More Like this

1. A dynamical graph-based feature extraction approach to enhance mental task classification in brain–computer interfaces

   https://doi.org/10.1016/j.compbiomed.2022.106498  

   Zhu, Shaotong; Ismail Hosni, Sarah; Huang, Xiaofei; Wana, Michael; Borgheai, Seyyed Bahram; McLinden, John; Shahriari, Yalda; Ostadabbas, Sarah (December 2022, Computers in biology and medicine)

   Graph theoretic approaches in analyzing spatiotemporal dynamics of brain activities are under-studied but could be very promising directions in developing effective brain–computer interfaces (BCIs). Many existing BCI systems use electroencephalogram (EEG) signals to record and decode human neural activities noninvasively. Often, however, the features extracted from the EEG signals ignore the topological information hidden in the EEG temporal dynamics. Moreover, existing graph theoretic approaches are mostly used to reveal the topological patterns of brain functional networks based on synchronization between signals from distinctive spatial regions, instead of interdependence between states at different timestamps. In this study, we present a robust fold-wise hyperparameter optimization framework utilizing a series of conventional graph-based measurements combined with spectral graph features and investigate its discriminative performance on classification of a designed mental task in 6 participants with amyotrophic lateral sclerosis (ALS). Across all of our participants, we reached an average accuracy of 71.1% ± 4.5% for mental task classification by combining the global graph-based measurements and the spectral graph features, higher than the conventional non-graph based feature performance (67.1% ± 7.5%). Compared to using either one of the graphic features (66.3% ± 6.5% for the eigenvalues and 65.9% ± 5.2% for the global graph features), our feature combination strategy shows considerable improvement in both accuracy and robustness performance. Our results indicate the feasibility and advantage of the presented fold-wise optimization framework utilizing graph-based features in BCI systems targeted at end-users. 

   more » « less
2. Identifying the Gaps in the Coverage of Web Domains in Wikipedia and Wikidata for Credibility Assessment Purposes

   Lu, Malinda; Mustafaraj, Eni (May 2023, Wiki Workshop (10th edition))

   In February 2021, Google Search added a new interface feature to support the evaluation of web domains, known as the “About this result” feature. A prominent part of this feature is a snippet of text pulled automatically from Wikipedia, if a Wiki page for the web domain exists. While conducting large-scale audits of Google Search, we discovered that less than 40% of web domains shown in Google Search results contain a Wikipedia page. Then, we retrieved their Wikidata entries and looked at the extent they incorporate features related to W3C credibility signals. The lack of information for many signals points out to avenues for expanding Wikidata coverage. 

   more » « less
3. Design Space for Graph Neural Networks

   You, Jiaxuan; Ying, Rex; Leskovec, Jure. (January 2020, Neural Information Processing Systems (NeurIPS))

   The rapid evolution of Graph Neural Networks (GNNs) has led to a growing number of new architectures as well as novel applications. However, current research focuses on proposing and evaluating specific architectural designs of GNNs, such as GCN, GIN, or GAT, as opposed to studying the more general design space of GNNs that consists of a Cartesian product of different design dimensions, such as the number of layers or the type of the aggregation function. Additionally, GNN designs are often specialized to a single task, yet few efforts have been made to understand how to quickly find the best GNN design for a novel task or a novel dataset. Here we define and systematically study the architectural design space for GNNs which consists of 315,000 different designs over 32 different predictive tasks. Our approach features three key innovations: (1) A general GNN design space; (2) a GNN task space with a similarity metric, so that for a given novel task/dataset, we can quickly identify/transfer the best performing architecture; (3) an efficient and effective design space evaluation method which allows insights to be distilled from a huge number of model-task combinations. Our key results include: (1) A comprehensive set of guidelines for designing well-performing GNNs; (2) while best GNN designs for different tasks vary significantly, the GNN task space allows for transferring the best designs across different tasks; (3) models discovered using our design space achieve state-of-the-art performance. Overall, our work offers a principled and scalable approach to transition from studying individual GNN designs for specific tasks, to systematically studying the GNN design space and the task space. Finally, we release GraphGym, a powerful platform for exploring different GNN designs and tasks. GraphGym features modularized GNN implementation, standardized GNN evaluation, and reproducible and scalable experiment management 

   more » « less
4. Optimal Feature Selection for Decision Robustness in Bayesian Networks

   https://doi.org/10.24963/ijcai.2017/215  

   Choi, YooJung; Darwiche, Adnan; Van den Broeck, Guy (August 2017, Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI))

   In many applications, one can define a large set of features to support the classification task at hand. At test time, however, these become prohibitively expensive to evaluate, and only a small subset of features is used, often selected for their information-theoretic value. For threshold-based, Naive Bayes classifiers, recent work has suggested selecting features that maximize the expected robustness of the classifier, that is, the expected probability it maintains its decision after seeing more features. We propose the first algorithm to compute this expected same-decision probability for general Bayesian network classifiers, based on compiling the network into a tractable circuit representation. Moreover, we develop a search algorithm for optimal feature selection that utilizes efficient incremental circuit modifications. Experiments on Naive Bayes, as well as more general networks, show the efficacy and distinct behavior of this decision-making approach. 

   more » « less
5. Enhanced Modeling of Joint Yaw and Axial Induction Control Using Blade Element Momentum Methods

   https://doi.org/10.1088/1742-6596/2767/3/032018  

   Liew, Jaime; Heck, Kirby; Howland, Michael F (June 2024, Journal of Physics: Conference Series)

   Wind turbine control via concurrent yaw misalignment and axial induction control has demonstrated potential for improving wind farm power output and mitigating structural loads. However, the complex aerodynamic interplay between these two effects requires deeper investigation. This study presents a modified blade element momentum (BEM) model that matches rotor-averaged quantities to an actuator disk model of yawed rotor induction, enabling analysis of joint yaw-induction control using realistic turbine control inputs. The BEM approach reveals that common torque control strategies such as K−Ω^2 exhibit sub-optimal performance under yawed conditions. Notably, the power-yaw and thrust-yaw sensitivities vary significantly depending on the chosen control strategy, contrary to common modeling assumptions. In the context of wind farm control, employing induction control which minimizes the thrust coefficient proves most effective at reducing wake strength for a given power output across all yaw angles. Results indicate that while yaw control deflects wakes effectively, induction control more directly influences wake velocity magnitude, underscoring their complementary effects. This study advances a fundamental understanding of turbine aerodynamic responses in yawed operation and sets the stage for modeling joint yaw and induction control in wind farms. 

   more » « less