A real-time comparison between direct control, sequential pattern recognition control and simultaneous pattern recognition control using a Fitts’ law style assessment procedure

This paper presents an investigation focused on the impact of muscle fatigue on a pattern recognition scheme for myoelectric control that uses three features sets and a Linear Discriminant Analysis classifier. Separability and repeatability between classes were used to evaluate the features changes while muscle fatigue was induced. Results show that while muscle fatigue is increasing over time, both separability and repeatability of the classes decrease. Finally two training schemes that use data acquired under fatigue, multiconditional training and selective classification, were evaluated using the Total Error Rate (TER). Results indicate that, when LDA classifier was trained whit no-fatigue, moderated fatigue and fatigue data, TER decreased to moderated and fatigue data, but increased to no-fatigue data. On the other hand, using three LDA classifiers to each of the condition, TER decreased to 9.26 % and 11 % in moderated fatigue and fatigue cases, while no-fatigue case was not affected.

This paper reports a new technique of control combining the concepts of sliding mode control and the multimodel approach. Baptized Integral Pseudo Sliding Mode Control, this control strategy, reduces the library of models whose number can block the establishment of the multi model control strategy in real time. It also allows, on the one hand, having a robust behavior compared to certain classes of uncertainties, and, on the other hand eliminating completely the chattering phenomenon.

The human hand along with its fingers possess one of the highest numbers of nerve endings in the human body. It thus has the capacity for the richest tactile feedback for positioning capabilities. This article shares a new technique of controlling slippage. The sensing system used for the detection of slippage is a modified force sensing resistor (FSR®). The control system is a fuzzy logic control algorithm with multiple rules that is designed to be processed on a mobile handheld computing platform and integrated/working alongside a traditional Electromyography (EMG) or Electroencephalography (EEG) based control system used for determining position of the fingers. A 5 Degrees of Freedom (DOF) hand, was used to test the slippage control strategy in real time. First a reference EMG signal was used for getting the 5 DOF hand to grasp an object, using position control. Then a slip was introduced to see the slippage control strategy at work. The results based on the plain tactile sensory feedback and the modified sensory feedback are discussed.

With the continuous development of vehicle intelligence technology and active safety technology, the autonomous emergency braking pedestrian (AEB-P) system has emerged as a crucial element of contemporary automotive active safety systems. However, there are still some deficiencies in the control strategies utilized by the current AEB-P system. It is imperative to design an AEB-P system that can adapt the safety threshold and control strategy in real time based on the current driving conditions. The objective of this paper is to propose an AEB-P system with an adaptive control strategy and analyse its effectiveness from the perspective of pedestrian head injuries. Initially, an algorithm for adaptive collision time threshold model is proposed, and the AEB-P control strategy integrating this threshold is designed. Subsequently, a finite element model of the human head is developed to predict pedestrian head injuries in pedestrian-vehicle collision (PVC) scenarios with AEB-P intervention. Additionally, a simplified finite element model of PVC is established, and real PVC scenarios are reconstructed to assess the effectiveness of various AEB-P control strategies in mitigating pedestrian head injuries. The results demonstrate that the conventional control strategy is ineffective in reducing the risk of pedestrian head injuries at medium to high speeds. Conversely, the AEB-P system, which incorporates an adaptive control strategy, proves to be effective in decreasing the risk of pedestrian head injuries. Overall, the AEB-P system with adaptive control strategy enhances pedestrian safety, particularly in scenarios where PVCs are inevitable.

Aiming at the problem that the motion characteristics of ships sailing at sea or inland rivers are time-varying and nonlinear, and the heading is difficult to control in real time and accurately, this paper proposes a heading control strategy based on neural network PID controller. The neural network PID controller imitates the structure of neural network. A series of formula derivations can prove that the output of the controller has proportional, integral and differential effects on the error. The parameters of this neural network PID controller are adaptively adjusted in real time online according to the error and the rate of error change. Therefore, the ship control system can still output the optimal control strategy in real time under the complicated and changeable operating environment. Matlab / Simulink is used for simulation. The simulation results prove that the heading control strategy based on neural network PID controller has obvious superiority in real-time and precise control of heading.

Introduction: Blood pressure (BP) control in the United States among persons with hypertension (HTN) is less than 50%. Performance and quality measures to improve care and outcomes for patients with high BP were published in 2019. The American Heart Association (AHA) recently completed its federally funded cooperative agreement, the National Hypertension Control Initiative (NHCI) to improve BP control in 350 community health centers (CHCs) with 1.5 million persons with HTN. Hypothesis: Use of a population health management platform can provide CHCs with more actionable, real-time Electronic Health Record (EHR) data to advance quality improvement (QI) efforts and evaluation capabilities. Methods: AHA identified a population health management platform to source EHR-derived data from 38 of 350 CHCs participating in NHCI. The objective was to demonstrate the value of readily accessing and using established measures for BP control in a project and system not already set up to do so. Eighteen clinical measures were used based on established performance and quality measures, aligning with Healthcare Effectiveness Data Information Set (HEDIS) where possible. Data for chosen measures was pulled from CHC EHRs on a monthly, quarterly, and ad hoc basis. This data expanded beyond what is required to be reported by CHCs to the Uniform Data System (UDS). Data sharing agreements were secured from 38 NHCI CHCs and 12 non-NHCI CHCs, as a comparison group, and all measures were made available to participating CHCs and other users. Results: Data was received for 12 quarters (January 2021 through December 2023) from the 50 CHCs on over 4.3 million encounters for 2.8 million patients. Data show a 48.7% relative improvement in the number of CHCs taking a BP reading at each patient encounter from Q1 2021-Q4 2023 (57.4% to 85.4%). Additionally, CHC BP control <140/90 mm Hg and <130/80 mm Hg reached 65.4% and 27.9%, respectively, in Q4 2023, as compared to the UDS reported 2023 BP control rate <140/90 mm Hg of 60.9% for 350 NHCI CHCs. Conclusion: The expanded 18 measures allowed for more timely, frequent, detailed, and potentially actionable data to inform QI efforts. The timeliness and higher frequency of data should enable CHCs to understand the effects of their BP control strategies in real time. Using a population health management platform that emphasizes clinical performance measures based on “real-time” EHR data may strengthen and accelerate BP control QI and evaluation efforts.

Although significant technological advances have been made in the last forty years, natural and effortless control of upper limb prostheses is still an open issue. Commercially available myoelectric prostheses present limited Degrees of Freedom (DoF) mainly because of the lack of available and reliable independent control signals from the human body. Thus, despite the crucial role that an actuated wrist could play in a transradial prosthesis in terms of avoiding compensatory movements, commercial hand prostheses present only manually adjustable passive wrists or actuated rotators controlled by (unnatural) sequential control strategies. In the present study we investigated the synergies between the humeral orientation with respect to the trunk and the forearm pronation/supination angles during the execution of a wide range of activities of daily living, in healthy subjects. Our results showed consistent postural synergies between the two selected body segments for almost the totality of the activities of daily living under investigation. This is a promising result because these postural synergies could be exploited to automatically control the wrist rotator unit in transradial prostheses improving the fluency and the dexterity of the amputee.

This paper describes a real-time multi-objective predictive control strategy for the wheelchair ergometer platform, which allows simulating the manual wheelchair (MWC) propulsion in virtual reality (VR). A nonlinear least-square method is used to build the predictive wheelchair ergometer model, where the trust-region-reflective algorithm is adopted. A detailed study of the wheelchair dynamics, and its performance on the rollers, and the frictions are presented. The main contribution is the implementation of a wheelchair ergometer model into a proposed controller in order to provide realistic navigation within the VR world by accurately detecting and tracking the rotation of the driving wheels. In particular, the proposed strategy has two objectives: 1) to generate force feedback (haptics) during the push phase (hand-to-rim contact); 2) assistance control to make the wheelchair movement more realistic in the immersive virtual environment during the recovery phase (hand-to-rim no contact). Various numerical examples emphasize the flexibility of the approach and experimental results confirm that the proposed controller successfully tracks the speed reference. It is also shown that the real-time tracking ability of the explicit MPC (eMPC) controller is superior to that of the PI controller.

This paper proposes two real-time feedback control strategies based on hourly measurements of effluent NH4-N and NOX-N concentrations. Using modified sigmoid functions to decide the DO setpoint, a control structure similar to the cascade-type control loop was selected as the real-time feedback NH4-N control strategy. For the realtime feedback NOX-N control strategy, a proper external carbon dose flow rate could be calculated based on the estimated NOX-N concentration in anoxic reactor by using the empirical equation. A control system, which included two proposed control strategies, was developed and applied in the pilot-scale A2/O process. As a result, the effluent NH4-N and NOX-N concentrations were maintained stably lower than the target values of 3 and 5 mg/L, respectively. Moreover, because the manipulated variables for removing the NH4-N and NOX-N concentrations were divided in the control strategies, the two different control strategies could be successfully applied together in the A2/O process.

Intelligent transportation systems (ITS) typically rely on massive sources of data to monitor the transportation system, estimate its current state, forecast its future state, and react with a set of control and management strategies in real time. This requires the prompt processing of a variety of data sources that is consistently changing with time and typically challenging to combine (and make sense of) in real time. This paper presents thoroughly the studies related to big data applications in ITS and its associated challenges.

This paper presents the real-time control strategies developed to regulate both the ammonia and nitrate concentration in the effluent of the new Vitoria WWTP (Spain). Nitrate control aims at the optimal use of the denitrification potential at any moment. For this purpose, the proposed control algorithm continuously adapts the internal recycle flow in order to maintain a desired nitrate set-point in the anoxic zone. Ammonia control aims at maintaining the required average concentration of ammonia in the effluent by manipulating the Dissolved Oxygen (DO) set-point. The control strategies have been based on a hierarchical structure where a high-level or supervisory control selects the set-point of the low-level or conventional controllers. The design of the controllers was carried out using the Quantitative Feedback Theory QFT for the design of robust control systems. Moving average values of some variables have been introduced in order to eliminate the perturbations associated with the daily 24-hour profiles. The controllers have been verified using long-time dynamic simulations based on a mathematical model previously calibrated in pilot plant. Influent load and temperature used in the simulations correspond to the real values measured in the full-scale WWTP during 12 months. The results obtained in the simulations show the good performance and stability of the control strategies independently from external disturbances. A short-time experimental verification of the controllers in pilot plant with real wastewater is also presented.

This paper proposes a model of agricultural product purchase intention based on live broadcast AI and recommendation algorithm (LiveRec). By combining AI behavior analysis in live broadcast with traditional recommendation algorithm, this model can adjust the recommendation strategy in real time according to the user's viewing behavior, interaction, comments and other information, thereby improving the user's purchase intention. This paper makes use of the live broadcast data from the e-commerce platform of agricultural products, including user behavior data and sales records, to evaluate the effectiveness of the model in the forecast of buying intention and the exchange rate. Experiments show that the precision of the prediction is increased by 18 %, and the conversion ratio is 15 % higher than that of conventional logistic regression and SVM. In particular, the model has good adaptability and real time performance in the user's personalized recommendation. The study indicates that the model based on live AI and recommended algorithm can increase the sales efficiency of agriculture products, and it will have a bright future. Future research will further optimize the model's real time performance and processing efficiency, and extend its application to other electronic commerce.

Progress in preparing real-time control schemes for Deuterium-Tritium operation in JET

Automation of wrist rotations in upper limb prostheses allows simplification of the human-machine interface, reducing the user's mental load and avoiding compensatory movements. This study explored the possibility of predicting wrist rotations in pick-and-place tasks based on kinematic information from the other arm joints. To do this, the position and orientation of the hand, forearm, arm, and back were recorded from five subjects during transport of a cylindrical and a spherical object between four different locations on a vertical shelf. The rotation angles in the arm joints were obtained from the records and used to train feed-forward neural networks (FFNNs) and time-delay neural networks (TDNNs) in order to predict wrist rotations (flexion/extension, abduction/adduction, and pronation/supination) based on the angles at the elbow and shoulder. Correlation coefficients between actual and predicted angles of 0.88 for the FFNN and 0.94 for the TDNN were obtained. These correlations improved when object information was added to the network or when it was trained separately for each object (0.94 for the FFNN, 0.96 for the TDNN). Similarly, it improved when the network was trained specifically for each subject. These results suggest that it would be feasible to reduce compensatory movements in prosthetic hands for specific tasks by using motorized wrists and automating their rotation based on kinematic information obtained with sensors appropriately positioned in the prosthesis and the subject's body.

Fine-wire intramuscular electrodes were used to obtain electromyogram (EMG) signals from six extrinsic hand muscles associated with the thumb, index, and middle fingers. Subjects' EMG activity was used to control a virtual three-degree-of-freedom (DOF) hand as they conformed the hand to a sequence of hand postures testing two controllers: direct EMG control and pattern recognition control. Subjects tested two conditions using each controller: starting the hand from a predefined neutral posture before each new posture and starting the hand from the previous posture in the sequence. Subjects demonstrated their abilities to simultaneously, yet individually, move all three DOFs during the direct EMG control trials; however, results showed subjects did not often utilize this feature. Performance metrics such as failure rate and completion time showed no significant difference between the two controllers.