Search Results (778)

Background: Differentiating Parkinson’s disease (PD) from essential tremor (ET) is often challenging, especially in early or atypical cases. Dopamine transporter (DAT) single-photon emission computed tomography (SPECT) with ¹²³I-Ioflupane supports diagnosis, and semi-quantitative tools such as DaTQUANT^® and BasGanV2™ provide objective measures. This study compared their diagnostic performance when integrated with supervised machine learning. Methods: We retrospectively analysed ¹²³I-Ioflupane SPECT scans from 169 patients (133 PD, 36 ET). Semi-quantitative analysis was performed using DaTQUANT^® v2.0 and BasGanV2™ v.2. Classification tree (ClT), k-nearest neighbour (k-NN), and support vector machine (SVM) models were trained and validated with stratified shuffle split (250 iterations). Diagnostic accuracy was compared between the two software packages. Results: All classifiers reliably distinguished PD from ET. DaTQUANT^® consistently achieved higher accuracy than BasGanV2™: 93.8%, 93.2%, and 94.5% for ClT, k-NN, and SVM, respectively, versus 90.9%, 91.7%, and 91.9% for BasGanV2™ (p < 0.001). Sensitivity and specificity were also consistently higher for DaTQUANT^® than BasGanV2. Class imbalance (PD > ET) was addressed using Synthetic Minority Over-sampling Technique (SMOTE). Conclusions: Machine learning analysis of ¹²³I-Ioflupane SPECT enhances differentiation between PD and ET. DaTQUANT^® outperformed BasGanV2™, suggesting greater suitability for AI-driven decision support. These findings support the integration of semi-quantitative and AI-based approaches into clinical workflows and highlight the need for harmonised methodologies in movement disorder imaging. Full article

Traditional machine learning approaches for 5G network management relieve data from operational networks, which are often noisy and confounded, making it difficult to identify key influencing factors. This research addresses the critical gap between correlation-based prediction and interpretable, data-driven explanation. To this end, a software-defined standalone 5G architecture was developed using srsRAN and Open5GS to support multi-user scenarios. A multi-user environment was then simulated with GNU Radio, from which the initial dataset was collected. This dataset was further generated using a Conditional Tabular Generative Adversarial Network (CTGAN) to improve diversity and balance. Several machine learning models, including Linear Regression, Decision Tree, Random Forest, Gradient Boosting, and XGBoost, were trained and evaluated for predicting network performance. Among them, XGBoost achieved the best results, with an R² score of 0.998. To interpret the model, we conducted a SHAP (SHapley Additive exPlanations) analysis, which revealed that the download-to-upload bitrate ratio (dl_ul_ratio) and upload bitrate (brate_ul) were the most influential features. By leveraging a controlled experimental 5G environment, this study demonstrates how machine learning can move beyond predictive accuracy to uncover the fundamental principles governing 5G system performance, providing a robust foundation for future network optimization. Full article

Smart Mobile Devices (SMD)—including hardware devices, such as smartphones, tablets, and wearables; the software systems that animate them; and the data-communication infrastructure that connects them—pose increasing sustainability challenges due to their short lifespans, high resource demands, and growing e-waste. While Sustainable Product–Service Systems (S.PSS) have been applied in various sectors to support environmental goals, limited research has addressed their application in the context of SMD. This study aims to explore how S.PSS can be tailored to support sustainability in the SMD sector. For that, it combines a literature review with a multiple-case analysis of seventeen commercial offerings to develop a conceptual framework refined through six expert interviews. Cases were coded using the classical PSS typology and other sector-specific criteria and subsequently clustered in a polarity diagram to identify designable patterns, underpinning the conceptual framework. The study contributes an S.PSS-SMD framework comprising a sector-tailored classification and sixteen archetypal models, operationalized in an archetypal map with potential opportunities. Theoretically, the study offers a sector-grounded operationalization that extends S.PSS design theory to digital product–service ecosystems. It provides a strategic decision aid for designing business models, service bundles, stakeholder roles, and lifecycle responsibilities to pursue win–win environmental and economic sustainability. Full article

This paper presents three simple and efficient advanced optimization algorithms, namely the best–worst–random (BWR), best–mean–random (BMR), and best–mean–worst–random (BMWR) algorithms designed to address unconstrained and constrained single- and multi-objective optimization tasks of the metal casting processes. The effectiveness of the algorithms is demonstrated through real case studies, including (i) optimization of a lost foam casting process for producing a fifth wheel coupling shell from EN-GJS-400-18 ductile iron, (ii) optimization of process parameters of die casting of A360 Al-alloy, (iii) optimization of wear rate in AA7178 alloy reinforced with nano-SiC particles fabricated via the stir-casting process, (iv) two-objectives optimization of a low-pressure casting process using a sand mold for producing A356 engine block, and (v) four-objectives optimization of a squeeze casting process for LM20 material. Results demonstrate that the proposed algorithms consistently achieve faster convergence, superior solution quality, and reduced function evaluations compared to simulation software (ProCAST, CAE, and FEA) and established metaheuristics (ABC, Rao-1, PSO, NSGA-II, and GA). For single-objective problems, BWR, BMR, and BMWR yield nearly identical solutions, whereas in multi-objective tasks, their behaviors diverge, offering well-distributed Pareto fronts and improved convergence. These findings establish BWR, BMR, and BMWR as efficient and robust optimizers, positioning them as promising decision support tools for industrial metal casting. Full article

Software development projects are highly susceptible to risks during the design phase, which plays a crucial role in shaping the architecture, functionality, and quality of the final product. Decisions made during the design stage significantly affect the outcomes of the subsequent phases, including coding, testing, deployment, and maintenance. However, the complexities and uncertainties inherent in the design phase are often inadequately addressed by traditional risk management tools as they rely on deterministic models that oversimplify interdependent risks. This research introduces a fuzzy logic-based risk assessment model tailored specifically for the design phase of software development projects. The proposed fuzzy model, unlike the existing state-of-the-art models, regards the iterative nature of the design phase, the interaction between diverse stakeholders, and the potential inconsistencies that may arise between the initial and final version of the software design. More specifically, it develops a customized fuzzy model that incorporates design-specific risk factors such as evolving architectural requirements, technical feasibility concerns, and stakeholder misalignment. Finally, it integrates expert-driven rule definitions to enhance model accuracy and real-world applicability, ensuring that risk assessments reflect actual challenges faced by software design teams. Simulations conducted across diverse real-world scenarios demonstrate the model’s robustness in predicting risk levels and supporting mitigation strategies. The simulation results confirm that the proposed fuzzy logic model outperforms conventional approaches by offering greater flexibility and adaptability in managing design-phase risks, assisting project managers in prioritizing mitigation efforts more effectively to improve project outcomes. Full article

To carry out data analysis, it is necessary to implement a model that guides the process in an orderly and sequential manner, with the aim of maintaining control over software development and its documentation. One of the most widely used tools in the field of data analysis is the Cross-Industry Standard Process for Data Mining (CRISP-DM), which serves as a reference framework for data mining, allowing the identification of patterns and, based on them, supporting informed decision-making. Another tool used for pattern identification and the study of relationships within systems is network analysis (NA), which makes it possible to explore how different components are interconnected. The integration of these tools can be justified and developed under the principles of Situational Method Engineering (SME), which allows for the adaptation and customization of existing methods according to the specific needs of a problem or context. Through SME, it is possible to determine which components of CRISP-DM need to be adjusted to efficiently incorporate NA, ensuring that this integration aligns with the project’s objectives in a structured and effective manner. The proposed methodological process was applied in a real working group, which allowed its functionality to be validated, each phase to be documented, and concrete outputs to be generated, demonstrating its usefulness for the development of analytical projects. Full article

Autonomous vehicles (AVs) are increasingly becoming a reality, enabled by advances in sensing technologies, intelligent control systems, and real-time data processing. For AVs to operate safely and effectively, they must maintain a reliable perception of their surroundings and internal state. However, sensor failures, whether due to noise, malfunction, or degradation, can compromise this perception and lead to incorrect localization or unsafe decisions by the autonomous control system. While modern AV systems often combine data from multiple sensors to mitigate such risks through sensor fusion techniques (e.g., Kalman filtering), the extent to which these systems remain resilient under faulty conditions remains an open question. This work presents a simulation-based fault injection framework to assess the impact of sensor failures on AVs’ behavior. The framework enables structured testing of autonomous driving software under controlled fault conditions, allowing researchers to observe how specific sensor failures affect system performance. To demonstrate its applicability, an experimental campaign was conducted using the CARLA simulator integrated with the Autoware autonomous driving stack. A multi-segment urban driving scenario was executed using a modified version of CARLA’s Scenario Runner to support Autoware-based evaluations. Faults were injected simulating LiDAR, GNSS, and IMU sensor failures in different route scenarios. The fault types considered in this study include silent sensor failures and severe noise. The results obtained by emulating sensor failures in our chosen system under test, Autoware, show that faults in LiDAR and IMU gyroscope have the most critical impact, often leading to erratic motion and collisions. In contrast, faults in GNSS and IMU accelerometers were well tolerated. This demonstrates the ability of the framework to investigate the fault-tolerance of AVs in the presence of critical sensor failures. Full article

The U.S. Department of the Interior, Bureau of Reclamation (Reclamation) supports water temperature management for fishery species protection in downstream river reaches below Central Valley Project (CVP) reservoirs in the Sacramento, American, and Stanislaus River systems. The Water Temperature Modeling Platform (WTMP) Project was initiated to modernize and enhance modeling capabilities to predict summer–fall water temperature through reservoir cold water pool management using temperature control facilities designed for temperature management. The WTMP supports forecasts, historical analyses, and long-term planning efforts and advances previous modeling approaches by using an integrated modeling platform. This platform includes a data management system that acquires real-time data, provides quality assurance methods, and yields model-ready data for simulations; a modeling framework that manages model input file construction for multiple models, controls selected model simulation for reservoir and/or river reaches, and manages model output; and an automated reporting feature providing efficient and comprehensive reporting of tabular and graphical output for assessment and analysis by technical teams and decision-makers. The WTMP takes advantage of technological advancements in simulation models, available software, and databases to support Reclamation’s short- and long-term water temperature management needs. The platform is also adaptive for future integration with new or improved models and tools. Full article

The development of information technology has transformed various aspects of life, including education, by making it more flexible, interactive, and accessible. One platform that plays an important role in this transformation is YouTube, a video sharing platform that allows users to upload, watch, share, and comment on videos online. YouTube is not only a medium of entertainment, but also a significant source of additional learning, especially in higher education such as the Informatics Engineering Department. The platform provides various learning materials, such as programming tutorials, computer network concepts, and software development, which can be accessed anytime and anywhere. YouTube’s advantages lie in its accessibility and the ability for users to repeat videos, making it easier to understand complex material. However, using YouTube as a learning resource also has its challenges, such as the difficulty in finding relevant and high-quality content, as well as the variety of academic standards used in the delivery of the material. Therefore, this study aims to evaluate the effectiveness of YouTube as an additional learning media and provide recommendations for the best channels for Informatics Engineering students. Factors, such as the number of views, the number of subscribers, the frequency of uploading new content, and the background of the content creator, are considered in channel selection. The Weighted Product (WP) method in the Decision Support System (SPK) is used to evaluate the effectiveness of YouTube based on predetermined standards. The research results are expected to provide recommendations for the most relevant and high-quality YouTube channels so as to improve students’ understanding of educational materials and optimize the use of digital learning resources. Full article

Desert regions face unique challenges under climate change, including the emerging phenomenon of sand dune expansion. This research investigates aeolian sand transport in the Seqale watershed (eastern Iran) using geostatistical and machine learning methods to model and forecast dune spread, aiming to reduce the loss of sustainability in these valuable landscapes. Predictor variables (altitude, slope, climate, land use, etc.) and wind erosion occurrence were analyzed using classification algorithms (decision tree, random forest, etc.) and bivariate methods (information value, area density) in R software 4.5.0. Risk zoning maps were created and evaluated by combining these approaches. Results indicate a higher sand dune presence in regions with specific altitude (1200–1400 m), gentle northeast-facing slopes (2–5 degrees), moderate rainfall (250–500 mm), high evaporation (2500–3000 mm), outside flood plains, and far from roads (>3000 m) and water channels (>500 m). Dune expansion maps based on density area and information value methods showed substantial areas classified as high to very high movement risk. Machine learning analysis identified the Support Vector Machine (SVM) algorithm (AUC = 0.94) as the most effective for classifying sand dune zones. The study concludes that spatial forecasts, combined with tailored physical and biological measures, are essential for effective sand dune management in the region. Full article

Background/Objective: This study investigates the implementation and evolution of intelligent medical question-answering (QA) systems in healthcare to enhance service efficiency and quality. Methods: Through an integrated literature review and bibliometric analysis using CiteSpace 6.3.R1(64-bit) Basic software, we systematically evaluated core concepts, frameworks, and applications within medical QA systems, analyzing literature from 2018 to 2025 to identify research trends. Results: Significant applications were revealed across clinical decision support, medical knowledge retrieval, traditional Chinese medicine (TCM) formulation development, medical imaging report analysis, medical record quality control, mental health monitoring, and emotion recognition, demonstrating optimized resource allocation and service efficiency. Persistent challenges include system accuracy limitations, multimodal interaction capabilities, user trust barriers, and privacy protection concerns. Conclusion: Future research should prioritize multimodal diagnostic imaging, TCM-specific AI agents, and virtual-reality-assisted surgical exploration. Contributions: This work consolidates current achievements while establishing theoretical–practical foundations for innovation and large-scale implementation, advancing intelligent healthcare transformation. Full article

Microbial growth and inhibition are complex biological processes influenced by diverse environmental and chemical factors, posing challenges for accurate modelling and prediction. Traditional mechanistic models often struggle to capture the nonlinear and multidimensional interactions inherent in real-world food systems, especially when multiple environmental variables and inhibitors are involved. This study presents the development of a novel, dynamic software platform that integrates classical predictive microbiology models—including both one-step and two-step frameworks—with advanced machine learning (ML) methods such as Support Vector Regression, Random Forest Regression, and Gaussian Process Regression. Uniquely, this platform enables direct comparisons between two-step and one-step modelling approaches across four widely used growth models (modified Gompertz, Logistic, Baranyi, and Huang) and three inhibition models (Log-Linear, Log-Linear + Tail, and Weibull), offering unprecedented flexibility for model evaluation and selection. Furthermore, the platform incorporates ML-based modelling for both microbial growth and inhibition, expanding predictive capabilities beyond traditional parametric frameworks. Validation against experimental and literature datasets demonstrated the platform’s high predictive accuracy and robustness, with machine learning models, particularly Gaussian Process Regression and Random Forest Regression, outperforming classical models. This versatile platform provides a powerful, data-driven decision-support tool for researchers, industry professionals, and regulatory bodies in areas such as food safety management, shelf-life estimation, antimicrobial testing, and environmental monitoring. Future work will focus on further optimization, integration with large public microbial databases, and expanding applications in emerging fields of predictive microbiology. Full article

Yin Yang 1 (YY1) is a multifunctional transcription factor implicated in gene regulation, cell proliferation, and survival. While its role in breast cancer (BC) has been explored, its prognostic significance remains controversial. In this study, we evaluated nuclear YY1 expression in 276 BC tissue samples using immunohistochemistry (IHC), tissue microarrays (TMAs), and digital pathology (DP). Nuclear staining was quantified using Aperio ImageScope software, focusing on tumor regions to avoid confounding from stromal or non-tumor tissues. This selective and standardized approach enabled precise quantification of YY1 expression. Our results show elevated median YY1 expression in tumor vs. normal matched tissues (p < 0.001). The optimal cutoff for medium-intensity nuclear YY1 expression in tumor areas for overall survival (OS) was established by a receiver operating characteristic (ROC) curve (AUC = 0.718, 95% CI: 0.587–0.849, p = 0.008). In contrast, ROC curves showed no prognostic impact (AUC and p-value) for YY1 quantification in whole spots (tumor + normal). As a categorical variable, high YY1 expression was correlated with more aggressive BC features, including tumor size > 3 cm (57.7% vs. 44.2% p = 0.037), the triple-negative breast cancer (TNBC) molecular subtype (27.3% vs. 13.9% p = 0.026), and advanced prognostic stage (III) (31.8% vs. 16.7% p = 0.003), while as a continuous variable, YY1 was associated with higher histological (p = 0.003) and nuclear grades (p = 0.022). High YY1 expression was significantly associated with a reduced OS of BC patients, as shown by Kaplan–Meier curves (HR = 2.227, p = 0.002). Since YY1 was significantly enriched in TNBC, we evaluated its prognostic resolution in this subgroup. But, probably due to the small number of patients within this subset, our results were not statistically significant (HR = 1.317, 95% CI: 0.510–3.405, p = 0.566). Next, we performed multivariate Cox regression, confirming YY1 as an independent prognostic factor for overall survival (HR = 1.927, 95% CI: 1.144–3.247, p = 0.014). In order to improve prognostic value, we constructed a mathematical model derived from the multivariate Cox regression results, including YYI, AJCC prognostic stage (STA), and axillary lymph node dissection (ALN), with the following equation: h(t) = h₀(t) × exp (0.695 × YY1 + 1.103 × STA − 0.503 × ALN). ROC analysis of this model showed a better AUC of 0.915, similar sensitivity (83.3%), and much higher specificity (92%). Bioinformatic analysis of public datasets supported these findings in BC, showing YY1 overexpression in multiple cancer types and its association with poor outcomes in BC. These results suggest that YY1 may play a role in tumor progression and serve as a valuable prognostic biomarker in BC. DP combined with molecular data enhanced biomarker accuracy, supporting clinical applications of YY1 in routine diagnostics and personalized therapy. Additionally, developing a combined score based on the modeling of multiple prognostic factors significantly enhanced survival predictions, representing a practical tool for risk stratification and the guidance of therapeutic decisions. Full article

In dynamic and open cloud service processes, particularly in distributed networked manufacturing environments, the complex and volatile manufacturing landscape introduces numerous uncertainties and disturbances. This paper addresses the common issue of cloud resource connection interruptions by proposing a path substitution strategy based on alternative service routes. By integrating agent-based simulation and complex network methodologies, a simulation model for evaluating the robustness of cloud manufacturing service systems is developed, enabling dynamic simulation and quantitative decision-making for the proposed robustness enhancement strategies. First, a hybrid modeling approach for cloud manufacturing service systems is proposed to meet the needs of robustness analysis. The specific construction of the hybrid simulation model is achieved using the AnyLogic 8.7.4 simulation software and Java-based secondary development techniques. Second, a complex network model focusing on cloud manufacturing resource entities is further constructed based on the simulation model. By combining the two models, two-dimensional robustness evaluation indicators—comprising performance robustness and structural robustness—are established. Then, four types of edge attack strategies are designed based on the initial topology and recomputed topology. To ensure system operability after edge failures, a path substitution strategy is proposed by introducing redundant routes. Finally, a case study of a cloud manufacturing project is conducted. The results show the following: (1) The proposed robustness evaluation model fully captures complex disturbance scenarios in cloud manufacturing, and the designed simulation experiments support the evaluation and comparative analysis of robustness improvement strategies from both performance and structural robustness dimensions. (2) The path substitution strategy significantly enhances the robustness of cloud manufacturing services, though its effects on performance and structural robustness vary across different disturbance scenarios. Full article

This article examines how veterinarians in Istanbul experience and navigate the ethical, emotional, and institutional complexities of performing euthanasia on dogs, with particular attention to the differences between companion and street dogs. Drawing on 29 in-depth interviews with private practice veterinarians in Istanbul, this study employs qualitative analysis using the NVivo 12 Plus software and reflexive thematic analysis to identify key patterns in moral reasoning, emotional labor, and clinical decision making. The findings indicate that euthanasia of companion dogs is often framed through shared decision making with guardians, emotional preparation, and post-procedural grief rituals. While still emotionally taxing, these cases are supported by relational presence and mutual acknowledgment. In contrast, euthanasia of street dogs frequently occurs in the absence of legal ownership, institutional accountability, or consistent caregiving, leaving veterinarians to bear the full moral and emotional weight of the decision. Participants described these cases as ethically distinct, marked by relational solitude, clinical ambiguity, and heightened moral distress. Six key themes that reveal how euthanasia becomes a site of both care and conflict when structural support is lacking are identified in this study, including emotional burden, ethical strain, and resistance to routinized killing. By foregrounding the roles of institutional absence and relational asymmetry in shaping end-of-life decisions, this study contributes to empirical veterinary ethics and calls for more contextually attuned ethical frameworks, particularly in urban settings with large populations of street dogs and culturally entrenched practices of collective guardianship and caregiving. Full article