scholarly journals WattScale

2021 ◽  
Vol 2 (1) ◽  
pp. 1-25
Author(s):  
Srinivasan Iyengar ◽  
Stephen Lee ◽  
David Irwin ◽  
Prashant Shenoy ◽  
Benjamin Weil
Keyword(s):  
Cooling System ◽  
Large Population ◽  
Ground Truth ◽  
Detection Algorithm ◽  
Building Envelope ◽  
Ground Truth Data ◽  
Heating And Cooling ◽  
Data Driven Approach ◽  
Execution Mode ◽  
The Individual

Buildings consume over 40% of the total energy in modern societies, and improving their energy efficiency can significantly reduce our energy footprint. In this article, we present WattScale, a data-driven approach to identify the least energy-efficient buildings from a large population of buildings in a city or a region. Unlike previous methods such as least-squares that use point estimates, WattScale uses Bayesian inference to capture the stochasticity in the daily energy usage by estimating the distribution of parameters that affect a building. Further, it compares them with similar homes in a given population. WattScale also incorporates a fault detection algorithm to identify the underlying causes of energy inefficiency. We validate our approach using ground truth data from different geographical locations, which showcases its applicability in various settings. WattScale has two execution modes—(i) individual and (ii) region-based, which we highlight using two case studies. For the individual execution mode, we present results from a city containing >10,000 buildings and show that more than half of the buildings are inefficient in one way or another indicating a significant potential from energy improvement measures. Additionally, we provide probable cause of inefficiency and find that 41%, 23.73%, and 0.51% homes have poor building envelope, heating, and cooling system faults, respectively. For the region-based execution mode, we show that WattScale can be extended to millions of homes in the U.S. due to the recent availability of representative energy datasets.

Gravitational community detection by predicting diameter

2021 ◽  
pp. 2150145
Author(s):  
Himansu Sekhar Pattanayak ◽  
Harsh K. Verma ◽  
Amrit Lal Sangal
Keyword(s):  
Community Detection ◽  
Ground Truth ◽  
Detection Algorithm ◽  
Local Information ◽  
Ground Truth Data ◽  
Overlapping Communities ◽  
Detection Algorithms ◽  
Np Hard Problem ◽  
Community Detection Algorithm ◽  
The Individual

Community detection is a pivotal part of network analysis and is classified as an NP-hard problem. In this paper, a novel community detection algorithm is proposed, which probabilistically predicts communities’ diameter using the local information of random seed nodes. The gravitation method is then applied to discover communities surrounding the seed nodes. The individual communities are combined to get the community structure of the whole network. The proposed algorithm, named as Local Gravitational community detection algorithm (LGCDA), can also work with overlapping communities. LGCDA algorithm is evaluated based on quality metrics and ground-truth data by comparing it with some of the widely used community detection algorithms using synthetic and real-world networks.

scholarly journals D.sort: template based automatic spike sorting tool

2018 ◽  
Author(s):  
Madeny Belkhiri ◽  
Duda Kvitsiani
Keyword(s):  
Template Matching ◽  
Ground Truth ◽  
Sorting Algorithm ◽  
Processing Unit ◽  
Spike Sorting ◽  
Ground Truth Data ◽  
Objective Metrics ◽  
Movement Artifacts ◽  
Freely Behaving ◽  
The Individual

AbstractUnderstanding how populations of neurons represent and compute internal or external variables requires precise and objective metrics for tracing the individual spikes that belong to a given neuron. Despite recent progress in the development of accurate and fast spike sorting tools, the scarcity of ground truth data makes it difficult to settle on the best performing spike sorting algorithm. Besides, the use of different configurations of electrodes and ways to acquire signal (e.g. anesthetized, head fixed, freely behaving animal recordings, tetrode vs. silicone probes, etc.) makes it even harder to develop a universal spike sorting tool that will perform well without human intervention. Some of the prevalent problems in spike sorting are: units separating due to drift, clustering bursting cells, and dealing with nonstationarity in background noise. The last is particularly problematic in freely behaving animals where the noises from the electrophysiological activity of hundreds or thousands of neurons are intermixed with noise arising from movement artifacts. We address these problems by developing a new spike sorting tool that is based on a template matching algorithm. The spike waveform templates are used to perform normalized cross correlation (NCC) with an acquired signal for spike detection. The normalization addresses problems with drift, bursting, and nonstationarity of noise and provides normative scoring to compare different units in terms of cluster quality. Our spike sorting algorithm, D.sort, runs on the graphic processing unit (GPU) to accelerate computations. D.sort is a freely available software package (https://github.com/1804MB/Kvistiani-lab_Dsort).

scholarly journals Energy Monitoring in a Heating and Cooling System in a Building Based on the Example of the Turówka Hotel

Energies ◽  
2020 ◽  
Vol 13 (8) ◽  
pp. 1968 ◽  
Author(s):  
Marek Borowski ◽  
Piotr Mazur ◽  
Sławosz Kleszcz ◽  
Klaudia Zwolińska
Keyword(s):  
Energy Consumption ◽  
Energy Management ◽  
Energy Demand ◽  
Cooling System ◽  
Energy Performance ◽  
High Energy ◽  
Building Envelope ◽  
Large Variability ◽  
Heating And Cooling ◽  
And Control

The energy consumption of buildings is very important for both economic and environmental reasons. Newly built buildings are characterized by higher insulation and airtightness of the building envelope, and are additionally equipped with technologies that minimize energy consumption in order to meet legal requirements. In existing buildings, the modernization process should be properly planned, taking into account available technologies and implementation possibilities. Hotel buildings are characterized by a large variability of energy demand, both on a daily and a yearly basis. Monitoring systems, therefore, provide the necessary information needed for proper energy management in the building. This article presents an energy analysis of the Turówka hotel located in Wieliczka (southern Poland). The historical hotel facility is being modernized as part of the project to adapt the building to the requirements of a sustainable building. The modernization proposal includes a trigeneration system with a multifunctional reverse regenerator and control module using neural algorithms. The main purpose is to improve the energy efficiency of the building and adapt it to the requirements of low-energy buildings. The implementation of a monitoring system enables energy consumption to be reduced and improves the energy performance of the building, especially through using energy management systems and control modules. The proposed retrofit solution considers the high energy consumption, structure of the energy demand, and limits of retrofit intervention on façades.

scholarly journals Predicting the Effects of Changes in Thermal Envelope Characteristics on Energy Consumption: Application and Verification of a Simple Model for Australian and Canadian Climates

1996 ◽  
Vol 7 (1) ◽  
pp. 1-28
Author(s):  
S. M. Cornick ◽  
P.C. Thomas ◽  
D.K. Prasad
Keyword(s):  
Cooling System ◽  
Thermal Characteristics ◽  
Building Envelope ◽  
Hvac System ◽  
Paper Briefly ◽  
Heating And Cooling ◽  
Wide Range ◽  
Similarities And Differences ◽  
System Configurations ◽  
New Buildings

A simple energy model was used for determining thermal envelope characteristics and building envelope trade-off procedures for the new Canadian and Australian energy efficiency codes for new buildings. The model relates heating and cooling system loads to envelope thermal characteristics. It was developed from thousands of DOE2.1E simulation runs. Two separate databases, one containing 25 Canadian locations and the other containing 9 Australian locations were created. The heating and cooling models were developed from these databases. The model is shown to give consistent results although there are significant differences in climate, construction of the building envelope, building operational schedules and HVAC system configurations. This paper briefly describes the DOE2.1E models used for the study in each country, highlighting similarities and differences. The consistency of results predicted by the model is discussed for typical climatic locations in both countries. The methods for predicting heating and cooling system loads are shown to produce good results over a wide range of climates and for different system configurations. The paper also discusses the development of climate correlations to extend the range of the models to include locations not in the original databases.

scholarly journals Mapping the Extent of Invasive Phragmites australis subsp. australis From Airborne Hyperspectral Imagery

2021 ◽  
Vol 9 ◽  
Author(s):  
Kathryn Elmer ◽  
Margaret Kalacska ◽  
J. Pablo Arroyo-Mora
Keyword(s):  
Remote Sensing ◽  
Invasive Species ◽  
Early Detection ◽  
Target Detection ◽  
Phragmites Australis ◽  
Hyperspectral Imagery ◽  
Ground Truth ◽  
Detection Algorithm ◽  
Visual Interpretation ◽  
Ground Truth Data

Invasive species pose one of the greatest threats to global biodiversity. Early detection of invasive species is critical in order to prevent or manage their spread before they exceed the ability of land management groups to control them. Optical remote sensing has been established as a useful technology for the early detection and mapping of invasive vegetation populations. Through the use of airborne hyperspectral imagery (HSI), this study establishes a target detection methodology used to identify and map the invasive reed Phragmites australis subsp. australis within the entire extent of Îles-de-Boucherville National Park (Quebec, ON, Canada). We applied the Spectral Angle Mapper (SAM) target detection algorithm trained with a high accuracy GNSS ground truth data set to produce a park-wide map illustrating the extent of detected Phragmites. The total coverage of detected Phragmites was 26.74 ha (0.267 km2), which represents 3.28% of the total park area of 814 ha (8.14 km2). The inherent spatial uncertainty of the airborne HSI (∼2.25 m) was accounted for with uncertainty buffers, which, when included in the measurement of detected Phragmites, lead to a total area of 59.17 ha (0.591 km2), or 7.26% of the park. The overall accuracy of the Phragmites map was 84.28%, with a sensitivity of 76.32% and a specificity of 91.57%. Additionally, visual interpretation of the validation ground truth dataset was performed by 10 individuals, in order to compare their performance to that of the target detection algorithm. The overall accuracy of the visual interpretation was lower than the target detection (i.e., 69.18%, with a sensitivity of 59.21% and a specificity of 78.31%). Overall, this study is one of the first to utilize airborne HSI and target detection to map the extent of Phragmites over a moderately large extent. The uses and limitations of such an approach are established, and the methodology described here in detail could be adapted for future remote sensing studies of Phragmites or other vegetation species, native or invasive, at study sites around the world.

scholarly journals Measuring Mobility and Room Occupancy in Clinical Settings: System Development and Implementation (Preprint)

2020 ◽  
Author(s):  
Gabriele Marini ◽  
Benjamin Tag ◽  
Jorge Goncalves ◽  
Eduardo Velloso ◽  
Raja Jurdak ◽  
...  
Keyword(s):  
System Development ◽  
Ground Truth ◽  
Data Driven ◽  
Clinical Settings ◽  
Ground Truth Data ◽  
Localization System ◽  
Data Driven Approach ◽  
Consistent Assessment ◽  
Occupancy Rates ◽  
New Strategies

BACKGROUND The use of location-based data in clinical settings is often limited to real-time monitoring. In this study, we aim to develop a proximity-based localization system and show how its longitudinal deployment can provide operational insights related to staff and patients' mobility and room occupancy in clinical settings. Such a streamlined data-driven approach can help in increasing the uptime of operating rooms and more broadly provide an improved understanding of facility utilization. OBJECTIVE The aim of this study is to measure the accuracy of the system and algorithmically calculate measures of mobility and occupancy. METHODS We developed a Bluetooth low energy, proximity-based localization system and deployed it in a hospital for 30 days. The system recorded the position of 75 people (17 patients and 55 staff) during this period. In addition, we collected ground-truth data and used them to validate system performance and accuracy. A number of analyses were conducted to estimate how people move in the hospital and where they spend their time. RESULTS Using ground-truth data, we estimated the accuracy of our system to be 96%. Using mobility trace analysis, we generated occupancy rates for different rooms in the hospital occupied by both staff and patients. We were also able to measure how much time, on average, patients spend in different rooms of the hospital. Finally, using unsupervised hierarchical clustering, we showed that the system could differentiate between staff and patients without training. CONCLUSIONS Analysis of longitudinal, location-based data can offer rich operational insights into hospital efficiency. In particular, they allow quick and consistent assessment of new strategies and protocols and provide a quantitative way to measure their effectiveness.

scholarly journals Ground Truth Generating Tool for Traffic Video Detector

2015 ◽  
Vol 20 (2) ◽  
pp. 17-27
Author(s):  
Szymon Bigaj ◽  
Andrzej Głowacz ◽  
Jacek Kościow ◽  
Zbigniew Mikrut ◽  
Piotr Pawlik
Keyword(s):  
Comparative Analysis ◽  
Road Traffic ◽  
Ground Truth ◽  
Detection Algorithm ◽  
Ground Truth Data ◽  
Video Detection ◽  
Detection Software ◽  
Traffic Video ◽  
Video Detector

Abstract The paper presents an application for generating ground truth data for the purposes of video detection and justifies its use in systems which analyze road traffic videos. The usefulness of described application in the development of video detection software is presented - especially during scene configuration and comparative analysis of video detection results versus ground truth data. The latter is possible due to simplicity of the result text files generated in a similar way both by the presented application and by the video detection algorithm. Two exemplary applications of the tool designed to generate ground truth data are presented, together with a discussion of their construction, functionality and abilities.

scholarly journals Unsupervised learning trajectory anomaly detection algorithm based on deep representation

2020 ◽  
Vol 16 (12) ◽  
pp. 155014772097150
Author(s):  
Zhongqiu Wang ◽  
Guan Yuan ◽  
Haoran Pei ◽  
Yanmei Zhang ◽  
Xiao Liu
Keyword(s):  
Anomaly Detection ◽  
Unsupervised Learning ◽  
Clustering Algorithm ◽  
Feature Fusion ◽  
Ground Truth ◽  
Real Data ◽  
Detection Algorithm ◽  
Learning Trajectory ◽  
Fusion Model ◽  
Ground Truth Data

Without ground-truth data, trajectory anomaly detection is a hard work and the result lacks of interpretability. Moreover, in most current methods, trajectories are represented by geometric features or their low-dimensional linear combination, and some hidden features and high-dimensional combined features cannot be found efficiently. Meanwhile, traditional methods still cannot get rid of the limitation of space attributes. Therefore, a novel trajectory anomaly detection algorithm is present in this article. Unsupervised learning mechanism is used to overcome nonground-truth problem and deep representation method is used to represent trajectories in a comprehensive way. First, each trajectory is partitioned into segments according to its open angles, then the shallow features at each point of a segment are extracted and. In this way, each segment is represented as a feature sequence. Second, shallow features are integrated into auto-encoder-based deep feature fusion model, and the fusion feature sequences can be extracted. Third, these fused feature sequences are grouped into different clusters using a unsupervised clustering algorithm, and then segments which quite differ from others are detected as anomalies. Finally, comprehensive experiments are conducted on both synthetic and real data sets, which demonstrate the efficiency of our work.

scholarly journals RIANN—A Robust Neural Network Outperforms Attitude Estimation Filters

AI ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 444-463
Author(s):  
Daniel Weber ◽  
Clemens Gühmann ◽  
Thomas Seel
Keyword(s):  
Neural Network ◽  
Motion Tracking ◽  
Method Development ◽  
State Of The Art ◽  
Inertial Sensor ◽  
Ground Truth ◽  
Attitude Estimation ◽  
Human Motion ◽  
Ground Truth Data ◽  
The Individual

Inertial-sensor-based attitude estimation is a crucial technology in various applications, from human motion tracking to autonomous aerial and ground vehicles. Application scenarios differ in characteristics of the performed motion, presence of disturbances, and environmental conditions. Since state-of-the-art attitude estimators do not generalize well over these characteristics, their parameters must be tuned for the individual motion characteristics and circumstances. We propose RIANN, a ready-to-use, neural network-based, parameter-free, real-time-capable inertial attitude estimator, which generalizes well across different motion dynamics, environments, and sampling rates, without the need for application-specific adaptations. We gather six publicly available datasets of which we exploit two datasets for the method development and the training, and we use four datasets for evaluation of the trained estimator in three different test scenarios with varying practical relevance. Results show that RIANN outperforms state-of-the-art attitude estimation filters in the sense that it generalizes much better across a variety of motions and conditions in different applications, with different sensor hardware and different sampling frequencies. This is true even if the filters are tuned on each individual test dataset, whereas RIANN was trained on completely separate data and has never seen any of these test datasets. RIANN can be applied directly without adaptations or training and is therefore expected to enable plug-and-play solutions in numerous applications, especially when accuracy is crucial but no ground-truth data is available for tuning or when motion and disturbance characteristics are uncertain. We made RIANN publicly available.

Sign in / Sign up

Export Citation Format

Share Document