1,720,963 research outputs found
Proposing a Dynamic Decision-Making Routing Method in Underwater Internet of Things
No full textOceans cover about 70% of the Earth’s surface, and about 95% remain unexplored for various reasons. Underwater wireless communication has been revolutionised with the help of Internet of Things networks. Recently, applications such as collecting marine data, marine monitoring, disaster prevention, historical exploration, oil and gas exploration, shipwreck exploration, maritime security, and monitoring of aquatic species and water pollution, and several applications have become possible. However, the problem of routing, information transfer, and resource preservation in the fluid underwater environment remains unsolved. In this research, we were looking for a solution to make routing more efficient, considering the various and practical criteria for the quality of service of the underwater IoT network. One of the outstanding features of this research is the possibility of dynamically weighing the parameters involved in routing and taking optimal and distributed decisions between network components. The proposed method has achieved acceptable results in terms of quality of service compared to recent methods
Semi-Supervised Supply Chain Fraud Detection with Unsupervised Pre-Filtering
No full textDetecting fraud in modern supply chains is difficult due to global complexity and limited labeled data. Traditional methods often fail with class imbalance and weak supervision. This paper proposes a two-phase framework to address these issues. First, Isolation Forest performs unsupervised anomaly detection to flag possible fraud and cut data volume. Second, a self-training SVM refines predictions with labeled and high-confidence pseudo-labeled samples for semi-supervised learning. We test the method on the DataCo Smart Supply Chain Dataset with fraud indicators. It achieves an F1-score of 0.817 and a false positive rate below 3.0%. These results show the value of combining unsupervised pre-filtering with semi-supervised refinement for fraud detection, though concept drift and lack of deep learning comparison remain as limits
An Enhanced Fuzzy Routing Protocol for Energy Optimization in the Underwater Wireless Sensor Networks
No full textUnderwater Wireless Sensor Networks (UWSNs) are gaining popularity because of their potential uses in oceanography, seismic activity monitoring, environmental preservation, and underwater mapping. Yet, these networks are faced with challenges such as self-interference, long propagation delays, limited bandwidth, and changing network topologies. These challenges are coped with by designing advanced routing protocols. In this work, we present Under Water Fuzzy-Routing Protocol for Low power and Lossy networks (UWF-RPL), an enhanced fuzzy-based protocol that improves decision-making during path selection and traffic distribution over different network nodes. Our method extends RPL with the aid of fuzzy logic to optimize depth, energy, Received Signal Strength Indicator (RSSI) to Expected Transmission Count (ETX) ratio, and latency. The proposed protocol outperforms other techniques in that it offers more energy efficiency, better packet delivery, low delay, and no queue overflow. It also exhibits better scalability and reliability in dynamic underwater networks, which is of very high importance in maintaining the network operations efficiency and the lifetime of UWSNs optimized. Compared to other recent methods, it offers improved network convergence time (10%–23%), energy efficiency (15%), packet delivery (17%), and delay (24%)
Ensemble-Based Fraud Detection: A Robust Approach Evaluated on IEEE-CIS
No full textCredit card fraud has increased with the fast expansion of online financial transactions, requiring the implementation of advanced detection systems. According to the IEEE-CIS dataset, this paper presents an extensive empirical assessment of ensemble learning methods for class-imbalanced fraud detection. By evaluating ensemble techniques such as Random Forest, XGBoost, LightGBM, and stacking approaches systematically, we address the critical issues of extreme class imbalance, concept drift, and real-time detection requirements. Our solution involves comprehensive feature engineering strategies tuned to the IEEE-CIS dataset, which consists of 590,540 transactions with a fraud rate of 3.5%, as well as advanced data balancing techniques (SMOTE, ADASYN, and Borderline-SMOTE). From experimental results, our ensemble stacking approach maintains low false positive rates while fraud is detected at high rates (0.918 AUC-ROC, 0.891 AUC-PR) and outperforms. The study offers useful implications for real-world practical implementation and empirical proof of the proficiency of ensemble approaches in dealing with highly imbalanced financial fraud datasets
Enhancing Energy Efficiency of Underwater Sensor Network Routing Aiming to Achieve Reliability
No full textIn response to the demands and harsh conditions of underwater environments, developing sensor networks and underwater Internet of Things (IoT) has paved the way for wireless communication, ocean exploration, and various research applications. However, challenges such as increasing failure rates and decreasing network efficiency remain open issues, hindering the achievement of quality of service (QoS) in underwater sensor networks. Addressing resource constraints, including processing power, memory, bandwidth, and energy resources, adds to the complexity of supporting network service quality. This study aims to investigate the service quality requirements in protocols and highlight the weaknesses of ongoing research in this field. Finally, a routing solution based on fuzzy logic is proposed, which provides better results than recent methods in tests of energy consumption rate, Jain’s fairness index, efficiency, and reliability
Uncertainty-Aware Deep Ensembles for Confident Customer Churn Prediction with Rejection Option
No full textCustomer churn prediction is an important problem in business intelligence, especially in industries where keeping customers is both difficult and expensive. Many existing models can predict churn accurately but do not show how confident they are in their results, which can cause costly or incorrect decisions. To solve this issue, this paper introduces an Uncertainty-Aware Ensemble (UA-Ensemble) framework that predicts churn while also estimating confidence levels. The model combines five neural network types, including attention-based LSTMs, Bayesian networks, and Monte Carlo Dropout, to measure both aleatoric and epistemic uncertainty. A cost-aware rejection rule is used to avoid unreliable predictions. Experiments on large banking, e-commerce, and telecom datasets reached 94.2% accuracy and reduced intervention costs by 18.3% compared to baseline models. The proposed approach outperforms traditional machine learning and deep learning methods, proving effective and trustworthy for business decision-making across various industries
Optimizing RPL Routing Using Tabu Search to Improve Link Stability and Energy Consumption in IoT Networks
No full textThe Routing Protocol for Low-power and Lossy Networks (RPL) is widely used in Internet of Things (IoT) systems, where devices usually have very limited resources. However, RPL still faces several problems, such as high energy usage, unstable links, and inefficient routing decisions, which reduce the overall network performance and lifetime. In this work, we introduce TABURPL, an improved routing method that applies Tabu Search (TS) to optimize the parent selection process. The method uses a combined cost function that considers Residual Energy, Transmission Energy, Distance to the Sink, Hop Count, Expected Transmission Count (ETX), and Link Stability Rate (LSR). Simulation results show that TABURPL improves link stability, lowers energy consumption, and increases the packet delivery ratio compared with standard RPL and other existing approaches. These results indicate that Tabu Search can handle the complex trade-offs in IoT routing and can provide a more reliable solution for extending the network lifetime
Adaptive multi-domain uncertainty quantification for digital twin water forecasting
No full textMachine learning (ML) models are often used to predict demand in digital twins (DTs) of water distribution systems (WDS). However, most models do not provide uncertainty estimation, and this makes risk evaluation limited. In this work, we introduce the first systematic framework for hierarchical uncertainty transfer in regional water networks, because until now no method existed for DT of regional water systems. We propose Adaptive Multi-Village Conformal Prediction (AMV-CP), a method that keeps theoretical guarantees and also allows transfer of uncertainty information between villages that are similar in structure but different in operation. The main ideas are: (i) village-adaptive conformity scores that capture local patterns, (ii) a meta-learning algorithm that reduces calibration cost by 88.6%, and (iii) regime-aware calibration that keeps 94.2% coverage when seasons change. We use eight years of data from six villages with 6174 users in one regional network. The results show a theoretical basis for cross-village transfer and 95.1% empirical coverage (target was 95%), with real-time speed of 120 predictions per second. Early multi-step tests also show 93.7% coverage for 24-hour horizons, with controlled trade-offs. This framework is the first systematic method for controlled uncertainty transfer in infrastructure DTs, with theoretical guarantees under φ-mixing and practical deployment. Our multi-village tests demonstrate the value of meta-learning for uncertainty estimation and make a base method that can be used in other hierarchical infrastructure systems. The system is validated in a Mediterranean rural network, but generalization to other climates, urban settings, and cascading systems needs further empirical study
Causal Digital Twins for cyber–physical security in water systems: A framework for robust anomaly detection
No full textndustrial Control Systems (ICS) in water distribution and treatment face cyber–physical attacks exploiting network and physical vulnerabilities. Current water system anomaly detection methods rely on correlations, yielding high false alarms and poor root cause analysis. We propose a Causal Digital Twin (CDT) framework for water infrastructures, combining causal inference with digital twin modeling. CDT supports association for pattern detection, intervention for system response, and counterfactual analysis for water attack prevention. Evaluated on water-related datasets SWaT, WADI, and HAI, CDT shows high compliance with physical constraints (90.8% for SWaT, 87.4%–90.8% across datasets) and structural Hamming distance 0.133 ± 0.02. F1-scores are 0.944 ± 0.014 (SWaT), 0.902 ± 0.021 (WADI), 0.923 ± 0.018 (HAI, p < 0.0024). Multi-scale temporal detection strategies (τ ∈ {5, 10, 20}) enable 91.7% detection of stealthy attacks through cumulative causal discrepancy analysis. CDT reduces false positives by 48% compared to state-of-the-art methods (70% vs. statistical baselines), achieves 78.4% root cause accuracy, and enables counterfactual defenses reducing attack success by up to 89.1%. Real-time performance at 3.2 ms latency ensures safe and interpretable operation for medium-scale water systems
- …
