Large Test Data Sets Research Articles

Understanding overfitting in random forest for probability estimation: a visualization and simulation study

BackgroundRandom forests have become popular for clinical risk prediction modeling. In a case study on predicting ovarian malignancy, we observed training AUCs close to 1. Although this suggests overfitting, performance was competitive on test data. We aimed to understand the behavior of random forests for probability estimation by (1) visualizing data space in three real-world case studies and (2) a simulation study.MethodsFor the case studies, multinomial risk estimates were visualized using heatmaps in a 2-dimensional subspace. The simulation study included 48 logistic data-generating mechanisms (DGM), varying the predictor distribution, the number of predictors, the correlation between predictors, the true AUC, and the strength of true predictors. For each DGM, 1000 training datasets of size 200 or 4000 with binary outcomes were simulated, and random forest models were trained with minimum node size 2 or 20 using the ranger R package, resulting in 192 scenarios in total. Model performance was evaluated on large test datasets (N = 100,000).ResultsThe visualizations suggested that the model learned “spikes of probability” around events in the training set. A cluster of events created a bigger peak or plateau (signal), isolated events local peaks (noise). In the simulation study, median training AUCs were between 0.97 and 1 unless there were 4 binary predictors or 16 binary predictors with a minimum node size of 20. The median discrimination loss, i.e., the difference between the median test AUC and the true AUC, was 0.025 (range 0.00 to 0.13). Median training AUCs had Spearman correlations of around 0.70 with discrimination loss. Median test AUCs were higher with higher events per variable, higher minimum node size, and binary predictors. Median training calibration slopes were always above 1 and were not correlated with median test slopes across scenarios (Spearman correlation − 0.11). Median test slopes were higher with higher true AUC, higher minimum node size, and higher sample size.ConclusionsRandom forests learn local probability peaks that often yield near perfect training AUCs without strongly affecting AUCs on test data. When the aim is probability estimation, the simulation results go against the common recommendation to use fully grown trees in random forest models.

A Critical Review of Emerging Technologies for Flash Flood Prediction: Examining Artificial Intelligence, Machine Learning, Internet of Things, Cloud Computing, and Robotics Techniques

There has been growing interest in the application of smart technologies for hazard management. However, very limited studies have reviewed the trends of such technologies in the context of flash floods. This study reviews innovative technologies such as artificial intelligence (AI)/machine learning (ML), the Internet of Things (IoT), cloud computing, and robotics used for flash flood early warnings and susceptibility predictions. Articles published between 2010 and 2023 were manually collected from scientific databases such as Google Scholar, Scopus, and Web of Science. Based on the review, AI/ML has been applied to flash flood susceptibility and early warning prediction in 64% of the published papers, followed by the IoT (19%), cloud computing (6%), and robotics (2%). Among the most common AI/ML methods used in susceptibility and early warning predictions are random forests and support vector machines. However, further optimization and emerging technologies, such as computer vision, are required to improve these technologies. AI/ML algorithms have demonstrated very accurate prediction performance, with receiver operating characteristics (ROC) and areas under the curve (AUC) greater than 0.90. However, there is a need to improve on these current models with large test datasets. Through AI/ML, IoT, and cloud computing technologies, early warnings can be disseminated to targeted communities in real time via electronic media, such as SMS and social media platforms. In spite of this, these systems have issues with internet connectivity, as well as data loss. Additionally, Al/ML used a number of topographical variables (such as slope), geological variables (such as lithology), and hydrological variables (such as stream density) to predict susceptibility, but the selection of these variables lacks a clear theoretical basis and has inconsistencies. To generate more reliable flood risk assessment maps, future studies should also consider sociodemographic, health, and housing data. Considering future climate change impacts, susceptibility or early warning studies may be projected under different climate change scenarios to help design long-term adaptation strategies.

Automatic identification of incidents involving potential serious injuries and fatalities (PSIF)

Safety incidents have always been a crucial risk in work spaces, especially industrial sites. In the last few decades, significant efforts have been dedicated to incident control measures to reduce the rate of safety incidents. Despite all these efforts, the rate of decline in serious injuries and fatalities (SIFs) has been considerably lower than the rate of decline for non-critical incidents. This observation has led to a change of risk reduction paradigm for safety incidents. Under the new paradigm, more focus has been allocated to reducing the rate of critical/SIF incidents, as opposed to reducing the count of all incidents. One of the challenges in reducing the number of SIF incidents is the proper identification of the risk prior to materialization. One of the reasons for risk identification being a challenge is that companies usually only focus on incidents where SIF did occur reactively, and incidents that did not cause SIF but had the potential to do so go unnoticed. Identifying these potentially significant incidents, referred to as potential serious injuries and fatalities (PSIF), would enable companies to work on identifying critical risk and taking steps to prevent them preemptively. However, flagging PSIF incidents requires all incident reports to be analyzed individually by experts and hence significant investment, which is often not affordable, especially for small and medium sized companies. This study is aimed at addressing this problem through machine learning powered automation. We propose a novel approach based on binary classification for the identification of such incidents involving PSIF (potential serious injuries and fatalities). This is the first work towards automatic risk identification from incident reports. Our approach combines a pre-trained transformer model with XGBoost. We utilize advanced natural language processing techniques to encode an incident record comprising heterogeneous fields into a vector representation fed to XGBoost for classification. Moreover, given the scarcity of manually labeled incident records available for training, we leverage weak labeling to augment the label coverage of the training data. We utilize the F2 metric for hyperparameter tuning using Tree-structured Parzen Estimator to prioritize the detection of PSIF records over the avoidance of non-PSIF records being mis-classified as PSIF. The proposed methods outperform several baselines from other studies on a significantly large test dataset.

Abstract 904: AI platform provides an EDGE and enables state-of-the-art identification of peptide-HLAs for the development of T cell inducing vaccines

Abstract T cell inducing vaccines are key for the development of effective therapies against cancer and infectious diseases. Peptides, presented by Human Leukocyte Antigens (HLAs), are the targets of T cells, and their identification is therefore critical to the development of such vaccines. Here, we present the latest improvement in our EDGETM (Epitope Discovery for GEnomes) platform to address this critical need. EDGE is comprised of AI models that can predict peptide presentation by HLA class I and class II. Although the models are trained primarily using immunopeptidomics data, EDGE scores are predictive of peptide-HLA immunogenicity. There are three class I presentation models in EDGE: an allele-specific model, a pan-specific model, and a model specific for infectious diseases. The allele-specific model is applicable to a large but pre-defined set of HLA alleles. On a large test dataset, the allele-specific model achieved an average precision (AP) of 63% (PPV40=79%) compared to the AP of a standard best-available public model of 21% (PPV40=28%). A Ph1/2 clinical study of personalized cancer vaccines encoding neoantigens predicted from the allele-specific model demonstrated a ~50% molecular response (defined as >=30% reduction in circulating tumor DNA relative to baseline) rate with associated extended overall survival (vs non-responders) in metastatic, microsatellite stable colorectal cancer patients. We observed that >50% of the mutations were able to elicit T cell responses. The pan-specific class I model uses HLA sequences as input feature when training and, therefore, is applicable to any HLA. On the same test dataset as above, it achieved an AP of 65% (PPV40=81%) and performed better on average for ~40 less-common HLA alleles. Prediction of viral peptide presentation by HLA class I is challenging due to the lack of immunopeptidomics data. The class I model for infectious diseases was specifically optimized to predict for viral peptides and, therefore, performed better than available class I models on published HIV and Influenza A datasets. Prediction of peptide presentation by HLA class II is challenging due to the flexibility in how the longer peptides interact with open HLA grooves as well as the lack of immunopeptidomics data as compared to the class I peptides. The class II model in EDGE, EDGE-II, uses the latest developments in protein large language models, a novel learned HLA allele-deconvolution strategy, and in-house immunopeptidomics data, resulting in improved prediction of peptide presentation by HLA class II and immunogenicity driven by CD4+ T cells. On a benchmark validation dataset, EDGE-II achieved an AP of 71% as compared to AP of 62% of a leading published model. In summary, EDGETM provides a comprehensive state-of-the-art platform for the development of vaccines that can induce both CD8+ and CD4+ T cell responses to provide durable benefit to patients. Citation Format: Joshua Klein, Daniel Sprague, Monica Lane, Meghan Hart, Olivia Petrillo, Italo Faria do Valle, Matthew Davis, Andrew Ferguson, Andrew Allen, Karin Jooss, Ankur Dhanik. AI platform provides an EDGE and enables state-of-the-art identification of peptide-HLAs for the development of T cell inducing vaccines [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 904.

An Enhanced Automated Identification of Brain Tumor Cells Using Image Segmentation

Brain tumors are a serious threat to human health, and getting a proper diagnosis quickly is essential for successful treatment. This study introduces a novel automated method that uses improved image segmentation algorithms to detect brain tumor cells in diagnostic images. The work uses cutting-edge deep learning models and novel preprocessing techniques to boost the precision and speed with which tumor cells may be identified. The procedure starts with gathering a large dataset of brain tumor images, then moves on to intensive preprocessing to improve the quality of those images. To accurately define tumor locations, a new picture segmentation approach is developed that utilizes convolutional neural networks (CNNs) and morphological operations. The segmented sections are then used to develop a deep learning classifier to recognize tumor cells. The proposed method has been shown to be effective in experiments, with a noticeable increase in the accuracy of identifying tumor cells over previous methods. On a large test dataset, the system demonstrates clinical viability with an average classification using Average polling technique of 92% and classification using Max polling technique of 98.87%. In conclusion, this study advances medical image analysis by providing a more effective automated method of identifying brain tumor cells.

Multi-UAV Cooperative Trajectory Planning Based on the Modified Cheetah Optimization Algorithm.

The capacity for autonomous functionality serves as the fundamental ability and driving force for the cross-generational upgrading of unmanned aerial vehicles (UAVs). With the disruptive transformation of artificial intelligence technology, autonomous trajectory planning based on intelligent algorithms has emerged as a key technique for enhancing UAVs' capacity for autonomous behavior, thus holding significant research value. To address the challenges of UAV trajectory planning in complex 3D environments, this paper proposes a multi-UAV cooperative trajectory-planning method based on a Modified Cheetah Optimization (MCO) algorithm. Firstly, a spatiotemporal cooperative trajectory planning model is established, incorporating UAV-cooperative constraints and performance constraints. Evaluation criteria, including fuel consumption, altitude, and threat distribution field cost functions, are introduced. Then, based on its parent Cheetah Optimization (CO) algorithm, the MCO algorithm incorporates a logistic chaotic mapping strategy and an adaptive search agent strategy, thereby improving the home-returning mechanism. Finally, extensive simulation experiments are conducted using a considerably large test dataset containing functions with the following four characteristics: unimodal, multimodal, separable, and inseparable. Meanwhile, a strategy for dimensionality reduction searching is employed to solve the problem of autonomous trajectory planning in real-world scenarios. The results of a conducted simulation demonstrate that the MCO algorithm outperforms several other related algorithms, showcasing smaller trajectory costs, a faster convergence speed, and stabler performance. The proposed algorithm exhibits a certain degree of correctness, effectiveness, and advancement in solving the problem of multi-UAV cooperative trajectory planning.

Efficient and scalable DBSCAN framework for clustering continuous trajectories in road networks

Clustering the trajectories of vehicles moving on road networks is a key data mining technique for understanding human mobility patterns, as well as their interactions with urban environments. The development of efficient and scalable trajectory clustering algorithms, however, still faces challenges because of the computational costs when measuring similarities among a large number of network-constrained trajectories. To address this problem, a novel trajectory clustering framework based on the well-developed Density-Based Spatial Clustering of Applications with Noise (DBSCAN) approach is proposed. This proposed framework accurately quantifies similarities using a trajectory representation of continuous polylines in the space and time dimensions, and does not require trajectory discretization. Further, the proposed framework utilizes the space-time buffering concept to formulate ε -neighborhood queries that directly retrieve the ε -neighbors of trajectories and thus avoids computing a trajectory similarity matrix. State-of-the-art trajectory databases and index structures are incorporated to further improve trajectory clustering performance. A comprehensive case study was carried out using an open dataset of 20,161 trajectories. Results show that the proposed framework efficiently executed trajectory clustering on the large test dataset within 3 min. This was approximately 2,700 times faster than existing DBSCAN algorithms.

Geometric Deep Learning for Molecular Crystal Structure Prediction.

We develop and test new machine learning strategies for accelerating molecular crystal structure ranking and crystal property prediction using tools from geometric deep learning on molecular graphs. Leveraging developments in graph-based learning and the availability of large molecular crystal data sets, we train models for density prediction and stability ranking which are accurate, fast to evaluate, and applicable to molecules of widely varying size and composition. Our density prediction model, MolXtalNet-D, achieves state-of-the-art performance, with lower than 2% mean absolute error on a large and diverse test data set. Our crystal ranking tool, MolXtalNet-S, correctly discriminates experimental samples from synthetically generated fakes and is further validated through analysis of the submissions to the Cambridge Structural Database Blind Tests 5 and 6. Our new tools are computationally cheap and flexible enough to be deployed within an existing crystal structure prediction pipeline both to reduce the search space and score/filter crystal structure candidates.

Large-scale demonstration of machine learning for the detection of volcanic deformation in Sentinel-1 satellite imagery

Radar (SAR) satellites systematically acquire imagery that can be used for volcano monitoring, characterising magmatic systems and potentially forecasting eruptions on a global scale. However, exploiting the large dataset is limited by the need for manual inspection, meaning timely dissemination of information is challenging. Here we automatically process ~ 600,000 images of > 1000 volcanoes acquired by the Sentinel-1 satellite in a 5-year period (2015–2020) and use the dataset to demonstrate the applicability and limitations of machine learning for detecting deformation signals. Of the 16 volcanoes flagged most often, 5 experienced eruptions, 6 showed slow deformation, 2 had non-volcanic deformation and 3 had atmospheric artefacts. The detection threshold for the whole dataset is 5.9 cm, equivalent to a rate of 1.2 cm/year over the 5-year study period. We then use the large testing dataset to explore the effects of atmospheric conditions, land cover and signal characteristics on detectability and find that the performance of the machine learning algorithm is primarily limited by the quality of the available data, with poor coherence and slow signals being particularly challenging. The expanding dataset of systematically acquired, processed and flagged images will enable the quantitative analysis of volcanic monitoring signals on an unprecedented scale, but tailored processing will be needed for routine monitoring applications.

Understanding the role of sequence stratigraphy and diagenesis on the temporal and spatial distribution of carbonate reservoir quality: A conceptual modeling approach

Karst caves formed by meteoric water leaching are important oil/gas storage spaces in carbonate reservoirs. However, carbonate reservoirs are transformed by atmospheric freshwater due to long-term cumulative effects that take place over millions of years, and laboratory physical simulations are therefore difficult to conduct. The mechanism by which meteoric water leaching transforms the carbonate sequence stratigraphy is therefore unclear, which has hindered the exploration and development of oil/gas resources. In this study, a large set of geological test data was utilized to develop a solute transport numerical simulation model based on multi-phase flow and multi-component reaction. This was then applied to construct a conceptual model of a grade III sequence stratigraphy for a reservoir in the Yingshan Formation in the central Tarim Basin, China. The multi-stage leaching process of meteoric water during the periodic exposure of the sequence stratigraphy was simulated to explore the effects of the diagenetic transformation of meteoric water on sequence stratigraphy and the associated physical responses. Results revealed that the composition of carbonate rocks affects the degree of reservoir development under the sequence boundary. Calcite dissolution plays a strong role in meteoric water leaching. Carbonate strata with a high calcite content forms secondary pores relatively easily and dolomite can be preserved. Under open geological conditions, the transformation of reservoirs by meteoric water in different periods has the characteristics of continuity, indirectness, superposition, and heterogeneity. In addition to the mineral dissolution caused by the unsaturated solution of the underlying strata, the transformation was also affected by the superposition and indirect influence of the migration and infiltration of the overlying strata fluid. Under heterogeneous conditions, meteoric water preferentially flowed along the dominant channels, which could improve reservoir performance locally, and may form oil and gas migration channels or large karst caves. This investigation of the control of meteoric water during reservoir development provides a theoretical basis for the genetic mechanism by which a high-quality reservoir can develop under the carbonate sequence boundary.

Optimization of hyperparameters of Gaussian process regression with the help of а low-order high-dimensional model representation: application to a potential energy surface

Gaussian process regression (GPR) has been finding an increased use in computational chemistry, including for applications where high accuracy of machine learning is required, such as potential energy surfaces or functionals for density functional theory. The quality of a GPR model critically depends on the choice of hyperparameters of the kernel. When the data are sparse, optimization of the hyperparameters by the commonly used methods such as maximum likelihood estimation (MLE) criterion can lead to overfitting. We show that choosing hyperparameters (in this case, the kernel length parameter and the regularization parameter) based on a criterion of the completeness of the basis in the corresponding linear regression problem is superior to MLE. We show that this is facilitated by the use of high-dimensional model representation (HDMR) whereby a low-order HDMR representation can provide reliable reference functions and allow generating large synthetic test data sets needed for basis parameter optimization even when the original data are few. This is expected to be particularly useful when fitting potential energy surfaces where a sufficiently low-order HDMR can provide a good approximation. An example of a 15-dimensional PES of UF6 is presented.

Predicting the Stability of Hierarchical Triple Systems with Convolutional Neural Networks

The dynamical stability of hierarchical triple systems is a long-standing question in celestial mechanics and dynamical astronomy. Assessing the long-term stability of triples is challenging because it requires computationally expensive simulations. Here we propose a convolutional neural network model to predict the stability of equal-mass hierarchical triples by looking at their evolution during the first 5 × 105 inner binary orbits. We employ the regularized few-body code tsunami to simulate 5 × 106 hierarchical triples, from which we generate a large training and test data set. We develop 12 different network configurations that use different combinations of the triples’ orbital elements and compare their performances. Our best model uses six time series, namely, the semimajor axes ratio, the inner and outer eccentricities, the mutual inclination, and the arguments of pericenter. This model achieves excellent performance, with an area under the ROC curve score of over 95% and informs of the relevant parameters to study triple systems stability. All trained models are made publicly available, which allows predicting the stability of hierarchical triple systems 200 times faster than pure N-body methods.

STORM DRAIN DETECTION AND LOCALISATION ON MOBILE LIDAR DATA USING A PRE-TRAINED RANDLA-NET SEMANTIC SEGMENTATION NETWORK

Abstract. As the expansion of cities and urban areas results in the construction of more impermeable road surfaces, a well designed urban drainage system becomes of greater importance. However, the accurate and up-to-date mapping of storm drains necessary to create accurate drainage models is often lacking. In recent years, mapping of the road infrastructure is increasingly carried out by highly efficient mobile mapping systems but which lack automatic interpretation of the massive amount data. In this paper we present a fully automatic storm drain detection method to extract and locate storm drain inlets in mobile mapping lidar data. The point cloud is first segmented by a pre-trained RandLa-Net model, which although untrained to segment storm drains, is able the segment storm drain clusters in the hardscape class. The results from this class are further processed by enforcing different requirements to only extract and locate storm drain clusters. Our approach is evaluated on a large testing dataset with 171 storm drains and achieves 81.9%, 95.2% and 88.1% for recall, precision and F1-score respectively. The majority of the false positive and false negative detections are due to incorrect point cloud segmentation of the RandLa-Net. In terms of localisation, our approach achieves an RMSE of 5.5 cm on the centre location while the dimensions of the bounding box are on average 23% off compared to the ground truth.

Deep Learning Approach for Radical Sound Valuation of Fetal Weight

It is a very complicated task to identify and decipher the standard output plane of the fetus in the evaluation of the second trimester of 2D ultrasound, which requires a long preparation time. In addition to directing the test to the correct area, it is difficult for a technician to distinguish the applicable structure in the picture. The programmatic picture preparation function allows the device to provide assistance to experienced administrators to help them solve these problems. We portray an extraordinary convolutional neural organization-based methodology for perceiving thirteen fetal well-known perspectives in freehand 2D ultrasound data and introducing fetal primary limitation by utilizing a bouncing field in this examination. Utilizing exclusively the objective life structures, the local area figures out how to pinpoint image level labels, which is a significant contribution. Tissue engineering aims to work continuously, while providing ideal benefits for localization tasks. We provide the results of continuous reviews, recover outlines from saved pictures, and localize them in an extremely large test data set, which includes pictures and video accounts of complete clinical peculiar examinations. We tracked down that the proposed acquired 91% exactness for review outline recovery and 82% precision in the localization task.

DEVELOPMENT OF TEST CORPUS WITH LARGE VOCABULARY FOR TURKISH SPEECH RECOGNITION SYSTEM AND A NEW TEST PROCEDURE

The most fundamental problem in the automatic speech recognition systems is not the development of a domainspecific automatic speech recognition system, but the development of an automatic speech recognition system with a large vocabulary. Developed automatic speech recognition systems should be tested with a large vocabulary test dataset. For this reason, an automatic speech recognition test corpus was prepared within the scope of the study. Prepared automatic speech recognition test corpus includes conversations from 20 different areas and text files of these conversations. The test procedure presented in the study was also tested on Turkish automatic speech recognition systems with a large vocabulary. It has been observed that the word error rate results ranged between 14-21%. The test corpus and test procedure with a large vocabulary prepared are guiding for the success of automatic speech recognition systems in future studies to be revealed more clearly.

A new approach to modeling cycles with summer and winter demand peaks as input variables for deep neural networks

Electricity demand is highly cyclical. In many markets, two demand peaks are observed – winter and summer. The paper presents a new, complex approach to modeling this type of cycles using trigonometric functions and long-term changes using the sliding window technique. The proposed method allows the modeling of annual cycles with asymmetrically located upper maxima of the demand. The new formulas take into account the moments of each peak occurrence, their values, as well as the demand course between them. All parameters can be selected in an algorithmic manner. Due to the modeling of each of the 24 h separately, it is possible to take into consideration the differences in the course of the cycles for each of them. The approach was tested in three electricity markets that differ in the demand pattern, with a different relation between values of winter and summer peaks. The precision of the proposed approach was verified by deep neural networks. They were used to forecast electricity demand for each of the 24 h of the day, one day ahead. As comparative models, deep neural networks based on lagged values of demand were used. A large test dataset out of sample forecasts covering a period of two calendar years was used. This showed that the proposed novel approach significantly reduces the mean absolute percentage error compared to the models directly forecasting total electricity demand. The described approach can also be used in forecasting techniques other than artificial neural networks.

Prediction of frictional braking noise based on brake dynamometer test and artificial intelligent algorithms

Based on brake noise dynamometer test data, combined with the artificial intelligent algorithms, frictional braking noise is quantitatively analyzed and predicted in this study. To achieve this goal, a frictional braking noise prediction method is indicatively proposed, which consists of two main parts: first, based on the experimental data obtained from the brake noise dynamometer tests, and combining with the improved Long-Short-Term Memory (LSTM) algorithm, the coefficients of friction (COFs) are predicted under various braking test conditions. Then, based on the predicted braking COFs and other selected critical braking parameters, the quantitative prediction of frictional braking noise is obtained by means of the optimized eXtreme Gradient Boosting (XGBoost) algorithm. Finally, the inherent features of the XGBoost algorithm are employed to qualitatively analyze the importance of the main factors affecting the frictional braking noise. The prediction algorithms of COFs and frictional braking noise are validated by the brake dynamomter test data, and the R2 (R square) scores of both the LSTM and XGBoost prediction algorithms are 0.9, which verifies the feasibility of both algorithms. The main contribution of this work is to predict the braking noise based on a large set of test data and combined with the LSTM and XGBoost artificial intelligent algorithms, which can significantly save time for the brake system development and braking performance testing, and has significance to the rapid prediction of braking frictional noise and fast NVH (noise, vibration, and harshness) optimal design of frictional braking systems.

Individual variations in 'brain age' relate to early-life factors more than to longitudinal brain change.

Brain age is a widely used index for quantifying individuals' brain health as deviation from a normative brain aging trajectory. Higher-than-expected brain age is thought partially to reflect above-average rate of brain aging. Here, we explicitly tested this assumption in two independent large test datasets (UK Biobank [main] and Lifebrain [replication]; longitudinal observations ≈ 2750 and 4200) by assessing the relationship between cross-sectional and longitudinal estimates of brain age. Brain age models were estimated in two different training datasets (n ≈ 38,000 [main] and 1800 individuals [replication]) based on brain structural features. The results showed no association between cross-sectional brain age and the rate of brain change measured longitudinally. Rather, brain age in adulthood was associated with the congenital factors of birth weight and polygenic scores of brain age, assumed to reflect a constant, lifelong influence on brain structure from early life. The results call for nuanced interpretations of cross-sectional indices of the aging brain and question their validity as markers of ongoing within-person changes of the aging brain. Longitudinal imaging data should be preferred whenever the goal is to understand individual change trajectories of brain and cognition in aging.

Computational analysis of axially loaded thin-walled rectangular concrete-filled stainless steel tubular short columns incorporating local buckling effects

This paper investigates the structural performance of concrete-filled stainless steel tubular (CFSST) columns composed of rectangular and square sections. A fiber-based mathematical model is developed to simulate the nonlinear performance of such columns loaded concentrically accounting for the local buckling of steel tube. An accurate lateral pressure model, as well as a strength degradation parameter are proposed based on the existing test results and incorporated in the mathematical modeling developed. A large test dataset is used to validate the accuracy of the numerical prediction. The mathematical model is employed to study the sensitivities of important column parameters on their axial behavior. The accuracy of the existing confinement model of rectangular CFST columns is evaluated in predicting the performance of CFSST short columns. Furthermore, the accuracy of the existing codified design models as well as and the simplified design model proposed in this study to quantify the ultimate compressive strength of such columns is investigated. An accurate artificial neural network (ANN) model along with the GUI feature is developed for the design engineers as a tool to predict their ultimate axial strengths.

ProFitFun: a protein tertiary structure fitness function for quantifying the accuracies of model structures.

An accurate estimation of the quality of protein model structures typifies as a cornerstone in protein structure prediction regimes. Despite the recent groundbreaking success in the field of protein structure prediction, there are certain prospects for the improvement in model quality estimation at multiple stages of protein structure prediction and thus, to further push the prediction accuracy. Here, a novel approach, named ProFitFun, for assessing the quality of protein models is proposed by harnessing the sequence and structural features of experimental protein structures in terms of the preferences of backbone dihedral angles and relative surface accessibility of their amino acid residues at the tripeptide level. The proposed approach leverages upon the backbone dihedral angle and surface accessibility preferences of the residues by accounting for its N-terminal and C-terminal neighbors in the protein structure. These preferences are used to evaluate protein structures through a machine learning approach and tested on an extensive dataset of diverse proteins. The approach was extensively validated on a large test dataset (n = 25005) of protein structures, comprising 23661 models of 82 non-homologous proteins and 1344 non-homologous experimental structures. In addition, an external dataset of 40000 models of 200 non-homologous proteins was also used for the validation of the proposed method. Both datasets were further used for benchmarking the proposed method with four different state-of-the-art methods for protein structure quality assessment. In the benchmarking, the proposed method outperformed some state-of-the-art methods in terms of Spearman's and Pearson's correlation coefficients, average GDT-TS loss, sum of z-scores and average absolute difference of predictions over corresponding observed values. The high accuracy of the proposed approach promises a potential use of the sequence and structural features in computational protein design. http://github.com/KYZ-LSB/ProTerS-FitFun. Supplementary data are available at Bioinformatics online.