Explore the vast range of titles available.

Tree-based methods and deep neural networks (DNNs) have drawn much attention in the classification of images. Interpretable canonical deep tabular data learning architecture (TabNet) that combines the concept of tree-based techniques and DNNs can be used for hyperspectral image classification. Sequential attention is used in such architecture for choosing appropriate salient features at each decision step, which enables interpretability and efficient learning to increase learning capacity. In this paper, TabNet with spatial attention (TabNets) is proposed to include spatial information, in which a 2D convolution neural network (CNN) is incorporated inside an attentive transformer for spatial soft feature selection. In addition, spatial information is exploited by feature extraction in a pre-processing stage, where an adaptive texture smoothing method is used to construct a structure profile (SP), and the extracted SP is fed into TabNet (sTabNet) to further enhance performance. Moreover, the performance of TabNet-class approaches can be improved by introducing unsupervised pretraining. Overall accuracy for the unsupervised pretrained version of the proposed TabNets, i.e., uTabNets, can be improved from 11.29% to 12.61%, 3.6% to 7.67%, and 5.97% to 8.01% in comparison to other classification techniques, at the cost of increases in computational complexity by factors of 1.96 to 2.52, 2.03 to 3.45, and 2.67 to 5.52, respectively. Experimental results obtained on different hyperspectral datasets demonstrated the superiority of the proposed approaches in comparison with other state-of-the-art techniques including DNNs and decision tree variants.

5G is considered as a key contributor and infrastructure supplier in the communication technology industry, capable of supporting a wide range of services such as virtual reality, driverless automobiles, e-health, and a variety of intelligent applications. Network slicing is designed to support the diversity of services applications with increased performance and flexibility needs by dividing the physical network into many logical networks. Service classification allows 5G service providers to accurately select the network slices for each service. We propose a Network Slicing classifier that uses a Multi-level Deep learning Model. First, we created a dataset of 5G network slicing that contain attributes connected with various network services. Next, we performed a multi-level model that consist of a set of Machine learning and deep learning model (such as deep Neural Network, Random Forest and Decision Tree) as a first level followed by next level that which is represent Attentive Interpretable Tabular Learning model. The outcomes of the experiment showed that the proposed model was able to exceed the normal models with high performance results.

Automated indoor environmental control is a research topic that is beginning to receive much attention in smart home automation. All machine learning models proposed to date for this purpose have relied on reinforcement learning using simple metrics of comfort as reward signals. Unfortunately, such indicators do not take into account individual preferences and other elements of human perception. This research explores an alternative (albeit closely related) paradigm called imitation learning. In the proposed architecture, machine learning models are trained with tabular data pertaining to environmental control activities of the real occupants of a residential unit. This eliminates the need for metrics that explicitly quantify human perception of comfort. Moreover, this article introduces the recently proposed deep attentive tabular neural network (TabNet) into smart home research by incorporating TabNet-based components within its overall framework. TabNet has consistently outperformed all other popular machine learning models in a variety of other application domains, including gradient boosting, which was previously considered ideal for learning from tabular data. The results obtained herein strongly suggest that TabNet is the best choice for smart home applications. Simulations conducted using the proposed architecture demonstrate its effectiveness in reproducing the activity patterns of the home unit’s actual occupants.

Wireless sensor networks (WSNs) are integral components of smart environments. These allow monitoring and communication to take place autonomously across distributed sensor nodes. Nevertheless, they suffer from constrained resources that make them susceptible to routine-layer attacks. These specifically involve blackhole, flooding, selective forwarding attack traffic and normal traffic. The conventional machine learning and deep learning methods employed are effective in catering to these attacks, yet they have generalization issues when the network conditions are dynamic. The models are generally trained on the local features that make them more dependable and less interpretable. To overcome these issues, this paper proposes an attention-driven transformer encoder for tabular WSN traffic, designed for robust and interpretable intrusion detection in WSNs. The model represents the WSN features as sequential tokens and employs multi-head self-attention to capture global and local dependencies among sensor attributes and employs a multi-head self-attention for capturing the local and global dependencies among the sensor attributes. The framework integrated several components, including normalization, chi-square-based feature selection, and positional embedding. These are followed by multi-layer transformer encoding blocks for the feature fusion and subsequent classification. The framework has been evaluated on the publicly available WSN dataset. Results have been shown to attain an accuracy of 99.37%, which makes it outperform the traditional deep learning baseline models. The comparative analysis has shown the model to be superior in terms of generalization and reduced convergence time. It further offers enhanced interpretability that makes it a good fit to be deployed in real-world scenarios where resources can be constrained.

This paper extends recent work on decision rule learning from neural networks for tabular data classification. We propose alternative formulations to trainable Boolean logic operators as neurons with continuous weights, including trainable NAND neurons. These alternative formulations provide uniform treatments to different trainable logic neurons so that they can be uniformly trained, which enables, for example, the direct application of existing sparsity-promoting neural net training techniques like reweighted L1 regularization to derive sparse networks that translate to simpler rules. In addition, we present an alternative network architecture based on trainable NAND neurons by applying De Morgan’s law to realize a NAND-NAND network instead of an AND-OR network, both of which can be readily mapped to decision rule sets. Our experimental results show that these alternative formulations can also generate accurate decision rule sets that achieve state-of-the-art performance in terms of accuracy in tabular learning applications.

This study presents TAQLA, a new Tabular Adaptive Q-Learning Agent for portfolio management in stochastic financial markets. TAQLA rests on a multi-model reinforcement learning (RL) architecture that integrates parameter-adaptive Q-Learning mechanisms into softmax-based exploration to reconcile short-term profit maximization with long-term capital preservation. The method is contrasted with vanilla Q-Learning, SARSA, and a random trading policy using simulated equity market data. Empirical analysis shows that TAQLA performs better on profitability, risk-adjusted performance, and drawdown minimization, with a last portfolio value of $1687.45 (+68.74% of initial capital), a Sharpe ratio of 1.41, and a maximum drawdown of just 12.8%. Q-Learning and SARSA, on the other hand, yield Sharpe ratios below 1.0 and drawdowns exceeding 18%. Parameter sensitivity analysis across β (softmax temperature), α (learning rate), and γ (discount factor) reveals that aggressive exploration (β ≈ 1.0–1.5) and reasonable discounting (γ ≈ 0.4–0.6) generate the most aggressive and robust outcomes. Such outcomes place TAQLA as a robust RL-based adaptive portfolio control method under uncertainty, with improved capital appreciation and robustness to adverse market conditions.

Background/Objectives Globalincreases in cesarean section (C-section) rates, often exceeding medical necessity, highlight the need for accurate antenatal prediction to support evidence-based birth planning. Reliable prediction of delivery mode is essential for reducing maternal and neonatal morbidity, improving clinical decision-making, and optimizing resource allocation. This study analyzes a publicly available dataset of 460 multiparous women, including 18 obstetric and antenatal variables, published by Yimer and Mekonnen. Methods Deep learning architectures were systematically evaluated for predicting delivery mode in multiparous pregnancies. Classical Multilayer Perceptrons (MLPs) served as baseline models, while modern tabular deep learning methods were assessed as advanced alternatives. Preprocessing included multiple imputation, outlier removal, and class balancing via SMOTE. Feature selection was performed using a hybrid Boruta–clinical expert strategy. Hyperparameters were tuned through Random Search. To improve interpretability, an explainability pipeline integrating SHAP and LIME was incorporated. Results Optimized MLPs produced modest performance gains, but dedicated tabular models demonstrated clear superiority. TabNet achieved the highest performance, with an ROC-AUC of 0.79 and a PR-AUC of 0.74, attributed to its attention and masking mechanisms and robust handling of minority classes. TabPFN and CBAM-MLP yielded stable and balanced results, whereas FT-Transformer showed competitive yet comparatively moderate accuracy. Conclusions The findings demonstrate that modern tabular deep learning approaches, particularly TabNet, surpass baseline MLP architectures in terms of accuracy, explainability, and clinical applicability for predicting C-section in multiparous women. This study presents the first comprehensive and explainable comparison of tabular deep learning models tailored to multiparous pregnancies, combining hybrid Boruta–expert feature selection with SHAP and LIME interpretability. TabNet emerges as the most promising candidate for integration into clinical decision support systems, contributing substantially to AI-driven strategies for addressing rising global C-section rates. Graphical Abstract

Spreadsheets, comma separated value files and other tabular data representations are in wide use today. However, writing, maintaining and identifying good formulas for tabular data and spreadsheets can be time-consuming and error-prone. We investigate the automatic learning of constraints (formulas and relations) in raw tabular data in an unsupervised way. We represent common spreadsheet formulas and relations through predicates and expressions whose arguments must satisfy the inherent properties of the constraint. The challenge is to automatically infer the set of constraints present in the data, without labeled examples or user feedback. We propose a two-stage generate and test method where the first stage uses constraint solving techniques to efficiently reduce the number of candidates, based on the predicate signatures. Our approach takes inspiration from inductive logic programming, constraint learning and constraint satisfaction. We show that we are able to accurately discover constraints in spreadsheets from various sources.

Credit default prediction from firm-level accounting statements is central to risk management, yet the underlying financial data are highly sensitive and often siloed across banks, auditors, and platforms. Federated learning (FL) offers a practical route to collaborative modeling without centralizing raw records, but standard FL optimization can converge slowly under severe client heterogeneity, heavy-tailed accounting features, and label imbalance typical of default events. This paper proposes FedQuAD, a novel fast-converging FL algorithm that couples (i) quasi-Newton curvature aggregation on the server with a lightweight limited-memory update to accelerate global progress, (ii) a proximal variance-reduced local solver that stabilizes client drift under non-IID accounting distributions, and (iii) federated robust standardization of tabular financial ratios via secure aggregated quantile statistics to mitigate scale instability and outliers. FedQuAD is communication-efficient by design: It transmits compact gradient and curvature sketches and adapts local computation to each client’s stochasticity and drift. We provide convergence guarantees for strongly convex default-risk objectives (logistic and calibrated GLM losses) under bounded heterogeneity, and extend the analysis to nonconvex deep tabular models via expected stationarity bounds. Experiments on public credit-risk benchmarks with simulated cross-silo (institutional) partitions demonstrate that FedQuAD reaches target AUC and calibration error with substantially fewer communication rounds than representative baselines while maintaining privacy constraints compatible with secure aggregation and optional client-level differential privacy accounting.

Accurate prediction of concrete compressive strength remains a challenging problem due to the complex and nonlinear interactions among mixture components and curing conditions. While machine learning approaches have shown promising results, existing studies are typically limited by static model integration strategies and insufficient consideration of structural relationships among input variables. To address these limitations, this study proposes a novel Adaptive Symmetry-Aware Physics-Informed Hybrid (ASAPH) learning framework. The proposed approach integrates three key components: (i) symmetry-consistent feature representation that preserves invariant relationships among mixture parameters, (ii) a stability-driven feature selection mechanism with a relevance–redundancy trade-off, and (iii) an adaptive input-dependent ensemble strategy that dynamically combines multiple learners. In contrast to conventional stacking methods, the proposed framework employs a learnable weighting function to adjust model contributions based on input characteristics, enabling more flexible, robust, and input-adaptive predictions. The framework combines an attention-based tabular model (TabNet) for representation learning and a tree-based ensemble model (XGBoost) for predictive robustness within a unified adaptive fusion architecture. Experimental results on a benchmark dataset using 10-fold cross-validation demonstrate that the proposed model achieves strong predictive performance, with R2 = 0.9162, RMSE = 4.8271, and MAE = 3.4118, outperforming strong baseline models including XGBoost and TabNet. Furthermore, explainability analysis based on SHAP reveals that curing age, cement content, and water-related parameters are the most influential factors governing compressive strength, consistent with established engineering knowledge. Among these, curing age emerges as the most dominant factor, followed by water-related ratios and cement content, indicating strong alignment with established domain knowledge. These findings confirm that incorporating symmetry-aware and physics-informed representations enhances both interpretability and predictive reliability. Overall, the proposed framework provides a principled and generalizable approach for modeling complex engineering systems, bridging the gap between data-driven learning and physically consistent modeling.