Search Results (832)

Intrusion Detection Systems (IDSs) operate under asymmetric misclassification costs: false alarms (FP) consume analysts’ time and erode trust, whereas missed attacks (FN) carry business risks. This paper presents a complete pipeline for network anomaly detection on the CIC-IDS2017 dataset using Histogram-Based Gradient Boosting (HGB), with a particular focus on cost-aware threshold selection on a validation split for representative operating regimes $w_{FP}:w_{FN}\in \{1:1, 1:2, 1:3, 1:4, 1:5, 1:10\}$—treated as scenario-based proxies for varying risk posture, attack severity, and analyst workload rather than as universally fixed costs—and on the role of isotonic calibration. The results indicate that (i) under 1:1, the cost-optimal operating point aligns with the F1/MCC optimum; (ii) for 1:k cost regimes, the optimum shifts to lower thresholds, reducing FN at the expense of FP and increasing the alert rate; and (iii) isotonic calibration improves PR/ROC (ranking separation), but in the reported 1:5 experiment it did not reduce the final TEST-set operational cost relative to the uncalibrated run, despite using a separately selected post-calibration threshold. The evaluation includes PR/ROC curves, Cost–Threshold and Alert–Threshold sweeps, per-class recall, and permutation importance. In addition, the proposed approach is compared with unsupervised baselines (Isolation Forest, LOF). The results provide practical guidance for SOC decisions on how to choose thresholds consistent with alert budgets and risk profiles. In deployment, these operating points can be indexed to context (e.g., user type, service class, or time of day), yielding a small library of adaptive thresholds rather than one immutable global threshold. Full article

The growing flexibility of load dispatching in modern smart grids has exposed critical limitations in conventional capacity pricing mechanisms, which calculate charges based solely on monthly maximum demand without distinguishing when peak demand occurs. This approach fails to reflect the temporal value of capacity and provides insufficient incentives for demand-side optimization. To address these challenges, this paper proposes a time-of-use (TOU) capacity pricing method that integrates user load characteristics to enable more equitable cost allocation and optimized electricity consumption patterns. The methodology employs K-means clustering analysis of user load profiles to partition pricing periods, accurately capturing differential capacity value across temporal intervals. We validate the clustering approach through the elbow method and silhouette analysis, confirming k = 3 as optimal and demonstrating K-means superiority over hierarchical and density-based alternatives. This data-driven approach ensures that period delineation reflects actual consumption patterns of commercial and industrial users. A capacity cost allocation model is established using the Shapley value method, incorporating maximum demand in each designated period while maintaining revenue neutrality for the grid operator. The 80% load simultaneity factor is empirically validated using 12 months of Shanghai industrial data (May 2023–April 2024). A Stackelberg game-based pricing model for TOU capacity tariffs is developed, incentivizing users to deploy energy storage systems and optimize charging strategies. We prove game convergence theoretically and demonstrate equilibrium achievement within 3–5 iterations across diverse initialization scenarios. Energy storage capacity is optimized by sector (3.5–6.5% of peak demand) rather than uniformly, and realistic battery self-discharge rates (0.006%/hour) are incorporated. Case study analysis using real operational data from 11 commercial and industrial sub-sectors in Shanghai demonstrates effectiveness. Extended to 12 months with seasonal analysis, results show the proposed strategy reduces the peak-to-valley difference ratio by 2.4% [95% CI: 1.9%, 2.9%], p < 0.001; increases the system load factor by 1.3% [95% CI: 0.9%, 1.7%], p < 0.001; and achieves reductions in users’ total capacity costs of 3.6% [95% CI: −4.2%, −3.0%], p < 0.001. Comparative analysis shows the proposed method significantly outperforms simple TOU (improvement +1.2 pp) and peak-responsibility pricing (improvement +0.6 pp). Monte Carlo robustness analysis (1000 scenarios) confirms performance stability under demand uncertainty. This research provides theoretical foundations and practical methodologies for capacity cost allocation, offering valuable insights for policymakers and utilities seeking to enhance demand-side response mechanisms and improve power resource allocation efficiency. Full article

Determining the optimal harvest time is among the most critical economic decisions for peanut (Arachis hypogaea L.) growers, directly influencing yield, quality, and market value. Unlike many other crops, peanuts are indeterminate, continuing to flower and produce pods throughout their life cycle. As a result, pod development and maturation are asynchronous, making harvest timing particularly challenging. Conventional maturity estimation techniques, including the hull scrape method, pod blasting, and visual maturity profiling, are invasive, labor-intensive, time-consuming, and spatially limited. Moreover, differences in cultivar maturity rates and agroclimatic conditions exacerbate inconsistencies in maturity prediction. These challenges highlight the urgent need for scalable, objective, and data-driven methods to support growers in achieving optimal harvest outcomes. This review synthesizes the current understanding of peanut pod maturity and evaluates existing traditional and non-invasive approaches for maturity estimation. It aims to identify the limitations of conventional techniques and explore the integration of advanced sensing technologies, artificial intelligence (AI), and geospatial analytics to enhance precision and scalability in peanut maturity assessment and harvest decision-making. This review examines traditional destructive techniques such as the hull scrape method and pod blasting, followed by emerging non-invasive methods employing proximal and remote sensing platforms. Applications of vegetation indices, multispectral and hyperspectral imaging, and AI-based data analytics are discussed in the context of maturity prediction. Additionally, the potential of multimodal remote sensing data fusion and digital frameworks integrating spatial big data analytics, centralized data management, and cloud-based graphical interfaces is explored as a pathway toward end-to-end decision-support systems. Recent advances in non-invasive sensing and AI-assisted modeling have demonstrated significant improvements in scalability, precision, and automation compared with traditional manual approaches. However, their effectiveness remains constrained by the limited inclusion of agroclimatic, phenological, and cultivar-specific variables. Furthermore, the translation of model outputs into actionable, field-level harvest decisions is still underdeveloped, underscoring the need for integrated, user-centric digital infrastructure. Achieving a robust and transferable digital peanut maturity estimation system will require comprehensive ground-truth data across cultivars, regions, and growing seasons. Multidisciplinary collaborations among agronomists, data scientists, growers, and technology providers will be essential for developing practical, field-ready solutions. Integrating AI, multimodal sensing, and geospatial analytics holds immense potential to transform peanut maturity estimation. Such innovations promise to enhance harvest precision, economic returns, and sustainability while reducing manual effort and uncertainty, ultimately improving the efficiency and quality of life for peanut producers worldwide. Full article

Recommender systems are central to helping users navigate the rapidly expanding entertainment ecosystem, yet achieving strong personalization with limited feedback while maintaining interpretability remains difficult, particularly under cold-start conditions and heterogeneous item metadata. This work presents an end-to-end hybrid recommendation framework that unifies a Large Language Model (LLM) with Graph Attention Network (GAT)-based collaborative filtering to improve both ranking accuracy and explanation quality across movies, books, and music. LLM-based agents first transform raw metadata such as titles, genres, descriptions, and auxiliary attributes into semantically grounded user and item profiles, which are embedded and used as initial node features in a user–item bipartite graph processed by a GAT-based recommender. Model optimization relies on a hybrid objective combining Bayesian Personalized Ranking, cosine-similarity regularization, and robust negative sampling to better align semantic and collaborative signals. Finally, in the post-processing stage, an LLM-based agent re-ranks the GAT outputs using a proposed Hybrid Confidence-Weighted Binary Search Tree, and another LLM-based agent that produces natural-language justifications tailored to each user. Experiments on diverse benchmark datasets and extensive ablations demonstrate that the proposed methodology increases precision, recall, NDCG, and MAP across various values of K. In addition, the post processing step is especially effective in cold-start scenarios, consistently strengthening recommendation metrics and enhancing transparency at smaller values of K. Overall, integrating LLM-enriched representations with attention-based graph modeling enables more accurate and explainable entertainment recommendations. Full article

This paper presents the design and implementation of a low-profile remote monitoring and control system for water level management in storage tanks located in rural communities. The system was developed to ensure a reliable water supply, prevent spills, reduce electrical energy consumption, and mitigate theft and vandalism risks posed by a previously installed, highly exposed commercial system. The proposed system employs LoRa technology to transmit water level data from the storage tank to a receiver located 6 km from the water well. When the water level drops below a predefined threshold, the system transmits an activation signal through the LoRa network to start the well pump and trigger tank refilling. In addition, an SMS monitoring module enables users to remotely verify water level and pump operational status at any time. System notifications and operational data are automatically delivered via SMS to predefined phone numbers, enabling continuous supervision without requiring internet connectivity. The implementation of the proposed system thus provides an efficient and reliable solution for water resource management in rural environments, ensuring continuous water availability and preventing supply shortages. LoRa communication enables robust long-range data transmission, while SMS-based monitoring offers real-time operational awareness for end users. The system was validated through field testing in a pilot rural community, demonstrating operational robustness, improved water management efficiency, and measurable positive impacts on residents’ water service continuity. The low-profile physical design significantly reduced theft and vandalism incidents reported by the local water authority. Experimental results showed an average monthly reduction of 41.2% in electrical energy consumption while maintaining high system reliability, physical security, and real-time monitoring capability. Full article

Background: Dental professionals are routinely exposed to occupational noise from high-speed handpieces and ultrasonic scalers, with levels that can reach up to 90 dB(A). While such exposure is suspected to affect cochlear function, objective assessments in this population remain limited. This study investigated short-term changes in distortion product otoacoustic emissions (DPOAEs) as a biomarker of outer hair cell (OHC) function following routine clinical dental procedures. Methods: DPOAEs were recorded at frequencies from 1000 to 6000 Hz in young dental professionals with clinically normal hearing. Measurements were obtained at three time points: prior to dental procedures (baseline), immediately after exposure (3–5 min post-procedure), and at a 48-h (follow-up). Participants were stratified into two groups based on exposure profile: those exposed to occupational dental noise alone (Group 1) and those with concurrent use of personal listening devices (PLDs) in addition to occupational exposure (Group 2). Results: A significant reduction in DPOAE amplitudes was observed immediately following dental procedures in both groups, indicating an acute effect on OHC function. This reduction was more pronounced in Group 1 (PLD users) compared to Group 2 (occupational noise only). Amplitudes returned to baseline levels at the 48-h follow-up in both groups, confirming the transient nature of the effect. The absence of significant Frequency × Time interactions indicates that the observed amplitude reductions were broadly distributed across the tested frequency range rather than confined to a specific spectral region. Conclusions: Routine clinical dental procedures can induce transient, measurable changes in cochlear outer hair cell function, detectable by DPOAEs in young professionals with normal audiometric thresholds. Although these changes appear reversible within 48 h, the greater acute response observed in individuals with concurrent personal listening device use suggests that cumulative acoustic exposure may increase cochlear susceptibility. These findings support the integration of objective cochlear monitoring into occupational health surveillance for dental personnel. Full article

Risk-based management of water quality in drinking water supply systems requires decision-support tools that extend beyond parameter-level hazard assessment and enable prioritization at the level of physical system objects. In this context, hazard assessment refers specifically to drinking water quality parameters and their possible operational and health-related implications, particularly in facilities serving sensitive user groups. This study proposes a class-based extension of the FPOR (Fuzzy Priority of Objects at Risk) framework to support object-level operational prioritization under conditions of limited data availability. Hazard importance is adopted from prior hazard prioritization using the Fuzzy Priority Index (FPI), while priority premises (PP) are represented as object classes reflecting typical functional and operational characteristics. Class-based profiles of local hazard relevance and object vulnerability are defined using expert-informed fuzzy representations and aggregated into FPOR scores to produce a relative ranking of priority premises classes. The results demonstrate how hazard prioritization can be systematically propagated to object-level decision units without reliance on site-specific monitoring data. The proposed framework provides a transparent and scalable basis for early-stage risk-based planning and supports the operational implementation of object-oriented management strategies in drinking water systems, while maintaining a clear conceptual separation from health risk assessment addressed in subsequent studies. Full article

Environmental scientists are increasingly monitoring therapeutic drugs and their metabolites in water systems, requiring knowledge of human drug metabolism and excretion. Many published studies, however, rely on data from small-scale human metabolism trials, typically involving around six (healthy, young, male) volunteers. Their generalizability to real-world drug users may be limited, potentially biasing environmental monitoring efforts. Here, we leveraged untargeted LC-SWATH/MS pharmacometabolomics data from 283 potential living kidney donors and 688 kidney transplant recipients to characterize the 24 h urinary excretion profiles of two widely used diuretics frequently monitored in wastewater, hydrochlorothiazide and furosemide. Both are expected to be excreted largely unchanged, which our analyses confirmed. For hydrochlorothiazide, however, we also identified (using reference standards) the previously underreported transformation products chlorothiazide and salamide. These findings highlight the relevance and capability of using untargeted metabolomics data from human excreta to provide insights from large, real-world cohorts into which chemicals enter wastewater systems, with both drugs serving as exemplary case studies for analogous analyses of other drugs. In particular, the qualitative information obtained (e.g., accurate mass, retention time, fragment spectra) may inform targeted biomonitoring and highlight cases where consensus-based estimates of excreted drug or metabolite fractions are overestimated. Full article

Traditional cloud pricing models are allocation-centric, where users are charged based on reserved resources rather than workload energy consumption. However, modern AI workloads exhibit substantial and heterogeneous power behavior, limiting the effectiveness of such allocation-centric pricing. This paper presents a comprehensive experimental study of nine widely used workloads across 50 controlled configurations, including standalone and concurrent executions under varying resource partitions. Our results show that total system power is largely unaffected by how resources are divided among co-located workloads, except in cases of explicit resource under-provisioning or severe resource contention. Across 45 workload–core groups, 41 exhibit a coefficient of variation below 3% across different co-located workloads, demonstrating structural stability of workload-level power profiles under heterogeneous execution environments. In contrast, deployment choice (e.g., CPU versus GPU execution) can shift the same model into distinct power regimes. Based on measured power decomposition and scaling behavior, we derive an empirical categorization framework distinguishing GPU-dominant and CPU-dominant workloads, further characterized by utilization and memory dimensions. From an energy perspective, CPU utilization (for CPU-dominant workloads) and SM utilization (for GPU-dominant workloads) emerge as the primary determinants of power magnitude, while memory-related parameters contribute marginally to overall power. These findings provide empirical evidence that allocation-based pricing is a weak proxy for actual energy cost and motivate energy-aligned cloud management strategies grounded in workload power profiles. As our findings are derived from a controlled single-node experiment, evaluations under more realistic data center environments will be required for further generalization. Full article

This paper will present a constant-force vibration isolator (CFVI), in which the isolated load is supported by two pulley-roller mechanisms, while the dynamic stiffness is modified by a cam mechanism with the piecewise profile redefined by the user. As a result, this model can generate the constant force-displacement response within the working region, thereby obtaining quasi-zero stiffness in this range. Because of the piecewise configuration of the cam, the system motion governed by the piecewise dynamic equation under base motion excitation will be analyzed and established. The approximate solution of the piecewise dynamic equation is derived by using the average method, from which the relative amplitude–frequency relation and the absolute amplitude transmissibility of the CFVI will be obtained. The effects of the key working parameters involving the damping coefficient, critical position, and excited amplitude on the dynamic behavior and isolation effectiveness of the CFVI are considered through numerical simulations. The simulation result reveals that the dynamic response of the CFVI offers two branches: resonance and isolation. The former is significantly affected by the working parameters, whereas the latter is weakly influenced. Furthermore, the isolation effectiveness of the CFVI will be compared with that of its linear counterpart and the quasi-zero stiffness vibration isolation model using a semicircle cam (QZSI). The results demonstrate that the CFVI outperforms the other models for base motion excitations. Full article

Applications for machine learning (ML) and deep learning (DL) are constantly growing and have already been adopted in the field of particle measurement technology. Even though analytical (ultra-)centrifugation (AC/AUC) is a widely used technique for characterizing dispersed particle systems, ML and DL have not yet been applied in this area. Data evaluation and interpretation in AC/AUC can be challenging and often requires expert knowledge. DL models can help, but their development is limited by a lack of annotated training data. One solution is to generate and use synthetic data instead. In the first part of this study, a model was trained to synthesize data from experiments using a combination of Variational Autoencoder (VAE) and Generative Adversarial Networks (GANs). The results appear highly realistic. Novice users could distinguish real from synthetic samples with only 63% accuracy. Then, a classifier was trained on experimental AC data to categorize real-world examples based on their underlying separation kinetics, testing different DL architectures. After initial training, the models were further fine-tuned with synthetic AC data. ResNet34 models achieved the best performance with 94% accuracy, comparable to an AC expert (91%), while inexperienced users reached only 53%. In the second part of our study, a regression model was trained for the analysis of sedimentation coefficients. Therefore, various generative models were developed and evaluated for synthesizing AUC data based on numerically simulated sedimentation boundaries. The best results were achieved by combining VAE and GAN architectures with embedded physical constraints. However, the generative networks have so far led to additional smearing of the profiles, resulting in a broadening of the sedimentation coefficient distribution and indicating that further refinement is necessary. Full article

Background: This study aims to examine the level of awareness, attitudes (including stigma and discrimination), and behaviors related to tuberculosis among the population of the Republic of Kazakhstan to identify priorities for raising awareness and reducing stigma. Methods: The study interviewed 2400 people from six regions of Kazakhstan using stratified random sampling based on gender and age. Respondents were chosen from cities and villages, including RK citizens over 18 who could answer questions. Additionally, 400 people with HIV, 200 drug users, 200 internal migrants, and 500 health workers were interviewed. Recruitment was done through profile organizations and the snowball method, with all participants giving informed consent. Results: The study showed different levels of knowledge about tuberculosis (TB) in Kazakhstan. Radiography was the most commonly known detection method (71–91%). Awareness of sputum testing was highest among drug users (84%) and HIV patients (77%), but lower among internal migrants (39%). Internal migrants had the most uncertainty about TB tests (17%). Stigmatizing views of TB patients existed, with 28–38% believing most people reject them. Among healthcare workers, only 38. 8% correctly identified the G-Xpert test for TB and rifampicin resistance, and over one-third misunderstood the Mantoux test’s purpose. Conclusions: The findings show a need for focused educational efforts to boost TB awareness and lessen stigma, especially among internal migrants and the general public. Vulnerable groups, like PLHIV and PWUD, have higher awareness but still encounter major barriers. Improving healthcare workers’ knowledge about TB diagnostics is also crucial. Specific communication strategies and policies are needed to improve TB detection, reduce social stigma, and improve healthcare access for at-risk groups in Kazakhstan. Full article

Sport tourism has experienced significant growth within the tourism industry, driven by the increasing demand of special interest tourists to watch or participate in sports events with local sightseeing. However, the massive volume of available information related to sport events may cause challenges to existing recommendation systems, which struggle to provide tailored suggestions for these niche tourists. Therefore, this paper proposes a novel, context-aware recommender framework that utilises the ontology-driven approach with unsupervised machine learning techniques to deliver personalised event matches for running tourists. Using an ontology-driven approach, the framework establishes a knowledge base of user profiles and running events. Furthermore, K-modes clustering was also applied to categorise participants based on their event participation characteristics, while the Apriori algorithm was used to uncover hidden relationships influencing event selection. To ensure the statistical integrity of the discovered association rule, permutation testing was implemented to mitigate bias inherent in small sample sizes. By integrating refined association rules with Jena rules, the resulting prototype offers adaptive, personalised, and contextually relevant running event recommendations that evolve with shifting user preferences and trends. The effectiveness of the prototype is confirmed through rigorous validation and evaluation across various sport tourism scenarios. Full article

Urban blue-green spaces (UBGS) are crucial nature-based solutions for enhancing urban resilience and improving public health. This study examined the experiential relationships linking BGS use to human well-being among users of five urban parks in Delhi, India. Using an integrated experience-centered framework, we collected in-situ survey data (n = 411) to profile usage patterns, assess environmental quality, and quantify restorative outcomes grounded in Attention Restoration Theory (ART) and Stress Reduction Theory (SRT). Advanced analytical techniques, including ordinal logistic regression and interpretable machine learning (SHAP), were used to identify the key factors associated with user satisfaction. The results revealed that for these respondents, BGS appeared to function as an essential neighbourhood, with over 40% visiting three or more times per week. Although visual attractiveness was rated positively, deficits in noise buffering and amenities indicated a gap between aesthetic and functional qualities. Restorative benefits, including emotional calmness, mood refreshment, and fatigue recovery, were consistently reported among respondents. Analyses showed that embodied experiences, particularly post-visit relaxation and physical comfort, were more strongly associated with user satisfaction. SHAP interpretation highlighted seating adequacy, routine use, and thermal comfort as prominent contributors, suggesting somatic relief may be particularly salient. This study provides exploratory evidence from a Global South megacity and context-sensitive insights into how restorative processes operate under high-density urban conditions. The findings show that routine accessibility, basic amenities, and thermal comfort are central to the everyday functioning of blue-green spaces as urban infrastructure, underscoring the need for experience-responsive and equity-oriented urban greening policies in high-density cities. Full article

Approximately one quarter of the European Union’s (EU’s) CO₂ emissions originate from the transport sector, of which road transport, such as cars and heavy-duty vehicles, contributes roughly 72%. Moreover, according to the European Automobile Manufacturers’ Association, 92% of cars in the EU are internal combustion engine vehicles powered by fossil fuels. Therefore, boosting the adoption of Electric Vehicles (EVs) is considered one of the most prominent solutions for reducing GHG emissions and achieving the EU’s climate targets. To increase EV adoption and fulfil the demand of EV users, adequate EV Charging Stations (EVCSs) are required. Nevertheless, since most EVCSs are supplied by electricity grids that remain predominantly fossil fuel-based, their operation entails substantial indirect GHG emissions. A prominent approach to reducing grid-related emissions is integrating renewable energy sources (RESs) with EVCSs, thereby lowering emissions and alleviating grid stress. Although promising, the energy, economic, and environmental (3E) benefits of this integration remain insufficiently explored. Therefore, this study develops and applies a 3E optimisation framework to assess the feasibility and performance of RES-powered EVCS at NOVA University Lisbon (UNL). Data was collected from the UNL parking area, such as time of arrival, and time of departure. Also, a rule-based algorithm was developed to curate data and estimate the EVCS load profile. Furthermore, HOMER optimisation software was employed to evaluate four scenarios, including (i) an EVCS based on PV, Wind Turbine (WT), and the grid, (ii) an EVCS based on PV and the grid, (iii) an EVCS based on WT and the grid, and (iv) an EVCS based only on energy withdrawal from the grid (base scenario). Under the adopted techno-economic assumptions, in the most optimised scenario, economic and environmental analyses illustrate significant improvements over the base scenario: CO₂ emissions are five times lower, and cost of energy is significantly lower, resulting in significantly lower EV charging costs for users. The results demonstrate that, through developed feasibility studies, researchers, decision-makers, and stakeholders can reach better conclusions about EVCS planning and management. Full article