Search Results (1,756)

The creation and authentication of real users on social media requires the implementation of artificial intelligence-based technologies that can mitigate malicious behavior from automated accounts. This study presents a machine learning-based approach for detecting social bots on Twitter/X, based on the analysis of user profile features and behavioral attributes. Four classification models were evaluated: a neural network (NN), support vector machines (SVM), a random forest classifier (RF), and Extreme Gradient Boosting (XGBoost), using five-fold stratified cross-validation. To improve the performance and robustness of the classification, additional features and data balancing techniques were incorporated. The experimental results show that the neural network achieved the best overall performance, with an average accuracy of 95.6 ± 0.6%, followed by the random forest (95.0 ± 0.6%), the linear SVM (94.1 ± 1.5%) and XGBoost (94.0 ± 1.1%). These results demonstrate that the proposed methodology improves the automated detection of social bots while maintaining the interpretability of the models, which contributes to the development of more reliable and explainable security mechanisms for social media platforms. Full article

Cotton boll opening is an important late-season indicator for maturity assessment, defoliation timing, and harvest planning, but field-level monitoring remains challenging because visible lint progression varies spatially and temporally. This study evaluates whether UAV-derived cotton visible lint percentage, aggregated at the Sentinel-2 10 m grid scale, can be estimated using Sentinel-2 spectral bands, vegetation indices (VIs), and accumulated growing degree days (AGDD) as phenological predictors. UAV multispectral imagery was used to derive visible lint percentage through red-band thresholding and segmentation within canopy masks. The UAV-derived visible lint information was summarized within fixed Sentinel-2 10 m grid cells to generate satellite-compatible response labels. Four supervised regression models, eXtreme Gradient Boosting (XGBoost), Random Forest (RF), k-Nearest Neighbors (kNN), and Neural Network/Multilayer Perceptron (NNET/MLP), were evaluated using raw and transformed target formulations. Raw visible lint percentage produced relatively high explanatory power for tree-based models, with R² values of 0.73 for both XGBoost and RF. However, the target distribution was strongly right-skewed and dominated by low visible lint values, with a mean PCTOPEN of 4.05%Open, motivating the evaluation of target transformations to reduce target skewness while assessing their impact on predictive performance. On the original PCTOPEN scale, the raw target produced RMSE = 4.38%Open points, MAE = 2.31%Open points, and MedianAE = 0.68%Open points. The square-root transformation provided the strongest overall predictive performance, maintaining R² = 0.73 and RMSE = 4.38%Open points while reducing MAE to 2.14%Open points and MedianAE to 0.41%Open points. Stronger transformations further reduced the typical prediction errors, with MedianAE = 0.35, 0.33, and 0.31%Open points for the cube-root, fourth-root, and fifth-root transformations, respectively. However, these improvements were accompanied by progressively lower R² values (0.72, 0.71, and 0.69) and higher RMSE values (4.48, 4.58, and 4.68%Open points), indicating that stronger transformations reduced typical prediction errors at the expense of overall predictive performance. These results indicate that UAV-derived visible lint percentage can be linked with Sentinel-2 observations for satellite-scale regression modeling, but prediction uncertainty remains influenced by target skewness, mixed 10 m pixels, canopy obstruction, and limited UAV acquisition density. Additional UAV–Sentinel-2-aligned acquisitions, supporting multi-field observations, and broader validation across fields, seasons, cultivars, and production environments are needed to improve robustness and support operational cotton boll-opening tracking applications. Full article

Cervical cancer (CC) affects women worldwide, and more than 95% of cases are caused by persistent infection with high-risk human papillomavirus (HR-HPV), such as type 16, which promotes the progression of precancerous lesions to cancer. This study aimed to identify differentially expressed proteins (DEPs) in biopsies from patients with HPV16+ low-grade squamous intraepithelial lesions (LSILs) and from patients with HPV16+ squamous cell carcinoma (SCC) compared with those from HPV-negative normal cervical tissue (NCT HPV−) controls. The samples were analyzed by high-performance liquid chromatography–tandem mass spectrometry (HPLC-MS/MS) using a data-independent acquisition (DIA) approach. Data processing and differential protein expression analysis were performed with the DIA-NN software (Data-Independent Acquisition Neural Networks), followed by bioinformatics analyses, including Venn diagrams, pathway enrichment, functional interactome, The Cancer Genome Atlas (TCGA)-SCC data integration, and Western blot detection. In total, 1607 DEPs associated with cell adhesion and extracellular matrix proteins were identified in LSILs, whereas 1516 DEPs associated with catalytic and transport activities were identified in SCC; the proteins overexpressed in LSILs (332) were enriched in processes such as metabolism, immune response activation, and stress and cell death responses. In contrast, proteins overexpressed in SCC (205) were associated with the cell cycle, DNA damage, drug metabolism, proteasome degradation, methylation, and immune response. Interaction analyses highlighted proteins related to early proteins 1,5,6 and 7 (E1, E5, E6, and E7). In terms of the two DEPs, S100 calcium binding protein A10 (S100A10/p11) and thymidine phosphorylase (TYMP) were detected in patients with LSIL, HSIL, and SCC at the protein level, consistent with their higher transcript levels in public datasets. Given the small, exploratory cohort, these findings are hypothesis-generating, and validation in a larger, balanced, independent cohort is required. In conclusion, this study identified DEPs associated with the progression of premalignant lesions to SCC that may represent candidate biomarkers and therapeutic targets warranting further investigation. Full article

Vehicle energy-regenerative suspension can convert part of the vibration energy induced by road excitation into electrical energy. However, there are coupled performance conflicts among energy recovery, ride comfort, and suspension safety, and a fixed-weight LQR controller finds it difficult to maintain a reasonable performance compromise under different road conditions. To address this problem, this paper proposes an AWG-NN-LQR control method based on an Adaptive Weight Generation neural network. First, a quarter-car energy-regenerative suspension model, an electromagnetic actuator model, and a random road model are established, and the vertical vehicle responses and energy-regeneration characteristics under different road classes are analyzed. Second, vehicle speed, road roughness coefficient, and statistical features of vehicle responses are used as inputs. LQR weight labels are generated through offline closed-loop simulation and candidate-weight search, and the AWG-NN is trained to learn the nonlinear mapping relationship between road conditions and weight parameters. Finally, closed-loop comparative validation is conducted for the passive suspension, fixed-weight LQR, and AWG-NN-LQR under a typical class-C road condition. The results show that, compared with the fixed-weight LQR, AWG-NN-LQR reduces the RMS of body acceleration from $1.7041{\mathrm{m}/\mathrm{s}}^2$ to $1.6527{\mathrm{m}/\mathrm{s}}^2$, and reduces the RMS of suspension deflection from $0.00863\mathrm{m}$ to $0.00844\mathrm{m}$, while achieving an average regenerated power of $9.41\mathrm{W}$. The proposed method can improve the objective-bias problem of the fixed-weight LQR under a typical operating condition while maintaining a certain energy-regeneration capability, providing a feasible approach for multi-objective adaptive control of energy-regenerative suspension. Full article

This paper investigates the quasi-synchronization (QS) problem for drive-response discrete-time delayed inertial neural networks (DTDINNS). Unlike existing studies that mainly rely on classical stability theorems, linear matrix inequality (LMI) methods, and matrix measure approaches (MMA), this work establishes three innovative quasi-synchronization criteria for DTDINNS by adopting the solution formula of second-order linear difference equations (SOLDES), infinite series summation techniques, and the solution formula of first-order linear difference equation group (Lemma 6). To the best of our knowledge, this study is the first attempt to introduce the general solution theory of second-order linear difference equations and infinite series summation methods to analyze the synchronization behavior of neural networks (NNS). The proposed framework offers a novel theoretical tool for the synchronization analysis of discrete-time delayed neural networks (DTDNNS), which bears important theoretical significance for relevant research fields. Full article

This study aims to accurately predict students’ academic performance trajectories for university entrance examinations by proposing a machine learning framework that explicitly accounts for missing data and uncertainty. Mock examination data are characterized by substantial missing values due to heterogeneous participation in exams, as well as inherent randomness caused by variations in test content and examinee conditions. Conventional single-value imputation methods cannot adequately reconstruct the missing values arising from such heterogeneous participation without introducing strong bias, and existing educational prediction models based on deterministic formulations do not account for the inherent randomness and uncertainty in examination scores, thereby limiting the reliability of their forecasts. To address these challenges, we employ GP-VAE and SAITS, state-of-the-art methods for time-series imputation, to reconstruct incomplete mock examination data. Furthermore, we develop a Bayesian Neural Network (BayesNN) to predict future academic performance while explicitly modeling uncertainty. By integrating temporally aware imputation with probabilistic prediction, the proposed framework aims to provide more accurate and reliable performance forecasts than existing approaches. We evaluate the effectiveness of the proposed method through comparative experiments involving various combinations of imputation techniques and prediction models. Experimental results demonstrate that the proposed framework achieves competitive predictive accuracy: the combination of deep imputation methods and BayesNN yields the lowest average estimation error of 15.98 points, compared with 16.75 points for the conventional combination of mean imputation and linear regression. The contribution of this study does not lie in proposing a new deep learning model itself, but rather in systematically comparing combinations of time-series imputation methods and uncertainty-aware prediction models using real-world mock examination sequence data with missing values, thereby providing effective design guidelines for educational data analysis. Full article

Breast cancer is one of the prominent reasons of death in women. HER2 is a promising target to counter breast cancer. In the current research, a structure-based pharmacophore model was generated to map and screen CMNPD, a comprehensive database of marine natural products. The two compounds (CMNPD30448 (hit1) and CMNPD7060 (hit2)) displayed better LibDock scores than the reference co-crystallized ligand. These compounds demonstrated stable molecular dynamics results conducted for 500 ns with stable root mean square deviation (RMSD) at 0.3 nm, stable radius of gyration (Rg) and root mean square fluctuation (RMSF). On ChEMBL compounds, different PaDEL descriptors and various machine learning (ML) and neural network (NN) methods were used. The results showed that PubChem fingerprints with random forest classification model displayed an accuracy of 0.91 and a receiver operating characteristic area under the curve (ROC-AUC) of 0.96. This model further predicted the retrieved compounds as ‘active’. The explainable random forest with LIME showed that PubChem fingerprint440 [C(-C)(-O)(=O)], PubChem fingerprint452 [C(-O)(=O)], PubChem fingerprint380 [C(~O)(~O)], PubChem fingerprint566 [O-C-C-N] and PubChem fingerprint712 [C-C(C)-C(C)-C] for hit1 and PubChem fingerprint700 [O-C-C-C-C-C-O-C], PubChem fingerprint380 [C(~O)(~O)], and PubChem fingerprint712 [C-C(C)-C(C)-C] for hit2 have contributed towards plausible inhibitory potential. These findings suggest the two compounds CMNPD30448 and CMNPD7060 might serve as HER2 inhibitors. Further in vitro and in vivo analysis are required before using them. Full article

This paper develops a stability-certified distributed residual neural network (ResNN) controller for leaderless consensus of continuous-time first-order multi-agent systems over undirected connected graphs. Unlikeconventional linear protocols and post-training verification methods, the proposed framework combines nonlinear transient shaping with certificate feasibility throughout learning. Each agent uses relative state differences with neighboring agents and applies a shared ResNN policy composed of a linear diffusive backbone and a bias-free neural residual branch. A computable residual-gain bound yields a sufficient condition for global exponential consensus, with the certified rate determined by the backbone–residual gain margin and the algebraic connectivity of the graph. Spectral-norm projection and gain reparameterization preserve this condition after every training update. A complementary forward-Euler certificate provides an explicit step-size condition for exponentially convergent digital implementation. The controller is trained through differentiable closed-loop simulation using an objective that balances disagreement and control effort. Ournumerical results verify the certified decay bound, demonstrate competitive transient trade-offs against three baselines, and evaluate direct deployment across different graph topologies and network sizes. Full article

Accurate prediction of the Remaining Useful Life (RUL) of nuclear power plant systems can support more informed maintenance strategies and help reduce unplanned outages, motivating continued research into reliable, physically grounded prognostic models. This study evaluates machine-learning-based prognostic models, focusing on their ability to learn degradation patterns directly from operational data. Baseline Feedforward Neural Networks (FNNs), Long Short-Term Memory (LSTM) networks, Graph Neural Networks (GNNs), and a hybrid GNN–Transformer architecture are assessed using data generated from the ASHERAH dynamic Pressurized Water Reactor simulator, which incorporates realistic degradation mechanisms, including condenser fouling and pump head loss. The proposed hybrid model integrates graph-based representations of component interactions with Transformer-based temporal attention to capture both system-level dependencies and long-term degradation dynamics. Model performance is evaluated using error-based and tolerance-based metrics, including Prediction Within Bounds Accuracy ($PWB{A}_{20\%}$), alongside uncertainty calibration via Prediction Interval Coverage Probability (PICP), with uncertainty quantified through deep ensembles. Results show that baseline NNs exhibit limited predictive accuracy and poor uncertainty calibration, while models incorporating temporal modeling and system topology achieve substantial improvements. The GNN–Transformer attains the strongest performance, yielding the highest $PWB{A}_{20\% }$ (87.3%) and significantly improved uncertainty calibration, with an average PICP of 90.0%. These findings demonstrate the effectiveness of topology-aware, attention-based architectures for robust and reliable RUL prediction in complex nuclear systems. Full article

As a key task in LiDAR data processing, point cloud classification directly determines the accuracy and reliability of downstream applications such as autonomous driving and robot navigation. However, in practical scenarios, point cloud sparsity is easily affected by various factors, leading to a decrease in classification accuracy. To address this issue, this paper proposes a sparse point cloud classification method based on the MSE-Mamba neural network. By combining the efficient sequence processing advantages of the MSE-Mamba module with the global modeling capability of the global attention Transformer module, high-precision classification of sparse point clouds is achieved. Extensive experimental results on ModelNet40, ScanObjectNN, and self-built 3D imaging LiDAR point cloud datasets show that the proposed method exhibits excellent point cloud classification performance in various scenarios, with overall accuracy improved compared to current mainstream methods. It provides a new approach for high-precision classification of sparse point clouds and is of great significance for promoting the practical application of LiDAR technology in complex scenes. Full article

State estimation is a fundamental component of model-based Fault Detection and Diagnosis (FDD) in dynamic systems, underpinning real-time monitoring, predictive maintenance, and safety-critical operations across industries such as aerospace, power systems, robotics, and autonomous vehicles. Traditional estimators, including the Kalman Filter (KF) and its variants, provide physically interpretable residuals for fault detection but often fail to deliver reliable performance under nonlinear dynamics, modeling uncertainties, sensor faults, and non-Gaussian noise. This paper presents a comprehensive review of state estimation-based FDD approaches, with a particular focus on Artificial Intelligence (AI)-augmented Kalman filtering and hybrid frameworks that integrate Machine Learning (ML) models, including Neural Networks (NNs), Support Vector Machines (SVMs), and Gaussian Processes (GPs), with classical estimation theory. The review systematically evaluates model-based, data-driven, and hybrid methods, comparing their robustness, accuracy, computational efficiency, scalability, and interpretability in complex Cyber-Physical Systems (CPSs). Furthermore, emerging trends and open research challenges are identified, including online adaptation, fault-tolerant estimation, sensor fusion, explainable artificial intelligence (XAI), and deployment in Industry 4.0 and Internet of Things (IoT)-enabled environments. By bridging classical estimation theory with modern AI techniques, this review provides a roadmap for designing intelligent, adaptive, and resilient FDD systems capable of enhancing reliability, operational safety, and real-world applicability. Full article

In this research, a signal-integrity control strategy of a through-silicon via (TSV) array for a Chiplet-based system is developed, based on the backpropagation neural network (BP-NN) model and particle swarm optimization algorithm with linear decreasing inertia weight (PSO-LDIW). Based on the HFSS software, the simulation results of the TSV array are obtained. The irregular relationship between design parameters (TSV pitches, height of TSV, radius of TSV, thickness of oxide layer, and offset angle) and signal indexes (return loss, insertion loss, near-end, and far-end crosstalk) is established by the BP-NN model. Then, the design parameters of the TSV array are optimized by the PSO-LDIW algorithm to obtain the desired signal indexes. Based on the optimized design parameters, the effectiveness of the developed signal-integrity control strategy is verified by HFSS simulations. For the three verification cases, the relative errors between the BP-NN-predicted values and the corresponding HFSS simulation values range from 0.31% to 5.02%. The relative deviations of the HFSS results from the desired NEXT, FEXT, and return-loss targets are no greater than 5.72%, while the maximum absolute deviation from the desired insertion-loss target is 0.0160 dB. These results demonstrate the feasibility of the developed strategy for controlling the signal indexes of the TSV array in the tested cases. Full article

As AI research advances, various performance optimization techniques have been studied for TinyML models on microcontrollers with very limited resources. In TinyML frameworks such as TFLM (TensorFlow Lite Micro) and NNOM (Neural Network on Microcontrollers), their execution engines mainly depend on CMSIS-NN for inference acceleration, which is an ARM’s back-end library to execute optimized kernel functions for performance optimization. But we often find that CMSIS-NN is not invincible for inference time optimization on TinyML. In this paper, we examine TinyML frameworks and their CMSIS-NN libraries and consider how to improve CMSIS-NN in terms of runtime. Then, we propose the D2I technique to reduce the overhead of memory operations that occur while performing the Im2col procedure within the convolution function, which takes most of the inference time in CMSIS-NN. The proposed technique creates a necessary index table, finds the location of the input with the corresponding index, and performs direct operations between filters and inputs. Thus, it can quite mitigate data copy operations in Im2col with a small additional amount of memory compared to Im2col. In extensive experiments using an Arduino nano 33 BLE board with Cortex-M4 and an STM32F746G-DISCO board with Cortex-M7, D2I was found to achieve about 16.3% and 14.5% inference time improvements against the Im2col in TFLM’s and NNOM’s CMSIS-NNs, respectively, for the SqueezeNet model. And the additional memory usage was shown to be identically 11.52 kB. Full article

The sideslip angle is crucial for vehicle stability, especially for single-track vehicles. As it is difficult to measure this quantity directly, the use of virtual sensors (observers) is common practice in this field.Neural network-based virtual sensors are becoming increasingly popular due to their ability to handle nonlinear conditions and noise. This paper presents a rigorous methodological approach to selecting measured quantities and determining the appropriate sampling frequency for stable sideslip reconstruction using a nonlinear autoregressive neural network with exogenous inputs (NARX-NN) model. A literature review suggests that most studies on sideslip angle estimation focus solely on achieving superior accuracy, with little extensive discussion of the selected quantities or sampling conditions required for effective estimation. This paper uses an information theory approach combined with a qualitative approach to select suitable model input quantities, the optimal number of look-ahead steps (‘embedding’), and the optimal sampling frequency to maximise the ratio between the latent information provided to the model for state reconstruction and the reduced computational burden on the electronic control unit (ECU). The results show that the sampling and computing frequency can be reduced by up to 20 times compared to the common baseline. This enables the use of less powerful hardware for the same model, resulting in better resource utilisation. Full article

Fixed-bottom or floating offshore structures are the foundations, platforms, and associated infrastructure that allow for oil and gas production systems, offshore wind turbines, and cabling. The remote nature of these structures and the harsh environment with high variability in wind, waves, currents, and weather make construction activity very difficult and unpredictable; the cost of variation in the schedule can lead to high construction vessel and personnel costs. The adoption of artificial intelligence using trends observed in historical data can help achieve more accurate construction costs and schedule predictions, reducing the capital expenditure cost of installation. A resource-significant activity, sometimes called a resource-critical activity or high-resource-demand activity, is an activity on a construction or project schedule that consumes a disproportionately large share of one or more resources compared with others. Plant Design Modelling (PDM) is a digital process that creates and manages a detailed 3D model of a building’s physical and functional characteristics and semantic information, such as cost and schedule. PDM serves as a single source of truth for multidisciplinary activities and, therefore, serves as a rich data source for various construction applications, including project scheduling and cost estimation. Neural networks (NNs), a subset of machine learning algorithms inspired by the human brain, excel at identifying patterns in complex datasets and making predictions, such as forecasting costs based on non-linear relationships and historical trends. Data from an offshore structure modification project were extracted from Aveva’s Everything PDM, focusing on installation activities to create a dataset for machine learning model training. The structured data extracted exhibit non-linear patterns; therefore, linear, regularised linear, robust linear, and the ensemble (tree-based) models and supervised neural network models with varied architecture and hyperparameter values were evaluated and compared. The best performance was obtained using the deep-optimised ANN model. The result obtained is consistent with previous studies. The neural network models show a superior ability to predict the non-linear nature of offshore construction activities’ time. Full article