Search Results (109)

The lack of clinical data for chronic kidney disease (CKD) prediction frequently results in model overfitting and inadequate generalization to novel samples. This research mitigates this constraint by utilizing a Conditional Tabular Generative Adversarial Network (CTGAN) to enhance a constrained CKD dataset sourced from the University of California, Irvine (UCI) Machine Learning Repository. The CTGAN model was trained to produce realistic synthetic samples that preserve the statistical and feature distributions of the original dataset. Multiple machine learning models, such as AdaBoost, Random Forest, Gradient Boosting, and K-Nearest Neighbors (KNN), were assessed on both the original and enhanced datasets with incrementally increasing degrees of synthetic data dilution. AdaBoost attained 100% accuracy on the original dataset, signifying considerable overfitting; however, the model exhibited enhanced generalization and stability with the CTGAN-augmented data. The occurrence of 100% test accuracy in several models should not be interpreted as realistic clinical performance. Instead, it reflects the limited size, clean structure, and highly separable feature distributions of the UCI CKD dataset. Similar behavior has been reported in multiple previous studies using this dataset. Such perfect accuracy is a strong indication of overfitting and limited generalizability, rather than feature or label leakage. This observation directly motivates the need for controlled data augmentation to introduce variability and improve model robustness. The dataset with the greatest dilution, comprising 2000 synthetic cases, attained a test accuracy of 95.27% utilizing a stochastic gradient boosting approach. Ensemble learning techniques, particularly gradient boosting and random forest, regularly surpassed conventional models like KNN in terms of predicted accuracy and resilience. The results demonstrate that CTGAN-based data augmentation introduces critical variability, diminishes model bias, and serves as an effective regularization technique. This method provides a viable alternative for reducing overfitting and improving predictive modeling accuracy in data-deficient medical fields, such as chronic kidney disease diagnosis. Full article

Speech is one of the earliest-affected modalities in Parkinson’s disease (PD). For more reliable PD evaluation, speech-based telediagnosis studies often use multiple samples from the same subject to capture variability in speech recordings. However, many existing studies split samples—rather than subjects—between training and testing, creating a biased experimental setup that allows data (samples) from the same subject to appear in both sets. This raises concerns for reliable PD evaluation due to data leakage, which results in over-optimistic performance (often close to 100%). In addition, detecting subtle vocal impairments from speech recordings using multiple feature extraction techniques often increases data dimensionality, although only some features are discriminative while others are redundant or non-informative. To address this and build a reliable speech-based PD telediagnosis system, the key contributions of this work are two-fold: (1) a uniform (fair) experimental setup employing subject-wise symmetric (stratified) splitting in 5-fold cross-validation to ensure better generalization in PD prediction, and (2) a novel hybrid data complexity-aware (HDC) feature selection method that improves class separability. This work further contributes to the research community by releasing a publicly accessible five-fold benchmark version of the Parkinson’s speech dataset for consistent and reproducible evaluation. The proposed HDC method analyzes multiple aspects of class separability to select discriminative features, resulting in reduced data complexity in the feature space. In particular, it uses data complexity measures (F4, F1, F3) to assess minimal feature overlap and ReliefF to evaluate the separation of borderline points. Experimental results show that the top-50 discriminative features selected by the proposed HDC outperform existing feature selection algorithms on five out of six classifiers, achieving the highest performance with 0.86 accuracy, 0.70 G-mean, 0.91 F1-score, and 0.58 MCC using an SVM (RBF) classifier. Full article

Objectives: The aim of this in vitro study was to evaluate the accuracy of intraoral impressions obtained using the Trios 3Shape^® (3Shape Trios, Copenaghen, Denmark) and Carestream CS 3600™ (Carestream Dental, Stuttgart, Germany) scanners, compared with traditional polyvinyl siloxane (PVS) impressions. A laboratory scanner served as the gold standard. Materials and Methods: The study was based on 3D-printed master models derived from partially edentulous clinical cases previously treated at our department (2017–2022). All cases required at least two implants. Data analysis was performed using one-way ANOVA and two-sample Z-tests (α = 0.05) to compare mean deviations and variability. Results: All techniques demonstrated high accuracy, with deviations from the reference point below 30 μm. The digital intraoral scanners (Trios 3Shape^® and Carestream CS 3600^®) showed superior accuracy compared with PVS analog impressions, with no statistically significant difference between the two IOS systems. Conclusions: Within the limitations of this in vitro study, both IOS systems and PVS analog impressions achieved clinically acceptable accuracy. Digital systems exhibited improved performance in terms of mean deviation and consistency. The higher accuracy and consistency of digital impressions may translate into improved clinical efficiency and prosthetic fit in implant rehabilitations. From a clinical perspective, these in vitro findings suggest that digital impressions may enhance prosthetic fit and workflow efficiency, though further in vivo validation is required. Clinical significance: This study supports the reliability of intraoral scanning compared with conventional impressions in implant-supported rehabilitations. By demonstrating high intrinsic accuracy, these findings contribute to optimizing digital workflows in implant dentistry and reinforce the potential of intraoral scanning in static computer-guided, flapless implant surgery. Trial registration: Ethical approval and trial registration were not applicable to the present in vitro investigation, as no patients were directly involved in the experimental phase. The digital data used to generate the laboratory master models originated from a separate clinical study conducted at ASST Santi Paolo e Carlo, Milan (Ethics Committee approval no. 1361, 12 July 2017; ClinicalTrials.gov registration, Unique Protocol ID 1361). Full article

This paper analyzes a finite-capacity $GI/M/2/N$ queue with two heterogeneous servers operating under a multiple working-vacation policy, Bernoulli feedback, and customer impatience. Using the supplementary-variable technique in tandem with a tailored recursive scheme, we derive the stationary distributions of the system size as observed at pre-arrival instants and at arbitrary epochs. From these, we obtain explicit expressions for key performance metrics, including blocking probability, average reneging rate, mean queue length, mean sojourn time, throughput, and server utilizations. We then embed these metrics in an economic cost function and determine service-rate settings that minimize the total expected cost via the Bat Algorithm. Numerical experiments implemented in R validate the analysis and quantify the managerial impact of the vacation, feedback, and impatience parameters through sensitivity studies. The framework accommodates general renewal arrivals ($GI$), thereby extending classical ($M/M/2/N$) results to more realistic input processes while preserving computational tractability. Beyond methodological interest, the results yield actionable design guidance: (i) they separate Palm and time-stationary viewpoints cleanly under non-Poisson input, (ii) they retain heterogeneity throughout all formulas, and (iii) they provide a cost–optimization pipeline that can be deployed with routine numerical effort. Methodologically, we (i) characterize the generator of the augmented piecewise–deterministic Markov process and prove the existence/uniqueness of the stationary law on the finite state space, (ii) derive an explicit Palm–time conversion formula valid for non-Poisson input, (iii) show that the boundary-value recursion for the Laplace–Stieltjes transforms runs in linear time $\mathcal{O}\left(N\right)$ and is numerically stable, and (iv) provide influence-function (IPA) sensitivities of performance metrics with respect to $({\mu }_1,{\mu }_2,\nu ,\alpha ,\varphi ,\beta )$. Full article

This paper analyzes a finite-capacity Markovian queueing system with two customer types, each assigned to a separate buffer, and a single alternating server whose service priority is dynamically controlled by a queue-length-based threshold policy. The arrivals of both customer types follow independent Poisson processes, and the service times are generally distributed. The server alternates between the two buffers, granting service priority to buffer 1 when its queue length exceeds a specified threshold immediately after service completion; otherwise, buffer 2 receives priority. Once buffer 1 gains priority, it retains it until it becomes empty, with all priority transitions occurring non-preemptively. We develop an embedded Markov chain model to derive the joint queue length distribution at departure epochs and employ supplementary variable techniques to analyze the system performance at arbitrary times. This study provides explicit expressions for key performance measures, including blocking probabilities and average queue lengths, and demonstrates the effectiveness of threshold-based control in balancing service quality between customer classes. Numerical examples illustrate the impact of buffer capacities and threshold settings on system performance and offer practical insights into the design of adaptive scheduling policies in telecommunications, cloud computing, and healthcare systems. Full article

Background/Objectives: The aim was to provide a comprehensive, systematic review on the Lateral Extra-articular Tenodesis (LET) methods used in anterior cruciate ligament (ACL) reconstruction in the light of recent data. Methods: To identify all of the essential studies that reported relevant data concerning primary outcomes: indications for surgery, surgical technique, graft type, fixation method, and tibial fixation location, an extensive search of the major and significant electronic databases (PubMed, Cochrane Central, ScienceDirect, Web of Science, Embase) was performed by three independent authors. A systematic investigation was conducted in November 2023, with no limits regarding the year of publication. After the database search, three independent reviewers screened all the papers, which followed strictly the inclusion and exclusion criteria, identifying a title, abstract, and full text concerning LET, surgical technique, femoral attachment, tibial attachment, graft type, fixation method, knee angle during fixation, and graft tension at fixation in ACL reconstruction. A systematic review of the collected literature was carried out according to the guidelines of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Study quality was assessed using the Cochrane Risk of Bias Tool. Results: Of the 35 papers reviewed, seven surgical techniques of LET differing in the way the procedure was performed were separated. The majority of papers were from Italy (n = 11), USA (n = 3), France (n = 3), and Canada (n = 3). The number of total participants across all studies was 6253. The majority of studies (17 papers) used the Lemaire modified procedure, and 10 papers used the MacIntosh technique modified by the Coker–Arnold approach. Most of the papers mentioned fixation location on the lateral distal part of the femur including six articles referring directly to lateral femoral epicondyle. Most authors (25 papers) defined tibial attachment as Gerdy’s tubercle. The most common graft was the iliotibial band and fixation method was sutures. The types of fixation in the surgical techniques of the collected papers were Sutures, Staples, Anchor, Interference screw, K-wire, Bioabsorbable Screw and Titanium Screw with a serrated polyethylene washer. Conclusions: Despite variability in technique, the Lemaire-modified procedure emerged as the preferred approach for Lateral Extra-articular Tenodesis, suggesting a general consensus around its reliability and reproducibility in clinical practice. The frequent use of the iliotibial band as graft material reflects its accessibility and suitability for reinforcing anterolateral stability. Similarly, the consistent use of sutures and fixation at Gerdy’s tubercle may indicate a favorable balance between technical ease and biomechanical strength. The variability in femoral fixation points—either at the lateral femoral condyle or epicondyle—highlights the ongoing debate or surgeon preference, underscoring the need for further comparative studies to establish optimal fixation strategy. Collectively, these patterns may help guide surgical decision-making, particularly when tailoring procedures to individual patient anatomy or surgical expertise. Full article

Early detection of physiological dysregulation is critical for timely intervention and effective health management. Traditional monitoring systems often rely on labeled data and predefined thresholds, limiting their adaptability and generalization to unseen conditions. To address this, we propose a framework for label-free classification of physiological states using Heart Rate Variability (HRV), combined with unsupervised machine learning techniques. This approach is particularly valuable when annotated datasets are scarce or unavailable—as is often the case in real-world wearable and IoT-based health monitoring. In this study, data were collected from participants under controlled conditions representing rest, stress, and physical exertion. Core HRV parameters such as the SDNN (Standard Deviation of all Normal-to-Normal intervals), RMSSD (Root Mean Square of the Successive Differences), DFA (Detrended Fluctuation Analysis) were extracted. Principal Component Analysis was applied for dimensionality reduction. K-Means, hierarchical clustering, and Density-based spatial clustering of applications with noise (DBSCAN) were used to uncover natural groupings within the data. DBSCAN identified outliers associated with atypical responses, suggesting potential for early anomaly detection. The combination of HRV descriptors enabled unsupervised classification with over 90% consistency between clusters and physiological conditions. The proposed approach successfully differentiated the three physiological conditions based on HRV and fractal features, with a clear separation between clusters in terms of DFA α1, α2, LF/HF, and RMSSD (with high agreement to physiological labels (Purity ≈ 0.93; ARI = 0.89; NMI = 0.92)). Furthermore, DBSCAN identified three outliers with atypical autonomic profiles, highlighting the potential of the method for early warning detection in real-time monitoring systems. Full article

Background/Objectives: Inter-limb asymmetry of a given variable for vertical jumps is commonly assessed in both healthy individuals and those undergoing rehabilitation post-injury. The aim of this study was to compare the asymmetry index between the take-off and landing of a single-leg counter movement jump (CMJ), as well as between females and males. Methods: Twenty-three healthy females (age: 21.5 ± 1.6 years) and twenty-three healthy males (age: 21.1 ± 1.8 years) participated in this study. The assessment of two asymmetry indices (AI1 and AI2) was conducted for the peak vertical ground reaction force (PVGRF) and maximum power (MP) during single-leg CMJ take-offs and landings performed on the force platform. Results: The analysis showed significant main effects (p < 0.001) for the phase factor (only AI2) and for the gender factor (only AI1). Moreover, there was a non-significant interaction effect between the phase factor and gender factor (p = 0.476). Pairwise comparisons revealed significant differences in the values of (1) AI2 between the take-off and landing (p < 0.001) and (2) AI1 between females and males (p < 0.001). Conclusions: Findings showed significant effects of the phase factor (only for AI2) and gender factor (only for AI1) on the magnitude of inter-limb asymmetry during single-leg CMJs. Furthermore, this study reported the significantly higher asymmetry of the PVGRF and MP for landing than take-off, which may result from difficulties in controlling the jumper’s landing technique on one foot at higher velocity. In addition, the assessment of asymmetry for single-leg CMJs using AI1 should be performed separately for females and males, as opposed to AI2. Participants of both genders generally demonstrated a higher AI level for the power than for the force. Full article

Biomass and other solid wastes create potential environmental and health hazards in our modern society. Conversion of the wastes into energy presents a promising avenue for sustainable energy generation. However, the feasibility of the approach is limited by the challenges in material handling because of the special properties of the materials. Despite their critical importance, the complexities of material handling often evade scrutiny until operational implementation. This paper highlights the challenges inherent in standard solid material-handling processes, preceded by a concise review of common solid waste typologies and their physical properties, particularly those related to biomass and biowastes. It delves into the complexities of material flow, storage, compaction, agglomeration, separation, transport, and hazard management. Specialised characterisation techniques essential for informed process design are also discussed to mitigate operational risks. In conclusion, this paper emphasises the necessity of a tailored framework before the establishment of any further conversion processes. Given the heterogeneous nature of biomaterials, material-handling equipment must demonstrate adaptability to accommodate the substantial variability in material properties in large-scale production. This approach aims to enhance feasibility and efficacy of any energy conversion initiatives by using biomass or other solid wastes, thereby advancing sustainable resource utilisation and environmental stewardship. Full article

Quantum memory is essential for the prolonged storage and retrieval of quantum information. Nevertheless, no current studies have focused on the creation of effective quantum memory for continuous variables while accounting for the decoherence rate. This work presents an effective continuous-variable quantum key distribution method with parameter optimization utilizing the Elitist Elk Herd Random Immigrants Optimizer (2E-HRIO) technique. At the outset of transmission, the quantum device undergoes initialization and authentication via Compressed Hash-based Message Authentication Code with Encoded Post-Quantum Hash (CHMAC-EPQH). The settings are subsequently optimized from the authenticated device via 2E-HRIO, which mitigates the effects of decoherence by adaptively tuning system parameters. Subsequently, quantum bits are produced from the verified device, and pilot insertion is executed within the quantum bits. The pilot-inserted signal is thereafter subjected to pulse shaping using a Gaussian filter. The pulse-shaped signal undergoes modulation. Authenticated post-modulation, the prediction of link failure is conducted through an authenticated channel using Radial Density-Based Spatial Clustering of Applications with Noise. Subsequently, transmission occurs via a non-failure connection. The receiver performs channel equalization on the received signal with Recursive Regularized Least Mean Squares. Subsequently, a dataset for side-channel attack authentication is gathered and preprocessed, followed by feature extraction and classification using Adaptive Depthwise Separable Convolutional Neural Networks (ADS-CNNs), which enhances security against side-channel attacks. The quantum state is evaluated based on the signal received, and raw data are collected. Thereafter, a connection is established between the transmitter and receiver. Both the transmitter and receiver perform the scanning process. Thereafter, the calculation and correction of the error rate are performed based on the sifting results. Ultimately, privacy amplification and key authentication are performed using the repaired key via B-CHMAC-EPQH. The proposed system demonstrated improved resistance to decoherence and side-channel attacks, while achieving a reconciliation efficiency above 90% and increased key generation rate. Full article

The Kadomtsev–Petviashvili (KP) equation serves as a powerful model for investigating various nonlinear wave phenomena in fluid dynamics, plasma physics, optics, and engineering. In this paper, by combining the method of separation of variables with the modified generalized exponential rational function method (mGERFM), abundant explicit exact non-traveling wave solutions for a (3+1)-dimensional generalized form of the equation are constructed. The proposed method utilizes a transformation approach to reduce the original equation to a simpler form. The derived solutions include several arbitrary functions, which enable the construction of a wide variety of exact solutions to the model. These solutions are expressed through diverse functional forms, such as exponential, trigonometric, and Jacobi elliptic functions. To the best of the author’s knowledge, these results are novel and have not been documented in prior studies. This study enhances understanding of wave dynamics in the equation and provides a practical method applicable to other related equations. Full article

This numerical study addressed the multi-objective optimization of a rocket-type Pulse Detonation Engine nozzle. The Pulse Detonation Engine consisted of a constant length, constant diameter cylindrical section plus a nozzle that could be either convergent, divergent, or convergent–divergent. The space of five design variables contained: equivalence ratio of the H2-Air mixture, convergent contraction ratio, divergent expansion ratio, dimensionless nozzle length, and convergent to divergent length ratio. The unsteady Euler-type numerical solver was quasi-one-dimensional with variable cross-sectional area. Chemistry was simulated by means of a one-step global reaction. The solver was used to generate three coarse five-dimensional data tensors that contained: specific impulse based on fuel, total impulse, and nozzle surface area, for each configuration. The tensors were decomposed using the High Order singular Value Decomposition technique. The eigenvectors of the decompositions were used to generate continuous descriptions of the data tensors. A genetic algorithm plus a Gradient Method optimization algorithm acted on the densified data tensors. Five different objective functions were considered that involved specific impulse based on fuel, total impulse, and nozzle surface area either separately or in doublets/triplets. The results obtained were discussed, both qualitatively and quantitatively, in terms of the different objective functions. Design guidelines were provided that could be of interest in the growing area of Pulse Detonation Engine engineering applications. Full article

This paper focuses on exploring the variable throat-assisted restart method for high-Mach-number inlets. A two-dimensional adjustable throat hypersonic inlet was designed, and unsteady numerical simulations were carried out on its restart process, which was triggered by unstart induced by excessive back pressure and assisted by throat adjustment. The Chimera grid technique was used for grid generation, and the simulations were performed on the ARI_CFD platform. Results show that during the throat adjustment restart process, different flow states emerged with an increase in adjustment height. Specifically, when the adjustment height was too low, an unstarted flow state existed; within a specific height range (with lower and upper critical heights of 1.190 and 1.196, respectively, in this study), a fully restarted flow state occurred; and when the height was too high, an off-design flow state induced by the separation region in the internal contraction section occurred. The geometric adjustment time and throat adjustment angle also had a significant impact on the restart process. Shorter adjustment times and larger adjustment angles expanded the adjustment interval for full restart, as the rotation of the isolator helps reduce the resistance of the separation bubble’s downstream movement on the compression surface, thereby facilitating the full restart of the inlet. Full article

The integration of renewable energy sources, such as wind power, into the electrical grid is essential for the development of sustainable energy systems. Doubly fed induction generators (DFIGs) have been significantly utilized in wind energy conversion systems (WECSs) because of their efficient power generation and variable speed operation. However, optimizing wind power extraction at variable wind speeds remains a major challenge. To address this, an artificial neural network (ANN) is adopted to predict the optimal shaft speed, ensuring maximum power point tracking (MPPT) for a wind energy-driven DFIG connected to a matrix converter (MC). The DFIG is controlled via field-oriented control (FOC), which allows independent power output regulation and separately controls the stator active and reactive power components. Through its compact design, bidirectional power flow, and enhanced harmonic performance, the MC, which is controlled by the simplified Venturini modulation technique, improves the efficiency and dependability of the system. Simulation outcomes confirm that the ANN-based MPPT enhances the power extraction efficiency and improves the system performance. This study shows how wind energy systems can be optimized for smart grids by integrating advanced control techniques like FOC and simplified Venturini modulation with intelligent algorithms like ANN. Full article

Melt crystallization is a promising separation technique that produces ultra-high-purity products while consuming less energy and generating lower CO₂ emissions than conventional methods. However, accurately modeling melt crystallization is challenging due to significant non-idealities and complex phase equilibria in multicomponent systems. This study develops and evaluates two neural network-based surrogate models for acrylic acid melt crystallization: a stand-alone (black-box) model and a thermodynamically guided (hybrid) model. The hybrid model incorporates UNIQUAC-based solid–liquid equilibrium constraints into the learning process. This framework combines first-principles thermodynamic knowledge—particularly activity coefficient calculations and mass balance equations—with multi-output regression to predict key process variables. Both models are rigorously tested for interpolation and extrapolation, with the hybrid approach demonstrating superior accuracy even under operating conditions significantly outside the training domain. Further analysis reveals the critical importance of accurate solid–liquid equilibrium (SLE) data for thermodynamic parameterization. A final case study illustrates how the hybrid approach can quickly explore feasible operating regions while adhering to strict product purity targets. These findings confirm that integrating mechanistic constraints into neural networks significantly enhances predictive accuracy, especially when processes deviate from nominal conditions, providing a practical framework for designing and optimizing industrial-scale melt crystallization processes. Full article