Search

Accurate forecasting of solar power generation with fine temporal and spatial resolution is vital for the operation of the power grid. However, state-of-the-art approaches that combine machine learning with numerical weather predictions (NWP) have coarse resolution. In this paper, we take a graph signal processing perspective and model multi-site photovoltaic (PV) production time series as signals on a graph to capture their spatio-temporal dependencies and achieve higher spatial and temporal resolution forecasts. We present two novel graph neural network models for deterministic multi-site PV forecasting dubbed the graph-convolutional long short term memory (GCLSTM) and the graph-convolutional transformer (GCTrafo) models. These methods rely solely on production data and exploit the intuition that PV systems provide a dense network of virtual weather stations. The proposed methods were evaluated in two data sets for an entire year: 1) production data from 304 real PV systems, and 2) simulated production of 1000 PV systems, both distributed over Switzerland. The proposed models outperform state-of-the-art multi-site forecasting methods for prediction horizons of six hours ahead. Furthermore, the proposed models outperform state-of-the-art single-site methods with NWP as inputs on horizons up to four hours ahead., 10 pages, 7 figures, accepted for publication in IEEE Transactions on Sustainable Energy

This paper introduces a knowledge-driven approach to real-time, continuous activity recognition based on multisensor data streams in smart homes. The approach goes beyond the traditional data-centric methods for activity recognition in three ways. First, it makes extensive use of domain knowledge in the life cycle of activity recognition. Second, it uses ontologies for explicit context and activity modeling and representation. Third and finally, it exploits semantic reasoning and classification for activity inferencing, thus enabling both coarse-grained and fine-grained activity recognition. In this paper, we analyze the characteristics of smart homes and Activities of Daily Living (ADL) upon which we built both context and ADL ontologies. We present a generic system architecture for the proposed knowledge-driven approach and describe the underlying ontology-based recognition process. Special emphasis is placed on semantic subsumption reasoning algorithms for activity recognition. The proposed approach has been implemented in a function-rich software system, which was deployed in a smart home research laboratory. We evaluated the proposed approach and the developed system through extensive experiments involving a number of various ADL use scenarios. An average activity recognition rate of 94.44 percent was achieved and the average recognition runtime per recognition operation was measured as 2.5 seconds.

Continual model learning for nonlinear dynamic systems, such as autonomous robots, presents several challenges. First, it tends to be computationally expensive as the amount of data collected by the robot quickly grows in time. Second, the model accuracy is impaired when data from repetitive motions prevail in the training set and outweigh scarcer samples that also capture interesting properties of the system. It is not known in advance which samples will be useful for model learning. Therefore, effective methods need to be employed to select informative training samples from the continuous data stream collected by the robot. Existing literature does not give any guidelines as to which of the available sample-selection methods are suitable for such a task. In this paper, we compare five sample-selection methods, including a novel method using the model prediction error. We integrate these methods into a model learning framework based on symbolic regression, which allows for learning accurate models in the form of analytic equations. Unlike the currently popular data-hungry deep learning methods, symbolic regression is able to build models even from very small training data sets. We demonstrate the approach on two real robots: the TurtleBot mobile robot and the Parrot Bebop drone. The results show that an accurate model can be constructed even from training sets as small as 24 samples. Informed sample-selection techniques based on prediction error and model variance clearly outperform uninformed methods, such as sequential or random selection.

Topic modeling, or identifying the set of topics that occur in a collection of articles, is one of the primary objectives of text mining. One of the big challenges in topic modeling is determining the correct number of topics: underestimating the number of topics results in a loss of information, i.e., omission of topics, underfitting, while overestimating leads to noisy and unexplainable topics and overfitting. In this paper, we consider a semantic-assisted non-negative matrix factorization (NMF) topics model, which we call SeNMFk, based on Kullback-Leibler(KL) divergence and integrated with a method for determining the number of latent topics. SeNMFk involves (i) creating a random ensemble of pairs of matrices whose mean is equal to the initial words-by-documents matrix representing the text corpus and the Shifted Positive Pointwise Mutual Information (SPPMI) matrix, which encodes the context information, respectively, and (ii) jointly factorizing each of these pairs with different number of topics to acquire sets of latent topics that are stable to noise. We demonstrate the performance of our method by identifying the number of topics in several benchmark text corpora, when compared to other state-of-the-art techniques. We also show that the number of document classes in the input text corpus may differ from the number of the extracted latent topics, but these classes can be retrieved by clustering the column-vectors of one of the factor matrices. Additionally, we introduce a software called pyDNMFk to estimate the number of topics. We demonstrate that our unsupervised method, SeNMFk, not only determines the correct number of topics, but also extracts topics with a high coherence and accurately classifies the documents of the corpus.

The European Union's Energy Efficiency Directive is placing an increased focus on the measurement and verification (M&V) of demand side energy savings. The objective of M&V is to quantify energy savings with minimum uncertainty. M&V is currently undergoing a transition to practices, known as M&V 2.0, that employ automated advanced analytics to verify performance. This offers the opportunity to effectively manage the transition from short-term M&V to long-term monitoring and targeting (M&T) in industrial facilities. The original contribution of this paper consists of a novel, robust and technology agnostic framework that not only satisfies the requirements of M&V 2.0, but also bridges the gap between M&V and M&T by ensuring persistence of savings. The approach features a unique machine learning-based energy modelling methodology, model deployment and an exception reporting system that ensures early identification of performance degradation. A case study demonstrates the effectiveness of the approach. Savings from a real-world project are found to be 177,962 +/- 12,334 kWh with a 90% confidence interval. The uncertainty associated with the savings is 8.6% of the allowable uncertainty, thus highlighting the viability of the framework as a reliable and effective tool.

This paper looks into the modulation classification problem for a distributed wireless spectrum sensing network. First, a new data-driven model for Automatic Modulation Classification (AMC) based on long short term memory (LSTM) is proposed. The model learns from the time domain amplitude and phase information of the modulation schemes present in the training data without requiring expert features like higher order cyclic moments. Analyses show that the proposed model yields an average classification accuracy of close to 90% at varying SNR conditions ranging from 0dB to 20dB. Further, we explore the utility of this LSTM model for a variable symbol rate scenario. We show that a LSTM based model can learn good representations of variable length time domain sequences, which is useful in classifying modulation signals with different symbol rates. The achieved accuracy of 75% on an input sample length of 64 for which it was not trained, substantiates the representation power of the model. To reduce the data communication overhead from distributed sensors, the feasibility of classification using averaged magnitude spectrum data and on-line classification on the low-cost spectrum sensors are studied. Furthermore, quantized realizations of the proposed models are analyzed for deployment on sensors with low processing power. ispartof: IEEE Transactions on Cognitive Communications and Networking vol:4 issue:3 pages:433-445 status: published

© 2016 IEEE, 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom), Activity recognition in smart environment has been investigated rigorously in recent years. Researchers are enhancing the underlying activity discovery and recognition process by adding various dimensions and functionalities. But one significant barrier still persists which is collecting the ground truth information. Ground truth is very important to initialize a supervised learning of activities. Due to a large variety in number of Activities of Daily Living (ADLs), acknowledging them in a supervised way is a non-trivial research problem. Most of the previous researches have referenced a subset of ADLs and to initialize their model, they acquire a vast amount of informative labeled training data. On the other hand to collect ground truth and differentiate ADLs, human intervention is indispensable. As a result it takes an immense effort and raises privacy concerns to collect a reasonable amount of labeled data. In this paper, we propose to use active learning to alleviate the labeling effort and ground truth data collection in activity recognition pipeline. We investigate and analyze different active learning strategies to scale activity recognition and propose a dynamic k-means clustering based active learning approach. Experimental results on real data traces from a retirement community-(IRB #HP-00064387) help validate the early promise of our approach.

Bug reports play essential roles in many software engineering tasks. Since validity and performance of these tasks definitely rely on the quality of bug reports, accurate information from bug reports is very important. However, as found in previous study, significant numbers of reports classified as bug are not really a bug. Recent studies proposed techniques to automatically classify bug reports into binary classes, yet there is still more to desire. These bug reports can be classified into multiple classes, which could help to identify what these reports are actually about. Moreover, previous study only looks into one possibility of topic modeling, that is, Latent Dirichlet Allocation (LDA). While LDA has its advantage, parameter tuning is required. In this paper, we propose a nonparametric approach to automatically classify bug reports with, another topic modeling method, Hierarchical Dirichlet Process (HDP). The result indicates that our nonparametric approach performance is comparable to the parametric one. We also examine various aspects of LDA to provide more thoroughly understanding of this process., SNPD 2014 : 15th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, 30 June-2 July 2014, Las Vegas, NV, USA