A5104291087- Topic Modeling
- Natural Language Processing Techniques
- Adversarial Robustness in Machine Learning
- Software Reliability and Analysis Research
- Software Engineering Research
- Robot Manipulation and Learning
- Carcinogens and Genotoxicity Assessment
- Reinforcement Learning in Robotics
- Radiation Effects in Electronics
- Multimodal Machine Learning Applications
- Fault Detection and Control Systems
- Business Process Modeling and Analysis
- Autonomous Vehicle Technology and Safety
- Financial Literacy, Pension, Retirement Analysis
- Advanced X-ray and CT Imaging
- Safety Systems Engineering in Autonomy
- Biomarkers in Disease Mechanisms
- Air Quality and Health Impacts
- Cancer-related molecular mechanisms research
- Electrostatic Discharge in Electronics
- Software Testing and Debugging Techniques
- Medical Research and Treatments
- Risk and Safety Analysis
- Housing Market and Economics
- Advanced materials and composites
University of Alberta
2022-2025
Tianjin Normal University
2024
Nvidia (United Kingdom)
2023
The University of Tokyo
2023
Tsinghua University
2023
Guangxi University
2023
Wuhan National Laboratory for Optoelectronics
2023
Huazhong University of Science and Technology
2023
Capital University of Economics and Business
2022
Wuhan University
2022
PURPOSE:To predict programmed death-ligand 1 (PD-L1) expression of tumor cells in non-small cell lung cancer (NSCLC) patients by using a radiomics study based on CT images and clinicopathologic features. MATERIALS AND METHODS:A total 390 confirmed NSCLC who performed chest scan i mmunohistochemistry (IHC) examination PD-L1 tumors with clinic data were collected this retrospective study, which divided into two cohorts namely, training (n = 260) validation 130) cohort. Clinicopathologic...
As a representative cyber-physical system (CPS), robotic manipulators have been widely adopted in various academic research and industrial processes, indicating their potential to act as universal interface between the cyber physical worlds. Recent studies robotics manipulation started employing artificial intelligence (AI) approaches controllers achieve better adaptability performance. However, inherent challenge of explaining AI components introduces uncertainty unreliability these...
The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, the potential erroneous behavior (e.g., generation misinformation hallucination) has also raised severe concerns for trustworthiness LLMs, especially in safety-, security- reliability-sensitive scenarios, potentially hindering real-world adoptions. While uncertainty estimation shown its interpreting prediction risks made by classic machine...
Parkinson’s disease (PD) is a common neurodegenerative disorder characterized by misfolding of α-synuclein. Clinical manifestations include slowly developing resting tremor, muscle rigidity, bradykinesia and abnormal gait. The pathological mechanisms underlying PD are complex yet to be fully elucidated. studies suggest that the onset gastrointestinal symptoms may precede motor in patients. microbiota-gut-brain axis plays bidirectional communication role between enteric nervous system central...
The recent performance leap of Large Language Models (LLMs) opens up new opportunities across numerous industrial applications and domains. However, erroneous generations, such as false predictions, misinformation, hallucination made by LLMs, have also raised severe concerns for the trustworthiness LLMs', especially in safety-, security- reliability-sensitive scenarios, potentially hindering real-world adoptions. While uncertainty estimation has shown its potential interpreting prediction...
There is a paucity of mechanistic information on the DNA methylation and particulate matter (PM) exposure. This study aimed to investigate association PM its component with methylation, roles methyltransferase (DNMTs).There were 240 high-exposed, 318 low-exposed 210 non-exposed participants in this study. Individual concentrations PM, polycyclic aromatic hydrocarbons (PAHs) metals identified by monitoring data their workplaces. Urinary 1-OHP determined as exposure markers. The global (% 5mC)...
Acrylamide has been shown to be neurotoxic. Brain-derived neurotrophic factor (BDNF) can alleviate acrylamide-induced synaptic injury; however, the underlying mechanism remains unclear. In this study, dibutyryl-cyclic adenosine monophosphate-induced mature human neuroblastoma (NB-1) cells were exposed with 0–100 μg/mL acrylamide for 24–72 hours. decreased cell viability and destroyed synapses. Exposure of co-cultured NB-1 Schwann 48 hours resulted in upregulated expression synapsin I BDNF,...
Studies on the application of deep learning image reconstruction (DLIR) in pediatric computed tomography (CT) are limited and have so far been mostly based phantom. The purpose this study was to compare quality radiation dose DLIR with that adaptive statistical iterative reconstruction-Veo (ASiR-V) during abdominal chest CT for population.A phantom used pilot study, 20 children were recruited clinical verification. preset scan parameter noise index (NI) 5, 8, 11, 13, 15, 18 8 13 study. We...
Abstract This retrospective study aimed to investigate the correlation between neonatal hyperbilirubinemia (NHB) and hypoglycemia (NH) in Chinese women with diabetes pregnancy (DIP), influencing factors. All data were collected July 1, 2017 June 30, 2020, 10,558 DIP live births included. Two separate multivariate binary stepwise forward logistic regression analysis calculated OR 95% CI. The prevalence rates of NHB NH was respectively 3.65% 5.82% among DIP. comorbidity both diseases 0.59%....
Cyber-physical systems (CPS) have been broadly deployed in safety-critical domains, such as automotive systems, avionics, medical devices, etc. In recent years, Artificial Intelligence (AI) has increasingly adopted to control CPS. Despite the popularity of AI-enabled CPS, few benchmarks are publicly available. There is also a lack deep understanding on performance and reliability CPS across different industrial domains. To bridge this gap, we initiate create public benchmark industry-level...
While Large Language Models (LLMs) have seen widespread applications across numerous fields, their limited interpretability poses concerns regarding safe operations from multiple aspects, e.g., truthfulness, robustness, and fairness. Recent research has started developing quality assurance methods for LLMs, introducing techniques such as offline detector-based or uncertainty estimation methods. However, these approaches predominantly concentrate on post-generation analysis, leaving the...
Cyber-Physical Systems (CPSs) are increasingly prevalent across various industrial and daily-life domains, with applications ranging from robotic operations to autonomous driving. With recent advancements in artificial intelligence (AI), learning-based components, especially AI controllers, have become essential enhancing the functionality efficiency of CPSs. However, lack interpretability these controllers presents challenges safety quality assurance AI-enabled CPSs (AI-CPSs). Existing...
Safe reinforcement learning (SRL) aims to realize a safe process for deep (DRL) algorithms by incorporating safety constraints. However, the efficacy of SRL approaches often relies on accurate function approximations, which are notably challenging achieve in early stages due data insufficiency. To address this issue, we introduce, work, novel generalizable enhancer (GenSafe) that can overcome challenge insufficiency and enhance performance approaches. Leveraging model order reduction...
Cyber-Physical Systems (CPSs) have been widely adopted in various industry domains to support many important tasks that impact our daily lives, such as automotive vehicles, robotics manufacturing, and energy systems. As Artificial Intelligence (AI) has demonstrated its promising abilities diverse like decision-making, prediction, optimization, a growing number of CPSs adopt AI components the loop further extend their efficiency performance. However, these modern AI-enabled tackle pivotal...
Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing design is also inherently linked LLM offers promising potential this context. Motivated by this, we...
Cyber-Physical Systems (CPS) have been widely deployed in safety-critical domains such as transportation, power and energy. Recently, there comes an increasing demand employing deep neural networks (DNNs) CPS for more intelligent control decision making sophisticated industrial conditions, giving birth to the class of DNN controllers. However, due inherent uncertainty opaqueness DNNs, concerns about safety DNN-enabled are also surging. In this work, we propose automated framework named...
Cyber-physical systems (CPSs) are now widely deployed in many industrial domains, e.g., manufacturing and autonomous vehicles. To further enhance the capability applicability of CPSs, there comes a recent trend from both academia industry to utilize learning-based AI controllers for system control process, resulting an emerging class AI-enabled cyber-physical (AI-CPSs). Although such AI-CPSs could achieve obvious performance enhancement lens some key requirement indicators, due random...
Motivated by the substantial achievements observed in Large Language Models (LLMs) field of natural language processing, recent research has commenced investigations into application LLMs for complex, long-horizon sequential task planning challenges robotics. are advantageous offering potential to enhance generalizability as task-agnostic planners and facilitate flexible interaction between human instructors systems. However, plans generated often lack feasibility correctness. To address...