Hybrid Method Research Articles

PW-FBPNN: A Hybrid Fault Diagnosis Method for Power Circuit Systems Combining Principal Component Analysis, Wavelet Packet Transform, and Fuzzy Neural Networks

Due to the complexity of fault states and the non-linear relationship between input and output responses, fault diagnosis in complex power circuit systems faces significant challenges. This study proposes a novel hybrid method, PW-FBPNN, which integrates principal component analysis (PCA), wavelet packet transform (WPT), and fuzzy back propagation neural network (FBPNN) to enhance fault diagnosis. The effectiveness of this method was demonstrated through experiments on the voltage divider basic operational amplifier and the second-order filter circuit of the four operational amplifiers. PW-FBPNN achieved 100% accuracy in diagnosing most types of faults, with a minimum accuracy of 91.67% for challenging faults. This method was significantly superior to existing methods such as FCM-HMM-SVM and KICA-DNN in terms of accuracy and computational efficiency and could complete the diagnosis in just 0.01 seconds. These results indicate that PW-FBPNN has the potential to improve fault diagnosis in power circuit systems, providing a promising solution for enhancing system reliability and maintenance efficiency.

Enhancing water security through advanced modeling: integrating deep learning and a novel metaheuristic optimization algorithm for accurate pan evaporation prediction

ABSTRACT This study evaluates and enhances machine learning models for predicting pan evaporation under diverse climatic conditions. Five fundamental machine learning models were employed and tested across four different stations. Subsequent comparisons were made with advanced techniques, including long short-term memory (LSTM) networks. An innovative approach was introduced, combining LSTM with Binary Al-Biruni Earth Radius (BER–LSTM). This hybrid method was benchmarked against other optimization techniques. The BER–LSTM model consistently outperformed other models across all stations and time scales, achieving up to a 97.54% improvement in root mean square error (RMSE) compared to standard LSTM on daily time scales. Compared to simpler models like Multilayer Perceptron and Support Vector Regressor, BER–LSTM showed even more substantial improvements, with up to a 99.03% reduction in RMSE. The BER–LSTM model demonstrates superior predictive capabilities for pan evaporation across varied climatic conditions, offering significant improvements over both traditional and advanced machine learning techniques. This approach shows promise for enhancing evaporation forecasting in diverse environmental contexts.

Detection of Diffusion Interlayers in Dissimilar Welded Joints in Processing Pipelines by Acoustic Emission Method

The paper considers the neural network application to detect microstructure defects in dissimilar welded joints using the acoustic emission (AE) method. The peculiarity of the proposed approach is that defect detection is carried out taking into account a priori information about the properties of the AE source and the acoustic waveguide parameters of the testing structure. Industrial process pipelines with dissimilar welded joints were studied as the testing object, and diffusion interlayers formed in fusion zones of welded joints were considered microstructure defects. The simulation of AE signals was carried out using a hybrid method: the signal waveform was determined based on a finite element model, while the amplitudes of AE hits were determined based on a physical experiment on mechanical testing of dissimilar welded joints. Measurement data from industrial process pipelines were used as noise realizations. As a result, a data sample was formed that considered the parameters of the AE source and the parameters of the acoustic waveguide with realistic noise parameters and a signal-to-noise ratio. The proposed method allows for a more accurate determination of the waveform, spectrum, and amplitude parameters of the AE signal. Greater certainty in the useful signal parameters allows for achieving a more accurate and reliable classification result. When using a backpropagation neural network, a percentage of correct classification of more than 90% was obtained for a data set in which the signal-to-noise ratio was less than (−5 dB) in 90% of cases.

AN INVESTIGATION ON NONLINEAR OPTION PRICING BEHAVIOURS THROUGH A NEW FRÉCHET DERIVATIVE-BASED QUADRATURE APPROACH

Abstract Complicated option pricing models attract much attention in financial industries, as they produce relatively better accurate values by taking into account more realistic assumptions such as market liquidity, uncertain volatility and so forth. We propose a new hybrid method to accurately explore the behaviour of the nonlinear pricing model in illiquid markets, which is important in financial risk management. Our method is based on the Newton iteration technique and the Fréchet derivative to linearize the model. The linearized equation is then discretized by a differential quadrature method in space and a quadratic trapezoid rule in time. It is observed through computations that the accurate solutions for the model emerge using very few grid points and time elements, compared with the finite difference method in the literature. Furthermore, this method also helps to avoid consideration of the convergence issues of the Newton approach applied to the nonlinear algebraic system containing many unknowns at each time step if an implicit method is used in time discretization. It is important to note that the Fréchet derivative supports to enhance the convergence order of the proposed iterative scheme.

Medical Image Segmentation

Medical image segmentation is a critical component in the development of computer-aided diagnosis and treatment planning systems. This paper provides a comprehensive survey of recent advances in segmentation techniques applied to various imaging modalities, including Magnetic Resonance Imaging (MRI). Traditional methods such as thresholding, region-growing, and active contours are reviewed alongside contemporary machine learning-based approaches, particularly deep learning models. The survey emphasizes the growing dominance of convolutional neural networks (CNNs) and their variants, including U-Net and Fully Convolutional Networks (FCNs), which have shown remarkable success in handling complex medical imaging challenges. Additionally, the paper discusses hybrid methods that combine classical techniques with artificial intelligence to improve accuracy and robustness in segmentation tasks. Key challenges such as class imbalance, boundary delineation, and computational efficiency are also highlighted. Future directions, including the integration of multi-modal data and advancements in self-supervised learning, are explored as potential solutions to overcome current limitations in medical image segmentation.

Design and Simulation of Adaptive Filters in Real-Time Environment

The results of the study showed that adaptive filters were designed and simulated to enhance signal processing capabilities in real-time environments. The study focused on the LMS and NLMS algorithms for echo and noise cancellation in audio signals, exploring the impact of different mu values (0.01, 0.05, 0.1, and 0.5) on algorithm performance. A comprehensive literature review underscored the importance of effective adaptive filtering techniques in real-time audio processing and highlighted the trade-off between convergence speed and stability. The results indicated that a mu value between 0.05 and 0.1 optimally balances convergence speed and stability for both LMS and NLMS algorithms. The NLMS algorithm consistently outperformed LMS due to its superior adaptation to signal power variations and better stability at higher mu values. Recommendations include using the NLMS algorithm for most applications, careful tuning of the mu value, and further research into adaptive and hybrid methods. These findings aimed to enhance echo and noise cancellation, resulting in clearer and more intelligible audio signals in real-world applications. Keywords: Adaptive Filters, LMS Algorithm, NLMS Algorithm, Real-Time Signal Processing

Targeted Drug Delivery: From Chemistry to Robotics at Small Scales

The limited bioavailability, susceptibility to degradation, and adverse side effects of novel drugs often hinder their effective administration. Nanoparticles, with customizable properties and small size, have emerged as potential carriers, though their delivery efficiency remains low. With their ability to navigate fluid environments, micro- and nanorobots offer promising solutions to improve the delivery and retention of drugs at targeted tissues. The design and composition of these motile devices, often inspired by natural locomotion mechanisms, are currently being refined for improved biocompatibility, adaptability, and collective task performance. Recent research has focused on loading these devices with therapeutic agents and evaluating their efficacy in living organisms. While chemotherapy has been predominant, micro- and nanorobots also show significant potential for biological and physical therapies, and hybrid methods combining multiple therapies have demonstrated synergistic benefits. This review identifies major challenges, including the need for application-specific solutions, standardized performance evaluation methods, and the integration of engineering with pharmacology.

An Autotuning Hybrid Method with Bayesian Optimization for Road Edge Extraction in Highway Systems from Point Clouds

In transportation infrastructure systems, feature images and spatial characteristics are generally utilized as complementary elements derived from point clouds for road edge extraction, but the involvement of one or more hyperparameters in each makes the extraction complicated. This study proposes an autotuning hybrid method with Bayesian optimization for road edge extraction in highway systems. The hybrid method combines the strengths of 2D feature images and 3D spatial characteristics while also automatically tuning the hyperparameter combination using Bayesian optimization. The hyperparameters encompass high and low pixel gradient thresholds, neighborhood radius, and normal vector threshold. Later, the point cloud dataset of national highways in Henan Province, China, is taken as the case study to evaluate the performance of the proposed method against three benchmark methods in two typical road scenarios: straight and curved edges. Experimental results show that the proposed method outperforms the benchmarks in detection quality and accuracy. It can serve as a decision-making tool to complement traditional manual road surveying, enabling efficient and automated road edge extraction in highway systems.

Accurate Medical Vial Identification Through Mixed Reality: A HoloLens 2 Implementation

The accurate identification of medicine vials is crucial for emergency medical services, especially for vials that resemble one another but have different labels, volumes, and concentrations. This study introduces a method to detect vials in real-time using mixed reality technology through Microsoft HoloLens 2. The system is also equipped with an SQL server to manage barcode and vial information. We conducted a comparative analysis of the barcode detection capabilities of the HoloLens 2 camera and an external scanner. The HoloLens 2 effectively identified larger barcodes when they were 20–25 cm away in normal lighting conditions. However, it faced difficulties in detecting smaller barcodes that were consistently detected by the external scanner. The frame rate investigation revealed performance fluctuations: an average of 10.54 frames per second (fps) under standard lighting conditions, decreasing to 10.10 fps in low light and further reducing to 10.05 fps when faced with high barcode density. Resolution tests demonstrated that a screen resolution of 1920 × 1080 yielded the best level of accuracy, with a precision rate of 98%. On the other hand, a resolution of 1280 × 720 achieved a good balance between accuracy 93% and speed. The HoloLens 2 demonstrates satisfactory performance under ideal circumstances; however, enhancements in detecting algorithms and camera resolution are required to accommodate diverse surroundings. This approach seeks to help paramedics make quick and accurate decisions during critical situations and tackle common obstacles such as reliance on networks and human mistakes. Our new approach of a hybrid method that integrates an external Bluetooth scanner with the MR device gives optimal results compared to the scanner-only approach.

Research on Financial Investment Risk Assessment Techniques and Applications

In recent years, the financial markets have undergone rapid development and significant volatility, leading to a pronounced urgency and complexity in investment risk assessment. This study explores the technologies and applications of financial investment risk evaluation, offering an in-depth analysis of the theoretical foundations and practical operations of quantitative, qualitative, and hybrid assessment methodologies. Traditional quantitative techniques, such as the Value at Risk (VaR) model, provide crucial objective data support, while qualitative approaches enrich the breadth of risk identification through expert opinions and seasoned experience. Hybrid methods synergistically combine the strengths of both, adapting to the intricacies of the market environment. The integration of big data and artificial intelligence technologies injects innovative momentum into risk assessment, enabling more precise and timely risk monitoring. Case applications span multi-layered risk management strategies within banks, insurance companies, and hedge funds, offering valuable insights for diverse financial institutions. The study posits that efficient risk assessment relies not only on technological advancements but also necessitates consideration of market dynamics and regulatory environment fluctuations. Continual innovation and practical optimization are pivotal in addressing future challenges.

A DIC-FEM hybrid method for measuring strains near fiber-matrix interface of CFRP cross section

A DIC-FEM hybrid method is proposed to capture micro-scale deformation behavior near the fiber-matrix interface by combining displacement distributions measured using digital image correlation (DIC) with finite element method (FEM) analysis. Images of CFRP cross section with fine random pattern before and after deformation are taken with a laser microscope. The in-plane displacement components near the interface of fiber and matrix are obtained using digital image correlation and they are used as the input of the hybrid method. Not only the displacement distributions but the strain fields are determined using the proposed hybrid method, based on the superposition principle, so that the same distributions are obtained as those obtained by the measurement. The proposed DIC-FEM hybrid provides the strains near the interface between fiber and matrix, compensating for the insufficient resolution of microscope images.

Flow Separation Control and Aeroacoustic Effects of a Leading-Edge Slat over a Wind Turbine Blade

To enable wind energy to surpass fossil fuels, the power-to-cost ratio of wind turbines must be competitive. Increasing installation capacities and wind turbine sizes indicates a strong trend toward clean energy. However, larger rotor diameters, reaching up to 170 m, introduce stability and aeroelasticity concerns and aerodynamic phenomena that cause noise disturbances. These issues hinder performance enhancement and social acceptance of wind turbines. A critical aerodynamic challenge is flow separation on the blade’s suction side, leading to a loss of lift and increased drag, ultimately stalling the blade and reducing turbine performance. Various active and passive flow control techniques have been studied to address these issues, with passive techniques offering the advantage of no external energy requirement. High-lift devices, such as leading-edge slats, are promising in improving aerodynamic performance by controlling flow separation. This study explores the geometric parameters of slats and their effects on wind turbine blades’ aerodynamic and acoustic performance. Using an adequate turbulence model at Re = 106 for angles of attack from 14° to 24°, 77 slat configurations were evaluated. Symmetric slats showed superior performance at high angles of attack, while slat chord length was inversely proportional to aerodynamic improvement. A hybrid method was employed to predict noise, revealing slat-induced modifications in eddy topology and increased low- and high-frequency noise. This study’s main contribution is correlating slat-induced aerodynamic improvements with their acoustic effects. The directivity reveals a 10–15 dB reduction induced by the slat at 1 kHz, while the slat induces higher noise at higher frequencies.

An interior inverse generalized impedance problem for the modified Helmholtz equation in two dimensions

AbstractWe consider the inverse interior problem of recovering the surface impedances of the cavity from sources and measurements placed on a curve inside of it. The uniqueness issue is investigated, and a hybrid method is proposed for the numerical solution. The approach takes advantages of both direct and iterative schemes, such as it does not require an initial guess and has an accuracy of a Newton‐type method. Presented numerical experiments demonstrate the feasibility and effectiveness of the approach.

Home Services Recommendation System using Machine Learning for Urban Areas

The Kotlin-based on-demand home service system streamlines household tasks by offering services such as repairs, cleaning, gardening, and plumbing. In today's fast-paced world, it provides quick solutions for maintaining a clean and hygienic living environment. The Housekeeper Finder app is a prominent player in this space, utilizing advanced machine learning algorithms to deliver personalized service recommendations based on user preferences. It includes essential services like cooking, laundry, and elder care, along with a robust feedback system to improve service quality. Users can easily book services from anywhere, leveraging GPS technology to connect them with nearby providers. The "Domestic Android Application for Home Services" further enhances accessibility through location-based service requests and mapping capabilities for a seamless user experience across platforms.A s cities transition into Smart Cities, integrated information systems open new avenues for urban service recommendations, fostering liveability and sustainability. Recommendation systems analyse user behaviour to provide tailored suggestions using techniques like collaborative filtering and hybrid methods. In response to the challenges of modern work culture, the e-commerce landscape now offers easy access to essential services via mobile applications, ultimately transforming how households address their needs and promoting safer, cleaner living space.

Employing Xception convolutional neural network through high-precision MRI analysis for brain tumor diagnosis

The classification of brain tumors from medical imaging is pivotal for accurate medical diagnosis but remains challenging due to the intricate morphologies of tumors and the precision required. Existing methodologies, including manual MRI evaluations and computer-assisted systems, primarily utilize conventional machine learning and pre-trained deep learning models. These systems often suffer from overfitting due to modest medical imaging datasets and exhibit limited generalizability on unseen data, alongside substantial computational demands that hinder real-time application. To enhance diagnostic accuracy and reliability, this research introduces an advanced model utilizing the Xception architecture, enriched with additional batch normalization and dropout layers to mitigate overfitting. This model is further refined by leveraging large-scale data through transfer learning and employing a customized dense layer setup tailored to effectively distinguish between meningioma, glioma, and pituitary tumor categories. This hybrid method not only capitalizes on the strengths of pre-trained network features but also adapts specific training to a targeted dataset, thereby improving the generalization capacity of the model across different imaging conditions. Demonstrating an important improvement in diagnostic performance, the proposed model achieves a classification accuracy of 98.039% on the test dataset, with precision and recall rates above 96% for all categories. These results underscore the possibility of the model as a reliable diagnostic tool in clinical settings, significantly surpassing existing diagnostic protocols for brain tumors.

Research on the Principles and Applications of Generative Adversarial Networks in Image Style Transfer

Abstract. With the rapid development of machine learning, the field of image style transfer has received widespread attention, and scientists have gradually realized that this is an important field in computer vision. Image style transfer refers to the conversion of an image from one visual style to another and preserving the content. The technology of changing image style has a wide range of applications in various fields from art to virtual reality. Although current learning models have achieved some results in the study of image style transfer, they still face challenges in improving resolution and complex style transfer. This paper mainly introduces the background and characteristics of existing learning models that can achieve image style transfer. It introduces the principles, characteristics and limitations of GANs. In the basis of introduction, this paper also analyses the differences and different characteristics of GANs and summarizes the advantages and disadvantages of GANs. At the same time, this paper predicts future research directions, continuing to optimize these models, reducing training costs, and exploring hybrid methods to further advance image style transfer technology. These developments not only strengthen the theoretical research of image style transfer and GANs, but also have broad application potential in fields such as art, design and medical imaging.

Data and model synergy-driven rolling bearings remaining useful life prediction approach based on deep neural network and Wiener process

Abstract Various Remaining Useful Life (RUL) prediction methods, encompassing model-based, data-driven, and hybrid methods, have been developed and successfully applied to prognostics and health management for diverse rolling bearing. Hybrid methods that integrate the advantages of model-based and data-driven approaches have garnered significant attention. However, the effective integration of the two methods to address the randomness in rolling bearing full lifecycle processes remains a significant challenge. To overcome the challenge, this paper proposes a data and model synergy-driven RUL prediction framework that includes two data and model synergy approaches. Firstly, a convolutional stacked bidirectional long and short-term memory network with temporal attention mechanism is established to construct health index. The RUL prediction is achieved based on HI and polynomial model. Secondly, a three-phase prediction model based on the Wiener process is established by considering the evolution law of different degradation phases. Then, two synergy methods are designed. Strategy 1: HI is adopted as the observation value for online updating of physics degradation model parameters under Bayesian framework, and the RUL prediction results are obtained from the physics degradation model. Strategy 2: The RUL prediction results from the data-driven and physics-based model are weighted linearly combined to improve the overall prediction accuracy. The effectiveness of the proposed model is verified using two bearing full lifecycle datasets. The results indicate that the proposed approach can accommodate both short-term and long-term RUL predictions, outperforming state-of-the-art single models.

Piecewise second kind Chebyshev functions for a class of piecewise fractional nonlinear reaction–diffusion equations with variable coefficients

In this paper, a new type of piecewise fractional derivative (PFD) is introduced. The ordinary and distributed-order fractional derivatives in the Caputo sense are used to define this type of PFD. A new version of nonlinear reaction–diffusion equations with variable coefficients is defined using this type of PFD. The orthonormal piecewise second kind Chebyshev functions (CFs), as a new family of basic functions, are generated. An explicit formula is extracted for PFD of these piecewise functions. A hybrid method based on the orthonormal piecewise second kind CFs and orthonormal second kind Chebyshev polynomials is proposed to solve the aforementioned problem. The established approach transforms solving the expressed problem into solving an algebraic system of equations. To illustrate the accuracy of the developed method, some numerical examples are considered.

Spatial-Temporal Distribution of 12-Year Periodontal Disease Prevalence in a Large Population Using Geographical Information Systems: A Longitudinal Study.

Periodontal diseases, commonly linked to dental biofilm and affecting adults, were studied using Geographic Information Systems (GIS) and Kernel Analyses with epidemiological data. This paper presents a hybrid method for use in epidemiological studies by evaluating the spatiotemporal distribution of disease prevalence. This study analy ed 47,757 patients from the Department of Periodontology out of 662,351 visitors to University Faculty of Dentistry (2012 to July 2023). The central districts of Kayseri in Turkey were selected as the study areas. Periodontitis prevalence was assessed through radiographic evidence and clinical examination. Point-based location data, including gender, age, and disease type, matched household data, creating building-based spatial data. Kernel Density (KD) and Average Nearest Neighbor (ANN) analyses examined patient concentration and disease types in specific regions. Accordingly, standard deviation ellipses were prepared by year to assess the spatial changes in the regions where patients resided. The study found higher periodontitis prevalence in males, increasing with age, while gingivitis decreased. After 2017, periodontitis prevalence notably declined. Location-based data exhibited clustering in patient distribution. KD maps showed similar patient distributions over the years, with more applications from areas closer to the Faculty of Dentistry. The spatial distribution of the patients applying has remained consistent over the last 5 years. Through GIS, KD maps reveal the spatial-temporal distribution of periodontitis patients. This aids in identifying high-prevalence regions and guiding strategic healthcare facility placement. Implementing preventive programs in high-demand areas, particularly in family health centers (local health facilities), can reduce community-wide periodontal disease prevalence.

A hybrid method for delineating homogeneous forest segments from LiDAR data in Catalonia (Spain)

ABSTRACT Laser scanning data are increasingly used to segment forests into homogeneous units, called segments or stand compartments. Region growing and region merging have been traditionally employed for this purpose. Recently, alternative methods such as cellular automata (CA), self-organizing maps (SOM), and combinatorial optimization have emerged, promising more homogeneous stand delineations. However, these newer methods often require fine-tuning due to rugged stand boundaries. To address this, we propose and assess a novel hybrid approach that combines two segmentation algorithms, resulting in smoother boundaries and homogeneous stands. Our hybrid method outperforms traditional fine-tuning techniques, particularly using CA or SOM for initial segmentation and then refining it with another cellular automaton (CA’), adjusted to produce smooth boundaries. The new two-step hybrid method resulted in better segmentation results than the one-step algorithm combined with previously suggested fine-tuning methods. SOM-CA’ showed the highest degree of explained variance (R2) of the LiDAR metrics used in the segmentation. CA-CA’ reached almost the same R2 values with a larger average segment area. When the R2 of the LiDAR metrics was used as the criterion, the segments produced by the hybrid method outperformed the stand delineations of the current Spanish forest map with a clear margin.