Indoor positioning systems based on radio frequency systems such as UWB inherently present multipath related phenomena. This causes ranging systems such as UWB}to lose accuracy by detecting secondary propagation paths between two devices. If a positioning algorithm uses ranging measurements without considering these phenomena, it will make important errors in estimating the position. This work analyzes the performance obtained in a localization system when combining location algorithms with machine learning techniques for a previous classification and mitigation of the propagation effects.
Please, if you use this dataset in your research activities, please add a reference to our related paper:
Barral, V.; Escudero, C.J.; García-Naya, J.A.; Suárez-Casal, P. Environmental Cross-Validation of NLOS Machine Learning Classification/Mitigation with Low-Cost UWB Positioning Systems. Sensors 2019, 19, 5438. https://doi.org/10.3390/s19245438
These are Matlab files.
The measurements were recorded in the scenario shown in the figure.
Three configurations where used:
- "h0_front" contains the measurements with the tag facing North at the same height than the anchors.Height = 1.28m.
- "h0_back.mat " includes the measurements with the tag facing South at the same height than the anchors. Height = 1.28m.
- "h1_front" includes the measurements with the tag facing North at a higher altitude than the anchors. Tag Height = 2.05m. Anchors Height = 1.28m.
How to use:
h0_front = load('h0_front.mat');
h0_back = load('h0_back.mat');
h1_front = load('h1_front.mat');
"h0_front" contains the measurements with the tag facing North at the same height than the anchors.
"h0_back.mat " includes the measurements with the tag facing South at the same height than the anchors.
"h1_front" includes the measurements with the tag facing North at a higher altitude than the anchors.
The file contains 3 arrays:
- beacons (1x5 struct) Contains the coordinates of each of the 5 anchors.
- pos (1x9 struct) Contains the coordinates of the 9 measurement points.
- ranging (1x9 struct) Each row contains the measurements from one of the 9 positions of the array. The struct includes:
- range (Nx1) int64. The value outputted by the device. In cm.
- rxPower (Nx1) double. The received power strength. In dBm.
- timestamp (Nx1) double. Measurement timestamp. In unix time.
- angle (Nx1) double. Not used in this set.
- destinationId (Nx1) int64. The index of the anchor
A set of datasets (Excel files since it also contains dynamically generated images) to facilitate the reproducibity of the test performed for the evaluation of the FDS proposal
Description: The set of datasets used for the paper in order to get the graphics that summarize the results from these datasets.Size: 293 KBPlatform: Microsoft Excel 365Environment: Any running MS Excel (Linux, Windows, MacOS)Major Component Description: 3 files are provided, each corresponding to a different dataset(s) with several sheet.1. "Comm latency": contains datasets and figures related with the data obtained when evaluating the communication latency of the proposal and the Amazon Cloud service one. · "Measures FDS": sheet that contain the data obtained when evaluating the communication latency of the proposal (FDS) · "Measures Cloud": sheet that contain the data obtained when evaluating the communication latency of Amazon Cloud service · "Comparison": a sheet containing a dynamic figure for comparing the data of the other two sheets2. "Power consumption": the largest dataset. It contains the samples for different situations regarding power consumption in the sensor nodes when using FDS or when running as they normally do (without storing any kind of data) ·Idle (DTIM1) naked 3,3V: sheet contains the samples for the "base" power consumption of a "bare-mounted" ESP8266 avoiding a programmer IC and a voltage regulator. Constant current was provided using an external power generator ·TX no SD card: sheet contains the power consumption data while transmitting when FDS is not used (no SD data storage is performed) ·RX no SD card: sheet contains the power consumption data while receiving when FDS is not used (no SD data storage is performed) ·RXTX no SD card: sheet contains the power consumption data while transmitting and receiving when FDS is not used (no SD data storage is performed) ·TX with SD card: sheet contains the power consumption data while transmitting when FDS is used (SD data storage is performed) ·RX with SD card: sheet contains the power consumption data while receiving when FDS is used (SD data storage is performed) ·RXTX with SD card: sheet contains the power consumption data while transmitting and receiving when FDS is used (SD data storage is performed) ·Comparison: sheet including the dynamic figure generated from the other sheets3. "Network overload": contains datasets and figures related with the data obtained when evaluating the network overload of the proposal and the Amazon Cloud service one (best and worst scenario). · Received: sheet contains number of messages for different replicates configuration in FDS as well as counts for the number of messages for the best and worst case for Amazon regarding messages received. · Sent: sheet contains number of messages for different replicates configuration in FDS regarding messages sent.Detailed Set-up Instructions: Unzip and open the files with MS ExcelContact Information: for additional information about these datasets, contact Marino Linaje, the corresponding author (email@example.com)
The dataset contains information about roses cultivation in greenhouses. It is aimed at identifying corrective actions to improve the roses state. Data acquisition was done with an autonomous robot incorporating sensors such as: soil humidity, light, temperature and humidity, and CO2.
1. Title: Roses greenhouse cultivation database repository (RosesGreenhDB)
Updated 17/07/2019 by Wilmer A. Champutiz
(a) Creators: Edison A. Fuentes-Hernández and Paul D. Rosero-Montalvo
(b) Date: July 2019
3. Relevant Information:
The present dataset contains information about roses cultivation in greenhouses.
It is aimed at identying corrective actions to improve the roses state.
Correspondingly, the target variables (labels) are as follows:
1 Soil without water
2 Environment correct
3 Too much hot
4 very cold
Data acquisition was done with an autonomous robot incorporating sensors such as: soil humidity, light, temperature and humidity, and CO2. Resulting dataset is imblanced.
4. Number of Instances: 300 (125 soil without water
28 correct environment
90 too much hot
57 very cold)
5. Number of Attributes: 5 numeric predictive attributes and the class
6. Attribute Information:
1. Soil humidity in analog-digital conversion
2. Light in lux
3. Temperature in °C
4. CO2 in analog-digital conversion
5. Humidity relative
1 soil without water
2 environment correct
3 too much hot
4 very cold
7. Missing Attribute Values: None
This dataset includes gathering 18-month raw PV data at time intervals of about 200 µs (5 kHz sampling). A post-processing 365-day day-by-day downsampled version, converted to 10 ms intervals (100 Hz sampling), is also included. The end results are two databases: 1. The original, raw, data, including both fast (short circuit, 200 µs) and slow (sweep, 2.5-3.9 s) information for 18 months. These show intervals of missing points, but are provided to allow potential users to reproduce any new work. 2.
For the PV_Data_Clean_1_year zip, there are 365 folders included organized by dates. Each folder contains a readme txt, summarizing the 10 ms short circuit currents and 2.5-3.9 s sweeps (short-circuit current, open-circuit voltage, and MPP voltage, current, and power extracted).
The Voltammetry-Based Sensing (VBS) methods are extremely interesting due to high specificity in several biochemical applications. Several considerations can be applied to use this method to measure different analytes, and implement efficient and optimized electronic measurement platform for point-of-care diagnostic, in wearable, portable, or IoT systems. The dataset contains the data presented in , which proves on real experimental data a method to define the optimized setup to develop efficient and electronic bio-sensing platforms.
The dataset contains measurements taken from four air handling units (AHU) installed in a medium-to-large size academic building. The building is a 7-story, 9000 sqm facility commissioned in 2016 hosting the PRECIS research center. It contains multiple research laboratories, multifunction spaces, meeting rooms, and a large auditorium as well as administrative offices. It is located at 44°2606.0N and 26°0244.0E in a temperate continental climate with hot summers and cold winters. Cooling is handled using on-site electric chillers while heating is provided from a district heating network.
Data for the article in the Transactions on Industrial Informatics
Indoor location systems based on ultra-wideband (UWB) technology have become very popular in recent years following the introduction of a number of low-cost devices on the market capable of providing accurate distance measurements. Although promising, UWB devices also suffer from the classic problems found when working in indoor scenarios, especially when there is no a clear line-of-sight (LOS) between the emitter and the receiver, causing the estimation error to increase up to several meters.