A new review in AI & Materials highlights the transformative potential of machine learning (ML) in nuclear materials research. ML techniques are being used to analyze complex microstructures, predict thermal conductivity and mechanical behavior, optimize processing and fabrication, and integrate with physics-based models.
Researchers from Shandong Technology and Business University survey the latest AI-powered techniques to fill in missing traffic data gaps. The study categorizes and compares leading data imputation methods, offering a clear roadmap for researchers and city planners to improve traffic management and smart city operations.
The study combines decision making and machine learning to improve robot learning for water analysis. The Random Forest Classifier achieved an accuracy of 69% which improved to 73% after applying Synthetic Minority Over-sampling Technique (SMOTE) and tuning hyperparameters. The robotic system can detect, analyze, and distinguish drinki...
Researchers have created a novel method to culture living brain cells in Alzheimer's and Parkinson's disease, using affordable 'ring-inserts' that support high-quality tissue cultures and enable real-time imaging. This cost-effective approach reduces experimental costs by up to €3,500 while maintaining experimental quality.
The study assesses autonomous vehicle adaptability on small-radius circular curves, showing ride comfort degrades to
Researchers propose a novel control scheme to address challenges in traditional backstepping control designs and event-triggered control. The scheme significantly reduces communication bandwidth usage, offering a new approach for efficient control of complex industrial systems.
Researchers developed an advanced modeling framework to enhance point cloud quality in metro tunnel inspections using backpack SLAM LiDAR systems. Inspection speed and scan density emerged as crucial determinants of point cloud quality, with optimal operational conditions achieving high-quality data.
A new framework leverages automated 3D object segmentation and mesh reconstruction to simulate dynamic and realistic construction sites. The approach captures real-world scenes, extracts key objects, and reconstructs them into editable 3D meshes, enabling applications such as virtual safety walkthroughs and AI-driven layout planning.
Researchers explore emerging role of extracellular RNAs in cancer diagnosis, prognosis, and treatment. These natural nanocarriers can reflect tumor behavior in real time and deliver targeted therapies.
The research develops a comprehensive family assistant capable of performing various tasks like picking up toys and fetching items. The robot uses YOLOv11 object recognition and flexible gripper to recognize objects of varying sizes and weights with high accuracy.
Reinforcement learning world models are introduced as a promising tool for modeling complex atomic level changes in catalyst surfaces. The review presents advancements in using Dreamer-based architectures and multi-objective optimization strategies to address long-standing challenges in catalytic surface modeling.
Researchers developed a novel framework combining worker self-reports and expert evaluations to predict worker performance. The proposed SOM-BN model demonstrated high accuracy and specificity, outperforming traditional methods.
Researchers uncover significant tectonic transition from subduction-related magmatism to extensional back-arc basin magmatism in Wutai Complex. The study suggests plate tectonics began operating by the latest Neoarchean, challenging traditional views of stagnant-lid tectonics.
A novel method predicts the working status of high-formwork support systems using a combination of finite element model simulations, deep learning, and large language models. The framework achieves superior performance over existing methods and demonstrates potential applications in complex structures.
Researchers have uncovered evidence of anomalous radioactive decay in cobalt-57 under ultrasonic stimulation, supporting the Deformed Space-Time (DST) theory. The findings suggest energy-dependent space-time distortions that violate local Lorentz invariance, leading to a departure from conventional exponential decay laws.
This study investigates the cyclic bond behavior of FRP bars in concrete, analyzing key factors such as bar diameter and embedment length. A unified bond stress–slip constitutive model is developed to capture interfacial degradation mechanisms under cyclic loads.
Researchers developed a non-invasive method combining 3D laser scanning and sensor data analysis to detect subsurface structural defects in water treatment filters. This breakthrough significantly reduces inspection time and labor costs, ensuring safer and more efficient water processing.
Artificial intelligence is revolutionizing the design and synthesis of biofunctional materials for medical applications. Machine learning models can predict material properties with over 90% accuracy, enabling faster and more cost-effective discovery.
The study proposes an event-triggered asymptotic composite neural tracking control scheme for intelligent vehicles, addressing system nonlinearities and uncertainties. It enhances tracking precision and reduces communication traffic through variable threshold-based triggering conditions.
Researchers have developed a new high-performance image sensor that incorporates a built-in solar cell structure using pinned-surface double-junction photodiodes. This design improves light sensitivity and reduces image lag, making it suitable for applications such as AI smart robot vision chips.
The study reviews recent advances in heterogeneous aquatic robot systems, integrating robots to perform coordinated tasks in complex marine environments. Key findings include the development status of communication, sensing, navigation, control, decision-making, and energy management technologies.
Researchers developed FESGlove, a glove-based system using functional electrical stimulation to selectively activate individual fingers. The device offers high selectivity and precision, making it suitable for clinical rehabilitation and assistive applications.
A new study reveals that protein sequences associated with microbial communities in the human gut have uniquely low stoichiometric water content and undergo counterintuitive chemical shifts during inflammation. Microbial communities inhabit distinct chemical environments throughout the human body, influencing microbial evolution.
The review highlights gaps in research for remote sensing, land use, urban growth, and forecasting, as well as opportunities to focus on specific types of risk. A new tool using natural language processing enables more in-depth gap analysis, revealing areas like AI methods and Water Resources as major opportunities.
A study uses a probabilistic life cycle approach to evaluate the carbon emission intensity of magnesium silicate hydrate cement (MSHC), finding that its low-carbon characteristics vary depending on mix proportions and Mg/Si ratio. Machine learning techniques improve accuracy and provide reliable scientific evidence for the construction...
Research highlights the challenges of assessing inter-limb asymmetries, emphasizing the importance of task specificity, data quality, temporal trends, and context. A decision-making framework guides practitioners in interpreting asymmetries effectively.
Researchers discuss innovative approaches to improve quality of life for cervical cancer patients, exploring phytocannabinoids, anti-angiogenic drugs and peptide-based therapies. These strategies aim to reduce opioid side effects and target tumour growth and progression.
Researchers explored combining checkpoint blockade therapy with in situ vaccination to improve anti-tumor immunity in colorectal cancer. This innovative approach aims to mitigate adverse effects and enhance treatment effectiveness by targeting immune checkpoints and promoting tumor-specific T cell responses.
The Global Confidence Degree-based Graph Neural Network (GCD-GNN) framework improves financial fraud detection by integrating global confidence metrics with advanced graph learning techniques. It achieves record-breaking accuracy on real-world datasets, including a 97.26% AUC on T-Finance.
Researchers developed a knowledge-based intelligence method to predict and control segment floating by optimizing shield tail grouting parameters. The method achieved high prediction accuracy and optimized parameter configuration, reducing risks of engineering accidents.
This study investigates the vibrational spectroscopy of lead-free potassium sodium niobate and related perovskite ferroelectrics. Raman and Brillouin scattering spectroscopies are used to analyze the lattice dynamical properties, phase transitions, and physical properties of KNN single crystals and solid solutions.
Researchers develop a CNN-LSTM coupled deep learning model to predict the bond stress-slip constitutive relationship of grouted corrugated ducts. The model demonstrates reduced prediction errors and captures complex nonlinear interactions, achieving high consistency with experimental results.
Researchers explored CFRP-RC composites to overcome brittle failure and residual deformation in conventional shear walls. A refined size-effect correction model was proposed to address limitations in seismic performance prediction, paving the way for more resilient designs.
Researchers found that the Onsager reciprocity principle is violated in the cell model of an ion-exchange membrane. The violation occurs when gradients of external forces do not coincide with local gradients within the framework of linear thermodynamics.
The conference aims to facilitate interdisciplinary collaboration and promote academic-industry partnerships. Original research submissions are welcome across various fields of interest including electronics, communication systems, and intelligent science applications.
The conference aims to bridge theoretical advancements with practical applications in deep learning and computer vision. It offers opportunities for scholars to submit their work, focusing on areas like machine learning, convolutional neural networks, and computer vision.
SEGRE 2025 brings together researchers, engineers, and industry leaders to discuss cutting-edge ideas and practical applications in renewable energy and smart grid technologies. The conference focuses on bridging theoretical advancements with real-world challenges and opportunities.
Renewable Energy Communities (RECs) reduce inequality, foster trust, and empower citizens by turning energy infrastructures into platforms for social equity and ecological resilience. Policymakers must prioritize inclusive governance to ensure no community is left behind in the fight for a just energy transition.
A new study in Advanced Manufacturing shows how to make recycled plastic pretty again with custom colors using a free and open source software package called SpecOptiBlend. This breakthrough paves the way for economic distributed recycling of waste plastic into low-cost 3D printed products.
Researchers developed a back-analysis framework for deep excavation in soft soil combining BIM and ML algorithms. This approach improves computing speed and accuracy, providing safer construction management.
The study evaluated bee products as a potential dressing material for skin treatments, revealing high antioxidant and antibacterial activity. The results showed that different bioactive substances in the honey, pollen, and propolis added improved water retention capacity and wettability to thin films.
The study aims to enhance tactile displays for the Metaverse, reducing power supply size and enabling wearability. The developed system uses a small 12V boost power supply, multi-channel piezoelectric IC, and software for controlling haptic sensation in multiple gradations.
Researchers explore using tiny exosomes to deliver non-coding RNAs to macrophages, steering them toward the healing M2 state and promoting tissue regeneration. This approach offers a promising new way to treat ischemic diseases by addressing their root causes.
Researchers investigated the impact of plasma storage conditions on endogenous miRNA stability. They found that degradation rates can be affected by miRNA structure and packaging, as well as extraction methods.
AIE materials have shown potential in diagnosing and treating urinary cancers, kidney disease, and infections due to their high quantum yield, excellent optical properties, and environmental responsiveness. However, challenges remain regarding stability, biocompatibility, and synthesis costs.
The 2nd International Conference on Big Data and Data Mining (BDDM) aims to advance academic exchange and cooperation in big data and AI research. The conference will feature submissions on various topics, including big data analytics, artificial intelligence, and semantic web technologies.
The study reveals the association between microstructure and G/R during WAAM, resulting in a columnar cellular micro-structure and an extremely low coefficient of thermal expansion (CTE) of 0.265×10^−6 K^−1 from 20℃ to 100℃. The research offers insights into super-invar alloy components manufactured by WAAM, paving the way for better a...
Exosomal RNAs modulate key signaling pathways and influence tumor microenvironment, promoting metastasis and therapy resistance. Liquid biopsy through saliva and blood samples offers promising avenue for early diagnosis and treatment monitoring.
IoTCIT 2025 invites researchers to submit papers on various areas of interest, including communication and Internet of Things. The conference aims to provide a platform for scholars to exchange research results and establish new ideas.
The conference aims to bridge theoretical advancements with practical applications in AI and visual computing. Researchers can submit original research papers and attend keynote sessions, offering opportunities to network with pioneers in intelligent technologies.