Model Predictions Research Articles

Target Structure Learning Framework for Unsupervised Multi-Class Domain Adaptation

Unsupervised multi-class domain adaptation (multi-class UDA) has recently been proposed to fill the gap between empirically practical methods for multi-class classification and well-founded theory with the setting of binary classification. Nevertheless, the multi-class UDA methods use model predictions to characterize the disagreement of multi-class scoring hypotheses, which is used to optimize the divergence between domain distributions. Such self-training manner may bring inaccurate model predictions, which would damage the target structure due to the absence of labels of the target domain, leading to sub-optimal performance. On the other hand, this disagreement between multi-class scoring hypotheses does not involve the relationships among all of the multiple classes. It causes that multi-class UDA cannot properly connect the advanced practical UDA methods that consider class-conditional distribution alignment. Thus, we propose to exploit the target structure information and then incorporate it into multi-class UDA to achieve class-conditional distribution alignment. We theoretically and experimentally explain the importance of accurate target structure information to reduce the expected error on the target domain. Notably, our method achieves state-of-the-art results on three commonly-used benchmarks with different scales. In addition, using the target structure information, we propose a variant to cope with noisy open-world source domains such as noisy labels and out-of-distribution samples, enhancing the robustness of our method. The source code is available at https://github.com/jingzhengli/Multi_Class_UDA .

SAL Method Applied in Grid Forecasting Product Verification with Three-Source Fusion Product

Quantitative precipitation forecast (QPF) verification stands out as one of the most formidable endeavors in the realm of forecast verification. Traditional verification methods are not suitable for high-resolution forecasting products in some cases. Therefore, the SAL (structure, amplitude and location) method was proposed as a method of object-based spatial verification that studies precipitation verification in a certain range, which is combined with factors including structure, amplitude and location of the targets. However, the setting of the precipitation threshold would affect the result of the verification. This paper presented an improved method for determining the precipitation threshold using the QPF from ECMWF, which is an ensemble forecast model and three-source fusion product that was used in China from 1 July to 31 August 2020, and then the results obtained with this method were compared with the other two traditional methods. Furthermore, the SAL and the traditional verification methods were carried out for geometric, simulated and real cases, respectively. The results showed the following: (1) The proposed method in this paper for determining the threshold was more accurate at identifying the precipitation objects. (2) The verification area size was critical for SAL calculation. If the area selected was too large, the calculated SAL value had little significance. (3) ME (Mean Error) could not identify the displacement between prediction and observation, while HSS (Heidke Skill Score) was sensitive to the displacement of the prediction field. (4) Compared with the traditional verification methods, the SAL method was more straight forward and simple, and it could give a better representation of prediction ability. Therefore, forecasters can better understand the model prediction effect and what needs to be improved.

A generalized health index: automated thoracic CT-derived biomarkers predict life expectancy

Abstract Objective To identify image biomarkers associated with overall life expectancy from low-dose computed tomography and integrate them as an index for assessing an individual’s health. Methods Two categories of CT image features, body composition tissues and cardiopulmonary vasculature characteristics, were quantified from LDCT scans in the Pittsburgh Lung Screening Study cohort(n = 3,635). Cox proportional-hazards models identified significant image features which were integrated with subject demographics to predict the subject’s overall hazard. Subjects were stratified using composite model predictions and feature-specific risk stratification thresholds. The model’s performance was validated extensively, including 5-fold cross-validation on PLuSS baseline, PLuSS follow-up examinations, and the National Lung Screening Trial (NLST). Results The composite model had significantly improved prognostic ability compared to the baseline model (p < 0.01) with AUCs of 0.774 (95% CI: 0.757-0.792) on PLuSS, 0.723 (95% CI: 0.703-0.744) on PLuSS follow-up, and 0.681 (95% CI: 0.651-0.710) on the NLST cohort. The identified high-risk stratum were several times more likely to die, with mortality rates of 79.34% on PLuSS, 76.47% on PLuSS follow-up, and 46.74% on NLST. Two cardiopulmonary structures (intrapulmonary artery vein ratio, intrapulmonary vein density) and two body composition tissues (SM density, bone density) identified high-risk patients. Conclusions Body composition and pulmonary vasculatures are predictive of an individual’s health risk; their integrations with subject demographics facilitate the assessment of an individual’s overall health status or susceptibility to disease. Advances in knowledge CT-computed body composition and vasculature biomarkers provide improved prognostic value. The integration of CT biomarkers and patient demographic information improves subject risk stratification.

Abstract 4143270: PREDICTIVE MODELS AID PHYSICIAN PROGNOSTICATION: A SECONDARY ANALYSIS EVALUATING INTEGRATED MODEL AND PHYSICIAN PROGNOSTIC ESTIMATES IN PATIENTS WITH HEART FAILURE WITH REDUCED EJECTION FRACTION

Background: In recent studies from a multicenter Canadian cohort of outpatients with heart failure (HF), we found that model predictions were significantly more accurate than HF cardiologists. In this study, trying to mimic practice, we evaluated the additional predictive value and clinical impact of model predictions to refine physician estimated risk of 1-year mortality by combining model and physician estimates. Methods: We included consented consecutive HF outpatients (LVEF <40%) followed at 11 HF clinics in Canada. HF cardiologists estimated patient 1-year mortality using their clinical judgment. We calculated model predicted mortality using the Seattle HF Model (SHFM). We followed patients for at least a year to record mortality (or urgent heart transplant or ventricular assist device implant as mortality-equivalent events). Using random forest survival model and cross-validation, we compared the performance SHFM and the HF cardiologist alone, and the integrated HF cardiologist and the SHFM predictions by evaluating model discrimination (c-statistic), calibration (observed vs predicted event rate), risk reclassification and clinical net benefit analyses. Results: Among 1,643 HF patients, 1-year event rate was 9% (95%CI 8%-11%). The SHFM had the adequate discrimination (c-statistic 0.76) and excellent calibration while cardiologists showed adequate discrimination (c-statistic 0.75) and poor calibration with significant risk overestimation ( Figure 1 ). When the SHFM estimates were added physician predictions, discrimination significantly improved (0.82, 95%CI 0.78-0.86) with excellent calibration. By risk reclassification analysis, among patients with events, HF cardiologist better reclassified 44% than the SHFM or the integrated model. Among patients without event, however, HF cardiologists worse risk-classified 52% in comparison to SHFM and 71% to the integrated model. By net clinical benefit analysis ( Figure 2 ), when the decision to treat involves patients with 1-year mortality of >5%, SHFM predictions would lead to higher benefit than guiding care by physician judgement. Integrating model and HF cardiologist predictions led to minimally increased benefit in comparison to SHFM alone. Conclusions: Integrating prediction from the SHFM to physician judgment or using the SHFM alone showed superior accuracy than HF cardiologist predictions, proving that model-informed care may provide more accurate prognostic information to tailor clinical decision making.

Quantifying uncertainty in neural network predictions of forced vibrations

AbstractThe prediction of forced vibrations in nonlinear systems is a common task in science and engineering, which can be tackled using various methodologies. A classical approach is based on solving differential (algebraic) equations derived from physical laws ('first principles'). Alternatively, Artificial Neural Networks (ANNs) may be applied, which rely on learning the dynamics of a system from given data. However, a fundamental limitation of ANNs is their lack of transparency, making it difficult to understand and trust the model's predictions. In this contribution, we follow a hybrid modelling approach combining a data‐based prediction using a stabilised Autoregressive Neural Network (s‐ARNN) with a priori knowledge from first principles. Moreover, aleatoric and epistemic uncertainty is quantified by a combination of mean‐variance estimation (MVE) and deep ensembles. Validating this approach for a classical Duffing oscillator suggests that the MVE ensemble is the most accurate and reliable method for prediction accuracy and uncertainty quantification. These findings underscore the significance of understanding uncertainties in deep ANNs and the potential of our method in improving the reliability of predictive nonlinear system modelling. We also demonstrate that including partially known dynamics can further increase accuracy, highlighting the importance of combining ANNs and physical laws.

Abstract 4134947: Explainable Machine Learning to Predict Heart Failure Outcomes Using Exercise and Clinical Data

Background: Heart failure (HF) hospitalizations are associated with disease burden and cardiovascular mortality. International guidelines highlight cardiopulmonary testing (CPET) for risk stratification and prognosis in HF. Identifying individuals at risk could direct interventions to prevent admissions. This study uses explainable machine learning (XML) tools to identify CPET and clinical variables predictive of HF hospitalizations. Hypothesis: XML analysis of CPET parameters and clinical factors can yield accurate, patient-specific prediction of HF admission within one year. Methods: A retrospective single center review of 178 CPETs in patients referred for HF was completed. Clinical data within one year of CPET trained a boosted machine learning model (XGBoost). SHAP (Shapley Additive Explanations) explainability analysis emphasized key features for model predictions. Results: 44 (24.7%) patients with CPET were admitted for HF within one year. The model predicted this outcome with an area under the receiver operating characteristic curve (AUC) of 0.772. SHAP analysis (Figure 1) selected factors for decision making: pulmonary artery systolic pressure (PASP) via cardiac catheterization or echocardiogram; oxygen consumption at the ventilatory threshold (VO 2 at VT); O 2 pulse at rest; ventilatory efficiency (VE/VCO 2 slope); minute ventilation per oxygen consumption at maximal exercise (VE/VO 2 max) during CPET; left ventricle end diastolic volume by echocardiogram; and sodium-glucose cotransporter-2 inhibitor usage. Peak VO2, predicted VO2, predicted O2 pulse, and VE/VCO2 slope were significant, consistent with past studies (Table 1). Conclusion: Our XML analysis emphasizes PASP (partially related to high left ventricular filling pressures) and VO 2 (at ventilatory threshold) as predictive for HF hospitalization within one year of CPET testing. Studies to prospectively evaluate these highlighted factors are needed to continue exploring predictive capabilities to tailor interventions.

Abstract 4137796: Novel Deep Learning Aligned Strain Techniques in Repaired Tetralogy of Fallot

Introduction: Multicenter studies show that demographic and CMR-based volumetrics and strain predict death, ventricular tachycardia and fibrillation (DVTF) in repaired tetralogy of Fallot (rTOF). We developed a novel deep learning method to calculate radial (RS) and circumferential strain (CS) from end-diastole (ED) to other key frames: mid systole (MS), end-systole (ES), peak flow (PF) in diastole, and mid-diastole (MD) (called ED2K), as well as from each key frame to the next (called K2K strain), for each left ventricle (LV) segment. Hypothesis: We hypothesized that: H1) ED-ES strain; H2) septal strain; and H3) diastolic strain would be additionally predictive of DVTF as compared to a traditional model. Approach: 704 patients combined from the German Competence Network and INDICATOR cohorts had ED2K and K2K strain values calculated using CMR short axis stack. We first created a 4-variable “traditional” logistic regression model including age at CMR, RVEF%, LVEF% and RVESVi. We then separately added ED2K and K2K parameters to assess increased ability to discriminate DVTF, measured by the c-statistic. Results: In univariate analyses, H1: ED to ES RS and CS; H2: multiple systolic septal and non-septal variables; and H3: overall diastolic RS and CS were significantly associated with DVTF, with c-statistics between 0.65 and 0.73 (n=56, Table 1). When added to the traditional model, H1: ED to ES CS; and H2: septal and non-septal CS slightly improved model performance (Table 2). Model calibration was adequate for all models. Conclusion: Our key-frame specific strain recapitulates the CS prediction of adverse events in rTOF, and slightly improves prediction in a multiparameter model. Future work includes external validation.

Novel Nordaucane Sesquiterpenoid and Sesquiterpene Lactone From Laserpitium Species: Isolation, Structure Elucidation, In Vitro, In Vivo, and In Silico Evaluation as Anticancer Agents

ABSTRACTIntroductionThis study explores the cytotoxic activity‐guided isolation of the underground parts of Laserpitium hispidum M. Bieb and Laserpitium petrophilum Boiss. & Heldr., which have not been previously investigated.ObjectivesThe aim is to isolate and evaluate bioactive compounds from Laserpitium L. species with anticancer potential.Material and MethodsThis study involves bioactivity‐guided isolation and structural studies of the pure compounds utilizing NMR, UV–Vis, IR spectroscopies, and HRMS. The cytotoxic activity of the isolated compounds was evaluated in vitro and in vivo, whereas molecular modeling, docking, and ADME predictions were conducted using Schrödinger software.ResultsThe study isolated phenylpropanoids (laserine (1), latifolone (2), myristicin (3)), sterol (stigmasterol (4)), polyenes (falcarindiol (5)), sesquiterpene lactone (11‐hydroxybadkhyzin (6)), and nordaucane sesquiterpene (norlasidiol angelate (7)) from L. hispidum, whereas L. petrophilum yielded 10β‐acetoxy‐8α‐angeloyloxy‐6αH,7αH‐guaian‐3‐en‐12,6‐olide (8), 10β‐acetoxy‐8α‐senecioyloxy‐6αH,7αH‐guaian‐3‐en‐6,12‐olide (9) and acetylisomontanolide (10). Molecular docking simulations revealed stable interactions between compounds 7 and 9 with estrogen receptor α (ERα) and vascular endothelial growth factor receptor 2 (VEGFR2), with compound 7 showing superior stability and binding affinity. In silico ADME predictions indicated favorable pharmacokinetic properties, including high oral absorption.ConclusionCompounds 7 and 9, representing new nordaucane and sesquiterpene lactones, have not been previously reported. In vitro cytotoxicity revealed that compound 7 exhibits potent anti‐cancer activity against MCF‐7 cells, whereas compound 9 showed reduced cytotoxicity. In vivo testing in Caenorhabditis elegans supported these findings, suggesting safety and efficacy in organisms. In silico results emphasize the potential of these compounds, with compound 7 promising due to its stability and strong binding affinity.

Comparison of inelasticity creep failure evaluation codes for elevated-temperature non-nuclear pressure equipment

PurposeTo ensure the reliable and safe operation of elevated-temperature pipes and equipment in the long term, it is essential to thoroughly assess the creep rupture life. Nevertheless, there is currently no design code that specifies a creep rupture life evaluation method for non-nuclear elevated-temperature equipment. The paper aims to discuss this issue.Design/methodology/approachAn analysis was conducted to compare the differences and conservativeness in calculating creep strain using three major codes (ASME-CC-2843, API-579 and BS-7910) based on the results of the 316H creep constitutive model and creep strain prediction. In addition, the creep resistances of 316H, 304H and 347H were compared. Subsequently, the ANSYS Usercreep subroutine was developed to compare the discrepancies between different codes under multiaxial stress conditions using numerical simulations.FindingsBS-7910 employs the Norton creep model with calculation parameters for the average creep strain rate, which is not applicable for the engineering design stage. ASME-CC2843 code primarily focuses on the primary and secondary creep stages, making it more suitable for non-nuclear pipeline and equipment design. For 316H, the creep strain curves predicted by ASME-CC2843 and API-579 typically intersect at a specific point. By combining the creep strain predicted by ASME-CC2843 and API-579, 347H exhibits superior predicted creep resistance compared to 316H, whereas 316H exhibited better predicted creep resistance than 304H.Originality/valueThis study provides a guide for future evaluation methods and material choices for non-nuclear equipment and pipelines operating at elevated temperatures.

Genome streamlining of Pseudomonas putida B6-2 for bioremediation

ABSTRACT Microbial transformation is a favored approach for environmental remediation. However, the effectiveness of microbial remediation has been limited by the lack of chassis cells with satisfactory contaminant degradation performance. Pseudomonas putida B6-2, with a wide substrate spectrum and high solvent tolerance, is a chassis strain with great potential for application in environmental remediation. Here, guided by bioinformatic analyses and genome-scale metabolic model (GEM) predictions, we successfully optimized P. putida B6-2 by rationally reducing its nonessential genetic components and generating a more robust genome-streamlined strain, P. putida BGR4. Several improvements were observed compared with the original P. putida B6-2 strain, including a 1.4 × 10 5 -fold increase in electroporation efficiency, an 8.3-fold increase in conjugation efficiency, improved glycerol utilization capability, and increased phenol utilization after heterologous expression of the phenol monooxygenase encoded by dmpKLMNOP . Additionally, P. putida BGR4 exhibited enhanced tolerance to several stressors, including starvation, oxidative stress, and DNA damage. Transcriptomic analysis revealed that genome streamlining led to the upregulation of genes involved in the “carbon metabolism” and “tricarboxylic acid cycle” pathways in P. putida BGR4, which likely contributed to the superior phenotype of P. putida BGR4 in terms of carbon source utilization and contaminant degradation capabilities. Furthermore, the absence of four prophages was identified as a potential cause of the enhanced stress resistance observed in P. putida BGR4. Overall, we developed a combined genome-streamlining strategy involving bioinformatic analyses and GEM predictions and generated a more robust chassis strain, P. putida BGR4, which expands the repertoire of chassis cells for environmental remediation. IMPORTANCE Despite the development of many chassis cells, there is still a lack of robust chassis cells with satisfactory contaminant degradation performance. Targeted genome streamlining is an effective way to provide powerful chassis cells. However, genome streamlining does not always lead to the improved phenotypes of genome-streamlined chassis cells. In this research, a novel procedure that combined bioinformatic analyses and GEM predictions was proposed to guide genome streamlining and predict the effects of genome streamlining. This genome streamlining procedure was successfully applied to Pseudomonas putida B6-2, which was a chassis cell with great potential for application in environmental remediation and resulted in the generation of a more robust chassis cell, P. putida BGR4, thereby providing a superior chassis cell for efficient and sustainable environmental remediation and a valuable framework for guiding the genome streamlining of strains for other applications.

Randomising spatial patterns supports the integration of intraspecific variation in ecological niche models

Ecological niche models (ENMs) are an essential modelling technique in biodiversity prediction and conservation and are frequently used to forecast species responses to global changes. Classic species‐level models may show limitations as they assume species homogeneity, neglecting intraspecific variation. Composite ENMs allow the integration of intraspecific variation by combining intraspecific‐level ENMs, capturing individual environmental responses over the species' geographic range. While recent studies suggest that accounting for intraspecific variation improves model predictions, we currently lack methods to test the significance of the improvement. Here, we propose a null model approach that randomises observed intraspecific structures as an appropriate baseline for comparison. We illustrate this approach by comparing predictive performance of a species‐level ENM to composite ENMs for European beech Fagus sylvatica. To investigate the influence of spatial lineage structure, we tested all models against the same withheld data to allow comparison across models based on five common performance metrics. We found that the species‐level ENM expressed higher overall performance (i.e. AUC, TSS, and Boyce index) and specificity (ability to predict absences), while the composite ENMs achieved higher sensitivity (ability to predict presences). In line with this, the composite ENMs also showed increased sensitivity and decreased specificity compared to the null models that randomised lineage structure. We showed that the assessment of model performance strongly varies based on the used measures, emphasising a careful investigation of multiple measures for evaluation. The application of null models allowed us to disentangle the effect of observed patterns of intraspecific variation in ENMs. Further, we highlight the validation and use of well‐founded subgroups for modelling. Although intraspecific variation improves the prediction of occurrences of European beech, it did not fully outcompete the classic species‐level model and should be used with care and rather to improve understanding and to supplement, not replace, species‐level models.

Pembrolizumab 400 mg every 6 weeks as first-line therapy for advanced melanoma (KEYNOTE-555): Results from cohort B of an open-label, phase 1 study

Intravenous pembrolizumab 400 mg every 6 weeks was approved across tumor types based on pharmacokinetic modeling, which showed exposures consistent with previous standard dosing of 200 mg or 2 mg/kg every 3 weeks, and early results of cohort B of the phase 1 KEYNOTE-555 study. Results after ≥1 year of potential follow-up for all patients in cohort B of KEYNOTE-555 are presented. Patients aged ≥18 years with previously untreated stage III/IV melanoma received pembrolizumab 400 mg every 6 weeks for ≤18 cycles. The primary endpoint was objective response rate per RECIST v1.1 by blinded independent central review. Secondary endpoints included duration of response, progression-free survival, pharmacokinetics, and safety. Overall, 101 patients received pembrolizumab. Median projected follow-up was 21.9 months (range, 17.0–25.7). The objective response rate was 50.5% (95% CI: 40.4–60.6; 19 complete responses, 32 partial responses). Median duration of response was not reached (NR; range, 2.4+ to 21.0+ months). Median progression-free survival was 13.8 months (95% CI: 4.1–NR). Observed pharmacokinetic exposures were consistent with model predictions for pembrolizumab 400 mg every 6 weeks and other approved and tested schedules (2 mg/kg or 200 mg every 3 weeks). Grade 3–4 treatment-related adverse events occurred in 13 patients (12.9%). No deaths were considered treatment related. These results support the pharmacokinetic modeling and demonstrate that the benefit-risk profile of pembrolizumab 400 mg Q6W is consistent with that of 200 mg or 2 mg/kg every 3 weeks. Clinically meaningful objective response rate and durable progression-free survival within the expected range for first-line pembrolizumab were observed. Clinical trial registry: ClinicalTrials.gov, NCT03665597.

Measurement of the D* longitudinal polarization in B0→D*−τ+ντ decays

The longitudinal polarization fraction of the D* meson is measured in B0→D*−τ+ντ decays, where the τ lepton decays to three charged pions and a neutrino, using proton-proton collision data collected by the LHCb experiment at center-of-mass energies of 7, 8 and 13 TeV and corresponding to an integrated luminosity of 5 fb−1. The D* polarization fraction FLD* is measured in two q2 regions, below and above 7 GeV2/c4, where q2 is defined as the squared invariant mass of the τντ system. The FLD* values are measured to be 0.52±0.07±0.04 and 0.34±0.08±0.02 for the lower and higher q2 regions, respectively. The first uncertainties are statistical and the second systematic. The average value over the whole q2 range is FLD*=0.41±0.06±0.03. These results are compatible with the Standard Model predictions. © 2024 CERN, for the LHCb Collaboration 2024 CERN

Abstract 4137726: A Deep Learning Digital Biomarker for Mitral Valve Prolapse using Echocardiogram Videos

Background: Mitral valve prolapse (MVP) has a prevalence of 2–3% and is a risk factor for heart failure and sudden death, but MVP diagnosis by transthoracic echocardiography (TTE) requires time and clinical expertise. We trained a deep learning model to classify MVP from TTE videos. Methods: DROID-MVP is a convolutional neural network trained to classify MVP using echocardiographer labels using 973,531 digital videos (parasternal long axis and apical views) from 45,657 studies performed in 15,728 cardiology patients at Massachusetts General Hospital. We validated DROID-MVP in 1,726 cardiology patients (4,869 studies) and 8,903 primary care patients (8,903 studies), and tested associations between predicted MVP score (range 0-1) and mitral regurgitation (MR) severity and left atrial (LA) anterior-posterior diameter in primary care patients with available measurements. Results: Of 15,728 patients (6,029 [38%] women; mean age at first TTE 61 ± 17 years) in the training set, 729 (4.6%) had at least 1 study with MVP. DROID-MVP identified MVP in both the cardiology (area under the receiver operating characteristic curve [AUC] 0.955 [95% confidence interval: 0.939-0.970]; average precision [AP] 0.716 [0.649-0.776]; prevalence 0.035) and primary care (AUC 0.966 [0.955-0.978]; AP 0.668 [0.601-0.730]; prevalence 0.022) test sets ( Figure 1 ). Discrimination persisted across strata of MR severity (AUC range 0.877-0.987). High (>0.67) vs low (<0.33) MVP score was associated with higher odds of moderate/severe MR (odds ratio 20.1 [12.2-33.4], p<0.001) and higher LA diameter (2.7 [0.9-4.4] mm, p<0.001; Figure 2 ), after adjusting for age, sex, height, and weight. Conclusions: A deep learning model identifies MVP from TTE videos with excellent discrimination and higher model predictions are associated with greater MR severity and LA size. Our work demonstrates how deep learning can automate MVP diagnosis and may serve as a digital biomarker of MVP-associated structural abnormalities.

T-KAER: Transparency-enhanced Knowledge-Augmented Entity Resolution Framework

Entity resolution (ER) is the process of determining whether two representations refer to the same real-world entity and plays a crucial role in data curation and data cleaning. Recent studies have introduced the KAER framework, aiming to improve pre-trained language models by augmenting external knowledge. However, identifying and documenting the external knowledge that is being augmented and understanding its contribution to the model's predictions have received little to no attention in the research community. This paper addresses this gap by introducing T-KAER, the Transparency-enhanced Knowledge-Augmented Entity Resolution framework. To enhance transparency, three Transparency-related Questions (T-Qs) have been proposed: T-Q(1): What is the experimental process for matching results based on data inputs? T-Q(2): Which semantic information does KAER augment in the raw data inputs? T-Q(3): Which semantic information of the augmented data inputs influences the predictions? To address the T-Qs, T-KAER is designed to improve transparency by documenting the entity resolution processes in log files. In experiments, a citation dataset is used to demonstrate the transparency components of T-KAER. This demonstration showcases how T-KAER facilitates error analysis from both quantitative and qualitative perspectives, providing evidence on `"what" semantic information is augmented and ``"why" the augmented knowledge influences predictions differently.

Emergent Dynamic Formation through Optical Interactions in a Robot Swarm

Self‐organized formation is a key direction in swarm robotics. It is still challenging to design local interactions toward desired global formations and even more challenging for dynamic formations in a physical robot swarm system. Herein, a self‐organized method for emergent dynamic circling formation in a robot swarm through optical interactions is proposed. First, this method is quantitatively modeled based on the geometrical relations among robots. This model is further adjusted according to the characteristics of the robot swarm system. To demonstrate the effectiveness of this model, the effects of three key parameters of this model are tested on the size and disorder level of the emergent dynamic circling formation. The experimental results are consistent with the model predictions. Overall, a robot swarm system, in the physical environment, is quantitatively controlled to emerge a dynamic circling formation in this article. This work advances the swarm robotics for quantitatively designing local interactions among robots to reliably emerge dynamic global patterns.

Shape Optimization of a Diffusive High-Pressure Turbine Vane Using Machine Learning Tools

Machine learning tools represent a key methodology for the shape optimization of complex geometries in the turbomachinery field. One of the current challenges is to redesign High-Pressure Turbine (HPT) stages to couple them with innovative combustion technologies. In fact, recent developments in the gas turbine field have led to the introduction of pioneering solutions such as Rotating Detonation Combustors (RDCs) aimed at improving the overall efficiency of the thermodynamic cycle at low overall pressure ratios. In this study, a HPT vane equipped with diffusive endwalls is optimized to allow for ingesting a high-subsonic flow (Ma=0.6) delivered by a RDC. The main purpose of this paper is to investigate the prediction ability of machine learning tools in case of multiple input parameters and different objective functions. Moreover, the model predictions are used to identify the optimal solutions in terms of vane efficiency and operating conditions. A new solution that combines optimal vane efficiency with target values for both the exit flow angle and the inlet Mach number is also presented. The impact of the newly designed geometrical features on the development of secondary flows is analyzed through numerical simulations. The optimized geometry achieved strong mitigation of the intensity of the secondary flows induced by the main flow separation from the diffusive endwalls. As a consequence, the overall vane aerodynamic efficiency increased with respect to the baseline design.

EPCO-29. PATHOMICS ANALYSIS IDENTIFIES POTENTIAL SUBTYPES OF DIFFUSE GLIOMAS IN H&E-STAINED WHOLE-SLIDE IMAGES

Abstract IDH status is the first criteria of diagnostic definition for diffuse gliomas in the 2021 WHO classification. While sufficient number of molecular tools are available to identify IDH1 and/or IDH2 mutations, they impose a time and cost burden on patients. We previously trained deep learning models visually differentiate IDH wild-type (IDHwt) and IDH mutant (IDHmut) gliomas in a small set of H&E-stained whole image slides (WSIs) from TCGA using an Uncertainty-Aware Convolutional Neural Network (CNN) at 10x magnification. In this follow-up study, we aimed to improve our models by expanding our annotations of a more representative subset of the TCGA public data, increasing the sampling magnification to 20x, redesigning the preprocessing filters, adjusting the training pipeline to reduce overfitting, and assessing the confidence in model prediction via uncertainty metrics. METHODS By modifying the pre-processing methods from our pilot study, we increased the number of expert-annotated WSIs. Using a 2:1:2 train/validation/test split, we fine-tuned a ResNet18 deep learning model with a pre-trained feature extractor and Monte Carlo dropouts. To identify image features critical for separating by IDH status, we extracted the learned embeddings and performed post-hoc analyses (PCA, t-SNE, and UMAP). RESULTS The new set of annotations resulted in ~15-fold increase in the number of WSIs (i.e.,>2.5 million tiles), without any data augmentation. Our prototype model demonstrated clear separation of cases according to IDH status (sensitivity = 0.63, specificity = 0.91, weighted F1 = 0.81). CONCLUSION We successfully improved the prediction of IDH status in H&E-stained WSIs and identified potential subtypes of IDHwt and IDHmut diffuse gliomas after significantly increasing the dataset size with appropriate expert annotations. We are currently addressing the data imbalance by annotating additional IDHmut glioma WSIs. Furthermore, we will integrate other biomarkers (1p19q, EGFR etc.) to increase the robustness of histo-pathomics as a surrogate for molecular tests.

Exchange Rate Dynamics and Monetary Fundamentals: Evidence from South Asian Countries

This paper examined the role of monetary fundamentals in determining nominal exchange rate changes in South Asian countries. The Vector Autoregressive (VAR) technique and Autoregressive Distribution Lag (ARDL) were used. Results from the VAR indicate that the exchange rate responds to shock originating from differences in money supply, inflation differential, interest rate, and real income differential and are consistent with the short-run predictions of the monetary model of the exchange rate. The results show that inflation and interest rate differentials are responsible for the majority of changes in exchange rates in the short run. The conclusion from the result is that, particularly in the short run, monetary fundamentals are the primary causes of exchange rate fluctuations in South Asian countries.

Vehicle Trajectory Prediction Using Residual Diffusion Model Based on Image Information

In automatic driving, accurate prediction of vehicle trajectory is the key to achieve automatic driving, and multi-vehicle joint trajectory prediction has become an important part of modern human-computer interaction systems such as automatic driving. In order to better predict vehicle trajectories, we propose a new residual diffusion model to infer the joint distribution of future multi-vehicle trajectories. This approach has several major advantages. First, the model is able to learn multiple probability distributions from trajectory data to obtain potential outcomes for vehicles to multiple future trajectories. Secondly, in order to integrate the motion characteristics of multiple vehicles in the same scene, we use the method of combining the reference denoising and multiple residual denoising to improve the model performance and prediction speed. Finally, on this basis, a general trajectory constraint function is introduced, so that the generated trajectories of multiple vehicles will not collide with each other. We perform a rich experimental comparison of various existing methods on the NGSIM dataset and demonstrate that the proposed algorithm achieves a 26% improvement on mAP.