Search Results (3,505)

This study advances the field of infectious disease forecasting by introducing a novel approach to micro-level contact modeling, leveraging human movement patterns to generate realistic temporal-dynamic networks. Through the incorporation of human mobility models and parameter tuning, this research presents an innovative method for simulating micro-level encounters that closely mirror infection dynamics within confined spaces. Central to our methodology is the application of Bayesian optimization for parameter selection, which refines our models to emulate both the properties of real-world infection curves and the characteristics of network properties. Typically, large-scale epidemiological simulations overlook the specifics of human mobility within confined spaces or rely on overly simplistic models. By focusing on the distinct aspects of infection propagation within specific locations, our approach strengthens the realism of such pandemic simulations. The resulting models shed light on the role of spatial encounters in disease spread and improve the capability to forecast and respond to infectious disease outbreaks. This work not only contributes to the scientific understanding of micro-level transmission patterns but also offers a new perspective on temporal network generation for epidemiological modeling. Full article

Hydraulic pumps are the core components that provide power for hydraulic transmission systems, which are widely used in aerospace, marine engineering, and mechanical engineering, and their failure affects the normal operation of the entire system. This paper takes a single axial piston pump as the research object and proposes a small-sample fault diagnosis method based on the model migration strategy for the situation in which only a small number of training samples are available for axial piston pump fault diagnosis. To achieve end-to-end fault diagnosis, a 1D Squeeze-and-Excitation Networks (1D-SENets) model was constructed based on a one-dimensional convolutional neural network and combined with the channel domain attention mechanism. The model was first pre-trained with sufficient labeled fault data from the source conditions, and then, based on the model migration strategy, some of the underlying network parameters were fixed, and a small amount of labeled fault data from the target conditions was used to fine-tune the rest of the parameters of the pre-trained model. In this paper, the proposed method was validated using an axial piston pump fault dataset, and the experimental results show that the method can effectively improve the overfitting problem in the small sample fault diagnosis of axial piston pumps and improve the recognition accuracy. Full article

Small wind turbines operating in low wind speed regions have not had any significant success. In addition, small wind speed regions occupy a large area of the world, so they represent a potential area for installing small wind turbines in the future. In this paper, a method to design an efficient airfoil for small wind turbines in low wind speed conditions using XFLR5 and CFD simulations is implemented. Because the impact of the airflow on the blade surface under low Re number conditions can change suddenly for small geometries, designing the airfoil shape to optimize the aerodynamic performance is essential. The tuning of the key geometric parameters using inversion techniques for better aerodynamic performance is presented in this study. A two-dimensional model was used to consider the airflow on the airfoil surface with differences in the angle of attack. The original S1010 airfoil was used to design a new airfoil for increasing the aerodynamic efficiency by using V6.57 XFLR5 software. Subsequently, the new VAST-EPU-S1010 airfoil model was adjusted to the maximum thickness and the maximum thickness position. It was simulated in low wind speed conditions of 4–6 m/s by a computational fluid dynamics simulation. The lift coefficient, drag coefficient, and C_L/C_D coefficient ratio were evaluated under the effect of the angle of attack and the maximum thickness by using the k-ε model. The simulation results show that the VAST-EPU-S1010 airfoil achieved the greatest aerodynamic efficiency at an angle of attack of 3°, a maximum thickness of 8%, and a maximum thickness position of 20.32%. The maximum value of C_L/C_D of the new airfoil at 6 m/s was higher than at 4 m/s by about 6.25%. Full article

Traditional mean-variance (MV) models, considered effective in stable conditions, often prove inadequate in uncertain market scenarios. Therefore, there is a need for more robust and better portfolio optimization methods to handle the fluctuations and uncertainties in asset returns and covariances. This study aims to perform a Systematic Literature Review (SLR) on robust portfolio mean-variance (RPMV) in stock investment utilizing genetic algorithms (GAs). The SLR covered studies from 1995 to 2024, allowing a thorough analysis of the evolution and effectiveness of robust portfolio optimization methods over time. The method used to conduct the SLR followed the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. The result of the SLR presented a novel strategy to combine robust optimization methods and a GA in order to enhance RPMV. The uncertainty parameters, cardinality constraints, optimization constraints, risk-aversion parameters, robust covariance estimators, relative and absolute robustness, and parameters adopted were unable to develop portfolios capable of maintaining performance despite market uncertainties. This led to the inclusion of GAs to solve the complex optimization problems associated with RPMV efficiently, as well as fine-tuning parameters to improve solution accuracy. In three papers, the empirical validation of the results was conducted using historical data from different global capital markets such as Hang Seng (Hong Kong), Data Analysis Expressions (DAX) 100 (Germany), the Financial Times Stock Exchange (FTSE) 100 (U.K.), S&P 100 (USA), Nikkei 225 (Japan), and the Indonesia Stock Exchange (IDX), and the results showed that the RPMV model optimized with a GA was more stable and provided higher returns compared with traditional MV models. Furthermore, the proposed method effectively mitigated market uncertainties, making it a valuable tool for investors aiming to optimize portfolios under uncertain conditions. The implications of this study relate to handling uncertainty in asset returns, dynamic portfolio parameters, and the effectiveness of GAs in solving portfolio optimization problems under uncertainty, providing near-optimal solutions with relatively lower computational time. Full article

In optical remote sensing image object detection, discontinuous boundaries often limit detection accuracy, particularly at high Intersection over Union (IoU) thresholds. This paper addresses this issue by proposing the Spatial Adaptive Angle-Aware (${\mathrm{SA}}^3$) Network. The ${\mathrm{SA}}^3$ Network employs a hierarchical refinement approach, consisting of coarse regression, fine regression, and precise tuning, to optimize the angle parameters of rotated bounding boxes. It adapts to specific task scenarios using either class-aware or class-agnostic strategies. Experimental results demonstrate its effectiveness in significantly improving detection accuracy at high IoU thresholds. Additionally, we introduce a Gaussian transform-based IoU factor during angle regression loss calculation, leading to the development of Edge-aware Skewed Bounding Box Loss (EAS Loss). The EAS loss enhances the loss gradient at the final stage of angle regression for bounding boxes, addressing the challenge of further learning when the predicted box angle closely aligns with the real target box angle. This results in increased training efficiency and better alignment between training and evaluation metrics. Experimental results show that the proposed method substantially enhances the detection accuracy of ReDet and ReBiDet models. The ${\mathrm{SA}}^3$ Network and EAS loss not only elevate the mAP of the ReBiDet model on DOTA-v1.5 to 78.85% but also effectively improve the model’s mAP under high IoU threshold conditions. Full article

Potential photovoltaic technology includes the newly developed dye-sensitized solar cells (DSSCs) and bulk heterojunction (BHJ) solar cells. Owing to their diverse qualities, polymers can be employed in third-generation photovoltaic cells to specifically alter their device elements and frameworks. Polymers containing phenothiazine, either as a part of their structure or as a dopant, are easy and economical to synthesize, are soluble in common organic solvents, and have the potential to acquire desired electrochemical and photophysical properties by mere tuning of their chemical structures. Such polymers have therefore been used either as photosensitizers in dye-sensitized solar cells, where they have produced power conversion efficiency (PCE) values as high as 5.30%, or as donor or acceptor materials in bulk heterojunction solar cells. Furthermore, they have been employed to prepare liquid-free polymer electrolytes for dye-sensitized and bulk heterojunction solar cells, producing a PCE of 8.5% in the case of DSSCs. This paper reviews and analyzes almost all research works published to date on phenothiazine-based polymers and their uses in dye-sensitized and bulk heterojunction solar cells. The impacts of their structure and molecular weight and the amount when used as a dopant in other polymers on the absorption, photoluminescence, energy levels of frontier orbitals, and, finally, photovoltaic parameters are reviewed. The advantages of phenothiazine polymers for solar cells, the difficulties in their actual implementation and potential remedies are also evaluated. Full article

This work presents a copper zinc tin sulfide (CZTS)-based solar cell structure (AI/ITO/C₆₀/CZTS/SnS/Pt) with C₆₀ as a buffer layer, developed using the SCAPS-1D simulator by optimizing each parameter to calculate the output. Optimizing the parameters, the acceptor concentration and thickness were altered from 6.0 × 10¹⁵ cm⁻³ to 6.0 × 10¹⁸ cm⁻³ and 1500 nm to 3000 nm, respectively. Although, in this simulator, we can tune the value for the acceptor concentration to 6.0 × 10²², higher doping might present an issue regarding adjustment in the physical experiment. Thus, tunable parameters need to be chosen according to the reliability of the experimental work. The defect density varied from 1.0 × 10¹⁴ cm⁻³ to 1.0 × 10¹⁷ cm⁻³ and the auger hole/electron capture coefficient was determined to be 1.0 × 10⁻²⁶ cm⁶ s⁻¹ for the maintenance of the minorities in theoretical to quasi-proper experimental measurements. Although the temperature was intended to be kept near room temperature, this parameter was varied from 290 K to 475 K to investigate the effects of the temperature on this cell. The optimization of the proposed structure resulted in a final acceptor concentration of 6.0 × 10¹⁸ cm⁻³ and a thickness of 3000 nm at a defect density of 1.0 × 10¹⁵ cm⁻³, which will help to satisfy the desired experimental performance. Satisfactory outcomes (V_OC = 1.24 V, J_SC = 27.03 mA/cm², FF = 89.96%, η = 30.18%) were found compared to the previous analysis. Full article

This study presents the design and simulation of an RF MEMS variable capacitor with a high tuning ratio and high linearity factor of capacitance–voltage response. An electrostatic torsion actuator with planar and non-planar structures is presented to obtain the high tuning ratio by avoiding the occurrence of pull-in point. In the proposed design, the capacitor plate is connected to the electrostatic actuators by using the s-shaped beam. The proposed design shows a 138% tuning ratio with the planar structure of the actuator and 167% tuning ratio by implementing the non-planar structure. A linearity factor of 99% is attained by adjusting the rates at which the capacitor plate rises as the actuation voltage increases and the rate at which the capacitance decreases as the plate rises. Parametric optimization of the design is performed by utilizing the finite element method (FEM) analysis and high-frequency structural simulator (HFSS) analysis to obtain an optimized high-tuning ratio RF MEMS varactor at low actuation voltage. S-parameters of the design are presented on HFSS, with a 50 ohm coplanar waveguide (CPW) serving as the transmission line. The proposed RF MEMS varactor can be utilized in tunable RF devices. Full article

Compared to hyperspectral trackers that adopt the “pre-training then fine-tuning” training paradigm, those using the “pre-training then prompt-tuning” training paradigm can inherit the expressive capabilities of the pre-trained model with fewer training parameters. Existing hyperspectral trackers utilizing prompt learning lack an adequate prompt template design, thus failing to bridge the domain gap between hyperspectral data and pre-trained models. Consequently, their tracking performance suffers. Additionally, these networks have a poor generalization ability and require re-training for the different spectral bands of hyperspectral data, leading to the inefficient use of computational resources. In order to address the aforementioned problems, we propose a spectral similarity prompt learning approach for hyperspectral object tracking (SPTrack). First, we introduce a spectral matching map based on spectral similarity, which converts 3D hyperspectral data with different spectral bands into single-channel hotmaps, thus enabling cross-spectral domain generalization. Then, we design a channel and position attention-based feature complementary prompter to learn blended prompts from spectral matching maps and three-channel images. Extensive experiments are conducted on the HOT2023 and IMEC25 data sets, and SPTrack is found to achieve state-of-the-art performance with minimal computational effort. Additionally, we verify the cross-spectral domain generalization ability of SPTrack on the HOT2023 data set, which includes data from three spectral bands. Full article

A large language model refers to a deep learning model characterized by extensive parameters and pretraining on a large-scale corpus, utilized for processing natural language text and generating high-quality text output. The increasing deployment of large language models has brought significant attention to their associated privacy and security issues. Recent experiments have demonstrated that training data can be extracted from these models due to their memory effect. Initially, research on large language model training data extraction focused primarily on non-targeted methods. However, following the introduction of targeted training data extraction by Carlini et al., prefix-based extraction methods to generate suffixes have garnered considerable interest, although current extraction precision remains low. This paper focuses on the targeted extraction of training data, employing various methods to enhance the precision and speed of the extraction process. Building on the work of Yu et al., we conduct a comprehensive analysis of the impact of different suffix generation methods on the precision of suffix generation. Additionally, we examine the quality and diversity of text generated by various suffix generation strategies. The study also applies membership inference attacks based on neighborhood comparison to the extraction of training data in large language models, conducting thorough evaluations and comparisons. The effectiveness of membership inference attacks in extracting training data from large language models is assessed, and the performance of different membership inference attacks is compared. Hyperparameter tuning is performed on multiple parameters to enhance the extraction of training data. Experimental results indicate that the proposed method significantly improves extraction precision compared to previous approaches. Full article

Mobile observation has been widely used in the monitoring of air pollution. However, studies on pollution sources and emission characteristics based on mobile navigational observation are rarely reported in the literature. A method for quantitative source analysis for industrial air pollutant emissions based on mobile observations is introduced in this paper. NO_x pollution identified in mobile observations is used as an example of the development of the method. A dispersion modeling scheme that fine-tuned the meteorological parameters according to the actual meteorological conditions was adopted to minimize the impact of uncertainties in meteorological conditions on the accuracy of small-scale dispersion modeling. The matching degree between simulated and observed concentrations was effectively improved through this optimization search. In response to the efficiency requirements of source resolution for multiple sources, a random search algorithm was first used to generate candidate solution samples, and then the solution samples were evaluated and optimized. Meanwhile, the new index $S_{match}$ was established to evaluate the quality of candidate samples, considering both numerical error and spatial distribution error of concentration, in order to address the non-uniqueness of the solution in the multi-source problem. Then, the necessity of considering the spatial distribution error of concentration is analyzed with the case study. The average values of NO_x emission rates for the two study cases were calculated as 69.8 g/s and 70.8 g/s. The $S_{match}$ scores were 0.92–0.97 and 0.92–0.99. The results were close to the online monitoring data, and this kind of pollutant emission monitoring based on the mobile observation experiment was initially considered feasible. Additional analysis and clarifications were provided in the discussion section on the impact of uncertainties in meteorological conditions, the establishment of a priori emission inventories, and the interpretation of inverse calculation results. Full article

A long-standing research goal is to develop computing technologies that mimic the brain’s capabilities by implementing computation in electronic systems directly inspired by its structure, function, and operational mechanisms, using low-power, spike-based neural networks. The Loihi neuromorphic processor provides a low-power, large-scale network of programmable silicon neurons for brain-inspired artificial intelligence applications. This paper exploits the Loihi processors and a theory-guided methodology to enable unsupervised learning of spike patterns. Our method ensures efficient and rapid selection of the network’s hyperparameters, enabling the neuromorphic processor to generate attractor states through real-time unsupervised learning. Precisely, we follow a fast design process in which we fine-tune network parameters using mean-field theory. Moreover, we measure the network’s learning ability regarding its error correction and pattern completion aptitude. Finally, we observe the dynamic energy consumption of the neuron cores for each millisecond of simulation equal to 23 $\mathsf{\mu }$J/time step during the learning and recall phase for four attractors composed of 512 excitatory neurons and 256 shared inhibitory neurons. This study showcases how large-scale, low-power digital neuromorphic processors can be quickly programmed to enable the autonomous generation of attractor states. These attractors are fundamental computational primitives that theoretical analysis and experimental evidence indicate as versatile and reusable components suitable for a wide range of cognitive tasks. Full article

A model for generating synthetic time series data using pre-trained large language models is proposed. Starting with the Google T5-base model, which employs an encoder–decoder transformer architecture, the model underwent pre-training on diverse datasets. It was then fine-tuned using the QLoRA technique, which reduces computational complexity by quantizing weight parameters. The process involves the tokenization of time series data through mean scaling and quantization. The performance of the model was evaluated with fidelity, utility, and privacy metrics, showing improvements in fidelity and utility but a trade-off with reduced privacy. The proposed model offers a foundation for decision intelligence systems. Full article

In this study, an optimization method for the motion trajectory of attitude actuators was investigated in order to improve assembly efficiency in the automatic docking process of large components. The self-developed dual-attitude adjustment mechanism (2-PPPR) is used as the research object, and the structure is symmetrical. Based on the modified Denavit–Hartenberg (MDH) parameter description method, a kinematic model of the attitude mechanism is established, and its end trajectory is parametrically expressed using a five-order B-spline curve. Based on the constraints of the dynamics and kinematics of the dual-posture mechanism, the total posturing time, the degree of urgency of each joint, and the degree of difficulty of the mechanism’s posturing are selected as the optimization objectives. The Lévy flight and Cauchy variation algorithms are introduced into the salp swarm algorithm (SSA) to solve the parameters of the multi-objective trajectory optimization model. By combining the evaluation method of the multi-objective average optimal solution, the optimal trajectory of the dual-tuning mechanism and the motion trajectory of each joint are obtained. The simulation and experiment results show that the trajectory planning method proposed in this paper is effective and feasible and can ensure that the large-part dual-posture mechanism can complete the automatic docking task smoothly and efficiently. Full article

The current study begins with an experimental investigation focused on measuring the pressure drop of a water–air mixture under different flow conditions in a setup consisting of horizontal smooth tubes. Machine learning (ML)-based pipelines are then implemented to provide estimations of the pressure drop values employing obtained dimensionless features. Subsequently, a feature selection methodology is employed to identify the key features, facilitating the interpretation of the underlying physical phenomena and enhancing model accuracy. In the next step, utilizing a genetic algorithm-based optimization approach, the preeminent machine learning algorithm, along with its associated optimal tuning parameters, is determined. Ultimately, the results of the optimal pipeline provide a Mean Absolute Percentage Error (MAPE) of 5.99% on the validation set and 7.03% on the test. As the employed dataset and the obtained optimal models will be opened to public access, the present approach provides superior reproducibility and user-friendliness in contrast to existing physical models reported in the literature, while achieving significantly higher accuracy. Full article