Search Results (67)

The Social Internet of Things (SIoT) combines social networks and the Internet of Things, enabling closer interaction between devices, users, and services. However, this interaction brings risks of trust attacks. These trust attacks not only affect the stability of SIoT systems but also threaten personal privacy and data security. This paper provides a decade-long review of SIoT trust attack research. First, it outlines the SIoT architecture, social relationship types, concept of trust, and trust management processes. It maps seven attacks—bad mouthing attack (BMA), ballot stuffing attack (BSA), self-promoting attack (SPA), discriminatory attack (DA), whitewashing attack (WWA), on-off attack (OOA), and opportunistic service attack (OSA)—clarifying their mechanisms and traits. Next, we synthesize the literature on SIoT trust models, enumerate which attack types they address, and classify defense strategies. It then conducts simulation-based comparative experiments on trust attacks to reveal their impact on node trust and transaction processing, compares attack capabilities along disruption speed, attack strength, and stealthiness, and summarizes attack surfaces with corresponding defense recommendations to better guide the design of SIoT trust management schemes. Finally, we identify open challenges and future research directions, to support the development of new trust management models better equipped to address evolving trust attacks. Full article

Medication-related osteonecrosis of the jaw (MRONJ) is a serious adverse effect of antiresorptive and antiangiogenic therapies, yet its molecular mechanisms remain poorly defined. The present study employed an analysis of microarray data (GSE7116) from peripheral blood mononuclear cells of patients with multiple myeloma, myeloma patients with MRONJ, and healthy controls. Differentially expressed genes were identified using the limma package, followed by functional enrichment analysis, weighted gene co-expression network analysis, and LASSO regression and CytoHubba network ranking. The predictive performance was validated by means of nested cross-validation, Firth logistic regression, and safe stratified 0.632+ bootstrap ridge regression. The profiling revealed distinct gene expression patterns between the groups: the upregulation of ribosomal and translational pathways, as well as the suppression of neutrophil degranulation and antimicrobial defense mechanisms, and identified key candidate genes, including PDE4B, JAK1, ETS1, EIF4A2, FCMR, IGKV4-1, and XPO7. These genes demonstrated substantial discriminatory capability, with an area under the curve ranging from 0.95 to 0.99, and were found to be functionally linked to immune system dysfunction, cytokine signaling, NF-κB activation, and a maladaptive stress response. These findings link MRONJ to systemic immune-inflammatory imbalance and translational stress disruption, offering novel insights and potential biomarkers for diagnosis and risk evaluation. Full article

Pistachio (Pistacia vera) is widely consumed among tree nuts but capable of triggering severe IgE-mediated reactions in allergic individuals. Due to the similarity of cashew-borne and pistachio-borne allergen proteins and DNA, traditional detection methods, such as ELISA and PCR, often suffer from cross-reactivity, limiting their ability to discriminate between these two allergens. This study presents a sensitive LC-MS/MS method for the simultaneous detection of pistachio and cashew allergens in processed food with a screening detection limit (SDL) equal to 1 mg/kg. The method was validated for specificity, SDL, β error, precision, and ruggedness, and applied to various matrices (cereals, chocolate, sauces, and meat products). Ruggedness testing showed that all considered parameters must be carefully monitored by the operator, and sample preparation must be carried out without any modification in parameter values, under strictly controlled conditions. Good reproducibility was achieved for pistachio detection, while ongoing investigations should be carried out to overcome existing constraints for cashew. The LC-MS/MS method described in this work is a discriminatory method suitable for official food allergen control to selectively differentiate pistachio from cashew allergens, overcoming the limitations of PCR and ELISA when cross-reactivity occurs. It represents a validated tool for pistachio detection and a promising approach toward improving cashew allergen analysis. Full article

The reliability of decision-making algorithms within soft set theory is fundamentally constrained by their underlying membership functions. Traditional binary approaches overlook the implicit connections between the attributes a candidate possesses and those it lacks—connections that can be inferred from the wider candidate pool. To address this core challenge, this paper puts forward the Relational Membership Value Calculation (RMVC), an algorithmic framework whose core is a fine-grained relational membership function. Our approach moves beyond binary logic to capture these nuanced interrelationships. We provide a rigorous theoretical analysis of the proposed algorithm, including its computational complexity and robustness, which is validated through a comprehensive sensitivity analysis. Crucially, a comparative analysis using the Gini Index quantitatively demonstrates that our method provides significantly higher granularity and discriminatory power on a representative case study. The RMVC is implemented as an open-source Python program, providing a foundational tool to enhance the reasoning capabilities of AI-driven decision support and expert systems. Full article

Individual identification of Holstein cattle is crucial for the intelligent management of farms. The existing closed-set identification models are inadequate for breeding scenarios where new individuals continually join, and they are highly sensitive to obstructions and alterations in the cattle’s appearance, such as back defacement. The current open-set identification methods exhibit low discriminatory stability for new individuals. These limitations significantly hinder the application and promotion of the model. To address these challenges, this paper proposes a prototype network-based incremental identification framework for Holstein cattle to achieve stable identification of new individuals under small sample conditions. Firstly, we design a feature extraction network, ResWTA, which integrates wavelet convolution with a spatial attention mechanism. This design enhances the model’s response to low-level features by adjusting the convolutional receptive field, thereby improving its feature extraction capabilities. Secondly, we construct a few-shot augmented prototype network to bolster the framework’s robustness for incremental identification. Lastly, we systematically evaluate the effects of various loss functions, prototype computation methods, and distance metrics on identification performance. The experimental results indicate that utilizing ResWTA as the feature extraction network achieves a top-1 accuracy of 97.43% and a top-5 accuracy of 99.54%. Furthermore, introducing the few-shot augmented prototype network enhances the top-1 accuracy by 4.77%. When combined with the Triplet loss function and the Manhattan distance metric, the identification accuracy of the framework can reach up to 94.33%. Notably, this combination reduces the incremental learning forgetfulness by 4.89% compared to the baseline model, while improving the average incremental accuracy by 2.4%. The proposed method not only facilitates incremental identification of Holstein cattle but also significantly bolsters the robustness of the identification process, thereby providing effective technical support for intelligent farm management. Full article

Sensor selection in IoT-based smart healthcare systems is a complex fuzzy decision-making problem due to the presence of numerous uncertain and interdependent evaluation criteria. Traditional fuzzy multi-criteria decision-making (MCDM) approaches often assume independence among criteria and rely on aggregation operators that impose sharp transitions between preference levels. These assumptions can lead to decision outcomes with insufficient differentiation, limited discriminatory capacity, and potential issues in consistency and sensitivity. To overcome these limitations, this study proposes a novel fuzzy decision-making framework by integrating Quasi-D-Overlap functions into the fuzzy MARCOS (Measurement of Alternatives and Ranking According to Compromise Solution) method. Quasi-D-Overlap functions represent a generalized extension of classical overlap operators, capable of capturing partial overlaps and interdependencies among criteria while preserving essential mathematical properties such as associativity and boundedness. This integration enables a more intuitive, flexible, and semantically rich modeling of real-world fuzzy decision problems. In the context of real-time health monitoring, a case study is conducted using a hybrid edge–cloud architecture, involving sensor tasks such as heartrate monitoring and glucose level estimation. The results demonstrate that the proposed method provides greater stability, enhanced discrimination, and improved responsiveness to weight variations compared to traditional fuzzy MCDM techniques. Furthermore, it effectively supports decision-makers in identifying optimal sensor alternatives by balancing critical factors such as accuracy, energy consumption, latency, and error tolerance. Overall, the study fills a significant methodological gap in fuzzy MCDM literature and introduces a robust fuzzy aggregation strategy that facilitates interpretable, consistent, and reliable decision making in dynamic and uncertain healthcare environments. Full article

Canine visceral leishmaniasis (CVL) is a major zoonosis that poses a growing challenge to public health services, as successful disease management requires sensitive, specific, and rapid diagnostic methods capable of identifying infected animals even at a subclinical level. The objective of this study was to evaluate the performance of the recombinant chimeric protein rMELEISH3 as an antigen in ELISA assays for the robust diagnosis of CVL. The protein was expressed in a bacterial system, purified by affinity chromatography, and evaluated through a series of serological assays using serum samples from dogs infected with Leishmania infantum. ROC curve analysis revealed a diagnostic sensitivity of 96.4%, a specificity of 100%, and an area under the curve of 0.996, indicating excellent discriminatory power. Furthermore, rMELEISH3 was recognized by antibodies present in the serum of dogs with low parasite loads, reinforcing the diagnostic potential of the assay in asymptomatic cases. It is concluded that the use of the recombinant antigen rMELEISH3 could significantly contribute to the improvement of CVL surveillance and control programs in endemic areas of Brazil and other countries, by offering a safe, reproducible and effective alternative to the methods currently recommended for the serological diagnosis of the disease. Full article

The Chinese mitten crab (Eriocheir sinensis) industry is currently facing the challenges of origin fraud, as well as a lack of precision and interpretability of existing traceability methods. Here, we propose a high-precision origin traceability method based on a combination of stable isotope analysis and interpretable machine learning. We sampled Chinese mitten crabs from six origins representing diverse aquatic environments and farming practices, and analyzed their δ¹³C, δ¹⁵N, δ²H, and δ¹⁸O stable isotope compositions in different sexes and tissues (hepatopancreas, muscle, and gonad). By comparing the classification performance of Random Forest, XGBoost, and Logistic Regression models, we found that the Random Forest model outperformed the others, achieving high accuracy (91.3%) in distinguishing samples from different origins. Interpretation of the optimal Random Forest model, using SHAP (SHapley Additive exPlanations) analysis, identified δ²H in male muscle, δ¹⁵N in female hepatopancreas, and δ¹³C in female hepatopancreas as the most influential features for discriminating geographic origin. This analysis highlighted the crucial role of environmental factors, such as water source, diet, and trophic level, in origin discrimination and demonstrated that isotopic characteristics of different tissues provide unique discriminatory information. This study offers a novel paradigm for stable isotope traceability based on explainable machine learning, significantly enhancing the identification capability and reliability of Chinese mitten crab origin traceability, and holds significant implications for food safety assurance. Full article

The present study introduces an AI (Artificial Intelligence) framework for surface roughness assessment in milling operations through sound signal processing. As industrial demands escalate for in-process quality control solutions, the proposed system leverages audio data to estimate surface finish states without interrupting production. In order to address this, a novel classification approach was developed that maps audio waveform data into predictive indicators of surface quality. In particular, an experimental dataset was employed consisting of sound signals that were captured during milling procedures applying various machining conditions, where each signal was labeled with a corresponding roughness quality obtained via offline metrology. The formulated classification pipeline commences with audio acquisition, resampling, and normalization to ensure consistency across the dataset. These signals are then transformed into Mel-Frequency Cepstral Coefficients (MFCCs), which yield a compact time–frequency representation optimized for human auditory perception. Next, several AI algorithms were trained in order to classify these MFCCs into predefined surface roughness categories. Finally, the results of the work demonstrate that sound signals could contain sufficient discriminatory information enabling a reliable classification of surface finish quality. This approach not only facilitates in-process monitoring but also provides a foundation for intelligent manufacturing systems capable of real-time quality assurance. Full article

This study assesses habitat suitability and identifies conservation priority areas for the endangered Marco Polo sheep throughout Khunjerab National Park (Pakistan) and Tashkurgan Natural Reserve (China). We analyzed species occurrence records against environmental variables (elevation, slope, climate, land cover) using MaxEnt modeling. Model performance was validated through AUC-ROC analysis and response curves, generating spatial predictions of suitable habitats to inform conservation strategies. Spatial predictions were generated to map potential distribution zones, aiding conservation planning for this endangered species. The model’s predictive performance was evaluated using the Area Under the Curve (AUC) of the Receiver Operating Characteristic curve, yielding an AUC of 0.919, indicating strong discriminatory capability. Elevation (43.9%), slope (25.9%), and September precipitation (15.9%) emerged as the most influential environmental predictors, collectively contributing 85.7% to the model. The total percentage contribution and permutation significance values were 98.6% and 77.8%, respectively. Jackknife analysis identified elevation (bio-1), slope (bio-7), hillshade (bio-2), and the maximum July temperature (bio-9) as the most significant factors influencing the distribution of Marco Polo sheep, Conversely, variables such as viewshade (bio-14), land cover (bio-3), and precipitation in August (bio-4) contributed a minimal gain, suggesting that they had little impact on accurately predicting species distribution. The habitat suitability map reveals varying conditions across the study area, with the highest suitability (yellow zones) found in the northern and western regions, particularly along the Wakhan Corridor ridgelines. The southern regions, including Khunjerab Pass, show predominantly low suitability, marked by purple zones, suggesting poor habitat conditions. The eastern region displays moderate to low suitability, with fragmented patches of green and yellow, indicating seasonal habitats. The survival of transboundary Marco Polo sheep remains at risk due to poaching activities and habitat destruction and border fence barriers. This study recommends scientific approaches to habitat restoration together with improved China–Pakistan cooperation in order to establish sustainable migratory patterns for this iconic species. Full article

Introduction: Cytokine release syndrome (CRS) and immune cell-associated neurotoxicity syndrome (ICANS) are both serious complications of CAR-T therapy associated with endothelial dysfunction, prompting prior use of a modified version of the endothelial activation and stress index (m-EASIX) to predict the occurrence of severe ICANS and CRS. Previous studies have linked both hypophosphatemia and elevated IL6 levels to CRS and ICANS. Our study aimed to enhance the early prediction of both syndromes by integrating phosphorous and IL-6 both together and separately into the m-EASIX score. Methods: Forty-two patients with non-Hodgkin’s lymphoma presenting for CAR-T treatment were used to generate three variations in the m-EASIX score, assessing performance for the clinically actionable time points of day +0 through day +3. Results: The addition of phosphorous through the P-m-EASIX improved the predictive capabilities for the occurrence of ICANS, most notably on day +1 (AUC 89.6%; p = 0.0090, OR of 2.23; p = 0.0096) compared to the m-EASIX (AUC 80.8%; p = 0.0047, OR 1.72; p = 0.0046). The P-m-EASIX also showed enhanced predictive capabilities for the occurrence of CRS, with peak discriminatory function on day +3 (AUC 92.0%; p = <0.0001, OR 2.21; p = 0.0014). The addition of IL6 in the IL6-m-EASIX showed the highest discriminatory capacity for the prediction of CRS progression to grade ≥ 2 with peak function on day +3 (AUC 89.7%; p = 0.0040, OR 1.57; p = 0.031). Conclusions: Incorporating phosphorus levels into the m-EASIX score offered a cost-effective and straightforward method to improve the prediction of CAR-T toxicities. Larger-scale studies assessing the effectiveness of including phosphorus and IL-6 in the m-EASIX score to mitigate complications associated with CAR-T therapy are warranted. Full article

Background and Objectives: The pulmonary artery pulsatility index (PAPi) is an emerging marker of right ventricular (RV) injury but has not been well investigated in acute pulmonary embolism (PE) or chronic thromboembolic pulmonary hypertension (CTEPH). We aimed to investigate its discriminatory capabilities and ability to detect therapeutic effects in acute PE and CTEPH. Materials and Methods: This was a secondary analysis of data from both experimental studies of autologous PE and human studies of acute PE and CTEPH. PAPi was calculated and compared in (1) PE versus sham and (2) before and after interventions aimed at reducing RV afterload in PE and CTEPH. The correlations between PAPi, cardiac output, and RV to pulmonary artery coupling were investigated. Results: PAPi did not differ between animals with acute PE versus sham, nor was it affected by clot burden (p = 0.673) or at a 30-day follow-up (p = 0.242). Pulmonary vasodilatation with oxygen was associated with a reduction in PAPi (4.9 [3.7–7.8] vs. 4.0 [3.2–5.6], p = 0.016), whereas positive inotropes increased PAPi in the experimental PE. In humans, PAPi did not change consistently with interventions. Balloon pulmonary angioplasty did not significantly increase PAPi (6.5 [4.3–10.7] vs. 9.8 [6.8–14.2], p = 0.1) in patients with CTEPH, and a non-significant reduction in PAPi (4.3 ± 1.6 vs. 3.3 ± 1.2, p = 0.074) was observed in patients with acute PE who received sildenafil. PAPi did not correlate well with cardiac output or measures of RV to pulmonary artery coupling in either species. Conclusions: PAPi did not detect acute, experimental PE or changes as a result of therapeutic interventions in patients with hemodynamically stable acute PE or CTEPH. However, it did change with pharmacological interventions in the experimental PE. Further research should establish its utility in detecting and monitoring RV injury in different clinical phenotypes of acute PE and CTEPH. Full article

Background and Objectives: The heterogeneous clinical manifestations of fibromyalgia syndrome have led to the revision of diagnostic criteria in the last decade. The aim of this study was to determine the capability of clinical, psychological, and cognitive patient-related outcome measures (PROMs) to differentiate women with fibromyalgia syndrome (FMS) from women with localized or regional pain conditions. Materials and Methods: A diagnostic accuracy study was conducted. Clinical (pain intensity—NPRS; related disability—FIQ), psychological (anxiety/depressive levels—HADS-A/HADS-D), and cognitive (sleep quality—PSQI; pain hypervigilance—PVAQ-9) PROMs were collected in 129 women with FMS and 65 women with localized/regional chronic pain conditions. The area under the receiver operating characteristic (ROC) curve, cut-off point, sensitivity/specificity values, and positive and negative likelihood (LR) ratios of each variable were calculated. Results: Women with FMS showed higher levels of pain, related disability, and anxiety/depressive levels, worse sleep quality, and higher levels of hypervigilance (all, p < 0.001) than women without FMS. All PROMs showed excellent discriminatory power and good sensitivity (pain intensity: ROC 0.987, sensitivity 91.5%; related disability: ROC 0.980, sensitivity 93.8%; HADS-A: ROC 0.901, sensitivity 81.4%; HADS-D: ROC 0.906, sensitivity 85.3%; PSQI: ROC 0.909, sensitivity 79.1%; PVAQ-9: ROC 0.798, sensitivity 80.6%). Specificity was extremely small for all variables (<18%) except for pain hypervigilance (specificity: 34%). Conclusions: Women with FMS exhibited worse clinical, psychological, and cognitive variables than women with localized/regional chronic pain. Although all PROMs had good discriminatory power, related disability and pain hypervigilance were those showing the best models. These PROMs could be combined with the American College of Rheumatology (ACR) diagnostic criteria to better discriminate between women with and without FMS. Studies investigating the relevance of combining these PROMs with the ACR diagnostic criteria in clinical settings are needed. Full article

Background/Objectives: Kidney transplantation (kTx) is the preferred treatment for end-stage kidney disease. Limited evaluation of structural changes in transplanted kidneys hinders the timely prediction of disease progression and the implementation of treatment modifications. Protocol biopsies provide valuable insights but are invasive and carry risks of biopsy-related complications. This study investigates whether multiparametric magnetic resonance imaging (MRI), including T1 and T2 mapping and diffusion-weighted imaging (DWI), can predict kidney function and the progression of interstitial fibrosis and tubular atrophy (IF/TA) in the early post-transplant period. Methods: A prospective study was conducted at The Hospital of Lithuanian University of Health Sciences Kauno Klinikos from May 2022 to March 2024. Thirty-four patients receiving kidney transplants from deceased donors underwent baseline biopsies and post-transplant MRI scans. Follow-up assessments included kidney function evaluation, biopsies, and MRI scans at three months post-transplant. Results: Significant correlations were observed between MRI parameters and kidney function: T1 and apparent diffusion coefficient (ADC) corticomedullary differentiation (CMD) correlated with eGFR at discharge (r = −0.338, p = 0.05; r = 0.392, p = 0.022, respectively). Linear and logistic regression models demonstrated that post-transplant T1 and ADC CMD values significantly predicted kidney function at discharge. Furthermore, T1 CMD values measured 10–15 days post-transplant predicted IF/TA progression at three months post-kTx, with an area under the curve of 0.802 (95% CI: 0.616–0.987, p = 0.001) and an optimal cut-off value of −149.71 ms. The sensitivity and specificity were 0.818 and 0.273, respectively (Youden’s index = 0.545). T2 mapping was not predictive. Conclusions: This study highlights the potential immediate clinical utility of MRI-derived biomarkers, particularly ADC and T1 CMD, in centers equipped with advanced imaging capabilities as tools for assessing kidney function in the early post-transplant period. With an AUROC of 0.802, T1 CMD demonstrates strong discriminatory power for predicting IF/TA progression early in the post-transplant period. Full article

Machine learning has transformed ophthalmology, particularly in predictive and discriminatory models for vitreoretinal pathologies. However, generative modeling, especially generative adversarial networks (GANs), remains underexplored. GANs consist of two neural networks—the generator and discriminator—that work in opposition to synthesize highly realistic images. These synthetic images can enhance diagnostic accuracy, expand the capabilities of imaging technologies, and predict treatment responses. GANs have already been applied to fundus imaging, optical coherence tomography (OCT), and fluorescein autofluorescence (FA). Despite their potential, GANs face challenges in reliability and accuracy. This review explores GAN architecture, their advantages over other deep learning models, and their clinical applications in retinal disease diagnosis and treatment monitoring. Furthermore, we discuss the limitations of current GAN models and propose novel applications combining GANs with OCT, OCT-angiography, fluorescein angiography, fundus imaging, electroretinograms, visual fields, and indocyanine green angiography. Full article