Find research datasets worth reusing

opencc-by-4.0Jun 2022View details →

PhytoNodes for Environmental Monitoring: Stimulus Classification based on Natural Plant Signals in an Interactive Energy-efficient Bio-hybrid System

Cities worldwide are growing, putting bigger populations at risk due to urban pollution. Environmental monitoring is essential and requires a major paradigm shift. We need green and inexpensive means of measuring at high sensor densities and with high user acceptance. We propose using phytosensing: using natural living plants as sensors. In plant experiments we gather electrophysiological data with sensor nodes. We expose the plant Zamioculcas zamiifolia to five different stimuli: wind, temperature, blue light, red light, or no stimulus. Using that data we train ten different types of artificial neural networks to classify measured time series according to the respective stimulus. We achieve good accuracy and succeed in running trained classifying artificial neural networks online on the microcontroller of our small energy-efficient sensor node. To indicate later possible use cases, we showcase the system by sending a notification to a smartphone application once our continuous signal analysis detects a given stimulus.   Data repository for our paper "PhytoNodes for Environmental Monitoring: Stimulus Classification based on Natural Plant Signals in an Interactive Energy-efficient Bio-hybrid System", submitted to the GoodIT conference. Please refer to the paper for more information.   Contents of this repository <ul> <li>mu_interface: Code for our data collection plant experiments, based on Raspberry Pis and the <a href="http://cybertronica.co/?q=products/phytosensor">Cybertronica phytosensing and phytoactuating system</a>.</li> <li>raw_data: The datasets from our plant experiments for the stimuli wind, temperature, red light, blue light, and no stimulus.</li> <li>dl-4-tsc: Deep learning framework developed by <a href="https://doi.org/10.1007/s10618-019-00619-1">Fawaz et. al (Deep learning for time series classification: a review)</a> and adapted to our use case. Find the training and testing datasets in the archives folder as well as the trained classifiers in the results folder.</li> <li>classification_results.ods: Overview of the results from the deep learning framework (accuracy, precision, recall, training time).</li> <li>TFLite_Models: The trained classifiers in TensorFlow Lite Format.</li> <li>00_AI_BLE_MeasuringOnlyWind: Source code for classification on STM-based PhytoNodes (using MCDCNN two-class classifier) and Bluetooth communication. The code is written for the STM32WB55 Nucleo board and can be transferred to the dongle.</li> <li>zavrsniProjekt_iOS: Source code of the iOS app used to receive data from the STM-based PhytoNodes.</li> <li>Watchplant_application_documentation.pdf: Instructions to build and use the iOS app.</li> </ul>

opencc-by-4.0Nov 2011View details →

Figure 7. The outcomes of the Monitoring and Control of the Greenhouse soil and climate Conditions for tomato crops-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

In the past generation greenhouses it was enough to have one cabled measurement point in the middle to provide the information to the greenhouse automation system. The system itself was usually simple without opportunities to control locally heating, lights, ventilation or some other activity, which was affecting the greenhouse interior climate. The optimal greenhouse climate and soil adjustment can enable us to improve productivity and to achieve remarkable energy savings. In this paper we proposed a multi-agent methodology for integrated management systems in greenhouses. In this regards wireless sensor networks play a vital role to monitor greenhouse and environment parameters. Each controlled process of the greenhouse environment is modeled as an autonomous agent with its own inputs, its own outputs and its own interactions with the other agents. Each agent acts autonomously, as it knows a priori the desired environmental set-points. In this way, any possible conflicting decisions of conventional environmental control methodologies are resolved through negotiations between the agents so that the possible optimal integrated solution is achieved. The developed system is simple, cost effective, and easily installable.

Figure 6. Structure of the MAS for integrated greenhouse management system.-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

The complete agents “environment” is shown in figure 6. Each agent receives the necessary environmental or plant condition measurements. While each agent keeps its autonomy and has its own “personal” goals, it interacts with the other agents through some specific communication language, in the “Agent discussion area”, where the overall goal is taken into account. This interaction takes place under the presence of information from the existing models and the target goals. At that point, each agent has decided on its best strategy.

Figure 2. Experimental wireless sensors setup in greenhouse-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

Figure 2 illustrates how the sensor nodes were deployed to the greenhouse block. The idea of the vertical deployment was to get a better understanding of the microclimate layers which typically exist in the greenhouse, and to figure out what kind of differences occur in the climate between lower and upper flora.

Figure 5. Multi-agent system information and knowledge scheme.-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

The negotiations between agents are subject to optimization based on “knowledge” that is derived from complete production models, yield models or even sparse models as expressed in fuzzy expert rules or practical rules of thumb. In addition, pest control and plant disease models provide additional information useful to the design of a successful strategy for optimal management [15] (illustrated in Figure 5).

Figure 1. Agent Architecture-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

The multi agent method creates a non-structured environment using agents, these agents, in order to reach the global optimum, must be capable of performing transactions between each other, achieving several “deals”, which is performed though a common vocabulary, a finite set of information exchange, a finite set of possible actions, penalties, etc. The power of each agent depends on the degree of contribution of its represented process to the final output of the entire system. Each agent communicates with the environment and adapts to its own internal state as well as to the state of the entire system. In this systems, for the realization of the multi agent architecture the JADE 4.1.1 (Java Agent DEvelopment Framework) have been used [7].

Figure 4. The multi-agent overall environment for integrated management-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

The value of the final product incorporates not only quantity issues but also quality issues, which are difficult to be measured or even estimated. The environment of each agent is defined by the same parameters that define the physical environment in addition to internal states reported by each agent.

Figure 3. Photosynthetic activity in different wavelengths of light radiation. 5.-Design and Development a Control and Monitoring System for Greenhouse Conditions Based-On Multi Agent System

The greenhouse protects the plants from the extreme weather conditions. However, if the period of daylight prevents the photosynthetic activity, the plants do not grow. Horticultural lighting allows the grower to extend the growing season. It enables a year-round producing of plants or makes it possible for the grower to start sowing in early spring and continue season till the first frost. Plants need about 10-12 hours light to improve growth. When the plants are producing flowers or fruits the supplemental need of light per day increases up to 16 hours. Figure 3 shows the photosynthetic activity in different wavelengths of light radiation [16].

opencc-by-4.0May 2024View details →

Cloud to Thing Continuum based Sports Monitoring System using Machine Learning and Deep Learning Model

Sports monitoring and analysis have seen significant advancements with the integration of cloud computing and continuum paradigms, facilitated by machine learning and deep learning techniques. In this study, we present a novel approach for sports monitoring that seamlessly transitions from traditional cloud-based architectures to a continuum paradigm, enabling real-time analysis and insights into player performance and team dynamics. Leveraging machine learning and deep learning algorithms, our framework offers enhanced capabilities for player tracking, action recognition, and performance evaluation in various sports scenarios. This research proposes a Cloud-to-Thing Continuum based Sports Monitoring System utilizing Machine Learning (ML) and Deep Learning (DL) models. The system integrates data acquisition, preprocessing, feature extraction, cloud-based processing, continuum paradigm integration, and decision-making stages. It leverages innovative techniques such as Improved Mask R-CNN for pose estimation, hybrid metaheuristic algorithms with Generative Adversarial Network (GAN) for classification, and fuzzy decision-making Based on the integrated analysis, decisions are made regarding player performance, team strategies, and tactical adjustments. The continuum approach ensures a balance between centralized cloud processing and distributed edge processing, optimizing resource utilization and reducing latency. Through this system, real-time analysis of sports events is achieved, enabling immediate feedback for time-sensitive applications.

opencc-by-4.0Jun 2024View details →

Open Data in German Forest Information Systems: Towards an EU Forest Resilience Monitor (Original dataset on Forest Resilience Indicators and their compliance with Open data criteria)

This dataset represents the original analysis on which my Master's Thesis in the pioneer master programme at the Universities of Münster, Tallinn (Taltech) and Leuven (KUL), titled "Open Data in German Forest Governance: Towards an EU Forest Resilience Monitor".  <ul> <li>The first sheet contains the coding on information systems on bird species occurrence and their compliance with Open data criteria, with justifications, links or further information speciefied in comments, where necessary. </li> <li>The second sheet contains the coding on information systems on tree species distribution and their compliance with Open data criteria, with justifications, links or further information speciefied in comments, where necessary. </li> <li>The third sheet contains the coding on information systems on soil water conditions and their compliance with Open data criteria, with justifications, links or further information speciefied in comments, where necessary. </li> <li>The fourth sheet contains the coding on information systems on canopy cover and their compliance with Open data criteria, with justifications, links or further information speciefied in comments, where necessary. </li> <li>The fifth sheet contains the coding on information systems on carbon sequestration and their compliance with Open data criteria, with justifications, links or further information speciefied in comments, where necessary. </li> <li>The sixth sheet contains the data on the individual scores per policy level/state per indicator group and the respective averages. More information on the operationaliation can be found in the methodology section of the thesis. </li> <li>The seventh sheet contains the data on the individual scores per policy level/state per indicator group and the respective averages, ranked from highest to lowest compliance. More information on the operationaliation can be found in the methodology section of the thesis. </li> <li>The last sheet gives information on the coding. </li> </ul>

opencc-by-4.0Aug 2024View details →

Surface Marine Carbonate System Data (2019-2024) from Volunteer Observing Ship monitoring across the Western Mediterranean Sea

1.     Introduction We present here a high-resolution dataset which spans five years (February 2019 - February 2024) and is based on weekly physicochemical observations of the surface waters along the western boundary of the Mediterranean Sea. Data were automatically collected by a Surface Ocean Observation Platform (SOOP) operating in underway mode aboard the Volunteer Observing Ship (VOS) MV JONA SOPHIE (formerly RENATE P until November 2021), a container ship managed by Nisa Maritima on the route between the Canary Islands and Barcelona. A total of 92 routes were completed in the Mediterranean Sea during the observation period. The SOOP CanOA-VOS line, designed and maintained by the QUIMA research group at IOCAG-ULPGC, is part of Spain’s contribution to the Integrated Carbon Observation System (ICOS-ERIC) since 2021 and is recognized as an ICOS Class 1 Ocean Station, ensuring that the measurement equipment and data collection techniques meet ICOS-ERIC's high-quality standards and methodological recommendations. The data collected is also available at the ICOS Data Portal (<a href="https://www.icos-cp.eu/data-products/ocean-release">https://www.icos-cp.eu/data-products/ocean-release</a>). 2.     Data collection The dataset includes continuous monitoring of CO2 levels in both surface ocean and low atmosphere, following protocols to ensure data comparability and quality given by Pierrot et al., (2009). A detailed description is provided by Curbelo-Hernández et al., 2021a, 2021b). An automated CO2 molar fraction (xCO2) measurement system, developed by Craig Nail and commercialized by General Oceanics™, was installed on the ship. This system integrates air and seawater equilibrators with a non-dispersive infrared analyzer by LICOR® for xCO2 detection. The analyzer is regularly calibrated using standard gases provided by the NOAA, traceable to the World Meteorological Organization (WMO). They were in the order of 0 ppm, 250 ppm, 400 ppm and 550 ppm until January 2021, when the gas bottles for standard 2 to 4 were changed for a new set with concentrations in the order of 300 ppm, 500 ppm and 800 ppm. In addition to xCO2, sea surface temperature (SST) and sea surface salinity (SSS) were monitored using high-precision instruments. The SST was monitored by using a SBE38 thermometer placed at the main seawater intake in the engine room, with a reported error of ±0.01ºC. A SBE45 thermosalinograph and a Hart Scientific HT1523 Handheld Thermometer, with reported errors of ±0.01ºC, were used to monitor the temperature at the entrance of the wet box and inside the equilibrator, respectively. The SBE45 thermosalinograph measured the sea surface salinity (SSS) with an estimated error of ±0.005. Discrete seawater samples were also collected during three round trips in February 2020, March 2021, and October 2023, for further analysis of total alkalinity and dissolved inorganic carbon. A total of 102 discrete samples has been collected in the Mediterranean Sea. Total alkalinity (AT) and total inorganic carbon (CT) were determined using a VINDTA 3C according to Mintrop et al., 2000. AT was analyzed via potentiometric titration with HCl, following the carbonic acid endpoint method (Millero et al., 1993; Dickson and Goyet, 1994), while CT was determined through coulometric titration (Johnson et al., 1993). The VINDTA 3C was calibrated using Certified Reference Material (CRMs) by A. Dickson, ensuring an accuracy of ±1.5 μmol kg-1 for AT and ±1.0 μmol kg-1 for CT. The dataset contains some gaps, including a year-long gap from September 2021 to 2022 due to vessel maintenance and shorter gaps due to technical issues, which were addressed during routine maintenance. Some technical issues in 2020 were delayed due to COVID-19 constraints. 3. Dataset content The dataset includes the following variables:  ·       “Date” (dd/mm/yyyy) ·       “Time” (hh:mm:ss) ·       “Latitude” ·       “Longitude” ·       “equTemp”: seawater temperature measured inside the equilibrator using a Hart Scientific HT1523 Handheld Thermometer. ·       “stdVal”: value of the standard gases used for automatically calibrations. ·       “xCO2”: measured CO2 molar fraction without performing any correlation (raw data). ·       “atmPress”: Atmospheric pressure (units: atm). ·       “equPress”: Diffeence in pressure between the atmosphere and the equilibrator (units: atm). ·       “SST_SBE38”: Sea surface temperature measured with a SBE38 thermometer at the main seawater intake of the vessel. ·       “Temp_SBE45”: Seawater temperature measured with a SBE45 thermosalinograph just before the water supply to the equilibrator. ·       “SSS_SBE45”: Sea surface salinity measured with a SBE45 thermosalinograph just before the water supply to the equilibrator. ·       “xCO2corr_sw”: CO2 molar fraction measured in the sea surface after correction by using standard gases. ·       “xCO2corr_atm”: CO2 molar fraction measured in low atmosphere after correction by using standard gases. ·       “pCO2sw”: Partial pressure of CO2 in the sea surface (units: µatm). ·       “pCO2atm”: Partial pressure of CO2 in low atmosphere (units: µatm). ·       “fCO2sw”: fugacity of CO2 in the sea surface (units: µatm). ·       “fCO2atm”: fugacity of CO2 in low atmosphere (units: µatm). ·       “AT”: Total Alkalinity (µmol kg-1) ·       “CT”: Total Inorganic Carbon (µmol kg-1) ·       “pH”: pH in surface seawater at in situ temperature computed in CO2sys using as input variables AT and fCO2sw. ·       “pH25”: pH in surface seawater at constant temperature of 25ºC computed in CO2sys using as input variables AT and fCO2sw.   Acknowledgement This research was supported by the Canary Islands Government and the Loro Parque Foundation through the CanBIO project, CanOA subproject (2019–2024), and the CARBOCAN agreement (Consejería de Transición Ecológica y Energía, Gobierno de Canarias). We would like to thank the JONA SOPHIE ship owner, the NISA-Marítima company and the captains and crew members for the support during this collaboration. Special thanks to the technician Adrian Castro-Alamo for biweekly equipment maintenance and discrete sampling of total alkalinity aboard the ship. The SOOP CanOA-VOS line is part of the Spanish contribution to the Integrated Carbon Observation System (ICOS-ERIC; https://www.icos-cp.eu/) since 2021 and has been recognized as an ICOS Class 1 Ocean Station. The participation of D. C-H was funded by the PhD grant PIFULPGC-2020-2 ARTHUM-2

opencc-by-4.0Jul 2023View details →

Multiparameter Water Quality Monitoring System for Continuous Monitoring of Fresh Waters Calibration and Measurement Data Set

This data set contains calibration data for all sensors incorporated in the sensor node. It provides comparison measurements of TPL fluorescence taken by the node and reference spectrofluorimeter. Initial test measurements, as well as site measurements, are also provided. Finally, data from a heuristic method of TPL detection in the presence of algae and mud are also given.

ClinicalTrials.gov40/100

Development of Continuous Glucose Monitoring System Cohort for Personalized Diabetes Prevention and Management Platform

ClinicalTrials.gov study NCT04369833. IPD Sharing: NO. Countries: 1. Publications: 11.

closedIPD-NOFeb 2026View details →

opencc-by-4.0Nov 2020View details →

EPSRC HEED Data Repository: Individual Appliance Monitoring System

The dataset deposited here was prepared under the EPSRC-funded <a href="http://heed-refugee.coventry.ac.uk/">Humanitarian Engineering and Energy for Displacement</a> research project (EP/P029531/1). The project aimed to understand energy needs of displaced communities, create an evidence base on the usage of different energy interventions and provide recommendations for improved design of future energy interventions to better meet the needs of people.  As part of the project, we deployed an Individual Appliance Monitoring (IAM) System in the Uttargaya settlement in Nepal. The Individual Appliance Monitoring System provides a simple, cost-effective and unobtrusive method of collecting data on the energy usage of connected appliances with the aim to: Evaluate energy consumption of different appliances and Evaluate usage patterns for different appliances. The monitoring system comprises of 2 types of devices – Energenie MiHome Smart Plugs MIHO005 (i.e. Individual Appliance Monitors (IAM)) to sense data relating to power and voltage drawn by the connected appliance, and gateway nodes to collect data from IAM. The unit cost of a MIHO005 adaptor and Raspberry Pi-based gateway is £34.99 and £74.17 respectively. The main component of the gateway node is a Raspberry Pi fitted with an Energenie ENER314-RT (receiver-transmitter) add-on board to allow the Pi to communicate with the smart plugs. The data collected by the gateway is stored locally in an SD card as well as sent to the heed-data server hosted in Coventry University. Post Deployment Challenges: ·         Power outages: These are common in the camp. Data is lost during this time as the devices have no access to power. ·         Internet connectivity: The availability and reliability of Wi-Fi continue to be an issue for the transmission of data to heed-data server.

dryad36/100

Monitoring mobility in older adults using a global positioning system (GPS) smartwatch and accelerometer: A validation study

Background There is interest in identifying the most reliable method for detecting early mobility limitations. Accelerometry and Global Positioning System (GPS) could provide insight into declines in mobility, but few studies have used this multi-sensor approach to monitor mobility in older adults. Methods Thirty-two volunteers (66.2±6.3 years) agreed to participate in our validation study. We conducted two experiments to determine the validity of the TicWatch S2 and Pro 3 Ultra GPS models against the Qstarz receiver in measuring life-space mobility, trip frequency, duration, and mode. We also assessed the accuracy of the TicWatch in measuring step count and agreement with the ActiGraph wGT3X-BT for activity counts and sedentary behavior. Participants wore devices simultaneously for three consecutive days and recorded activity and trip information. Results The TicWatch Pro 3 Ultra GPS performed better than the S2 model and was similar to the Qstarz in all tested trip-related measures, and it was able to estimate both passive and active trip modes. Both models showed similar results to the Qstarz in life-space-related measures. The TicWatch S2 demonstrated good to excellent overall agreement with the ActiGraph algorithms for the time spent in sedentary and non-sedentary activities, with 84% and 87% agreement rates, respectively. Under supervised conditions, the TicWatch Pro 3 Ultra GPS measured step count consistently with the gold standard observer, with a bias of 0.4 steps. The thigh-worn ActiGraph algorithm accurately classified sitting and lying postures (97%) and standing postures (90%). Conclusion Our multi-sensor approach to monitoring mobility has the potential to capture both accelerometer-derived movement data and trip/life-space data only available through GPS. In this study, we found that the TicWatch models are valid devices for capturing GPS and raw accelerometer data, making them useful tools for assessing real-world mobility in older adults and advancing our knowledge of early mobility decline.

opencc-zeroJan 2024View details →

opencc-by-4.0Aug 2022View details →

Dataset for the article "PERFORMANCE EVALUATION OF AN IMAGING RADIATION PORTAL MONITOR SYSTEM"

The dataset includes root files used in generating the main figures for the article "PERFORMANCE EVALUATION OF AN IMAGING RADIATION PORTAL MONITOR SYSTEM" by Jana Vasiljević, Alf Göök and Bo Cederwal. The article will be submitted to MDPI Applied Sciences.

opencc-by-4.0Feb 2023View details →

Monitoring ML Systems: Challenges, Solutions and Metrics from a Practitioners' Perspective

This is the dataset for the paper "Monitoring ML Systems: Challenges, Solutions and Metrics from a Practitioners' Perspective". The dataset is recorded in an MS Excel file which contains the following Excel sheets, and the description of each sheet is briefly presented below. (1) Selected Projects (GitHub) contain the 15 selected ML projects with the URL of each project. (2) Raw Data (GitHub) contains the information about the randomly selected 600 issues, such as issue titles, issue links, issue id. (3) Raw Data (SO) contains the information about the randomly selected 2088 SO posts (part of the 2174 SO posts), such as post titles, post link, post id, and open date. (4) MLOps (SO) contains the information about the 86 MLOps SO posts (part of the 2174 SO posts), such as post titles, post link, post id, and open date. (5) Identified Challenges (GitHub) contain the list of categories, subcategories, and codes of identified challenges from GitHub issues. (6) Identified Solutions (GitHub) contain the list of categories, subcategories, and codes of identified solutions from GitHub issues. (7) Identified Metrics (GitHub) contain the list of identified metrics from GitHub issues. (8) Identified Challenges (SO) contain the list of categories, subcategories, and codes of identified challenges from SO posts. (9) Identified Solutions (SO) contain the list of categories, subcategories, and codes of identified solutions from SO posts. (10) Identified Metrics (SO) contain the lists of identified metrics from SO posts. (11) Identified Challenges (Interview) contain the list of categories, subcategories, and codes of identified challenges from interviews. (12) Identified Solutions (Interview) contain the list of categories, subcategories, and codes of identified solutions from interviews. (13) Identified Metrics (Interview) contain the list of identified metrics from interviews. (14) Identified Challenges (Final) contain the taxonomy of the final challenges identified from GitHub issues, SO posts, and interviews. (15) Identified Solutions (Final) contain the taxonomy of the final solutions identified from GitHub issues, SO posts, and interviews. (16) Identified Metrics (Final) contain the final list of metrics identified from GitHub issues, SO posts, and interviews.

opencc-by-4.0Jun 2024View details →

Open Data in German Forest Information Systems: Towards an EU Forest Resilience Monitor (Collection of Forest Resilience Indicators)

This dataset represents the collection of forest indicators for my Master's Thesis in the pioneer master programme at the Universities of Münster, Tallinn (Taltech) and Leuven (KUL), titled "Open Data in German Forest Governance: Towards an EU Forest Resilience Monitor".  It contains a classification of inicators sourced from: <ul> <li> Nikinmaa, L., Lindner, M., Cantarello, E., Jump, A. S., Seidl, R., Winkel, G., & Muys, B. (2020). Reviewing the use of resilience concepts in forest sciences. Current Forestry Reports, 6, 61-80. </li> <li> European Commission. (2023a). Proposal for a REGULATION OF THE EUROPEAN PARLIAMENT AND OF THE COUNCIL on a monitoring framework for resilient European forests. Directorate-General for Environment. Lastly retrieved on December 17, 2023 from <a href="https://ec.europa.eu/transparency/documents-register/detail?ref=COM(2023)728&amp;lang=en&lang=en">https://ec.europa.eu/transparency/documents-register/detail?ref=COM(2023)728&amp;lang=en&lang=en</a>. </li> <li> European Parliament. (2024, February 27). European Parliament legislative resolution of 27 February 2024 on the proposal for a regulation of the European Parliament and of the Council on nature restoration (COM(2022)0304 – C9-0208/2022 – 2022/0195(COD)). Lastly retrieved on April 26, 2024 from <a href="https://www.europarl.europa.eu/doceo/document/TA-9-2024-0089_EN.html">https://www.europarl.europa.eu/doceo/document/TA-9-2024-0089_EN.html</a>. </li> </ul>

opencc-by-4.0Jul 2024View details →

Dataset for the paper "Ocean wave energy harvesting with high energy density and self-powered monitoring system"

Dataset for the paper "Ocean wave energy harvesting with high energy density and self-powered monitoring system“.