A5061001626- Multi-Agent Systems and Negotiation
- Logic, Reasoning, and Knowledge
- Semantic Web and Ontologies
- Topic Modeling
- Urinary and Genital Oncology Studies
- Pelvic floor disorders treatments
- Urological Disorders and Treatments
- Service-Oriented Architecture and Web Services
- Urologic and reproductive health conditions
- Bladder and Urothelial Cancer Treatments
- Natural Language Processing Techniques
- Anorectal Disease Treatments and Outcomes
- Explainable Artificial Intelligence (XAI)
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Renal cell carcinoma treatment
- Ferroptosis and cancer prognosis
- Epigenetics and DNA Methylation
- Testicular diseases and treatments
- AI in Service Interactions
- Ureteral procedures and complications
- Robotics and Automated Systems
- Mycobacterium research and diagnosis
- Bayesian Modeling and Causal Inference
- AI-based Problem Solving and Planning
- Diagnosis and treatment of tuberculosis
The University of Texas at Dallas
2023-2025
First Affiliated Hospital of Xiamen University
2014-2023
Fujian Medical University
2023
Xiamen University
2023
Efforts have been made to make machines converse like humans in the past few decades. The recent techniques of Large Language Models (LLMs) it possible human-like conversations with machines, but LLM's flaws lacking understanding and reliability are well documented. We believe that best way eliminate this problem is use LLMs only as parsers translate text knowledge vice versa carry out conversation by reasoning over using answer set programming. I developing a framework based on ASP realize...
Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions.While large models (LLMs) such as GPT-3 ChatGPT are able leverage patterns in the text solve a variety of NLP tasks, they fall short problems that require reasoning.They also cannot reliably explain answers generated for given question.In order emulate humans better, we propose STAR, framework combines LLMs Answer...
We present an approach to building systems that emulate human-like intelligence. Our uses machine learning technology (including generative AI systems) extract knowledge from pictures, text, etc., and represents it as (pre-defined) predicates. Next, we use the s(CASP) automated commonsense reasoning system check consistency of this extracted reason over in a manner very similar how human would do it. have used our for visual question answering, task-specific chatbots can ``understand"...
Achieving human-like communication with machines remains a classic, challenging topic in the field of Knowledge Representation and Reasoning Natural Language Processing. These Large Models (LLMs) rely on pattern-matching rather than true understanding semantic meaning sentence. As result, they may generate incorrect responses. To an assuredly correct response, one has to "understand" semantics achieve this "understanding", logic-based (commonsense) reasoning methods such as Answer Set...
To evaluate the efficacy and safety of single-incision mini-sling for stress urinary incontinence based on network Meta-analysis.We searched PubMed, Embase, Cochrane libraries from August 2008 to 2019. Randomized controlled trials comparing two or more indicators Miniarc (Single Incision Mini-slings), Ajust (Adjustable Single-Incision Sling), C-NDL (Contasure-Needleless), TFS (Tissue Fixation System), Ophria (Transobturator Vaginal Tap), TVT-O Tape), TOT (Trans-obturatortape) in treating...
The development of large language models (LLMs), such as GPT, has enabled the construction several socialbots, like ChatGPT, that are receiving a lot attention for their ability to simulate human conversation. However, conversation is not guided by goal and hard control. In addition, because LLMs rely more on pattern recognition than deductive reasoning, they can give confusing answers have difficulty integrating multiple topics into cohesive response. These limitations often lead LLM...
Abstract The development of large language models (LLMs), such as GPT, has enabled the construction several socialbots, like ChatGPT, that are receiving a lot attention for their ability to simulate human conversation. However, conversation is not guided by goal and hard control. In addition, because LLMs rely more on pattern recognition than deductive reasoning, they can give confusing answers have difficulty integrating multiple topics into cohesive response. These limitations often lead...
Humans understand language by extracting information (meaning) from sentences, combining it with existing commonsense knowledge, and then performing reasoning to draw conclusions. While large models (LLMs) such as GPT-3 ChatGPT are able leverage patterns in the text solve a variety of NLP tasks, they fall short problems that require reasoning. They also cannot reliably explain answers generated for given question. In order emulate humans better, we propose STAR, framework combines LLMs...
Objective To discuss the clinical and pathological features of juvenile xanthogranuloma testis.Methods A case testis was reported.A 6-month-old boy presented with scrotal mass for 2 weeks before admission.Physical examination revealed that left hard size 2.0 cm×2.0 cm serum alpha-fetoprotein 37.60 μg/L.Chest X-ray human chorionic gonadotropin investigations were normal.B-ultrasound showed a solid uniform homogeneity in testis,with rich blood supply.Results The patient underwent operation...
<title>Abstract</title> <bold>Background：</bold>Bladder urothelial carcinoma (BLCA) is a malignant tumor occurring in the bladder and derived from cells. It one of ten most common cancers world. There has been no significant progress treatment patients with recurrence BLCA past decades. With systemic treatment, overall survival period (OS) improved, but prognosis still poor, which needs improvement clinically. The development immunotherapy changed status initially. Natural killer (NK) cells,...
Objective To compare the long-term outcomes of retropubic tension-free vaginal tape (TVT) versus transobturator (TVT-O) for women with stress urinary incontinence (SUI). Methods From July 2001 to June 2011, data 120 female patients SUI were retrospectively reviewed, which 45 received TVT treatment, while 75 TVT-O. The median age in group was 45.1 years (range 35-72 years), and TVT-O 50.5 39-76 years). We analyzed subjective effect, objective effect rate complications two...
Objective To analyze the infiltration of inflammatory cells under mucosa female cystitis glandularis and different in clinical pathological types glandularis. Methods Immunohistochemical method was used to detect bladder mucosal tissue samples 10 patients confirmed admitted from June 2016 October 2016.The results immunohistochemical staining were collected statistically analyzed by automatic microscopy image analysis system.In addition, data sample 49 cases treated December 2006...
Objective To explore the clinical efficacy of female urethral diverticulum resection and reconstruction under folding position. Methods Retrospective analysis 22 patients with was performed from September 2010 to December 2018. There were 12 cases simple diverticulum, 6 horseshoe 4 circumferential aged 26 72 years, an average 46.2 whose BMI ranged 24.2 34.8 kg/m2, 30.4 kg/m2. Eleven (50%) presented dysuria, 10 (45.5%) repeated urinary tract infections, 7 (31.2%) difficulty voiding,...
Abstract Objective: Fructose bisphosphate aldolase (ALDOB) is a glycolytic metabolic enzyme, which considered to be therapeutic target for many cancers. However, ALDOB expression level and its regulatory mechanism in renal clear cell carcinoma not clear. To explore we downloaded gene data sets analyzed them by bioinformatics. Methods: The of GSE53757, GSE40435 GSE105261 about human were from the GEO database using Venn diagram. We screened out relationship network interested genes through...