# Publications

Date

+++ title = “Embedded Commissioning of Building Systems” date = “2011-11-01” authors = [“O. Akin”,“T. Turkaslan-Bulbul”,“S. Hoon Lee”] publication_types = [“5”] publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “BLUED: A Fully Labeled Public Dataset for Event-Based Non-Intrusive Load Monitoring Research” date = “2012-08-01” authors = [“K. Anderson”,“A. Ocneanu”,“D. Benitez”,“D. Carlson”,“A. Rowe”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2nd KDD Workshop on Data Mining Applications in Sustainability (SustKDD)“ publication_short = “” abstract = “The problem estimating the electricity consumption of individual appliances in a building from a limited number of voltage and/or current measurements in the distribution system has received renewed interest from the research community in recent years. In this paper, we present a Building-Level fUlly-labeled dataset for Electricity Disaggregation (BLUED). The dataset consists of voltage and current measurements for a single-family residence in the United States, sampled at 12 kHz for a whole week. Every state transition of each appliance in the home during this time was labeled and time-stamped, providing the necessary ground truth for the evaluation of event-based algorithms. With this dataset, we aim to motivate algorithm development and testing. The paper describes the hardware and software configuration, as well as the dataset’s benefits and limitations. We also present some of our detection results as a preliminary benchmark.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Event Detection for Non Intrusive Load Monitoring” date = “2012-11-01” authors = [“K. Anderson”,“M. Berges”,“A. Ocneanu”,“D. Benitez”,“J. M. F. Moura”] publication_types = [“1”] publication = “Proceedings of the 38th Annual Conference on IEEE Industrial Electronics Society (IECON)“ publication_short = “” abstract = “Monitoring electricity consumption in the home is an important way to help reduce energy usage and Non-Intrusive Load Monitoring (NILM) techniques are a promising approach to obtain estimates of the electrical power consumption of individual appliances from aggregate measurements of voltage and/or current in the distribution system. In this paper, we discuss event detection algorithms used in the NILM literature and propose new metrics for evaluating them. In particular, we introduce metrics that incorporate information contained in the power signal instead of strict detection rates. We show that this information is important for NILM applications with the goal of improving appliance energy disaggregation. Our work was carried out on a week-long dataset of real residential power usage which we intend to make publicly available.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Non-Intrusive Load Monitoring: A Power Consumption Based Relaxation” date = “2015-12-01” authors = [“K. Anderson”,“M. Berges”,“J. M. F. Moura”] publication_types = [“1”] publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Unsupervised approximate power trace decomposition algorithm” date = “2014-01-01” authors = [“K. Anderson”,“J. MF Moura”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2nd International Workshop on Non-Intrusive Load Monitoring“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Brick: Towards a unified metadata schema for buildings” date = “2016-01-01” authors = [“B. Balaji”,“A. Bhattacharya”,“G. Fierro”,“J. Gao”,“J. Gluck”,“D. Hong”,“A. Johansen”,“J. Koh”,“J. Ploennigs”,“Y. Agarwal”,“M. Berges”,“D. Culler”,“R. Gupta”,“M. Baun Kjaergaard”,“M. Srivastava”,“K. Whitehouse”] publication_types = [“1”] publication = “Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Brick: Metadata Schema for Portable Smart Building Applications” date = “2018-01-01” authors = [“B. Balaji”,“A. Bhattacharya”,“G. Fierro”,“J. Gao”,“J. Gluck”,“D. Hong”,“A. Johansen”,“J. Koh”,“J. Ploennigs”,“Y. Agarwal”,“M. Berges”,“D. Culler”,“R. Gupta”,“M. Baun Kjaergaard”,“M. Srivastava”,“K. Whitehouse”] publication_types = [“2”] publication = “Applied Energy“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/https://doi.org/10.1016/j.apenergy.2018.02.091"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Portable Queries Using the Brick Schema for Building Applications: Demo Abstract” date = “2016-01-01” authors = [“B. Balaji”,“A. Bhattacharya”,“G. Fierro”,“J. Gao”,“J. Gluck”,“D. Hong”,“A. Johansen”,“J. Koh”,“J. Ploennigs”,“Y. Agarwal”,“M. Berges”,“D. Culler”,“R. Gupta”,“M. Baun Kjaergaard”,“M. Srivastava”,“K. Whitehouse”] publication_types = [“1”] publication = “Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A comparison of non-intrusive load monitoring methods for commercial and residential buildings” date = “2014-01-01” authors = [“N. Batra”,“O. Parson”,“M. Berges”,“A. Singh”,“A. Rogers”] +++ title = “Building Commissioning as an Opportunity for Training Non-Intrusive Load Monitoring Algorithms” date = “2010-07-01” authors = [“M. Berges”,“L. Soibelman”,“H. Scott Matthews”] publication_types = [“1”] publication = “Proceedings of the 6th International Conference on Innovation in Architecture, Engineering and Construction (AEC)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Enhancing Electricity Audits in Residential Buildings with Nonintrusive Load Monitoring” date = “2010-10-01” authors = [“M. Berges”,“E. Goldman”,“H. Scott Matthews”,“L. Soibelman”] publication_types = [“2”] publication = “Journal of Industrial Ecology“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1111/j.1530-9290.2010.00280.x"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Evaluating the Electric Consumption of Residential Buildings: Current Practices and Future Prospects” date = “2010-01-01” authors = [“M. Berges”,“L. Soibelman”,“H. Scott Matthews”,“E. Goldman”] publication_types = [“1”] publication = “Proceedings of the 2010 Construction Research Congress“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1061/41109(373)8"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Learning systems for electric consumption of buildings” date = “2009-01-01” authors = [“M. Berges”,“E. Goldman”,“H. Scott Matthews”,“L. Soibelman”] publication_types = [“1”] publication = “ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Leveraging Data From Environmental Sensors to Enhance Electrical Load Disaggregation Algorithms” date = “2010-06-01” authors = [“M. Berges”,“L. Soibelman”,“H. Scott Matthews”] publication_types = [“1”] publication = “Proceedings of the 13th International Conference on Computing in Civil and Building Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Poster Abstract: Appliance Classification and Energy Management Using Multi-Modal Sensing” date = “2011-01-01” authors = [“M. Berges”,“A. Rowe”] publication_types = [“1”] publication = “Proceedings of the 3rd ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Building“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A system for disaggregating residential electricity consumption by appliance” date = “2010-01-01” authors = [“M. Berges”,“H. Scott Matthews”,“L. Soibelman”] publication_types = [“1”] publication = “Sustainable Systems and Technology (ISSST), 2010 IEEE International Symposium on“ publication_short = “” abstract = “Research on Non-Intrusive Load Monitoring (NILM), a technique for discerning individual appliance operation from whole-house measurements, has been underway for over 20 years [4],[5]. Most implementations utilize changes in the total real (P) and reactive (Q) power of a building as signatures for each appliance state transition. There are a small number of commercially available systems that implement NILM, albeit marketed for utilities as a tool for performing load research. As a proof of concept, and in order to obtain preliminary data that would help us evaluate the feasibility of using NILM to support electricity audits in a residential building, we decided to focus our attention on one of the top residential loads: the refrigerator. We installed a NILM prototype system in an apartment building, and a plug-level power meter was used to accurately track the individual consumption of this appliance. The experiment consisted in monitoring this load for a week, using the two methodologies (NILM and pluglevel meters), and then comparing the estimated energy consumption as computed by each.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1109/ISSST.2010.5507758"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Towards Automated Detection and State Tracking of Artificial Light Sources From Sequential Pictures Inside Buildings” date = “2011-07-01” authors = [“M. Berges”,“E. Can Kara”,“E. Goldman”,“A. Rowe”] publication_types = [“1”] publication = “International Workshop on Intelligent Computing in Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Training Load Monitoring Algorithms on Highly Sub-Metered Home Electricity Consumption Data” date = “2008-01-01” authors = [“M. Berges”,“E. Goldman”,“H. Scott Matthews”,“L. Soibelman”] publication_types = [“2”] publication = “Tsinghua Science & Technology“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “User-centered Non-Intrusive Electricity Load Monitoring for Residential Buildings” date = “2011-01-01” authors = [“M. Berges”,“E. Goldman”,“L. Soibelman”,“H. Scott Matthews”,“K. Anderson”] publication_types = [“2”] publication = “Journal of Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “How Many Appliances does it take to…?” date = “2012-01-01” authors = [“D. R. Carlson”,“M. Berges”,“H. Scott Matthews”] publication_types = [“1”] publication = “1st International Workshop on Non-Intrusive Load Monitoring“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “One Size Does Not Fit All: Averaged Data on Household Electricity is Inadequate for Residential Energy Policy and Decisions” date = “2013-09-01” authors = [“D. Carlson”,“H. Scott Matthews”,“M. Berges”] publication_types = [“2”] publication = “Energy and Buildings“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.enbuild.2013.04.005"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Mobile visual clothing search” date = “2013-07-01”

# Authors. Comma separated list, e.g. ["Bob Smith", "David Jones"].

authors = [“GA Cushen”, “MS Nixon”]

# 6 = Book chapter

publication_types = [“1”]

# Publication name and optional abbreviated version.

publication = “In International Conference on Multimedia and Expo Workshops (ICMEW), IEEE.” publication_short = “In ICMEW

# Abstract and optional shortened version.

abstract = “We present a mobile visual clothing search system whereby a smart phone user can either choose a social networking photo or take a new photo of a person wearing clothing of interest and search for similar clothing in a retail database. From the query image, the person is detected, clothing is segmented, and clothing features are extracted and quantized. The information is sent from the phone client to a server, where the feature vector of the query image is used to retrieve similar clothing products from online databases. The phone’s GPS location is used to re-rank results by retail store location. State of the art work focuses primarily on the recognition of a diverse range of clothing offline and pays little attention to practical applications. Evaluated on a challenging dataset, the system is relatively fast and achieves promising results.” abstract_short = “A mobile visual clothing search system is presented whereby a smart phone user can either choose a social networking image or capture a new photo of a person wearing clothing of interest and search for similar clothing in a large cloud-based ecommerce database. The phone’s GPS location is used to re-rank results by retail store location, to inform the user of local stores where similar clothing items can be tried on.”

# Featured image thumbnail (optional)

image_preview = “”

selected = true

# Simply enter the filename (excluding ‘.md’) of your project file in content/project/.

projects = [“example-external-project”]

url_pdf = “http://eprints.soton.ac.uk/352095/1/Cushen-IMV2013.pdf" url_preprint = “http://eprints.soton.ac.uk/352095/1/Cushen-IMV2013.pdf" url_code = “#” url_dataset = “#” url_project = “#” url_slides = “#” url_video = “#” url_poster = “#” url_source = “#”

# Uncomment line below to enable. For multiple links, use the form [{...}, {...}, {...}].

url_custom = [{name = “Custom Link”, url = “http://example.org"}]

math = true

highlight = true

# Place your image in the static/img/ folder and reference its filename below, e.g. image = "example.jpg".

+++

More detail can easily be written here using Markdown and $\rm \LaTeX$ math code. +++ title = “Effects of Planning and Data Collection Approaches on the Quality of Processed Laser Scanned Data: Lessons Learned” date = “2012-01-01” authors = [“M. Eybpoosh”,“B. Akinci”,“M. Berges”] publication_types = [“1”] publication = “Construction Research Congress“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Effects of damage location and size on sparse representation of guided-waves for damage diagnosis of pipelines under varying temperature” date = “2015-01-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“1”] publication_short = “” abstract = “In spite of their many advantages, real-world application of guided-waves for structural health monitoring (SHM) of pipelines is still quite limited. The challenges can be discussed under three headings: (1) Multiple modes, (2) Multipath reflections, and (3) Sensitivity to environmental and operational conditions (EOCs). These challenges are reviewed in the authors’ previous work. This paper is part of a study whose objective is to overcome these challenges for damage diagnosis of pipes, while addressing the limitations of the current approaches. That is, develop methods that simplify signal while retaining damage information, perform well as EOCs vary, and minimize the use of transducers. In this paper, a supervised method is proposed to extract a sparse subset of the ultrasonic guided-wave signals that contain optimal damage information for detection purposes. That is, a discriminant vector is calculated so that the projections of undamaged and damaged pipes on this vector is separated. In the training stage, data is recorded from intact pipe, and from a pipe with an artificial structural abnormality (to simulate any variation from intact condition). During the monitoring stage, test signals are projected on the discriminant vector, and these projections are used as damage-sensitive features for detection purposes. Being a supervised method, factors such as EOC variations, and difference in the characteristics of the structural abnormality in training and test data, may affect the detection performance. This paper reports the experiments investigating the extent to which the differences in damage size and damage location, as well as temperatures, can influence the discriminatory power of the extracted damage-sensitive features. The results suggest that, for practical ranges of monitoring and damage sizes of interest, the proposed method has low sensitivity to such training factors. High detection performances are obtained for temperature differences up to 14°C. The findings reported in this paper suggest that although the proposed method is a supervised approach, labeling of the training data does not require prior knowledge about the damage characteristics (e.g., size, location). Moreover, the potential of the proposed method for online monitoring is illustrated, for wide range of temperature variations and different damage scenarios.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1117/12.2084439"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “An energy-based sparse representation of ultrasonic guided-waves for online damage detection of pipelines under varying environmental and operational conditions” date = “2016-01-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“2”] publication = “Mechanical Systems and Signal Processing“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Investigation on the effects of environmental and operational conditions (EOC) on diffuse-field ultrasonic guided-waves in pipes” date = “2014-06-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Nonlinear feature extraction methods for removing temperature effects in multi-mode guided-waves in pipes” date = “2015-01-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“1”] publication_short = “” abstract = “Ultrasonic guided-waves propagating in pipes with varying environmental and operational conditions (EOCs) are usually the results of complex superposition of multiple modes travelling in multiple paths. Among all of the components forming a complex guided-wave signal, the arrivals scattered by damage (so called scatter signal) are of importance for damage diagnosis purposes. This paper evaluates the potentials of nonlinear decomposition methods for extracting the scatter signal from a multi-modal signal recorded from a pipe under varying temperatures. Current approaches for extracting scatter signal can be categorized as (A) baseline subtraction methods, and (B) linear decomposition methods. In this paper, we first illustrate, experimentally, the challenges for applying these methods on multi-modal signals at varying temperatures. To better analyze the experimental results, the effects of temperature on multi-modal signals are simulated. The simulation results show that different wave modes may have significantly different sensitivities to temperature variations. This brings about challenges such as shape distortion and nonlinear relations between the signals recorded at different temperatures, which prevent the aforementioned methods to be extensible to wide range of temperatures. In this paper, we examine the potential of a nonlinear decomposition method, namely nonlinear principal component analysis (NLPCA), for removing the nonlinear relation between the components of a multi-modal guided-wave signal, and thus, extracting the scatter signal. Ultrasonic pitch-catch measurements from an aluminum pipe segment in a thermally controlled laboratory are used to evaluate the detection performance of the damage-sensitive features extracted by the proposed approach. It is observed that NLPCA can successfully remove nonlinear relations between the signal bases, hence extract scatter signal, for temperature variations up to 10℃, with detection accuracies above 99%.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1117/12.2084436"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Sparse representation of ultrasonic guided-waves for robust damage detection in pipelines under varying environmental and operational conditions” date = “2016-02-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“2”] publication = “Structural Control and Health Monitoring“ publication_short = “” abstract = “The challenges of guided-wave based structural health monitoring can be discussed under three headings: (a) multiple modes, (b) multi-path reflections, and © sensitivity to environmental and operational conditions (EOCs). The objective of this paper is to develop damage detection methods that simplify guided-wave signals while retaining damage information and have low sensitivity to EOC variations. A supervised method is proposed for damage detection. The detection performance is maximized, by imposing a sparsity constraint on the signals. This paper reports a diverse set of laboratory and field experiments validating the extent to which EOC variations, as well as damage characteristics can influence the discriminatory power of the damage-sensitive features. The laboratory setup includes an aluminum pipe with temperature varying between 24 and 38 ° C. The method is further validated using an operational hot water supply piping system of different size and configuration than the one used in the laboratory, which operates under noisy environment, with constantly varying flow rate, temperature, and inner pressure. Moreover, the proposed method is used to detect occurrence of consecutive actual damages, namely, a crack and a mass loss as small as 10% and 8% of the wall thickness, respectively. The validation results suggest that a simple binary-labeled training data (i.e., undamaged/damaged), obtained under a limited range of EOCs, are sufficient for the proposed method. That is, the detection method does not require prior knowledge about the characteristics of the damage (e.g., size, type, and location), and/or a training dataset that is obtained from a wide range of EOCs. Copyright © 2015 John Wiley & Sons, Ltd.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1002/stc.1776"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A Taxonomy for Depicting Geospatial Deviations of Facilities Extracted through Comparisons between Point Clouds and Building Information Models” date = “2012-01-01” authors = [“M. Eybpoosh”,“B. Akinci”,“M. Berges”] publication_types = [“1”] publication = “ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1061/9780784412343.0062"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Temperature variation effects on sparse representation of guided-waves for damage diagnosis in pipelines” date = “2015-01-01” authors = [“M. Eybpoosh”,“M. Berges”,“H. Young Noh”] publication_types = [“1”] publication_short = “” abstract = “Multiple ultrasonic guided-wave modes propagating along a pipe travel with different velocities which are themselves a function of frequency. Reflections from the features of the structure (e.g., boundaries, pipe welding, damage, etc.), and their complex superposition, adds to the complexity of guided-waves. Guided-wave based damage diagnosis of pipelines becomes even more challenging when environmental and operational conditions (EOCs) vary (e.g., temperature, flow rate, inner pressure, etc.). These complexities make guided-wave based damage diagnosis of operating pipelines a challenging task. This paper reviews the approaches to-date addressing these challenges, and highlights the preferred characteristics of a method that simplifies guided-wave signals for damage diagnosis purposes. A method is proposed to extract a sparse subset of guided-wave signals in time-domain, while retaining optimal damage information for detection purpose. In this paper, the general concept of this method is proved through an extensive set of experiments. Effects of temperature variation on detection performance of the proposed method, and on discriminatory power of the extracted damage-sensitive features are investigated. The potential of the proposed method for real-time damage detection is illustrated, for wide range of temperature variation scenarios (i.e., temperature difference between training and test data varying between -2°C and 13°C).” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1117/12.2084434"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A Data-driven Meta-data Inference Framework for Building Automation Systems” date = “2015-01-01” authors = [“J. Gao”,“J. Ploennigs”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2Nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/2821650.2821670"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A feasibility study of automated plug-load identification from high-frequency measurements” date = “2015-12-01” authors = [“J. Gao”,“E. Can Kara”,“S. Giri”,“M. Berges”] publication_types = [“1”] publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “PLAID: a public dataset of high-resoultion electrical appliance measurements for load identification research: demo abstract” date = “2014-01-01” authors = [“J. Gao”,“S. Giri”,“E. Can Kara”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “An energy estimation framework for event-based methods in Non-Intrusive Load Monitoring” date = “2015-01-01” authors = [“S. Giri”,“M. Berges”] publication_types = [“2”] publication = “Energy Conversion and Management“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “An error correction framework for sequences resulting from known state-transition models in Non-Intrusive Load Monitoring” date = “2017-04-01” authors = [“S. Giri”,“M. Berges”] publication_types = [“2”] publication = “Advanced Engineering Informatics“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.aei.2017.01.006"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Novel Techniques For ON and OFF states detection of appliances for Power Estimation in Non-Intrusive Load Monitoring” date = “2013-08-01” authors = [“S. Giri”,“P. Lai”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the The 30th International Symposium on Automation and Robotics in Construction and Mining (ISARC)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A study on the feasibility of automated data labeling and training using an EMF sensor in NILM platforms” date = “2012-07-01” authors = [“S. Giri”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2012 International EG-ICE Workshop on Intelligent Computing“ publication_short = “” abstract = “Non-Intrusive Load Monitoring (NILM) has been studied for a few decades now as a method of disaggregating information about appliance level power consumption in a building from measurements obtained at a centralized location in the electrical system. The training phase required at the beginning of a NILM setup is a big hindrance to wide adoption of the technique. One of the recent advances in this research area includes the addition of an Electro-Magnetic Field (EMF) sensor that measures the electric and magnetic field around an appliance to detect its state. This information, when coupled with the aggregate power data, can effectively train a NILM system almost automatically, which is a significant step towards automating the training phase. This paper explores the theory behind the operation of the EMF sensor and analyzes the feasibility in terms of automating the training and classification process. It then outlines our plan for further analysis.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Towards automatic classification of appliances: Tackling cross talk in EMF sensors using blind source separation techniques” date = “2013-07-01” authors = [“S. Giri”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2013 International EG-ICE Workshop on Intelligent Computing“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Towards automated appliance recognition using an EMF sensor in NILM platforms” date = “2013-10-01” authors = [“S. Giri”,“M. Berges”,“A. Rowe”] publication_types = [“2”] publication = “Advanced Engineering Informatics“ publication_short = “” abstract = “Non-Intrusive Load Monitoring (NILM) has been studied for a few decades now as a method of disaggregating information about appliance level power consumption in a building from aggregate measurements of voltage and/or current obtained at a centralized location in the electrical system. When such information is provided to the electricity consumer as feedback, they can then take the necessary steps to modify their behavior and conserve electricity. Research has shown potential for savings of up to 20% through this kind of feedback. The training phase required to allow the algorithms to recognize appliances in the home at the beginning of a NILM setup is a big hindrance to wide adoption of the technique. One of the recent advances in this research area includes the addition of an Electro-Magnetic Field (EMF) sensor that measures the electric and magnetic field nearby an appliance to detect its operational state. This information, when coupled with the aggregate power consumption data for the home, can help to train a NILM system, which is a significant step forward in automating the training phase. This paper explores the theory behind the operation of the EMF sensor and discusses the feasibility of automating the training and classification process using these devices. A case study is presented, where magnetic field measurements of eight appliances are analyzed to determine the viability of using these signals alone to determine the type of appliance that the EMF sensor has been placed next to. Various dimensionality reduction techniques are applied to the collected data, and the resulting feature vectors are used to train a variety of common machine learning classifiers. A vector subspace obtained using Independent Component Analysis (ICA), along with a k-NN classifier, was found to perform best among the different alternatives explored. Possible reasons behind the findings are discussed and areas for further exploration are proposed.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.aei.2013.03.004"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Virtual metering of electrical appliances through analysis of data from contactless sensing” date = “2015-12-01” authors = [“S. Giri”,“M. Berges”] publication_types = [“1”] publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Exploratory Study Towards Streamlining the Identification of Sensor Locations Within a Facility” date = “2014-06-01” authors = [“A. Gomez”,“M. Berges”,“B. Akinci”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Lessons Learned from Monitoring Electricity Consumption in a Research Lab Through a Capstone Project Course” date = “2014-06-01” authors = [“A. Gomez Rivera”,“S. Guindon”,“T. Pianka”,“N. Patel”,“V. Kasireddy”,“E. Li”,“J. Li”,“S. Ergan”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” abstract = “This paper describes the experiences and lessons learned by a team of Civil and Environmental Engineering graduate students during a capstone project-based course, which orients students to acquire knowledge on sensing technologies, data management, systems engineering, and visualization concepts in order to design and implement an energy monitoring system in a three room lab space. The team, mentored by faculty members, was responsible for the deployment of hardware, establishing communications, database design and implementation, and developing visualizations to communicate the relevant information based on the requirements of a client role-played by a faculty member. Lessons learned from this project include the importance of applying a systems engineering approach during the iterative scope definition and design processes, and the use of alternative communications, learning, and problem-solving methods in order to tackle challenges of larger scope and complexity than presented in classroom-setting coursework, while working on a team environment.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Unsupervised disaggregation of appliances using aggregated consumption data” date = “2011-08-01” authors = [“H. Goncalves”,“A. Ocneanu”,“M. Berges”] publication_types = [“1”] publication = “1st KDD Workshop on Data Mining Applications in Sustainability (SustKDD)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Ultrasonic guided wave detection of scatterers on large clad steel plates” date = “2016-01-01” authors = [“P. Gong”,“J. B. Harley”,“M. Berges”,“W. R. Junker”,“D. W. Greve”,“I. J. Oppenheim”] publication_types = [“1”] publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1117/12.2214393"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Towards Passive Training for Non-Intrusive Load Monitoring” date = “2013-07-01” authors = [“F. Jazizadeh”,“B. Becerik-Gerber”,“L. Soibelman”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2013 International EG-ICE Workshop on Intelligent Computing“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Unsupervised Clustering of Residential Electricity Consumption Measurements for Facilitated User-Centric Non-Intrusive Load Monitoring” date = “2014-06-01” authors = [“F. Jazizadeh”,“B. Becerik-Gerber”,“M. Berges”,“L. Soibelman”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “An unsupervised hierarchical clustering based heuristic algorithm for facilitated training of electricity consumption disaggregation systems” date = “2014-01-01” authors = [“F. Jazizadeh”,“B. Becerik-Gerber”,“M. Berges”,“L. Soibelman”] publication_types = [“2”] publication = “Advanced Engineering Informatics“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information” date = “2018-01-01” authors = [“Z. Jiang”,“J. Francis”,“A. Kumar Sahu”,“S. Munir”,“C. Shelton”,“A. Rowe”,“M. Berges”] publication_types = [“1”] publication = “American Control Conference (ACC), 2018“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Robust adaptive event detection in non-intrusive load monitoring for energy aware smart facilities” date = “2011-05-01” authors = [“Y. Jin”,“E. Tebekaemi”,“M. Berges”,“L. Soibelman”] publication_types = [“1”] publication = “Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A time-frequency approach for event detection in non-intrusive load monitoring” date = “2011-01-01” authors = [“Y. Jin”,“E. Tebekaemi”,“M. Berges”,“L. Soibelman”] publication_types = [“1”] publication = “Proceedings of the Signal Processing, Sensor Fusion, and Target Recognition XX“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1117/12.884385"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Anomaly Detection on Piezometer Data Collected from Embankment Dams Using Physical Model-Based Simulation” date = “2014-06-01” authors = [“I. Jung”,“M. Berges”,“J. H. Garrett Jr.”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Exploration and evaluation of AR, MPCA and KL anomaly detection techniques to embankment dam piezometer data” date = “2015-10-01” authors = [“I. Jung”,“M. Berges”,“J. H. Garrett Jr.”,“B. Poczos”] publication_types = [“2”] publication = “Advanced Engineering Informatics“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.aei.2015.10.002"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Interpreting the Dynamics of Embankment Dams through a Time-Series Analysis of Multiple Piezometer Data Using a Non-Parametric Spectral Estimation Method” date = “2013-06-01” authors = [“I. Jung”,“M. Berges”,“J. H. Garrett”,“C. Kelly”] publication_types = [“1”] publication = “Proceedings of the 2013 ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Towards Dam Information Modeling: Best Practices Learned From the AEC/FM Domain” date = “2013-08-01” authors = [“I. Jung”,“J. Fraizer”,“B. Akinci”,“M. Berges”,“E. Semiha”,“J. H. Garrett”,“C. Kelly”] publication_types = [“1”] publication = “Proceedings of the 2013 International Commission on Large Dams (ICOLD)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Electric load prediction baseline for airport buildings: A case study” date = “2016-06-01” authors = [“M. Kang”,“M. Berges”,“B. Akinci”] publication_types = [“1”] publication = “Proceedings of the 2016 Construction Research Congress“ publication_short = “” abstract = “Given their large energy footprint and the availability of building energy management systems, airports are uniquely positioned to take advantage of demand response (DR) programs. Although a baseline, which is the estimation of what the load would have been without load reduction, is essential to assess the performance of DR strategies, however, there has been very little published research on developing baselines for airports. Therefore, the research described in this paper aims to develop baseline models specifically intended for airport facilities. Specifically, we propose piece-wise linear regression models for predicting electricity demand using time-of-week, temperature, and flight schedule information. We hypothesize that flight schedule information would help explain a significant portion of the load after temperature and time-of-week information has been accounted for. However, the result reveals that a model with time-of-week and temperature as input variables and trained over specific seasonal data have the best prediction performance. The number of passengers of departure flight schedule is shown to have a positive relationship with the load, but does not improve the model accuracy significantly.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Forecasting Airport Building Electricity Demand Based on Flight Schedule Information for Demand Response Applications” date = “2017-01-01” authors = [“M. Kang”,“M. Berg’es”,“B. Akinci”] publication_types = [“1”] publication = “Transportation Research Board 96th Annual Meeting Compendium of Papers“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Demand Response in Buildings: Engaging Thermostatically Controlled Loads in the Power Grid” date = “2013-06-01” authors = [“E. Can Kara”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2013 ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Estimating the benefits of electric vehicle smart charging at non-residential locations: A data-driven approach “ date = “2015-01-01” authors = [“E. C. Kara”,“J. S. Macdonald”,“D. Black”,“M. Berges”,“G. Hug”,“S. Kiliccote”] publication_types = [“2”] publication = “_Applied Energy _” publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/http://dx.doi.org/10.1016/j.apenergy.2015.05.072"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Impact of Disturbances on Modeling of Thermostatically Controlled Loads for Demand Response” date = “2015-01-01” authors = [“E. Can Kara”,“M. Berges”,“G. Hug”] publication_types = [“2”] publication = “IEEE Transactions on Smart Grid“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1109/TSG.2015.2406316"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Modeling Thermostatically Controlled Loads to Engage Households in the Smart Grid: Lessons Learned from Residential Refrigeration Units” date = “2014-06-01” authors = [“E. Can Kara”,“M. Berges”,“G. Hug”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A Moving Horizon State Estimator in the Control of Thermostatically Controlled Loads for Demand Response” date = “2013-09-01” authors = [“E. Can Kara”,“Z. Kolter”,“M. Berges”,“B. Krogh”,“G. Hug”,“T. Yuksel”] publication_types = [“1”] publication = “Proceedings of the 4th International Conference on Smart Grid Communications (SmartGridComm)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Using Smart Devices for System-level Management and Control in the Smart Grid: A Reinforcement Learning Framework” date = “2012-11-01” authors = [“E. Can Kara”,“M. Berges”,“K. Bruce H.”,“S. Kar”] publication_types = [“1”] publication = “Proceedings of the 3rd International Conference on Smart Grid Communications (SmartGridComm)“ publication_short = “” abstract = “This paper presents a stochastic modeling framework to employ adaptive control strategies in order to provide short term ancillary services to the power grid by using a population of heterogenous thermostatically controlled loads. A classical Markov Decision Process (MDP) representation is developed to leverage existing tools in the field of reinforcement learning. Initial considerations and possible reductions in the action and state spaces are described. A Q-learning approach is implemented in simulation to demonstrate the performance of the presented adaptive control framework on a reference tracking scenario.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Comparison of linear correlation and a statistical dependency measure for inferring spatial relation of temperature sensors in buildings” date = “2014-01-01” authors = [“M. Koc”,“B. Akinci”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “BOLT: Energy Disaggregation by Online Binary Matrix Factorization of Current Waveforms” date = “2016-01-01” authors = [“H. Lange”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Efficient Inference in Dual-emission FHMM for Energy Disaggregation” date = “2016-02-01” authors = [“H. Lange”,“M. Berges”] publication_types = [“1”] publication = “Workshops at the Thirtieth AAAI Conference on Artificial Intelligence“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “The Nerual Energy Decoder: Energy Disaggregation by Combining Binary Subcomponents” date = “2016-05-01” authors = [“H. Lange”,“M. Berges”] publication_types = [“1”] publication = “3rd International Workshop on Non-Intrusive Load Monitoring“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Variational BOLT: Approximate Learning in Factorial Hidden Markov Models With Application to Energy Disaggregation” date = “2018-01-01” authors = [“H. Lange”,“M. Berges”] publication_types = [“1”] publication = “AAAI’18: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Assessment of Industry Foundation Classes (IFC) in Supporting Building Energy Benchmarking” date = “2015-10-01” authors = [“X. Lei”,“M. Kang”,“M. Berges”,“B. Akinci”] publication_types = [“1”] publication = “Proceedings of the 32nd CIB W78 Conference 2015“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Poster: COD: A Dataset of Commercial Building Occupancy Traces” date = “2017-01-01” authors = [“K. Sum Liu”,“E. Vindel Pinto”,“S. Munir”,“J. Francis”,“C. Shelton”,“M. Berges”,“S. Lin”] publication_types = [“1”] publication = “Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Domain-Specific Querying Formalisms for Retrieving Information of HVAC Systems” date = “2013-02-01” authors = [“X. Liu”,“B. Akinci”,“M. Berges”,“J. H. Garrett”] publication_types = [“2”] publication = “Journal of Computing in Civil Engineering“ publication_short = “” abstract = “In order to save energy and improve the control of indoor environments, researchers have developed hundreds of computer algorithms that can automatically and continuously analyze the conditions of Heating, Ventilation and Air-Conditioning (HVAC) systems. However, the complex information requirements of these algorithms inhibit deploying them in real-world facilities. We propose an integrated performance analysis framework that automatically collects, merges and provides the information required by them. In previous studies, we have identified a general set of information requirements for the computerized approaches and formalized a semi-automated approach that integrates multiple data models to support the required information. In order to automatically retrieve the information required by different approaches, the research discussed in this paper explored a query mechanism that can represent the required information in a formal way that can be reasoned about. We categorize the information items that are used to represent the information needs, formalize a domain-specific query language that can formally represent the query statements, and develop a library of mechanisms that can automatically reason about and retrieve the needed information. In order to validate the performance of the query language and mechanisms, we also developed a prototype, which includes a graphic user interface that helps users to define the queries, and the implementation of the reasoning mechanisms that process the queries. The precision and recall of the query language and mechanisms were tested using the queries identified from previous research.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1061/(ASCE)CP.1943-5487.0000294"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Exploration and Comparison of Approaches for Integrating Heterogeneous Information Sources to Support Performance Analysis of HVAC Systems” date = “2012-01-01” authors = [“X. Liu”,“B. Akinci”,“M. Berges”,“J. H. Garrett Jr”] publication_types = [“1”] publication = “ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Extending the information delivery manual approach to identify information requirements for performance analysis of HVAC systems” date = “2013-01-01” authors = [“X. Liu”,“B. Akinci”,“M. Berges”,“J. H. Garrett Jr.”] publication_types = [“2”] publication = “Advanced Engineering Informatics“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.aei.2013.05.003"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Identifying Pipe Degradation In a Highly Dynamic Environment Using Singular Value Decomposition” date = “2013-09-01” authors = [“C. Liu”,“J. B. Harley”,“D. Greve”,“M. Berges”,“I. Oppenheim”] publication_types = [“1”] publication = “Proceedings of the Ninth International Workshop on Structural Health Monitoring“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “An Integrated Performance Analysis Framework for HVAC Systems Using Heterogeneous Data Models and Building Automation Systems” date = “2012-01-01” authors = [“X. Liu”,“B. Akinci”,“M. Berges”,“J. H. Garrett”] publication_types = [“1”] publication = “Proceedings of the 4th ACM Workshop on Embedded Systems for Energy-Efficiency in Building“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Requirements and Development of a Computerized Approach for Analyzing Functional Relationships Among HVAC Components Using Building Information Models” date = “2011-01-01” authors = [“X. Liu”,“B. Akinci”,“J. H. Garrett Jr”,“M. Berges”] publication_types = [“1”] publication = “CIB W078 - W102“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Requirements for an Integrated Framework of Self-Managing HVAC Systems” date = “2011-01-01” authors = [“X. Liu”,“B. Akinci”,“J. Garrett Jr”,“M. Berges”] publication_types = [“1”] publication = “ASCE International Workshop on Computing in Civil Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Requirements for A Formal Approach to Represent Information Exchange Requirements of a Self-managing Framework for HVAC Systems” date = “2012-07-01” authors = [“X. Liu”,“B. Akinci”,“J. H. Garrett”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2012 International Conference on Computing in Civil and Building Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Robust change detection in highly dynamic guided wave signals with singular value decomposition” date = “2012-01-01” authors = [“C. Liu”,“J. Harley”,“N. O’Donoughue”,“Y. Ying”,“M. H Altschul”,“M. Berg’es”,“J. H Garrett”,“D. W Greve”,“J. MF Moura”,“I. J Oppenheim”,“o. “] publication_types = [“1”] publication = “Ultrasonics Symposium (IUS), 2012 IEEE International“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A robust baseline removal method for guided wave damage localization” date = “2014-01-01” authors = [“C. Liu”,“J. B Harley”,“M. Berges”,“D. W Greve”,“W. R Junker”,“I. J Oppenheim”] publication_types = [“1”] publication = “SPIE Smart Structures and Materials+ Nondestructive Evaluation and Health Monitoring“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Robust ultrasonic damage detection under complex environmental conditions using singular value decomposition” date = “2015-04-01” authors = [“C. Liu”,“J. B. Harley”,“M. Berges”,“D. W. Greve”,“I. J. Oppenheim”] publication_types = [“2”] publication = “Ultrasonics“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1016/j.ultras.2014.12.005"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Singular value decomposition for novelty detection in ultrasonic pipe monitoring” date = “2013-02-01” authors = [“C. Liu”,“J. B. Harley”,“Y. Ying”,“M. Berges”,“J. H. Garrett”,“D. Greve”,“I. Oppenheim”] publication_types = [“1”] publication = “Proceedings of the 2013 SPIE Smart Structures/NDE Conference“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Ultrasonic Scatterer Detetion in a Pipe Under Operating Conditions Using Singular Value Decomposition” date = “2012-07-01” authors = [“C. Liu”,“J. B. Harley”,“N. O’Donoughue”,“Y. Ying”,“M. Berges”,“M. H. Altschul”,“J. H. Garrett”,“D. Greve”,“J. M. F. Moura”,“I. Oppenheim”,“L. Soibelman”] publication_types = [“1”] publication = “39th Annual Review of Progress in Quantitative Nondestructive Evaluation“ publication_short = “” abstract = “Pipes carrying fluids under pressure are critical components in infrastructure and industry. Piezoelectric transducers bonded to the pipe produce guided waves that propagate long distances and illuminate the whole pipe, providing a promising tool for pipe structure health monitoring. However it is difficult to recognize the change produced by a scatterer because of the many wave modes and wave paths. Moreover, under operating conditions, the environmental and operational variations produce significant changes in pitch-catch signals, which would produce false-positive results with conventional change detection methods. We instrumented pressurized pipe segments in a working hot-water supply system that experiences ongoing variations in pressure, temperature, and flow rate in an environment that is noisy mechanically and electrically. We conducted pitch-catch tests between transducers located roughly 16 diameters apart on a 10-in. pipe. We show significant environmental and operational variations, even after temperature compensation. At several different time intervals we applied and removed a grease-coupled mass scatterer on the pipe as a physical simulation of damage. We then use singular value decomposition (SVD) to build a change detector that is sensitive to the mass scatterer but insensitive to the changes produced by operational and environmental variations, and we show examples of its successful performance on field experiments data. We show that specific components are associated with the changes produced by the mass scatterer, while others are associated with the environmental variations.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Ultrasonic Monitoring of a Pressurized Pipe in Operation” date = “2013-04-01” authors = [“C. Liu”,“J. B. Harley”,“Y. Ying”,“M. H. Altschul”,“M. Berges”,“D. Greve”,“J. M. F. Moura”,“I. Oppenheim”,“L. Soibelman”] publication_types = [“1”] publication = “Proceedings of the 2013 ASCE Structures Congress“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Optimal Sensor Placement for Urban Heat Risk Response” date = “2016-01-01” authors = [“C. Malings”,“M. Pozzi”,“K. Klima”,“E. Bou-Zeid”,“P. Ramamurthy”,“M. Berges”] publication_types = [“1”] publication = “13th International Conference on Probabilistic Safety Assessment and Management (PSAM 13). Seoul, Republic of Korea“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Surface heat assessment for developed environments: Probabilistic urban temperature modeling” date = “2017-01-01” authors = [“C. Malings”,“M. Pozzi”,“K. Klima”,“M. Berges”,“E. Bou-Zeid”,“P. Ramamurthy”] publication_types = [“2”] publication = “Computers, Environment and Urban Systems“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/https://doi.org/10.1016/j.compenvurbsys.2017.07.006"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Automatically disaggregating the total electrical load in residential buildings: a profile of the required solution” date = “2008-01-01” authors = [“H. Scott Matthews”,“L. Soibelman”,“M. Berges”,“E. Goldman”] publication_types = [“1”] publication = “International Workshop on Intelligent Computing in Engineering“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Information Exchange Requirements to Support Commissioning of HVAC and Building Envelope Components During an Energy Retrofit Project - A Comparative Case Study” date = “2014-06-01” authors = [“M. Mora”,“A. Burcu”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 2014 International Conference on Computing in Civil and Building Engineering (ICCCBE)“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Demo: FORK: Fine grained Occupancy estimatoR using Kinect on ARM Embedded Platforms” date = “2017-01-01” authors = [“S. Munir”,“J. Francis”,“C. Shelton”,“R. Singh Arora”,“C. Hesling”,“M. Quintana”,“A. Rowe”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Real-Time Fine Grained Occupancy Estimation using Depth Sensors on ARM Embedded Platforms” date = “2017-01-01” authors = [“S. Munir”,“R. Singh Arora”,“C. Hesling”,“J. Li”,“J. Francis”,“C. Shelton”,“C. Martin”,“A. Rowe”,“M. Berges”] publication_types = [“1”] publication = “Real-Time and Embedded Technology and Applications Symposium (RTAS), 2017 IEEE“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1109/RTAS.2017.8"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Deploying and evaluating the effectiveness of energy eco-feedback through a low-cost NILM solution” date = “2011-06-01” authors = [“N. Nunes”,“L. Pereira”,“F. Quintal”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 6th International Conference on Persuasive Technology“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Exploring Sequential and Association Rule Mining for Pattern-based Energy Demand Characterization” date = “2013-01-01” authors = [“L. Ong”,“M. Berges”,“H. Young Noh”] publication_types = [“1”] publication = “Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/2528282.2528308"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Mortar.io: a concrete building automation system: demo abstract” date = “2014-01-01” authors = [“C. Palmer”,“P. Lazik”,“M. Buevich”,“J. Gao”,“M. Berges”,“A. Rowe”,“R. Lopes Pereira”,“C. Martin”] publication_types = [“1”] publication = “Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “The Design of a Hardware-software Platform for Long-term Energy Eco-feedback Research” date = “2012-06-01” authors = [“L. Pereira”,“F. Quintal”,“N. J. Nunes”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 4th ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS)“ publication_short = “” abstract = “Researchers often face engineering problems, such as optimizing prototype costs and ensuring easy access to the collected data, which are not directly related to the research problems being studied. This is especially true when dealing with long-term studies in real world scenarios. This paper describes the engineering perspective of the design, development and deployment of a long-term real word study on energy eco-feedback, where a non-intrusive home energy monitor was deployed in 30 houses for 18 months. Here we report on the efforts required to implement a costeffective non-intrusive energy monitor and, in particular, the construction of a local network to allow remote access to multiple monitors and the creation of a RESTful webservice to enable the integration of these monitors with social media and mobile software applications. We conclude with initial results from a few eco-feedback studies that were performed using this platform.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/2305484.2305521"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “SURF and SURF-PI: a file format and API for non-intrusive load monitoring public datasets” date = “2014-01-01” authors = [“L. Pereira”,“N. Nunes”,“M. Berg’es”] publication_types = [“1”] publication = “Proceedings of the 5th international conference on Future energy systems“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/2602044.2602078"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A Person Re-Identification System For Mobile Devices” date = “2015-09-01”

# Authors. Comma separated list, e.g. ["Bob Smith", "David Jones"].

authors = [“GA Cushen”]

# 6 = Book chapter

publication_types = [“2”]

# Publication name and optional abbreviated version.

publication = “In Signal Image Technology & Internet Systems (SITIS), IEEE.” publication_short = “In SITIS

# Abstract and optional shortened version.

abstract = “Person re-identification is a critical security task for recognizing a person across spatially disjoint sensors. Previous work can be computationally intensive and is mainly based on low-level cues extracted from RGB data and implemented on a PC for a fixed sensor network (such as traditional CCTV). We present a practical and efficient framework for mobile devices (such as smart phones and robots) where high-level semantic soft biometrics are extracted from RGB and depth data. By combining these cues, our approach attempts to provide robustness to noise, illumination, and minor variations in clothing. This mobile approach may be particularly useful for the identification of persons in areas ill-served by fixed sensors or for tasks where the sensor position and direction need to dynamically adapt to a target. Results on the BIWI dataset are preliminary but encouraging. Further evaluation and demonstration of the system will be available on our website.” abstract_short = “”

# Featured image thumbnail (optional)

image_preview = “”

selected = false

# Simply enter the filename (excluding ‘.md’) of your project file in content/project/.

projects = [“deep-learning”]

url_pdf = “http://arxiv.org/pdf/1512.04133v1" url_preprint = “” url_code = “” url_dataset = “” url_project = “” url_slides = “” url_video = “” url_poster = “” url_source = “”

math = true

highlight = true

# Place your image in the static/img/ folder and reference its filename below, e.g. image = "example.jpg".

[header] image = “” caption = “”

+++

More detail can easily be written here using Markdown and $\rm \LaTeX$ math code. +++ title = “SINAIS: home consumption package: a low-cost eco-feedback energy-monitoring research platform” date = “2010-01-01” authors = [“F. Quintal”,“N. J Nunes”,“A. Ocneanu”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 8th ACM Conference on Designing Interactive Systems“ publication_short = “” abstract = “This paper describes a low cost eco-feedback energy monitoring research platform. The prototype system developed in Quartz Composer uses the computer’s audio input and a current transformer to calculate real-time energy usage while also offering multiple visualization options and tracking human-activities. The prototype is being used in a multidisciplinary research project to understand the long-term effects of eco-feedback and enduring behavioral changes towards practices that promote sustainability.” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/1858171.1858252"}] math = true highlight = true [header] image = “” caption = “” +++

ACM ID: 1858252 +++ title = “Demo: Design and Implementation of a Low-cost Arduino-based High-Frequency AC Waveform Meter Board for the Raspberry Pi” date = “2017-01-01” authors = [“M. Quintana”,“H. Lange”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments“ publication_short = “” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Demo Abstract: A Magnetic Field-based Appliance Metering System” date = “2013-04-01” authors = [“N. Rajagopal”,“A. Rowe”,“S. Giri”,“M. Berges”] publication_types = [“1”] publication = “Proceedings of the 12th ACM/IEEE International Conference on Information Processing in Sensor Networks“ publication_short = “” abstract = “In this demonstration, we show an energy measurement system that estimates the energy consumption of individual appliances using a wireless sensor network consisting of contactless electromagnetic field (EMF) sensors deployed near each appliance, and a whole-house power meter [1]. The EMF sensor can detect appliance state transitions within close proximity based on magnetic fluctuations. Data from these sensors are then relayed back to the main meter using a low-latency wireless sensor networking protocol, where changes in the total power consumption of the house are used to determine the power usage of individual appliances. The sensors are low-cost, easy to deploy and are able to detect current changes associated with the appliance from a few inches away making it possible to externally monitor in-wall wiring to devices like overhead lights or heavy machinery that might operate on multiple phases of the AC distribution system of the building. Appliance-level energy data provide continuous feedback to end users about their consumption patterns and provide building managers accurate information that can be used to target the most effective update and retrofit strategies.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “A Magnetic Field-based Appliance Metering System” date = “2013-04-01” authors = [“N. Rajagopal”,“S. Giri”,“A. Rowe”,“M. Berges”] publication_types = [“1”] publication = “ACM/IEEE Third International Conference on Cyber-Physical Systems“ publication_short = “” abstract = “Understanding where energy is being used in buildings is an important CPS component that can help improve energy conservation and efficiency. Current approaches for appliance-level energy metering typically require the installation of plug-through power meters, which is often difficult and costly for devices with inaccessible wires or outlets, or appliances that draw large amounts of current. In this paper, we present an energy measurement system that estimates the energy consumption of individual appliances using a wireless sensor network consisting of contactless electromagnetic field (EMF) sensors deployed near each appliance, and a whole-house power meter. We present the design of a battery-operated EMF sensor, which can detect appliance state transitions within close proximity based on magnetic and electric field fluctuations. Each detector wirelessly transmits state change events to a circuit-panel energy meter, in a time-synchronized fashion, so that the overall power measurements can be used to estimate appliance-level energy usage. The time synchronization and data throughput requirements of this problem motivated the development of a new low-power TDMA sensor networking protocol. Our EMF sensors are able to detect significant power state changes from a few inches away, thus making it possible to externally monitor in-wall wiring to devices. We experimentally evaluate our proposed EMF sensor, three-phase power meter and communication protocol in a residential building collecting data for over a week. The system is able to estimate appliance energy consumption with an average accuracy of 95.8%.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Contactless sensing of appliance state transitions through variations in electromagnetic fields” date = “2010-01-01” authors = [“A. Rowe”,“M. Berges”,“R. Rajkumar”] publication_types = [“1”] publication = “Proceedings of the 2nd ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Building“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1145/1878431.1878437"}] math = true highlight = true [header] image = “” caption = “” +++ +++ title = “Sensor Andrew: Large-scale campus-wide sensing and actuation” date = “2011-01-01” authors = [“A. Rowe”,“M. Berges”,“G. Bhatia”,“E. Goldman”,“R. Rajkumar”,“J. H. Garrett”,“J. M. F. Moura”,“L. Soibelman”] publication_types = [“2”] publication = “IBM Journal of Research and Development“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1147/JRD.2010.2089662"}] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Data Fusion Approaches and Applications for Construction Engineering” date = “2011-01-01” authors = [“S. M. Shahandashti”,“S. N. Razavi”,“L. Soibelman”,“M. Berges”,“C. H. Caldas”,“I. Brilakis”,“J. Teizer”,“P. Vela”,“C. Haas”,“J. H. Garrett”,“B. Akinci”,“Z. Zhu”] publication_types = [“2”] publication = “Journal of Construction Engineering and Management“ publication_short = “” abstract = “Data fusion can be defined as the process of combining data or information for estimating the state of an entity. Data fusion is a multi-disciplinary field that has several benefits, such as enhancing the confidence, improving reliability and reducing ambiguity of measurements for estimating the state of entities in engineering systems. It can also enhance completeness of fused data that can be required for estimating the state of engineering systems. Data fusion has been applied to different fields, such as robotics, automation, and intelligent systems. This paper reviews some examples of recent applications of data fusion in civil engineering and presents some of the potential benefits of using data fusion in civil engineering.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “CEC: Sensing and Field Data Capture for Construction and Facility Operations” date = “2011-01-01” authors = [“S. Taneja”,“B. Akinci”,“J. H Garrett”,“L. Soibelman”,“M. Berges”,“G. Atasoy”,“X. Liu”,“S. M. Shahandashti”,“E. B. Anil”,“E. Ergen”,“A. Pradhan”,“P. Tang”] publication_types = [“2”] publication = “Journal of Construction Engineering and Management“ publication_short = “” abstract = “Collection of accurate, complete and reliable field data is not only essential for active management of construction projects involving various tasks, such as material tracking, progress monitoring and quality assurance, but also for facility/infrastructure management during the service lives of facilities/infrastructure systems. Limitations of current manual data collection approaches in terms of speed, completeness and accuracy render these approaches ineffective for decision support in highly dynamic environments, such as construction and facility operations. Hence, there is a need to leverage the advancements in automated field data capture technologies to support decisions during construction and facility operations. These technologies can be used not only for acquiring data about the various operations being carried out at construction and facility sites, but also for gathering information about the context surrounding these operations and monitoring the workflow of activities during these operations. With this, it is possible for project and facility managers to better understand the effect of environmental conditions on construction and facility operations, as well as to identify inefficient processes in these operations. This paper presents an overview of the various applications of automated field data capture technologies in construction and facility fieldwork. These technologies include image capture technologies such as laser scanners and video cameras, automated identification technologies such as barcodes and Radio Frequency Identification (RFID) tags, tracking technologies such as GPS and Wireless LAN, and process monitoring technologies such as on-board instruments (OBI). The authors observe that though there exist applications for capturing construction and facility fieldwork data, these technologies have been underutilized for capturing the context at the fieldwork sites as well as for monitoring the workflow of construction and facility operations.” image_preview = “” selected = false projects = [] math = true highlight = true [header] image = “” caption = “” +++

+++ title = “Predicting Leaks in Natural Gas Distribution Networks Using Generalized Linear Models” date = “2017-01-01” authors = [“Y. H. Tari”,“B. Akinci”,“M. Berges”,“M. Pozzi”] publication_types = [“1”] publication = “ASCE International Workshop on Computing in Civil Engineering 2017“ publication_short = “” image_preview = “” selected = false projects = [] url_custom = [{name = “DOI”, url = “http://dx.doi.org/10.1061/9780784480823.041"}] math = true highlight = true [header] image = “” caption = “” +++