State Predictor Research Articles

O072 Simple Vestibular-Occular Motor Assessment as a Predictor of Alertness State and Driving Impairment during Extended Wakefulness

Abstract Introduction Driver fatigue contributes to 2-16% of road crashes, highlighting the need for improved detection of at-risk drivers. We used a novel and brief test of vestibular ocular motor system (VOMS) assessed via virtual reality goggles to predict alertness state and driving simulator performance during 29hr extended wakefulness. Methods 49 individuals (Mean±SD Age, 32.6±12.9, 45% Males) undergone 9hr baseline sleep opportunity followed by ~29hrs extended wakefulness with five 60min driving assessments. Cluster analysis, combining steering deviation and number of crashes were used to split participants into groups of either poor vs good driving performance. VOMS assessment was conducted using virtual reality goggles approximately 10mins before and after each drive. Predictive importance of VOMs metrics were ranked using XGBoost machine learning model, which was then utilized to distinguish between poor vs good driving groups. Model performance was evaluated using a 5-fold cross-validation approach using ROC analysis. Results XGBoost machine learning ranked all 70 VOMS metrics on their importance in predicting driving performance group for each drive. Top 10 metrics from pre-drive VOMS test predicted both daytime driving (tests 1-3, AUC 0.8 [95%CI 0.64-0.93], p<0.001) and night-time driving (tests 4-5, AUC 0.78 [95%CI 0.6-0.95, p<0.001]). Post-driving VOMS assessments also predicted daytime (AUC 0.74 [95%CI 0.53-0.9, p<0.001] and night-time driving (AUC 0.76 [95%CI 0.52-0.94, p<0.001]). Conclusion VOMS assessment show promise as a short and effective assessment of sleepiness to predict driving failure. Future validation in independent samples, sleep disordered population and in-field on-road testing are needed to confirm these promising findings.

Research on L1 Adaptive Control of Autonomous Underwater Vehicles with X-Rudder

This study focuses on addressing the the coupling problem of the vertical and horizontal plane of an autonomous underwater vehicle (AUV) with an X-rudder. To guarantee the steering performance of the AUV, a depth and course control algorithm based on an L1 adaptive control algorithm (L1AC) is proposed. Firstly, the linear quadratic regulator (LQR) is designed on the basis of an AUV vertical and horizontal linear model, and the system has optimal control quality for both of the nominal vertical and horizontal models. Secondly, the nonlinear state predictor, disturbance estimator, and adaptive controller are designed separately, which is used for the compensation of the uncertainty and disturbance of the AUV dynamic. Finally, the rudder angle allocation algorithm is designed to realize the rudder angle command of the cross rudder to the X-rudder. The simulation and experiment results show that the adaptive control algorithm proposed in this paper can effectively control AUV to complete high-performance course and depth control. Based on the experiments, the prospects and shortcomings of the L1AC, LQR and MRAC algorithm in AUV control are compared and analyzed.

Modeling and Simulation Analysis of Bionic Flapping-Wing Flight Attitude Control Based on L1 Adaptive

Flapping-wing flight control is a multi-input and multi-output nonlinear system with uncertainties, which is affected by modeling errors, parameter variations, external disturbances, and unmodeled dynamics. Parameter uncertainty has a great impact on the stability control of flapping-wing flight, and gain adjustment is a common means to deal with parameter uncertainty, but it is complex and time-consuming. Based on the mechanism of flapping-wing flight, a nonlinear dynamic model for flapping-wing dynamic flight is established by analyzing the forces, moments, and attitude changes of the fuselage and wing in detail. Based on the constructed dynamic model, a fast robust adaptive flapping-wing flight control method is proposed. The state predictor is designed to estimate and monitor the uncertain parameters in the flapping-wing attitude control model, and the adaptive law adjusts the parameter estimation to ensure that the output error between the state predictor and the controlled object is stable in the Lyapunov sense, and finally the adaptive control law is obtained. At the same time, the Monte Carlo-support vector machine method is used to optimize the boundary of the control parameters in the flight control to obtain the control parameters that can meet the control expectations, and the obtained parameters are classified and judged according to the stable level flight conditions. Based on the adjusted parameters and the predetermined control signal, the control amount is adjusted according to the control law. When the adaptive gain is large enough, the simulation results show that the system has good transient response characteristics.

Design of non-smooth consensus protocol for multi-agent systems under DoS attacks

In this paper, we focus on the consensus problem of leaderless multi-agent systems with external disturbance under denial-of-service (DoS) attacks. First, the state predictor is constructed to reproduce the state information blocked during the active periods of DoS attacks. Then, a robust non-smooth consensus protocol is designed using the predictor states, which mitigates the open-loop phenomenon caused by the DoS attacks. Besides, we obtain the sufficient condition for agents to achieve consensus within a region, and demonstrate that the protocol can enhance the anti-disturbance and anti-attack capabilities of the systems. Finally, the theoretical results are verified through numerical simulations.

Impact of obesity on the conversion of immediate-release tacrolimus to extended-release tacrolimus in kidney transplant recipients.

Outcomes analyzing conversion from IR-tacrolimus (IR) to LCP-tacrolimus (LCP) in obesity are limited. This was a retrospective longitudinal cohort study of patients converted from IR to LCP from June 2019 to October 2020. Primary outcomes were conversion ratios for weight-based dose at a steady-state therapeutic level and identification of appropriate dosing weight. Other outcomes included tacrolimus coefficient of variation (CV), time in therapeutic range (TITR), adverse events, infections, donor specific antibodies (DSAs), and acute rejection. A total of 292 patients were included; 156 and 136 patients with a BMI<30 and BMI≥30kg/m2 , respectively. Baseline characteristics were similar, except for pancreas transplant, diabetes, and HLA mismatch. IR to LCP conversion ratio ranged from .73 to .79. Mean LCP dose was similar (.08 vs. .07mg/kg/day for BMI<30 and BMI≥30kg/m2 , respectively); there was a significant difference in IR and LCP mg/kg dosing at steady state with TBW (.11mg/kg vs.09mg/kg and .08mg/kg vs. .06mg/kg, respectively). The most appropriate dosing weight was adjusted body weight (AdjBW), consistent across IR and LCP steady-state doses, and might yield more accurate steady-state dosing requirements. In multivariable modeling, BMI was a significant predictor of steady state mg/kg dosing at therapeutic goal for total body weight (TBW), but not ideal body weight (IBW) or AdjBW.

Dynamic Coordinated Control for Multiconverter Systems via a Multistep Prediction Scheme

Modular DC-DC converters are popular in DC power systems such as demagnetization systems due to their advantages of high efficiency, high reliability, and low current stress on components. However, the dynamic consensus of output currents of the multiple converter degaussing systems (MCDSs) has not been well solved yet, especially when communication delay is considered. In this paper, a novel coordinated control method based on multi-step state predictions with active compensation of delay is proposed to address the poor dynamic consensus performance of currents in MCDSs. The implementation of the scheme consists of two main phases: the design of a multi-step state predictor for MCDSs and the optimization of the coordinating cost of currents. The multi-step state predictor can estimate immeasurable future states of converters over a large horizon length, which presents a novel approach to the current regulator design. The optimal control protocol is derived by minimizing a distributed coordinating performance index function (PIF) for the output currents. This optimization of the PIF minimizes the consensus error between output currents for converters and compensates for communication constraints. Further, the conditions for simultaneous stability and consensus of the closed-loop degaussing system with the distributed multi-step state prediction controller are given. Finally, the performance of the proposed scheme is verified by numerous case studies in an FPGA-based OPAL-RT experimental testbed.

State of charge estimation based on a modified extended Kalman filter

&lt;p&gt;&lt;span lang="EN-US"&gt;The global transition from fossil-based automobile systems to their &lt;br /&gt; electric-driven counterparts has made the use of a storage device inevitable. Owing to its high energy density, lower self-discharge, and higher cycle lifetime the lithium-ion battery is of significant consideration and usage in electric vehicles. Nevertheless, the state of charge (SOC) of the battery, which cannot be measured directly, must be calculated using an estimator. This paper proposes, by means of a modified priori estimate and a compensating proportional gain, an improved extended Kalman filter (IEKF) for the estimation task due to its nonlinear application and adaptiveness to noise. The improvement was achieved by incorporating the residuals of the previous state matrices to the current state predictor and introducing an attenuating factor in the Kalman gain, which was chosen to counteract the effect of the measurement and process noise resulting in better accuracy performance than the conventional SOC curve fitting-based estimation and ampere hour methods. Simulation results show that the standard EKF estimator results in performance with an error bound of 12.9% due to an unstable start, while the modified EKF reduces the maximum error to within 2.05% demonstrating the quality of the estimator.&lt;/span&gt;&lt;/p&gt;

Inundation–Desiccation State Prediction for Salt Pans in the Western Pannonian Basin Using Remote Sensing, Groundwater, and Meteorological Data

Salt pans are unique wetland ecosystems. In the Austrian Seewinkel region, salt pans are in an increasingly vulnerable state due to groundwater drainage and heightened climatic pressures. It is crucial to model how seasonal and long-term hydrological and climatological variations affect the salt pan dynamics in Seewinkel, yet a comprehensive understanding of the driving processes is lacking. The goal of this study is to develop random forest machine learning models driven by hydrological and meteorological data that allow us to predict in early spring (March) of each year the inundation state in the subsequent summer and fall. We utilize Earth observation data from Landsat 5 (L5), 8 (L8), and 9 (L9) to derive the time series of the inundation state for 34 salt pans for the period 1984–2022. Furthermore, we demonstrate that the groundwater level observed in March is the strongest predictor of the salt pan inundation state in summer and fall. Utilizing local groundwater data yields a Matthews correlation coefficient of 0.59. Models using globally available meteorological data, either instead of or in addition to groundwater data, provide comparable results. This allows the global transfer of the approach to comparable ecosystems where no in situ data are available.

Ecological monitoring of emotional intensity, variability, and instability in individuals with schizophrenia spectrum disorders: Results of a multicentre study.

Evaluating emotional experiences in the life of people with Schizophrenia Spectrum Disorder (SSD) is fundamental for developing interventions aimed at promoting well-being in specific times and contexts. However, little is known about emotional variability in this population. In DiAPAson project, we evaluated between- and within-person differences in emotional intensity, variability, and instability between people with SSD and healthy controls, and the association with psychiatric severity and levels of functioning. 102 individuals diagnosed with SSD (57 residential patients, 46 outpatients) and 112 healthy controls were thoroughly evaluated. Daily emotions were prospectively assessed with Experience Sampling Method eight times a day for a week. Statistical analyses included ANOVA, correlations, and generalized linear models. Participants with SSD, and especially residential patients, had a higher intensity of negative emotions when compared to controls. Moreover, all people with SSD reported a greater between-person-variability of both positive and negative emotions and greater intra-variability of negative emotions than healthy controls. In addition, the emotion variability in people with SSD does not follow a linear or quadratic trend but is more "chaotic" if compared to controls. Adequate assessments of positive and negative emotional experiences and their time course in people with SSD can assist mental health professionals with well-being assessment, implementing targeted interventions through the identification of patterns, triggers, and potential predictors of emotional states.

Variable speed limit modelling to improve traffic safety and efficiency of mixed traffic flow by a two-stage framework

A two-stage variable speed limits (VSL) modelling framework is proposed to enhance traffic safety and efficiency at freeway bottlenecks with mixed traffic flow comprising both human-driven and autonomous vehicles. The first-stage macroscopic VSL control framework is based on an extended cell transmission model (ECTM) and a VSL optimal control model. The ECTM serves as a traffic state predictor and characterises mixed traffic flow by modelling various characteristics such as driving behaviours and flow performance. The ECTM-based optimal control model aims to improve safety and efficiency. The second-stage microscopic validation framework is designed using the VISSIM_COM to validate the effectiveness and sophistication of the proposed VSL strategy. The proposed strategy is compared with a fixed speed limit strategy (FSL) and a VSL strategy considering only efficiency improvement (VSL_E). The results demonstrate that the proposed strategy improves traffic efficiency compared to the FSL and significantly outperforms VSL_E in traffic safety.

Distributed Extended State Estimation for Complex Networks With Nonlinear Uncertainty.

This article studies the distributed state estimation issue for complex networks with nonlinear uncertainty. The extended state approach is used to deal with the nonlinear uncertainty. The distributed state predictor is designed based on the extended state system model, and the distributed state estimator is designed by using the measurement of the corresponding node. The prediction error and the estimation error are derived. The prediction error covariance (PEC) is obtained in terms of the recursive Riccati equation, and the upper bound of the PEC is minimized by designing an optimal estimator gain. With the vectorization approach, a sufficient condition concerning stability of the upper bound is developed. Finally, a numerical example is presented to illustrate the effectiveness of the designed extended state estimator.

Design of Reconfigurable Periodic Structures Based on Machine Learning

The design of periodic structures is a very time-consuming process because it requires many cycles of full-wave simulations to obtain the desired electromagnetic (EM) properties. This challenge is amplified when designing reconfigurable periodic structures. This article proposes an intelligent method for the reconfigurable periodic structure design (RPSD) based on machine learning. First, an improved physical and mathematical modeling approach is proposed for reconfigurable periodic structures, which enables the application of machine learning in RPSD. Thereafter, we set up distributed predictors for different reconfigurable states to avoid the one-to-many mapping problem. In addition, the networks of these predictors are trained using variational autoencoders (VAEs) to reduce the associated learning difficulties. These enable the obtention of accurate predictors with small sample data. Moreover, the training of these predictors can be easily accelerated by parallel computation because of their independence. Finally, reconfigurable periodic structures can be intelligently designed by the combination of the trained predictors and a stochastic optimization technique. Some examples are provided to verify the practicality and accuracy of the proposed method.

The Impact of Burnout on the Psychological Well-being of ESL Students in Higher Education Environment

This quantitative study delved into the intricate relationship between language learning and psychological well-being, emphasising its importance in holistic educational approaches, specifically for English as a Second Language (ESL) learners only. The demanding nature of SLA is emphasised as a significant consequence, guiding this exploration within the theoretical framework of Maslach's theory of burnout. The quantitative study involved 207 ESL students, obtained through convenience sampling, in Karachi Pakistan, utilising the Maslach Burnout Inventory-English Student Survey and the Psychological Well-Being Scale to measure burnout and psychological well-being (PWB). The gathered data was analysed using SPSS version 25. The results reveal a significant negative correlation between psychological well-being and burnout, with burnout emerging as a significant negative predictor of students' psychological states. These findings emphasise the need for proactive strategies to address burnout in ESL education, promoting mental health and fostering supportive learning environments. Ultimately, this research contributes a growing body of literature to the field, emphasising the paramount importance of nurturing the well-being of ESL students as they navigate the path to language proficiency in our interconnected global society.

Multi-dimensional influence of pediatric epilepsy on children and their families: A cross-sectional study

ObjectiveIn this study, we aimed to evaluate the effects of pediatric epilepsy on family burden, parental anxiety, depression states, and quality of life of both parents and children. MethodsThe study was undertaken between March and December 2021 using an online questionnaire that included the Family Burden Scale of Disease, the 7-item Generalized Anxiety Disorder scale, the 9-item Patient Health Questionnaire, the WHO Quality of Life Scale (WHOQOL-BREF), and the PedsQL 4.0 Generic Core Scales (parent-proxy report). ResultsA total of 288 parents of children aged 2–18 years were included. Overall, 94.8% of the participating families experienced high levels of disease burden, 67.0% of parents suffered from anxiety states, 57.0% suffered from depression states, and 56.2% of children with epilepsy suffered from comorbid neuropsychiatric symptoms. The mean WHOQOL-BREF score for parental quality of life was 53.7 ± 12.8, while the median PedsQL score for children's quality of life was 65.4 (49.6–81.7). Parental depression states contributed the most to family burden and parental quality of life, whereas comorbidities of epilepsy contributed the most to children's quality of life. Seizure frequency significantly influenced parental anxiety states, and family burden was the most significant predictor of parental depression states. ConclusionHeavy disease burden, anxiety states, and depression states are prevalent in families with children suffering from epilepsy, and most have a poor quality of life. There is a need for greater focus on the quality of life of this patient population and their caregivers, as well as increased resources to help combat anxiety, depression, and poor quality of life.

A Novel Set-Valued Sensor Fault Diagnosis Method for Lithium-Ion Battery Packs in Electric Vehicles

Sensor fault diagnosis is of great significance to ensure safe battery operation. This paper proposes a novel sensor fault diagnosis method that achieves the simultaneous fault detection, fault source and type identification, and fault estimation in a comprehensive way. Specifically, a set-valued observer, featuring a state predictor and a state estimator, is first constructed and designed to guarantee the inclusion of the unavailable actual battery state due to unknown modeling errors and noises at every instant of time. Compared with the traditional observers, a distinct feature of the proposed one lies in that the calculated state predictions and estimations of the battery system at each time step are ellipsoidal sets in state space rather than single vectors. The boundedness of state prediction and estimation errors is formally proved, and the tractable design criteria for determining the real-time optimal prediction and estimation ellipsoids are also derived. As for diagnosis algorithm, fault detection is implemented based on the intersection between the prediction and estimation ellipsoids. Then, a two-layer Pearson correlation coefficient analysis mechanism is developed to identify the source and type of sensor faults. Another set-valued observer based on an augmented battery model is further designed to estimate the fault level. Finally, experimental studies of a battery cell under different sensor fault sources, types and values are elaborated to verify the effectiveness of the proposed method.

Model-free finite-time formation containment control of underactuated UUVs subject to input delays and unknown interaction information

This paper put forwards a model-free adaptive neural finite-time formation-containment (FC) control scheme for time-delayed underactuated unmanned underwater vehicles (UUVs) with unknown dynamic models and some interaction information under switching topologies. The UUVs are steered by multiple child leaders moving along with a root leader, where all leaders are virtual and defined by a new generalized dynamic. A novel autoregressive model-based state predictor is created for each UUV, which can construct future motion states online relying on current and stored states. Considering the containment layer, a finite-time super-twisting observer is used to recover the unavailable interaction information. Moreover, observer-based finite-time kinematic guidance laws employing only 3D positions of the neighboring UUVs are devised, together with protocols for completing formation in finite time. Aiming to accurately identify unknown dynamics and control gains simultaneously, estimator-based adaptive neural networks are introduced exploiting both historical and real-time data. Finally, model-free anti-disturbance finite-time kinetic control protocols are designed based on the data-driven adaptive neural networks and nonlinear tracking differentiators. It is proven that all signals of the closed-loop FC system are bounded, the deployed FC tracking can be achieved in finite time. Simulation results verify the feasibility and superiority of the proposed FC control scheme.

Structural and Functional Brain Patterns Predict Formal Thought Disorder’s Severity and Its Persistence in Recent-Onset Psychosis: Results From the PRONIA Study

BackgroundFormal thought disorder (FThD) is a core feature of psychosis, and its severity and long-term persistence relates to poor clinical outcomes. However, advances in developing early recognition and management tools for FThD are hindered by a lack of insight into the brain-level predictors of FThD states and progression at the individual level. MethodsTwo hundred thirty-three individuals with recent-onset psychosis were drawn from the multisite European Prognostic Tools for Early Psychosis Management study. Support vector machine classifiers were trained within a cross-validation framework to separate two FThD symptom-based subgroups (high vs. low FThD severity), using cross-sectional whole-brain multiband fractional amplitude of low frequency fluctuations, gray matter volume and white matter volume data. Moreover, we trained machine learning models on these neuroimaging readouts to predict the persistence of high FThD subgroup membership from baseline to 1-year follow-up. ResultsCross-sectionally, multivariate patterns of gray matter volume within the salience, dorsal attention, visual, and ventral attention networks separated the FThD severity subgroups (balanced accuracy [BAC] = 60.8%). Longitudinally, distributed activations/deactivations within all fractional amplitude of low frequency fluctuation sub-bands (BACslow-5 = 73.2%, BACslow-4 = 72.9%, BACslow-3 = 68.0%), gray matter volume patterns overlapping with the cross-sectional ones (BAC = 62.7%), and smaller frontal white matter volume (BAC = 73.1%) predicted the persistence of high FThD severity from baseline to follow-up, with a combined multimodal balanced accuracy of BAC = 77%. ConclusionsWe report the first evidence of brain structural and functional patterns predictive of FThD severity and persistence in early psychosis. These findings open up avenues for the development of neuroimaging-based diagnostic, prognostic, and treatment options for the early recognition and management of FThD and associated poor outcomes.

Joint tenderness at 3 months follow-up better predicts long-term pain than baseline characteristics in early rheumatoid arthritis patients.

To investigate pain course over time and to identify baseline and 3-month predictors of unacceptable pain with or without low inflammation in early RA. A cohort of 275 patients with early RA, recruited in 2012-2016, was investigated and followed for 2 years. Pain was assessed using a visual analogue scale (VAS; 0-100 mm). Unacceptable pain was defined as VAS pain >40, and low inflammation as CRP <10 mg/l. Baseline and 3-month predictors of unacceptable pain were evaluated using logistic regression analysis. After 2 years, 32% of patients reported unacceptable pain. Among those, 81% had low inflammation. Unacceptable pain, and unacceptable pain with low inflammation, at 1 and 2 years was significantly associated with several factors at 3 months, but not at baseline. Three-month predictors of these pain states at 1 and 2 years were higher scores for pain, patient global assessment, and the health assessment questionnaire, and more extensive joint tenderness compared with the number of swollen joints. No significant associations were found for objective inflammatory measures. A substantial proportion of patients had unacceptable pain with low inflammation after 2 years. Three months after diagnosis seems to be a good time-point for assessing the risk of long-term pain. The associations between patient reported outcomes and pain, and the lack of association with objective inflammatory measures, supports the uncoupling between pain and inflammation in RA. Having many tender joints, but more limited synovitis, may be predictive of long-term pain despite low inflammation in early RA.

Psychosocial predictors of trajectories of mental health distress during the COVID-19 pandemic: A four-wave panel study

Previous research suggested that during the COVID-19 pandemic, mental distress did not affect all people equally. This longitudinal study aims to examine joint trajectories of depressive, anxiety, and stress symptoms in a sample of Italian adults during the pandemic, and to identify psychosocial predictors of distress states. We analyzed four-wave panel data from 3,931 adults who had received assessments of depressive, anxiety and stress symptoms between April 2020 and May 2021. Trajectories of individual psychological distress were identified by Latent Class Growth Analysis (LCGA) with parallel processes, and multinomial regression models were conducted to identify baseline predictors. Parallel process LCGA identified three joint trajectory classes for depression, anxiety and stress symptoms. Most individuals (54%) showed a resilient trajectory. However, two subgroups showed vulnerable joint trajectories for depression, anxiety and stress. Expressive suppression, intolerance to uncertainty, and fear of COVID-19 were risk characteristics associated with vulnerable trajectories for mental health distress. Moreover, vulnerability to mental health distress was higher in females, younger age groups and those unemployed during the first lockdown. Findings support the fact that group heterogeneity could be detected in the trajectories of mental health distress during the pandemic and it may help to identify subgroups at risk of worsening states.

Predicting sUAS conflicts in the national airspace with interacting multiple models and Haversine-based conflict detection system

In this paper, a conflict detection system for small Unmanned Aerial Vehicles (sUAS), composed of an interacting multiple model state predictor and a Haversine-distance based conflict detector, is proposed. The conflict detection system was developed and tested via a random recursive simulation in the ROS-Gazebo physics engine environment. The simulation consisted of ten small unmanned aerial vehicles flying along randomly assigned way-point navigation missions within a confined airspace. Way-points are generated from a uniform distribution and then sent to each vehicle. The interacting multiple model state predictor runs on a ground-based system and only has access to current vehicle positional information. It does not have access to the future way-points of individual vehicles. The state predictor is based on Kalman filters that utilize constant velocity, constant acceleration, and constant turn models. It generates near-future position estimates for all vehicles operating within an airspace. These models are probabilistically fused together and projected into the near-future to generate state predictions. These state predictions are then passed to the Haversine distance-based conflict detection algorithm to compare state estimates and identify probable conflicts. The conflicts are detected and flagged based on tunable threshold values which compare distances between predictions for the vehicles operating within the airspace. This paper discusses the development of the random recursive simulation for the ROS-Gazebo framework and the derivation of the interacting multiple model along-with the Haversine-based future conflict detector. The results are presented via simulation to highlight mid-air conflict detection application for sUAS operations in the National Airspace.