Search Results (158)

Rural road programs are essential for enhancing connectivity in remote areas, yet they frequently encounter schedule delays and budget overruns. This study explores the extent to which specific project characteristics influence these deviations in Colombian rural road contracts. A dataset comprising 229 projects was extracted from the national SECOP open-procurement platform and processed using the CRISP-DM protocol. Following the cleaning and coding of 14 project-level variables, statistical analyses were conducted using Spearman correlations, Kruskal–Wallis tests, and post-hoc Wilcoxon comparisons to identify significant bivariate relations I confirm I confirm I confirm hips. A Random Forest model was subsequently applied to determine the most influential multivariate predictors of cost and time deviations. In parallel, a directed content analysis of contract addenda reclassified 22 recorded deviation descriptors into ten internationally recognized categories of causality, enabling an integrated interpretation of both statistical and documentary evidence. The findings indicate that contract value, geographical region, and contractor configuration are significant determinants of cost and time performance. Additionally, project intensity and discrepancies between awarded and bid values emerged as key contributors to cost escalation. Scope changes and adverse weather conditions together accounted for 76% of all documented deviation triggers, underscoring the relevance of robust front-end planning and climate-risk considerations in rural infrastructure delivery. The findings provide information for stakeholders, policymakers, and professionals who aim to manage the risk of schedule and budget deviations in public infrastructure projects. Full article

With the growing deployment of latency-sensitive applications, the Age of Information (AoI) has emerged as a key performance metric for the evaluation of data freshness in networked systems. While prior studies have extensively explored the AoI under centralized scheduling or random-access protocols such as carrier sense multiple access (CSMA) and ALOHA, most assume that sources generate independent information. However, in practical scenarios such as environmental monitoring and visual sensing, information correlation frequently exists among correlated sources, providing new opportunities to enhance network timeliness. In this paper, we propose a novel analytical framework that captures the interplay between CSMA channel contention and spatial information correlation among sources. By leveraging the stochastic hybrid systems (SHS) methodology, we jointly model random backoff behavior, medium access collisions, and correlated updates in a scalable and mathematically tractable manner. We derive closed-form expressions for the average AoI under general correlation structures and further propose a lightweight estimation approach for scenarios where the correlation matrix is partially known or unknown. To our knowledge, this is the first work that integrates correlation-aware modeling into AoI analysis under distributed CSMA protocols. Extensive simulations confirm the accuracy of the theoretical results and demonstrate that exploiting information redundancy can significantly reduce the AoI, particularly under high node densities and constrained sampling budgets. These findings offer practical guidance for the design of efficient and timely data acquisition strategies in dense or energy-constrained Internet of Things (IoT) networks. Full article

This study examines how the Russia–Ukraine conflict has affected the robustness of the global liquefied natural gas (LNG) trade network—an essential component of the global energy transition. As environmental concerns intensify worldwide, LNG is gaining strategic importance due to its cleaner emissions and greater flexibility compared to traditional fossil fuels. However, the global LNG trade network remains vulnerable to geopolitical shocks, particularly due to its concentrated structure. In this context, we construct the LNG trade network from 2020 to 2023 and employ complex network analysis to explore its structural characteristics. We assess network robustness under various attack strategies, budget constraints, and phases of the conflict. Furthermore, we utilize the difference-in-differences (DID) method to evaluate the conflict’s impact on network robustness. Our findings reveal that the global LNG trade network exhibits a distinct center–periphery structure and regional clustering. Although the network scale has continuously expanded, its connectivity still requires improvement. The Russia–Ukraine conflict has significantly weakened network robustness, with negative impacts intensifying across attack phases and under greater budget constraints. The optimal attack strategy causes the most severe degradation, followed by high-importance attacks, while random and low-importance attacks exert limited influence. Our DID-based analysis further confirms the conflict’s significant negative impact. To strengthen its resilience, the global LNG trade network should diversify its partnerships and invest in infrastructure enhancements. Full article

To fully leverage Google Analytics and derive actionable insights, web analytics practitioners must go beyond standard implementation and customize the setup for specific functional requirements, which involves additional web development efforts. Previous studies have not provided solutions for estimating web analytics development efforts, and practitioners must rely on ad hoc practices for time and budget estimation. This study presents a COSMIC-based measurement framework to measure the functional size of Google Analytics implementations, including two examples. Next, a set of 50 web analytics projects were sized in COSMIC Function Points and used as inputs to various machine learning (ML) effort estimation models. A comparison of predicted effort values with actual values indicated that Linear Regression, Extra Trees, and Random Forest ML models performed well in terms of low Root Mean Square Error (RMSE), high Testing Accuracy, and strong Standard Accuracy (SA) scores. These results demonstrate the feasibility of applying functional size for web analytics and its usefulness in predicting web analytics project efforts. This study contributes to enhancing rigor in web analytics project management, thereby enabling more effective resource planning and allocation. Full article

We address the problem of humanoid locomotion in 3D environments consisting of planar regions with arbitrary inclination and elevation, such as staircases, ramps, and multi-floor layouts. The proposed framework combines an offline randomized footstep planner with an online control pipeline that includes a model predictive controller for gait generation and a whole-body controller for computing robot torque commands. The planner efficiently explores the environment and returns the highest-quality plan it can find within a user-specified time budget, while the control layer ensures dynamic balance and adequate ground friction. The complete framework was evaluated via dynamic simulation in MuJoCo, placing the JVRC1 humanoid in four scenarios of varying complexity. Full article

The increasing digitization of educational data poses critical challenges in balancing predictive accuracy with privacy protection for sensitive student information. This study introduces DP-TabNet, a pioneering framework that integrates the interpretable deep learning architecture of TabNet with differential privacy (DP) techniques to enable secure and effective student grade prediction. By incorporating the Laplace Mechanism with a carefully calibrated privacy budget ($ϵ$ = 0.7) and sensitivity ($\Delta f$ = 0.1), DP-TabNet ensures robust protection of individual data while maintaining analytical utility. Experimental results on real-world educational datasets demonstrate that DP-TabNet achieves an accuracy of 80%, only 4% lower than the non-private TabNet model (84%), and outperforms privacy-preserving baselines such as DP-Random Forest (78%), DP-XGBoost (78%), DP-MLP (69%), and DP-SGD (69%). Furthermore, its interpretable feature importance analysis highlights key predictors like resource engagement and attendance metrics, offering actionable insights for educators under strict privacy constraints. This work advances privacy-preserving educational technology by demonstrating that high predictive performance and strong privacy guarantees can coexist, providing a practical and responsible framework for educational data analytics. Full article

Bank loan prediction (BLP) analyzes the financial records of individuals to conclude possible loan status. Financial records always contain confidential information. Hence, privacy is significant in the BLP system. This research aims to generate a privacy-preserving automated BLP scheme. To achieve this, differential privacy (DP) is combined with machine learning (ML). Using a benchmark dataset, the proposed method analyzes two different DP techniques, namely Laplacian and Gaussian, with five different ML models: Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), Logistic Regression (LR), and Categorical Boosting (CatBoost). Each of the DP techniques is evaluated by varying distinct privacy parameters with 10-fold cross-validation, and from the outcome analysis, optimal parameters are nominated to balance privacy and security. The analysis indicates that applying the Laplacian mechanism with a DP budget of 2 and the RF model achieves the highest accuracy of 62.31%. For the Gaussian method, the best accuracy of 81.25% is attained by the CatBoost model in privacy budget 1.5. Additionally, the proposed method uses explainable artificial intelligence (XAI) to show the conclusion capability of DP-integrated ML models. The proposed research shows an efficient method for automated BLP while preserving the privacy of personal financial information and, thus, mitigating vulnerability to scams and fraud. Full article

In the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Traditionally, differential privacy’s noise injection often degrades model performance. To address this, we propose two adaptive privacy budget allocation strategies considering weight changes across neural network layers. The first, LS-ADP, utilizes layer sensitivity to assess the influence of individual layer weights on model performance and develops an adaptive differential privacy algorithm. The second, ROW-DP, comprehensively assesses weight variations and absolute values to propose a random one-layer weighted differential privacy algorithm. These algorithms provide differentiated privacy protection for various weights, mitigating privacy leakage while ensuring model performance. Experimental results on simulated and clinical datasets demonstrate improved predictive performance and robust privacy protection. Full article

Background: A grid search, at the cost of training and testing a large number of models, is an effective way to optimize the prediction performance of deep learning models. A challenging task concerning grid search is time management. Without a good time management scheme, a grid search can easily be set off as a “mission” that will not finish in our lifetime. In this study, we introduce a heuristic three-stage mechanism for managing the running time of low-budget grid searches with deep learning, sweet-spot grid search (SSGS) and randomized grid search (RGS) strategies for improving model prediction performance, in an application of predicting the 5-year, 10-year, and 15-year risk of breast cancer metastasis. Methods: We develop deep feedforward neural network (DFNN) models and optimize the prediction performance of these models through grid searches. We conduct eight cycles of grid searches in three stages, focusing on learning a reasonable range of values for each of the adjustable hyperparameters in Stage 1, learning the sweet-spot values of the set of hyperparameters and estimating the unit grid search time in Stage 2, and conducting multiple cycles of timed grid searches to refine model prediction performance with SSGS and RGS in Stage 3. We conduct various SHAP analyses to explain the prediction, including a unique type of SHAP analyses to interpret the contributions of the DFNN-model hyperparameters. Results: The grid searches we conducted improved the risk prediction of 5-year, 10-year, and 15-year breast cancer metastasis by 18.6%, 16.3%, and 17.3%, respectively, over the average performance of all corresponding models we trained using the RGS strategy. Conclusions: Grid search can greatly improve model prediction. Our result analyses not only demonstrate best model performance but also characterize grid searches from various aspects such as their capabilities of discovering decent models and the unit grid search time. The three-stage mechanism worked effectively. It not only made our low-budget grid searches feasible and manageable but also helped improve the model prediction performance of the DFNN models. Our SHAP analyses not only identified clinical risk factors important for the prediction of future risk of breast cancer metastasis, but also DFNN-model hyperparameters important to the prediction of performance scores. Full article

The air temperature near the Earth’s surface is one of the most important meteorological and climatological parameters. Yet, accurate and timely readings are not available in significant parts of the world. The development and first validation of a methodology for the estimation of the near-surface air temperature (NSAT) is presented here. Machine learning and satellite products are at the core of the developed model. Land Surface Analysis Satellite Application Facility (LSA SAF) products related to Earth’s surface radiation, temperature and humidity budgets, albedo and land cover, along with static topography parameters and weather station measurements, are used in the analysis. A series of experiments showed that the Random Forest regression with 20 selected satellite and topography predictors was the optimum selection for the estimation of the NSAT. The mean absolute error (MAE) of the NSAT estimation model was 0.96 °C, while the mean biased error (MBE) was −0.01 °C and the R² was 0.976. Limited seasonality was present in the efficiency of the model, while an increase in errors was noted during the first morning and afternoon hours. The topography influence in the model efficiency was rather limited. Cloud-free conditions were associated to only marginally smaller errors, supporting the applicability of the model under both cloud-free and cloudy conditions. Full article

Flexible pavements are susceptible to distress when subjected to long-term vehicle loads and environmental factors, thereby reqsuiring appropriate maintenance. To overcome the hectic field data collection and traffic congestion problems, this paper presents an intelligent prediction system framework utilizing Extreme Gradient Boosting (XGboost) to predict two relevant functional indices: rutting deformation and cracks damage. The model framework considers multiple essential factors, such as traffic load, material characteristics, and climate data conditions, to predict rutting behavior and employs image data to classify cracks behavior. The Extreme Gradient Boosting (XGboost) algorithm exhibited good performance, achieving an R² value of 0.9 for rutting behavior and an accuracy of 0.91, precision of 0.92, recall of 0.9, and F1-score of 0.91 for cracks. Moreover, a comparative assessment of the framework model with prominent AI methodologies reveals that the XGboost model outperforms support vector machine (SVM), decision tree (DT), random forest (RF), and K-Nearest Neighbor (KNN) methods in terms of quality of the result. For rutting behavior, a SHAP (Shapley Additive Explanations) analysis was performed on the XGboost model to interpret results and analyze the importance of individual features. The analysis revealed that parameters related to load and environmental conditions significantly influence the model’s predictions. Finally, the proposed model provides more precise estimates of pavement performance, which can assist in optimizing budget allocations for road authorities and providing dependable guidance for pavement maintenance. Full article

As traditional federated learning algorithms often fall short in providing privacy protection, a growing body of research integrates local differential privacy methods into federated learning to strengthen privacy guarantees. However, under a fixed privacy budget, with the increase in the dimensionality of model parameters, the privacy budget allocated per parameter diminishes, which means that a larger amount of noise is required to meet privacy requirements. This escalation in noise may adversely affect the final model’s performance. For that, we propose a privacy protection federated learning (PPRD-FL) approach. First, we design a randomized parameter selection strategy that combines randomization with importance-based filtering, effectively addressing the privacy budget dilution problem by selecting only the most crucial parameters for global aggregation. Second, we develop a dynamic local differential privacy-based perturbation mechanism, which adjusts the noise levels according to the training phase, not only providing robustness and security but also optimizing the dynamic allocation of the privacy budget. Finally, our experiments have demonstrated that the proposed approach maintains a high performance while ensuring strong privacy guarantees. Full article

In decentralized scenarios without fully trustable parties (e.g., in mobile edge computing or IoT environments), the shuffle model has recently emerged as a promising paradigm for differentially private federated learning. Despite many efforts of privacy accounting for federated learning with many sequential rounds in the shuffle model, they suffer from generality and tightness. For example, existing accounting methods are targeted to single-message shuffle protocols (which have intrinsic utility barriers compared to multi-message ones), and are untight for the commonly used vector randomized response randomizer. As countermeasures, we first present a tight total variation characterization of vector randomized response randomizers in the shuffle model, which demonstrates over 20% budget conservation. We then unify the representation of single-message and multi-message shuffle protocols and derive their privacy loss distribution (PLD). The PLDs are finally composed by Fourier analysis to obtain the overall privacy loss of many sequential rounds in the shuffle model. Through simulations in federated decision tree building and federated deep learning, we show that our approach saves up to 80% budget when compared to existing methods. Full article

Locating community facilities is a long-term, daunting task for governments, requiring ongoing budget or policy updates for gradual improvement. This study proposes a bi-objective multi-scenario dynamic model (BOMSDM) for community-facility siting, which aims to maximize service efficiency and social equity while considering variable facility numbers and inter-community competition. This study also provides a framework to demonstrate how the newly proposed model operates. This framework includes the BOMSDM itself, the data collection and processing method, and the constrained NSGA-II as the computational algorithm. Under this framework, the BOMSDM, along with three comparative frameworks derived from traditional models—including a random allocation non-incremental model, a random allocation incremental model, and an average allocation non-incremental model—was applied to a real-world scenario in Shaoxing. The results demonstrate the effectiveness and superiority of BOMSDM: it significantly outperforms the realistic solution in terms of service efficiency, fairness, and community allocation rate. Compared to alternative frameworks, BOMSDM sacrifices some objective values in scenarios without facility redundancy to ensure higher community coverage while exhibiting rapid improvement in objective values when redundancy is present, highlighting the framework’s flexibility. This framework provides government decision-makers with an effective tool for community-facility site selection. Full article

Physically unclonable functions (PUFs) represent emerging cryptographic primitives that exploit the uncertainty of the CMOS manufacturing process as an entropy source for generating unique, random and stable keys. These devices can be potentially used in a wide variety of applications ranging from secret key generation, anti-counterfeiting, and low-cost authentications to advanced protocols such as oblivious transfer and key exchange. Unfortunately, guaranteeing adequate PUF stability is still challenging, thus often requiring post-silicon stability enhancement techniques. The latter help to contrast the raw sensitivity to on-chip noise and variations in the environmental conditions (i.e., voltage and temperature variations), but their area and energy costs are not always feasible for IoT devices that operate with constrained budgets. This pushes the demand for ever more stable, area- and energy-efficient solutions at design time. This review aims to provide an overview of several weak PUF solutions implemented in CMOS technology, discussing their performance and suitability for being employed in security applications. Full article