A5100623199- Computability, Logic, AI Algorithms
- Constraint Satisfaction and Optimization
- semigroups and automata theory
- Robotic Path Planning Algorithms
- Formal Methods in Verification
- Underwater Vehicles and Communication Systems
- Brain Tumor Detection and Classification
- Modular Robots and Swarm Intelligence
- Robotic Locomotion and Control
- Solar Radiation and Photovoltaics
- Manufacturing Process and Optimization
- E-commerce and Technology Innovations
- Web Data Mining and Analysis
- Medical Imaging and Analysis
- Organ Transplantation Techniques and Outcomes
- ECG Monitoring and Analysis
- Air Quality Monitoring and Forecasting
- Robotics and Sensor-Based Localization
- Optimization and Packing Problems
- Wind Energy Research and Development
- Parasites and Host Interactions
- Mathematical Biology Tumor Growth
- Additive Manufacturing Materials and Processes
- Recycling and Waste Management Techniques
- Environmental Changes in China
Renji Hospital
2024
Shanghai Jiao Tong University
2024
Georgia Institute of Technology
2024
Nio (China)
2024
Southwest Petroleum University
2023
Shandong University of Science and Technology
2023
Ministry of Industry and Information Technology
2022
Beijing Institute of Technology
2022
University of Toronto
2022
Sun Yat-sen University
2009-2022
Microplastics quantification and classification are demanding jobs to monitor microplastic pollution evaluate the potential health risks. In this paper, microplastics from daily supplies in diverse chemical compositions shapes imaged by scanning electron microscopy. It offers a greater depth finer details of at wider range magnification than visible light microscopy or digital camera, permits further composition analysis. However, it is labour-intensive manually extract micrographs,...
In this paper, target detection of car images in roads is performed based on the YOLOv8 model YOLO family models, which improves accuracy and generalisation task by combining multi-scale prediction, CSPNet structure optimisation techniques such as BoF BoS. The input contain five types vehicles Ambulance, Bus, Car, Motorcycle Truck, are analysed learnt to have a classification 75.4% 53.5% 55.1% 51.1% 42.5% Truck. Despite gap specific accuracy, can detect 100% road, demonstrating good...
The Ramsey problem R(3, k) seeks to determine the smallest value of n such that any red/blue edge coloring complete graph on vertices must either contain a blue triangle (3-clique) or red clique size k. Despite its significance, many previous computational results for as 8) and 9) lack formal verification. To address this issue, we use software MATHCHECK generate certificates problems (and symmetrically R(8, 3) R(9, 3)) by integrating Boolean satisfiability (SAT) solver with computer algebra...
Underwater spherical robots are good assistants for ocean exploration, where motion control algorithms play a vital role. Conventional cannot eliminate the coupling relationship between various directions, which will cause of directions to interfere with one other and significantly affect effect. This study proposes new decoupling algorithm based on robot attitude calculation an underwater designed offshore, shallow water, narrow terrain. The proposed method uses four fuzzy...
One of the fundamental results in quantum foundations is Kochen-Specker (KS) theorem, which states that any theory whose predictions agree with mechanics must be contextual, i.e., a observation cannot understood as revealing pre-existing value. The theorem hinges on existence mathematical object called KS vector system. While many systems are known, problem finding minimum system three dimensions (3D) has remained stubbornly open for over 55 years. To address problem, we present new...
This paper introduces AlphaMapleSAT, a novel Monte Carlo Tree Search (MCTS) based Cube-and-Conquer (CnC) SAT solving method aimed at efficiently challenging combinatorial problems. Despite the tremendous success of CnC solvers in variety hard problems, lookahead cubing techniques heart have not evolved much for many years. Part reason is sheer difficulty coming up with new that are both low-cost and effective partitioning input formulas into sub-formulas, such overall runtime minimized....
The Ramsey problem R(3,8) asks for the smallest n such that every red/blue coloring of complete graph on vertices must contain either a blue triangle or red 8-clique. We provide first certifiable proof = 28, automatically generated by combination Boolean satisfiability (SAT) solver and computer algebra system (CAS). This SAT+CAS is significantly faster than SAT-only approach. While was computationally solved McKay Min in 1992, it not verifiable proof. method we use our very general can be...
The problem of finding the minimum three-dimensional Kochen–Specker (KS) vector system, an important in quantum foundations, has remained open for over 55 years. We present a new method to address this based on combination Boolean satisfiability (SAT) solver and computer algebra system (CAS). Our approach improved lower bound size KS from 22 24. More importantly, we provide first computer-verifiable proof certificate with 41.6 TiB order 23. efficiency is due powerful SAT solvers CAS-based...
One of the fundamental results in quantum foundations is Kochen–Specker (KS) theorem, which states that any theory whose predictions agree with mechanics must be contextual, i.e., a observation cannot understood as revealing pre-existing value. The theorem hinges on existence mathematical object called KS vector system. While many systems are known, problem finding minimum system three dimensions (3D) has remained stubbornly open for over 55 years. To address problem, we present new...
In this paper, target detection of car images in roads is performed based on the YOLOv8 model YOLO family models, which improves accuracy and generalisation task by combining multi-scale prediction, CSPNet structure optimisation techniques such as BoF BoS. The input contain five types vehicles Ambulance, Bus, Car, Motorcycle Truck, are analysed learnt to have a classification 75.4% 53.5% 55.1% 51.1% 42.5% Truck. Despite gap specific accuracy, can detect 100% road, demonstrating good...
In this work, we propose a minimizing functional based on Mumford-Shah model, which provides model for image segmentation and smoothing. The paper analyzes the physical characteristics of related modified Poisson equation in local coordinates explains that diffusion behavioral is superior to isotropic essence. Thus our more suitable smoothing while simultaneously preserving edges than piecewise smooth (PSMS) noisy images with intensity inhomogeneities. finally applied wide variety denoising...
Autonomous driving has now made great strides thanks to artificial intelligence, and numerous advanced methods have been proposed for vehicle end target detection, including single sensor or multi detection methods. However, the complexity diversity of real traffic situations necessitate an examination how use these in road conditions. In this paper, we propose RMMDet, a road-side multitype multigroup system autonomous driving. We ROS-based virtual environment simulate real-world conditions,...
AI-driven drug design relies significantly on predicting molecular properties, which is a complex task. In current approaches, the most commonly used feature representations for training deep neural network models are based SMILES and graphs. While these methods concise efficient, they have limitations in capturing spatial information. Recently, researchers recognized importance of incorporating three-dimensional information structures into models. However, requires introduction additional...
In this paper, the abdominal tumor is a general term for tumors in kidney, liver and pancreas. Accurate segmentation of essential their treatment. However, varying shapes sizes organs result significant differences regions. Existing convolution neural networks (CNNs) can only accurately segment individual tumors, lacking sufficient generalizability. We aim to design network that achieve good results different tumors. To end, we present Spider-net which consists high-resolution multi-scale...