Many learning problems involve multiple patterns and varying degrees of uncertainty dependent on the covariates. Advances in Deep Learning (DL) have addressed these issues by learning highly nonlinear input-output dependencies. However, model interpretability and Uncertainty Quantification (UQ) have often straggled behind. In this context, we introduce the Competitive/Collaborative Fusion of Experts (CoCoAFusE), a novel, Bayesian Covariates-Dependent Modeling technique. CoCoAFusE builds on the very philosophy behind Mixtures of Experts (MoEs), blending predictions from several simple sub-models (or "experts") to achieve high levels of expressiveness while retaining a substantial degree of local interpretability. Our formulation extends that of a classical Mixture of Experts by contemplating the fusion of the experts' distributions in addition to their more usual mixing (i.e., superimposition). Through this additional feature, CoCoAFusE better accommodates different scenarios for the intermediate behavior between generating mechanisms, resulting in tighter credible bounds on the response variable. Indeed, only resorting to mixing, as in classical MoEs, may lead to multimodality artifacts, especially over smooth transitions. Instead, CoCoAFusE can avoid these artifacts even under the same structure and priors for the experts, leading to greater expressiveness and flexibility in modeling. This new approach is showcased extensively on a suite of motivating numerical examples and a collection of real-data ones, demonstrating its efficacy in tackling complex regression problems where uncertainty is a key quantity of interest.

Home Energy Management Systems (HEMS) have emerged as a pivotal tool in the smart home ecosystem, aiming to enhance energy efficiency, reduce costs, and improve user comfort. By enabling intelligent control and optimization of household energy consumption, HEMS plays a significant role in bridging the gap between consumer needs and energy utility objectives. However, much of the existing literature construes consumer comfort as a mere deviation from the standard appliance settings. Such deviations are typically incorporated into optimization objectives via static weighting factors. These factors often overlook the dynamic nature of consumer behaviors and preferences. Addressing this oversight, our paper introduces a multi-mode Deep Reinforcement Learning-based HEMS (DRL-HEMS) framework, meticulously designed to optimize based on dynamic, consumer-defined preferences. Our primary goal is to augment consumer involvement in Demand Response (DR) programs by embedding dynamic multi-mode preferences tailored to individual appliances. In this study, we leverage a model-free, single-agent DRL algorithm to deliver a HEMS framework that is not only dynamic but also user-friendly. To validate its efficacy, we employed real-world data at 15-minute intervals, including metrics such as electricity price, ambient temperature, and appliances' power consumption. Our results show that the model performs exceptionally well in optimizing energy consumption within different preference modes. Furthermore, when compared to traditional algorithms based on Mixed-Integer Linear Programming (MILP), our model achieves nearly optimal performance while outperforming in computational efficiency.

This paper addresses the challenge of mapping polygonal buildings from remote sensing images and introduces a novel algorithm, the Global Collinearity-aware Polygonizer (GCP). GCP, built upon an instance segmentation framework, processes binary masks produced by any instance segmentation model. The algorithm begins by collecting polylines sampled along the contours of the binary masks. These polylines undergo a refinement process using a transformer-based regression module to ensure they accurately fit the contours of the targeted building instances. Subsequently, a collinearity-aware polygon simplification module simplifies these refined polylines and generate the final polygon representation. This module employs dynamic programming technique to optimize an objective function that balances the simplicity and fidelity of the polygons, achieving globally optimal solutions. Furthermore, the optimized collinearity-aware objective is seamlessly integrated into network training, enhancing the cohesiveness of the entire pipeline. The effectiveness of GCP has been validated on two public benchmarks for polygonal building mapping. Further experiments reveal that applying the collinearity-aware polygon simplification module to arbitrary polylines, without prior knowledge, enhances accuracy over traditional methods such as the Douglas-Peucker algorithm. This finding underscores the broad applicability of GCP. The code for the proposed method will be made available at https://github.com/zhu-xlab.

Accurate wind power forecasting can help formulate scientific dispatch plans, which is of great significance for maintaining the safety, stability, and efficient operation of the power system. In recent years, wind power forecasting methods based on deep learning have focused on extracting the spatiotemporal correlations among data, achieving significant improvements in forecasting accuracy. However, they exhibit two limitations. First, there is a lack of modeling for the inter-variable relationships, which limits the accuracy of the forecasts. Second, by treating endogenous and exogenous variables equally, it leads to unnecessary interactions between the endogenous and exogenous variables, increasing the complexity of the model. In this paper, we propose the 2DXformer, which, building upon the previous work's focus on spatiotemporal correlations, addresses the aforementioned two limitations. Specifically, we classify the inputs of the model into three types: exogenous static variables, exogenous dynamic variables, and endogenous variables. First, we embed these variables as variable tokens in a channel-independent manner. Then, we use the attention mechanism to capture the correlations among exogenous variables. Finally, we employ a multi-layer perceptron with residual connections to model the impact of exogenous variables on endogenous variables. Experimental results on two real-world large-scale datasets indicate that our proposed 2DXformer can further improve the performance of wind power forecasting. The code is available in this repository: \href{https://github.com/jseaj/2DXformer}{https://github.com/jseaj/2DXformer}.

This paper addresses several critical stages of designing a walking robot, including optimal structural synthesis, introducing a novel 'rational' mechanical structure aimed at enhancing efficiency and simplifying control system, while addressing practical limitations observed in existing designs. The study includes development of novel multicriteria synthesis methods for achieving optimal leg design, integrating analytical and numerical methods. In addition, a method based on Non-dominated Sorting Genetic Algorithm II is presented. Turning modes are investigated, and for the first time, the isotropy criterion, typically applied to parallel manipulators, is used for optimizing walking robot parameters to ensure optimal force and motion transfer in all directions. Several physical prototypes are developed to experimentally validate the functionality of different mechanisms of the robot, including adaptation to the surface irregularities and navigation using LiDAR.

Advancements in remote sensing (RS) imagery have provided high-resolution detail and vast coverage, yet existing methods, such as image-level captioning/retrieval and object-level detection/segmentation, often fail to capture mid-scale semantic entities essential for interpreting large-scale scenes. To address this, we propose the conteXtual referring Map (XeMap) task, which focuses on contextual, fine-grained localization of text-referred regions in large-scale RS scenes. Unlike traditional approaches, XeMap enables precise mapping of mid-scale semantic entities that are often overlooked in image-level or object-level methods. To achieve this, we introduce XeMap-Network, a novel architecture designed to handle the complexities of pixel-level cross-modal contextual referring mapping in RS. The network includes a fusion layer that applies self- and cross-attention mechanisms to enhance the interaction between text and image embeddings. Furthermore, we propose a Hierarchical Multi-Scale Semantic Alignment (HMSA) module that aligns multiscale visual features with the text semantic vector, enabling precise multimodal matching across large-scale RS imagery. To support XeMap task, we provide a novel, annotated dataset, XeMap-set, specifically tailored for this task, overcoming the lack of XeMap datasets in RS imagery. XeMap-Network is evaluated in a zero-shot setting against state-of-the-art methods, demonstrating superior performance. This highlights its effectiveness in accurately mapping referring regions and providing valuable insights for interpreting large-scale RS environments.

Autonomous robots must operate in diverse environments and handle multiple tasks despite uncertainties. This creates challenges in designing software architectures and task decision-making algorithms, as different contexts may require distinct task logic and architectural configurations. To address this, robotic systems can be designed as self-adaptive systems capable of adapting their task execution and software architecture at runtime based on their context.This paper introduces ROSA, a novel knowledge-based framework for RObot Self-Adaptation, which enables task-and-architecture co-adaptation (TACA) in robotic systems. ROSA achieves this by providing a knowledge model that captures all application-specific knowledge required for adaptation and by reasoning over this knowledge at runtime to determine when and how adaptation should occur. In addition to a conceptual framework, this work provides an open-source ROS 2-based reference implementation of ROSA and evaluates its feasibility and performance in an underwater robotics application. Experimental results highlight ROSA's advantages in reusability and development effort for designing self-adaptive robotic systems.

Author William R. Forstchen's bestselling novel "One Second After" – which imagines the devastating effects of an EMP (electromagnetic pulse) strike on the United States – is being adapted into a feature film. The screenplay will be written by renowned sci-fi writer J. Michael Straczynski, with Forstchen himself serving as an executive producer. Fox News Digital spoke with Forstchen about the real-world inspiration behind his work and why he warns that an EMP attack is a looming threat, not just science fiction. "I wanted to write an accurate, a very accurate story of what would happen in a small town in North Carolina if the power went off, and it never came back on," he said. Electromagnetic pulse expert William R. Forstchen speaks at the rally against North Korea on San Francisco's Golden Gate Bridge and Yerba Buena Gardens to support the new Homefront video game on March 2, 2011, in San Francisco, Calif.

Designing concept cars seems kind of like being back in grade school, when kids are encouraged to dream up things like a bedroom with a bouncy-house floor or a spaceship with an ice cream machine on board. At least concept cars have a chance of making it to production at some point, even if that timeline is a long way off. At Kia's EV Day in Barcelona, Spain in March, the brand unveiled a new modular electric van it's calling the Platform Beyond Vehicle (PBV). The PV5 is the first in the automaker's plan, with four variants: Cargo, Passenger, Crew, and a Wheelchair Access Vehicle option. The designers pushed that a little further with the PV5 WKNDR concept, an EV made for camping and overlanding.

Abstract--This study examines the feasibility and profitability of utilizing surplus electricity for Bitcoin mining. Surplus electricity refers to the remaining electricity after net metering, which can be repurposed for Bitcoin mining to improve Korea Electric Power Corporation's (KEPCO) energy resource efficiency and alleviate its debt challenges. Net metering (or net energy metering) is an electricity billing mechanism that allows consumers who generate some or all of their own electricity to use that electricity when they want, rather than when it is produced. Using the latest Bitcoin miner, the Antminer S21 XP Hyd, the study evaluates daily Bitcoin mining when operating at 30,565 and 45,439 units, incorporating Bitcoin network hash rates to assess profitability . T o examine profitability, the Random Forest Regressor and Long Short-T erm Memory models were used to predict the Bitcoin price. The analysis shows that the use of excess electricity for Bitcoin mining not only generates economic revenue, but also minimizes energy loss, reduces debt, and resolves unsettled payment issues for KEPCO. This study empirically investigates and analyzes the integration of electricity surplus in South Korea with bitcoin mining for the first time. The findings highlight the potential to strengthen the financial stability of KEPCO and demonstrate the feasibility of Bitcoin mining. In addition, this research serves as a foundational resource for future advancements in the Bitcoin mining industry and the efficient use of energy resources.