Continuous Estimation Research Articles

Supplemental Material for Reliability in Unidimensional Ordinal Data: A Comparison of Continuous and Ordinal Estimators

Supplemental Material for Reliability in Unidimensional Ordinal Data: A Comparison of Continuous and Ordinal Estimators

Incorporating control inputs in continuous-time Gaussian process state estimation for robotics

Abstract Continuous-time batch state estimation using Gaussian processes is an efficient approach to estimate the trajectories of robots over time. In the past, relatively simple physics-motivated priors have been considered for such approaches, using assumptions such as constant velocity or acceleration. This paper presents an approach to incorporating exogenous control inputs, such as velocity or acceleration commands, into the continuous Gaussian process state estimation framework. It is shown that this approach generalizes across different domains in robotics, making it applicable to both the estimation of continuous-time trajectories for mobile robots and the estimation of quasi-static continuum-robot shapes. Results show that incorporating control inputs leads to more informed priors, potentially requiring less measurements and estimation nodes to obtain accurate estimates. This makes the approach particularly useful in situations in which limited sensing is available. For example, in a mobile robot localization experiment with sparse landmark distance measurements and frequent odometry control inputs, our approach provides accurate trajectory estimates with root-mean-square errors around 3-4 cm and 4-5 degrees, even with time intervals up to five seconds between discrete estimation nodes, which significantly reduces computation time.

Impact of nitroglycerin-induced vasodilation on stroke volume and diuretic response in acute heart failure: A protocol for a mechanistic trial.

Acute heart failure is a clinical syndrome characterized by cardiac dysfunction and neurohumoral activation, encompassing complex underlying pathophysiology which may vary across phenotypes. Nitroglycerine is a nitrate donor with vasodilatory effects on both venous capacitance vessels and arterial resistance vessels in higher doses, typically used with the aim of reducing congestion, preload, and afterload. A limited number of studies have proposed that nitroglycerin could promote diuresis and natriuresis. However, the exact hemodynamic effects of nitroglycerin remain uncertain in the clinical setting of acute decompensated heart failure. We hypothesize that intravenous nitroglycerin induces a significant increase in stroke volume and urinary output while lowering cardiac filling pressures. This will be a prospective single-center interventional clinical study of 21 patients hospitalized with a diagnosis of AHF. Patients are examined before and after administration of intravenous nitroglycerin. To characterize hemodynamic phenotypes of AHF, continuous estimates of stroke volume will be obtained, and total blood volume estimated. Vital signs and estimates of peripheral perfusion will be recorded continuously. Measures of cardiac function, renal function, volume status, and autonomic function will be assessed sequentially. This study will assess the acute effects of vasodilation on stroke volume and urinary output in hospitalized patients with AHF. Furthermore, characterizing the hemodynamic profile of the patient prior to vasodilation may help explore which patients will benefit from vasodilation.

Robust adaptive motion control for cable-driven aerial manipulators with input saturation

Robust adaptive motion control for cable-driven aerial manipulators with input saturation

The Impact of Aging on Measurement of Continuity of Treatment Among Children Living With HIV in the PEPFAR Supported Program in Kenya.

To reduce HIV-related morbidity and mortality among children living with HIV (CLHIV), continuity of treatment is critical. We sought to understand how aging out among CLHIV in Kenya impacts estimates of treatment continuity. A retrospective cohort analysis was performed on deidentified individual-level data from the Kenya National Data Warehouse for all clients who initiated and/or received antiretroviral therapy between the periods of October 2018 and September 2022 [US Government fiscal years (FYs) 2019-2022]. CLHIV previously on treatment and those newly initiating treatment were included in the analysis. Outcomes included aging out of childhood (turning 15 years old), interruption in treatment, return to treatment and remaining active on treatment. The number of active CLHIV on treatment at the end of FY 2019 was 44,628. This changed to 48,218, 48,262 and 44,780 representing 8%, 0% and -7% cohort growth/reduction at the end of FYs 2020, 2021 and 2022, respectively. Among those who were on treatment at the beginning of each FY, aging out of childhood accounted for 53%, 61% and 72% of the total cohort reductions for the periods 2020, 2021 and 2022, respectively. Interruptions in treatment accounted for proportions ranging from 5% to 9% among those active on treatment, while those who aged out of childhood ranged between 11% and 13%. Among those who returned to treatment in each FY, the proportions who remained active at the end of the FY varied from 72% to 76%. Accounting for aging out of childhood can improve program estimates of their true rates of interruptions of treatment in children, as they work to achieve epidemic control among CLHIV.

Brief communication: Monitoring snow depth using small, cheap, and easy-to-deploy snow–ground interface temperature sensors

Abstract. Temporally continuous snow depth estimates are vital for understanding changing snow patterns and impacts on permafrost in the Arctic. We trained a random forest machine learning model to predict snow depth from variability in snow–ground interface temperature. The model performed well on Alaska's Seward Peninsula where it was trained and at Arctic evaluation sites (RMSE ≤ 0.15 m). It performed poorly at temperate sites with deeper snowpacks, partially due to training data limitations. Small temperature sensors are cheap and easy to deploy, so this technique enables spatially distributed and temporally continuous snowpack monitoring at high latitudes to an extent previously infeasible.

Multijoint Continuous Motion Estimation for Human Lower Limb Based on Surface Electromyography

The estimation of multijoint angles is of great significance in the fields of lower limb rehabilitation, motion control, and exoskeleton robotics. Accurate joint angle estimation helps assess joint function, assist in rehabilitation training, and optimize robotic control strategies. However, estimating multijoint angles in different movement patterns, such as walking, obstacle crossing, squatting, and knee flexion–extension, using surface electromyography (sEMG) signals remains a challenge. In this study, a model is proposed for the continuous motion estimation of multijoint angles in the lower limb (CB-TCN: temporal convolutional network + convolutional block attention module + temporal convolutional network). The model integrates temporal convolutional networks (TCNs) with convolutional block attention modules (CBAMs) to enhance feature extraction and improve prediction accuracy. The model effectively captures temporal features in lower limb movements, while enhancing attention to key features through the attention mechanism of CBAM. To enhance the model’s generalization ability, this study adopts a sliding window data augmentation method to expand the training samples and improve the model’s adaptability to different movement patterns. Through experimental validation on 8 subjects across four typical lower limb movements, walking, obstacle crossing, squatting, and knee flexion–extension, the results show that the CB-TCN model outperforms traditional models in terms of accuracy and robustness. Specifically, the model achieved R2 values of up to 0.9718, RMSE as low as 1.2648°, and NRMSE values as low as 0.05234 for knee angle prediction during walking. These findings indicate that the model combining TCN and CBAM has significant advantages in predicting lower limb joint angles. The proposed approach shows great promise for enhancing lower limb rehabilitation and motion analysis.

An Active Control Method for a Lower Limb Rehabilitation Robot with Human Motion Intention Recognition

This study presents a method for the active control of a follow-up lower extremity exoskeleton rehabilitation robot (LEERR) based on human motion intention recognition. Initially, to effectively support body weight and compensate for the vertical movement of the human center of mass, a vision-driven follow-and-track control strategy is proposed. Subsequently, an algorithm for recognizing human motion intentions based on machine learning is proposed for human-robot collaboration tasks. A muscle–machine interface is constructed using a bi-directional long short-term memory (BiLSTM) network, which decodes multichannel surface electromyography (sEMG) signals into flexion and extension angles of the hip and knee joints in the sagittal plane. The hyperparameters of the BiLSTM network are optimized using the quantum-behaved particle swarm optimization (QPSO) algorithm, resulting in a QPSO-BiLSTM hybrid model that enables continuous real-time estimation of human motion intentions. Further, to address the uncertain nonlinear dynamics of the wearer-exoskeleton robot system, a dual radial basis function neural network adaptive sliding mode Controller (DRBFNNASMC) is designed to generate control torques, thereby enabling the precise tracking of motion trajectories generated by the muscle–machine interface. Experimental results indicate that the follow-up-assisted frame can accurately track human motion trajectories. The QPSO-BiLSTM network outperforms traditional BiLSTM and PSO-BiLSTM networks in predicting continuous lower limb motion, while the DRBFNNASMC controller demonstrates superior gait tracking performance compared to the fuzzy compensated adaptive sliding mode control (FCASMC) algorithm and the traditional proportional–integral–derivative (PID) control algorithm.

A GIS based spatiotemporal modelling approach for cycling risk mapping using crowd-sourced sensor data

ABSTRACT The major objective of this study is to apply integrated data-driven methods to estimate cyclist risk and discomfort in Berlin based on the OpenSenseMap dataset. The proposed approach makes use of crowd-sourced sensor data collected during cycling (speed, bike vibration, distance to other objects), spatial statistics and multi-criteria decision analysis to provide a continuous estimation of cycling discomfort and risk in the traffic network. We employed cycling traffic volume and route discomfort estimation techniques to determine the spatiotemporal patterns of cycling traffic volume and discomfort levels. Accordingly, a GIS-based multiple criteria analysis approach was applied to map areas with high cycling traffic volume based on the condition of the cycling lanes, environmental, road traffic, land use and sociodemographic characteristics. The results show that the central area of Berlin has a high cycling traffic volume as well as a high level of discomfort. In this context, we found a significant spatial correlation between the cycling traffic volume and discomfort with the land use characteristics such as commercial or residential areas, motor vehicle traffic volume and sociodemographic characteristics in Berlin. Furthermore, results revealed a correlation between intensive traffic volume and commercial zones, schools and university areas. As we identified high-risk cycling directions and their autocorrelation with relevant indicators, the obtained results from this study will support decision-makers and authorities in recognizing the high-risk cycling areas and optimizing the risk areas, which accordingly increase the cycling safety and wellbeing of citizens.

Harnessing Multi-Source Data and Deep Learning for High-Resolution Land Surface Temperature Gap-Filling Supporting Climate Change Adaptation Activities

Addressing global warming and adapting to the impacts of climate change is a primary focus of climate change adaptation strategies at both European and national levels. Land surface temperature (LST) is a widely used proxy for investigating climate-change-induced phenomena, providing insights into the surface radiative properties of different land cover types and the impact of urbanization on local climate characteristics. Accurate and continuous estimation across large spatial regions is crucial for the implementation of LST as an essential parameter in climate change mitigation strategies. Here, we propose a deep-learning-based methodology for LST estimation using multi-source data including Sentinel-2 imagery, land cover, and meteorological data. Our approach addresses common challenges in satellite-derived LST data, such as gaps caused by cloud cover, image border limitations, grid-pattern sensor artifacts, and temporal discontinuities due to infrequent sensor overpasses. We develop a regression-based convolutional neural network model, trained on ECOSTRESS (ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station) mission data, which performs pixelwise LST predictions using 5 × 5 image patches, capturing contextual information around each pixel. This method not only preserves ECOSTRESS’s native resolution but also fills data gaps and enhances spatial and temporal coverage. In non-gap areas validated against ground truth ECOSTRESS data, the model achieves LST predictions with at least 80% of all pixel errors falling within a ±3 °C range. Unlike traditional satellite-based techniques, our model leverages high-temporal-resolution meteorological data to capture diurnal variations, allowing for more robust LST predictions across different regions and time periods. The model’s performance demonstrates the potential for integrating LST into urban planning, climate resilience strategies, and near-real-time heat stress monitoring, providing a valuable resource to assess and visualize the impact of urban development and land use and land cover changes.

Development of Shape-Mimetics Wireless Monitoring System by 3D Printer and its Application to Grasp-Less Handling Based on Ball Rolling Motion with a Dual-Arm Robot and Egg Washing Inspection Process

This study focuses on the development and implementation of a shape-mimetics wireless monitoring system. A 3D printer is used to monitoring device, which mimics these shapes, is referred to as a shape-mimetics wireless monitoring robot. The effectiveness of this system depends on the complexity of both the shape and the environment. When both factors are relatively simple, trajectory estimation can be performed using mathematical modeling. This was validated through experiments involving the motion of a ball on a horizontal plane using grasp-less handling. In contrast, when both factors are complex, vibrations and external forces can be directly monitored as raw data in a straightforward manner. This was demonstrated during the egg washing and inspection process, which served as a complex, real-world application. These results show that the shape-mimetics wireless monitoring system can achieve continuous trajectory estimation and monitor vibrations and external forces at a higher sampling frequency compared to conventional vision-based monitoring systems. The findings suggest that the proposed system could be beneficial in a wide range of industries, including manufacturing and food processing.

Multimodal Continual Learning for Process Monitoring: A Novel Weighted Canonical Correlation Analysis With Attention Mechanism.

Aimed at sequential dynamic modes, a novel multimodal weighted canonical correlation analysis using an attention (MWCCA-A) mechanism is introduced to derive a single model for process monitoring, by integrating two ideas of replay and regularization in continual learning. Under the assumption that data are received sequentially, subsets of data from past modes with dynamic features are selected and stored as replay data, which are utilized together with the current mode data for continual model parameter estimation. The weighted canonical correlation analysis (WCCA) is introduced to achieve appropriate weightings of past modes' replay data so that the latent variables are extracted by maximizing the weighted correlation with its prediction via the attention mechanism. Specifically, replay data weightings are obtained via the probability density estimation from each mode. This is also beneficial in overcoming data imbalance among multiple modes and consolidating the significant features of past modes further. Alternatively, the proposed model also regularizes parameters based on its previous modes' importance, which is measured by synaptic intelligence (SI). Meanwhile, the objective is decoupled into a regularization-related part and a replay-related part, to overcome the potentially unstable optimization trajectory of SI-based continual learning. In comparison with several multimode monitoring methods, the effectiveness of the proposed MWCCA-A approach is demonstrated by a continuous stirred tank heater (CSTH), Tennessee Eastman process (TEP), and a practical coal pulverizing system.

EMG-Based Continuous Estimation of Index Finger Movements With Varying Interjoint Coordination Patterns by Modeling Musculoskeletal Dynamics

EMG-Based Continuous Estimation of Index Finger Movements With Varying Interjoint Coordination Patterns by Modeling Musculoskeletal Dynamics

Localized solar radiation zoning by combining spatially continuous estimates and Gaussian mixture models

Localized solar radiation zoning by combining spatially continuous estimates and Gaussian mixture models

Impact of spatial layout optimization on photovoltaic power consumption: insights from China

ABSTRACT Developing rooftop photovoltaics (PV) has become an important global initiative for achieving carbon neutrality. However, the consumption of variable PV generation remains a major challenge for the electric grid. This study presents a novel multi-objective optimization framework to investigate how spatial layout affects rooftop PV generation consumption in large-scale grid-connected scenarios. Unlike previous studies, our framework integrates continuous spatiotemporal estimates of PV generation and simulation of trans-regional power dispatch simulations, explicitly accounting for the regional differences in power generation, transmission, storage, consumption, and curtailment. An analysis of China's pilot scheme reveals that a suboptimal layout exacerbates the challenges associated with PV consumption, whereas an optimal spatial layout can contribute to a 7% reduction in PV curtailment while maintaining a comparable level of PV penetration. Our findings also underscore the importance of ensuring background climate diversity and regional balance in site selection for future PV expansion. This study provides innovative tools and actionable insights for optimizing the spatial layout of variable energy sources, contributing to policy development and renewable energy integration.

Multi-scale attention patching encoder network: a deployable model for continuous estimation of hand kinematics from surface electromyographic signals

BackgroundSimultaneous and proportional control (SPC) based on surface electromyographic (sEMG) signals has emerged as a research hotspot in the field of human–machine interaction (HMI). However, the existing continuous motion estimation methods mostly have an average Pearson coefficient (CC) of less than 0.85, while high-precision methods suffer from the problem of long inference time (> 200 ms) and can only estimate SPC of less than 15 hand movements, which limits their applications in HMI. To overcome these problems, we propose a smooth Multi-scale Attention Patching Encoder Network (sMAPEN).MethodsThe sMAPEN consists of three modules, the Multi-scale Attention Fusion (MAF) module, the Patching Encoder (PE) module, and a smoothing layer. The MAF module adaptively captures the local spatiotemporal features at multiple scales, the PE module acquires the global spatiotemporal features of sEMG, and the smoothing layer further improves prediction stability.ResultsTo evaluate the performance of the model, we conducted continuous estimation of 40 subjects performing over 40 different hand movements on the Ninapro DB2. The results show that the average Pearson correlation coefficient (CC), normalized root mean square error (NRMSE), coefficient of determination (R2), and smoothness (SMOOTH) of the sMAPEN model are 0.9082, 0.0646°, 0.8163, and − 0.0017, respectively, which significantly outperforms that of the state-of-the-art methods in all metrics (p < 0.01). Furthermore, we tested the deployment performance of sMAPEN on the portable device, with a delay of only 97.93 ms.ConclusionsOur model can predict up to 40 hand movements while achieving the highest predicting accuracy compared with other methods. Besides, the lightweight design strategy brings an improvement in inference speed, which enables the model to be deployed on wearable devices. All these promotions imply that sMAPEN holds great potential in HMI.

Simultaneous and continuous estimation of upper limb kinematics of shoulder press movements: state-space EMG model

Simultaneous and continuous estimation of upper limb kinematics of shoulder press movements: state-space EMG model

Continuous Estimation of Blood Pressure by Utilizing Seismocardiogram Signal Features in Relation to Electrocardiogram.

There is an ongoing search for a reliable and continuous method of noninvasive blood pressure (BP) tracking. In this study, we investigate the feasibility of utilizing seismocardiogram (SCG) signals, i.e., chest motion caused by cardiac activity, for this purpose. This research is novel in examining the temporal relationship between the SCG-measured isovolumic moment and the electrocardiogram (PEPIM). Additionally, we compare these results with the traditionally measured pre-ejection period with the aortic opening marked as an endpoint (PEPAO). The accuracy of the BP estimation was evaluated beat to beat against invasively measured arterial BP. Data were collected on separate days as eighteen sets from nine subjects undergoing a medical procedure with anesthesia. Results for PEPIM showed a correlation of 0.67 ± 0.18 (p < 0.001), 0.66 ± 0.17 (p < 0.001), and 0.67 ± 0.17 (p < 0.001) when compared to systolic BP, diastolic BP, and mean arterial pressure (MAP), respectively. Corresponding results for PEPAO were equal to 0.61 ± 0.22 (p < 0.001), 0.61 ± 0.21 (p < 0.001), and 0.62 ± 0.22 (p < 0.001). Values of PEPIM were used to estimate MAP using two first-degree models, the linear regression model (achieved RMSE of 11.7 ± 4.0 mmHg) and extended model with HR (RMSE of 10.8 ± 4.2 mmHg), and two corresponding second-degree models (RMSE of 10.8 ± 3.7 mmHg and RMSE of 8.5 ± 3.4 mmHg for second-degree polynomial and second-degree extended, respectively). In the intrasubject testing of the second-degree model extended with HR based on PEPIM values, the mean error of MAP estimation in three follow-up measurements was in the range of 7.5 to 10.5 mmHg, without recalibration. This study demonstrates the method's potential for further research, particularly given that both proximal and distal pulses are measured in close proximity to the heart and cardiac output. This positioning may enhance the method's capacity to more accurately reflect central blood pressure compared to peripheral measurements.

Two-source energy balance schemes exploiting land surface temperature and soil moisture for continuous vineyard water use estimation

Two-source energy balance schemes exploiting land surface temperature and soil moisture for continuous vineyard water use estimation

Wearable System for Continuous Estimation of Transepidermal Water Loss

To maintain skin moisture, we need to maintain good stratum corneum barrier function, which prevents moisture evaporation from the inside of the skin. Transepidermal water loss (TEWL), the amount of water that evaporates from the skin, indicates the state of barrier function. The barrier function of facial skin is easily damaged in daily life, and the condition of the skin becomes worse without us noticing. We should constantly monitor TEWL to prevent worsening skin conditions. In this paper, we propose a wearable device that continuously measures TEWL. We estimate TEWL using machine learning from temperature and humidity values of water evaporation from the skin and parameters that affect TEWL, such as skin surface temperature and galvanic skin response. We experimented with the prototype device in a controlled environment. We confirmed that the prototype device could estimate TEWL accurately enough to judge the skin’s condition in stationary and conversational situations. Then, we experimented to verify the environmental conditions for estimating TEWL using the prototype device. The prototype device could estimate TEWL with sufficient precision in an office without airflow. However, we could not estimate TEWL in the office with airflow and outdoor.