Tracking Response Research Articles

Efficient maximum power point tracker based on neural network and sliding-mode control for buck converters

Abstract This paper presents detailed design steps of an effective control system aiming to increase the solar energy harvested via photovoltaic power-generation systems. The design of an intelligent maximum power point tracker (MPPT) supported by a robust sliding-mode (SM) controller is discussed in this study. The proposed control scheme is designed to track the MPP and provide a smooth system response by removing the overshoot in the load current during any variation in the connected load. Such a system is suitable for DC–DC buck converter applications. The study begins with modelling the buck converter for a continuous current mode operation. The reference voltage of the tracking system is produced by the proposed neural network (NN) algorithm. The proposed intelligent MPPT integrated with an SM controller is simulated in a MATLAB®/Simulink® platform. The simulation results are analysed to investigate and confirm the satisfaction level of the adopted four-serially connected PV-modules system. The system performance is evaluated at a light intensity of 500 W/m2 and an ambient temperature of 25°C. Applying only the proposed NN algorithm guarantees the MPP tracking response by delivering 100 W at a resistive load of 13 Ω, and 200 W at a load of 6.5 Ω, respectively, with 99.77% system efficiency. However, this simultaneously demonstrates a current spike of ~0.5 A when the load is varied from 50% to 100%. The integrated SM controller demonstrates a robust and smooth response, eliminating the existing current spike.

Optimizing the response to mental health deterioration: Nurses experiences of using a Mental Health Observation Response Chart.

Recognizing mental health deterioration remains a challenge for health systems globally, with evidence of suboptimal care for patients with increasing co-morbid psychiatric illness. Mechanisms exist to detect and respond to physical deterioration with the use of Observation Response Charts, monitoring of vital signs and medical emergency teams but registered nurses lack psychiatric nursing skills to care for this patient population. Currently, there are no validated processes in place to recognize and respond to mental health deterioration in general hospital wards. This qualitative descriptive study explores nurses' experiences of using a Mental Health Observation Response Chartthat uses signs of distress to track and trigger tiered responses to mental health deterioration on general hospital wards. Thirty-five surgical and rehabilitation nurses participated in focus groups from January to March 2020. All qualitative data were thematically analysed using an inductive approach. Analysis resulted in four themes: clinical relevance, a useful chart, identifying distress, and working with doctors. The clinical relevance of the chart was influenced by the level of nursing experience; patient distress; existing escalation pathways and ward culture. The study findings will inform the establishment of a process for nurses to recognize mental health deterioration that could improve patient outcomes and promote staff safety. Further research is needed to validate specific signs of distress with patients in general hospital wards and to develop findings for the clinical relevance of this approach to detect mental health deterioration and improve patient outcomes.

Energy harvesting space-air-sea integrated networks for MEC-enabled maritime Internet of Things

In recent years, various maritime applications such as unmanned surface vehicles, marine environment monitoring, target tracking, and emergency response have developed rapidly in maritime communication networks (MCNs), and these applications are often accompanied by complex computation tasks and low latency requirements. However, due to the limited resources of the vessels, it is critical to design an efficient mobile edge computing (MEC) enabled network for maritime computation. Inspired by this motivation, energy harvesting space-air-sea integrated networks (EH-SASINs) for maritime computation tasks offloading are proposed in this paper. We first make the optimal deployment of tethered aerostats (TAs) with the K-means method. In addition, we study the issue of computation task offloading for vessels, focusing on minimizing the process delay of computation task based on the proposed architecture. Finally, because of the NP-hard properties of the optimization problem, we solve it in two stages and propose an improved water-filling algorithm based on queuing theory. Simulation results show that the proposed EH-SASINs and algorithms outperform the existing scenarios and can reduce about 50% of the latency compared with local computation.

A practical evaluation of correlation filter-based object trackers with new features

Visual object tracking is a critical problem in the field of computer vision. The visual object tracker methods can be divided into Correlation Filters (CF) and non-correlation filters trackers. The main advantage of CF-based trackers is that they have an accepted real-time tracking response. In this article, we will focus on CF-based trackers, due to their key role in online applications such as an Unmanned Aerial Vehicle (UAV), through two contributions. In the first contribution, we proposed a set of new video sequences to address two uncovered issues of the existing standard datasets. The first issue is to create two video sequence that is difficult to be tracked by a human being for the movement of the Amoeba under the microscope; these two proposed video sequences include a new feature that combined background clutter and occlusion features in a unique way; we called it hard-to-follow-by-human. The second issue is to increase the difficulty of the existing sequences by increasing the displacement of the tracked object. Then, we proposed a thorough, practical evaluation of eight CF-base trackers, with the top performance, on the existing sequence features such as out-of-view, background clutters, and fast motion. The evaluation utilized the well-known OTB-2013 dataset as well as the proposed video sequences. The overall assessment of the eight trackers on the standard evaluation metrics, e.g., precision and success rates, revealed that the Large Displacement Estimation of Similarity transformation (LDES) tracker is the best CF-based tracker among the trackers of comparison. On the contrary, with a deeper analysis, the results of the proposed video sequences show an average performance of the LDES tracker among the other trackers. The eight trackers failed to capture the moving objects in every frame of the proposed Amoeba movement video sequences while the same trackers managed to capture the object in almost every frame of the sequences of the standard dataset. These results outline the need to improve the CF-based object trackers to be able to process sequences with the proposed feature (i.e., hard-to-follow-by-human).

Lysosomal tracking with red-fluorescent solid lipid nanoparticles

Lysosomes are organelles with many functions in cell metabolism, the morphology changes as a function of the different cellular mechanisms. Some enzymes in the lysosomal medium are responsible for the cellular digestion process. This work reports a new biocompatible lysosome, the tracker, with the long-life fluorescence emission. They were investigated by steady-state, time-resolved spectroscopic, and confocal microscopy analysis in organic and biological mediums. It was observed that the probe could already be used at low concentrations to monitor lysosomes in live and fixed cell culture with selective fluorescence detection with high photostable spectroscopic. Therefore, a responsive emission in the red region of the light spectrum and the high fluorescence signal were observed even after 24 hours. The incubation time with highly selective lysosomal tracking and good response for long-time in vitro experiments, high solubility in a biological media, and reproducible signal response, with lower signal noise rates.

Mud pumping in high-speed railway: in-situ soil core test and full-scale model testing

Mud pumping induced by moving train loads on rainwater-intruded roadbed causes intensive track vibrations and threatens safety of high-speed trains. In this paper, a vehicle–track–subgrade finite element model was established to analyze the dynamic responses of a ballastless track, and results showed that the concrete base and roadbed were detached because of the whipping effect arising from the rainwater intrusion channel. An in-situ soil core test showed that the intruded rainwater accumulated in roadbed to form standing water and saturated the roadbed. The flapping action of the concrete base caused by the whipping effect led to mud formation mixed with fine particles and rainwater, which migrated upward under the pore-water pressure (PWP) gradient. Mud pumping resulted from continuous particle migration in the saturated roadbed under moving train loads: under normal roadbed condition, coarse and fine particles were uniformly distributed in the roadbed; in early period of mud pumping, fine particles migrated downward to bottom of the roadbed because of the rainwater infiltration flow; in middle stage of mud pumping, fine particles migrated upward and gathered at the roadbed surface under PWP gradient; in later period of mud pumping, fine particles were entrained and removed with the dissipation of excess PWP. Moreover, a full-scale physical model was established to reproduce mud pumping, and polyurethane injection remediation against mud pumping was validated on this physical model. The remediation method was applied to an in-situ mud pumping. The deviation of the vertical track profile reduced remarkably and remained at a low level within half a year, showing a good long-term service performance of the polyurethane remediated roadbed.

Different response of North Pacific storm tracks in the upper and lower troposphere to jet strength

The midwinter suppression of North Pacific storm tracks (NPSTs) reflects that the linear relationship between the NPST and baroclinicity breaks in winter. Based on the reanalysis data during the cold seasons of 1979–2019 and a tracking algorithm, this study analyzes the eddy growth process and shows that an enhanced upper-tropospheric jet favors the generation of upper-level eddies on the northeast side of the Pacific jet, but increasingly suppresses the generation of those in the Northwest Pacific. The upper-level eddies generated upstream of the jet core are unable to grow sufficiently throughout the whole cold season, and only those generated downstream of the jet core can grow normally and constitute the main body of the upper-level NPST. By contrast, the main lower-level eddy genesis area and growth area coincide with the baroclinic zone, with the genesis number and local growth rate increasing with the baroclinicity.摘要北太平洋风暴轴的深冬抑制表明风暴轴强度与斜压性之间的线性关系在冬季破裂. 本研究基于1979–2019年冷季的再分析数据和拉格朗日跟踪算法, 对比分析了高低层扰动的具体生长过程. 结果表明太平洋急流的增强有利于高层扰动在急流核东北侧产生, 但却抑制其在西北太平洋的生成. 在急流核上游产生的高层扰动在整个冷季都无法充分发展, 只有在急流核下游产生的高层扰动才能正常生长且它们是构成高层太平洋风暴轴的主体. 相比之下, 低层扰动的生成区和生长区都与斜压区重合, 并且它们的生成数量和局部增长率随着斜压性的增强而增强.

EV-miRome-wide profiling uncovers miR-320c for detecting metastatic colorectal cancer and monitoring the therapeutic response

PurposeMolecular composition of circulating small extracellular vesicles (EVs) does not merely reflect the cells of origin, but also is enriched in specific biomolecules directly associated with the cellular transformation. However, while most of the currently identified EV-miRs are only geared towards one-dimensional disease detection, their application for long-term tracking and treatment response monitoring has been largely elusive.MethodsWe established and optimized a rapid, sensitive and robust liquid biopsy sampling method, and further used small RNA sequencing to comprehensively catalogue EV-miRomes in association with the progression and outcome of metastatic colorectal cancer (mCRC).ResultsBy cross-comparison of EV-miRomes (n = 290) from multi-stage and longitudinal cohorts, we uncovered a 15-EV-miR signature with dual detection and long-term monitoring of tumor size progression for mCRC. From this panel, EV-miR-320c was uncovered as a strong clinical marker – aside from its diagnostic power and a therapeutic monitoring performance superior to carcinoembryonic antigen (CEA), its high expression has also been linked to lower overall survival and a greater likelihood of disease recurrence. Further, integrative analyses of tissue transcriptomic and liquid biopsy implicated this 15-EV-miR signature in programming the mesenchymal–epithelial transition (MET) for distant localization of the metastasized cells and also in creating a tumor-favoring metastatic niche.ConclusionOur clinically-oriented delineation of the mCRC-associated circulating EV-miRomes systematically revealed the functional significance of these liquid biopsy markers and further strengthen their translational potential in mCRC therapeutic monitoring.Graphical abstract

Impacts of wave feedbacks and planetary boundary layer parameterization schemes on air-sea coupled simulations: A case study for Typhoon Maria in 2018

Typhoon Maria was a devastating super typhoon hitting China in 2018. We conducted five numerical experiments based on the Coupled Ocean–Atmosphere–Wave–Sediment Transport model system to explore the sensitivity of typhoon track, intensity, structure, and oceanic response to the feedbacks of ocean surface waves (particular attention was paid to wave-induced sea surface roughness [SSR]), and different planetary boundary layer (PBL) parameterization schemes. The model results were in good agreement with observations. It was found that Typhoon Maria's intensity and structure, especially the distribution of air-sea interface heat flux and the shape of the typhoon centre, were highly sensitive to the feedbacks of waves, the choices of PBL and wave-induced SSR parameterization schemes. Previous model results based only on atmospheric models have shown that typhoon simulation accuracy is very sensitive to the parameterization scheme of PBL. In this study, it was revealed that the effect of wave feedbacks on typhoon simulation results could be comparable to that of using different PBL parameterization schemes. The wave feedbacks include the modification of the SSR and the additional cooling induced by wave-enhanced ocean mixing. From the sensitivity experiments, the former was the most dominant, and its main mechanism lies in the correction of the SSR to affect the exchange coefficients of momentum and heat fluxes at the air-sea interface and ultimately the typhoon simulation results. A systematic analysis of sea temperature response during typhoon was conducted, and the response showed small difference in different experiments. This suggests that the difference in typhoon intensity and structure among the experimental simulations is not significantly related to the difference in simulated sea surface temperature, but is most likely related to the difference in momentum and heat fluxes caused by wave feedbacks and the choices of PBL and wave-induced SSR parameterization schemes. The difference of significant wave height (SWH) in experiments with different wave-induced SSR parameterization schemes reached 10% (1.5 m). The typhoon-induced sea surface height (SSH) reached 2.4 m, and the difference of SSH caused by wave feedbacks, different PBL and wave-induced SSR parameterization schemes reached 12.5%, 12.5% and 8.3%, respectively. This study has significant implication for improving the simulation accuracy of typhoon track, intensity, structure, and disasters caused by typhoons.

Disrupted neural tracking of sound localization during non-rapid eye movement sleep

Spatial hearing in humans is a high-level auditory process that is crucial to rapid sound localization in the environment. Both neurophysiological models with animals and neuroimaging evidence from human subjects in the wakefulness stage suggest that the localization of auditory objects is mainly located in the posterior auditory cortex. However, whether this cognitive process is preserved during sleep remains unclear. To fill this research gap, we investigated the sleeping brain's capacity to identify sound locations by recording simultaneous electroencephalographic (EEG) and magnetoencephalographic (MEG) signals during wakefulness and non-rapid eye movement (NREM) sleep in human subjects. Using the frequency-tagging paradigm, the subjects were presented with a basic syllable sequence at 5 Hz and a location change that occurred every three syllables, resulting in a sound localization shift at 1.67 Hz. The EEG and MEG signals were used for sleep scoring and neural tracking analyses, respectively. Neural tracking responses at 5 Hz reflecting basic auditory processing were observed during both wakefulness and NREM sleep, although the responses during sleep were weaker than those during wakefulness. Cortical responses at 1.67 Hz, which correspond to the sound location change, were observed during wakefulness regardless of attention to the stimuli but vanished during NREM sleep. These results for the first time indicate that sleep preserves basic auditory processing but disrupts the higher-order brain function of sound localization.

Study on the Vertical Stiffness of Bridge Expansion Joints Based on the Vehicle-Track-Bridge Coupled Model

Bridge expansion joints (BEJs) are equipped at the girder end of long-span railway bridges to ensure the reliable transition of the track. BEJs should have suitable dynamic stiffness to ensure the running safety and stability of the vehicle. To explore the influence of dynamic vertical stiffness of BEJs on the dynamic response of vehicle, track, and bridge, a three-dimensional vehicle-track-bridge coupled model is established, and the influence of sleeper spacing and vehicle speed are taken into consideration. Taking a high-speed railway line in China as a case study, the dynamic response of the whole system is calculated. The results show that (1) the dynamic response of BEJs and the vehicle is affected by the vehicle speed and sleeper spacing. With the increase of vehicle speed and sleeper spacing, the dynamic response of the system increases; (2) the vertical stiffness of BEJs will affect the dynamic response of BEJs and the interaction between the wheel and rail: the vertical dynamic displacement of movable sleeper will exceed the limit if the vertical stiffness of pressure-bearing is insufficient, and the wheel unloading rate may exceed the limit if the vertical stiffness of the cushion plate is insufficient. Based on the results, the larger vertical stiffness of the cushion plate and pressure-bearing is recommended. These results have been applied to the design of BEJs on the studied railway line, which are in good service condition at present.

Low-Complexity Prescribed Performance Control for Unmanned Aerial Manipulator Robot System Under Model Uncertainty and Unknown Disturbances

This article presents a trajectory tracking control method for the unmanned aerial manipulator robot system (UAMRS) under model uncertainty and unknown disturbances. More specifically, a low-complexity prescribed performance controller is proposed to effectively reduce the design complexity and achieve the prescribed transient and steady-state performance. First, the dynamics model of the UAMRS is analyzed and modeled, where the unmeasured internal interaction generated by the coupling effect and the random environmental disturbances are considered simultaneously. Then, utilizing the property of prescribed performance, the UAMRS with model uncertainty and external disturbances can guarantee preferable trajectory tracking responses, where the nonlinear disturbance observer is used to estimate and compensate uncertainties and external disturbances. Moreover, the proposed controller defined by simple expressions does not require accurate knowledge of the UAMRS, which is of low complexity and can effectively reduce the amount of calculation. The stability of the proposed controller is analyzed. Finally, the performances of the proposed scheme are demonstrated by the numerical simulation comparisons and real-world experiments, where a quadrotor with a 3-DOF onboard active manipulator is adopted in outdoor experimental validations.

Digital Current Controller Design for SPMSM With Low Switching-to-Fundamental Frequency Ratios

High speed becomes an important development direction of permanent magnet synchronous machines (PMSM) for higher power density. However, with the reduction of the switching-to-fundamental frequency ratios (SFRs), the dynamic performance and robustness of the current controller deteriorate and even lead to instability. To address this issue, this article proposes a distinctive current controller designed directly in the discrete-time domain for PMSM, which combines two-degree-of-freedom internal model control (TDOF-IMC) with active damping. The salient feature of this controller is that from the point of directly assigning or optimizing the pole and zero coordinates, a distinctive current controller is designed. Specifically, the TDOF-IMC realizes the ability to arbitrarily arrange the pole–zero placement of the closed-loop transfer function, and, therefore, the current tracking response can be improved. The addition of active damping enhances the antidisturbance ability, and as a result, the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">dq</i> -axis current oscillations effectively at low SFR are getting weakened. On this basis, current control can achieve better dynamic response and robustness at the same time. Finally, simulation and experimental results validate the effectiveness of the proposed controller.

Stress-deformation analysis of rail substructure under moving wheel load

A three-dimensional (3D) finite element (FE) analysis is developed to study the effect of moving wheel load on the dynamic response of track with the key objective of determining the accurate stress-deformation response of the substructure. The 3D FEM model is first calibrated and then validated with two independent set of field measurements. The computed transient displacements and vertical stresses corroborate well with the field data from the selected case studies, endorsing the reliability of the current numerical model. The changes attributed to dynamic stress paths and the angle of principal stress rotation are also analysed with respect to the train speed in the range, 60–450 km/h. The results show some limitations of the existing dynamic amplification factor in relation to the design of railway track. This traditional approach will only be appropriate when the train speeds are relatively low, but it will not be accurate at significantly higher speeds at which significant principal stress rotation occurs, resulting in correspondingly increased shear stresses. The current FEM model enables a limiting train speed to be determined to prevent shear failure of the ballast layer when the dynamic response in relation to ballast properties is interpreted based on the proposed R-wave speed /critical track speed ratio.

Design and Validation of a Torque-Controllable Series Elastic Actuator-Based Hip Exoskeleton for Dynamic Locomotion

Abstract Series elastic actuators (SEAs) are increasingly popular in wearable robotics due to their high fidelity closed-loop torque control capability. Therefore, it has become increasingly important to characterize its performance when used in dynamic environments. However, the conventional design approach does not fully capture the complexity of the entire exoskeleton system. These limitations stem from identifying design criteria with inadequate biomechanics data, utilizing an off-the-shelf user interface, and applying a benchtop-based proportional-integral-derivative control for actual low-level torque tracking. While this approach shows decent actuator performance, it does not consider human factors such as the dynamic back-driving nature of human-exoskeleton systems as well as soft human tissue dampening during the load transfer. Using holistic design guidelines to improve the SEA-based exoskeleton performance during dynamic locomotion, our final system has an overall mass of 4.8 kg (SEA mass of 1.1 kg) and can provide a peak joint torque of 108 Nm with a maximum velocity of 5.2 rad/s. Additionally, we present a user state-based feedforward controller to further improve the low-level torque tracking for diverse walking conditions. Our study results provide future exoskeleton designers with a foundation to further improve SEA-based exoskeleton’s torque tracking response for maximizing human-exoskeleton performance during dynamic locomotion.

Hydraulic Robotic Leg for HYDROïD Robot: Modeling and Control

This paper presents a new hydraulic robotic leg for the humanoid hydraulic robot HYDROïD. The main parts of this leg are divided into two main parts; the knee subsystem and the ankle subsystem. The presented leg mechanism consists of 4 DOFs, all of which are operated using highly dynamic servo valves. The design of the leg is thoroughly presented and all of its parts are demonstrated. Moreover, the inverse kinematics for both sub-mechanisms are presented to be able to control the angular position of the leg joints. Also, a virtual dynamic model is introduced in which a position controller is applied to the model to regulate the actuating pistons, check the new structure, and analyze the position of the joints and their torques. To test the new leg experimentally, the new leg is assembled with the rest of the robot, and rapid prototyping software is used with a position controller. Experimental position tracking responses are introduced showing the validity of the new design and the implemented controller.

Closed-loop modulation of model parkinsonian beta oscillations based on CAR-fuzzy control algorithm.

Closed-loop deep brain stimulation (DBS) can apply on-demand stimulation based on the feedback signal (e.g. beta band oscillation), which is deemed to lower side effects of clinically used open-loop DBS. To facilitate the application of model-based closed-loop DBS in clinical, studies must consider state variations, e.g., variation of desired signal with different movement conditions and variation of model parameters with time. This paper proposes to use the controlled autoregressive (CAR)-fuzzy control algorithm to modulate the pathological beta band (13-35Hz) oscillation of a basal ganglia-cortex-thalamus model. The CAR model is used to identify the relationship between DBS frequency parameter and beta oscillation power. Then the error between the one-step-ahead predicted beta power of CAR model and the desired value is innovatively used as the input of fuzzy controller to calculate the next step stimulation frequency. Compared with 130Hz open-loop DBS, the proposed closed-loop DBS method could lower the mean stimulation frequency to 74.04Hz with similar beta oscillation suppression performance. The Mamdani fuzzy controller is selected because which could establish fuzzy controller rules according to human operation experience. Adding prediction module to closed-loop control improves the accuracy of fuzzy control, compared with proportional-integral control and fuzzy control, the proposed CAR-fuzzy control algorithm has higher tracking reliability, response speed and robustness.

Statistical learning in patients in the minimally conscious state.

When listening to speech, cortical activity can track mentally constructed linguistic units such as words, phrases, and sentences. Recent studies have also shown that the neural responses to mentally constructed linguistic units can predict the outcome of patients with disorders of consciousness (DoC). In healthy individuals, cortical tracking of linguistic units can be driven by both long-term linguistic knowledge and online learning of the transitional probability between syllables. Here, we investigated whether statistical learning could occur in patients in the minimally conscious state (MCS) and patients emerged from the MCS (EMCS) using electroencephalography (EEG). In Experiment 1, we presented to participants an isochronous sequence of syllables, which were composed of either 4 real disyllabic words or 4 reversed disyllabic words. An inter-trial phase coherence analysis revealed that the patient groups showed similar word tracking responses to real and reversed words. In Experiment 2, we presented trisyllabic artificial words that were defined by the transitional probability between words, and a significant word-rate EEG response was observed for MCS patients. These results suggested that statistical learning can occur with a minimal conscious level. The residual statistical learning ability in MCS patients could potentially be harnessed to induce neural plasticity.

Discrete‐time current regulator with arbitrary poles placement for alternating current machines

To pursue high-performance motor drive, the current regulators are designed directly in the discrete domain. However, few kinds of research are developed to achieve arbitrary poles placement simply. To fill this gap, the authors propose a discrete-time current regulator consisting of two parts: the main regulator used to obtain decoupling control of dq axes currents, and the bi-proper compensator applied to realise arbitrary poles placement. To strengthen the anti-disturbance ability of the current regulator, the active resistance is added to the inner feedback path. Combining the active resistance, a new zero-order-hold equivalent motor model is developed, based on which the main regulator is designed using the zero-pole cancellation method. Furthermore, in this way, decoupling control for the two control objectives of reference tracking and anti-disturbance is realised. To achieve fast tracking response and negligible overshoot, an easy-to-implement scheme that simplifies the tuning of the current regulator is proposed based on the arbitrary poles placement. Moreover, the current regulator can be treated as a two-degree-of-freedom controller with this scheme. Finally, the effectiveness and reliability of the proposed current regulator are validated by the simulation results and experimental results in an alternating current machine drive platform.

Predicting Food Intake from Food Reward and Biometric Responses to Food Cues in Adults with Normal Weight Using Machine Learning

BackgroundEating behaviors are determined by a complex interplay between behavioral and physiologic signaling occurring before, during, and after eating. ObjectivesThe aim was to explore how selected behavioral and physiologic variables separately and grouped together predicted intake of 8 different foods. MethodsOne hundred adults with normal weight performed a food preference task combined with biometric measurements (the Steno Biometric Food Preference Task) in the fasting state. The task measured food reward as well as biometric (eye tracking, electrodermal activity, and facial expressions) responses to images of foods varying in fat content and taste. Energy intake from an ad libitum buffet of the same 8 foods as assessed in the preference task was subsequently assessed. A mixed-effects random forest approach was applied to explore how individual and combined measures of food reward and biometric responses predicted energy intake of the 8 single foods. The performance of the different prediction models was compared with the predictions from a linear model including only an intercept (naïve model) using bootstrap cross-validation. ResultsParticipants had a median [IQR] intake of 369 kJ [126–472 kJ] per food. Combined or separate measures of food reward or biometric responses did not predict energy intake better than the naïve model. ConclusionsWe did not find that the reward or biometric responses to food cues assessed in a clinical setting were useful in predicting energy intake of single foods. However, this study provides a framework in the field of behavioral nutrition for applying machine learning with a focus on individual predictions. This is necessary on the road toward personalized nutrition and provides great potential for handling complex data with multiple variables.This trial was registered at clinicaltrials.gov as NCT03986619.