Hyoseop Lee

Bio: Hyoseop Lee is an academic researcher from Bell Labs. The author has contributed to research in topics: Laplace transform & Two-sided Laplace transform. The author has an hindex of 10, co-authored 27 publications receiving 271 citations. Previous affiliations of Hyoseop Lee include New Generation University College & University of Wyoming.

Convolutional Autoencoder Based Feature Extraction and Clustering for Customer Load Analysis

Abstract: As the number of smart meters increases, compression of metering data becomes essential for data transmission, storing and processing perspectives. Specifically, feature extraction can be used for the compression of metering data and further be utilized for smart grid applications such as customer clustering. So far, there are many studies for compression and clustering based on daily load profiles. However, in order to account for long-term characteristics of electricity load, utilizing yearly load profiles (YLPs) is vital for customer load clustering and analysis. In this paper, we propose a deep learning-based YLP feature extraction that jointly captures daily and seasonal variations. By leveraging convolutional autoencoder (CAE), YLPs in 8,640-dimensional space are compressed to 100-dimensional vectors. We apply the proposed CAE framework to YLPs of 1,405 residential customers and verify that the proposed CAE outperforms other dimensionality reduction methods in terms of reconstruction errors, e.g., by 19–40%, or the compression ratio is increased by 130% or higher than other methods for the same reconstruction error. In addition, clustering analysis is performed on the encoded YLPs. Our results confirm that year-round characteristics are well captured during the clustering process and also clearly visualized with load images.

Subtask Gated Networks for Non-Intrusive Load Monitoring

Abstract: Non-intrusive load monitoring (NILM), also known as energy disaggregation, is a blind source separation problem where a household’s aggregate electricity consumption is broken down into electricity usages of individual appliances. In this way, the cost and trouble of installing many measurement devices over numerous household appliances can be avoided, and only one device needs to be installed. The problem has been well-known since Hart’s seminal paper in 1992, and recently significant performance improvements have been achieved by adopting deep networks. In this work, we focus on the idea that appliances have on/off states, and develop a deep network for further performance improvements. Specifically, we propose a subtask gated network that combines the main regression network with an on/off classification subtask network. Unlike typical multitask learning algorithms where multiple tasks simply share the network parameters to take advantage of the relevance among tasks, the subtask gated network multiply the main network’s regression output with the subtask’s classification probability. When standby-power is additionally learned, the proposed solution surpasses the state-of-the-art performance for most of the benchmark cases. The subtask gated network can be very effective for any problem that inherently has on/off states.

The ENERTALK dataset, 15 Hz electricity consumption data from 22 houses in Korea

Abstract: AMI has been gradually replacing conventional meters because newer models can acquire more informative energy consumption data. The additional information has enabled significant advances in many fields, including energy disaggregation, energy consumption pattern analysis and prediction, demand response, and user segmentation. However, the quality of AMI data varies significantly across publicly available datasets, and low sampling rates and numbers of houses monitored seriously limit practical analyses. To address these challenges, we herein present the ENERTALK dataset, which contains both aggregate and per-appliance measurements sampled at 15 Hz from 22 houses. Among the publicly available datasets with both aggregate and per-appliance measurements, 15 Hz was the highest sampling rate. The number of houses (22) was the second-largest where the largest one had a sampling rate of 1 Hz. The ENERTALK dataset is also the first Korean open dataset on residential electricity consumption. Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.9874028

Response of pulmonary tuberculomas to anti-tuberculous treatment

Abstract: Pulmonary tuberculomas are well-circumscribed masses caused by Mycobacterium tuberculosis. However, the response of tuberculomas to anti-tuberculous (TB) treatment has not been well defined as yet. The response of pulmonary tuberculomas to anti-TB treatment was retrospectively reviewed in 45 patients diagnosed between January 1997 and December 2001. The areas of pulmonary tuberculomas were estimated by calculating products of the longest and their perpendicular short diameters on chest radiographs. The response to anti-TB treatment was categorised as "decreased" (> 25% reduction in area versus its initial area), "increased" (> 251% increase) and "no change" (the remainder). The mean of treatment duration was 11.5 +/- 3.6 months. Three months after treatment, 18 patients (40.0%) were categorised as decreased, 25 (55.6%) as no change and two (4.4%) as increased. Twelve months after treatment, out of 42 patients available for chest radiographs, 32 patients (76.2%) were categorised as decreased, nine (21.4%) as no change and one patient (2.4%) as increased. At the last follow-up (mean follow-up 27.0 +/- 10.2 months), 37 patients (82.2%) were categorised as decreased. The majority of pulmonary tuberculomas were decreased by anti-tuberculosis treatment during and even after treatment, although a transient enlargement during the early period of treatment was observed infrequently.

Data Requirements for Applying Machine Learning to Energy Disaggregation

Abstract: Energy disaggregation, or nonintrusive load monitoring (NILM), is a technology for separating a household’s aggregate electricity consumption information. Although this technology was developed in 1992, its practical usage and mass deployment have been rather limited, possibly because the commonly used datasets are not adequate for NILM research. In this study, we report the findings from a newly collected dataset that contains 10 Hz sampling data for 58 houses. The dataset not only contains the aggregate measurements, but also individual appliance measurements for three types of appliances. By applying three classification algorithms (vanilla DNN (Deep Neural Network), ML (Machine Learning) with feature engineering, and CNN (Convolutional Neural Network) with hyper-parameter tuning) and a recent regression algorithm (Subtask Gated Network) to the new dataset, we show that NILM performance can be significantly limited when the data sampling rate is too low or when the number of distinct houses in the dataset is too small. The well-known NILM datasets that are popular in the research community do not meet these requirements. Our results indicate that higher quality datasets should be used to expedite the progress of NILM research.

The Laplace Transform

Abstract: THE theory of Fourier integrals arises out of the elegant pair of reciprocal formulae The Laplace Transform By David Vernon Widder. (Princeton Mathematical Series.) Pp. x + 406. (Princeton: Princeton University Press; London: Oxford University Press, 1941.) 36s. net.

[ACM Press the 2nd ACM Workshop - Zurich, Switzerland (2010.11.02-2010.11.02)] Proceedings of the 2nd ACM Workshop on Embedded Sensing Systems for Energy-Efficiency in Building - BuildSys \'10 - Occupancy-driven energy management for smart building automation

Abstract: Buildings are among the largest consumers of electricity in the US. A significant portion of this energy use in buildings can be attributed to HVAC systems used to maintain comfort for occupants. In most cases these building HVAC systems run on fixed schedules and do not employ any fine grained control based on detailed occupancy information. In this paper we present the design and implementation of a presence sensor platform that can be used for accurate occupancy detection at the level of individual offices. Our presence sensor is low-cost, wireless, and incrementally deployable within existing buildings. Using a pilot deployment of our system across ten offices over a two week period we identify significant opportunities for energy savings due to periods of vacancy. Our energy measurements show that our presence node has an estimated battery lifetime of over five years, while detecting occupancy accurately. Furthermore, using a building simulation framework and the occupancy information from our testbed, we show potential energy savings from 10% to 15% using our system.

The Exponentially Convergent Trapezoidal Rule

Abstract: It is well known that the trapezoidal rule converges geometrically when applied to analytic functions on periodic intervals or the real line. The mathematics and history of this phenomenon are reviewed, and it is shown that far from being a curiosity, it is linked with computational methods all across scientific computing, including algorithms related to inverse Laplace transforms, special functions, complex analysis, rational approximation, integral equations, and the computation of functions and eigenvalues of matrices and operators.

50 Years of Time Parallel Time Integration

Abstract: Time parallel time integration methods have received renewed interest over the last decade because of the advent of massively parallel computers, which is mainly due to the clock speed limit reached on today’s processors. When solving time dependent partial differential equations, the time direction is usually not used for parallelization. But when parallelization in space saturates, the time direction offers itself as a further direction for parallelization. The time direction is however special, and for evolution problems there is a causality principle: the solution later in time is affected (it is even determined) by the solution earlier in time, but not the other way round. Algorithms trying to use the time direction for parallelization must therefore be special, and take this very different property of the time dimension into account.We show in this chapter how time domain decomposition methods were invented, and give an overview of the existing techniques. Time parallel methods can be classified into four different groups: methods based on multiple shooting, methods based on domain decomposition and waveform relaxation, space-time multigrid methods and direct time parallel methods. We show for each of these techniques the main inventions over time by choosing specific publications and explaining the core ideas of the authors. This chapter is for people who want to quickly gain an overview of the exciting and rapidly developing area of research of time parallel methods.

The solitary pulmonary nodule.

Abstract: This study is a clinical pathological correlation based on 887 resected pulmonary masses. Because of the nature of the study and the source of the material there is a certain amount of selection. The patients were all males, and they had all been healthy enough to have been inducted into the armed services. Only 16 of 887 had significant other pulmonary disease. While the author draws few conclusions, the monograph itself asserts some very forceful points: second primary malignancies can and do occur and may present as pulmonary nodules; pulmonary granulomas can occur in patients with history of malignancy elsewhere; benign tumors of the lung can occur in patients who have had a previous malignancy; preoperative examination with bronchoscopy, cytologic study of the sputum, and scalene node biopsy offer a very low yield of positive diagnoses in pulmonary nodules; size cannot be used as a criterion for determining malignancy; tuberculosis