Researchers developed a rapid battery-capacity estimation method using early voltage response during the first discharge cycle. The approach extracts electrochemical signatures related to battery condition and enhances features to improve prediction accuracy, reducing testing time by over 80%.
Researchers proposed a model-based diagnostic framework for electric vertical take-off and landing aircraft battery systems, improving fault detection and isolation under demanding aviation conditions. The approach achieves high detection rates, even in concurrent-fault scenarios, making it suitable for certifying eVTOL systems.
Researchers propose a personalized longitudinal motion planning policy combining reinforcement learning and imitation learning for intelligent vehicles. The approach adapts driving style to target drivers while meeting performance requirements, promoting human-like behavior and increasing acceptance.
A novel active equalization scheme uses path planning to address cell inconsistency in battery packs, improving equalization speed, accuracy, and robustness. The approach combines flexible topology with graph-based energy-transfer modeling and adaptive battery grouping to reduce energy loss and improve overall pack performance.
The study developed a ferrocene-modified nanoscale COF-based sonodynamic platform that integrates ultrasound-triggered ROS generation with Fenton-like catalysis, ferroptosis induction, and immune microenvironment remodeling. This approach showed potent antitumor activity against primary breast tumors and bone metastasis.
A novel bioengineered platform enhances MSC potency through 3D culture and localized delivery, preserving therapeutic phenotype and boosting paracrine activity. The system demonstrates significant therapeutic outcomes in a murine ALI model, addressing unmet needs in ALI therapy.
A new humanoid robotic bioreactor delivers human-like multiaxial mechanical stimulation to engineered tendon constructs, enhancing cell alignment and mechanotransduction-related responses. This study shows that biomimetic multiaxial loading can reshape cellular mechanosensing and promote early tendon-related biological responses.
Researchers developed a hybrid BCI framework integrating frequency, phase, and spatial information to unlock full potential of visual spatiotemporal neural signals. The system achieved record-breaking performance with high-density EEG recording, expanding command set and reducing stimulus size.
Researchers developed an uncertainty-aware AI framework for predicting proton exchange membrane fuel cell degradation trends. The framework provides both point estimates and interval estimates with probability density information, improving the reliability of fuel-cell prognosis under realistic operating conditions.
Researchers have developed a fast prediction and suppression method for transient piston displacement overshoot in free piston Stirling generators. The new approach detects dangerous overshoot without relying on displacement sensors and suppresses the fault response early enough to maintain safe operation and continuous power delivery.
Researchers developed a dynamic range compression dual-domain attention network to tackle extreme exposure conditions in tunnels. The DRC-DFANet model optimizes global illumination coordination and local detail restoration, preserving fine details while adjusting brightness intelligently.
The integrated framework combines incremental capacity analysis with image feature transformation and a hybrid machine-learning pipeline to improve SOH estimation accuracy. It achieves an RMSE of 1.76% on the NASA dataset and shows robustness when operating conditions shift, suggesting better generalization across different datasets.
Researchers developed a predictive energy management framework for megawatt-class parallel hybrid-electric regional aircraft, showing improved environmental and operational performance. Simulation results show reduced fuel consumption, CO2 emissions, NOx emissions, and energy-specific air range.
Researchers have developed a multi-fidelity framework combining coupled degradation mechanisms with machine learning to predict battery lifespan. The framework addresses the challenge of making reliable forecasts before long-term aging data are available, enabling safer operation and better-informed decision-making.
Researchers developed a lightweight fault-diagnosis framework for high-speed train bogies using selective knowledge distillation-based domain adaptation. The approach improves cross-domain diagnostic accuracy by at least 2.1% while keeping the final model size to 28.5 kB.
Researchers developed a two-step diagnostic strategy to detect subtle abnormal behavior in lithium-ion batteries. The method combines Hellinger distance with an Inverse Markov Method to identify micro short circuits that can lead to serious safety failures and thermal runaway.
Researchers developed a three-dimensional electro-thermo-mechanical model to quantify the swelling force generated by lithium-ion batteries during charging. The model accurately identifies and quantifies swelling force, offering a new tool for improving battery safety.
Researchers developed a nonlinear galloping-driven triboelectric-electromagnetic hybrid generator to harvest low-speed wind energy. The system can work over a wide wind-speed range and produce enough power to support practical electronics.
A new soft multiaxial strain mapping interface combines with AI processing to capture complex throat muscle movements and decode silent speech. The system achieved 85.8% recognition accuracy for NATO phonetic words in controlled tests and real-world noisy environments.
RST2G automates tumor segmentation, reducing radiologist workload and improving accuracy. It captures complex tumor morphologies and boundaries, outperforming traditional methods in visual assessments.
Researchers from Sun Yat-sen University and TianQin Research Center propose a novel method for detecting Earth's free oscillations using the TianQin space-borne gravitational wave detector. Through numerical simulation and Bayesian parameter estimation, they demonstrate clear detection of seismic events with high signal-to-noise ratios...
This study introduces a novel method that couples buoyancy-driven convection with localized acoustic microstreaming to enhance macroscopic mixing and microscopic mass transfer. The results show significant advantages in high-viscosity media, including increased effective coverage area and mean flow velocity amplitude.
A new UAV perching system utilizes a magnetic tensegrity-enabled robotic gripper with an adaptive energy barrier, enabling low-power and stable aerial operations. The system demonstrates rapid closure and high holding capability, with improved performance on rough surfaces.
Burst stimulation effectively mitigates decline in turning response decay, preserving stable frequency-response relationship and improving closed-loop locomotion control. The proposed navigation system achieves reliable path following with a success rate of 73% and average tracking error of approximately 12 mm.
A new study uses swarm intelligence to optimize the integration of distributed generation and fast Electric Vehicle Charging Stations in power distribution networks. The approach reduces active power losses by up to 68% and enhances voltage profiles across the network.
A new fusion model combining CNN, GRU, and PF techniques achieves remarkable improvements in lithium-ion battery RUL prediction accuracy. This enhances safety and longevity in electric vehicles and grid applications.
Researchers developed an accurate detection approach for lithium plating in lithium-ion capacitors, enabling safe exploitation of their full potential. The study reveals that lithium plating initiates at a charging rate of 20 C and can be reversed under certain conditions, but above 50 C, irreversible 'dead' lithium accumulates.
The brain extracellular space plays a crucial role in molecular diffusion, metabolic waste clearance, and post-blood–brain barrier drug transport. Recent advances have improved ECS characterization, enabling its integration into studies of CNS disease mechanisms, therapeutic design, and regulatory evaluation.
The study introduces a domain generalization method for EEG that leverages domain-invariant features and data augmentation to improve cross-subject generalization and noise robustness. The model achieved state-of-the-art accuracy across three public datasets, demonstrating stability and strong noise robustness.
A robotic suction disc with a hybrid adhesion mechanism inspired by the lamprey has been developed, achieving impressive grip strength in both air and water. The device successfully lifted heavy loads and maintained its grip on rough surfaces, with effective adhesion time increased by up to 540% in water.
A novel framework uses multimodal large language models to predict ischemia and reperfusion risk, achieving high sensitivity and specificity in large-scale datasets. The system outperforms baseline models with a 4.8-9.5% relative improvement and maintains consistent performance across diverse subgroups.
A new EEG domain generalization method achieves state-of-the-art accuracy across three public datasets, outperforming baseline methods in noise robustness. The model uses domain-invariant feature and data augmentation to enhance cross-subject generalization, demonstrating robust solutions for BCI technology applications.
The SimTac simulator accurately models biomorphic sensors using particle-based deformation, light-field rendering, and neural network prediction. It achieves high performance in optical and mechanical response accuracy, adaptability to diverse morphologies, and simulation efficiency.
A groundbreaking system repurposes a vehicle's taillight as an LED matrix transmitter to enable data transmission between vehicles in platoons. The approach eliminates the need for roadside units or photodetectors, offering a secure and low-cost solution for V2V communication.
The EMG-driven EVF robot enhances both voluntary motor control and sensory feedback to the wrist and hand muscles, improving sensorimotor integration and restoring balanced motor control. Significant improvements were observed in Fugl-Meyer Assessment scores and Action Research Arm Test scores.
The Marker-GMformer model, a lightweight deep learning approach, accurately predicts lower limb biomechanics with high correlation coefficients (>0.97) and low RMSE values (1.95° for joint angles). It offers real-time inference suitable for applications requiring fast feedback, such as robotic control and monitoring.
The Beijing Institute of Technology Press Co., Ltd is recruiting young editorial board members who will contribute to the publication process and benefit from training and networking opportunities.
A new circular motion paradigm enables continuous decoding of hand motion angles using EEG signals and polar coordinates. The experiment showed excellent performance across six deep learning models, with the best model achieving a mean squared error of 1.012 rad².
The RDP-type actuator enhances bidirectional consistency and motion linearity due to its symmetric driving structure and constant contact force. It demonstrates excellent performance across low and high-frequency ranges, showing minimal speed fluctuation and strong load-bearing capacity.
This study identifies shared genetic variants linking schizophrenia with left- vs right-hemisphere white-matter tracts, revealing hemispheric asymmetry. Hemispheric specificity was observed in the left posterior thalamic radiation and tapetum, with higher proportions of shared loci.
Researchers developed a nanodelivery system that synergizes ferroptosis and STING activation to treat metastatic bladder cancer. The system showed robust tumor control and improved survival rates, with enhanced immune response and reduced metastasis.
The system uses a human-in-the-loop knot planner and three optimization metrics to ensure task reliability. It successfully completed real-world experiments, lifting heavy payloads in unstructured environments with high success rates.
The study investigates regional mechanical variability in porcine pia–arachnoid complex (PAC) using a region-by-region, multi-scale design. Regional differences in mechanical properties are linked to biochemical distributions via two-photon imaging and RNA-seq.
The review explores how multiplayer games, social robots, and virtual agents can advance artificial empathy in therapy and healthcare by embedding interpersonal interaction. It highlights the need for deeper, more seamless closed-loop interaction and emphasizes the importance of emotion recognition, trust, engagement, and rapport.
A new model predicts cerebral blood flow using carotid ultrasound and brain MRI data, enabling non-invasive monitoring of astronauts' cognitive function during long-duration spaceflight. The CatBoost algorithm outperforms other models, providing a practical solution for safeguarding brain health in space.
MMWs inhibit tumor growth by modulating immune proteins, reducing tumor cell membrane synthesis and energy metabolism. The therapy boosts anti-tumor immune responses, increasing infiltration of immune cells and reducing immunosuppressive populations.
Researchers develop an intelligent decision-making algorithm using functional Near-Infrared Spectroscopy (fNIRS) to analyze passengers' physiological states and enhance autonomous vehicle safety. The study shows improved safety, comfort, and convergence speed compared to traditional methods.
Researchers propose a theoretical model to analyze adhesion and escape phenomena during low-velocity impacts between charged dust particles and spacecraft. The study focuses on the interaction between charged particles and spacecraft within a plasma sheath, considering significant size differences.
Space: Science & Technology has been officially indexed in the Web of Science: Science Citation Index Expanded (SCIE) since December 8, 2025. The journal aims to promote innovation and breakthroughs in space science and technology.
Hybrid magneto-acoustic microrobots combine magnetic steering with acoustic propulsion for precise navigation and powerful locomotion. These robots enable targeted drug delivery, minimally invasive surgery, and medical imaging with high accuracy and efficiency.