This is a library of many hundreds of hours of wireless body area network (BAN) channel measurements of BAN radio channel transmit-receive link gain, featuring many different transmit-receive positions.The two VSA subfolders imply that a A National Instruments Vector Signal Analyzer (VSA) was used for the data measurements recorded in those subfolders.The wearable radio data was captured using a NICTA developed wearable channel sounder/radio.Please see Info.txt in sub-folders that can further describe the process, links, environment, carrier frequencies, measurement scenario, etc. for capturing body area network (BAN) channel gain data (majority on-body, but some off-body, none in-body).Except, where otherwise indicated the measurement environment for the Wearable radio data, is "Everyday" mixed-activity data denoting a range of person-wearing-radio measurement locations.All data is stored in Matlab binary .mat files as structs which when loaded contains one struct named "data". Most fields in the data struct, labeled 'pl*' represent a particular Tx/Rx link, containing a contiguous data-series of negative path loss in dB, which is equivalent to channel gain (magnitude) in dB.To open the file .mat file, type load filename (whatever the file name is for the particular data) at the Matlab command prompt.To access any field's data in the "data" struct, type data.fieldname (whatever the fieldname is) at the Matlab command prompt.In the VSA folders all fields are the BAN Tx/Rx link data, whereas in the wearable_radio folders the first three fields, which are the same for all data in these folders are:-carrier_frequency (in Hz)-fs (packets per second across whole wearable radio network being measured - not necessarily the channel gain sampling rate for a particular link, please see relevant "info.txt" in each particular sub-folder for more details) and -tx_power in dBm.Across all measurements there were 22 adult subjects used to capture this BAN channel data. In each .mat file filename, each adult subject is referred to anonymized, with gender, i.e. Male or Female, followed by a number identifier. Thus, e.g., any filename that contains "Male1" implies the BAN link data captured for the same male person accross all filenames containing "Male1", similar for "Female1", "Male2", etc...The first 8 characters of each .mat filename refer to the date on which the particular data was collected, i.e., "20081030" implies the data was collected on 30-October-2008.Each Tx/Rx link field in the .mat data is referred to with *_Txlocation_Rxlocation in the fieldname.Please also note that in all of the wearable_radio data when the channel power dropped below receiver sensitivity of the wearable radio, the path loss data value is recorded as not-a-number NAN. (A NAN is generally recorded when the channel gain drops below -100 dB in the wearable radio data here).However the measurement process for the VSA was sufficiently sensitive to capture all values of channel gain data (hence there are no NANs in this data).

This is one of two collection records. Please see the link below for the other collection of associated text files.The two collections together comprise an open clinical dataset of three sets of 10 nursing handover records, very similar to real documents in Australian English. Each record consists of a patient profile, spoken free-form text document, written free-form text document, and written structured document.This collection contains 3 X 100 spoken free-form audio files in WAV

This is one of two collection records. Please see the link below for the other collection of associated audio files.Both collections together comprise an open clinical dataset of three sets of 101 nursing handover records, very similar to real documents in Australian English. Each record consists of a patient profile, spoken free-form text document, written free-form text document, and written structured document.This collection contains 3 sets of text documents.Data Set 1 for Training and DevelopmentThe data set, released in June 2014, includes the following documents:Folder initialisation: Initialisation details for speech recognition using Dragon Medical 11.0 (i.e., i) DOCX for the written, free-form text document that originates from the Dragon software release and ii) WMA for the spoken, free-form text document by the RN)Folder 100profiles: 100 patient profiles (DOCX)Folder 101writtenfreetextreports: 101 written, free-form text documents (TXT)Folder 100x6speechrecognised: 100 speech-recognized, written, free-form text documents for six Dragon vocabularies (TXT)Folder 101informationextraction: 101 written, structured documents for information extraction that include i) the reference standard text, ii) features used by our best system, iii) form categories with respect to the reference standard and iv) form categories with respect to the our best information extraction system (TXT in CRF++ format).An Independent Data Set 2The aforementioned data set was supplemented in April 2015 with an independent set that was used as a test set in the CLEFeHealth 2015 Task 1a on clinical speech recognition and can be used as a validation set in the CLEFeHealth 2016 Task 1 on handover information extraction. Hence, when using this set, please avoid its repeated use in evaluation – we do not wish to overfit to these data sets.The set released in April 2015 consists of 100 patient profiles (DOCX), 100 written, and 100 speech-recognized, written, free-form text documents for the Dragon vocabulary of Nursing (TXT). The set released in November 2015 consists of the respective 100 written free-form text documents (TXT) and 100 written, structured documents for information extraction.An Independent Data Set 3For evaluation purposes, the aforementioned data sets were supplemented in April 2016 with an independent set of another 100 synthetic cases.