This paper explores the use of a Deep Reinforcement Learning (DRL) model for dynamic portfolio management in the financial market. With the help of deep neural networks and the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm, the framework is able to process high dimensional market data and dynamic environment. The TD3 algorithm incorporates transaction costs and risk aversion constraints in order to simulate the environment of real-world investments. It uses features such as the Moving Average ConvergenceDivergence (MACD) and Relative Strength Index (RSI) to construct its decision-making state space. The performance of the model was assessed using the historical data of six NASDAQ stocks, starting from 2021 to 2023. The results obtained were then compared with two other methods, namely Proximal Policy Optimization (PPO) and Deep Deterministic Policy Gradient (DDPG). Some of the performance measures of the portfolio include cumulative return, annual volatility, Sharpe ratio and the maximum drawdown. The TD3 algorithm produced better results in terms of cumulative and risk return, where it got a $51.28 \%$ cumulative return as compared to a cumulative return of ${2 5. 9 1 \%}$ by DDPG and $17.56 \%$ by PPO. However, the TD3 managed portfolio was accompanied by high annual volatility and drawdown suggesting a risk-return paradox. From the results, it is shown that the TD3 policy is able to produce high returns while maintaining a certain level of risk and outperform static strategies like buy and hold. However, it also included some drawbacks, where the model was not able to forecast the short-term movements of the market and was based on lagging indicators.
Accurate 3D semantic occupancy perception is essential for autonomous driving in complex environments with diverse and irregular objects. While vision-centric methods suffer from geometric inaccuracies, LiDAR-based approaches often lack rich semantic information. To address these limitations, MS-Occ, a novel multi-stage LiDAR-camera fusion framework which includes middle-stage fusion and late-stage fusion, is proposed, integrating LiDAR's geometric fidelity with camera-based semantic richness via hierarchical cross-modal fusion. The framework introduces innovations at two critical stages: (1) In the middle-stage feature fusion, the Gaussian-Geo module leverages Gaussian kernel rendering on sparse LiDAR depth maps to enhance 2D image features with dense geometric priors, and the Semantic-Aware module enriches LiDAR voxels with semantic context via deformable cross-attention; (2) In the late-stage voxel fusion, the Adaptive Fusion (AF) module dynamically balances voxel features across modalities, while the High Classification Confidence Voxel Fusion (HCCVF) module resolves semantic inconsistencies using self-attention-based refinement. Experiments on two large-scale benchmarks demonstrate state-of-the-art performance. On nuScenes-OpenOccupancy, MS-Occ achieves an Intersection over Union (IoU) of 32.1% and a mean IoU (mIoU) of 25.3%, surpassing the state-of-the-art by +0.7% IoU and +2.4% mIoU. Furthermore, on the SemanticKITTI benchmark, our method achieves a new state-of-the-art mIoU of 24.08%, robustly validating its generalization capabilities.Ablation studies further confirm the effectiveness of each individual module, highlighting substantial improvements in the perception of small objects and reinforcing the practical value of MS-Occ for safety-critical autonomous driving scenarios.
ABSTRACT In this paper, the observer design problem is investigated for a class of nonlinear systems with periodic disturbances. An iterative learning observer (ILO) is constructed to handle the periodic disturbances. Within this ILO, a variable is employed to estimate the periodic disturbances using the iterative learning technique, thereby ensuring satisfactory accuracy in state estimation. To conserve communication resources, an event‐triggered mechanism is utilized to determine the release of measurements to the ILO. The objective of this paper is to design the ILO such that the estimation error system is exponentially ultimately bounded, with the ultimate bound ensured to be independent of the periodic disturbances. First, sufficient conditions are provided to guarantee the ultimate boundedness of the estimation error system. Then, the ILO gains are computed by solving certain linear matrix inequalities. Finally, the effectiveness of the proposed ILO design scheme is validated through a simulation example.
ABSTRACT Urban and remote communities face persistent challenges associated with centralized power grids. This study investigates the potential of hybrid renewable energy systems with integrated storage solutions as a decentralized alternative to improve efficiency and resilience. The research combines a comprehensive theoretical review of configurations, focusing on hydro pumped storage and hydrogen storage, with the development and application of an optimization model for a remote community exposed to desertification risks. Generation and surplus forecasts were used to evaluate storage strategies, and a multicriteria optimization algorithm was applied to enhance demand–supply matching. The base‐case system consists of 13.5 kW of hydropower, 20 kW of solar PV, and 6 kW of wind capacity, assessed over a 35‐year project lifetime. Results indicate that solar and hydropower contribute approximately 90% of total generation, achieving a levelized cost of energy of 0.05 €/kWh, an internal rate of return of 17.5%, and a payback period of 5 years. The system can export up to 42 000 kWh annually to the grid or nearby users. Additionally, the integration of green hydrogen provides further flexibility, resulting in a levelized cost of hydrogen of 3.5 €/kg, an IRR of 10%, and a 14‐year payback period.
In this paper we solve the elasticity problem of two elastic half spaces that are joined together over a region that does not differ much from a circle, i.e., the problem of an external planar crack leaving a nearly circular uncracked connection. The method we use is based on the perturbation technique developed by Rice (1985) for solving the elastic field of a crack whose front deviates slightly from some reference geometry. Quantities such as crack opening displacement and stress intensity factor are derived in detail to the first order of accuracy in the deviation of the shape of the connection from a circle. In addition, some results such as the crack face weight functions and Green's functions for a perfectly circular connection are also discussed under various boundary conditions at infinity. The formulae derived are used to study the configurational stability problem for quasistatic growth of an external circular crack. The results, derived when the crack front is perturbed from circular in a harmonic waveform and is subjected to axisymmetric loading, suggest that a perturbation of wavenumber higher than one is configurationally stable under all boundary conditions at infinity. The perturbation with wavenumber equal to one, which corresponds to a translational shift of the geometric center of the circular connection, turns out to be configurationally stable if any rotation in the remote field is suppressed and configurationally unstable if there is no such restraint.
Read moreThis study addresses the problem of event-triggered and privacy-preserved platooning control of connected automated vehicles with finite communication resources and data privacy constraints. To efficiently use the communication resources, an asynchronous edge-based dynamic event-triggered mechanism that features adaptive edge-related triggering parameters is designed. Such a design allows for dynamic scheduling of the inter-vehicle communication on a per-edge basis while avoiding the Zeno behavior. Privacy of transmitted vehicular data is then protected through a novel hybrid privacy-preserving strategy that combines output masking with matrix transformation. Subsequently, a set of event-triggered adaptive distributed estimators with guaranteed privacy is developed to facilitate each follower vehicle’s accurate estimation of the full leader motion state. The state estimates are then employed in the design of neural adaptive platoon controllers such that each follower vehicle in the platoon follows the leader with synchronized speed and acceleration under a refined constant time headway spacing policy. Tractable design criteria for admissible estimator and controller gains as well as triggering and learning parameters, are further derived. Finally, co-simulations using CarSim and MATLAB/Simulink are performed to validate the effectiveness of the derived results.
Read moreThis research introduces a novel methodology that combines Building Information Modelling (BIM) and Economic Multi-Criteria Decision-Making (EMCDM) with Neural Networks to optimize hybrid renewable energy systems in small communities. Its core aim is to improve sustainability, technical performance, and financial vokiability through integrated modelling and decision-making. The approach is applied to a hydropower site, evaluating five Scenarios (IDs 1–5) under a Community and Industry model. Financial benchmarks include a 10% Minimum Required Return and a 7-year payback period. ID3—hydropower, solar, and wind—proves most effective, with ANPV of €10,905 (wet) and €4501 (dry), and ROI of 155%/64%. Its ROIA/MRA Index peaks at 539%, and Payback/N ratios remain within acceptable limits (55%/96%). LCOE stays stable in average conditions (0.042–0.046 €/kWh), rising in dry years (0.07–0.10 €/kWh). Profitability differences primarily stem from demand and curtailment, rather than production costs. The NARX neural network reliably models SS% values from renewable inputs with low error across scenarios. The integrated BIM–EMCDM framework ensures transparent, sustainable, and risk-balanced energy system decisions for long-term autonomy.
Read moreReferring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method.
Read moreDue to the limited understanding of Industrial Control Systems (ICSs), device identification has become increasingly vital for threat detection and security defense in ICS environments. However, the narrow range of device types and models in the existing datasets has significantly hindered the effectiveness and scalability of current device identification methods. To address this gap, we introduce a novel data collection framework specifically designed for ICS devices and present the resulting dataset, ICSLibrary, which we have made publicly available. To the best of the authors' knowledge, ICSLibrary is the first dataset dedicated to device identification in ICS security. It encompasses the most extensive range of device types, models and instances from 27 industrial vendors, collected across two countries over a 21-month period. Furthermore, we use ICSLibrary as a benchmark to evaluate several typical device fingerprinting methods, revealing a notable 16% drop in accuracy in the device model identification task, which highlights the unique challenges posed by ICSLibrary.
Read moreThe Hybrid Smart Energy Community (HySEC) model is an integrated framework for optimizing hybrid renewable energy systems, unifying BIM, IoT, and data-driven modeling, as an innovative approach for the energy transition. A Revit—Twinmotion BIM model, enriched with topographic, CAD, and real-image data, enhances spatial accuracy and stakeholder communication, while a digital–physical architecture linking sensors, gateways, edge devices, and cloud platforms enables decentralized peer-to-peer communication and real-time monitoring. The framework is applied to a smart energy community composed of a hydropower–wind–solar PV system serving six buildings (48.8 MWh/year), supported by high-resolution hourly Open-Meteo data. A NARX neural network trained on 8760 hourly observations achieves an MSE of 2.346 at epoch 16, providing advanced predictive capability. Benchmarking against HOMER demonstrates clear advantages in grid exports (15,130 vs. 8274 kWh/year), battery cycling (445 vs. 9181 kWh/year), LCOE (€0.09 vs. €0.180/kWh), IRR (9% vs. 6%), payback (8.7 vs. 10.5 years), and CO2 emissions (−9.4 vs. 101 tons). These results confirm HySEC as a conceptually flexible solution that strengthens energy autonomy, supports heritage site rehabilitation, and promotes sustainable rural development.
Read moreABSTRACT This article addresses the problem of resilient cubature Kalman filtering (RCKF) for nonlinear systems with sensor saturations under a round‐robin protocol (RRP) affected by channel noises. To enhance transmission efficiency, the RRP is employed in the communication channel to regulate data signal transmission, with particular consideration given to channel noises to more accurately reflect practical conditions. The focus is on the development of an RCKF algorithm that ensures an upper bound of the filtering error covariance (UBFEC) in the presence of sensor saturations and RRP influenced by channel noises. Subsequently, the minimization of the trace of this upper bound is achieved through the design of an appropriate filter gain. Furthermore, the uniform boundedness of the UBFEC is examined by using the matrix theory. Finally, the superiority and efficiency of the proposed RCKF scheme are demonstrated through a simulation experiment that includes comparisons.
Read moreTactile sensing is a fundamental modality for embodied intelligence, offering unique and direct feedback on contact geometry, material properties, and interaction dynamics that remote sensors cannot replace. However, unimodal tactile perception is inherently limited by its sparse spatial coverage and lack of global semantic context. With the recent explosion in deep learning and large language models, integrating tactile with vision and language has become essential to bridge physical interaction with semantic reasoning, leading to the emergence of Multimodal Tactile Fusion. Despite rapid progress, the existing researches remain fragmented across disparate datasets, sensing modalities, and tasks, lacking a unified theoretical framework. To address this gap, this paper provides a comprehensive survey of multimodal tactile fusion research up to the first quarter of 2026. We propose a hierarchical taxonomy that organizes the field into two primary dimensions: multimodal datasets and multimodal methods. On the data side, we categorize resources ranging from Tactile-Vision datasets, Tactile-Language datasets, Tactile-Vision-Language datasets, and Tactile-Vision-Other datasets. On the method side, we structure prior work into three core pillars: (1) Multimodal Perception and Recognition, which focuses on object understanding and grasp prediction; (2) Cross-Modal Generation, focusing on bidirectional translation between tactile, vision, and text; and (3) Multimodal Interaction, emphasizing feedback control and language-guided manipulation. Furthermore, we summarize representative tactile sensing hardware, review commonly used evaluation metrics and benchmark settings, and discuss current challenges and promising future directions.
Read moreOnline Multi-Object Tracking (MOT) plays a pivotal role in autonomous systems. The state-of-the-art approaches usually employ a tracking-by-detection method, and data association plays a critical role. This paper proposes a learning and graph-optimized (LEGO) modular tracker to improve data association performance in the existing literature. The proposed LEGO tracker integrates graph optimization, which efficiently formulates the association score map, facilitating the accurate and efficient matching of objects across time frames. To further enhance the state update process, the Kalman filter is added to ensure consistent tracking by incorporating temporal coherence in the object states to further enhance the state update process. Our proposed method, utilising LiDAR alone, has shown exceptional performance compared to other online tracking approaches, including LiDAR-based and LiDAR-camera fusion-based methods. LEGO ranked 3<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>rd</i></sup> among all trackers (both online and offline) and 2<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>nd</i></sup> among all online trackers in the KITTI MOT benchmark for cars<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>, at the time of submitting results to KITTI object tracking evaluation ranking board. Moreover, our method also achieves competitive performance on the Waymo open dataset benchmark.
Read more
.jpg){kind=small}
.jpg){kind=small}
