Results of the incremental PCA [8] on the cumulative energy stopping rule: θ1 = 0.7, θ2 = 0.8, θ3 = 0.9, θ4 = 0.99.

Large-scale weather forecasting is critical for ensuring maritime safety and optimizing transoceanic voyages. However, sparse meteorological data, incomplete forecasts, and unreliable communication hinder accurate, high-resolution wind system predictions. This study addresses these challenges to enhance dynamic voyage planning and intelligent ship navigation. We propose IPCA-MHA-DSRU-Net, a novel deep learning model integrating incremental principal component analysis (IPCA) with a spatial-temporal depthwise separable U-Net. Key components include: (1) IPCA preprocessing to reduce dimensionality and noise in 2D wind field data; (2) depthwise-separable convolution (DSC) blocks to minimize parameters and computational costs; (3) multi-head attention (MHA) and residual mechanisms to improve spatial-temporal feature extraction and prediction accuracy. The framework is optimized for real-time onboard deployment under communication constraints. The model achieves high accuracy in high-resolution wind predictions, validated through reanalysis datasets. Experiments demonstrated enhanced path planning efficiency and robustness in dynamic oceanic conditions. The IPCA-MHA-DSRU-Net balances computational efficiency and accuracy, making it viable for resource-limited ships. This novel IPCA application provides a promising alternative for preprocessing large-scale meteorological data.

Additional file 8 Pair plots of all the pCA (PBMCs) implementations.

Additional file 11 Pair plots of all the pCA (Brain) implementations.

Additional file 15 Crashed jobs caused by out-of-memory errors.

Additional file 25 Comparison of normalizing size factors.

Road safety and accident prevention are critical concerns in modern transportation. This paper presents a comprehensive survey of driver safety systems, focusing on the latest advancements in this field. We analyze the existing literature to identify key research trends in driver safety systems, encompassing various categories of solutions. Our survey delves into the reasons behind road accidents and assesses the effectiveness of emerging technologies and solutions in accident prevention. By categorizing and evaluating these solutions based on the Internet of Things and Machine Learning, we provide valuable insights into the landscape of road accident detection and prevention systems. This survey not only highlights the current state of the art but also serves as a reference for future research and innovation in the domain of driver safety. Abbreviations IoT: Internet of things; CNN: Convolutional Neural Network; SVM: Support vector machine; HRV: Heart rate variability; RRI: R-R Interval; MSPC: Multivariate Statistical process control; EAR: Eye aspect ratio; HUD: Head-up display; GPS: Global positioning system; CAN: Controller area network; GPU: Graphics processing unit; IR: Infrared; GSM: Global system for mobile communication; EEG: Electroencephalogram; PCA: Principal component analysis; SVC: Support vector classifier; SdsAEs: Stacked denoising sparse autoencoders; ECG: Electrocardiogram; LED: Light emitting diode; NFC: Near field communication; PSO: Personal security officer; PPG: Photoplethysmography; EDA: Electrodermal activity; EMG: Electromyography; LCD: Liquid crystal display; RF SoCs: Radiofrequency system on chip; PLR: Piecewise linear representation; BAC: Blood alcohol content; BPNN: Backpropagation Neural Network; ADSD: Automated driver sleepiness detection; EOG: Electroocoulogram; KNN: K nearest neighbor; CBR: Case-based reasoning; RF: Random forest; NIR: Near-infrared; LBP: Local binary pattern; PERCLOS: Percentage of Eye Closure; SVD: Singular value decomposition; FFT: Fast Fourier transform; LSTM: Long short-term memory; DDD: Drunk driver detection; BLE: Bluetooth low energy; SWM: Steering wheel movements; M-SVM: Mobile-based Support Vector Machine; AI: Artificial intelligence; ML: Machine learning; DL: Deep learning; PCA: Principal component analysis; IPCA: Incremental principal component analysis; ANN: Artificial neural network; CAV: Connected and automated vehicles

This dataset includes processed PCA of ankle and subtalar joint angles and momoments while performing the badminton footwork, right-forward (RF), left-forward (LF), cross-step (CS), and side-step (SS) with novel badminton shoes with incremental lateral wedge hardness (LN55, LN60, LN65, and LN70).

Table shows the network community structures (NCS) that were most similar to the confirmatory 5, 6, 7, 8, 9, and 10 principal component structure (PCS) of the CPRS dataset. Component structure: the component structure that was matched against the candidate network community structures obtained from the incremental pruning procedure (see Materials and Methods). Principal Component: the number of the principal component from this component structure. % mismatch per cluster: the percentage of items in a network cluster of the most similar NCS that did not match the item content of its corresponding principal component. % overall mismatch: the percentage of items in the entire NCS that did not match its corresponding PCS. ABS(r): the absolute value of the correlation coefficient at which the optimal match with a NCS was found. p: the corresponding p value. Nrnodes: number of nodes left in the NCS at this threshold (some nodes dropped off the network due to incremental pruning, see text).Table showing the quantitative results of the cluster-to-component matching procedure.

Soybean is often damaged by hypoxia caused by waterlogging at the seedling stage. Hypoxia severely inhibits root development and retards plant growth. We aimed to clarify phenotypic variation in root development under hypoxia condition at the seedling stage using diverse soybean accessions. Root development in 162 accessions was evaluated in hydroponic culture. Substantial changes under hypoxia were investigated by means of WinRHIZO analysis before and after the treatment. We found significant phenotypic variation in hypoxia tolerance in root among the 162 accessions. A principal components analysis indicated an association between hypoxia tolerance and the country of origin. We found three new accessions which have a high ability to develop roots under hypoxia (Kokubu 7, Maetsue zairai 90B, and Yahagi). Root development in selected accessions was also evaluated in soil culture. Root development levels in hydroponic and soil culture were significantly correlated. These results will provide important information on waterlogging damage in regions where waterlogging occurs. The three accessions with hypoxia-tolerant roots might be useful for genetic improvement of waterlogging tolerance of modern soybean varieties.

Exposure parameters used in the incremental lifetime cancer risk (ILCR) assessment.