Multiple Metrics Research Articles

Quantifying and correcting geolocation error in spaceborne LiDAR forest canopy observations using high spatial accuracy data: A Bayesian model approach

AbstractGeolocation error in spaceborne sampling light detection and ranging (LiDAR) measurements of forest structure can compromise forest attribute estimates and degrade integration with georeferenced field measurements or other remotely sensed data. Data integration is especially problematic when geolocation error is not well quantified. We propose a general model that uses airborne laser scanning data to quantify and correct geolocation error in spaceborne sampling LiDAR. To illustrate the model, LiDAR data from NASA Goddard's LiDAR Hyperspectral and Thermal Imager (G‐LiHT) was used with a subset of LiDAR data from NASA's Global Ecosystem Dynamics Investigation (GEDI). The model accommodates multiple canopy height metrics derived from a simulated GEDI footprint kernel using spatially coincident G‐LiHT, and incorporates both additive and multiplicative mapping between the canopy height metrics generated from both datasets. A Bayesian implementation provides probabilistic uncertainty quantification in both parameter and geolocation error estimates. Results show a systematic geolocation error of 9.62 m in the southwest direction. In addition, estimated geolocation errors within GEDI footprints were highly variable, with results showing a 0.45 probability the true footprint center is within 20 m. Estimating and correcting geolocation error via the model outlined here can help inform subsequent efforts to integrate spaceborne LiDAR data, like GEDI, with other georeferenced data.

Climate change-related biodiversity fluctuations and composition changes in an old-growth subtropical forest: A 26-yr study

The detection and attribution of biodiversity change is of great scientific interest and central to policy effects aimed at meeting biodiversity targets. Yet, how such a diverse climate scenarios influence forest biodiversity and composition dynamics remains unclear, particularly in high diversity systems of subtropical forests. Here we used data collected from the permanent sample plot spanning 26 years in an old-growth subtropical forest. Combining various climatic events (extreme drought, subsequent drought, warming, and windstorm), we analyzed long-term dynamics in multiple metrics: richness, turnover, density, abundance, reordering and stability. We did not observe consistent and directional trends in species richness under various climatic scenarios. Still, drought and windstorm events either reduced species gains or increased species loss, ultimately increased species turnover. Tree density increased significantly over time as a result of rapid increase in smaller individuals due to mortality in larger trees. Climate events caused rapid changes in dominant populations due to a handful of species undergoing strong increases or declines in abundance over time simultaneously. Species abundance composition underwent significant changes, particularly in the presence of drought and windstorm events. High variance ratio and species synchrony weaken community stability under various climate stress. Our study demonstrates that all processes underlying forest community composition changes often occur simultaneously and are equally affected by climate events, necessitating a holistic approach to quantifying community changes. By recognizing the interconnected nature of these processes, future research should accelerate comprehensive understanding and predicting of how forest vegetation responds to global climate change.

Proposed hybrid Model in Online Education

The advancement of technology powering e-learning has brought numerous benefits, including consistency, scalability, cost reduction, and improved usability. However, there are also challenges that need to be addressed. Here are some key considerations for enhancing the technology powering e-learning. Artificial intelligence has revolutionized the field of e-learning and created tremendous opportunities for education Storage, servers, software systems, databases, online management systems, and apps are examples of such resources. This paper aims to forecast students' adaptability to online education using predictive machine learning (ML) models, including Logistic Regression, Decision tree, Random Forest, AdaBoost, ANN. The dataset utilized for this study was sourced from Kaggle and comprised 1205 high school to college students. The research encompasses several stages of data analysis, including data preprocessing, model training, testing, and validation. Multiple performance metrics such as accuracy, specificity, sensitivity, F1 score, and precision were employed to assess the effectiveness of each model. The findings demonstrate that all five models exhibit considerable predictive capabilities. Notably, decision tree and hybrid models outperformed the others, achieving an impressive accuracy rate of 92%. Consequently, it is recommended to utilize these two models, RF and XGB, for predicting students' adaptability levels in online education due to their superior predictive accuracy. Additionally, the Logistic regression, KNN, and AdaBoost, ANN models also yielded respectable performance levels, achieving accuracy rates of 77.48%, 83.77 ,74.17% and 91.06% respectively. In summary, this study underscores the superiority of RF and XGB models in delivering higher prediction accuracy, aligning with similar research endeavours employing ML techniques to forecast adaptability levels.

Interpretable machine learning model for early prediction of 28-day mortality in ICU patients with sepsis-induced coagulopathy: development and validation

ObjectiveSepsis-induced coagulopathy (SIC) is extremely common in individuals with sepsis, significantly associated with poor outcomes. This study attempted to develop an interpretable and generalizable machine learning (ML) model for early predicting the risk of 28-day death in patients with SIC.MethodsIn this retrospective cohort study, we extracted SIC patients from the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV, and eICU-CRD database according to Toshiaki Iba's scale. And the overlapping in the MIMIC-IV was excluded for this study. Afterward, only the MIMIC-III cohort was randomly divided into the training set, and the internal validation set according to the ratio of 7:3, while the MIMIC-IV and eICU-CRD databases were considered the external validation sets. The predictive factors for 28-day mortality of SIC patients were determined using recursive feature elimination combined with tenfold cross-validation (RFECV). Then, we constructed models using ML algorithms. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), accuracy, sensitivity, specificity, negative predictive value, positive predictive value, recall, and F1 score. Finally, Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) were employed to provide a reasonable interpretation for the prediction results.ResultsA total of 3280, 2798, and 1668 SIC patients were screened from MIMIC-III, MIMIC-IV, and eICU-CRD databases, respectively. Seventeen features were selected to construct ML prediction models. XGBoost had the best performance in predicting the 28-day mortality of SIC patients, with AUC of 0.828, 0.913 and 0.923, the AUPRC of 0.807, 0.796 and 0.921, the accuracy of 0.785, 0.885 and 0.891, the F1 scores were 0.63, 0.69 and 0.70 in MIMIC-III (internal validation set), MIMIC-IV, and eICU-CRD databases. The importance ranking and SHAP analyses showed that initial SOFA score, red blood cell distribution width (RDW), and age were the top three critical features in the XGBoost model.ConclusionsWe developed an optimal and explainable ML model to predict the risk of 28-day death of SIC patients 28-day death risk. Compared with conventional scoring systems, the XGBoost model performed better. The model established will have the potential to improve the level of clinical practice for SIC patients.Graphical

Selective logging intensity and time since logging drive tropical bird and dung beetle diversity: a case study from Amazonia

SummaryUnderstanding how selective logging affects biodiversity is crucial to planning cost-effective conservation strategies in tropical forests, yet there is limited understanding of its impacts on fauna functional diversity in the tropical Americas. We assessed how selective logging intensification and time since logging influence multiple metrics of fauna functional integrity in the Brazilian Amazon by collecting bird and dung beetle data within 48 logging management units that had experienced varying exploitation intensities between 1.5–2.0 and 5.0–6.0 years before the faunal surveys. We investigated assemblage responses and used functional attributes to assess changes in functional diversity, specialization, originality and species rarity. Using point counts and pitfall traps, we collected 5081 records of 182 bird species and 7892 dung beetles from 45 species. Logging intensification led to significant declines in most dung beetle responses and bird body mass, whereas time since logging was a key driver of dung beetle and bird functional and taxonomic diversity. Our study presents novel empirical evidence of how logging intensification effects vary across taxa, ecological metrics and time since logging, which is key to informing forest conservation and further investigating environmental degradation impacts on tropical biodiversity.

A PRECISION HEALTH APPROACH FOR OSTEOARTHRITIS: PREDICTION OF RAPID KNEE OSTEOARTHRITIS PROGRESSION USING AUTOMATED MACHINE LEARNING

Precision health aims to develop personalised and proactive strategies for predicting, preventing, and treating complex diseases such as osteoarthritis (OA). Due to OA heterogeneity, which makes developing effective treatments challenging, identifying patients at risk for accelerated disease progression is essential for efficient clinical trial design and new treatment target discovery and development.To create a reliable and interpretable precision health tool that predicts rapid knee OA progression over a 2-year period from baseline patient characteristics using an advanced automated machine learning (autoML) framework, “Autoprognosis 2.0”.All available 2-year follow-up periods of 600 patients from the FNIH OA Biomarker Consortium were analysed using “Autoprognosis 2.0” in two separate approaches, with distinct definitions of clinical outcomes: multi-class predictions (categorising disease progression into pain and/or radiographic progression) and binary predictions. Models were developed using a training set of 1352 instances and all available variables (including clinical, X-ray, MRI, and biochemical features), and validated through both stratified 10-fold cross-validation and hold-out validation on a testing set of 339 instances. Model performance was assessed using multiple evaluation metrics. Interpretability analyses were carried out to identify important predictors of progression.Our final models yielded higher accuracy scores for multi-class predictions (AUC-ROC: 0.858, 95% CI: 0.856-0.860) compared to binary predictions (AUC-ROC: 0.717, 95% CI: 0.712-0.722). Important predictors of rapid disease progression included WOMAC scores and MRI features. Additionally, accurate ML models were developed for predicting OA progression in a subgroup of patients aged 65 or younger.This study presents a reliable and interpretable precision health tool for predicting rapid knee OA progression. Our models provide accurate predictions and, importantly, allow specific predictors of rapid disease progression to be identified. Furthermore, the transparency and explainability of our methods may facilitate their acceptance by clinicians and patients, enabling effective translation to clinical practice.

Machine learning based predictive model of Type 2 diabetes complications using Malaysian National Diabetes Registry: A study protocol.

The prevalence of diabetes in Malaysia is increasing, and identifying patients with higher risk of complications is crucial for effective management. The use of machine learning (ML) to develop prediction models has been shown to outperform non-ML models. This study aims to develop predictive models for Type 2 Diabetes (T2D) complications in Malaysia using ML techniques. This 10-year retrospective cohort study uses clinical audit datasets from Malaysian National Diabetes Registry from 2011 to 2021. T2D patients who received treatment in public health clinics in the southern region of Malaysia with at least two data points in 10 years are included. Patients with diabetes complications at baseline are excluded to ensure temporality between predictors and the target variable. Appropriate methods are used to address issues related to data cleaning, missing data imputation, data splitting, feature selection, and class imbalance. The study uses 7 ML algorithms, including logistic regression, support vector machine, k-nearest neighbours, decision tree, random forest, extreme gradient boosting, and light gradient boosting machine, to develop predictive models for four target variables: nephropathy, retinopathy, ischaemic heart disease, and stroke. Hyperparameter tuning is performed for each algorithm. The model training is performed using a stratified k-fold cross-validation technique. The best model for each algorithm is evaluated on a hold-out dataset using multiple metrics. The prediction model may be a valuable tool for diabetes management and secondary prevention by enabling earlier interventions and optimal resource allocation, leading to better health outcomes.

Position Fusing and Refining for Clear Salient Object Detection.

Multilevel feature fusion plays a pivotal role in salient object detection (SOD). High-level features present rich semantic information but lack object position information, whereas low-level features contain object position information but are mixed with noises such as backgrounds. Appropriately addressing the gap between low-and high-level features is important in SOD. We first propose a global position embedding attention (GPEA) module to minimize the discrepancy between multilevel features in this article. We extract the position information by utilizing the semantic information at high-level features to resist noises at low-level features. Object refine attention (ORA) module is introduced to refine features used to predict saliency maps further without any additional supervision and heighten discriminative regions near the salient object, such as boundaries. Moreover, we find that the saliency maps generated by the previous methods contain some blurry regions, and we design a pixel value (PV) loss to help the model generate saliency maps with improved clarity. Experimental results on five commonly used SOD datasets demonstrated that the proposed method is effective and outperforms the state-of-the-art approaches on multiple metrics.

Geographies of regulatory disparity underlying Australia’s energy transition

Disparities in electricity retail regulatory protections will see some consumers approaching energy transition from an uneven footing. Here we examine the spatial organization of regulatory inequities in Australia by mapping electricity legal protections for settlements nationwide. Multiple logistic regression (n = 2,996) identifies the geographic and socio-demographic characteristics of settlements likely to be underserved by regulations to: protect life-support customers, guarantee service levels, clarify connection requirements for rooftop solar, require disconnection reporting and set clear and independent complaints processes. Assessing whether communities receive fewer than four of five protections, we find that Indigenous communities are 15% more likely to be underserved across multiple metrics and remote communities are 18% more likely to be underserved. These groups overlap. Those communities whose lands are rich in resources necessary for energy transition are simultaneously at risk of non-recognition of their own energy needs under current regulation, requiring policy remedies for a just transition.

A machine learning-enabled process optimization of ultra-fast flow chemistry with multiple reaction metrics

An automated flow chemistry platform was designed to collect data for a lithium-halogen exchange reaction. The data was used to train a Bayesian multi-objective optimization algorithm to optimize the process parameters and build process knowledge.

Logic mining with hybridized 3-satisfiability fuzzy logic and harmony search algorithm in Hopfield neural network for Covid-19 death cases

<abstract> <p>Since the beginning of the Covid-19 infections in December 2019, the virus has emerged as the most lethally contagious in world history. In this study, the Hopfield neural network and logic mining technique merged to extract data from a model to provide insight into the link between factors influencing the Covid-19 datasets. The suggested technique uses a 3-satisfiability-based reverse analysis (3SATRA) and a hybridized Hopfield neural network to identify the relationships relating to the variables in a set of Covid-19 data. The list of data is to identify the relationships between the key characteristics that lead to a more prolonged time of death of the patients. The learning phase of the hybridized 3-satisfiability (3SAT) Hopfield neural network and the reverse analysis (RA) method has been optimized using a new method of fuzzy logic and two metaheuristic algorithms: Genetic and harmony search algorithms. The performance assessment metrics, such as energy analysis, error analysis, computational time, and accuracy, were computed at the end of the algorithms. The multiple performance metrics demonstrated that the 3SATRA with the fuzzy logic metaheuristic algorithm model outperforms other logic mining models. Furthermore, the experimental findings have demonstrated that the best-induced logic identifies important variables to detect critical patients that need more attention. In conclusion, the results validate the efficiency of the suggested approach, which occurs from the fact that the new version has a positive effect.</p> </abstract>

Thermal constraints on exercise and metabolic performance do not explain the use of dormancy as an overwintering strategy in the cunner (Tautogolabrus adspersus).

Winter cold slows ectotherm physiology, potentially constraining activities and ecological opportunities at poleward latitudes. Yet, many fishes are winter-active, facilitated by thermal compensation that improves cold performance. Conversely, winter-dormant fishes (e.g. cunner, Tautogolabrus adspersus) become inactive and non-feeding overwinter. Why are certain fishes winter-dormant? We hypothesized that winter dormancy is an adaptive behavioural response arising in poleward species that tolerate severe, uncompensated constraints of cold on their physiological performance. We predicted that below their dormancy threshold of 7--8°C, exercise and metabolic performance of cunner are greatly decreased, even after acclimation (i.e. shows above-normal, uncompensated thermal sensitivity, Q10>1-3). We measured multiple key performance metrics (e.g. C-start maximum velocity, chase swimming speed, aerobic scope) in cunner after acute exposure to 26-2°C (3°C intervals using 14°C-acclimated fish) or acclimation (5-8 weeks) to 14-2°C (3°C intervals bracketing the dormancy threshold). Performance declined with cooling, and the acute Q10 of all six performance rate metrics was significantly greater below the dormancy threshold temperature (Q10,acute8-2°C=1.5-4.9, mean=3.3) than above (Q10,acute14-8°C=1.1-1.9, mean=1.5), inferring a cold constraint. However, 2°C acclimation (temporally more relevant to seasonal cooling) improved performance, abolishing the acute constraint (Q10,acclimated8-2°C=1.4-3.0, mean=2.0; also cf. Q10,acclimated14-8°C=1.2-2.9, mean=1.7). Thus, dormant cunner show partial cold-compensation of exercise and metabolic performance, similar to winter-active species. However, responsiveness to C-start stimuli was greatly cold-constrained even following acclimation, suggesting dormancy involves sensory limitation. Thermal constraints on metabolic and exercise physiology are not significant drivers of winter dormancy in cunner. In fact, compensatory plasticity at frigid temperatures is retained even in a dormant fish.

Dielectrophoretic enrichment of live chemo-resistant circulating-like pancreatic cancer cells from media of drug-treated adherent cultures of solid tumors.

Due to low numbers of circulating tumor cells (CTCs) in liquid biopsies, there is much interest in enrichment of alternative circulating-like mesenchymal cancer cell subpopulations from in vitro tumor cultures for utilization within molecular profiling and drug screening. Viable cancer cells that are released into the media of drug-treated adherent cancer cell cultures exhibit anoikis resistance or anchorage-independent survival away from their extracellular matrix with nutrient sources and waste sinks, which serves as a pre-requisite for metastasis. The enrichment of these cell subpopulations from tumor cultures can potentially serve as an in vitro source of circulating-like cancer cells with greater potential for scale-up in comparison with CTCs. However, these live circulating-like cancer cell subpopulations exhibit size overlaps with necrotic and apoptotic cells in the culture media, which makes it challenging to selectively enrich them, while maintaining them in their suspended state. We present optimization of a flowthrough high frequency (1 MHz) positive dielectrophoresis (pDEP) device with sequential 3D field non-uniformities that enables enrichment of the live chemo-resistant circulating cancer cell subpopulation from an in vitro culture of metastatic patient-derived pancreatic tumor cells. Central to this strategy is the utilization of single-cell impedance cytometry with gates set by supervised machine learning, to optimize the frequency for pDEP, so that live circulating cells are selected based on multiple biophysical metrics, including membrane physiology, cytoplasmic conductivity and cell size, which is not possible using deterministic lateral displacement that is solely based on cell size. Using typical drug-treated samples with low levels of live circulating cells (<3%), we present pDEP enrichment of the target subpopulation to ∼44% levels within 20 minutes, while rejecting >90% of dead cells. This strategy of utilizing single-cell impedance cytometry to guide the optimization of dielectrophoresis has implications for other complex biological samples.

Dynamic acoustic compensation and adaptive focal training for personalized speech enhancement

Recently, more and more personalized speech enhancement (PSE) systems with excellent performance have been proposed. Compared with traditional speech enhancement systems, PSE systems have a wider range of application scenarios, which can simultaneously remove background noise and interfering speaker's speech. However, two issues still limit the performance and generalization ability of the model: 1) Acoustic environment mismatch between the test noisy speech and clean enrollment speech of target speaker, which limits the performance of personalized speech enhancement system; 2) Hard sample mining and learning. How to improve the performance of hard samples determines the practicality of a personalized speech enhancement system in complex real-world scenarios. In this paper, a dynamic acoustic compensation (DAC) is proposed to alleviate the environment mismatch, by intercepting the acoustic segments from noisy speech and mixing it with enrollment speech. To well exploit the hard samples, we propose an adaptive focal training (AFT) strategy by assigning adaptive loss weights to hard and non-hard samples during training. Both the DAC and AFT are proposed to improve and generalize our previous work, a densely-connected pyramid complex convolutional network with speaker encoder (sDPCCN) for personalized speech enhancement. In addition, a time-frequency multi-loss training is further introduced to enhance the improved sDPCCN. To examine the effectiveness of the proposed methods, we generate the noisy-reverb training and test data by utilizing non-overlapping segments of the 4th Deep Noise Suppression (DNS4) Challenge Dataset. Results show that, DAC effectively alleviates the acoustic environment mismatch and brings large improvements in terms of multiple evaluation metrics, and AFT reduces the hard sample rate significantly. When all proposed methods are applied, the perceptual evaluation of speech quality (PESQ) score is improved from 3.21 to 3.36, and the scale invariant signal-to-noise ratio (SISNR) is improved from 15.11 to 15.89 on the test set, which fully verify their effectiveness and practicality.

Customized K-nearest neighbors’ algorithm for malware detection

The security and integrity of computer systems and networks highly depend on malware detection. In the realm of malware detection, the K-Nearest Neighbors (KNN) algorithm is a well-liked and successful machine learning algorithm. However, the choice of an acceptable distance metric parameter has a significant impact on the KNN algorithm's performance. This study tries to improve malware detection by adjusting the KNN algorithm's distance metric parameter. The distance metric greatly influences the similarity or dissimilarity between instances in the feature space. The KNN algorithm for malware detection can be more accurate and effective by carefully choosing or modifying the distance metric. This paper analyzes multiple distance metrics, including Minkowski distance, Manhattan distance, and Euclidean distance. These metrics account for the traits of malware samples while capturing various aspects of similarity. The effectiveness of the KNN algorithm is evaluated using the MalMem-2022 malware dataset, and the results are broken down into these three-distance metrics. The experimental findings show that, among the three distance metric parameters, the Euclidean and Minkowski distance metric parameters considerably produced the best outcomes with binary classification. While with multiclass classification, the KNN algorithm has achieved the highest outcomes using Manhattan distance.

Decentralized Blockchain-Based and Trust-Aware Task Offloading Strategy for Healthcare IoT

Although smart healthcare has achieved rapid development and has gained considerable attention from academia and industry, pressing challenges exist such as resource limitation and stringent security demand. To tackle the issues, a blockchain-based and trust-aware task-offloading strategy (BBTAS) is proposed in this work, whereby task offloading requests are published as blockchain transactions that are automatically yet securely performed by smart contracts (SCs). A SC is a set of codes implementing pre-defined rules agreed by the participants involved. When a rule meets certain criteria or triggered by some events or transactions, a SC can perform by itself and generate verifiable results, which can be validated and securely stored in the blockchain. The proposed recommendation filtering method (RFM) and trust penalty measure (TPM)-based trust mechanism is powerful in resisting network insider attacks, and the inherent time-inefficiency problem of blockchain can be alleviated by integrating trust factor, which is theoretically analyzed in this work. To optimize the selection of service node, a utility-based decision-making method (UB-DMM) is proposed, which can maximize the system utility on the basis of fully considering multiple significant performance metrics of the system. Extensive simulations have been carried out to validate the effectiveness and superiority of the proposed measures.

Reliable AI models can reveal key processes of heat recovery steam generator operation in air pollutant emission

Artificial intelligence (AI) algorithms have been applied to air pollution prediction modeling, but assessment of their trustworthiness is lacking. This study aims to examine whether AI-based models can identify key operational processes of a Heat Recovery Steam Generator (HRSG) facility and predict the emission of target air pollutants, including nitrogen oxides (NOx), sulfur oxides (SOx), and total suspended particles (TSP). First, key operational variables are selected based on the feature importance of the Random Forest models (that is, data-driven input selection). Secondly, Bidirectional Long Short-Term Memory-based AutoEncoder (BiLSTM-AE) and Random Forest (RF) models with the data-driven input selection are trained and evaluated using multiple predictive performance metrics. Then, the BiLSTM-AE and RF models are trained and evaluated using the operational variables selected by experts. Results demonstrate that the data-driven and expertise-based methods select five common operational variables that are key factors to predict variations of target output variables. The results from the multi-metric evaluations show a skillful prediction of BiLSTM-AE and RF models for NOx and TSP, but not SOx. For TSP prediction, RF is more sensitive to the input selection method than BiLSTM-AE. This study underscores the dependency of the prediction skill of AI algorithm-based models on the target air pollutant and input selection method, and suggests the trustworthiness of selected key operational variables by RF's feature importance.

ETMA: Efficient Transformer-Based Multilevel Attention Framework for Multimodal Fake News Detection

In this new digital era, social media has created a severe impact on the lives of people. In recent times, fake news content on social media has become one of the major challenging problems for society. The dissemination of fabricated and false news articles includes multimodal data in the form of text and images. The previous methods have mainly focused on unimodal analysis. Moreover, for multimodal analysis, researchers fail to keep the unique characteristics corresponding to each modality. This article aims to overcome these limitations by proposing an efficient transformer-based multilevel attention (ETMA) framework for multimodal fake news detection, which comprises the following components: a visual attention-based encoder, a textual attention-based encoder, and joint attention-based learning. Each component utilizes different forms of attention mechanisms and uniquely deals with multimodal data to detect fraudulent content. The efficacy of the proposed network is validated by conducting several experiments on four real-world fake news datasets: Twitter, Jruvika fake news dataset, Pontes fake news dataset, and Risdal fake news dataset using multiple evaluation metrics. The results show that the proposed method outperforms the baseline methods on all four datasets. Furthermore, the computation time of the model is also lower than the state-of-the-art methods.

Effects of different training methods in tele-exercise on acute performance decrement in adults with disability and wheelchair users

Purpose Wheelchair users and people with disabilities have limited access to physical exercise due to various factors, including medical follow-up and training facilities. Although tele-exercise guided by experts has become a viable option, there is limited knowledge about the acute performance decrement (APD) resulting from remote training methods. The current cross-sectional study aimed to: (1) assess the APD of muscle resistance strength after three synchronous tele-exercise training methods in wheelchair users and (2) compare the training loads associated with each training method. Materials and methods Eighteen male and female wheelchair users who participated in tele-exercise strength practices were recruited. The participants performed a maximum resistance strength test by synchronous tele-assessment (push-up test, PUT) at baseline and immediately after three training methods: high-intensity interval training (HIIT), moderate-intensity continuous training (MICT) and sprint interval training (SIT). The primary outcome was the APD, which was measured by the percentage decrease in the number of repetitions of the PUT immediately after the training methods. Results APD was observed for all three training methods, with no significant differences between them (–34.8%, −29.9% and −38.0% for MICT, SIT and HII, respectively), and presented a non-significant correlation with the training loads. HIIT had a significantly higher training load than MICT and SIT. Conclusions APD occurred in all training sessions, but did not correlate with training load, indicating that it is not an appropriate metric for comparison. Findings provide insight into APD response and highlight the need to consider multiple metrics when comparing training protocols.

RHDP: An Aspect Sharing-Enhanced Hierarchical Topic Model for Multi-Domain Corpus

Learning topic hierarchies from a multi-domain corpus is crucial in topic modeling as it reveals valuable structural information embedded within documents. Despite the extensive literature on hierarchical topic models, effectively discovering inter-topic correlations and differences among subtopics at the same level in the topic hierarchy, obtained from multiple domains, remains an unresolved challenge. This article proposes an enhanced nested Chinese restaurant process (nCRP), nCRP+, by introducing an additional mechanism based on Chinese restaurant franchise (CRF) for aspect-sharing pattern extraction in the original nCRP. Subsequently, by employing the distribution extracted from nCRP+ as the prior distribution for topic hierarchy in the hierarchical Dirichlet processes (HDP), we develop a hierarchical topic model for multi-domain corpus, named rHDP. We describe the model with the analogy of Chinese restaurant franchise based on the central kitchen and propose a hierarchical Gibbs sampling scheme to infer the model. Our method effectively constructs well-established topic hierarchies, accurately reflecting diverse parent-child topic relationships, explicit topic aspect sharing correlations for inter-topics, and differences between these shared topics. To validate the efficacy of our approach, we conduct experiments using a renowned public dataset and an online collection of Chinese financial documents. The experimental results confirm the superiority of our method over the state-of-the-art techniques in identifying multi-domain topic hierarchies, according to multiple evaluation metrics.