Search Results (11,921)

The exponential growth of genomic and proteomic data has made computational protein–protein interaction (PPI) prediction indispensable, driving the need for a comprehensive and method-aware evaluation of supervised learning approaches. PPIs are fundamental to understanding cellular processes and disease mechanisms, yet experimental identification remains slow, costly, and difficult to scale. This survey systematically investigates ten supervised learning models—Extreme Learning Machine (ELM), Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Deep Neural Networks (DNNs), Naïve Bayes, Probabilistic Decision Tree, Support Vector Machine (SVM), Least Squares SVM (LS-SVM), K-Nearest Neighbor (KNN), and Weighted K-Nearest Neighbor (WKNN)—through a tri-layered framework that integrates Comparative Quantitative Analysis, Comparative Observational Analysis, and Experimental Evaluations. Beyond conventional accuracy summaries, this work provides critical commentary tied to real-world use, analyzing where techniques succeed or fail in practice—for instance, when instance-based methods bottleneck during inference, when kernel choices influence SVM variance, or when deep architectures trade accuracy for computational cost. The survey also offers concrete deployment guidance, such as calibration insights for WKNN versus KNN under varying feature noise or dataset curation quality, delivering operational perspectives that typical surveys omit. Comparative Quantitative Analysis consolidates metrics such as accuracy, F1-score, and computational time from the existing literature, while Comparative Observational Analysis evaluates interpretability, scalability, dataset suitability, and efficiency. Complementing these, Experimental Evaluations conducted by the authors empirically validate model performance on benchmark datasets. Together, these layers provide a unified and evidence-backed perspective on algorithmic strengths, weaknesses, and practical applicability. Findings show that GNNs and DNNs achieve the highest predictive accuracy due to their ability to capture structural and topological relationships, whereas ELM and Naïve Bayes offer superior efficiency. SVM and LS-SVM maintain robust stability under noisy conditions, and CNNs are well-suited for sequence-based prediction tasks. By combining empirical validation, critical insights, and deployment-focused recommendations, this survey delivers decision-grade guidance that bridges theoretical understanding with real-world implementation, thus clarifying the trade-offs among accuracy, efficiency, and scalability in PPI detection research. Full article

Photovoltaic (PV) power generation is inherently intermittent due to unpredictable irradiance variations, posing significant challenges for grid integration. While conventional power smoothing strategies mitigate short-term fluctuations, they do not explicitly enforce the tracking of a scheduled power trajectory. This paper proposes a dispatchable PV framework that integrates a hybrid convolutional neural network-long short-term memory (CNN-LSTM) model for precise day-ahead power forecasting with a real-time supercapacitor (SC) compensation strategy. The CNN-LSTM network captures complex spatiotemporal meteorological dependencies to generate a robust day-ahead reference trajectory. Concurrently, a supercapacitor energy storage system (SC-ESS) integrated at the DC-link level via a bidirectional buck–boost converter actively balances the instantaneous mismatch between this forecast trajectory and the actual PV generation. Unlike filter-based hybrid methods, the SC-ESS is employed as a direct forecast error actuator in a closed-loop control scheme. This strategy strictly enforces real-time forecast tracking while preserving maximum power point tracking (MPPT) and DC-link voltage stability. Simulations and laboratory experiments under rapidly varying irradiance confirm that the proposed method significantly reduces power deviations from the forecast reference and improves short-term power predictability without imposing excessive stress on the SC. This forecast-aware strategy effectively enhances the dispatchability of PV systems, providing a practical solution for grid-supportive operation. Full article

Recent studies have shown that common household activities produce characteristic patterns in indoor air pollutants, enabling activity inference using environmental measurements alone. However, pollutant-based approaches are usually formulated as flat multi-class classification problems, even though indoor environments are dominated by long baseline periods with no emission-generating activity, leading to false alarms and unstable predictions. This work proposes a gated hierarchical inference framework for recognizing activities from indoor air quality data. A first-stage gate detects whether a time window contains activity-induced pollutant dynamics, while a second-stage classifier conditionally identifies the specific activity only when activity relevance is detected. Multivariate time-series measurements of particulate matter, volatile organic compounds, nitrogen oxides, carbon dioxide, temperature and relative humidity were collected using a portable monitoring system during controlled household cooking and cleaning experiments. Temporal windows were processed using recurrent neural network models in both stages. By separating activity detection from activity identification, the proposed method aligns inference with the physical generation of indoor pollutant signals and improves robustness in baseline-dominated monitoring scenarios while maintaining reliable discrimination among activities. The framework supports unobtrusive activity recognition and enables applications in exposure-aware monitoring and intelligent indoor environmental management. Full article

With the increasing penetration of wind power, the participation of wind farms in primary frequency regulation has become important for maintaining power system frequency stability. However, virtual inertia and droop control, while providing frequency support, can increase structural fatigue loads in wind turbines and shorten their service life. To address this issue, this study proposes a coordinated optimization method for wind farm primary frequency control parameters based on fatigue load prediction. First, damage equivalent load (DEL) data under different power disturbances, wind speeds, and control parameter settings are generated through OpenFAST–Simulink co-simulation. Then, a multilayer perceptron (MLP) neural network is developed to establish the mapping from power disturbance, wind speed, and control parameters to turbine DEL. Based on the trained model, an optimization framework is constructed to minimize the total DEL of the wind farm, improve the uniformity of DEL distribution among turbines, and satisfy grid frequency support constraints. Simulation results show that the proposed method effectively reduces the overall fatigue load of the wind farm while ensuring system frequency security and improving load distribution uniformity among turbines. Full article

Neural ordinary differential equations (Neural ODEs) describe the feature evolution of deep networks by continuous-time dynamical systems and enable end-to-end learning through differentiable numerical solvers. Nevertheless, in closed-loop rolling prediction for small-sample time series, conventional Neural ODEs remain vulnerable to error accumulation and numerical instability. To improve the controllability of long-term evolution, this study proposes a neural ordinary differential equation framework based on fractional-order operators. Rather than directly introducing full-history convolution kernels into the governing dynamics, the proposed approach constructs a fractional effective step size from the closed-form expression of the Riemann–Liouville fractional integral of a constant function and consistently embeds it into all sub-steps of a fourth-order Runge–Kutta solver. In this way, the scale of continuous-depth propagation is regulated by a single tunable parameter. Combined with a residual output structure, the method preserves the interpretability of continuous dynamics while effectively suppressing trajectory drift in closed-loop prediction and improving training stability. To investigate the impact of the fractional-order parameter on fitting and extrapolation, particle swarm optimization is employed to search automatically for the optimal order. Experimental evaluations on the linear spiral system and Lorenz continuous dynamical systems and on a small-sample provincial annual electricity-consumption dataset show that the proposed model achieves lower prediction errors across multiple tasks and exhibits superior trajectory preservation and robustness under long-horizon forecasting. Full article

Ecological vulnerability assessment serves as a prerequisite for ecological governance, yet evaluating large-scale ecological vulnerability remains challenging. To address this challenge, this study integrates geological elements into ecological vulnerability assessment, taking Ruyuan Area in the Northern Guangdong Mountains, China, as a case study. The area faces ecological hazards such as land desertification and soil erosion, indicating severe governance challenges. This study selected 14 ecological vulnerability factors and constructed assessment models based on Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs). A total of 800 ecological vulnerability sampling points were obtained by combining field survey data with remote sensing imagery. The models were trained using binary vulnerability labels. The resulting continuous probability outputs were then classified into five vulnerability levels using the natural breaks method to generate the final ecological vulnerability map. It should be noted that the multi-level vulnerability map represents graded probability-based differentiation rather than supervised multi-class prediction. Model performance was validated using three metrics: Area Under Receiver Operating Characteristic Curve (AUC–ROC), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE). The CNN (AUC = 0.916) model outperformed the DNN model (AUC = 0.895). According to the CNN-based classification results, non-vulnerable, slightly vulnerable, mildly vulnerable, moderately vulnerable, and highly vulnerable areas accounted for 36.19%, 22.85%, 14.24%, 12.31%, and 14.41% of the total area, respectively. High ecological vulnerability zones were concentrated in Daqiao, Luoyang, Dabu, and parts of Rucheng towns, with soil parent material and vegetation coverage identified as the main contributing factors, among which parent material was the most important. This finding underscores the notable impact of geological factors on local ecological vulnerability. Based on these results, nine ecological–geological subareas were delineated, and targeted ecological protection and restoration recommendations were proposed. This study, employing machine learning techniques, constructed an ecological vulnerability assessment model incorporating geological elements, thereby providing scientific support for targeted ecological governance in the study area. Full article

The durability and serviceability of steel-fiber-reinforced concrete (SFRC) tunnel linings in cold regions are significantly challenged by repeated freeze–thaw actions, making the accurate prediction of frost resistance a critical engineering problem. Although extensive research has been conducted on the freeze–thaw characteristics of concrete, the existing empirical and mechanism-based models remain limited in capturing the complex nonlinear interactions among mixture proportions, steel fiber characteristics, and environmental conditions. Therefore, a data-driven prediction framework based on machine learning was developed in this study. A database containing 277 groups of standardized SFRC freeze–thaw test results was established, incorporating key variables including mixture design parameters, fiber properties, and freeze–thaw cycle conditions. Four machine-learning models, namely, support vector regression, back-propagation neural network, gradient boosting, and extreme gradient boosting (XGB), were constructed and systematically compared. Model accuracy was assessed using MAE, MAPE, MSE, RMSE, and R². The results demonstrate that all models can reflect the nonlinear relationship between the input variables and mass loss rate, while the XGB model exhibits superior predictive performance with a testing R² of 0.91, representing an improvement of approximately 3–28% compared with other models. Meanwhile, the prediction errors are reduced significantly, with RMSE and MAE decreased by about 19–58% and 22–65%, respectively. The proposed approach provides an improved and reliable tool for predicting frost resistance and supports the durability design and optimization of SFRC tunnel linings in severe cold-region environments. Full article

Reversible data hiding (RDH) enables the reversible embedding of additional data into cover media, allowing the cover media to be perfectly recovered after extracting the embedded data. RDH relies on accurate prediction of pixels to generate sharply distributed prediction error histograms, thereby maximizing embedding capacity and minimizing visual distortion. While convolutional neural network (CNN)-based predictors excel in smooth regions of cover images by leveraging local correlation, they often fail to produce accurate predictions in the textured regions. To address the limitation of CNN predictors, we propose a novel attention fusion-based CNN predictor (AFCNNP) that adaptively combines the CNN predictor with a non-local means (NLM) predictor. The proposed fusion framework learns spatial weight maps to favor CNN predictions in smooth regions and NLM predictions in textured regions. The experimental results show that the proposed framework outperforms other state-of-the-art CNN predictors by significantly lowering the mean absolute error, mean squared error, and variance of prediction errors, leading to more accurate pixel predictions. With the proposed fusion framework, the embedding and visual performance of prediction error expansion (PEE)-based RDH is improved compared to typical CNN-based RDH methods. Full article

Real-time traffic signal control represents a key challenge in modern intelligent transportation systems, particularly under highly variable traffic flows and the presence of priority vehicles. This study proposes a hybrid framework for adaptive signal plan control at a signalized intersection. The framework integrates deep learning-based traffic prediction, surrogate-based performance evaluation, and reinforcement learning-based adaptive control. Short-term traffic flow is predicted using recurrent neural networks, providing anticipatory information for traffic control decisions. Based on predicted flows and generated candidate signal plans, a machine learning surrogate model enables fast estimation of key performance indicators, including average vehicle delay and queue length. Adaptive control is implemented using the Proximal Policy Optimization algorithm within the SUMO environment via TraCI, which enables real-time fine-tuning of signal phases. A dedicated priority and stability module ensures effective emergency vehicle preemption and adaptive public transport priority while preserving intersection stability. Simulation results show that the proposed framework reduces average vehicle delay by up to 35% compared with FT and by up to 15% compared with standalone RL, while also improving traffic flow efficiency and priority vehicle performance. Full article

Accurate prediction of electricity demand during hot seasons is essential for maintaining power system reliability, particularly in humid subtropical regions such as Guangdong, China, where high temperatures strongly influence consumption. However, many models rely primarily on air temperature and may not fully capture combined atmospheric effects. This study evaluates the potential of biometeorological thermal indices for improving summer electricity load forecasting. Daily maximum load and meteorological data during May–September 2019–2021 were analyzed using Back-Propagation Neural Network (BP), Random Forest (RF), and a Stacking ensemble model. Three indices—Effective Temperature (ET), Physiological Equivalent Temperature (PET), and the Universal Thermal Climate Index (UTCI)—were introduced as predictors. The ensemble model achieved the best performance, with Ensemble–UTCI yielding the highest accuracy (R² = 0.559, RMSE = 60.96 × 10⁴ kW, MAE = 45.10 × 10⁴ kW). Compared with temperature-based models, biometeorological indices consistently improved predictions, with UTCI performing best (average RMSE = 62.81 × 10⁴ kW). Bayesian analysis shows strong evidence of improvement in RF and ensemble models, but not in BP or linear models, indicating model dependence. During the July 2021 heat event, RF showed greater robustness, with PET–RF achieving the lowest error (MAPE = 3.03%). These results demonstrate the value of biometeorological indices for load forecasting in humid subtropical regions. Full article

The objective of this work was to establish mathematical models and an artificial neural network to predict changes in channel catfish quality during storage. Secondary models of microorganisms, using the total viable count (TVC) as an indicator, were established based on the modified Gompertz equation combined with the Belehradek equation. The secondary kinetic models for total volatile basic nitrogen (TVB-N) were developed by combining the primary model with the Arrhenius equation, from which the early warning thresholds for quality change were determined based on the slopes of the kinetic curves. For most samples, the relative error between the measured and predicted values of the secondary kinetic model remained within ±20% across the tested storage temperatures, while during the practically relevant 2–6 days period, the error was tightly controlled within ±15% for the majority of samples. Moreover, the prediction models were established based on Back Propagation Neural Networks and Radial Basis Function Neural Networks, with determination coefficients (R2) exceeding 0.9. In conclusion, the developed predictive models provide a scientific basis and technical support for quality monitoring and cold-chain distribution of channel catfish under varying temperatures. Full article

The lack of graph information caused by ignoring the association between learners often affects the accuracy of graph-based learning. This paper proposes an approach called attention-based multi-topological graph convolution (A-MTGCN) to address this. It uses a graph neural network to predict academic tasks. The method involves an attention mechanism that assigns weights to different academic characteristics to reflect their effects on prediction. Additionally, the topology between learners is constructed from multiple perspectives to capture potential interactions and collaboration, forming a weighted learner association diagram. This reduces redundancy and information dispersion in the graph, while retaining the correlation features. The approach divides learners into four types. Experiments show the enhanced GCN performs well in learner node classification, with an accuracy of 92.53%, precision of 89.15%, recall of 92.27%, and F1-score of 87.83%. The evolution process of learners’ learning state is reflected by constructing learners’ state transition matrix. Full article

In this paper, an intelligent localization framework based on deep learning is proposed to address the limitations of insufficient accuracy and robustness in defect identification and localization during the ultrasonic guided-wave non-destructive testing (NDT) of receiver tubes in tower-type molten salt Concentrated Solar Power (CSP) stations. In the proposed method, a 1D convolutional neural network (1D-CNN) initially processes raw time-series-guided wave signals, achieving coarse identification and preliminary localization of defective segments. Then, Mel spectrograms are employed to exploit multi-dimensional features in the time–frequency domain and transform 1D signals into 2D representations, thereby enriching feature diversity. A regression-based 2D-CNN was designed to predict the start and end points of defect segments, enabling precise interval localization. Furthermore, the Tree Seed Algorithm (TSA) was integrated to jointly optimize key hyperparameters, enhancing training efficiency and prediction accuracy. Experimental validation on a dataset of ultrasonic guided-wave signals from molten salt receiver tubes demonstrates that the TSA-optimized Mel+2D-CNN model achieves superior performance, with a Mean Absolute Error (MAE) of 75.11 sampling points and a Coefficient of Determination (R²) of 0.90. At an Intersection over Union (IoU) threshold of 0.3, the model achieves a hit rate of 89.21%, exhibiting significantly higher localization accuracy and stability compared to the 1D-CNN baseline model. These findings indicate that the proposed method effectively enhances the accuracy and robustness of guided wave-based defect localization in slender structures. While promising, the model’s generalization capability remains dependent on the data distribution and operating conditions; future work will focus on validating its engineering applicability across diverse, multi-scenario industrial environments. Full article

In order to achieve more accurate and efficient oil-paper insulation aging assessment, and to improve the operation and maintenance level of oil-paper insulated power equipment, this paper proposes an aging evaluation method of oil-paper insulation based on Raman spectrum and frequency-domain spectroscopy. First, oil-paper insulation samples with different aging degrees were prepared by an accelerated thermal aging test in this experiment. Then, Raman spectroscopy and frequency-domain dielectric spectroscopy were used to examine the samples and analyze the aging characteristics of the samples by LightGBM R2019b. Finally, the gray neural network is used to establish a prediction model for the degree of polymerization of insulating paper based on frequency-domain dielectric features and Raman spectral features. The results of this study showed that there is a certain correlation between the Raman characteristics of insulating oil and the FDS characteristics of insulating paper. The average absolute error of the prediction of the R-F-PGNN model developed in this paper is 20.4. The research in this paper provides a strong support for the development of Raman spectroscopy diagnosis technology for oil-paper insulation aging in the power industry, which has certain academic value and engineering application significance. Full article

Accurate prediction of binary stock price movements remains a challenging task due to the coexistence of short-term noise and medium-term trend dynamics in financial time series. Existing recurrent models typically encode raw price sequences within a single representation stream and aggregate temporal information using softmax-based attention, which often entangles noisy fluctuations with underlying trends and limits nonlinear expressiveness in the final classification stage. In this paper, we propose PULSE-KAN (Price-aware Unified Linear-attention and Smoothed-trend Encoder with Kolmogorov–Arnold Network Head), a modular neural architecture designed to enhance binary stock movement prediction. The proposed framework introduces three plug-and-play components designed for LSTM-based pipelines as demonstrated here within the Adv-ALSTM framework. First, the P-EMA Trend Bridge constructs an explicit smoothed trend representation via a parameterized exponential moving average and fuses it with the raw price stream to improve trend awareness. Second, the Pola Pulse Router performs efficient temporal aggregation using linear-complexity polarized attention combined with local convolutional priors, enabling better capture of multi-scale temporal dependencies. Third, the KAN Signal Refiner replaces the conventional linear prediction head with learnable Chebyshev-polynomial activations, providing enhanced nonlinear modeling capacity for decision boundaries. Extensive experiments on two public benchmark datasets demonstrate that PULSE-KAN consistently outperforms strong recurrent and attention-based baselines in terms of both classification accuracy and the Matthews Correlation Coefficient. Further ablation studies verify that each proposed component contributes independently and significantly to the overall performance improvement. Full article