Training Time Research Articles

The Use of continuous action representations to scale deep reinforcement learning for inventory control

Abstract Deep reinforcement learning (DRL) can solve complex inventory problems with a multi-dimensional state space. However, most approaches use a discrete action representation and do not scale well to problems with multi-dimensional action spaces. We use DRL with a continuous action representation for inventory problems with a large (multi-dimensional) discrete action space. To obtain feasible discrete actions from a continuous action representation, we add a tailored mapping function to the policy network that maps the continuous outputs of the policy network to a feasible integer solution. We demonstrate our approach to multi-product inventory control. We show how a continuous action representation solves larger problem instances and requires much less training time than a discrete action representation. Moreover, we show its performance matches state-of-the-art heuristic replenishment policies. This promising research avenue might pave the way for applying DRL in inventory control at scale and in practice.

Deep Learning for Urban Tree Canopy Coverage Analysis: A Comparison and Case Study

Urban tree canopy (UTC) coverage, or area, is an important metric for monitoring changes in UTC over large areas within a municipality. Several methods have been used to obtain these data, but remote sensing image classification is one of the fastest and most reliable over large areas. However, most studies have tested only one or two classification methods to accomplish this while using costly satellite imagery or LiDAR data. This study seeks to compare three urban tree canopy cover classifiers by testing a deep learning U-Net convolutional neural network (CNN), support vector machine learning classifier (SVM) and a random forests machine learning classifier (RF) on cost-free 2012 aerial imagery over a small southern USA city and midsize, growing southern USA city. The results of the experiment are then used to decide the best classifier and apply it to more recent aerial imagery to determine canopy changes over a 10-year period. The changes are subsequently compared visually and statistically with recent urban heat maps derived from thermal Landsat 9 satellite data to compare the means of temperatures within areas of UTC loss and no change. The U-Net CNN classifier proved to provide the best overall accuracy for both cities (89.8% and 91.4%), while also requiring the most training and classification time. When compared spatially with city heat maps, city periphery regions were most impacted by substantial changes in UTC area as cities grow and the outer regions get warmer. Furthermore, areas of UTC loss had higher temperatures than those areas with no canopy change. The broader impacts of this study reach the urban forestry managers at the local, state/province, and national levels as they seek to provide data-driven decisions for policy makers.

Effects of time-of-day resistance training on muscle strength, hormonal adaptations, and sleep quality during Ramadan fasting

ObjectivesWe investigated the timing of resistance training (RT) during Ramadan fasting (RF) on muscle strength, hormonal adaptations, and sleep quality.MethodsForty healthy and physically active male Muslims (age = 25.7 ± 5.6 years, body mass = 85.1 ± 17.5 kg, height = 175 ± 9 cm, BMI = 28.3 ± 5.7 kg/m2) were enrolled in this study and 37 completed pre and post-tests. Subjects were randomly allocated into two experimental groups. Group 1 (FAST, n = 20) completed an 8-week whole-body RT in the late afternoon (between 16 h and 18 h) while fasting. Group 2 (FED, n = 20) completed the similar RT protocol compared with FAST at night (between 20 h and 22 h). The following parameters were analyzed at various time-points: 2 weeks before the start of RF (T0), on the 15th day of Ramadan (T1), on the 29th day of Ramadan (T2), and 21 days after the last day of RF (T3) where both groups were in a fed state. One-repetition maximum tests (1-RM) were conducted for the squats (1-RMSQ), the deadlift (1-RMDL) and the bench press (1-RMBP). Sleep quality was assessed using the full Pittsburgh Sleep Quality Index (PSQI). Blood samples were taken to determine cortisol, testosterone and IGF-1 levels. Additionally, acute hormonal responses were evaluated before (BF), immediately after (AF), and 30 min after a RT session (AF-30 min) at T0, T1, T2, and T3.ResultsSignificant group-by-time interactions were identified for 1-RMSQ (p = 0.001; effect size [ES] = 0.43) and 1-RMDL (p = 0.001; ES = 0.36). Post-hoc tests indicated significant 1-RMSQ (p = 0.03; ES = 0.12) and 1-RMDL (p = 0.04; ES = 0.21) improvements from T0-T2 for FED. Additionally, significant group-by-time interactions were observed for the chronic effects on cortisol (p = 0.03; ES = 0.27) and testosterone levels (p = 0.01; ES = 0.32). Post-hoc tests indicated significant increases of cortisol levels among FAST at T1 and T2 compared to T0 (p = 0.05; ES = 0.41, p = 0.03; ES = 0.34) and a significant increase in cortisol levels in FED at T1 (p = 0.05; ES = 0.29) and T2 (p = 0.04; ES = 0.25). However, the observed increase was lower compared to FAST. Post-hoc tests also indicated significant increases of testosterone only among FED at T2 (p = 0.04; ES = 0.31). A significant group-by-time interaction was found for the acute effect of exercise on cortisol level (p = 0.04; ES = 0.34). The cortisol level immediately after RT was higher in FAST only at T1 (p = 0.03; ES = 0.39) and T2 (p = 0.05; ES = 0.22) compared with T0. No significant group-by-time interactions were identified for sleep quality (p = 0.07; ES = 0.43).ConclusionMuslims can safely practice RT during RF. However, training in a fed state during Ramadan might be more effective than during fasted state for the enhancement of maximal strength with better hormonal responses observed.

Strength Training Among Male Master Cyclists—Practices, Challenges, and Rationales

Background: Cycling performance declines with age due to reduced aerobic capacity, along with reductions in muscle mass and bone density. Strength training can help counter these effects. This study aims to explore the strength training practices, challenges, and decision-making rationale of male master cyclists to optimize performance and health as they age. Methods: A total of 555 male master cyclists aged 35 and above completed an online questionnaire, distributed via social media platforms, that included Likert-type, single- and multiple-selection, and open-ended questions. Participants were then divided into two age groups: 35–49 years (n = 359) and ≥50 years (n = 196). Analyses involved descriptive statistics, Wilcoxon signed-rank tests, Mann–Whitney U-tests, and chi-square tests, with qualitative data analyzed using content analysis. Results: More cyclists engaged in strength training during the off-/pre-season, with a significant reduction in both frequency and the number of cyclists engaging in strength training during the race season. The strength training practice was focused mainly on core and lower body, employing hypertrophy and maximal strength training methods. Key challenges included fatigue induced by strength training and limited time to perform strength training. The main rationale for the strength training revolved around improving cycling performance, reducing injury risk, and the health benefits of strength training. Both age categories, but the older group in particular, reported bone health as a primary rationale for strength training. Conclusions: While strength training offers performance and health benefits, issues of fatigue and time constraints remain substantial, suggesting the need for tailored training programs to improve adherence and effectiveness.

DecTree: a physics-based geochemical surrogate for surface complexation of uranium on clay

Abstract. Geochemistry is usually the computational bottleneck in coupled reactive transport simulations, which hampers the complexity of the systems and of the processes they can investigate. In recent years, promising speedups have been obtained by substituting the numerical solution of geochemical models with approximated surrogates borrowed from artificial intelligence and machine learning (AI/ML). In the framework of the DONUT/EURAD project a set of benchmarks were defined to assess the performance and the accuracy of different surrogate approaches in settings relevant to the safety assessment of nuclear waste repositories, such as the surface complexation and exchange of U(VI) on clay. In this context, this work introduces am original surrogate modelling approach based on recursive partitioning of parameter space, which exploits prior domain knowledge for the training. The surrogate, which can be represented as a decision tree, hence the DecTree name, performs dimensionality reduction by identifying functional relationships between outputs and input variables using a straightforward non-monotonic extension of the Spearman's rank correlation coefficient. New predictions are then interpolated from the partitioned training data. Applied to a low-dimensional geochemical model, DecTree shows virtually no training time and excellent accuracy, ensuring a throughput of around 500 000 predictions per second on a single CPU core.

Water Supply Pipeline Failure Evaluation Model Based on Particle Swarm Optimization Neural Network

The degradation and failure of the urban water supply network may lead to serious safety hazards, including pipe breaks, water supply interruptions, water resource losses, and contaminant intrusions. The risk evaluation of water supply pipeline failure in a distribution network is a challenging task, because most of the available data cannot fully reflect pipeline failure events and many of the mechanisms still cannot be fully understood. Therefore, a predictive model is urgently needed to assess pipeline failure risk based on available data. In this paper, based on the traditional risk assessment theory, seven main factors affecting pipeline failure are selected and scored, and then a pipeline failure model is established by using the particle swarm optimization (PSO) neural network. The model uses the neural network training of historical data to evaluate the failure of the water supply pipeline, and the PSO is used to optimize the neural network to effectively improve the training time and accuracy. The model error and correlation coefficient are 0.003 and 0.987, respectively. The proposed model can be used as a powerful support tool to assist infrastructure managers and pipeline maintainers in their plans and decision-making.

Efficient Cross-Domain Fault Diagnosis via Distributed Multi-Source Domain Deep Transfer Learning

Abstract In the actual industrial production, the working conditions of rotating machinery are complex and changeable, and the health-state monitoring data are increasingly large and difficult to be labeled, which will seriously restrict the accuracy and efficiency of cross-domain fault diagnosis (CDFD) of rotating machinery. Therefore, an efficient multi-source domain deep transfer learning (MDDTL) method for CDFD of rotating machinery is proposed. Firstly, a MDDTL model is constructed to improve the accuracy of CDFD. In the model, a dual-phase domain alignment strategy is designed, which considers the alignment of feature distributions between each source and target domain pair in the feature space and that of prediction probabilities between domain-specific fault classifiers in the output space. The fault prediction results from multiple different fault classifiers are merged dynamically by the proposed imbalanced adaptive prediction strategy. Secondly, a data-parallel distributed training scheme for MDDTL model is proposed. Based on the idea of data parallelism, the distributed parallel training of MDDTL model is performed with Horovod-GPU platform, and the parameters are synchronously updated with the bandwidth-optimal Ring-AllReduce architecture. Under the premise of ensuring the accuracy of fault diagnosis (FD), the training time of MDDTL model is significantly reduced. Finally, extensive experiments are conducted to verify the effectiveness of the proposed MDDTL method. The results demonstrate that the proposed method not only effectively improves the accuracy of CDFD of rotating machinery, but also significantly improves the training efficiency of MDDTL model. After adopting the proposed method, the diagnosis accuracies achieved under two different cross-working condition scenarios reach 97.09% and 97.87% respectively, and the model training time is reduced by 73.62% when facing a large-scale rotating machinery training set.

SSFAN: A Compact and Efficient Spectral-Spatial Feature Extraction and Attention-Based Neural Network for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is a crucial technique that assigns each pixel in an image to a specific land cover category by leveraging both spectral and spatial information. In recent years, HSI classification methods based on convolutional neural networks (CNNs) and Transformers have significantly improved performance due to their strong feature extraction capabilities. However, these improvements often come with increased model complexity, leading to higher computational costs. To address this, we propose a compact and efficient spectral-spatial feature extraction and attention-based neural network (SSFAN) for HSI classification. The SSFAN model consists of three core modules: the Parallel Spectral-Spatial Feature Extraction Block (PSSB), the Scan Block, and the Squeeze-and-Excitation MLP Block (SEMB). After preprocessing the HSI data, it is fed into the PSSB module, which contains two parallel streams, each comprising a 3D convolutional layer and a 2D convolutional layer. The 3D convolutional layer extracts spectral and spatial features from the input hyperspectral data, while the 2D convolutional layer further enhances the spatial feature representation. Next, the Scan Block module employs a layered scanning strategy to extract spatial information at different scales from the central pixel outward, enabling the model to capture both local and global spatial relationships. The SEMB module combines the Spectral-Spatial Recurrent Block (SSRB) and the MLP Block. The SSRB, with its adaptive weight assignment mechanism in the SToken Module, flexibly handles time steps and feature dimensions, performing deep spectral and spatial feature extraction through multiple state updates. Finally, the MLP Block processes the input features through a series of linear transformations, GELU activation functions, and Dropout layers, capturing complex patterns and relationships within the data, and concludes with an argmax layer for classification. Experimental results show that the proposed SSFAN model delivers superior classification performance, outperforming the second-best method by 1.72%, 5.19%, and 1.94% in OA, AA, and Kappa coefficient, respectively, on the Indian Pines dataset. Additionally, it requires less training and testing time compared to other state-of-the-art deep learning methods.

Resource Allocation in UAV-D2D Networks: A Scalable Heterogeneous Multi-Agent Deep Reinforcement Learning Approach

In unmanned aerial vehicle (UAV)-assisted device-to-device (D2D) caching networks, the uncertainty from unpredictable content demands and variable user positions poses a significant challenge for traditional optimization methods, often making them impractical. Multi-agent deep reinforcement learning (MADRL) offers significant advantages in optimizing multi-agent system decisions and serves as an effective and practical alternative. However, its application in large-scale dynamic environments is severely limited by the curse of dimensionality and communication overhead. To resolve this problem, we develop a scalable heterogeneous multi-agent mean-field actor-critic (SH-MAMFAC) framework. The framework treats ground users (GUs) and UAVs as distinct agents and designs cooperative rewards to convert the resource allocation problem into a fully cooperative game, enhancing global network performance. We also implement a mixed-action mapping strategy to handle discrete and continuous action spaces. A mean-field MADRL framework is introduced to minimize individual agent training loads while enhancing total cache hit probability (CHP). The simulation results show that our algorithm improves CHP and reduces transmission delay. A comparative analysis with existing mainstream deep reinforcement learning (DRL) algorithms shows that SH-MAMFAC significantly reduces training time and maintains high CHP as GU count grows. Additionally, by comparing with SH-MAMFAC variants that do not include trajectory optimization or power control, the proposed joint design scheme significantly reduces transmission delay.

Replay-Based Incremental Learning Framework for Gesture Recognition Overcoming the Time-Varying Characteristics of sEMG Signals

Gesture recognition techniques based on surface electromyography (sEMG) signals face instability problems caused by electrode displacement and the time-varying characteristics of the signals in cross-time applications. This study proposes an incremental learning framework based on densely connected convolutional networks (DenseNet) to capture non-synchronous data features and overcome catastrophic forgetting by constructing replay datasets that store data with different time spans and jointly participate in model training. The results show that, after multiple increments, the framework achieves an average recognition rate of 96.5% from eight subjects, which is significantly better than that of cross-day analysis. The density-based spatial clustering of applications with noise (DBSCAN) algorithm is utilized to select representative samples to update the replayed dataset, achieving a 93.7% recognition rate with fewer samples, which is better than the other three conventional sample selection methods. In addition, a comparison of full dataset training with incremental learning training demonstrates that the framework improves the recognition rate by nearly 1%, exhibits better recognition performance, significantly shortens the training time, reduces the cost of model updating and iteration, and is more suitable for practical applications. This study also investigates the use of the incremental learning of action classes, achieving an average recognition rate of 88.6%, which facilitates the supplementation of action types according to the demand, and further improves the application value of the action pattern recognition technology based on sEMG signals.

A GRAPH CONVOLUTIONAL NETWORK APPROACH FOR PREDICTING NETWORK ROBUSTNESS

Network robustness, which includes controllability robustness and connectivity robustness, reflects the ability of a network system to withstand attacks. In this paper, a Graph Convolutional Network (GCN) approach is proposed for predicting network robustness. In contrast to the existing Convolutional Neural Network (CNN) approach, the network topology and the node characteristics are directly used as GCN input without being converted into a grayscale image. Due to the reduction in the number of feature maps, the model size of a GCN is greatly reduced to only 1% of a CNN. Extensive experimental studies on four representative networks and six real networks have proven that the proposed approach can achieve better predictive performance with less training and running time.

Implementation of Parallel Optimization Algorithms for NLP: Mini-batch SGD, SGD with Momentum, AdaGrad Adam

Abstract. With the rapid development of machine learning technology, optimization algorithms and optimizers have become key to the development of related technologies contemporarily. Models need the help of optimizers to meet other performance indicators while saving computing resources. This research focuses on comparisons between optimizers, in the context of text sentiment classification tasks. The optimizers mainly compared in this article are mini batch SGD, momentum SGD, Adagrad and Adam. Through comparative experiments, it was found that SGD and its variants have a high dependence on the initial learning rate setting, while the performance of Adagrad and Adam is relatively balanced. Although the training time of Adagrad is shorter than that of Adam, its principal formula has flaws, which are not reflected in this task. The conclusions drawn in this article through comparison can point out the advantages and disadvantages of each optimizer, and can help realize better optimizers in subsequent research.

Analysis of the Hyperparameter Selection in Machine Learning

Abstract. A Machine learning is now playing a role in various fields. With the development of the internet, the volume of data is increasing, and the algorithms of machine learning are becoming more complex. Adjusting hyperparameters is a challenge for beginners who are new to machine learning. This research implemented a simple neural network model through code. Moreover, this study has changed some of the most basic parameters of the model and trained different models. This study has used visualization methods to show how the model training time and performance change with the alteration of hyperparameters, and derived their respective accuracy rates. This article provides entry-level data and code for newcomers to the field of machine learning. Since this experiment uses a federated learning model, employs local_update SGD, and also utilizes parallel methods, it is quite comprehensive, covering many algorithm codes for machine learning beginners. Testing the basic parameters of the model can help newcomers to machine learning understand more clearly the impact of hyperparameters on the model. It also aids in the development of more algorithms for adjusting hyperparameters.

Model of Dynamic Mechanical Parameters and Vibration Analysis in Hot Rolling

As the core equipment of metal shaping processing, the vibration problem of rolling mill seriously affects the product quality and production efficiency. To address the problem of the limited prediction of mill vibration due to small sample data in non-steady states, we propose to predict dynamic mechanical parameters (rolling force and rolling torque) based on the TCN-LSTM step strategy transfer model. The prediction accuracies of the TCN-LSTM step strategy transfer model under 1000 sets of training data reach 95.8% and 93.2%, respectively, and at the same time, it saves the time of training and regulation of the deep learning model and can better meet the needs of online prediction. The horizontal-torsion hot rolling vibration model is further established to quantitatively analyze the relationship between process parameters and mill vibration. The experimental results show that with the vibration suppression measures of 10% reduction of the rolling speed and 10% reduction of the entrance thickness, the horizontal vibration displacement amplitude is reduced from 0.687 × 10−4 m to 0.229 × 10−4 m, and the rotational displacement amplitude is reduced from 0.0273 m to 0.0117 m, which effectively suppresses the vibration of the mill and improves the stability of the rolling process.

Non-small cell lung cancer detection through knowledge distillation approach with teaching assistant.

Non-small cell lung cancer (NSCLC) exhibits a comparatively slower rate of metastasis in contrast to small cell lung cancer, contributing to approximately 85% of the global patient population. In this work, leveraging CT scan images, we deploy a knowledge distillation technique within teaching assistant (TA) and student frameworks for NSCLC classification. We employed various deep learning models, CNN, VGG19, ResNet152v2, Swin, CCT, and ViT, and assigned roles as teacher, teaching assistant and student. Evaluation underscores exceptional model performance in performance metrics achieved via cost-sensitive learning and precise hyperparameter (alpha and temperature) fine-tuning, highlighting the model's efficiency in lung cancer tumor prediction and classification. The applied TA (ResNet152) and student (CNN) models achieved 90.99% and 94.53% test accuracies, respectively, with optimal hyperparameters (alpha = 0.7 and temperature = 7). The implementation of the TA framework improves the overall performance of the student model. After obtaining Shapley values, explainable AI is applied with a partition explainer to check each class's contribution, further enhancing the transparency of the implemented deep learning techniques. Finally, a web application designed to make it user-friendly and classify lung types in recently captured images. The execution of the three-stage knowledge distillation technique proved efficient with significantly reduced trainable parameters and training time applicable for memory-constrained edge devices.

Research on motion control strategy of athlete muscle training based on blockchain and visual image analysis

Muscle training is an important part of athletes’ physical training. Its goal is to keep athletes in high intensity and improve sports performance in physical training. With the continuous improvement of the level of competitive sports, there are still many problems in the training of competitive athletes. The research on the control strategies of some technical movements in the process of athletes’ muscle development would help to improve the efficiency and effect of athletes’ training. By analyzing and quant description of muscle movement control process based on blockchain and visual image processing technology, the muscle movement control rule is discussed and then a complete movement database is constructed. At the same time, combined with the sports experiment method and cognitive behavioral theory, this paper analyzed the exercise load, exercise time allocation, muscle training time allocation methods and the corresponding muscle training strategy selection methods under different muscle states, providing theoretical basis for athletes to conduct muscle strength training scientifically and efficiently. This paper first analyzed the importance of athletes’ muscle training action control. After that, the research was mainly carried out from the following two aspects. The first is to analyze the motion control strategy of athlete muscle training based on blockchain and visual image, and summarize its characteristics. The second is to use electronic imaging technology to analyze the data related to posture control in athletes’ muscle training, and explore the characteristics and changes of muscle posture. At last, this paper put forward relevant algorithms about visual images and conducted experimental research on athletes’ physical indicators and performance under different muscle training according to the research in this paper. It was concluded that the score ratio of athletes’ performance after muscle training action control was 7.39% higher than that of general muscle training. Therefore, it is very important to strengthen the research of movement technology in muscle training and analyze the influence of some training control strategies on the development of athletes’ muscles in training.

ConvLSTM-based spatiotemporal and temporal processing models for chaotic vibration prediction of a microbeam

The current work proposes a hybrid data-driven model, consisting of convolutional neural networks (CNN) and convolutional long short-term memory (ConvLSTM), to enable an innovative application in prediction for microbeam's chaotic vibrations. In the proposed CNNConvLSTM model, CNN is used as feature extractor while ConvLSTM retains long-term connectivity across the entire sequence of frames. The flexibility and effectiveness of the model are demonstrated by its capability to perform both spatiotemporal and temporal processing. Specifically, the spatiotemporal model predicts the chaotic vibrations at 19 selected locations within the microbeam at a specific instant, while the temporal model predicts the microbeam's chaotic vibrations at a fixed location over time. Additionally, two conventional spatiotemporal models and three conventional temporal models are built for comparison, demonstrating the superior performance of CNNConvLSTM in terms of shorter training time and lower training and testing loss. The CNNConvLSTM model can provide useful guidance when investigating chaotic vibrations for performance enhancement and design optimization of microbeam-related devices.

Interpersonal neural synchronization in frontal-temporal regions as new neurophysiological index of interpretation quality: an fNIRS hyperscanning study

ABSTRACT The evaluation of interpretation quality is fundamental to interpreting development. Previous interpretation evaluation studies focused solely on the interpretation itself, overlooking the interlocutors as recipients of the interpretation. We propose a novel approach by evaluating interpretation through mutual understanding between interlocutors. Using fNIRS hyperscanning, we examined neural activities of 20 interlocutor dyads communicating in Chinese-English context with interpreters. Results showed greater interpersonal neural synchronization (INS) in frontal-temporal regions during communication. Notably, INS in the left middle temporal gyrus (MTG) positively related to communication quality. Interpretation scores positively predicted INS in the left MTG, while mental load negatively predicted INS in the left inferior frontal gyrus, suggesting that INS in speech comprehension areas signifies interpretation quality at a semantic level. Moreover, the positive correlation between interpretation training time and INS in the left dorsolateral prefrontal cortex indicates that INS in mentalizing area reflects interpretation quality at a more advanced level.

Multilevel attention mechanism for motion fatigue recognition based on sEMG and ACC signal fusion.

This study aims to develop a cost-effective and reliable motion monitoring device capable of comprehensive fatigue analysis. It achieves this objective by integrating surface electromyography (sEMG) and accelerometer (ACC) signals through a feature fusion strategy. The study introduces a multi-level attention mechanism for classification, leveraging convolutional neural networks (CNNs). The preprocessing phase involves a local feature attention mechanism that enhances local waveform features using the amplitude envelope. A dual-scale attention mechanism, operating at both channel and neuron levels, is employed to enhance the model's learning from high-dimensional fused data, improving feature extraction and generalization. The local feature attention mechanism significantly improves the model's classification accuracy and convergence, as demonstrated in ablation experiments. The model, optimized with multi-level attention mechanisms, excels in accuracy and generalization, particularly in handling data with pseudo-artifacts. Computational analysis indicates that the proposed optimization algorithm has minimal impact on CNN's training and testing times. The study achieves recognition accuracies of 92.52%, 92.38%, and 92.30%, as well as F1-scores of 91.92%, 92.13%, and 92.29% for the three fatigue states, affirming its reliability. This research provides technical support for the development of affordable and dependable wearable motion monitoring devices.

Preventing Allogeneic Stem Cell Transplant-Related Cardiovascular Dysfunction: ALLO-Active Trial.

Allogeneic stem cell transplantation (allo-SCT) is an efficacious treatment for hematologic malignancies but can be complicated by cardiac dysfunction and exercise intolerance impacting quality of life and longevity. We conducted a randomized controlled trial testing whether a multicomponent activity intervention could attenuate reductions in cardiorespiratory fitness and exercise cardiac function (co-primary end points) in adults undergoing allo-SCT. Sixty-two adults scheduled for allo-SCT were randomized to a 4-month activity program (n=30) or usual care (UC; n=32). Activity comprised multicomponent exercise training (3 days/week) and sedentary time reduction (≥30 min/day) program and was delivered throughout hospitalization (≈4 weeks) and for 12 weeks after discharge. Physiological assessments conducted before admission and at 12 weeks after discharge included cardiopulmonary exercise testing to quantify peak oxygen uptake ([Formula: see text]), exercise cardiac magnetic resonance imaging for peak cardiac volume (CIpeak) and stroke volume (SVIpeak) index, echocardiography-derived left ventricular ejection fraction and global longitudinal strain, and cardiac biomarkers (cTn-I [troponin-I] and BNP [B-type natriuretic peptide]). Fifty-two participants (84%) completed follow-up (25 activity and 27 UC); median (interquartile range [IQR]) adherence to the activity program was 74% (41-96%). There was a marked decline in [Formula: see text] in the UC program (-3.4 mL‧kg-1‧min-1 [95% CI, -4.9 to -1.8]) that was attenuated with activity (-0.9 mL‧kg-1‧min-1 [95% CI, -2.5 to 0.8]; interaction P=0.029). Activity preserved exercise cardiac function, with preservation of CIpeak (0.30 L‧min-1‧m-2 [95% CI, -0.34 to 0.41]) and SVIpeak (0.6 mL/m2 [95% CI, -1.3 to 2.5]), both of which declined with UC (CIpeak, -0.68 L‧min-1‧m-2 [95% CI, -1.3 to -0.32]; interaction P=0.008; SVIpeak, -2.7 mL/m2 [95% CI, -4.6 to -0.9]; interaction P=0.014). There were no treatment effects of activity on cardiac biomarkers or echocardiographic indices. Multicomponent activity intervention during and after allo-SCT is beneficial for preserving patient cardiorespiratory fitness and exercise cardiac function. These results may have important implications for cardiovascular morbidity and mortality after allo-SCT. URL: https://anzctr.org.au/; Unique identifier: ACTRN12619000741189.