Datasets. In the following we present a short description of each datasets used for our experiments.
a) Office-31: Office-31 [27] is a dataset containing 31 classes divided in 3 domains: Amazon (A), DSLR (D) and Webcam (W). Office-31 has a total of 4110 images, with a maximum of 2478 images per domain. In this dataset we use deep features extracted from the ResNet-50 architecture [28] pretrained on ImageNet.
Datasets. This Data Use Agreement (“Agreement”) is made and entered into by and between the SOUTH ALAMO REGIONAL ALLIANCE FOR THE HOMELESS (“Covered Entity”), a 501(c)(3) non-profit organization in the State of Texas, and Insert Name of Entity (“Data Recipient”), a [insert description of legal status (public / private / profit / non-profit / company incorporated in what state, LLP or LLC or other entity incorporated or registered in what state)] on (Today’s Date) for the purpose of collecting and analyzing Homeless Management Information System (HMIS) data from XXXXX.
Datasets. 6.1 Some datasets are already under the ownership of BWI. Numerous relevant datasets (with various data ownership) are already published publicly by the National Biodiversity Data Centre. Additional important datasets are in the ownership of BWI and use will be subject to appropriate permissions being received.
6.2 Datasets used by this project – see Appendix 1.
6.3 NPWS/DHLGH have provided the datasets set out in Appendix 2 and permission for all those listed there to be used for the purposes of this Project (including those of which BWI already holds a copy).
6.4 These datasets are stored on secured BWI IT infrastructure.
6.5 Access to these datasets are restricted to BWI staff involved in the project and only for the purposes outlined in this MOU.
6.6 NPWS/DHLGH have provided data at the highest resolution available for the purposes of informing the hotspot scoring.
Datasets. For our experiments, we have recorded two entirely new, multi-modal datasets (cf. Fig.
Datasets. In order to ensure a fair comparison, we used the same data as used by [2]. The data is part of CoMon project which is a monitoring infrastructure for PlanetLab [2]. It contains CPU utilization of more than thousands of virtual machines measured from servers located at different places all around the world. The data of ten random days are chosen from the workload traces that are collected in March and April 2011. The data files contain CPU utilization values of virtual machines measured every 5 min for 24 h. Note that each line in a file represents a single request, and data for each day are combined in a single folder. In total, all the folders contain 11,746 files, which contain over 3.3 million user requests. The properties of the data are summarized in Tab.
Datasets. Pilot 1a aims to predict the maintenance status of wind turbine electrical drivetrain components, such as generators and power converters. It examines onshore and offshore wind turbines powered by a doubly-fed induction generator and provides five datasets: • La Haute-Lys dataset- Wind turbine SCADA data (SCADA-Pilot1a): This dataset is collected from various wind turbines situated in multiple wind farms. There is a unique data structure and tag name for every turbine brand. A wind turbine's Supervisory Control and Data Acquisition system contains sensor data at the most important subcomponents of the wind turbine; the collected data are analysed at 10- minute intervals. Turbines during a period where the electrical subcomponents had faults are also included. • High-frequency Data (VUB-Pilot1a): This data is derived from a dedicated measurement campaign on onshore wind turbines and consists of a limited set of electric measurements and operational parameters (e.g., wind speed). • Open wind speed dataset (Flemish-banks-data-Pilot1a): includes environmental measurements (e.g., wind speeds, wind directions) collected along the Belgian North Sea. As a basis for defining semantic labels describing wind conditions, the dataset in LLUC 1a-01 shows the typical range of wind measurements occurring in the field. • Offshore measurement campaign data (High-frequency-accelerations-Pilot1a): This dataset includes acceleration measurements, that were taken of the drivetrain of an offshore wind turbine. • Dedicated current measurement campaign data (ENGIE-VUB-Pilot1a): This dataset consists of current signals that are acquired on an onshore wind turbine. These data are similar to the La Haute Lys dataset. As such they will be merged in further discussions on data handling and analytics with the La Haute Lys data as the same processing methodology applies.
Datasets. Pilot 2a focuses on integrating and deploying different PLATOON analytical services with the Institute Xxxxxxx Xxxxx (IMP) proprietary VIEW4 Supervisory control and data acquisition (SCADA) system deploys the energy value chain in Serbia. Energy resources related to Renewable Energy Sources (RES) in this pilot include: wind power plants and PV power Plants. Electricity production from solar and wind plants is subject to forecast errors that drive demand for balancing. These data sources are described as follows: PUPIN-RES-PROD: Historical Wind Power Production Measurements; it contains measurements of the production from the wind power plant, as well as topology data. These four data sources composed the catalog EBPM (Electricity Balance and Predictive Maintenance); they provide data in English (ENG) and Serbian (RS). More details in D2.4.
Datasets. Pilot 3a is about an office building equipped with a building management system (BMS) that controls HVAC and comfort in multiple zones of the building. This pilot includes LLUC 3a- 01 - Optimizing HVAC control regarding occupancy, and LLUC 3a-02 - Providing Demand Response Service through HVAC control.
Datasets. Pilot 3b aims at acquiring, aggregating, and processing data of energy consumption and related properties of various buildings for making energy domain-specific analyses, e.g., consumption forecasting, predictive maintenance, benchmarking. Pilot 3b is formed of 2 subpilots: 3b-PI and 3b-ROM. Each of the subpilots have different datasets as explained below: There are four possible destinations for the building spaces in Poste Italiane buildings located in the Rome Municipality Area: Datacenter, Logistics distribution, and cross-docking (mail & parcels), Retail and Office (Directional), with a total of 16 buildings. • Building Data (ANAG-Pilot3b): This dataset includes information about each building's features and general characteristics (ID office, address, destination use, square feet, climate zone, etc.). • Building Occupancy dataset (OCCU_C & OCCU_E): In each building of the pilot, the number of employees and customers is recorded daily. • Calendar (CALE-Pilot3b): keeps information regarding office openings and shifts. • Consumption on Building (EC_TOT & EC_SB): An overview on the temperature and humidity inside a building or line as well as information about active energy consumption (kWh). Among its many uses will be consumption prediction and benchmarking, identifying anomalies, and assessing lighting consumption. The information from the climate sensors serves various purposes, e.g., predicting consumption to maintain a certain comfort level, and appropriate consumption. • Building Energy Systems (BS-Pilot3b): This dataset provides a description of the heating, cooling, and lighting systems in all buildings. It will be possible to use building HVAC plant information for a variety of purposes, including consumption prediction and consumption benchmarking. In addition, building lighting plants information will be utilized to calculate lighting consumption, benchmarks and estimate lighting energy consumption. • Systems Anomalies (Fault-Pilot3b): The data is derived from monitoring the temperature within the building. In addition, alerts are generated when temperatures exceed a given threshold. These are the available datasets: • Energy Meters Electrical Monthly Consumptions (EMEMC-Pilot3b-ROM): All power consumption from last month's meters (energy vendor). • Energy Meters Electrical Historical Consumptions (EMEHC2): A historical daily record (kwh) of the electric consumption for ROM buildings; divided in rows for each 15-minute consumption period. • B...
Datasets. Pilot 4a consists of four datasets from the area of Milan, Italy: ● Microgrid PV power production and forecast (MicroGridPVPilot4a): consists of forecasting and modeling of Photovoltaic (PV) power. The dataset is expected to grow with more than 30K records per day, and the updates are per minute. ●Microgrid battery (MicroGridBatteryPilot4a): comprises observations of batteries described in terms of State of Charge (SOC), State of Health (SOH), Direct Current (DC), and Alternate Current (AC). Current and voltage are registered, as well as average cell temperature and average ambient temperature. This dataset grows in 86K records per day, and new observations arrive per 1 sec. ● Microgrid potable water production (MPWPPilot4a): contains relevant measurements of a plant for potable water production. The dataset collects active and reactive power values, frequency of pump rotation, feed and permeate water conductivity, concentrate and permeate water flow rate, and temperature and pressure in the hydraulic circuit. It has a growth trend of 1,440 records per day, and updates are per minute. ●Microgrid weather parameters (MicroGridWeatherStationPilot4a): consist of observations sensed by a weather station. It reports ambient temperature, wind speed, wind direction, relative humidity, rain, and irradiance. The growth trend is 65K records per day, and observations are registered every 10 seconds. ● Microgrid full skype imaging (MicroGridFSIPilot4a): comprises full-sky images in JPEG format. It grows in more than 250 records per day every 5 minutes.
