Search Results (28,622)

Background/Objectives: Peptide receptor radionuclide therapy (PRRT) is an established treatment for metastatic neuroendocrine tumors (NETs), yet long-term disease control occurs only in a subset of patients. Predicting progression-free survival (PFS) could support individualized treatment planning. This study evaluates laboratory, imaging, and multimodal deep learning models for PFS prediction in PRRT-treated patients. Methods: In this retrospective, single-center study 116 patients with metastatic NETs undergoing [177Lu]Lu-DOTATOC were included. Clinical characteristics, laboratory values, and pretherapeutic somatostatin receptor positron emission tomography/computed tomographies (SR-PET/CTs) were collected. Seven models were trained to classify low- vs. high-PFS groups, including unimodal (laboratory, SR-PET, or CT) and multimodal fusion approaches. Performance was assessed via repeated 3-fold cross-validation with area under the receiver operating characteristic curve (AUROC) and area under the precision–recall curve (AUPRC). Explainability was evaluated by feature importance analysis and gradient based saliency maps. Results: Forty-two patients (36%) displayed short PFS (≤1 year) and 74 patients displayed long PFS (>1 year). Groups were similar in most characteristics, except for higher baseline chromogranin A (p = 0.003), elevated $\gamma$-GT (p = 0.002), and fewer PRRT cycles (p < 0.001) in short-PFS patients. The Random Forest model trained only on laboratory biomarkers reached an AUROC of 0.59 ± 0.02. Unimodal three-dimensional convolutional neural networks using SR-PET or CT performed worse (AUROC 0.42 ± 0.03 and 0.54 ± 0.01, respectively). A multimodal fusion model integrating laboratory values, SR-PET, and CT—augmented with a pretrained CT branch—achieved the best results (AUROC 0.72 ± 0.01, AUPRC 0.80 ± 0.01). Explainability analyses provided insights into model predictions, with explainability patterns in the fusion model appearing physiologically plausible and predominantly tumor-focused. Conclusions: Multimodal deep learning combining SR-PET, CT, and laboratory biomarkers outperformed unimodal approaches for PFS prediction after PRRT. Upon external validation, such models may support risk-adapted follow-up strategies. Full article

Spectrum scarcity has become a critical issue due to the rapid deployment of fifth-generation (5G) networks and the explosive growth of future wireless data traffic. Spectrally Efficient Frequency Division Multiplexing (SEFDM) is a promising technique to enhance spectral efficiency by compressing subcarrier spacing and allowing spectral overlap; however, it suffers from severe inter-carrier interference (ICI) caused by the loss of orthogonality. In particular, under Rayleigh fading channels, the combined effects of ICI and multipath fading lead to significant degradation in bit error rate (BER) performance. Conventional SEFDM systems employing a cyclic prefix (CP) encounter an unavoidable error floor due to residual interference stemming from non-orthogonality. On the other hand, while zero-padding (ZP)-based SEFDM offers superior multipath tolerance, further enhancement in communication quality is still desired. This paper proposes a novel receiver architecture utilizing sector antennas to spatially separate multipath components based on the angle of arrival (AoA). Furthermore, we investigate and compare sector selection algorithms specifically tailored for SEFDM systems. Simulation results demonstrate that the proposed method, employing a sector selection scheme based on the maximum channel response power, effectively suppresses inter-symbol interference (ISI) and improves BER performance for both CP-SEFDM and ZP-SEFDM. Furthermore, our quantitative evaluations confirm that the proposed architecture successfully achieves the theoretical maximum spectral efficiency even in higher-order modulation schemes (16QAM), while maintaining a low computational complexity compared to conventional spatial diversity techniques. Full article

Accurate forecasting of pork prices is important yet challenging because pork price series are highly volatile and non-stationary. Existing hybrid forecasting models often rely on fixed-weight integration, which may limit their ability to adapt to multi-scale temporal variation and complex temporal dependencies. To address these issues, this study proposes VMD–EMSA–HCTM–Informer, a hybrid forecasting framework that combines signal decomposition with an enhanced encoder–decoder architecture. Variational Mode Decomposition (VMD) is first used to reduce signal non-stationarity by extracting intrinsic mode functions. Within the Informer backbone, an Enhanced Multi-Scale Attention (EMSA) encoder is introduced to capture local fluctuations at different temporal scales, while a Hybrid Convolutional–Temporal Module (HCTM) decoder is used to strengthen temporal feature extraction and channel interaction modeling. Empirical evaluation was conducted on daily pork price data from the China Pig Industry Network and a large-scale intensive breeding enterprise in southern China over the period 2013–2025. Under the current experimental setting, the proposed framework achieved the lowest average errors among the compared baselines across five independent runs, with an average MAE of 0.4875 and an average MAPE of 3.0540%. These results suggest that the proposed framework provides a useful and relatively stable univariate forecasting approach for volatile pork prices. However, the findings should be interpreted within the scope of the present dataset and experimental design, and future work will extend the framework to multivariate forecasting with exogenous drivers and uncertainty quantification. Full article

Short-term load forecasting plays a pivotal role in modern power system operations yet it remains challenging due to the complex spatiotemporal dependencies in load data. This paper proposes a dual-head attention residual network (DARNet) that significantly advances STLF through three key innovations: (1) a hybrid encoder combining 1D-CNN and GRU architectures to simultaneously capture the local load patterns and long-term temporal dependencies, achieving a 28% better locality awareness than that of conventional approaches; (2) a novel dual-head attention mechanism that dynamically models both the inter-temporal relationships and cross-variable dependencies, reducing the feature engineering requirements; and (3) an autocorrelation-adjusted recursive forecasting framework that cuts the multi-step prediction error accumulation by 33% compared to that with standard seq2seq models. Extensive experiments on real-world datasets from three Chinese cities demonstrate DARNet’s superior performance, outperforming six state-of-the-art benchmarks by 21–35% across all of the evaluation metrics (MAPE, SMAPE, MAE, and RRSE) while maintaining robust generalization across different geographical regions and prediction horizons. Full article

The increasing demand for innovative strategies in sustainable food production—driven by rapid global population growth, particularly in sub-Saharan Africa (SSA)—necessitates urgent attention to agricultural resilience. Recent technological advancements have enhanced crop productivity, post-harvest preservation, and environmentally sustainable farming practices. However, three critical bottlenecks remain: (i) the lack of accurate, maize-specific yield prediction methods tailored to SSA; (ii) limited multimodal modeling approaches capable of capturing complex, nonlinear interactions among heterogeneous data sources; and (iii) a lack of explainability mechanisms, which render high-performing models “black boxes” and hinder stakeholder trust. To address these gaps, this study presents an explainable machine learning framework for smart maize yield prediction. We integrate multimodal SSA-specific soil, crop, and weather data to capture the multi-dimensional drivers of maize productivity. Six diverse algorithms—including extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), categorical boosting (CatBoost), support vector machine (SVM), random forest (RF), and an artificial neural network (ANN) combined with a k-nearest neighbors (kNN)—were benchmarked to evaluate predictive performance. To ensure robustness against spatial heterogeneity, we employed a Leave-One-Plot-Out (LOPO) cross-validation strategy. Empirical results on unseen test data identify CatBoost as the best-performing model, achieving a coefficient of determination of ($R^2 =~76\%$), demonstrating its ability to capture complex, nonlinear relationships in agricultural data. To enhance transparency and stakeholder trust, we integrated Local Interpretable Model-agnostic Explanations (LIME), providing plot-level insights into the physiological and environmental drivers of maize yield. Together, these contributions establish a scalable and interpretable modeling framework capable of supporting data-driven agricultural decision-making in SSA. Full article

Coastal freak waves (CFWs) are sudden and hazardous wave events that occur near shorelines and can pose serious threats to coastal visitors and infrastructure. Due to the complex interactions among coastal bathymetry, wave dynamics, and environmental conditions, the mechanisms governing CFW formation remain poorly understood, making reliable prediction difficult. This study investigates the feasibility of applying machine learning techniques to predict CFW occurrences using observational environmental data. Three machine learning algorithms, the Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), were developed to generate probability-based predictions of CFW events. Environmental variables derived from buoy observations, including wave characteristics, wind conditions, swell parameters, wave grouping indicators, and nonlinear wave interaction indices, were used as model inputs. Hyperparameters were optimized using grid search combined with k-fold cross-validation. The results show that all three models achieved comparable predictive performance, with AUC values close to 0.80 and overall prediction accuracy around 74%. The ANN model achieved the highest recall, indicating strong capability in detecting CFW events, while the RF and SVM models showed more balanced precision and recall. Analysis of high-probability prediction events suggests that CFW occurrences are associated with swell-dominated conditions, strong wave grouping behavior, and enhanced nonlinear wave interactions. These results demonstrate that machine learning provides a promising framework for probabilistic prediction of coastal freak waves and has potential applications in coastal hazard assessment and early warning systems. Full article

Photocatalytic anti-corrosion materials are an emerging intelligent protective material that has been widely used in marine and offshore engineering in recent years. However, its failure mechanism under multi-factor coupling is complex, and it is difficult for traditional methods to achieve accurate life prediction and mechanism analysis. This article takes submarine pipelines as the research object and designs an innovative multi-source environmental data-driven method combined with deep learning (DL), aiming to establish an intelligent prediction model for the failure of the material. This article first systematically collects the multi-source heterogeneous data of materials during service; on this basis, this article constructs a hybrid DL model. Firstly, a multi-scale multimodal image feature fusion network (MMFCT) based on the combination of convolutional neural network (CNN) and Transformer is adopted to automatically extract corrosion features from microscopic images and capture the dynamic correlation between environmental temporal data and performance degradation; then, the Sparrow Search Algorithm (SSA) was constructed to optimize the BP neural network (BPNN) model for predicting the ultimate bearing capacity of submarine corroded pipelines. Simulation experiments show that the proposed method achieves accurate prediction of material remaining life and key performance degradation paths. The corrosion recognition precision reaches 94.7%, and the bearing capacity prediction error remains below 3.1%. Full article

This study presents a nanosensor network system for autonomous microclimate optimization in precision horticulture, leveraging a field-programmable gate array (FPGA)-based control architecture that is integrated with an edge-level machine learning inference. Unlike the conventional greenhouse automation systems, which exhibit thermal and hygroscopic hysteresis often exceeding 32 °C and 78% relative humidity, the proposed framework embeds a random forest regression (RFR) model directly within the Altera DE2-115 FPGA fabric to enable predictive environmental regulation. The model achieved an R² of 0.985 and root mean square error (RMSE) of 0.28 °C, allowing proactive compensation for the thermodynamic disturbances from the high-intensity light-emitting diode (LED) lighting with a 120 s predictive horizon. The real-time monitoring and remote supervision were supported via a NodeMCU-based IoT gateway, achieving a 140 ms mean communication latency and a 99.8% packet delivery reliability. The preliminary validation using lettuce (Lactuca sativa) optimized the environmental parameters, while the subsequent experiments with pepper (Capsicum annuum), a commercially important and environmentally sensitive crop, demonstrated system performance under real-world conditions. The control system maintained a temperature and humidity within ±0.3 °C and ±1.2% of the setpoints, respectively, and outperformed the baseline rule-based control with a 28% increase in fresh biomass, a 22% improvement in dry matter accumulation, a 25% reduction in actuator duty-cycle switching, and an 18% decrease in overall energy consumption. These results highlight the efficacy of FPGA-integrated edge intelligence combined with low-latency IoT telemetry as a scalable, energy-efficient, and high-fidelity solution for sub-degree environmental control in next-generation, controlled-environment, and vertical farming systems. Full article

The tomato hind (Cephalopholis sonnerati) is a marine aquaculture fish species with high economic value. Elucidating the mechanisms underlying its growth regulation is crucial for the development of the aquaculture industry. To analyze the biological mechanisms underlying growth differences, individuals with extreme body sizes at 8 months of age from the same batch were selected in this study. A combined experiment of “body size × feeding status” was constructed, and transcriptome sequencing and weighted gene co-expression network analysis (WGCNA) were performed on brain and muscle tissues. The results showed that 2553 differentially expressed genes (DEGs) were identified between individuals with distinct body sizes, which were significantly enriched in growth regulation pathways such as PI3K–Akt, MAPK, and FoxO. Feeding differences affected 4480 genes, which were significantly enriched in signaling pathways including the insulin signaling pathway. WGCNA further identified co-expression modules (brown4, blue, coral1) significantly correlated with growth, as well as hub genes including pik3r1 and eif4ebp2. Comprehensive analysis demonstrated that the growth regulation of C. sonnerati operates as a cascade network. Brain tissues perceive signals through neuroactive ligand–receptor interactions and integrate and transduce these signals via core pathways including Ras–MAPK and PI3K–Akt. Finally, growth processes are executed in muscle tissues by regulating glycogen metabolism, protein synthesis, and other processes, which are precisely regulated by terminal processes such as cellular senescence. Among them, pik3r1 and eif4ebp2, as key molecular switches, play a central role in integrating upstream signals and precisely regulating downstream growth programs. This study preliminarily clarifies the molecular mechanism network of growth differences in C. sonnerati, providing a theoretical basis and candidate genes for the genetic improvement of its growth traits. Full article

Rapid expansion of electric vehicle adoption has led to increased dependence on a charging infrastructure that is tightly integrated with energy distribution systems and digital communication networks. As electric vehicle charging stations evolve into complex cyber–physical systems, cybersecurity risks pose a growing threat to grid reliability and user trust. This paper presents a hybrid decision-support framework for cybersecurity risk assessment in EV charging infrastructure that advances beyond prior multi-criteria decision-making approaches by combining interpretability with data-driven validation. Specifically, the framework integrates the Analytic Hierarchy Process (AHP) for expert-driven weighting of cybersecurity attributes with PROMETHEE for flexible threat prioritization, enabling transparent and auditable risk rankings. The framework categorizes cybersecurity criteria across four infrastructure layers—transmission, distribution, consumer, and electric vehicle charging stations—and assigns relative weights through expert-driven pairwise comparisons. PROMETHEE is then applied to rank potential cyber threats based on these weights, allowing for flexible prioritization of cybersecurity interventions. The methodology is validated using the real-world WUSTL-IIoT-2018 SCADA dataset, which includes simulated reconnaissance (network scanning), device identification, and exploitation attacks. While this dataset does not natively include OCPP 2.0 or ISO 15118 protocols, the experimental results demonstrate strong discrimination power (AUC = 0.99, recall = 95%) and provide a basis for extension to modern EVSE communication standards. The results identify critical metrics such as anomalous source packet behavior and encryption reliability as key vulnerability markers, aligning with documented EV charging attack scenarios. By bridging expert judgment with empirical traffic data, the proposed framework offers both technical robustness and explainability, supporting grid operators, SOC teams, and infrastructure planners in systematically assessing risks, allocating resources, and enhancing the resilience of EV charging ecosystems against evolving cyber threats. Full article

This study systematically investigates the formulation–property relationships of epoxy-based silver conductive adhesives by varying silver filler architecture, total filler loading, and organic carrier design. Rotational viscometry, four-point probe measurements, thermal conductivity analysis, and scanning electron microscopy (SEM) were employed to elucidate the correlations among rheological behavior, conductive network formation, and electrical–thermal transport properties. All formulations incorporate dicyandiamide (DICY) as a latent curing agent, in combination with a thermally activated accelerator and silane coupling agents, to stabilize filler–matrix interfaces and suppress moisture-assisted side reactions. This latent curing chemistry enables effective low temperature curing at approximately 155 °C, providing compatibility with temperature-sensitive flexible polymer substrates. After sealed storage at 25 °C and 60% relative humidity for two weeks, all formulations exhibited viscosity variations within ≤16%, demonstrating extended pot life and good storage stability under ambient conditions. Meanwhile, the normalized volume resistivity and thermal conductivity remained close to their initial values, with maximum relative deviations of approximately 12% and 7%, respectively, from the initial (Day 0) values across all formulations, indicating stable electrical and thermal transport properties during storage. Differences in conductive network formation and filler packing characteristics were reflected in the observed electrical and thermal transport behaviors. Balanced electrical–thermal performance was achieved without the need for high-temperature sintering or post-annealing, underscoring the effectiveness of the low temperature curing strategy. Overall, this work defines a practical formulation design window that simultaneously achieves low temperature curability, long pot life, stable rheology, and robust electrical–thermal performance. The results provide useful material-level guidelines for the development of epoxy-based silver conductive adhesives intended for conductive interconnects on flexible polymer substrates and related flexible electronic applications. Full article

WSN node energy forecasting contributes to improving network efficiency, extending network lifespan, and providing energy management strategies. In this study, a deep-learning-based wireless sensor network (WSN) node energy forecasting model based on Long Short-Term Memory (LSTM) and stacked-LSTM was developed across different wireless communication technologies in both static and dynamic WSN setups. The performance of the deep-learning-based models was compared with traditional forecasting techniques such as Exponential Smoothing and Prophet. The results showed the superiority of LSTM and stacked-LSTM in terms of root mean square error and mean absolute error, with consistently lower values compared with the traditional forecasting techniques. The results also show that the models perform best with Long Range technology. The deep learning-based model also demonstrates its ability to perform better in both static and dynamic WSN scenarios. These results demonstrate the potential of deep-learning-based models in WSN node energy management, which can result in an optimal energy efficiency and prolong the network lifetime. Future research is needed to explore hybrid approaches to further improve the prediction performance of deep learning-based models by combining their strengths with statistical or traditional forecasting techniques. Full article

Meat quality serves as a pivotal determinant of consumer purchasing behavior and of the economic viability of the livestock industry; as such, research into its regulatory mechanisms is of critical significance for the development of modern agriculture. Traditional investigations into meat quality have predominantly centered on sensory and physicochemical assessments of ultimate phenotypic traits, thereby facing inherent limitations in systematically deciphering the intricate molecular regulatory networks underlying meat quality formation. By contrast, an integrated analysis of the transcriptome and metabolome effectively connects the cascade of “gene transcription—metabolic regulation—phenotypic determination,” which has emerged as a core methodological paradigm in contemporary research on the molecular mechanisms governing meat quality. This review systematically delineates the evolutionary trajectory and principal technological frameworks of meat quality evaluation systems, with a focused synthesis of recent advances achieved through combined transcriptomic and metabolomic analyses in the field of meat quality regulation. The scope of this review encompasses core transcriptional regulatory networks associated with meat quality attributes, pivotal metabolic pathways, signal transduction mechanisms, and protein degradation dynamics. Furthermore, the regulatory impacts exerted by genetic variation among breeds, nutritional modulation, rearing environments, and stress responses on meat quality characteristics are comprehensively elucidated. Integrative analysis reveals that combined transcriptome–metabolome approaches transcend the inherent limitations of single-omics investigations, systematically unraveling the hierarchical regulatory mechanisms governing fundamental meat quality traits, such as muscle fiber type differentiation, postmortem glycolytic progression, intramuscular fat deposition, and flavor compound accumulation. Such integrative strategies have facilitated the identification of functional genes and metabolic biomarkers with potential utility for the early prediction of meat quality outcomes. Concurrently, this review acknowledges persistent challenges confronting the field, including the absence of standardized protocols for multi-omics data integration, insufficient functional causal validation, and a discernible disconnect between research discoveries and practical industrial implementation. Building upon this comprehensive assessment, prospective directions for future multi-omics research in meat quality are proposed, accompanied by the formulation of an integrated end-to-end improvement framework spanning fundamental research, technological innovation, and industrial application. Collectively, this review provides a systematic theoretical foundation for the in-depth elucidation of mechanisms that determine meat quality and the precision-oriented regulation of quality-determining traits in livestock production practices, thereby offering substantial scientific guidance for quality improvement initiatives within the animal husbandry sector. Full article

Background/Objectives: Intrapulmonary metastasis (IPM) after an initial single primary lung cancer (SPLC) is an adverse follow-up pattern; however, when studying population-based longitudinal records, the determinants remain unclear. We aimed to identify factors associated with subsequent IPM after initial SPLC using artificial intelligence (AI)-driven analytical approaches. Methods: We used Surveillance, Epidemiology, and End Results (SEER) lung cancer records from 2000 to 2019. Adults with at least two records were restricted to those with SPLC at the first record. Outcome at the second record was registry-classified IPM versus persistent SPLC. A machine learning framework based on random forest models was developed using baseline variables, first record characteristics, and the interval between records. Temporal validation was performed by training on cases from 2000 to 2013 and testing on cases from 2014 to 2019. A dynamic Bayesian network (DBN) supported simulated intervention (SI) analyses to estimate model-implied risk ratios (RRs) with 95% confidence intervals (CIs). Results: Among 3450 patients, 361 had registry-classified IPM at the second record. The random forest model achieved an area under the curve (AUC) of 0.852 in internal validation and 0.929 in temporal validation. Surgery and record timing were the leading predictors. The DBN retained surgery as the only direct parent and achieved an AUC of 0.779. SI analyses showed higher IPM probability for pleural invasion level (PL) 3 versus PL 0, RR 1.378 (95% CI, 1.080–1.657). Lobectomy with mediastinal lymph node dissection versus wedge resection lowered the IPM probability, RR 0.378 (95% CI, 0.219–0.636). Conclusions: AI-based time-sequence modeling integrating machine learning and a DBN allowed for the identification of surgery, pleural invasion, and record timing as key factors associated with subsequent IPM classification after initial SPLC. This framework demonstrates the potential of combining predictive and probabilistic dependency modeling to investigate registry-based disease classification patterns, and may support hypothesis generation for future prospective studies. Full article

Accurate feature selection is critical for machine learning in medical diagnosis, yet conventional methods often fail to capture complex non-linear relationships in biomedical data. This study introduces an advanced feature selection approach that integrates distance correlation with adaptive weighting to enhance cardiac arrhythmia detection. The proposed method ranks features based on distance correlation, applies an inverse penalty weighting scheme to suppress highly correlated features while emphasizing moderately correlated ones, and incorporates RBF kernel transformation followed by LASSO refinement. Fifteen feature selection techniques were evaluated on an electrocardiographic database of 279 morphological and physiological features using 4-fold cross-validation with a neural network classifier. The proposed method outperformed all alternatives, including the best conventional approach, by effectively capturing non-linear dependencies, mitigating multicollinearity and overfitting, and leveraging synergistic kernel-based interaction modeling with sparse selection. These results demonstrate that combining statistical dependence measures, adaptive regularization, and non-linear transformations provides a robust framework for feature selection in cardiac arrhythmia classification and broader medical informatics applications. Full article