Search Results (14,718)

In clinical decision support systems (CDSSs), where accurate classification of drug–drug interactions (DDIs) can directly affect treatment safety and outcomes, identifying drug interactions is a major challenge, introducing a scalable approach for classifying DDIs utilizing a finely-tuned biomedical language model. The method shown here uses BiomedBERT, a domain-specific version of bidirectional encoder representations from transformers (BERT) that was pre-trained on biomedical literature, to reduce the number of resources needed during fine-tuning. Low-rank adaptation (LoRA) was used to fine-tune the model on the DrugBank dataset. The objective was to classify DDIs into two clinically distinct categories, that is, synergistic and antagonistic interactions. A pseudo-labeling strategy was created to deal with the problem of not having enough labeled data. A curated ground-truth dataset was constructed using polarity-labeled interaction entries from DrugComb and verified DrugBank antagonism pairs. The fine-tuned model is used to figure out what kinds of interactions there are in the rest of the unlabeled data. A checkpointing system saves predictions and confidence scores in small pieces, which means that the process can be continued and is not affected by system crashes. The framework is designed to log every prediction it makes, allowing results to be refined later, either manually or through automated updates, without discarding low-confidence cases, as traditional threshold-based methods often do. The method keeps a record of every output it generates, making it easier to revisit earlier predictions, either by experts or with improved tools, without depending on preset confidence cutoffs. It was built with efficiency in mind, so it can handle large amounts of biomedical text without heavy computational demands. Rather than focusing on model novelty, this research demonstrates how existing biomedical transformers can be adapted to polarity-aware DDI classification with minimal computational overhead, emphasizing deployment feasibility and clinical relevance. Full article

In this paper, an image-based visual control scheme is proposed for a quadrotor aerial vehicle with unknown mass and moment of inertia. In order to reduce the impacts of underactuation in quadrotor dynamics, a virtual image plane is introduced and appropriate image moment features are defined to decouple the image features from the movement of the vehicle. Subsequently, based on the quadrotor dynamics, a backstepping method is used to construct the torque controller, ensuring that the control system has superior dynamic performance. Furthermore, an adaptive control scheme is then designed to enable online estimation of dynamic parameters. Finally, stability is formally verified through constructive Lyapunov methods, and performance test results validate the efficacy and robustness of the proposed control scheme. It can be verified through performance tests that the quadrotor successfully positions itself at the desired position under uncertain dynamic parameters, and the attitude angles converge to the expected values. Full article

To evaluate the response of broiler breeder hens submitted to different amino acid intakes of methionine+cystine, lysine, and threonine, and to determine the coefficients for egg output and body weight for maintenance. Three studies were performed using 160 broiler breeder hens housed individually in metabolic cages. A summit diet and a nitrogen-free diet were formulated. The levels ranged from 1.79 to 7.13, 2.49 to 8.3, and 2.04 to 6.79 g/kg of methionine+cystine, lysine, and threonine, respectively. The variables measured were feed intake, amino acid intake, rate of lay, egg weight, and egg output. The broken line model was used to evaluate the responses. It was verified that higher values of the rate of lay, egg weight, and egg output were observed for the higher concentrations of amino acids studied. A significant difference was observed for the variables rate of lay, egg weight, egg output, and body weight (p < 0.05) for the three amino acids evaluated. The amount of each amino acid required to produce one gram per egg was estimated at 12.4 mg, 14.5 mg, and 11.2 mg for methionine+cystine, lysine, and threonine, respectively. The values estimated by coefficient b that represent the amino acid for maintenance requirement were methionine+cystine, lysine, and threonine of 30.2, 32.2, and 42.4 mg/kg BW, respectively. The coefficients may be used to design additional models to study requirements nutrition in broiler breeders, allowing a better understanding of how these birds respond to different dietary amino acids. Full article

To solve the problem of traditional engineering drilling rig propulsion systems being difficult to adapt to complex working conditions due to their bulky structure and poor load adaptability, this study proposes a new type of mechanical hydraulic composite electro-hydraulic proportional propulsion system. The system innovatively adopts a composite design of parallel hydraulic cylinders and movable pulley groups in mechanical structure, aiming to achieve system lightweighting through displacement multiplication effect. In terms of control strategy, a fuzzy adaptive PID controller based on position feedback was designed to improve the dynamic tracking performance and robustness of the system under nonlinear time-varying loads. The study established a multi physics domain mathematical model of the system and conducted joint simulation using AMESim and MATLAB/Simulink to deeply verify the overall performance of the proposed scheme. The simulation results show that the mechanical structure can stably achieve a 2:1 displacement multiplication effect, providing a feasible path for shortening the system size. Compared with traditional PID control, the proposed fuzzy adaptive PID control strategy significantly improves the positioning accuracy of the system. The maximum tracking errors of the master and slave hydraulic cylinders are reduced from 6.3 mm and 10.4 mm to 2.3 mm and 5.6 mm, respectively, and the accuracy is improved by 63.49% and 46.15%, providing theoretical support and technical reference for the design of engineering drilling rig propulsion control systems. Full article

Deep Federated Learning (DFL) revolutionizes machine learning (ML) by enabling collaborative model training across diverse, decentralized data sources without direct data sharing, emphasizing user privacy and data sovereignty. Despite its potential, DFL’s application in sensitive sectors is hindered by challenges in meeting rigorous standards like the GDPR, with traditional setups struggling to ensure compliance and maintain trust. Addressing these issues, our research introduces an innovative Zero Trust-based DFL architecture designed for GDPR compliant systems, integrating advanced security and privacy mechanisms to ensure safe and transparent cross-node data processing. Our base paper proposed the basic GDPR-Compliant DFL Architecture. Now we validate the previously proposed architecture by formally verifying it using High-Level Petri Nets (HLPNs). This Zero Trust-based framework facilitates secure, decentralized model training without direct data sharing. Furthermore, we have also implemented a case study using the MNIST and CIFAR-10 datasets to evaluate the existing approach with the proposed Zero Trust-based DFL methodology. Our experiments confirmed its effectiveness in enhancing trust, complying with GDPR, and promoting DFL adoption in privacy-sensitive areas, achieving secure, ethical Artificial Intelligence (AI) with transparent and efficient data processing. Full article

The existence of fault zones in high-intensity earthquake areas has a serious impact on engineering structures, and the longitudinal response of tunnels crossing faults needs further in-depth research. To analyze the tangential contact effect between the surrounding rock and the tunnel lining, and the axial deformation characteristics of the tunnel structure, tangential foundation springs were introduced and a theoretical model for the longitudinal response of the tunnel under fault dislocation was established. Firstly, the tunnel was simplified as a finite-length beam. The normal and tangential springs were taken to represent the interaction between the soil and the lining. The fault’s free-field displacement was applied at the end of the normal foundation spring to simulate fault dislocation, and the differential equation for the longitudinal response of the tunnel structure was obtained. The analytical solution of the structural response was obtained using the Green’s function method. Then, the three-dimensional finite difference method was used to verify the effectiveness of the analytical model in this paper. The results show that the tangential contact effect between the surrounding rock and the lining has a significant impact on the longitudinal response of the tunnel structure. Ignoring this effect leads to an error of up to 35.33% in the peak value of the structural bending moment. Finally, the influences of the width of the fault zone, the soil stiffness of the fault zone, and the stiffness of the tunnel lining on the longitudinal response of the tunnel were explored. As the fault width increases, the internal force of the tunnel structure decreases. Increasing the lining concrete grade leads to an increase in the internal force of the structure. The increase in the elastic modulus of the surrounding rock in the fault area reduces the bending moment and shear force of the structure and increases the axial force. The research results can provide a theoretical basis for the anti-dislocation design of tunnels crossing faults. Full article

Artificial intelligence (AI)-generated content (AIGC) is an innovative technology that utilizes machine learning, AI models, reward modeling, and natural language processing (NLP) to create diverse digital content such as videos, images, and text. It has the potential to support various human activities with significant implications in teaching and learning, facilitating heuristic teaching for educators. By using AIGC, teachers can create extensive knowledge content and effectively design instructional strategies to guide students, aligning with heuristic teaching. However, incorporating AIGC into heuristic teaching has controversies and concerns, which potentially mislead outcomes. Nevertheless, leveraging AIGC greatly benefits teachers in enhancing heuristic teaching. When integrating AIGC to support heuristic teaching, challenges and risks must be acknowledged and addressed. These challenges include the need for users to possess sufficient knowledge reserves to identify incorrect information and content generated by AIGC, the importance of avoiding excessive reliance on AIGC, ensuring users maintain control over their actions rather than being driven by AIGC, and the necessity of scrutinizing and verifying the accuracy of information and knowledge generated by AIGC to preserve its effectiveness. Full article

As the penetration of intermittent renewable energy sources continues to increase, ensuring reliable power system and frequency stability is of importance. Battery energy storage systems (BESSs) have emerged as an important solution to mitigate these challenges by providing essential grid support services. In this context, a state-of-charge (SOC)-frequency control strategy for grid-forming BESSs is proposed to enhance their role in stabilizing grid frequency and improving overall system performance. In the system, the DC-link capacitor is regulated to maintain the angular frequency through a matching control scheme, emulating the characteristics of the rotor dynamics of a synchronous generator (SG). Thereby, the active power control is implemented in the control of the DC/DC converter to further regulate the grid frequency. More specifically, the relationship between the active power and the frequency is established through the SOC of the battery. In addition, owing to the inevitable presence of differential operators in the control loop, a high-gain observer (HGO) is employed, and the corresponding parameter design of the proposed method is elaborated. The proposed strategy simultaneously achieves frequency regulation and implicit energy management by autonomously balancing power output with available battery capacity, demonstrating a novel dual benefit for sustainable grid operation. To verify the effectiveness of the proposed control strategy, a 0.5-Hz frequency change and a 10% power change are carried out through simulations and also on a hardware-in-the-loop (HIL) platform. Full article

In the design of small-scale test models for hull structures, the directional dimensional analysis method is commonly employed. However, conventional dimensional analysis based on elasticity theory may be insufficient to capture the nonlinear behaviors of structural materials under dynamic loading, which restricts its applicability in ultimate strength tests for small-scale hull structure models. This paper presents a scaling method grounded in the theory of finite similitude. Based on the finite similitude theory, this paper deduces similarity scaling criteria applicable to the static and dynamic responses of box girders and designs a series of trial models of box girders. The scaling criteria are verified and analyzed through numerical tests conducted under static and dynamic loads. On the basis of the numerical test results of dynamic responses, the dynamic response similarity criteria considering the similarity relationship of material constitutive parameters are modified and verified. By applying the static response scaling criteria in this paper to select appropriate materials, the prediction deviation of the box girder trial models under static loads is less than 2%. With the modified dynamic response scaling criteria proposed in this paper, the prediction deviations of each trial model under dynamic loads are less than 2% and 7%. A comprehensive analysis of material parameters was conducted to examine their impact on the nonlinear similarities observed in the processes. To validate the ultimate strength and nonlinear response scaling criterion based on the finite similitude approach, numerical experiments were performed to assess the ultimate strength and dynamic buckling response characteristics of the box girder across various scaling ratios and material parameters. The analysis demonstrated that the ultimate strength scaling criterion and the nonlinear response scaling criterion derived from the finite similitude approach effectively captured material nonlinearity. The results from the small-scale model provided accurate predictions of the ultimate strength of the full-scale model. Full article

The increasing penetration of distributed renewable energy and the emergence of large-scale, flexible loads such as data centers pose significant challenges to the economic and secure operation of distribution systems. Traditional static pricing mechanisms are often inadequate, leading to inefficient resource dispatch and curtailment of renewable generation. To address these issues, this paper proposes a hierarchical pricing and dispatch framework modeled as a tri-level Stackelberg game that coordinates interactions among an upstream grid, a distribution system operator (DSO), and multiple virtual power plants (VPPs). At the upper level, the DSO acts as the leader, formulating dynamic time-varying purchase and sale prices to maximize its revenue based on upstream grid conditions. In response, at the lower level, each VPP acts as a follower, optimally scheduling its portfolio of distributed energy resources—including microturbines, energy storage, and interruptible loads—to minimize its operating costs under the announced tariffs. A key innovation is the integration of a schedulable data center within one VPP, which responds to a specially designed wind-linked incentive tariff by shifting computational workloads to periods of high renewable availability. The resulting high-dimensional bilevel optimization problem is solved using a Kriging-based surrogate methodology to ensure computational tractability. Simulation results verify that, compared to a static-pricing baseline, the proposed strategy increases DSO revenue by 18.9% and reduces total VPP operating costs by over 28%, demonstrating a robust framework for enhancing system-wide economic and operational efficiency. Full article

This study proposes a novel metaheuristic algorithm, Cosmic Evolution Optimization (CEO), for numerical optimization and engineering design. Inspired by the cosmic evolution process, CEO simulates physical phenomena including cosmic expansion, universal gravitation, stellar system interactions, and celestial orbital resonance.The algorithm introduces a multi-stellar framework system, which incorporates search agents into distinct subsystems to perform simultaneous exploration or exploitation behaviors, thereby enhancing diversity and parallel exploration capabilities. Specifically, the CEO algorithm was compared against ten state-of-the-art metaheuristic algorithms on 29 typical unconstrained benchmark problems from CEC2017 across different dimensions and 13 constrained real-world optimization problems from CEC2020. Statistical validations through the Friedman test, the Wilcoxon rank-sum test, and other statistical methods have confirmed the competitiveness and effectiveness of the CEO algorithm. Notably, it achieved a comprehensive Friedman rank of 1.28/11, and the winning rate in the Wilcoxon rank-sum tests exceeded 80% in CEC2017. Furthermore, CEO demonstrated outstanding performance in practical engineering applications such as robot path planning and photovoltaic system parameter extraction, further verifying its efficiency and broad application potential in solving real-world engineering challenges. Full article

In this paper, we study the classification problem of short-time-window steady-state visual evoked potentials (SSVEPs) and propose a novel deep convolutional network named EEGResNet based on the idea of residual connection to further improve the classification performance. Since the frequency-domain features extracted from short-time-window signals are difficult to distinguish, the EEGResNet starts from the filter bank (FB)-based feature extraction module in the time domain. The FB designed in this paper is composed of four sixth-order Butterworth filters with different bandpass ranges, and the four bandwidths are 19–50 Hz, 14–38 Hz, 9–26 Hz, and 3–14 Hz, respectively. Then, the extracted four feature tensors with the same shape are directly aggregated together. Furthermore, the aggregated features are further learned by a six-layer convolutional neural network with residual connections. Finally, the network output is generated through an adaptive fully connected layer. To prove the effectiveness and superiority of our designed EEGResNet, necessary experiments and comparisons are conducted over two large public datasets. To further verify the application potential of the trained network, a virtual simulation of brain computer interface (BCI) based quadrotor control is presented through V-REP. Full article

This paper reports a statistical analysis of a database archiving information on the strengths of the materials in existing Italian bridges having pre- and post-tensioned concrete beams. Data were collected in anonymous form by analyzing a stock of about 170 bridges built between 1960 and 2000 and located in several Italian regions. To date, the database refers to steel reinforcing bars, concrete, and prestressing steel, whose strengths were gathered from design nominal values, acceptance certificates, and in situ test results, all derived by consulting the available documents for each examined bridge. At first, this paper describes how the available data were collected. Then, the results of a statistical analysis are presented and commented on. Moreover, goodness-of-fit tests are carried out to verify the assumption validity of a normal distribution for steel reinforcing bars and prestressing steel, and a log-normal distribution for concrete. The database represents a valuable resource for researchers and practitioners for the assessment of existing bridges. It may be applied for the use of prior knowledge within a framework where Bayesian methods are included for reducing uncertainties. The database provides essential information on the strengths of the materials to be used for a simulated design and/or for verification in the case of limited knowledge. Goodness-of-fit tests make the collected information very useful, even if probabilistic methods are applied. Full article

The growing need for secure and privacy-preserving identity management in industrial environments has exposed the limitations of traditional, centralized authentication systems. In this context, SIBERIA was developed as a modular solution that empowers users to control their own digital identities, while ensuring robust protection of critical services. The system is designed in alignment with European standards and regulations, including EBSI, eIDAS 2.0, and the GDPR. SIBERIA integrates a Self-Sovereign Identity (SSI) framework with a decentralized blockchain-based infrastructure for the issuance and verification of Verifiable Credentials (VCs). It incorporates multi-factor authentication by combining a voice biometric module, enhanced with spoofing-aware techniques to detect synthetic or replayed audio, and a behavioral biometrics module that provides continuous authentication by monitoring user interaction patterns. The system enables secure and user-centric identity management in industrial contexts, ensuring high resistance to impersonation and credential theft while maintaining regulatory compliance. SIBERIA demonstrates that it is possible to achieve both strong security and user autonomy in digital identity systems by leveraging decentralized technologies and advanced biometric verification methods. Full article

Considering the challenges posed by traditional continuous control set model predictive control (CCS-MPC) calculations, this paper proposes an event-triggered-based model predictive control (ET-MPC). First, a novel tracking error state-space model is proposed to improve tracking performance. Second, a reduced-order extended state observer (RESO) is designed to estimate and compensate for the total disturbances, thereby effectively improving robustness against the variations of the load resistance and reference voltage. At the same time, RESO significantly reduces computational complexity and accelerates the convergence speed of state estimation. Subsequently, an event trigger mechanism is introduced to enhance the MPC with a threshold function for the converter status. Finally, the reduced-order extended state observer-based model predictive control (RESO-MPC) is compared with the proposed ET-MPC through experiments. The ripple voltage of ET-MPC is within 2%, and the computational burden is reduced by more than 57%, verifying the effectiveness of the proposed ET-MPC. Full article