A5039743074- Electric and Hybrid Vehicle Technologies
- Electric Vehicles and Infrastructure
- Retinal Imaging and Analysis
- Advanced Battery Technologies Research
- Vehicle emissions and performance
- Glaucoma and retinal disorders
- Retinal and Optic Conditions
- Traffic control and management
- Retinal Diseases and Treatments
- Autonomous Vehicle Technology and Safety
- Vehicle Dynamics and Control Systems
- Traffic Prediction and Management Techniques
- Machine Learning and ELM
- Real-time simulation and control systems
- Child Nutrition and Water Access
- Birth, Development, and Health
- Neural Networks and Applications
- Advanced Sensor and Control Systems
- Hydraulic and Pneumatic Systems
- Industrial Technology and Control Systems
- Transportation Planning and Optimization
- Transportation and Mobility Innovations
- Marine Ecology and Invasive Species
- Parasite Biology and Host Interactions
- Constructed Wetlands for Wastewater Treatment
Jilin University
2014-2025
Suzhou Vocational University
2025
Jiangnan University
2023-2024
Fujian Medical University
2018-2024
Yunnan University
2024
Innovation Team (China)
2024
Fuzhou Maternity and Child Health Care Hospital
2024
Nanchang University
2024
State Key Laboratory of Automotive Simulation and Control
2022-2024
Hubei University of Medicine
2022-2024
Purpose To establish and validate a universal artificial intelligence (AI) platform for collaborative management of cataracts involving multilevel clinical scenarios explored an AI-based medical referral pattern to improve efficiency resource coverage. Methods The training validation datasets were derived from the Chinese Medical Alliance Artificial Intelligence, covering healthcare facilities capture modes. labelled using three-step strategy: (1) mode recognition; (2) cataract diagnosis as...
Retinal detachment can lead to severe visual loss if not treated timely. The early diagnosis of retinal improve the rate successful reattachment and results, especially before macular involvement. Manual screening is time-consuming labour-intensive, which difficult for large-scale clinical applications. In this study, we developed a cascaded deep learning system based on ultra-widefield fundus images automated detection macula-on/off discerning. performance reliable comparable an experienced...
Lattice degeneration and/or retinal breaks, defined as notable peripheral lesions (NPRLs), are prone to evolving into rhegmatogenous detachment which can cause severe visual loss. However, screening NPRLs is time-consuming and labor-intensive. Therefore, we aimed develop evaluate a deep learning (DL) system for automated identifying based on ultra-widefield fundus (UWF) images.A total of 5,606 UWF images from 2,566 participants were used train verify DL system. All classified by 3...
Background: Myopia is the leading cause of visual impairment and affects millions children worldwide. Timely annual manual optometric screenings entire at-risk population improve outcomes, but screening challenging due to lack availability training assessors economic burden imposed by screenings. Recently, deep learning computer vision have shown powerful potential for disease screening. However, these techniques not been applied large-scale myopia using ocular appearance images. Methods: We...
The Cooperative Adaptive Cruise Control (CACC) is considered to be an effective method improve traffic flow. However, the comfortability and economy need paid more attention besides stability safety. In this paper, a CACC strategy proposed for electric vehicle platoon economy, following performance, safety, characteristics, based on model predictive control (MPC) with simulated annealing-particle swarm optimization (SA-PSO) algorithm. Firstly, braking force distribution of vehicles designed...
Car-following behavior is one of the most common driving behaviors. To reduce impact driver reaction delay and accumulated errors in predicting long sequences on accuracy speed prediction, we propose a deep learning car-following model based sequence-to-sequence (seq2seq) architecture with an attention mechanism. Firstly, analyze characteristics during process design mechanism to learn probability distribution delay. This allows consider more environmental information at moment when actually...
Climate risk has a negative impact on the stable operation of social, economic, and financial systems. Local commercial banks operate in single geographical area are unable to effectively diversify risk. This article uses data from local 2009 2021 explore climate soundness banks. The research results show that risk, represented by extreme rainfall transition affects increasing direct losses credit entities, reducing corporate profitability, decreasing demand. Further analysis shows for rural...
A challenge of chronic diseases that remains to be solved is how liberate patients and medical resources from the burdens long-term monitoring periodic visits. Precise management based on artificial intelligence (AI) holds great promise; however, a clinical application fully integrates prediction telehealth computing has not been achieved, further efforts are required validate its real-world benefits. Taking congenital cataract as representative, we used Bayesian deep-learning algorithms...
Background/Aims To develop a deep learning system for automated glaucomatous optic neuropathy (GON) detection using ultra-widefield fundus (UWF) images. Methods We trained, validated and externally evaluated GON based on 22 972 UWF images from 10 590 subjects that were collected at 4 different institutions in China Japan. The InceptionResNetV2 neural network architecture was used to the system. area under receiver operating characteristic curve (AUC), sensitivity specificity assess...
BackgroundApproximately 1 in 33 newborns is affected by congenital anomalies worldwide. We aimed to develop a practical model for identifying infants with high risk of cataracts (CCs), which the leading cause avoidable childhood blindness.MethodsThis case-control study was performed Zhongshan Ophthalmic Center and involved 2005 subjects, including 1274 children CCs 731 healthy controls. The CC identification models were established based on birth conditions, family medical history,...
Benefitting from the advances in sensor nets, wireless communication, and embedded systems, cyber-physical system (CPS) has been implemented many practical areas. The cyber world physical CPS are closely linked merged, guaranteeing reliable efficient performance of world. service-oriented hot research development. In this paper, we present a novel velocity-profile prediction method based on specific architecture. Three main efforts have made. First, architecture which is appropriate for...
This paper presents a prescient energy management strategy based on the model predictive control (MPC) for parallel plug-in hybrid electric vehicles (PHEVs). In this hierarchical strategy, dynamic programming (DP), with its improved calculation speed, is chosen as solution algorithm to calculate optimal power distribution combinations in predicted receding horizon and under given terminal battery state-of-charge (SOC) constraint. A synthesized velocity profile prediction (SVPP) method...
Purpose: To develop and evaluate a deep learning (DL) system for retinal hemorrhage (RH) screening using ultra-widefield fundus (UWF) images. Methods: A total of 16,827 UWF images from 11,339 individuals were used to the DL system. Three experienced retina specialists recruited grade independently. independent data sets 3 different institutions validate effectiveness The set Zhongshan Ophthalmic Center (ZOC) was selected compare classification performance general ophthalmologists. heatmap...
In this paper, a novel energy management strategy with the improved adaptability to various conditions for plug-in hybrid electric vehicle (PHEV) is proposed. The control parameters, derived from benchmark test, are optimized offline different driving conditions. parameters implemented according behaviours identified online. and online cooperation improves performance of in Three main efforts have been made: Firstly, valuable features that describe extracted by random forest (RF) used...
Energy management strategies based on instantaneous optimization have been widely used in hybrid/plug-in hybrid electric vehicles (HEV/PHEV) order to improve fuel economy while guaranteeing vehicle performance. In this study, an adaptive-equivalent consumption minimum strategy (A-ECMS) target driving cycle (TDC) generation was proposed for extended-range bus (E-REB) operating fixed routes. Firstly, a Hamilton function and co-state equation E-REB were determined according the Pontryagin...
Artificial intelligence (AI) based on deep learning has shown excellent diagnostic performance in detecting various diseases with good-quality clinical images. Recently, AI systems developed from ultra-widefield fundus (UWF) images have become popular standard-of-care tools screening for ocular diseases. However, real-world settings, these must base their diagnoses uncontrolled quality ("passive feeding"), leading to uncertainty about performance. Here, using 40,562 UWF images, we develop a...
To predict visual acuity (VA) and post-therapeutic optical coherence tomography (OCT) images 1, 3, 6 months after laser treatment in patients with central serous chorioretinopathy (CSC) by artificial intelligence (AI). Real-world clinical imaging data were collected at Zhongshan Ophthalmic Center (ZOC) Xiamen Eye (XEC). The obtained from ZOC (416 eyes of 401 patients) used as the training set; XEC (64 60 test set. Six different machine learning algorithms a blending algorithm to VA,...
Visual systems of primates are the gold standard robust perception. There is thus a general belief that mimicking neural representations underlie those will yield artificial visual adversarially robust. In this work, we develop method for performing adversarial attacks directly on primate brain activity. We then leverage to demonstrate above-mentioned might not be well founded. Specifically, report biological neurons make up exhibit susceptibility perturbations comparable in magnitude...
In a cut-in scenario, traditional adaptive cruise control usually cannot effectively identify the vehicle and respond to it in advance. This paper proposes an (ACC) strategy based on MPC algorithm for scenarios. A finite state machine (FSM) is designed manage different For method quantify possibility of proposed. At same time, safety distance model established as basis transition machine. Taking quantified reference, predictive (MPC) algorithm, which considers constraints driving comfort,...