN with multiple hidden layers was an optimal candidate; however, since the ANN is a black box learning approach, it is difficult to interpret implicit relationships between inputs and outputs.</p>
RAIN Journal-ANNSVM: A Novel Method for Graph-Type Classification by Utilization of Fourier Transformation, Wavelet Transformation, and Hough Transformation-Figure 4. Processes of all experiments:
<p>In this study, accuracy values of each dataset showed the performance of each method. These values represent are the proportion of the total number of predictions that were correctly classified. Initially, we classified training instances into three classes, with approximately 300 images per class. The graphs had been selectively gathered from the Web. We manually normalized the collected images by eliminating unused areas, such as unnecessary text. Moreover, we evaluated the experiments with 10 folds cross-validation because such an approach can mitigate the problem of over-fitting. </p>
BRAIN Journal-ANNSVM: A Novel Method for Graph-Type Classification by Utilization of Fourier Transformation, Wavelet Transformation, and Hough Transformation-Figure 2. Illustrating the core process of one-dimensional image construction by applying a DFT
<p>First, we collect graph images as raw data, which contain different scales and sizes, and therefore need to be normalized. We clean the images by omitting irrelevant areas. For example, we omit unnecessary text that has nothing to do with our classification procedure. Moreover, to standardize the sizes and shapes of the images, we resize and reshape them to be 64 x 64 squares. Second, we examine each image pixel, each of which contains one color value. After each pixel is projected along the x- and y-axes, we count the number of projected pixels with a color value greater than zero to reduce image dimensionality. We, therefore, obtain two one-dimensional images from the x- and y-axes. </p>
Dataset for article "Measurement report: Molecular characteristics of cloud water in southern China and insights into aqueous-phase processes from Fourier Transform Ion Cyclotron Resonance Mass Spectrometry"
<p>This dataset is the result of molecular composition of cloud water collected in southern China obtained by ESI FT-ICR MS. This dataset is for the article "Measurement report: Molecular characteristics of cloud water in southern China and insights into aqueous-phase processes from Fourier Transform Ion Cyclotron Resonance Mass Spectrometry" published in Atmospheric Chemistry and Physics by Sun et al. (2021).</p>
Dataset - Dissolved organic matter sources and processing in the endorheic Lake Nam Co catchment (Tibet) as assessed by ultra-high resolution Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS)
<p> </p> <p>Disclaimer 2022-01-04: Associated full text in preparation</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.