Search Results (811)

In the real world, most data are unlabeled, which drives the development of semi-supervised learning (SSL). Among SSL methods, least squares regression (LSR) has attracted attention for its simplicity and efficiency. However, existing semi-supervised LSR approaches suffer from challenges such as the insufficient use of unlabeled data, low pseudo-label accuracy, and inefficient label propagation. To address these issues, this paper proposes dual label propagation-driven least squares regression with feature selection, named DLPLSR, which is a pseudo-label-free SSL framework. DLPLSR employs a fuzzy-graph-based clustering strategy to capture global relationships among all samples, and manifold regularization preserves local geometric consistency, so that it implements the dual label propagation mechanism for comprehensive utilization of unlabeled data. Meanwhile, a dual-feature selection mechanism is established by integrating orthogonal projection for maximizing feature information with an ℓ_2,1-norm regularization for eliminating redundancy, thereby jointly enhancing the discriminative power. Benefiting from these two designs, DLPLSR boosts learning performance without pseudo-labeling. Finally, the objective function admits an efficient closed-form solution solvable via an alternating optimization strategy. Extensive experiments on multiple benchmark datasets show the superiority of DLPLSR compared to state-of-the-art LSR-based SSL methods. Full article

Landslide susceptibility assessment (LSA) plays a crucial role in disaster prevention and mitigation. Traditional random selection of non-landslide samples (labeled as 0) suffers from poor representativeness and high randomness, which may include potential landslide areas and affect the accuracy of LSA. To address this issue, this study proposes a novel Landslide Susceptibility Index–based Semi-supervised Fuzzy C-Means (LSI-SFCM) sampling strategy combining membership degrees. It utilizes landslide and unlabeled samples to map landslide membership degree via Semi-supervised Fuzzy C-Means (SFCM). Non-landslide samples are selected from low-membership regions and assigned membership values as labels. This study developed three models for LSA—Convolutional Neural Network (CNN), U-Net, and Support Vector Machine (SVM), and compared three negative sample sampling strategies: Random Sampling (RS), SFCM (samples labeled 0), and LSI-SFCM. The results demonstrate that the LSI-SFCM effectively enhances the representativeness and diversity of negative samples, improving the predictive performance and classification reliability. Deep learning models using LSI-SFCM performed with superior predictive capability. The CNN model achieved an area under the receiver operating characteristic curve (AUC) of 95.52% and a prediction rate curve value of 0.859. Furthermore, compared with the traditional unsupervised fuzzy C-means (FCM) clustering, SFCM produced a more reasonable distribution of landslide membership degrees, better reflecting the distinction between landslides and non-landslides. This approach enhances the reliability of LSA and provides a scientific basis for disaster prevention and mitigation authorities. Full article

This work presents the design of a control algorithm based on an augmented incremental state-space model, emphasizing its compatibility with Takagi–Sugeno (T–S) fuzzy models for nonlinear systems. The methodology integrates key components such as incremental modeling, fuzzy system identification, discrete Linear Quadratic Regulator (LQR) design, and state observer implementation. To optimize controller performance, the Extremum Seeking Control (ESC) technique is employed for the automatic tuning of LQR gains, minimizing a predefined cost function. The control strategy is formulated within a generalized framework that evolves from conventional discrete fuzzy models to a higher-order incremental-N state-space representation. The simulation results on a nonlinear multivariable thermal mixing tank system validate the effectiveness of the proposed approach under reference tracking and various disturbance scenarios, including ramp, parabolic, and higher-order polynomial signals. The main contribution of this work is that the proposed scheme achieves zero steady-state error for reference inputs and disturbances up to order N−1 by employing the incremental-N formulation. Furthermore, the system exhibits robustness against input and load disturbances, as well as measurement noise. Remarkably, the ESC algorithm maintains its effectiveness even when noise is present in the system output. Additionally, the proposed incremental-N model is applicable to fast dynamic systems, provided that the system dynamics are accurately identified and the model is discretized using a suitable sampling rate. This makes the approach particularly relevant for control applications in electrical systems, where handling high-order reference signals and disturbances is critical. The incremental formulation, thus, offers a practical and effective framework for achieving high-performance control in both slow and fast nonlinear multivariable processes. Full article

Current sampling methods do not provide effective quantitative assessment mechanisms for evaluating the intrinsic credibility of negative samples. This impedes the systematic quantification of the effect of misselection of geologically predisposed areas (i.e., potential landslide zones) as negative samples on the accuracy of landslide susceptibility evaluation models. To overcome this challenge, this study proposes a fuzzy membership-based sampling method for assessing negative sample credibility in the Liangshan Yi Autonomous Prefecture, where credibility is defined as the confidence level of stable nonlandslide samples. Subsequently, negative samples were sampled across stratified credibility thresholds to construct a frequency ratio–random forest coupled model. The influence of negative sample credibility on model performance was then systematically evaluated using various metrics, including the F1-score (metrics for evaluating classification performance), area under the receiver operating characteristic curve (AUC), and actual landslide distribution ratio (landslide proportion) in high-susceptibility zones. The results are as follows: (1) Increasing the credibility threshold progressively improves model precision while inducing systematic overestimation bias in regional susceptibility assessment; (2) Integrated analysis of model performance and landslide distribution characteristics (where recall, F1-score, and AUC values initially increase then decrease) confirms the optimal effectiveness when selecting negative samples within a credibility threshold range of 0.7–1.0. This study innovatively achieves quantitative optimization of negative samples and provides a universal solution for improving the performance of diverse models reliant on negative sampling strategies. Full article

Amid the rapid growth of social media and live streaming platforms, streamers, who serve as a crucial link between products and users, have garnered significant attention from both academia and industry. This study explores the impact of the streamer’s social capital (S) on user stickiness (R), as well as the mediating roles of perceived value and flow experience (O) in light of the Stimuli-Organism-Response (SOR) framework and social capital theory. A total of 322 valid samples were analyzed through Structural Equation Modeling (SEM) and Fuzzy-set Qualitative Comparative Analysis (fsQCA). The results from the SEM indicate that the structural capital, cognitive capital, and relational capital of streamers in e-commerce live streaming significantly influence users’ perceived value, while structural capital and relational capital substantially impact users’ flow experience. Furthermore, both perceived value and flow experience are found to have a significant effect on user stickiness, with chained mediating effects observed between perceived value and flow experience. The fsQCA results further identify three configurational paths influencing user stickiness: the perceived value-oriented path, the flow experience-oriented path, and a hybrid path. This study offers valuable insights and practical implications for e-commerce merchants and companies involved in live streaming activities. Full article

Delineating soil management zones in cocoa cultivation areas can help optimize production and minimize ecological and environmental risks. This research assessed the spatial distribution of heavy metal concentration and soil fertility indicators in Cross River State, Nigeria, to delineate soil management zones (MZs). A total of n = 63 georeferenced, composite soil samples were collected at the 0–30 cm depth increment, air-dried, and subjected to physicochemical analysis. The soil data were subjected to principal component analysis (PCA), and the selected principal components (PCs) were used for fuzzy c-means clustering analysis to delineate the MZs. The result indicated that soil pH varied from 4.8 (strongly acidic) to 6.3 (slightly acidic), with high average organic carbon contents. The degree of contamination was low, while the ecological risk indicator (RI) of the environment under cocoa cultivation ranged from low risk (RI = 18.24) to moderate risk (RI = 287.15), with moderate risk areas mostly found in patches around the central and upper regions. Higher pH was associated with increased levels of exchangeable Ca, Mg, and K, and TN and OC. Strong spatial dependence was observed for silt, pH, OC, Mg, Zn, Cu, Pb, Cd, Cr, and DC. The result showed the first six principal components (PCs) with eigenvalues >1 accounting for 83.33% of the cumulative variance, and three MZs were derived via the selected six PCs using fuzzy c-means clustering analysis. The results of this study further indicated that MZ3 had the highest pH (6.06), TN (0.24%), OC (2.79%), exchangeable Ca (10.62 cmol/kg), Mg (4.01 cmol/kg), and K (0.12 cmol/kg). These were significantly (p < 0.05) higher than those observed in MZ2 and MZ1, and they represent the most fertile parts of the study area. Furthermore, 40.6% of the study area had marginal soil (i.e., soil under MZ2). Full article

Lithology identification during drilling plays a vital role in geological and geotechnical exploration, as it facilitates the early detection of formation-related hazards and supports the development of optimized mining strategies. Traditional lithology identification research involves problems such as fuzzy indicator characteristics and unbalanced sample quantities, which affect the accuracy and interpretability of model identification. In order to solve these problems, the Shanxi Guoqiang Coal Mine was taken as the research object, and a combined machine learning model was used to conduct a study on lithology identification during drilling. First, the least absolute shrinkage and selection operator (LASSO) algorithm was used to screen the independent variables and retain the parameters that contributed the most to lithology identification. Then, the synthetic minority oversampling technique (SMOTE) algorithm was used to expand the data samples, increase the amounts of minority sample data, and keep the ratios of various lithology data at 1:1. Then, the Bayesian optimization (BO) algorithm was used to optimize the penalty factor C and kernel function hyperparameter γ—two important parameters of the support vector machine (SVM) model—and the BO-SVM lithology identification model was established. Finally, the data samples were processed, and the results were compared with those of single models and unbalanced sample processing to evaluate their effect. The results showed the following: during the drilling process, the four indicators of drilling speed, mud pressure, slurry flow rate, and torque are strongly correlated with the lithology and can be used for lithology identification and classification research. After the data set was oversampled using the SMOTE algorithm, each model had better robustness and generalization ability; the classification result evaluation indicators were also greatly improved, especially for the random forest model, which had a poor original evaluation effect. The BO algorithm was used to optimize the parameters of the SVM model and establish a combined model that correctly identified 95 groups of data out of 96 groups of test samples with an identification accuracy rate of 99%, which was better than that of the traditional machine learning model. The evaluation results were compared with measured data, which confirmed the reliability of the combined model classification method and its potential to be extended to lithology identification and classification work. Full article

A fuzzy prediction model has been developed considering the concentration of acetic acid (pH), temperature, and biopolishing time as input variables, while the color change, measured with DEcmc, between samples before and after biopolishing, was used as the output variable. The parameters influencing the color change in knitted cotton fabrics exhibit significant non-linearity. The fuzzy inference system proves to be an effective modeling tool, capable of representing non-linear relationships with a limited amount of experimental data. For the variables, triangular and trapezoidal membership functions were adopted, and a total of 27 rules were established in this research. It was observed that the impact of cellulase concentration on color change is relatively low, but it is strongly influenced by temperature, even at a constant concentration of cellulase. The model developed in this study was validated with an additional experimental data set. The developed system is capable of predicting shade changes with an accuracy of over 90%, which helps to reduce rework and reprocessing in the wet processing sectors. Full article

Talent significantly influences urban technological innovation and sustainable economic development. Enhancing urban talent competitiveness (UTC) necessitates a systemic perspective on upgrading and optimizing the combination of both tangible and intangible resources, such as economic vitality, livability, and social harmony, which is a typical configurational issue. This paper utilizes empirical data from 96 Chinese cities and applies an innovative grey quantitative comparative analysis (GQCA) method to investigate the impact and mechanisms of different urban talent ecology (UTE) on talent competitiveness. The findings reveal that there are no bottleneck factors constraining UTC within the sample, interactions, and couplings among six urban talent elements that generated 30 distinct UTEs. By calculating the possibility of each UTE achieving talent competitiveness, it was found that 16 UTEs, characterized by vibrant business-led development, comprehensive development and integrated leadership, regional development leadership, and economy-led international innovation, lead to high UTC. Conversely, 14 UTEs result in low UTC. These findings were further validated through fuzzy set qualitative comparative analysis (fsQCA) for robustness testing. Finally, the study offers policy recommendations for urban talent strategies from both short-term and long-term perspectives. Full article

The digitalization of rural areas has emerged as a crucial strategy for promoting economic development, yet the phenomenon of “digital suspension” poses a challenge, where the lack of digital integration in certain sectors may hinder economic progress. This study delves into this issue by identifying multiple configurations that drive county-level economic growth. More specifically, this study aims to explore how rural digitalization contributes to county-level economic growth through different combinations of environmental and subject-level factors. To address this issue, this study applies the fuzzy-set qualitative comparative analysis method, guided by systems thinking and ecological systems theory. The analysis is based on 89 case samples selected from China’s digital village pilot counties, using data from the China County-level Digital Rural Index Research Report jointly released by Peking University and Ali Research Institute, published in 2022, and other county-level statistical data. The study explores the complex causal mechanisms and configuration paths through which rural digitalization empowers county-level economic growth. This study found that (1) the conditions necessary to generate high county-level economic growth do not exist in the process of rural digitalization (at least not within the digital village pilot); (2) four configurations facilitate high county-level economic growth: digital governance-led configuration, dual promotion of digital governance and digital infrastructure, dual promotion of digital life and digital infrastructure, and dual promotion of digital life and digital economy; and (3) two configurations yield non-high county-level economic growth and exhibit asymmetrical relationships with those configurations conducive to high growth. These research findings not only broaden the application of systems thinking and ecological systems theory in the realm of rural digitalization but also offer practical insights into strategies for enhancing county-level economic growth. Full article

This paper introduces a robust neural adaptive MIMO control strategy to improve the stability and adaptability of bipedal locomotion amid uncertainties and external disturbances. The control combines nonlinear dynamic inversion, finite-time convergence, and radial basis function (RBF) neural networks for fast, accurate trajectory tracking. The main novelty of the presented control strategy lies in unifying instantaneous feedback, real-time learning, and dynamic adaptation within a multivariable feedback framework, delivering superior robustness, precision, and real-time performance under extreme conditions. The control scheme is implemented on a 5-DOF underactuated $\mathrm{R}\mathrm{A}\mathrm{B}\mathrm{B}\mathrm{I}\mathrm{T}$ robot using a $\mathrm{d}\mathrm{S}\mathrm{P}\mathrm{A}\mathrm{C}\mathrm{E}\mathrm{D}\mathrm{S}1103$ platform with a sampling rate of $∆t=1.5 \mathrm{m}\mathrm{s} (667 \mathrm{H}\mathrm{z})$. The experimental results show excellent performance with the following: The robot achieved stable cyclic gaits while keeping the tracking error within $e=\pm 0.04 \mathrm{r}\mathrm{a}\mathrm{d}$ under nominal conditions. Under severe uncertainties of trunk mass variations ${∆m}_{\mathrm{t}\mathrm{r}\mathrm{u}\mathrm{n}\mathrm{k}}=+100\%$, limb inertia changes ${∆I}_{\mathrm{l}\mathrm{i}\mathrm{m}\mathrm{b}}=\pm 30\%$, and actuator torque saturation at $\tau =\pm 150 \mathrm{N}\mathrm{m}$, the robot maintains stable limit cycles with smooth control. The performance of the proposed controller is compared with classical nonlinear decoupling, non-adaptive finite-time, neural-fuzzy learning, and deep learning controls. The results demonstrate that the proposed method outperforms the four benchmark strategies, achieving the lowest errors and fastest convergence with the following: $\mathrm{I}\mathrm{A}\mathrm{E}=1.36$, $\mathrm{I}\mathrm{T}\mathrm{A}\mathrm{E}=2.43$, $\mathrm{I}\mathrm{S}\mathrm{E}=0.68$, $t_{ss}=1.24 \mathrm{s}$, and $M_p=2.21\%$. These results demonstrate evidence of high stability, rapid convergence, and robustness to disturbances and foot-slip. Full article

In this study, the vegetation of the natural area of the Göksu Delta Special Environmental Protection Agency (SEPA), one of Turkey’s most important wetlands, is researched. The importance of this study in terms of contributing to environmental protection and land use planning studies reveals that this natural area, where rare ecosystems are found, has started to degrade and disappear under human influence. This study was conducted because the area is not only a designated RAMSAR wetland (a wetland site designated of international importance especially for the Waterfowl Habitat under the Ramsar Convention) but also includes nearby residential developments. With this study, the vegetation of the area was studied to determine the syntaxonomic units across different habitats. The natural area of Göksu Delta is divided into three main habitat groups: aquatic, sand dune, and halophytic. In the research, the Braun-Blanquet method was used. During the research in the Göksu Delta, 279 sample areas were surveyed. The data were analysed according to the fuzzy means cluster method. During the investigation, 29 associations were identified, and 16 of them are considered a new finding for science. These 29 associations can be classified as follows: aquatic vegetation is represented with four associations (three of them belong to Phragmito-Magnocaricetea and one of them belongs to Potametea classes), sand dune vegetation is represented with 12 associations (belonging to Ammophiletea Br.-Bl. & Tüxen ex Westhoff, Dijk, & Passchier 1946 class), and halophytic vegetation is represented with 13 associations (six of them belong to Salicornietea fruticosae Br.-Bl. & Tüxen ex A. & O. Bolòs 1950, six of them belong to Juncetea maritimi Br.-Bl. in Br.-Bl., Roussine & Nègre 1952, and one of them belong to Molinio-Juncetea Br.-Bl. (1931) 1947 classes). Three (Onopordum boissieri, Ambrosia maritima, and Chlamydophora tridentata) of the endemics and rare plants that were explored during the study were recorded as new alliance characteristics. Full article

Precise temperature control in high-temperature furnaces is challenged by nonlinearities, parameter drift, and high thermal inertia. This study proposes an adaptive control strategy combining a classical PID loop with real-time gain updates from a feed-forward artificial neural network (ANN). Implemented on an 18 kW retrofitted Blue-M furnace, the system was characterized by second-order transfer functions for heating and forced convection cooling. A dataset of 9702 samples was built from eight fixed PID configurations tested under a multi-ramp thermal profile. The selected 3-64-64-32-2 ANN, executed in Python and interfaced with LabVIEW, computes optimal gains in 0.054 ms while preserving real-time monitoring capabilities. Experimental results show that the ANN-assisted PID reduces the mean absolute error to 5.08 °C, limits overshoot to 41% (from 53%), and shortens settling time by 20% compared to the best fixed-gain loop. It also outperforms a fuzzy controller and remains stable under ±5% signal noise. Notably, gain reversals during cooling prevent temperature spikes, improving transient response. Relying on commodity hardware and open-source tools, this approach offers a cost-effective solution for legacy furnace upgrades and provides a replicable model for adaptive control in high-temperature, safety-critical environments like metal processing, battery cycling, and nuclear systems. Full article

Path-planning algorithms for planetary rovers are critical for autonomous robotic exploration, enabling the efficient and safe traversal of complex and dynamic extraterrestrial terrains. Unlike terrestrial mobile robots, planetary rovers must navigate highly unpredictable environments influenced by diverse factors such as terrain variability, obstacles, illumination conditions, and temperature fluctuations, necessitating advanced path-planning strategies to ensure mission success. This review comprehensively synthesizes recent advancements in planetary rover path-planning algorithms. First, we categorize these algorithms from a constraint-oriented perspective, distinguishing between internal rover state constraints and external environmental constraints. Next, we examine rule-based path-planning approaches, including graph search-based methods, potential field methods, sampling-based techniques, and dynamic window approaches, analyzing representative algorithms in each category. Subsequently, we explore bio-inspired path-planning methods, such as evolutionary algorithms, fuzzy computing, and machine learning-based approaches, with a particular emphasis on the latest developments and prospects of machine learning techniques in planetary rover navigation. Finally, we synthesize key insights from existing algorithms and discuss future research directions, highlighting their potential applications in planetary exploration missions. Full article

This study proposes a robust methodology for vibration suppression and trajectory tracking in rotary flexible-link systems by leveraging guided reinforcement learning (GRL). The approach integrates the twin delayed deep deterministic policy gradient (TD3) algorithm with a linear quadratic regulator (LQR) acting as a guiding controller during training. Flexible-link mechanisms common in advanced robotics and aerospace systems exhibit oscillatory behavior that complicates precise control. To address this, the system is first identified using experimental input-output data from a Quanser^® virtual plant, generating an accurate state-space representation suitable for simulation-based policy learning. The hybrid control strategy enhances sample efficiency and accelerates convergence by incorporating LQR-generated trajectories during TD3 training. Internally, the TD3 agent benefits from architectural features such as twin critics, delayed policy updates, and target action smoothing, which collectively improve learning stability and reduce overestimation bias. Comparative results show that the guided TD3 controller achieves superior performance in terms of vibration damping, transient response, and robustness, when compared to conventional LQR, fuzzy logic, neural networks, and GA-LQR approaches. Although the controller was validated using a high-fidelity digital twin, it has not yet been deployed on the physical plant. Future work will focus on real-time implementation and structural robustness testing under parameter uncertainty. Overall, this research demonstrates that guided reinforcement learning can yield stable and interpretable policies that comply with classical control criteria, offering a scalable and generalizable framework for intelligent control of flexible mechanical systems. Full article