Combination Of Features Research Articles

Feasibility of Acoustic Features of Vowel Sounds in Estimating the Upper Airway Cross Sectional Area during Wakefulness: A Pilot Study

Assessment of upper airway dimensions has shown great promise in understanding the pathogenesis of obstructive sleep apnea (OSA). However, the current screening system for OSA does not have an objective assessment of the upper airway. The assessment of the upper airway can accurately be performed by MRI or CT scans, which are costly and not easily accessible. Acoustic pharyngometry or Ultrasonography could be less expensive technologies, but these require trained personnel which makes these technologies not easily accessible, especially when assessing the upper airway in a clinic environment or before surgery. In this study, we aimed to investigate the utility of vowel articulation in assessing the upper airway dimension during normal breathing. To accomplish that, we measured the upper airway cross-sectional area (UA-XSA) by acoustic pharyngometry and then asked the participants to produce 5 vowels for 3 seconds and recorded them with a microphone. We extracted 710 acoustic features from all vowels and compared these features with UA-XSA and developed regression models to estimate the UA-XSA. Our results showed that Mel frequency cepstral coefficients (MFCC) were the most dominant features of vowels, as 7 out of 9 features were from MFCC in the main feature set. The multiple regression analysis showed that the combination of the acoustic features with the anthropometric features achieved an R2 of 0.80 in estimating UA-XSA. The important advantage of acoustic analysis of vowel sounds is that it is simple and can be easily implemented in wearable devices or mobile applications. Such acoustic-based technologies can be accessible in different clinical settings such as the intensive care unit and can be used in remote areas. Thus, these results could be used to develop user-friendly applications to use the acoustic features and demographical information to estimate the UA-XSA.

Preoperative Prediction of Lymph Node Metastases in Nonfunctional Pancreatic Neuroendocrine Tumors Using a Combined CT Radiomics-Clinical Model.

PanNETs are a rare group of pancreatic tumors that display heterogeneous histopathological and clinical behavior. Nodal disease has been established as one of the strongest predictors of patient outcomes in PanNETs. Lack of accurate preoperative assessment of nodal disease is a major limitation in the management of these patients, in particular those with small (< 2cm) low-grade tumors. The aim of the study was to evaluate the ability of radiomic features (RF) to preoperatively predict the presence of nodal disease in pancreatic neuroendocrine tumors (PanNETs). An institutional database was used to identify patients with nonfunctional PanNETs undergoing resection. Pancreas protocol computed tomography was obtained, manually segmented, and RF were extracted. These were analyzed using the minimum redundancy maximum relevance analysis for hierarchical feature selection. Youden index was used to identify the optimal cutoff for predicting nodal disease. A random forest prediction model was trained using RF and clinicopathological characteristics and validated internally. Of the 320 patients included in the study, 92 (28.8%) had nodal disease based on histopathological assessment of the surgical specimen. A radiomic signature based on ten selected RF was developed. Clinicopathological characteristics predictive of nodal disease included tumor grade and size. Upon internal validation the combined radiomics and clinical feature model demonstrated adequate performance (AUC 0.80) in identifying nodal disease. The model accurately identified nodal disease in 85% of patients with small tumors (< 2cm). Non-invasive preoperative assessment of nodal disease using RF and clinicopathological characteristics is feasible.

Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image and Video Forgeries

This paper introduces a hybrid architecture combining Long Short-Term Memory (LSTM) networks and an encoderdecoder model for the detection and localization of image and video forgeries. The proposed system leverages resampling features and LSTM cells to identify manipulation patterns such as splicing and retouching in multimedia content. By utilizing a combination of spatial and temporal features, the model achieves high precision in detecting forged regions. Extensive testing on diverse datasets demonstrates the robustness of the proposed method.

Prediction of microvascular invasion in hepatocellular carcinoma with conventional ultrasound, Sonazoid-enhanced ultrasound, and biochemical indicator: a multicenter study

PurposeTo develop and validate a preoperative prediction model based on multimodal ultrasound and biochemical indicator for identifying microvascular invasion (MVI) in patients with a single hepatocellular carcinoma (HCC) ≤ 5 cm.MethodsFrom May 2022 to November 2023, a total of 318 patients with pathologically confirmed single HCC ≤ 5 cm from three institutions were enrolled. All of them underwent preoperative biochemical, conventional ultrasound (US), and contrast-enhanced ultrasound (CEUS) (Sonazoid, 0.6 mL, bolus injection) examinations. Univariate and multivariate logistic regression analyses on clinical information, biochemical indicator, and US imaging features were performed in the training set to seek independent predictors for MVI-positive. The models were constructed and evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis in both validation and test sets. Subgroup analyses in patients with different liver background and tumor sizes were conducted to further investigate the model’s performance.ResultsLogistic regression analyses showed that obscure tumor boundary in B-mode US, intra-tumoral artery in pulsed-wave Doppler US, complete Kupffer-phase agent clearance in Sonazoid-CEUS, and biomedical indicator PIVKA-II were independently correlated with MVI-positive. The combined model comprising all predictors showed the highest AUC, which were 0.937 and 0.893 in the validation and test sets. Good calibration and prominent net benefit were achieved in both sets. No significant difference was found in subgroup analyses.ConclusionsThe combination of biochemical indicator, conventional US, and Sonazoid-CEUS features could help preoperative MVI prediction in patients with a single HCC ≤ 5 cm.Critical relevance statementInvestigation of imaging features in conventional US, Sonazoid-CEUS, and biochemical indicators showed a significant relation with MVI-positivity in patients with a single HCC ≤ 5 cm, allowing the construction of a model for preoperative prediction of MVI status to help treatment decision making.Key PointsMVI status is important for patients with a single HCC ≤ 5 cm.The model based on conventional US, Sonazoid-CEUS and PIVKA-II performs best for MVI prediction.The combined model has potential for preoperative prediction of MVI status.Graphical

Multi-modality deep learning model for prediction of chronic obstructive coronary artery disease

Abstract Background/Introduction The incidence of coronary artery disease (CAD) is on the rise with an increasing burden of stable ischemic heart disease (SIHD) and high prevalence of obesity, diabetes, hyperlipidemia, and other cardiovascular risk factors. Pre-test probability estimation for CAD based on demographic features and characterization of chest pain is insufficient to accurately assess whether further evaluation for CAD is warranted. Purpose To develop and validate a deep learning (DL) algorithm utilizing electrocardiogram (ECG) waveforms and clinical features to predict obstructive CAD. Methods Clinical data from subjects undergoing invasive angiography over a 4-year period at a quaternary care center exclusive of subjects who had concern for acute coronary syndromes were used for model training. ECGs obtained up to 5 years prior to angiography were included; ECGs were partitioned 8:1:1 for training, validation, and test datasets. Obstructive CAD was defined as receiving percutaneous coronary intervention during elective angiography. Convolutional neural network models were developed for ECG waveforms alone (DL-ECG), clinical features from standard risk scores (DL-Clinical), and the combination of ECG waveforms and clinical features (DL-ECG+Clinical); a commonly used pre-test probability estimation tool derived from the CAD Consortium study was used as a comparison (PTP). The models were evaluated based on area under the curve receiver operating characteristics (AUC). Shapley additive explanations (SHAP) analysis was performed to understand feature importance in the DL models. Results A total of 40,602 ECGs and 8,361 coronary angiograms from 7,201 patients were included in the analysis. The median age was 66 (IQR 56-75), 71.9% were men, 34.9% had hypertension, 30.6% had diabetes mellitus, and 39.0% had dyslipidemia. The PTP model (AUC 0.733 [0.717-0.750]) had similar performance as the DL-Clinical model (AUC 0.762 [0.746-0.778]). The DL-ECG model (AUC 0.741 [0.726-0.758]) had similar performance as both the clinical feature models. The DL-ECG+Clinical model (AUC 0.807 [0.793-0.822]) trained on ECG waveforms and clinical features had a superior performance (Figure 1). SHAP analysis for the DL-ECG+Clinical model revealed that ECG waveforms had the largest influence on the model’s output followed by age and chest pain type (Figure 2). Conclusions Multi-modality DL model utilizing ECG and commonly used features can improve prediction of obstructive CAD in SIHD compared to traditional pre-test probability estimates. Prospective research is warranted to determine whether incorporation of DL methods to ECG analysis effectively improves diagnosis and outcomes in obstructive CAD.Figure 1.Figure 2.

Combined mammographic breast density and breast arterial calcification is incrementally predictive of coronary artery disease beyond traditional risk factors

Abstract Background Coronary artery disease (CAD) risk is underestimated in women using current risk stratification tools. The mammographic finding of breast arterial calcification (BAC) associates with CAD. Furthermore, breast adipose tissue, measured through breast density (BD) on mammography (low breast density indicates high adiposity) has shown potential to act as a pro-inflammatory, pro-atherogenic fat deposit. Given its uptake in screening programs, mammography may therefore represent a novel risk stratification tool for cardiovascular disease in women. Purpose To evaluate the association between the combined mammographic features of BD and BAC, with CAD. Methods Single-centre, retrospective, cross-sectional study, including 153 women, mean age 62±10, who had both clinically indicated mammography, and coronary computed tomography angiogram (CCTA) for suspected CAD. CAD risk was identified by the CAD Consortium Score, with a 15% threshold for low and high risk. BD was visually assessed and categorised by 4-level BI-RADS grade with grade A-B representing low density, and C-D representing high density (Figure 1). BAC was visually assessed and categorised as present/absent (Figure 1). CAD was categorised as presence/absence of coronary artery plaque on CCTA. Logistic regression was performed with results presented as Odds Ratio (OR) and [95% Confidence Intervals]. Receiver operator characteristic area under the curve (AUC) was used for model discrimination. Results Low BD (n=103 (67%)) was associated with CAD (OR 3.20 [1.58-6.53], p=0.001, as was BAC presence (n=37 (24%), OR 4.36 [1.58-12], p=0.004). There were 51 (33%) with elevated CAD risk. Participants were categorised into 4 subgroups based on low/high BD and presence/absence of BAC: 29 (19%) had low BD and BAC, 74 (48%) had low BD and no BAC, 8 (5%) had high BD and BAC and 42 (27%) had high BD and no BAC. Significantly higher proportions of CAD were noted with low BD and BAC alone, as well as combined low BD and BAC (Figure 2). Compared with high BD/BAC negative, the presence of low BD and BAC independently associated with CAD (OR 5.27 [1.19-23.3], p=0.03). Significant incremental benefit was seen after adding BD/BAC status to CAD Consortium Score (AUC 0.65 vs. 0.72, p=0.004). Conclusions Combined, and individual mammographic features of low BD and BAC presence are associated with CAD and improve risk prediction beyond standard coronary risk probabilities. Standardised reporting of these features to inform risk identification may be of further benefit and should be tested in prospective screening studies.

Quantitative texture analysis using machine learning for predicting interpretable pulmonary perfusion from non-contrast computed tomography in pulmonary embolism patients

BackgroundPulmonary embolism (PE) is life-threatening and requires timely and accurate diagnosis, yet current imaging methods, like computed tomography pulmonary angiography, present limitations, particularly for patients with contraindications to iodinated contrast agents. We aimed to develop a quantitative texture analysis pipeline using machine learning (ML) based on non-contrast thoracic computed tomography (CT) scans to discover intensity and textural features correlated with regional lung perfusion (Q) physiology and pathology and synthesize voxel-wise Q surrogates to assist in PE diagnosis.MethodsWe retrospectively collected 99mTc-labeled macroaggregated albumin Q-SPECT/CT scans from patients suspected of PE, including an internal dataset of 76 patients (64 for training, 12 for testing) and an external testing dataset of 49 patients. Quantitative CT features were extracted from segmented lung subregions and underwent a two-stage feature selection pipeline. The prior-knowledge-driven preselection stage screened for robust and non-redundant perfusion-correlated features, while the data-driven selection stage further filtered features by fitting ML models for classification. The final classification model, trained with the highest-performing PE-associated feature combination, was evaluated in the testing cohorts based on the Area Under the Curve (AUC) for subregion-level predictability. The voxel-wise Q surrogate was then synthesized using the final selected feature maps (FMs) and model score maps (MSMs) to investigate spatial distributions. The Spearman correlation coefficient (SCC) and Dice similarity coefficient (DSC) were used to assess the spatial consistency between FMs or MSMs and Q-SPECT scans.ResultsThe optimal model performance achieved an AUC of 0.863 during internal testing and 0.828 on the external testing cohort. The model identified a combination containing 14 intensity and textural features that were non-redundant, robust, and capable of distinguishing between high- and low-functional lung regions. Spatial consistency assessment in the internal testing cohort showed moderate-to-high agreement between MSMs and reference Q-SPECT scans, with median SCC of 0.66, median DSCs of 0.86 and 0.64 for high- and low-functional regions, respectively.ConclusionsThis study validated the feasibility of using quantitative texture analysis and a data-driven ML pipeline to generate voxel-wise lung perfusion surrogates, providing a radiation-free, widely accessible alternative to functional lung imaging in managing pulmonary vascular diseases.Clinical trial numberNot applicable.

Integrative machine learning model for predicting patient-oriented composite endpoints in acute myocardial infarction: a neuroendocrine biomarker approach

Abstract Background Acute Myocardial Infarction (AMI) represents a significant clinical challenge with diverse outcomes. Predicting patient-oriented composite endpoints (POCE) (all-cause death, any stroke, any AMI, or any revascularization) can significantly enhance post-AMI care. Incorporating clinical data with neuroendocrine biomarkers may offer improved prognostic capabilities. Objective To develop and validate a machine learning model to predict POCE in AMI patients, utilizing clinical parameters and neuroendocrine biomarkers. Methods There was prospective, observational, single-center study. Three approaches have been used to obtain the predictions for POCE event. First, as the dataset was imbalanced, an adaptive synthetic (ADASYN) sampling approach was used to generate synthetic instances, particularly focusing on those that are difficult-to-learn by using a weighted distribution. Then, random forest classifier (RF) was used to build a machine learning model to predict POCE. The model was tuned via a grid-search algorithm for optimal hyperparameters and validated using a 10-fold stratified cross-validation. Finally, the feature importance was determined by Shapley Additives, which measure the average marginal contribution of a feature value across all potential feature combinations. For the comparative purpose, the Gini index, which also shows the feature importance but in terms of mean decrease in impurity, was calculated. Results The study incorporated data from 315 patients, examining 47 variables and identifying 72 instances of POCE. After applying the ADASYN algorithm, the class distribution within the dataset was effectively equalized, facilitating the training of a robust RF model. Upon training with 252 instances, the model distinguished POCE with an accuracy of 83.8%, demonstrating a sensitivity of 80% and a specificity of 86%. During 10-fold cross-validation, the model's accuracy slightly dipped to 75%, with a sensitivity of 56% and specificity of 82%, indicating a balance between generalizability and overfitting. Testing mirrored these results, underscoring the model’s consistent performance. Notably, SHAP value analysis highlighted C-Reactive Protein (CRP) and alanine transaminase (ALT) as the most influential features, underscoring their significance in the context of AMI (Figure 1-2). The predictive power of each feature was further demonstrated by the mean decrease in Gini index (Figure 1-2). Conclusion Our study highlights the feasibility of employing machine learning to predict POCE post-AMI using an integrative dataset of clinical and neuroendocrine markers. The predictive model has the potential to revolutionize post-AMI care by allowing clinicians to identify high-risk patients early, tailor interventions, and allocate resources efficiently. Future research could explore the integration of this model into clinical workflows and its impact on patient outcomes.

Clinical course and prognosis of patients with idiopathic pulmonary arterial hypertension after COVID-19

The coronavirus disease of 2019 (COVID-19) is an infectious disease caused by severe acute respiratory coronavirus (SARS-CoV-2). This virus has many factors in its pathogenesis that affect the function of the right ventricle and pulmonary hemodynamics, which can negatively influence the clinical course of IPAH. According to the results of our study, the fact of getting over COVID-19 in patients with IPAH leads to some changes in laboratory and instrumental parameters. But no significant effect of COVID-19 on risk modification during the year was detected. This result can be explained by a combination of pathophysiological features of the pulmonary hypertension and the protective effect of constantly taken PAH-specific and anticoagulant therapy.

Selection of optimal spectral features for leaf chlorophyll content estimation

Leaf chlorophyll content (LCC) is crucial for monitoring the physiological processes of crops. Many studies have utilized spectral features to develop regression models for accurate LCC estimation, enabling the quantitative assessment and evaluation of crop growth status. The selection of optimal spectral features and regression algorithms significantly affects the precision of LCC estimation. In this study, we compared and analyzed the optimal spectral features for LCC estimation, as well as the consistency of machine learning methods across different crop types, phenology periods, and sensors. First, we extracted various spectral features, including the original spectral features (OS), first-order derivative spectral features (FDS), original continuum-removed spectra (CR) along with their four related derivative spectral features, principal component variables derived from different spectral features, and highly correlated spectral features with LCC. These extracted spectral features were then employed to construct the LCC models using six common regression algorithms on different datasets. Finally, we analyzed the optimal combination of spectral features and regression algorithms for accurate LCC estimation considering various dimensions, such as crop type, phenological period, and sensor used in observation conditions. The results demonstrate that the combinations of the principal component variables of continuum-removed derivative reflectance with the top 10 correlations with LCC (PCA_CRDR_R) combined with Gaussian process regression (GPR) can be considered as the optimal choice for estimating LCC under diverse observation conditions at a canopy scale, and its R2 can reach 0.62 for sugar beet LCC estimation; thus providing valuable theoretical guidance for selecting appropriate spectral features for LCC estimation.

Prediction of hepatocellular carcinoma response to radiation segmentectomy using an MRI-based machine learning approach.

To evaluate the value of pre-treatment MRI-based radiomics in patients with hepatocellular carcinoma (HCC) for the prediction of response to Yttrium 90 radiation segmentectomy. This retrospective study included 154 patients (38 female; mean age 66.8years) who underwent contrast-enhanced MRI prior to radiation segmentectomy. Radiomics features were manually extracted on volumes of interest on post-contrast T1-weighted images at the portal venous phase (PVP). Tumor-based response assessment was evaluated 6months post-treatment using mRECIST. A logistic regression model was used to predict binary response outcome [complete response at 6months with no-re-treatment (response group) against the rest (non-response group, including partial response, progressive disease, stable disease and complete response after re-treatment within 6months after radiation segmentectomy) using baseline clinical parameters and radiomics features. We accessed the value of different sets of predictors using cross-validation technique. AUCs were compared using DeLong tests. A total 168 HCCs (mean size 2.9 ± 1.7cm) were analyzed in 154 patients. The response group consisted of 113 HCCs and the non-response group of 55 HCCs. Baseline clinical parameters (AUC 0.531; sensitivity, 0.781; specificity, 0.279; positive predictive value (PPV), 0.345; negative predictive value (NPV), 0.724) and AFP (AUC 0.632; sensitivity, 0.833; specificity, 0.466; PPV, 0.432; NPV, 0.851) showed poor performance for response prediction. The model using a combination of radiomics features and clinical parameters/AFP showed the best performance (AUC 0.736; sensitivity, 0.706; specificity, 0.662; PPV 0.504; NPV, 0.822), significantly better than the clinical model (p < 0.001) or AFP alone (p < 0.001). The combination of radiomics features from pre-treatment MRI with clinical parameters and AFP showed fair performance for predicting HCC response to radiation segmentectomy, better than that of AFP. These results need further validation.

Future directions in myelodysplastic syndromes/neoplasms and acute myeloid leukaemia classification: from blast counts to biology.

Myelodysplastic syndromes/neoplasms (MDS) and acute myeloid leukaemia (AML) are neoplastic haematopoietic cell proliferations that are diagnosed and classified based on a combination of morphological, clinical and genetic features. Specifically, the percentage of myeloblasts in the blood and bone marrow is a key feature that has historically separated MDS from AML and, together with several other morphological parameters, defines distinct disease entities within MDS. Both MDS and AML have recurrent genetic abnormalities that are increasingly influencing their definitions and subclassification. For example, in 2022, two new MDS entities were recognised based on the presence of SF3B1 mutation or bi-allelic TP53 abnormalities. Genomic information is more objective and reproducible than morphological analyses, which are subject to interobserver variability and arbitrary numeric cut-offs. Nevertheless, the integration of genomic data with traditional morphological features in myeloid neoplasm classification has proved challenging by virtue of its sheer complexity; gene expression and methylation profiling also can provide information regarding disease pathogenesis, adding to the complexity. New machine-learning technologies have the potential to effectively integrate multiple diagnostic modalities and improve on historical classification systems. Going forward, the application of machine learning and advanced statistical methods to large patient cohorts can refine future classifications by advancing unbiased and robust previously unrecognised disease subgroups. Future classifications will probably incorporate these newer technologies and higher-level analyses that emphasise genomic disease entities over traditional morphologically defined entities, thus promoting more accurate diagnosis and patient risk stratification.

Speech profile in different clinical PSP phenotypes: an acoustic-perceptual study.

Progressive supranuclear palsy (PSP) is a neurodegenerative disease with pathological hallmarks and different clinical presentations. Recently, the Movement Disorder Society (MDS) promoted a new classification; specific combinations of the core clinical features identify different phenotypes, including PSP with Richardson's syndrome (PSP-RS) and PSP with predominant parkinsonism (PSP-P). Since speech disorders are very common in PSP, they were included in the MDS-PSP criteria as a supportive clinical feature in the form of hypokinetic, spastic dysarthria. However, little is known about how dysarthria presents across the different PSP variants. The aim of the present study is to evaluate the presence of differences in speech profile in a cohort of PSP-RS and PSP-P patients diagnosed according to the MDS-PSP criteria. Each patient underwent a neurological evaluation and perceptual and acoustic analysis of speech. Disease severity was rated using the Natural History and Neuroprotection in Parkinson plus syndromes-Parkinson plus scale (NNIPPS-PPS), including global score and sub-scores. Twenty-five patients (mean disease duration [standard deviation] = 3.32 [1.79]) were classified as PSP-RS, while sixteen as PSP-P (mean disease duration [standard deviation] = 3.47 [2.00]). These subgroups had homogeneous demographical and clinical characteristics, including disease severity quantified by the NNIPPS-PPS total score. Only the NNIPPS-PPS oculomotor function sub-score significantly differed, being more impaired in PSP-RS patients. No significant differences were found in all speech variables between the two groups. Speech evaluation is not a distinguishing feature of PSP subtypes in mid-stage disease.

A codifiable methodology for estimating pallet sliding displacements on steel racking systems

AbstractTo facilitate the logistic processes within a modern warehouse, the contents of steel racking systems are not mechanically connected to the supporting beams, allowing a content‐sliding mechanism to develop when static friction is exceeded. Given that the mass of contents is dominant, this is beneficial for limiting the apparent inertia. On the other hand, pallet fall‐off may occur during strong seismic excitations, which is a failure mode that is not addressed by current seismic design processes and guidelines for racks. Along these lines, a codifiable methodology is proposed for estimating sliding displacements on steel racking systems, based on the statistical interpretation of a large set of response history analyses, using different rack configurations and ground motions. Firstly, a multi‐parametric analysis is conducted using simplified rack models to (i) select the intensity measure and engineering demand parameter that can best describe the problem of pallet sliding and (ii) identify the salient rack characteristics that dominate sliding behavior. Thereafter, a series of multi‐stripe analyses are performed using 180 rack realizations with different feature combinations to derive a so‐called, Empirical Sliding Prediction Equation (ESPE) by following a three‐step procedure: (a) perform regression on maximum sliding, (b) perform regression on the normalized sliding profile, and (c) combine steps a‐b to derive the denormalized profile at a given confidence level. The proposed empirical relationships are then validated through a comparison between the observed and fitted sliding displacements in three rack case studies.

An efficient state-of-health estimation method for lithium-ion batteries based on feature-importance ranking strategy and hybrid kernel extreme learning machine algorithm

The safe and reliable operation of battery systems depends critically on accurately and dependably estimating the state of health (SOH) of lithium-ion batteries (LIBs). However, accurate prediction of SOH still needs improvement due to the complex battery aging mechanism. This paper introduces a hybrid kernel extremum learning machine (HKELM) for estimating battery SOH. To improve estimation accuracy, we enhance the standard dung beetle optimization algorithm (DBO) with a new initialized population, adaptive weights method, and improved population diversification. We then use the enhanced IDBO algorithm to optimize the parameters of HKELM. This study examines two distinct anode types of LIBs from NASA and Oxford datasets. Fifty significant features are extracted from charging voltage, current, temperature, and incremental capacity (IC) curves. The importance indices of these features are then computed using statistical analyses, including Pearson's correlation coefficient and Spearman's rank correlation coefficient, followed by optimal ranking. The optimal number of final features is determined by comparing various combinations of high-level features, thus reducing model complexity and improving estimation accuracy. This paper proposes the IDBO-HKELM algorithm for SOH estimation. Compared to other methods, the algorithm shows superior estimation performance and anti-interference capability. Both B0007 and Cell8 estimate SOH with MAE < 0.15, RMSE <0.2, and R2 > 99.9 %. Experimental results demonstrate the robustness of the proposed method, achieving accurate and noise-immune SOH estimation.

Combining CEUS and CT/MRI LI-RADS major imaging features: diagnostic accuracy for classification of indeterminate liver observations in patients at risk for HCC.

To determine the diagnostic accuracy of combining CEUS and CT/MRI LI-RADS major imaging features for the improved categorization of liver observations indeterminate on both CT/MRI and CEUS. A retrospective analysis using a database from a prospective study conducted at 11 centers in North America and Europe from 2018 to 2022 included a total of 109 participants at risk for HCC who had liver observations with indeterminate characterization (LR3, LR-4, and LR-M) on both CEUS and CT/MRI. The individual CEUS and CT/MRI LI-RADS major features were extracted from the original study and analyzed in various combinations. Reference standards included biopsy, explant histology, and follow-up CT/MRI. The diagnostic performance of the combinations of LI-RADS major features for definitive diagnosis of HCC was calculated. A reverse, stepwise logistical regression sub-analysis was also performed. This study included 114 observations indeterminate on both CT/MRI and CEUS. These observations were categorized as LR-3 (n = 37), LR-4 (n = 41), and LR-M (n = 36) on CT/MRI and LR-3 (n = 48), LR-4 (n = 36), LR-M (n = 29), and LR-TIV (n = 1) on CEUS. Of them, 43.0% (49/114) were confirmed as HCC, 37.3% (43/114) non-malignant, and 19.3% (22/114) non-hepatocellular malignancies. The highest diagnostic accuracy among the combinations of imaging features was achieved in CT/MRI LR-3 observations, where the combination of CEUS arterial phase hyper-enhancement (APHE) + CT/MRI APHE had 96.7% specificity, 75.0% positive predictive value (PPV), and 86.5% accuracy for HCC. The combination of LI-RADS major features on CT/MRI and CEUS showed higher specificity, PPV, and accuracy compared to individual modalities' assessments, particularly for CT/MRI LR-3 observations.

Recent sedimentology at the grounding zone of the Kamb Ice stream, West Antarctica and implications for ice shelf extent

Sediment accumulating beneath floating ice contains a record of ice dynamics in polar regions where in situ observations are rare. In 2019 a hole was melted through a 590m-thick region of the Ross Ice Shelf ∼5 km seawards of the Kamb Ice Stream (KIS) grounding line (82.7841°S, 155.2626°W) to access the seafloor. Imagery from a remotely operated vehicle (ROV, Icefin) shows ocean current-generated ripples likely formed by tidal flow parallel to the grounding line (GL). Observed current speeds <0.15 m s−1 suggest these bedforms may be relict. Larger, dm-scale, ‘furrows’ parallel to the former direction of KIS flow may relate to past grounding line processes. A 0.49 m-long gravity core collected from the seafloor contains weakly stratified diamicton. The sediment matrix comprises variable mixtures of reworked Tertiary biogenic silica, predominantly diatoms, and arkose material. Sediment εNd values of ∼7 are consistent with derivation from the WAIS, as is the U-Pb age distribution and modelled late Holocene ice flows. Ramped pyrolysis 14C analysis shows all fractions are either >30 ka or 14C dead. By contrast, 210Pb-210 activity of >30 Bq Kg−1 indicates deposition within the last 120 years. The combination of features suggests rapid rainout deposition from melting of a sediment-laden basal debris layer as the GL retreated, followed by some reworking by ocean currents and little modern accumulation. Although Tertiary diatoms are abundant, unambiguously Late Quaternary forms are absent and we speculate on the implications for Ross Ice Shelf stability. [239 wds]

Automatic authorship attribution in Albanian texts.

Automatic authorship identification is a challenging task that has been the focus of extensive research in natural language processing. Regardless of the progress made in attributing authorship, the need for corpora in under-resourced languages impedes advancing and examining present methods. To address this gap, we investigate the problem of authorship attribution in Albanian. We introduce a newly compiled corpus of Albanian newsroom columns and literary works and analyze machine-learning methods for detecting authorship. We create a set of hand-crafted features targeting various categories (lexical, morphological, and structural) relevant to Albanian and experiment with multiple classifiers using two different multiclass classification strategies. Furthermore, we compare our results to those obtained using deep learning models. Our investigation focuses on identifying the best combination of features and classification methods. The results reveal that lexical features are the most effective set of linguistic features, significantly improving the performance of various algorithms in the authorship attribution task. Among the machine learning algorithms evaluated, XGBoost demonstrated the best overall performance, achieving an F1 score of 0.982 on literary works and 0.905 on newsroom columns. Additionally, deep learning models such as fastText and BERT-multilingual showed promising results, highlighting their potential applicability in specific scenarios in Albanian writings. These findings contribute to the understanding of effective methods for authorship attribution in low-resource languages and provide a robust framework for future research in this area. The careful analysis of the different scenarios and the conclusions drawn from the results provide valuable insights into the potential and limitations of the methods and highlight the challenges in detecting authorship in Albanian. Promising results are reported, with implications for improving the methods used in Albanian authorship attribution. This study provides a valuable resource for future research and a reference for researchers in this domain.

Detecting event-related driving anger with facial features captured by smartphones

Driving anger is a serious global issue that poses risks to road safety, thus necessitating the development of effective detection and intervention methods. This study investigated the feasibility of using smartphones to capture facial expressions to detect event-related driving anger. Sixty drivers completed the driving tasks in scenarios with and without multi-stage road events and were induced to angry and neutral states, respectively. Their physiological signals, facial expressions, and subjective data were collected. Four feature combinations and six machine learning algorithms were used to construct driving anger detection models. The model combining facial features and the XGBoost algorithm outperformed models using physiological features or other algorithms, achieving an accuracy of 87.04% and an F1-score of 85.06%. Eyes, mouth, and brows were identified as anger-sensitive facial areas. Additionally, incorporating individual characteristics into models further improved classification performance. This study provides a contactless and highly accessible approach for event-related driving anger detection. Practitioner Summary: This study proposed a cost-effective and contactless approach for event-related and real-time driving anger detection and could potentially provide insights into the design of emotional interactions in intelligent vehicles.

A Deep Learning Model for Predicting the Laminar Burning Velocity of NH3/H2/Air

Both NH3 and H2 are considered to be carbon-free fuels, and their mixed combustion has excellent performance. Considering the laminar burning velocity as a key characteristic of fuels, accurately predicting the laminar burning velocity of NH3/H2/Air is crucial for its combustion applications. The study made improvements to the XGBoost model and developed NH3/H2/Air Laminar Burning Velocity Net (NHLBVNet), which adopts a composite hierarchical structure to connect the functions of feature extraction, feature combination, and model prediction. The dataset consists of 487 sets of experimental data after the exclusion of outliers. The correlation coefficient (R2 &gt; 0.99) of NHLBVNet is higher than that of the XGBoost model (R2 &gt; 0.93). Robustness experiment results indicate that this model can obtain more accurate prediction results than other models even under small sample datasets.