Real-time State Research Articles

A parameter privacy-preserving strategy for mixed-autonomy platoon control

It has been demonstrated that leading cruise control (LCC) can improve the operation of mixed-autonomy platoons by allowing connected and automated vehicles (CAVs) to make longitudinal control decisions based on the information provided by surrounding vehicles. However, LCC generally requires surrounding human-driven vehicles (HDVs) to share their real-time states, which can be used by adversaries to infer drivers’ car-following behavior, potentially leading to financial losses or safety concerns. This paper aims to address such privacy concerns and protect the behavioral characteristics of HDVs by devising a parameter privacy-preserving approach for mixed-autonomy platoon control. First, we integrate a parameter privacy filter into LCC to protect sensitive car-following parameters. The privacy filter allows each vehicle to generate seemingly realistic pseudo states by distorting the true parameters to pseudo parameters, which can protect drivers’ privacy in behavioral parameters without significantly influencing the control performance. Second, to enhance the reliability and practicality of the privacy filter within LCC, we first introduce an individual-level parameter privacy preservation constraint to the privacy filter, focusing on the privacy level of each individual parameter pair. Subsequently, we extend the current approach to accommodate continuous parameter spaces through a neural network estimator. Third, analysis of head-to-tail string stability reveals the potential impact of privacy filters in degrading mixed traffic flow performance. Simulation shows that this approach can effectively trade off privacy and control performance in LCC. We further demonstrate the benefit of such an approach in networked systems, i.e., by applying the privacy filter to a preceding vehicle, one can also achieve a certain level of privacy for the following vehicle.

Enhancing driver attention and road safety through EEG-informed deep reinforcement learning and soft computing

This paper introduces a transformative edge computing-based approach for enhancing driver attention and road safety using EEG-driven deep reinforcement learning (DRL). As driver inattention remains a significant factor in accidents, real-time cognitive state monitoring enabled by in-vehicle edge devices offers new promise. Our method leverages EEG data collected from drivers using headsets, analyzing signals related to visual attention. Edge computing resources in the vehicle extract features and classify attention levels using Deep Q-Network (DQN) and Proximal Policy Optimization (PPO) models trained to approximate optimal driving decisions. A novel reward structure combining driving performance and attention guides the models. Our edge computing-powered framework reacts within critical time latencies to maximize attention through interventions adapting to the driving environment. Results demonstrate the effectiveness of this approach, with PPO agent on edge devices achieving high average rewards up to 489,752.4 and 99.3% reward as accuracy in classifying attention states, thereby significantly outperforming traditional methods. This underscores edge computing’s potential to enable real-time integration of neuroscience and AI, advancing road safety. The edge resources deliver time-critical analysis and adaptation, while connectivity to the fog and cloud allows optimizing and learning at scale across populations. This research pioneers a new epoch for road safety powered by edge intelligence.

Simultaneous modeling and adaptive fuzzy sliding mode control scheme for underactuated USV formation based on real-time sailing state data

Simultaneous modeling and adaptive fuzzy sliding mode control scheme for underactuated USV formation based on real-time sailing state data

Advanced Monitoring and Real-Time State of Temperature Prediction in Lithium-Ion Cells Under Abusive Discharge Conditions Using Data-Driven Modelling

Advanced Monitoring and Real-Time State of Temperature Prediction in Lithium-Ion Cells Under Abusive Discharge Conditions Using Data-Driven Modelling

Adaptive Traffic Signal Control Method Based on Offline Reinforcement Learning

The acceleration of urbanization has led to increasingly severe traffic congestion, creating an urgent need for effective traffic signal control strategies to improve road efficiency. This paper proposes an adaptive traffic signal control method based on offline reinforcement learning (Offline RL) to address the limitations of traditional fixed-time signal control methods. By monitoring key parameters such as real-time traffic flow and queue length, the proposed method dynamically adjusts signal phases and durations in response to rapidly changing traffic conditions. At the core of this research is the design of a model named SD3-Light, which leverages advanced offline reinforcement learning to predict the optimal signal phase sequences and their durations based on real-time intersection state features. Additionally, this paper constructs a comprehensive offline dataset, which enables the model to be trained without relying on real-time traffic data, thereby reducing costs and improving the model’s generalization ability. Experiments conducted on real-world traffic datasets demonstrate the effectiveness of the proposed method in reducing the average travel time. Comparisons with several existing methods highlight the clear advantages of our approach in enhancing traffic management efficiency.

SARM: A network State-Aware Adaptive Routing Mutation method for power IoT

With the rapid development of Power Internet of Things (PIoT), the application of Internet of Things technology in smart grids is becoming increasingly widespread, but it also enlarges the attack surface of the system. Against this backdrop, traditional defense methods are limited by the asymmetry of network attack and defense, which makes it difficult to effectively resist the ievolving sniffing attacks and link flooding attacks. In order to improve the security of PIoT, this paper proposes an Adaptive Route Mutation based on Network State Awareness (SARM). It generates a route mutation space using a path state matrix and optimizes the time complexity of mutation space generation with a backtracking method. Furthermore, the SARM can dynamically adjust the route mutation strategy according to the real-time network state to realize self-adaptive defense. In conclusion, SARM is evaluated through simulations conducted with Mininet. Compared to Random Routing Mutation (RRM), it enhances defense against Sniffing and Distributed Denial of Service attacks by approximately 30% and 35% respectively. Additionally, in various example topologies, SARM consistently outperforms RRM.

Real-time Facial State Recognition and Fatigue Analysis based on Deep Neural Networks

Real-time Facial State Recognition and Fatigue Analysis based on Deep Neural Networks

Application of Electroencephalography Sensors and Artificial Intelligence in Automated Language Teaching.

This study developed an automated language learning teaching assessment system based on electroencephalography (EEG) and differential language large models (LLMs), aimed at enhancing language instruction effectiveness by monitoring learners' cognitive states in real time and personalizing teaching content accordingly. Through detailed experimental design, the paper validated the system's application in various teaching tasks. The results indicate that the system exhibited high precision, recall, and accuracy in teaching effectiveness tests. Specifically, the method integrating differential LLMs with the EEG fusion module achieved a precision of 0.96, recall of 0.95, accuracy of 0.96, and an F1-score of 0.95, outperforming other automated teaching models. Additionally, ablation experiments further confirmed the critical role of the EEG fusion module in enhancing teaching quality and accuracy, providing valuable data support and theoretical basis for future improvements in teaching methods and system design.

Design and development of an ai-driven communication model for stimulating memory recall in patients with Alzheimer’s and other neurodegenerative diseases

This study presents the development and evaluation of an AI-driven communication tool designed to stimulate memory recall in patients with Alzheimer’s disease and other neurodegenerative disorders. The tool integrates machine learning algorithms, including Random Forest and Long Short-Term Memory (LSTM) networks, with mass communication theories to deliver personalized and adaptive communication strategies. The AI models were trained and tested on patient interaction data, enabling the tool to dynamically adjust its prompts based on real-time cognitive states. Performance metrics such as accuracy, precision, and AUC-ROC were used to assess model efficacy, with the Random Forest model achieving the highest performance across all metrics. Clinical trials demonstrated significant improvements in memory recall and emotional engagement in patients using the AI tool compared to standard cognitive stimulation therapy. Caregivers also reported higher satisfaction with the tool's usability and impact on patient interaction quality. These findings highlight the potential of AI-driven, personalized communication tools to revolutionize Alzheimer's care, offering scalable, adaptive interventions that improve cognitive and emotional health. Academically, this work advances the integration of AI and health communication, emphasizing culturally sensitive and patient-centered approaches. In healthcare, it presents a promising non-pharmacological intervention that can be easily scaled for widespread use, potentially reducing caregiver burden and improving patient outcomes.

Multi-UAVs task allocation method based on MPSO-SA-DQN

Multi-UAVs play an important role in the battlefield. Although many methods are proposed to solve the Multi-UAV task allocation, there still existing the problems of complex time constraints and uncertain solution space. The reason is that multi-UAVs usually face changing environmental factors. Aiming at solving such problem, this paper proposes a multi-UAV task assignment method based on Deep Q-based evolutionary reinforcement learning algorithms (MPSO-SA-DQN). Specifically, this method builds a multi-agent training framework based on the deep evolutionary reinforcement learning mechanism and SA-DQN. Its aim is to improve the global exploration and optimization capabilities of multi-agents. At the same time, the multi-dimensional particle swarm optimization algorithm is introduced to optimize the state space. Based on task priority mapping, the MPSO-SA-DQN algorithm framework is proposed. As a result, multi-agents can optimize the execution state in real time in the environment interaction. Besides, it also has the ability to reach optimal state and maximum reward. According to the characteristics of multi-UAV global task assignment, this paper designs a priority state space autoencoder strategy and global task feature. A multi-UAVs tasks allocation and iterative optimization method based on MPSO-SA-DQN algorithm is proposed, so as to continuously optimize the task allocation scheme. The simulation results show that the multi-UAV task allocation method based on MPSO-SA-DQN can effectively solve the problem of uncertainty in the optimal solution space of task allocation. At the same time, the algorithm achieves faster convergence result, and a good prospect of promotion in the field of UAV swarm cooperative task planning.

Nanofibrous metal oxide semiconductor for sensory face masks

Sensory face masks are designed to integrate sensors that monitor health metrics, such as breathing rate and body temperature, thereby providing continuous physiological data. However, current sensing materials are predominantly in film form. In this study, we report on the use of fibrous amorphous indium gallium zinc oxide, which offers an enlarged surface area to facilitate gas diffusion and transport into charge-carrying sites. A detailed morphological analysis and an electrical investigation of this fibrous network were conducted. By integrating this material with a wireless, miniaturised flexible circuit and mounting it on a face mask, we successfully monitored different human respiratory states in real time. This wearable face mask demonstrates the potential for promising applications in health monitoring.

Research on scenario extrapolation and emergency decision-making for fire and explosion accidents at university laboratories based on BN-CBR

To solve the problems of suddenness, uncertainty and untimely emergency decision-making related to fire and explosion accidents in university laboratories, a combined method of BN and CBR is introduced to analyze laboratory accidents. By summarizing the characteristics of 72 accident cases worldwide, four scenario elements with key roles are extracted by combining the public safety triangle theoretical model; a BN is established from the macro perspective, which is based on the construction of dynamic scenarios; the evolution path is analyzed via BN theory; and the probability of occurrence of accidents is quantified from the microscopic perspective, with a focus on the analysis of the accidental evolution process. A case similarity calculation is carried out via CBR, and the construction of a BN-CBR-assisted decision-making model is completed, verified and corrected in an case study. The results show that the BN-CBR model can quickly determine the accident evolution path and the most similar historical cases, and its quantitative probability calculation enables one to comprehensively grasp the real-time state of the whole accident and the emergency response in a timely manner, which provides a new way to approach emergency decision-making of accidents.

Design of an Improved Model for Spectrum Sharing and Resource Management Using Deep Q-Network, Federated Averaging, and Ant Colony Optimization

Indeed, the ever-evolving wireless communication requires DSS and resource management for effectiveness. The old methods of spectrum allocation have a strategic shortfall since they are static and thus not adapted to real-time network conditions. Besides, more important challenges include issues over privacy and inefficiency of resource utilization. In the light of such problems, this paper proposes a new method by bringing together three deep-learning techniques, which are Deep Q-Networks, Federated Averaging, and Ant Colony Optimisation. Each is chosen because of its various competencies and complementary capabilities. First, DQN is chosen because it has the capability to handle high-dimensional action space. DQN applies deep learning to approximate the Q Value function, which provides the optimal decision of spectrum allocation based on real-time network states, such as spectrum usage and interference levels. With this scheme, up to a 20% gain in network throughput and up to a 15% cut in wasted spectrum compared to traditional methods are achievable. The second component FedAvg tackles the model training collaboration issue with privacy. It enables FedAvg for privacy-preserving resource management, where multiple devices update the global model collaboratively by communicating model updates without exchanging raw data samples. For this approach, the resulting method leads to a further increase in data privacy by reducing data leakage as high as 40%, with an improvement in resource management accuracy of up to 15%. ACO was employed to optimize resource allocation and improve spectrum efficiency. ACO emulates the natural foraging behavior of ants to solve combinatorial optimization problems. Consequently, it has led to up to 25% increase in spectral efficiency and up to 20% improvement in resource allocation balance sets. All these methods put together will provide a wholesome solution that not only optimizes spectrum and resource management but also promises privacy and adaptability. This represents severe improvement in overcoming the weaknesses of the existing approaches and will provide a strong foundation for next-generation wireless networks.

Intelligent vibration control of tensile cable based on deep reinforcement learning

Vibration of tensile cables commonly occurs in the engineering structures such as cable-stayed bridges, which may have negative effect on the driving comfort and safety, and further lead to the fatigue problems of the structure. This paper proposes a semi-active control strategy based on deep reinforcement learning and magneto-rheological (MR) damper, for the vibration control of tensile cables, and the corresponding algorithm have been developed. Through the interaction with the cable-damper system, the intelligent agent can evaluate every possible control parameter and achieve an effective control policy. Then, according to the real-time vibration state, the agent would determine an action current for the MR damper and thus change the damping coefficient of the damper, further make influences on the vibrating cable. Basically, the proposed strategy realizes the model-free semi-active control of cable vibrations. To validate the effectiveness of the proposed semi-active control strategy, a scale model test has been conducted, where the test cases of passive and semi-active control strategies are carried out and compared. Results show that, the semi-active control shows a prior performance in vibration reduction compared to the passive control strategy, with regard to the vibration profile, the vibration energy, as well as the energy dissipation of MR damper.

One-shot entorhinal maps enable flexible navigation in novel environments.

Animals must navigate changing environments to find food, shelter or mates. In mammals, grid cells in the medial entorhinal cortex construct a neural spatial map of the external environment1-5. However, how grid cell firing patterns rapidly adapt to novel or changing environmental features on a timescale relevant to behaviour remains unknown. Here, by recording over 15,000 grid cells in mice navigating virtual environments, we tracked the real-time state of the grid cell network. This allowed us to observe and predict how altering environmental features influenced grid cell firing patterns on a nearly instantaneous timescale. We found evidence that visual landmarks provide inputs to fixed points in the grid cell network. This resulted in stable grid cell firing patterns in novel and altered environments after a single exposure. Fixed visual landmark inputs also influenced the grid cell network such that altering landmarks induced distortions in grid cell firing patterns. Such distortions could be predicted by a computational model with a fixed landmark to grid cell network architecture. Finally, a medial entorhinal cortex-dependent task revealed that although grid cell firing patterns are distorted by landmark changes, behaviour can adapt via a downstream region implementing behavioural timescale synaptic plasticity6. Overall, our findings reveal how the navigational system of the brain constructs spatial maps that balance rapidity and accuracy. Fixed connections between landmarks and grid cells enable the brain to quickly generate stable spatial maps, essential for navigation in novel or changing environments. Conversely, plasticity in regions downstream from grid cells allows the spatial maps of the brain to more accurately mirror the external spatial environment. More generally, these findings raise the possibility of a broader neural principle: by allocating fixed and plastic connectivity across different networks, the brain can solve problems requiring both rapidity and representational accuracy.

Design and Development of an Immersive Virtual Reality Serious Game With Biofeedback for Physiological Regulation: Alice, Beyond Reality

The adolescence period is characterized by significant changes in individuals' lives, which can lead to various emotional and behavioural problems. Therefore, it is important for young adults to have tools for self-regulation, understanding, and controlling their physiological symptoms. Integrating these tools as gamified elements into new technologies is a way to engage a younger audience. In recent years, the effectiveness of immersive Virtual Reality has been repeatedly demonstrated in fields such as Psychology and Education. The combination of this technology with biosensors enables individuals to be aware of their real-time physiological states. This physiological monitoring can lead to adaptations in applications based on the individual's emotional state, for example. This work describes the design and development of an immersive Virtual Reality game whose main interaction is through biofeedback. The game is called "Alice, Beyond Reality", and its objective is to help young adults learn to self-regulate their physiological responses. The game draws inspiration from the well-known story of "Alice in Wonderland". In this story, the Queen of Hearts has transformed all the characters into cards, and the players must help them escape before it's too late. To achieve this, the players are guided by the White Rabbit through different levels where interaction through physiology is key. For instance, the players must learn to increase and decrease their heart rate to solve puzzles that allow them to progress to the next level. Throughout the game, gamification elements such as points, progressive difficulty, and various challenges are included to motivate the players to continue advancing in the game. Through the biofeedback system, the players become aware of their physiological changes to control them voluntarily. In the final screen, the players are shown their progression throughout the game so they can recognize their evolution. In the near future, an initial validation with users will be conducted to assess the usability and functionality of the game.

PB-Trajectron: Physics bounded neural network for generalized trajectory prediction

Vehicle trajectory prediction is a critical technology in autonomous driving systems, as the quality of prediction directly affects downstream path planning and vehicle control. Although recent studies have shown that models combining kinematic rules with data-driven methods exhibit better interpretability in trajectory prediction, these models often adopt fixed constraint strengths, limiting their generalization ability in diverse traffic scenarios. This fixed constraint strength design restricts the model’s adaptability to different traffic environments.To address this issue, we propose PB-Trajectron, a dynamic integration mechanism that enhances the model’s prediction performance and generalization capability. PB-Trajectron is a dynamic integration mechanism that combines vehicle kinematic rules with deep learning prediction models for generalized vehicle trajectory prediction. The model integrates physics-based motion models and Deep Neural Networks (DNNs) to provide reasonable physical explanations for predicting vehicle trajectories at different speeds. First, we establish two vehicle kinematic constraints applicable to different prediction scenarios, enabling the agent to switch between these constraints based on the causal relationships between vehicle motion states to avoid generating non-physical trajectory results. Second, we propose a kinematic constraint decision framework based on velocity thresholds, which demonstrates adaptive adjustment, allowing the agent to switch tasks according to real-time state conditions and adaptively adjust the contribution of different physical constraints based on actual vehicle speeds. Finally, we investigate the advantages of PB-Trajectron in Out-of-Domain(OOD) generalization.Cross-scenario experiments on the nuScenes dataset show that, compared to previous methods, PB-Trajectron reduces the final displacement error by 7.69% when the prediction step length is 4. Furthermore, out-of-domain generalization tests on the INTERACTION dataset demonstrate that PB-Trajectron achieves a 12.23% reduction in average prediction error on datasets from different countries and scenarios compared to previous methods. The proposed mechanism can better adapt to complex and diverse traffic scenarios, laying the foundation for explainable and robust autonomous driving systems.

ASLAM-FD: a multi-sensor adaptive collaborative fusion SLAM framework based on degradation detection and deep reinforcement learning

Abstract Aiming at the difficulty in ensuring accuracy and performance of existing Simultaneous Localization And Mapping (SLAM) technology based on multi-sensor fusion in complex dynamic environments, a multi-sensor adaptive fusion SLAM framework based on degradation detection and deep reinforcement learning (ASLAM-FD) is proposed. This framework can achieve adaptive collaborative precise adjustment of fusion weights (FWs) based on the real-time self-degradation states and relative degradation states quantified by each sensor, and can adapt to different tightly coupled SLAM algorithms based on FWs. In addition, within this framework, the continuous quantification models for the degradation states of internal/external sensors with certain versatility (we refer to them as EX-DM and IN-DM) is proposed. These quantitative models can achieve continuous quantification of degradation states of various mainstream internal/external sensors. Based on the above sensor degradation state quantification models, this paper further proposes a deep reinforcement learning (DRL) network suitable for adaptive collaborative adjustment of FWs. This network focuses more on the temporal nature of sensor observation data and degradation states, making it more suitable for modeling relationships between data with temporal features. In the experimental section, we adapted the proposed ASLAM-FD to different multi-sensor fusion SLAM algorithms on multiple datasets, and compared it with multiple advanced fusion SLAM algorithms. We found that adapting ASLAM-FD can effectively improve the accuracy and performance of fusion SLAM in complex dynamic environments.

Multifunctional Human-Computer Interaction System Based on Deep Learning-Assisted Strain Sensing Array.

Continuous and reliable monitoring of gait is crucial for health monitoring, such as postoperative recovery of bone joint surgery and early diagnosis of disease. However, existing gait analysis systems often suffer from large volumes and the requirement of special space for setting motion capture systems, limiting their application in daily life. Here, we develop an intelligent gait monitoring and analysis prediction system based on flexible piezoelectric sensors and deep learning neural networks with high sensitivity (241.29 mV/N), quick response (66 ms loading, 87 ms recovery), and excellent stability (R2 = 0.9946). The theoretical simulations and experiments confirm that the sensor provides exceptional signal feedback, which can easily acquire accurate gait data when fitted to shoe soles. By integrating high-quality gait data with a custom-built deep learning model, the system can detect and infer human motion states in real time (the recognition accuracy reaches 94.7%). To further validate the sensor's application in real life, we constructed a flexible wearable recognition system with human-computer interaction interface and a simple operation process for long-term and continuous tracking of athletes' gait, potentially aiding personalized health management, early detection of disease, and remote medical care.

A dynamic migration route planning optimization strategy based on real-time energy state observation considering flexibility and energy efficiency of thermal power unit

New energy resources compromising intermittent and fluctuating natures have been integrated into the power grid on a large scale, and thermal power units are obliged to promote the depth of deep peak shaving and flexible response-ability to cope with this new scenario. The safety, flexibility, and high efficiency of coal-fired units are the ultimate goals of its transformation, and there is a mutual influence and mutual restriction relationship among these indicators. To exploit the flexibility of thermal power units, take into account efficiency and safety, and play a supporting role in the new power system, a control strategy that weighs various indicators needs to be developed. Based on heat flow model and dynamic state space model, and updated matrix in real time, the key process parameters affecting the flexibility of heat transfer can be fully characterized. By using the observed state and calculation, the load response index and the energy efficiency index are optimized under the boundary constraint. The results show that the multi-objective optimization methods can avoid over regulation, reduce the flue gas flow by 3.23%–3.59%, and reduce the fluctuation of state quantity under the premise of satisfying the load response rate, about 2.32%–2.52% away from the safety boundary of the design temperature parameter to achieve the flexibility of frequency modulation, high efficiency of energy transmission and operation safety.