Search

Icons are widely used to communicate information in graphical user interfaces, and it is essential for designers to understand how users recognize and interpret them. This study investigates the impact of university students’ knowledge structures on icon usability. It examines the effects of icon metaphors (appearance, symbolic, relational, arbitrary) and icon characteristics (concreteness, abstractness) on icon recognition. One hundred participants from the liberal arts and sciences were tested (N =50). The test parameters included form recognition rate, functional accuracy rate, and response time. The results indicated that university students’ knowledge structures influenced the recognition of icon characteristics, with liberal arts students preferring concrete icons and science students preferring abstract icons. However, differences in knowledge structure had no significant effect on icon metaphor recognition. Furthermore, the liberal arts and science students showed some differences in recognizing specific combinations of icon characteristics and metaphors. These findings suggest that icon characteristics are influenced by knowledge structure, whereas metaphor recognition is more dependent on cultural structure. Specific combinations of icon characteristics and metaphors can significantly improve icon usability. The implications of these findings suggest new ways for graphical interface icons to enhance usability.

Continual learning paradigm learns from a continuous stream of tasks in an incremental manner and aims to overcome the notorious issue: the catastrophic forgetting. In this work, we propose a new adaptive progressive network framework including two models for continual learning: Reinforced Continual Learning (RCL) and Bayesian Optimized Continual Learning with Attention mechanism (BOCL) to solve this fundamental issue. The core idea of this framework is to dynamically and adaptively expand the neural network structure upon the arrival of new tasks. RCL and BOCL employ reinforcement learning and Bayesian optimization to achieve it, respectively. An outstanding advantage of our proposed framework is that it will not forget the knowledge that has been learned through adaptively controlling the architecture. We propose effective ways of employing the learned knowledge in the two methods to control the size of the network. RCL employs previous knowledge directly while BOCL selectively utilizes previous knowledge (e.g., feature maps of previous tasks) via attention mechanism. The experiments on variants of MNIST, CIFAR-100 and Sequence of 5-Datasets demonstrate that our methods outperform the state-of-the-art in preventing catastrophic forgetting and fitting new tasks better under the same or less computing resource. [ABSTRACT FROM AUTHOR]

To have sustainable battery swapping stations (BSSs), a multistakeholder planning and operational strategy is proposed that involves BSS owners, electric vehicle (EV) drivers, and power-distributing company (DisCo) operators. A multiobjective bilevel optimization approach is used based on the flexible load linking the embedded optimization of DisCo operators and the outer optimizations of the BSS owners and EV drivers. BSS owners and EV drivers optimize their swapping and shifting visit decisions based on tradeoffs in the multiobjective framework. In addition, the strategy embeds the network-constrained allowed power decisions of DisCo operators. Case studies have been investigated such as shifting station visits, network constraints, and profit-sharing. For the Australian case scenario, cooperation between these stakeholders led to varied flexible load and power generation responses. The case studies have demonstrated the utility of the proposed multistakeholder approach. [ABSTRACT FROM AUTHOR]

The existing inertia estimation based on electromechanical oscillation relies on a single mode, which is limited in complex systems. In this letter, the inertia is estimated without worrying about the number of modes in the oscillation. The inertia expression is derived based on the swing equation in the frequency domain, which considers the mode coupling in the electromechanical bandwidth using a summation calculation. The effectiveness of the proposed inertia estimation method is validated through simulation data and real measurements. [ABSTRACT FROM AUTHOR]

Non-intrusive load monitoring (NILM), including state detection and energy disaggregation, aims to identify the on/off state and energy consumption from the aggregate load of a building. By monitoring the electrical behavior of consumers, smart grid applications such as demand response and recommendation services can also be realized for saving energy bills, environmental effectiveness, assisted living, and fault diagnosis. To achieve latency-free monitoring, this paper presents a Scale- and Attention-experts based Multi-task neural network (SAMNet) with a large enough context of the view to make full use of the correlation between the tasks of the NILM. A shared expert learner is designed to learn a good summary of the features. Self-attention mechanism is creatively adopted to realize the weighted fusion of different experts. To address the problem of manually setting different threshold values for different appliances to decide the on/off states, we designed the network automatically labeling the on/off states. Extensive experimental results with the public datasets demonstrate the effectiveness and superiority of our proposed model. [ABSTRACT FROM AUTHOR]

Battery energy storage (BES) and demand response (DR) are two important resources to increase the operational flexibility of a virtual power plant (VPP) and thus reduce the economic risks that VPP faces in the short-term electricity market. This article develops a data-driven approach for VPP resource planning (VRP), in which BES sizing and DR customer selection are optimized synergistically to maximize VPP's profit in the electricity market. Heterogeneity in DR potential across individual customers is considered in the planning framework by utilizing the knowledge learnt from smart meter data. The overall VRP problem is formulated by a risk-managed, multistage stochastic programming framework to address the uncertainties from the intermittent renewable energy sources, load demands, market prices, and DR resources. Case studies compare the VRP results under two market imbalance settlement settings, namely, penalty-charged and penalty-free markets. The results demonstrate that jointly optimizing BES and DR customer selection leveraging the smart meter data can improve the VPP's expected profit under both market settings. [ABSTRACT FROM AUTHOR]

Smart meter data provides rich information on customers’ energy consumption behaviors, which can be a valuable resource for evaluating customers’ demand response (DR) potential and thus can inform the distribution system expansion planning (DSEP). This paper presents a novel DSEP framework incorporating a data-driven model for a particular type of incentive-based DR called the thermostatically-controlled-load DR. The heterogeneity in individual customers’ DR potential is considered in the DSEP by leveraging the healing, ventilation, and air conditioning (HVAC) load information extracted from smart meter data. The relationship between the DR incentive and the customer participation rate is also considered so that incentives can be optimally designed for customers with different DR potentials in a differentiated way. The overall DSEP problem is formulated into a robust optimization framework to address the uncertainties from the load demands, renewable energy generations, and DR resources. Case studies show that the proposed DSEP model can substantially reduce the total expansion cost over conventional planning paradigms, demonstrating the positive role of the proposed data-driven DR model in DSEP. [ABSTRACT FROM AUTHOR]

Understanding customers’ energy consumption at the individual appliances level is crucial for the planning and implementation of demand response (DR) programs. The appliances’ usage profiles can be disaggregated from whole-house energy consumption data using non-intrusive load monitoring (NILM) methods. The appliance load patterns of each customer are considerably different, which make it challenging to train a model with strong generalization ability. In this paper, a novel methodology using transfer knowledge between domains for NILM is proposed. A temporal convolutional network is developed to learn the dynamic features of individual appliance load. A domain adaption loss is used to quantify the domain distribution discrepancy between source and target domain representation. By jointly optimizing domain adaptation and energy disaggregation, an invariant representation across domains for the individual appliance states can be learned. Data experiments on ground truth data validate the accuracy and the robustness of the proposed model, and demonstrate its superior transferability and application potential under those scenarios of data shortage. [ABSTRACT FROM AUTHOR]

Accurate estimation of residential solar photovoltaic (PV) generation is crucial for the power distribution and demand response program implementation. Currently, most distributed PVs are installed behind-the-meters (BTMs), and are thus invisible to the utilities. The existing methods separate the BTM solar generation from the available net load in a centralized manner assuming that all data are accessible to utilities. However, this can cause privacy issues, since the data are owned by different utilities and they may be unwilling to share their data. To this end, a novel method is proposed for disaggregating community-level BTM solar generation using a federated learning-based Bayesian neural network (FL-BNN), which can preserve the privacy of utilities. Specifically, a Bayesian neural network (BNN) is designed as the probabilistic energy disaggregation model with the ability to capture uncertainties. The BNN training process is extended into a decentralized manner based on the federated learning framework. To enable the model customized for each community, the layers of BNN are categorized into shallow and deep layers, and a layerwise parameter aggregation strategy is proposed to update the model. Both community-specific features and community-invariant features can be learned. The effectiveness of the proposed method is validated on a publicly available dataset. [ABSTRACT FROM AUTHOR]

Automatic quantification of the left ventricle (LV) from cardiac magnetic resonance (CMR) images plays an important role in making the diagnosis procedure efficient, reliable, and alleviating the laborious reading work for physicians. Considerable efforts have been devoted to LV quantification using different strategies that include segmentation-based (SG) methods and the recent direct regression (DR) methods. Although both SG and DR methods have obtained great success for the task, a systematic platform to benchmark them remains absent because of differences in label information during model learning. In this paper, we conducted an unbiased evaluation and comparison of cardiac LV quantification methods that were submitted to the Left Ventricle Quantification (LVQuan) challenge, which was held in conjunction with the Statistical Atlases and Computational Modeling of the Heart (STACOM) workshop at the MICCAI 2018. The challenge was targeted at the quantification of 1) areas of LV cavity and myocardium, 2) dimensions of the LV cavity, 3) regional wall thicknesses (RWT), and 4) the cardiac phase, from mid-ventricle short-axis CMR images. First, we constructed a public quantification dataset Cardiac-DIG with ground truth labels for both the myocardium mask and these quantification targets across the entire cardiac cycle. Then, the key techniques employed by each submission were described. Next, quantitative validation of these submissions were conducted with the constructed dataset. The evaluation results revealed that both SG and DR methods can offer good LV quantification performance, even though DR methods do not require densely labeled masks for supervision. Among the 12 submissions, the DR method LDAMT offered the best performance, with a mean estimation error of 301 mm $^2$ for the two areas, 2.15 mm for the cavity dimensions, 2.03 mm for RWTs, and a 9.5% error rate for the cardiac phase classification. Three of the SG methods also delivered comparable performances. Finally, we discussed the advantages and disadvantages of SG and DR methods, as well as the unsolved problems in automatic cardiac quantification for clinical practice applications. [ABSTRACT FROM AUTHOR]

This paper investigates systemwide short-term voltage stability concerns of power systems due to the multiple parametric uncertainties in the dynamic load model. The impact of regional load model uncertainty can be widespread and may mislead the whole system analysis and subsequent measures, if not properly addressed. This research discloses that the systemwide impact is related to the voltage weak areas through voltage stability modal analysis, and suggests that the impact of uncertain parameters needs to be assessed from a systems perspective, which has rarely been done in the existing practices. We thus present a three-step methodology for evaluating the systemwide uncertainty impacts: Firstly, it screens possible trajectories of all buses. The second step verifies whether the screened trajectories comply with the defined criteria, and determines the necessity of the final step. The final detailed analysis is conducted for those selected scenarios. Comprehensive studies for both the IEEE test and real Korea power systems consistently confirm the observations and demonstrate the efficacy and validity of the proposed method. [ABSTRACT FROM AUTHOR]

The refined estimation of inertia can provide a reliable basis for power system operation and control. In this article, a data-driven approach for the estimation of inertia is proposed, and it can estimate the effective inertia of different areas in the interconnected power systems. Based on eigenstructure analysis, the intrinsic relationships between inertia and the eigenvalue and eigenvector are analyzed using a linearized dynamic equation. Furthermore, detailed mathematical expressions between inertia and the eigenvalue and eigenvector are established. In addition, dynamic mode decomposition is introduced to extract eigenvalues and eigenvectors from the synchronized measurements to ensure that the scheme proposed in this article can estimate the effective inertia by using only the outputs measured by the phase measurement unit. The effectiveness of the proposed approach is demonstrated through numerical simulations on the IEEE 16-machine 5-area test system and the real measurements of an actual power system. [ABSTRACT FROM AUTHOR]