Dynamic Environment Research Articles

Flexible Training and Uploading Strategy for Asynchronous Federated Learning in Dynamic Environments

Flexible Training and Uploading Strategy for Asynchronous Federated Learning in Dynamic Environments

Application of supervised and unsupervised learning for enhancing energy efficiency and thermal comfort in air conditioning scheduling under uncertain and dynamic environments

Air conditioning (AC) plays a major role in building energy management because it generally requires a large amount of energy to maintain indoor thermal comfort. The main objective of this study is to develop a novel method for scheduling AC operations to minimize energy costs and ensure the thermal comfort of occupants under uncertainty. The key challenge is the uncertainty and variability in time-series data and their serial dependence in determining AC operation. To address this challenge, we propose an optimization-informed learning approach that integrates unsupervised and supervised learning techniques with a stochastic optimization model. This method derives energy-efficient and thermal comfort-aware AC operation schedules through a comprehensive interpretation of uncertainties and variabilities in time-series data. Numerical experimental results demonstrate that the proposed approach can reduce energy costs by up to 15.6% and decrease thermal comfort violations by up to 63.6% compared to the Deep Q-learning method, while also reducing energy costs by 1.8% and decreasing thermal comfort violations by 37.5% compared to the forecast data-driven AC scheduling method.

Decentralized Coordination for Multi-Agent Data Collection in Dynamic Environments

Decentralized Coordination for Multi-Agent Data Collection in Dynamic Environments

Payoff-driven migration promotes the evolution of trust in networked populations

Establishing and maintaining trustworthy behaviors in large populations of self-interested individuals is a significant problem which received extensive attentions from research fields such as evolutionary biology, economics, sociology and engineering. As a well-known model that captures social trust dilemmas, the N-player trust game is adopted to investigate the evolution of trust in groups consisting of investors and trustees. In addition, to model real scenarios in dynamic environments, we introduce a novel migration mechanism, called adaptive environment-benefit-driven migration, which considers the influence of individuals’ payoffs on migration. Through theoretical analysis and Monte Carlo simulations, we demonstrate the effectiveness of the migration mechanism on facilitating trust behaviors in the framework of evolutionary game theory. We find that the population density plays a crucial role in establishing trust. Simulation results reveal that trust can be fostered in a dynamic environment influenced by individual migration with the medium vacancy rate. This work significantly contributes to the understanding of mutual trust behaviors in networked social systems from a more realistic perspective.

Deep reinforcement learning for autonomous SideLink radio resource management in platoon-based C-V2X networks: An overview

Dynamic and autonomous SideLink (SL) Radio Resource Management (RRM) is essential for platoon-based cellular vehicular networks. However, this task is challenging due to several factors. These include the limited spectrum below 6 GHz, stringent vehicle-to-everything (V2X) communications requirements, uncertain and dynamic environments, limited vehicle sensing capabilities, and inherent distributed operation. These limitations often lead to resource collisions, data packet loss, and increased latency. Current standardized approaches in Long-Term Evolution-V2X (LTE-V2X) and New Radio-V2X (NR-V2X) rely on random resource selection, limiting their efficiency. Moreover, RRM is inherently a complex combinatorial optimization problem. It may involve conflicting objectives and constraints, making traditional approaches inadequate. Platoon-based communication necessitates careful resource allocation to support a diverse mix of communication types. These include safety-critical control messaging within platoons, less time-sensitive traffic management information between platoons, and even infotainment services like media streaming. Optimizing resource sharing inter- and intra- platoons is crucial to avoid excessive interference and ensure overall network performance. Deep Reinforcement Learning (DRL), combining Deep Learning (DL) and Reinforcement Learning (RL), has recently been investigated for network resource management. It offers a potential solution for these challenges. A DRL agent, represented by deep neural networks, interacts with the environment and learns optimal decision-making through trial and error. This paper overviews proposed DRL-based methods for autonomous SL RRM in single and multi-agent platoon-based C-V2X networks. It considers both intra- and inter-platoon communications with their specific requirements. We discuss the components of Markov Decision Processes (MDP) used to model the sequential decision-making of RRM. We then detail the DRL algorithms, training paradigms, and insights on the achieved results. Finally, we highlight challenges in existing works and suggest strategies for addressing them.

Fuzzy logic assessment of X-ray tube risks in robotic C-arm angiography: a failure mode and effect analysis study

This research examines the integration of robotic C-arm technology in angiography, a critical tool for treating cardiac conditions. The robotic C-arm, which includes an X-ray tube, is essential for scanning patients during procedures. The study also investigates the associated risks, specifically in Indonesian hospitals with cardiac facilities. Angiography is used to diagnose and treat heart disease by visualizing blood vessels and facilitating catheterization procedures. However, its mobility poses hazards and can impact the process. To address potential risks, failure mode and effect analysis (FMEA) is utilized. Traditionally, risk assessment using risk priority numbers (RPN) is conducted, but these may not accurately reflect failures due to complex evaluating processes. To overcome this limitation, fuzzy logic is employed, enhancing risk assessment accuracy. Through this approach, twenty-seven failure modes are identified across two brands, with ten major ones prioritized using fuzzy logic. These findings facilitate the development of preventive measures to mitigate future failures and enhance patient safety during angiography in hospitals. In conclusion, the study underscores the importance of robust risk management in medical equipment, particularly in dynamic environments. By integrating fuzzy logic into risk assessment, the study improves prioritization accuracy, enabling effective allocation of resources for preventive actions.

Multi-agent reinforcement learning with synchronized and decomposed reward automaton synthesized from reactive temporal logic

Multi-agent systems (MAS) consist of multiple autonomous agents interacting to achieve collective objectives. Multi-agent reinforcement learning (MARL) enhances these systems by enabling agents to learn optimal behaviors through interaction, thus improving their coordination in dynamic environments. However, MARL faces significant challenges in adapting to complex dependencies on past states and actions, which are not adequately represented by the current state alone in reactive systems. This paper addresses these challenges by considering MAS operating under task specifications formulated as Generalized Reactivity of rank 1 (GR(1)). These synthesized strategies are used as a priori knowledge to guide the learning. To tackle the difficulties of handling non-Markovian tasks in reactive systems, we propose a novel synchronized decentralized training paradigm that guides agents to learn within the MARL framework using a reward structure constructed from decomposed synthesized strategies of GR(1). We initially formalize the synthesis of GR(1) strategies as a reachability problem of winning states of the system. Subsequently, we develop a decomposition mechanism that constructs individual reward structures for decentralized MARL, incorporating potential values calculated through value iteration. Theoretical proofs are provided to verify that the safety and liveness properties are preserved. We evaluate our approach against other state-of-the-art methods under various GR(1) specifications and scenario maps, demonstrating superior learning efficacy and optimal rewards per episode. Additionally, we show that the decentralized training paradigm outperforms the centralized training paradigm. The value iteration strategy used to calculate potential values for the reward structure is compared against two other strategies, showcasing its advantages.

A Novel Approach to Node Coverage Enhancement in Wireless Sensor Networks Using Walrus Optimization Algorithm

Wireless Sensor Networks (WSNs) are crucial components of modern technology, supporting applications like healthcare, industrial automation, and environmental monitoring. This research aims to design intelligent and adaptive sensor networks by integrating metaheuristics with node coverage optimization in WSNs. By incorporating metaheuristics and optimizing node coverage, WSNs can become more resilient and robust, leading to the development of self-adapting, self-organizing networks capable of efficiently covering dynamic and diverse environments. This research introduces the Walrus Optimization Algorithm for Node Coverage Enhancement in WSNs, called the WaOA-NCEWSN technique. The primary goal of this technique is to optimize the coverage of a target region using a limited number of Sensor Nodes (SNs) and by improving their placement. The WaOA is inspired by walrus behaviours like feeding, migrating, breeding, escaping, roosting, and gathering in response to environmental signals. The WaOA-NCEWSN technique uses an objective function that defines the coverage ratio, representing the maximum probability of coverage in a 2D-WSN monitoring area. Comparative analysis with other models using 50, 75, 100, and 200 nodes shows that the WaOA-NCEWSN technique performs better. The compilation times for the WaOA-NCEWSN technique are 5.14s, 6.48s, 6.54s, and 7.47s for 50, 75, 100, and 200 nodes, respectively. Experimental results indicate that the WaOA-NCEWSN technique offers superior coverage performance compared to other models.

Robust and energy-efficient RPL optimization algorithm with scalable deep reinforcement learning for IIoT

The increasing complexity and quantity of the Industrial Internet of Things (IIoT) pose new challenges to the traditional routing protocol for low-power and lossy networks (RPL) in terms of dynamic management, data transmission reliability, and energy efficiency optimization. This paper proposes a scalable deep reinforcement learning (DRL) algorithm with a multi-attention actor double critic model for routing optimization (MADC) to meet the requirements of IIoT for efficient and intelligent routing decisions while improving data transmission reliability and energy efficiency. Specifically, MADC employs the centralized training and decentralized execution (CTDE) learning paradigm to decouple the model’s training and inference tasks, which reduces the difficulty and computational cost of model learning and improves the training efficiency. In addition, a lightweight actor network based on multi-scale convolutional attention mechanism is designed in MADC, which can provide intelligent and real-time decision-making capabilities for resource-constrained nodes with low computational and storage complexities. Moreover, a scalable critic network utilizing multiple attention mechanisms is proposed. It is not only suitable for dynamic and changing network environments but also can more comprehensively and accurately evaluate local observation states, providing more accurate and efficient guidance for model optimization. Furthermore, MADC incorporates a double critic network architecture to mitigate potential overestimation issues during training, thereby ensuring the model’s robustness and reliability. Simulation results demonstrate that MADC outperforms existing RPL optimization algorithms in terms of energy efficiency, data transmission reliability, and adaptability.

Simultaneous nitrification and denitrification framework for decentralized systems: Long-term study utilizing rope-type biofilm media under field conditions

This research introduces a novel approach to achieve simultaneous nitrification-denitrification (SND) under dynamic load conditions using a cost-effective rope-type biofilm technology. The approach represents a significant advancement in wastewater treatment, particularly beneficial for remote and decentralized communities. The biofilm-based SND process was developed using a pilot-scale flow-through reactor by implementing upstream carbon management with constant-timer-based aeration control versus dynamic-sensor-based aeration control strategies. The findings indicate that adding an upstream anaerobic pretreatment process to handle excess carbon plays a substantial role in achieving a sustainable SND process under a dynamic load environment using simple aeration on-off control. The most optimal nitrification performance of 0.32 g NH3-N/m2/d (89 % removal) was achieved under a 1-hour ON/30-minute OFF aeration. The process sustained an average bulk liquid DO of 5.16 mg/L and 3.80 mg/L during the aeration ON and OFF periods, respectively, facilitating a 0.13 g N/m2/d (41 %) total inorganic nitrogen (TIN) removal, notably, implementing advanced aeration strategies driven by DO, NH3, and NO3 sensors enhanced TIN removal efficiency to 72 %. The nitrification performance remained comparable (89 % removal), resulting in 3 and 10 mg N/L effluent ammonia and TIN concentration, respectively. Additionally, utilizing two multivariate approaches accounting for 82 % and 64 % of the variance, this study discerned patterns in monitored variables and performance. Additionally, the analysis underscored the difference of bulk liquid DO levels in the biofilm versus suspended systems inhibiting the SND process. Distinct bacterial communities were established in biofilms under aerobic, anaerobic, and SND conditions, with the SND reactor showing a hierarchy of functional group and enzymes, enriched sequentially from heterotrophs to denitrifiers, nitrifiers, and anammox bacteria. These innovations underline the potential of tailored control strategies to enhance a passive biofilm-based SND process efficiency under dynamic conditions, providing scalable solutions for diverse target water quality demands in remote communities and decentralized systems.

Dynamic 3D Point Cloud Sequences as 2D Videos.

Dynamic 3D point cloud sequences serve as one of the most common and practical representation modalities of dynamic real-world environments. However, their unstructured nature in both spatial and temporal domains poses significant challenges to effective and efficient processing. Existing deep point cloud sequence modeling approaches imitate the mature 2D video learning mechanisms by developing complex spatio-temporal point neighbor grouping and feature aggregation schemes, often resulting in methods lacking effectiveness, efficiency, and expressive power. In this paper, we propose a novel generic representation called Structured Point Cloud Videos (SPCVs). Intuitively, by leveraging the fact that 3D geometric shapes are essentially 2D manifolds, SPCV re-organizes a point cloud sequence as a 2D video with spatial smoothness and temporal consistency, where the pixel values correspond to the 3D coordinates of points. The structured nature of our SPCV representation allows for the seamless adaptation of well-established 2D image/video techniques, enabling efficient and effective processing and analysis of 3D point cloud sequences. To achieve such re-organization, we design a self-supervised learning pipeline that is geometrically regularized and driven by self-reconstructive and deformation field learning objectives. Additionally, we construct SPCV-based frameworks for both low-level and high-level 3D point cloud sequence processing and analysis tasks, including action recognition, temporal interpolation, and compression. Extensive experiments demonstrate the versatility and superiority of the proposed SPCV, which has the potential to offer new possibilities for deep learning on unstructured 3D point cloud sequences.

A new approach based on genetic algorithm for computation off-loading optimization in multi-access edge computing networks

The proliferation of smart devices and the increasing demand for resource- intensive applications present significant challenges in terms of computational efficiency, leading to surge in data traffic. While cloud computing offers partial solutions, its centralized architecture raises concerns about latency. Multi-access edge computing (MEC) emerges as promising alternative by deploying servers at the network edge to bring computations closer to user devices. However, op- timizing computation offloading in the dynamic MEC environment remains a complex challenge. This paper introduces novel genetic algorithm-based ap- proach for efficient computation offloading in MEC, considering processing and transmission delays, user preferences, and system constraints. The pro- posed approach integrates computation offloading and resource allocation al- gorithm based on evolutionary principles, combined with a greedy strategy to maximize overall system performance. By utilizing genetic algorithms, the pro- posed method enables dynamic adaptation to changing conditions, eliminating the need for intricate mathematical models and providing an appealing solution to the complexities inherent in MEC. The urgency of this research arises from the critical need to enhance mobile application performance. Simulation re- sults demonstrate the robustness and efficacy of our approach in achieving near- optimal solutions while efficiently balancing computation offloading, minimiz- ing latency, and maximizing resource utilization. Our approach offers flexibility and adaptability, contributing to advancement of MEC networks and addressing the requirements of latency-sensitive applications.

Dynamic long short-term memory model for enhanced product recommendations in e-commerce

Recommendation systems are pivotal for personalized user experiences, employing algorithms to predict and suggest items aligned with user preferences. Deep learning (DL) models, such as recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), excel in capturing sequential dependencies, enhancing recommendation accuracy. However, challenges persist in session-based recommendation systems, particularly with gradient descent and class imbalances. Addressing these challenges, this work introduces dynamic LSTM (D-LSTM), a novel DL-based recommendation system tailored for dynamic E-commerce environments. The primary objective is to optimize recommendation accuracy by effectively capturing temporal dependencies within user sessions. The methodology involves the integration of D-LSTM with weight matrix optimization and a Bayesian personalized ranking (BPR) adaptable learning rate optimizer to enhance learning efficiency. Experimental results demonstrate the efficacy of D-LSTM, showing significant improvements over existing models. Specifically, comparisons with the hybrid time-centric prediction (HTCP) model reveal a performance enhancement of 19.4%, 17.2%, 35.41%, and 21.99% for hit-rate (HR) and mean reciprocal rank (MRR) in 10k and 20k recommendation sets using the Tmall dataset. These findings underscore the superior performance of D-LSTM, highlighting its potential to advance personalized recommendations in dynamic E-commerce settings.

Design of flexible polyimide-based serpentine EMG sensor for AI-enabled fatigue detection in construction

Physical fatigue and musculoskeletal disorders are critical health issues for construction workers, stemming from repetitive motions, heavy lifting, and awkward postures. These factors compromise worker well-being, productivity, and safety while increasing the risk of accidents and long-term health problems. Recent advancements in wearable health monitoring technology offer potential solutions, but current sensors encounter significant challenges in the dynamic construction environment. These include inadequate skin contact, increased contact impedance, and vulnerability to motion artifacts all of which degrade signal quality and reduce the accuracy of fatigue detection. This paper develops a fractal-based, flexible sensor for enhanced adaptability and accurate fatigue estimation. Finite element analysis compared five space-filling designs, with the serpentine curve exhibiting the highest contact area and lowest strain, making it the preferred choice for fabrication. Evaluations demonstrated significant improvements in signal-to-noise ratio (SNR) and motion artifact reduction, with the newly developed sensor achieving a 37 % to 59 % SNR improvement over commercial electrodes across different muscle groups. The developed flexible sensor was integrated with a fatigue-detecting framework based on a vision transformer model which provided an average accuracy of 87 % for fatigue detection. The developed sensor significantly enhances EMG signal quality and reliability, promising improved health monitoring and safety for construction workers.

Heterogeneous Unmanned Aerial Vehicles Cooperative Search Approach for Complex Environments

This paper studies a heterogeneous Unmanned Aerial Vehicles (UAVs) cooperative search approach suitable for complex environments. In the application, a fixed-wing UAV drops rotor UAVs to deploy the cluster rapidly. Meanwhile, the fixed-wing UAV works as a communication relay node to improve the search performance of the cluster further. The distributed model predictive control and genetic algorithms are adopted to make online intelligent decisions on UAVs’ search directions. On this basis, a jump grid decision method is proposed to satisfy the maneuverability constraints of UAVs, a parameter dynamic selection method is developed to make search decisions more responsive to task requirements, and a search information transmission method with low bandwidth is designed. This approach can enable UAVs to discover targets quickly, cope with various constraints and unexpected situations, and make adaptive decisions, significantly improving the robustness of search tasks in complex, dynamic, and unknown environments. The proposed approach is tested with several search scenarios, and simulation results show that the cooperative search performance of heterogeneous UAVs is significantly improved compared to homogeneous UAVs.

Seasonal variations of allocation strategy in carbon, nitrogen and phosphorus among tissues of male Mytilus coruscus are regulated by the gametogenic cycle: a case study in a mariculture system

This study examines the seasonal allocation strategy of carbon, nitrogen, and phosphorus in tissues of male Mytilus coruscus within a mariculture system at Gouqi Island, providing insights into the mussels' reproductive and nutritional adaptations. The reproductive cycle of mussels is bifurcated, with a resting phase in summer and active gametogenesis from autumn to spring. Digestive enzyme activity in mussels correlates negatively with food conditionality, especially when food is scarce in winter, enzyme activity is heightened to enhance nutrient extraction, whereas in summer, with an abundance of food, enzymatic activity is conserved for other physiological processes. This suggests an adaptive modulation to optimize energy allocation between growth, maintenance, and reproduction. Allometric growth analysis reveals that smaller mussels exhibit uniform nutrient allocation across tissues, focusing on somatic growth. In contrast, larger, mature mussels prioritize phosphorus utilization in gonads, indicative of reproductive investment. This shift aligns with the predictive adaptive response model, anticipating future reproductive demands by adjusting resource allocation. The study also identifies seasonal fluctuations in nutrient demand and allocation among tissues, with gonadal tissues showing preferential accumulation of nitrogen and phosphorus during mature phases. Although mussels preferentially allocate nutrients to the shell only in autumn, a consistent preferential accumulation of nitrogen and phosphorus to this critical structural component, highlighting the importance of these elements in biomineralization and shell maintenance. This research elucidates the complex interplay between environmental factors, physiological processes, and nutrient dynamics in male M. coruscus, and underscore the importance of considering seasonal variations in nutrient allocation for sustainable mariculture practices.

Air quality in olive mill wastewater evaporation ponds: Assessment of chemical and microbiological pollutants.

Olive mill wastewater (OMW), a pollutant residue from the olive oil industry, is typically stored as sludge in evaporation ponds. This study examines the long-term emissions of OMW sludge and its impact on local air quality, analysing chemical pollutants like PM2.5, volatile organic compounds (VOCs), and trace elements (TEs), along with microbial communities (bacteria and fungi). The study also considered meteorological conditions and back-trajectories to identify sources of these elements. The ecological risk index (ERI) was found to be over 720 due to high Hg levels in the sludge (19.0±0.9ng/g) and air (0.28±0.13ng/m³), indicating a significant ecological threat. VOCs, particularly oxygenated compounds such as aldehydes and phenol, contributed to the area's strong odour. Meteorological conditions and Sahara dust intrusions influenced bioaerosol loads and seasonal bacterial diversity, whose composition is closely associated with VOC concentrations. The results could contribute to a better understanding of the environmental dynamics in the OMW sludge evaporation ponds, and they could also assist in formulating effective management strategies.

Unveiling the Dynamics of Entrepreneurial Leadership and Radical Innovation Performance of China Internet SMEs: Resource-based View

This paper explores the interconnection between entrepreneurial leadership and the radical innovation performance of SMEs in China’s web development industry. Applying RBV theory and a quantitative research design with Smart PLS analysis results in an inquiry of entrepreneurial leadership’s impact on innovative outcomes. A quantitative research design was chosen, using SmartPLS 4.0, with the sample population being Chinese internet industry employees working for SMEs. The sample was made up of 268 employees working in Internet related SMEs in China. The study has demonstrated a notable and positive link between entrepreneurial leadership and radical innovation performance, thus highlighting the crucial role of this function in promoting innovation among the highly competitive Chinese Internet possessions. This study highlights the most important moderating role of entrepreneurial orientation which is its being a mental bridge between entrepreneurial leadership and radical innovation outcomes. The research further gives an insight into the rising relationship between entrepreneurial leadership and entrepreneurial orientation as a result of the moderating effect of power distance within Chinese internet SMEs. Thus, this research provides important information for Chinese Internet small and medium-sized enterprises that intend to increase their radical innovation capacity. It is a blueprint for organizational development and leadership which are the key factors needed to foster the sustainable growth of the internet industry in this dynamic environment.

Economic impacts of federal reserve policies on taxation and corporate finance

Federal Reserve policies play a pivotal role in shaping the U.S. economy, influencing not only macroeconomic stability but also the financial strategies and tax implications for corporations. Broadly, the Federal Reserve's use of monetary tools—such as interest rate adjustments, Quantitative Easing (QE), and inflation targeting—affects the economic environment within which businesses operate, impacting costs of capital, investment incentives, and overall corporate behaviour. Through mechanisms like lowering interest rates, the Federal Reserve reduces borrowing costs, which encourages companies to adjust their capital structures and debt levels, with significant implications for tax planning due to interest deductibility. QE, on the other hand, drives asset prices higher, promoting increased investment activity, stock buybacks, and changes in dividend policies that indirectly influence corporate taxation. This article examines the nuanced relationships between Federal Reserve decisions and corporate finance, analysing how shifts in policy impact tax revenue and how governments adapt tax policies to manage economic conditions such as inflation. By presenting case studies from the 2008 financial crisis and the COVID-19 pandemic, this analysis illustrates the practical effects of the Federal Reserve's actions on corporate financial decisions and the broader tax landscape. The article concludes by addressing the future of Federal Reserve policies in light of technological advances in finance and the adaptive strategies that corporate and regulatory bodies may adopt to navigate an increasingly dynamic economic environment.

Using a tablet to understand the spatial and temporal characteristics of complex upper limb movements in chronic stroke

Robotic devices are commonly used to quantify sensorimotor function of the upper limb after stroke; however, the availability and cost of such devices make it difficult to facilitate implementation in clinical environments. Tablets (e.g. iPad) can be used as devices to facilitate rehabilitation but are rarely used as assessment tools for the upper limb. The current study aimed to implement a tablet-based Maze Navigation Task to examine complex upper-limb movement in individuals with chronic stroke. We define complex upper-limb movement as reaching movements that require multi-joint coordination in a dynamic environment. We predicted that individuals with stroke would have more significant spatial errors, longer movement times, and slower speeds compared to controls with increasing task complexity. Twenty individuals with chronic stroke who had a variety of arm and hand function (Upper extremity Fugl-Myer 52.8 ± 18.3) and twenty controls navigated eight pseudorandomized mazes on an iPad using a digitizing stylus. The task was designed to elicit reaching movements engaging both the shoulder and elbow joints. Each maze became increasingly complex by increasing the number of 90° turns. We instructed participants to navigate each maze as quickly and accurately as possible while avoiding the maze’s boundaries. Sensorimotor behavior was quantified using the following metrics: Error Time (time spent hitting or outside boundaries), Peak Speed, Average Speed, and Movement Time, Number of Speed Peaks. We found that individuals with stroke had significantly greater Error Time for all maze levels (all, p < 0.01), while both speed metrics, Movement Time and Number of Speed Peaks were significantly lower for several levels (all, p < 0.05). As maze complexity increased, the performance of individuals with stroke worsened only for Error Time while control performance remained consistent (p < 0.001). Our results indicate that a complex movement task on a tablet can capture temporal and spatial impairments in individuals with stroke, as well as how task complexity impacts movement quality. This work demonstrates that a tablet is a suitable tool for the assessment of complex movement after stroke and can serve to inform rehabilitation after stroke.