Stream gauge height (water level) is a significant indicator for forecasting future floods. Flooding occurs when the water level exceeds the flood stage. Predicting imminent floods can save lives, protect infrastructure, and improve road traffic management and transportation. Deep neural networks have been increasingly used in this domain due to their predictive capabilities in capturing complex features and interdependencies. This study employs four distinct models—Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), transformer, and LSTNet—with MLP serving as the baseline model to forecast water levels. The models are trained using data from 20 distinct river gages across the state of Missouri to ensure consistent performance. Random search optimization is employed for hyperparameter tuning. The prediction intervals are set at 4, 6, 8, and 10 (each interval equivalent to 30 min) to ensure that performance results are robust and not due to random weight initialization or suboptimal hyperparameters and are consistent throughout different prediction intervals. The findings of this study indicate that the LSTNet model leads to a better performance than the other models, with a median RMSE of 0.00724, 0.00959, 0.01204, and 0.01230 for the 4, 6, 8, and 10 intervals, respectively. As climate change leads to localized storms driven by atmospheric shifts, water level fluctuations are becoming increasingly extreme, further exacerbating data drift in real-world datasets. The LSTNet model demonstrates superior performance in terms of RMSE, MAE, and the correlation coefficient across all prediction intervals when forecasting water levels under data drift conditions.

This study aims to deepen the understanding and classification of tinnitus through a comprehensive analysis of EEG signals utilizing innovative microstate analysis techniques and cutting-edge machine learning approaches. EEG data were collected from two datasets: a primary dataset with 36 participants (16 healthy, 20 tinnitus) and a public dataset with 37 participants (15 healthy, 22 tinnitus). Signals were decomposed into five frequency bands (delta, theta, alpha, beta, gamma) using Daubechies 4 wavelet at five decomposition levels. Microstate features (Duration, Occurrence, Mean Global Field Power, and Coverage) were extracted across four microstate configurations (4-state to 7-state) under both eyes-closed and eyes-open conditions. Classification was performed using SVM, Decision Tree, Random Forest, and Deep Neural Networks. Additionally, pre-trained models (VGG16, ResNet50, Xception) were used with a novel feature-to-image transformation approach for validation. Analysis revealed significant alterations in beta band microstates, with microstate A showing increased duration (+ 7.8% to + 11.2%) and microstate B showing decreased duration (− 9.0% to − 13.8%) in tinnitus patients. Occurrence rates were markedly elevated (~ 28–29% higher) in the tinnitus group. Transition probability analysis identified distinctive patterns between groups, with the most pronounced differences observed in gamma band (6-state configuration) during eyes-closed condition (healthy: F → B = 0.143; tinnitus: C → D = 0.153) and beta band (7-state configuration) also during eyes-closed condition (healthy: E → A = 0.091; tinnitus: C → E = 0.082). In the eyes-open condition, gamma band with 7 microstates showed substantial differences in transition patterns (healthy: E → A = 0.149; tinnitus: C → G = 0.157). Classification performance was exceptional, with DNN achieving 100% accuracy in the gamma frequency band during eyes-open condition with 5-state configuration. Frequency band analysis demonstrated that gamma band performed best for open eyes (99.89% accuracy) and beta band excelled for closed eyes (96.46% accuracy). Validation with pre-trained models showed ResNet50 with SVM classifier using 6-state configurations provided optimal discrimination (100% accuracy). EEG microstate dynamics in beta and gamma bands serve as reliable markers for distinguishing tinnitus patients. These findings provide insights into tinnitus-related neural alterations and highlight microstate analysis as a potential objective diagnostic tool for guiding personalized neuromodulation therapies.

This study developed and evaluated a hybrid deep learning framework for automated lung segmentation and multi-class severity classification in chest CT scans, addressing key methodological gaps including heterogeneous dataset labeling, pseudo-label bias in segmentation, limited interpretability of intensity thresholds, and unvalidated preprocessing effects. A dataset of 3,921 chest CT images from three geographically distinct sources (Iran, Bangladesh, Iraq) was harmonized into four severity classes (No Lesion, Mild, Moderate, Severe) through a structured expert annotation protocol (κ = 0.847) and augmented to 4,392 balanced samples. U-Net architectures with three CNN backbones (VGG16, ResNet50, Xception) were trained for lung segmentation with CLAHE preprocessing and evaluated against both morphological pseudo-labels and independently annotated expert ground truth. A novel Brightness Intensity Range (BIR) classifier analyzed pixels within the normalized intensity range [0.35, 0.70], corresponding to approximately − 450 to + 100 HU and encompassing ground-glass opacities and partial consolidation, using perimeter-to-area ratio thresholds for severity stratification. Hybrid classification pipelines combined CNN feature extraction with SVM, Gradient Boosting, and Logistic Regression classifiers. A controlled ablation study isolated the contribution of each preprocessing step. All models were evaluated using patient-level fivefold cross-validation to prevent data leakage between training and test partitions. The VGG16-based U-Net achieved 98.1% segmentation accuracy with a Dice coefficient of 0.927 against pseudo-labels and 0.921 ± 0.089 against expert annotations, confirming that pseudo-label training introduced no systematic bias. ResNet50 + GradientBoosting achieved the highest classification accuracy of 96.35 ± 0.82% with ROC-AUC exceeding 99% across all classes. The BIR-VGG16 model reached 94.8% accuracy with ROC-AUC values of 0.963 to 0.988. The ablation study identified normalization as the dominant preprocessing contributor (34.3% accuracy gain), followed by CLAHE (21.7%) and resizing (6.0%), mechanistically explaining the large performance gap between preprocessed and non-preprocessed conditions. Cross-dataset generalization yielded 93.78% accuracy on an independent cohort. The proposed framework demonstrates superior performance, methodological transparency, and clinical viability. The explicit HU-grounded BIR thresholds, expert-validated segmentation, and ablation-confirmed preprocessing rationale collectively enhance the generalizability of the approach for automated lung pathology assessment.