Continuous measurement of stress levels in naturalistic settings using heart rate variability: An experience-sampling study driving a machine learning approach

<p class="Abstract"><span id="page629R_mcid43" class="markedContent"><span dir="ltr">Developing automatic methods to measure psychological stress in everyday life has become an important research challenge. Here, we describe the design and implementation of a personalized mobile system for the detection of psychological stress episodes based on Heart-Rate Variability (HRV) indices. The system’s architecture consists of three main modules: a mobile acquisition module; an analysis-decision module; and a visualization-reporting module. Once the stress level is calculated by the mobile system, the visualization-reporting module of the mobile application displays the current stress level of the user. We carried out an experience-sampling study, involving 15 participants, monitored longitudinally, for a total of 561 ECG analyzed, to select the HRV features which best correlate with self-reported stress levels. Drawing on these results, a personalized classification system is able to automatically detect stress events from those HRV features, after a training phase in which the system learns from the subjective responses given by the user. Finally, the performance of the classification task was evaluated on the empirical dataset using the leave one out cross-validation process. Preliminary findings suggest that incorporating self-reported psychological data in the system’s knowledge base allows for a more accurate and personalized definition of the stress response measured by HRV indices.</span></span></p>

Assessment and Feedback Control of Paving Quality of Earth-Rock Dam Based on OODA Loop

Paving thickness and evenness are two key factors that affect the paving operation quality of earth-rock dams. However, in the recent study, both of the key factors characterising the paving quality were measured using finite point random sampling, which resulted in subjectivity in the detection and a lag in the feedback control. At the same time, the on-site control of the paving operation quality based on experience results in a poor and unreliable paving quality. To address the above issues, in this study, a novel assessment and feedback control framework for the paving operation quality based on the observe–orient–decide–act (OODA) loop is presented. First, in the observation module, a cellular automaton is used to convert the location of the bulldozer obtained by monitoring devices into the paving thickness of the levelling layer. Second, in the orient module, the learning automaton is used to update the state of the corresponding and surrounding cells. Third, in the decision module, an overall path planning method is developed to realise feedback control of the paving thickness and evenness. Finally, in the act module, the paving thickness and evenness of the entire work unit are calculated and compared to their control thresholds to determine whether to proceed with the next OODA loop. The experiments show that the proposed method can maintain the paving thickness less than the designed standard value and effectively prevent the occurrence of ultra-thick or ultra-thin phenomena. Furthermore, the paving evenness is improved by 21.5% as compared to that obtained with the conventional paving quality control method. The framework of the paving quality assessment and feedback control proposed in this paper has extensive popularisation and application value for the same paving construction scene.

Policy-based monocular vision autonomous quadrotor obstacle avoidance method

Aiming at the obstacle avoidance control problem of small quadrotor, a method of quadrotor obstacle avoidance based on reinforcement learning is proposed. The proposed method can make training converge quickly and has good environmental robustness. The proposed methods include: (1) a framework adopts perception module and decision module to improve the generalization ability of the obstacle avoidance model; (2) An Actor-Critic framework-based Proximal Policy Optimization (PPO) algorithm to provide quadrotor with policy-based decision-making capabilities; The experimental simulation results show that the strategy-based framework converges quickly and has a high success rate, the training time is much lower than that of the value-based framework. The monocular vision observation ability is limited, which leads to deviations between local observation and global state, So LSTM layer is usually added to increase model performance. Policy -based decision can have a good obstacle avoidance effect without adding the LSTM layer, and have good generalization ability after short relearning after changing.

Towards an integrated decision-support system for sustainable organic waste management (optim-O)

Biomethanation projects across the world struggle with multiple challenges related to the location selection and optimization of the treatment facilities. Important aspects such as treatment plant location and treatment process chain configuration depend on the waste sources to be treated, the required end-product type and quality, as well as its final use destination, all of which are variable in time and space. This research describes the development and use of an integrated decision-support software tool that allows setting up optimal organic waste value chains, named optim-O. Key features of the tool include a multidimensional spatiotemporal database, a model-based decision module for simulation and optimization, as well as a user-friendly interface. The availability of such a software tool will not only allow to save time and money on data collection and calculations, but will also induce more comprehensive decisions by simultaneously taking into account a variety of factors, thereby significantly facilitating and enhancing the decision-making process.

Self-adaptive Intrusion Detection System for UAV-to-UAV Communications in UAV Networks

Unmanned aerial vehicles (UAVs) have recently attracted many researchers' attention because of their extensive applications. Security issues, in particular, are a serious concern in such networks since the top-secret information exchanged between UAVs is susceptible to various attacks such as Sybil, blackhole, and Flooding attacks. To identify such malicious UAVs that threaten the connections between normal UAVs, we introduce an impermeability method called SID-UAV that works at the level of UAV-to-UAV. The SID-UAV method, by employing a self-adaptive system, discovers the most reliable route from origin to destination. This approach deals with finding the malicious UAV and selecting the most reliable routes in several phases, including the route discovery phase, the decision-making phase, the attacker counter phase, and the knowledge database phase by using multi-module methods and applying Human Immune System (HIS). In the SID-UAV method, three main modules are intended: route analysis module, decision module, and defense module. Each of these modules has sub-modules and is distributed in different parts in UAV networks. Each module and its sub-modules have tasks, and all of these modules are connected to the knowledge base to record information in it and use the stored information quickly. The NS-3 simulator tool is exploited to simulate the proposed method. The results gained from simulation indicated that the SID-UAV method in criteria of Average Detection Ratio (ADR), Average Packet Delivery Ratio (APDR), Average Packet Lost Ratio (APLR), Average False Positive (AFP), Average False Negative (AFN) have acceptable performance relative to BRUIDS, SFA, and SUAS-HIS methods.

Predictive Motion Planning for Autonomous Vehicles With Geometric Constraints via Convex Optimization

In this paper, we propose an MPC-based motion planning algorithm, including a decision-making module, an obstacle-constraints generating module, and an MPC-based planning module. The designed decision module effectively distinguishes between structured and unstructured roads and processes them separately, so that the algorithm is more robust in different environments. Besides, the movement of obstacles is considered in the decision-making and obstacle constraints generating module. By processing obstacles with lateral and longitudinal speed separately, obstacle avoidance can be done in scenarios with moving obstacles, including moving obstacles crossing the road. Instead of treating the vehicle as a mass point, we explicitly consider the geometric constraints by modeling the vehicle as three intersecting circles when generating obstacle constraints. This ensures that the vehicle is collision-free in motion planning, especially when the vehicle turns. For non-convex obstacle constraints, we propose an algorithm that generates up to two alternative linear constraints to convexify the obstacle constraints for improving computational efficiency. In MPC, we consider the vehicle kino-dynamic constraints and two generated linear constraints. Therefore, the proposed method can achieve better real-time performance and can be applied to more complicated traffic scenarios with moving obstacles. Simulation results in three different scenarios show that motion planning can achieve satisfactory performance in both structured and unstructured roads with moving obstacles.

Longitudinal and lateral dynamics control of automatic lane change system

The urgency of extending functionalities of current advanced driver assistance systems (ADAS), and eventually progressing to highly automated highway driving necessitates the design of automatic lane change system. This paper presents an automatic lane change system targeting on discretional lane change scenario in highway driving. Assuming motion signals of all participants to be available, the MOBIL model is employed as the decision module. The functionality of the adaptive cruise controller is extended to realize dual-target tracking, so as to prevent abrupt acceleration change provoked by the sudden switch of the leading vehicle during the lane change. For the lateral part, a hierarchical trajectory planning algorithm, which combines parametric function and learning-based technique, is proposed to account for uncertainties of driver characteristics in different traffic situations. The trajectory is then tracked by a low-level controller based on model predictive control (MPC) theory, which employs a force input model to predict the motion of the vehicle, and formulates environment envelope and handling limits as constraints. The proposed algorithm is validated through simulations of typical scenarios. Overall, this paper lays a solid foundation for the prototype of ADAS regarding lane change.

Sensor Information Fusion by Integrated AI to Control Public Emotion in a Cyber-Physical Environment

The cyber-physical system (CPS) is a next-generation smart system that combines computing with physical space. It has been applied in various fields because the uncertainty of the physical world can be ideally controlled using cyber technology. In terms of environmental control, studies have been conducted to enhance the effectiveness of the service by inducing ideal emotions in the service space. This paper proposes a CPS control system for inducing emotion based on multiple sensors. The CPS can expand the constrained environmental sensors of the physical space variously by combining the virtual space with the physical space. The cyber space is constructed in a Unity 3D space that can be experienced through virtual reality devices. We collect the temperature, humidity, dust concentration, and current emotion in the physical space as an environmental control elements, and the control illumination, color temperature, video, sound and volume in the cyber space. The proposed system consists of an emotion prediction module using modular Bayesian networks and an optimal stimulus decision module for deriving the predicted emotion to the target emotion based on utility theory and reinforcement learning. To verify the system, the performance is evaluated using the data collected from real situations.

HYBRID DECIDING MODULES WITH VIRTUAL STREAMS FOR CLASSIFICATION AND PREDICTION OF FUNCTIONAL STATE OF COMPLEX SYSTEMS

The problem reviewed of building intelligent decision support systems for classification and prediction of the functional state of complex systems in the article. To predict the state of complex systems, hybrid decision modules with virtual flows are proposed, which reflect the hidden system connections between real and virtual data. The vector of informative features at the input of the hybrid decision module consists of two subsectors, the first of which corresponds to real flows, and the second - to virtual flows. Simulation modeling of classification processes using latent variables was performed, which allowed to evaluate the effect on the quality of classification of artificially introduced virtual flows. The structure of a neural network model with virtual recurrent-type streams is developed. The structure consists of N consecutively included neural network approximants. The outputs of the previous approximators are combined with the vector of in-formative attributes of the subsequent approximators, which allows forming virtual flows of different dimensions. A method is developed for the formation of non-linear models of virtual flows, characterized by the use of the GMDH-simulation method to obtain models of the influence of real flows on virtual flows, learned through nonlinear adalines. The method makes it possible to form a subvector of latent variables of unlimited dimension. Non-linear models of virtual flows are formed through a method based on the use of GMDH modeling. The method makes it possible to obtain neural network structures built on the basis of GMDH models and nonlinear adalines, which make it possible to form a subvector of latent variables of unlimited dimensionality.