A5052583897- Energy Load and Power Forecasting
- Advanced Text Analysis Techniques
- Semantic Web and Ontologies
- Power Systems Fault Detection
- Web Data Mining and Analysis
- Islanding Detection in Power Systems
- Open Source Software Innovations
- Electric Power System Optimization
- Solar Radiation and Photovoltaics
- Imbalanced Data Classification Techniques
- Natural Language Processing Techniques
- Smart Grid Energy Management
- Intellectual Property and Patents
- Complex Network Analysis Techniques
- Machine Learning and Algorithms
- Data Mining Algorithms and Applications
- Remote-Sensing Image Classification
- Data Visualization and Analytics
- Automated Road and Building Extraction
- Neural dynamics and brain function
- EEG and Brain-Computer Interfaces
- scientometrics and bibliometrics research
- Phytoplasmas and Hemiptera pathogens
- Wikis in Education and Collaboration
- IPv6, Mobility, Handover, Networks, Security
Expedia Group (United States)
2020-2023
Harvard University Press
2023
McGill-Queen's University Press
2023
Khalifa University of Science and Technology
2017-2020
Institute of Science and Technology
2008-2017
Masdar Institute of Science and Technology
2012-2017
Technology Innovation Institute
2014-2017
Sadjad University of Technology
2017
Higher Institute of Engineering
2014-2015
Institute of Engineering Science
2011
Microgrids can be operated either grid-connected to reduce system losses and for peak shaving or islanded increase reliability provide backup power during utility outage. Such dual configuration capability imposes challenges on the design of protection system. Fault current magnitudes will vary depending microgrid operating mode. In this paper, a scheme that relies optimally sizing fault limiters setting directional overcurrent relays is proposed. The designed taking into account both modes...
Inspired by the social and economic benefits of diversity, we analyze over 9 million papers 6 scientists to study relationship between research impact five classes diversity: ethnicity, discipline, gender, affiliation, academic age. Using randomized baseline models, establish presence homophily in gender affiliation. We then effect diversity on scientific impact, as reflected citations. Remarkably, considered, ethnic had strongest correlation with impact. To further isolate effects used...
How predictable are life trajectories? We investigated this question with a scientific mass collaboration using the common task method; 160 teams built predictive models for six outcomes data from Fragile Families and Child Wellbeing Study, high-quality birth cohort study. Despite rich dataset applying machine-learning methods optimized prediction, best predictions were not very accurate only slightly better than those simple benchmark model. Within each outcome, prediction error was...
The protection of a microgrid containing inverter- based distributed generators (IBDGs) presents several problems if traditional techniques which rely on the current (fuses and overcurrent relays) are used. A possible solution to these is use new type relay takes advantage enhanced processing communication infrastructure, both recently becoming available for power networks application. This paper proposes communication-based scheme isolated microgrids where data mining approach used identify...
Tree-based ensemble learning has received significant interest as one of the most reliable and broadly applicable classes machine techniques. However, thus far, it rarely been used to model evaluate drivers energy consumption in buildings such its performance accuracy this field have yet be properly tested or fully understood. The goal paper is three algorithms modelling predicting heating cooling loads buildings, namely (i) random forests, (ii) extremely randomized trees (extra-trees),...
In this paper, a new passive islanding detection method for grid-connected inverter-based distributed-generation (DG) systems is proposed. A statistical signal-processing algorithm known as estimation of signal parameters via rotational invariance techniques used to extract features from measurements the voltage and frequency at point common coupling indicators. The are defined based on damped-sinusoid model power system waveforms, include modal initial amplitudes, oscillation frequencies,...
This study investigates the problem of fault protection in a microgrid containing inverter‐based distributed generators (IBDGs). Owing to low magnitude short circuit currents generated by IBDGs, traditional techniques which relay on current (fuses and overcurrent relays) may fail protect such networks. addresses finding suitable features derived from local electrical measurements that can be used statistical classifiers better discriminate events normal network events. Given series simple...
In this work, we try to solve the problem of day-ahead prediction electricity demand using an ensemble forecasting model. Based on Pattern Sequence Similarity (PSF) algorithm, implemented five models different clustering techniques: K-means model (as in original PSF), Self-Organizing Map model, Hierarchical Clustering K-medoids and Fuzzy C-means By incorporating these models, then proposed named Forecasting Ensemble Model (PFEM), with iterative procedure. We evaluated its performance three...
This paper presents a computational method that employs Natural Language Processing (NLP) and text mining techniques to support requirements engineers in extracting modeling goals from textual documents. We developed NLP-based goal elicitation approach within the context of KAOS goal-oriented engineering method. The hierarchical relationships among are inferred by automatically building taxonomies extracted goals. use smart metering system as case study investigate proposed approach. Smart...
High concentrations of induction motor loads can impose stress on transmission and distribution systems, leading to voltage instability in some situations. Properly sized coordinated reactive power sources will provide for improved operation. We present a strategy finding an optimal mix (type, size, location) dynamic shunt compensation devices. The planning is subject satisfying steady-state, transient performance criteria such as fault-induced delayed recovery limits, well related single (...
Abstract Introduction Fast-emerging technologies are making the job market dynamic, causing desirable skills to evolve continuously. It is therefore important understand transitions in proactively identify skill sets required. Case description A novel data-driven approach developed trending jobs through a case study oil and gas industry. The proposed leverages range of data analytics tools, including Latent Semantic Indexing (LSI), Dirichlet Allocation (LDA), Factor Analysis Non-Negative...
Alzheimer's disease (AD) is a degenerative which causes serious cognitive decline. Studies suggest that effective treatments for AD may be aided by the detection of in its early stages, prior to extensive neuronal degeneration. In this paper, we propose set novel techniques could help perform task, and present results experiments conducted evaluate these approaches. The challenge discriminate between spontaneous EEG recordings from two groups subjects: one afflicted with mild impairment...
A deregulated electricity market is one of the keystones up-and-coming smart grid deployments. In such a market, forecasting prices essential to helping stakeholders with decision making process. Electricity price an inherently difficult problem due its special characteristics dynamicity and nonstationarity. our research, we use Artificial Neural Network (ANN) model on carefully crafted input features for hourly next 24 hours. The are selected from pool derived information as past data,...
Forecasting of electricity prices is important in deregulated markets for all the stakeholders: energy wholesalers, traders, retailers and consumers. Electricity price forecasting an inherently difficult problem due to its special characteristic dynamicity non-stationarity. In this paper, we present a robust mechanism that shows resilience towards aggregate demand response effect provides highly accurate forecasted stakeholders dynamic environment. We employ ensemble prediction model which...
Ageing power systems infrastructure and concerns about climate change have increased interest in the next generation of grid infrastructure, known as smart (SG). This study studies a particularly critical SG application: intelligent monitoring transformers for early detection insulation failure. Specifically, focus is on use machine learning algorithms to distinguish between different types partial discharges, which are closely correlated with Measurements made using acoustic emission...
Prediction markets are well-established tools for aggregating information from diverse sources into accurate forecasts. Their success has been demonstrated in a wide range applications, including presidential campaigns, sporting events, and economic outcomes. Recently, they've introduced to the machine learning community form of artificial prediction markets, which algorithms trade contracts reflecting their levels confidence. To date, these have mostly studied context offline...
In this paper, we use feature extraction and data analysis techniques for the elucidation of patterns trends in technological innovation. studying innovation, focus on role public research institutions (research universities national laboratories) development new industries. More specifically, are interested measuring innovation through collaborations between these private sector. The proposed methods primarily drawn from field bibliometrics – i.e. information publication text documents,...