Accès ouvert
2026
preprint
OpenAlex
Hongbo Du, Zixin Lu, Jiaming Qu
Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible …
Accès ouvert
2026
preprint
OpenAlex
Hongbo Du, Zixin Lu, Jiaming Qu
Large language models (LLMs) are increasingly used for clinical text tasks such as summarization and revision. While most studies evaluate the fluency and coherence of LLM-generated text, whether LLMs correctly preserve diagnostic uncertainty remains underexplored. In clinical practice, phrases such as ``possible …
us
(code pays fourni par la source)
Accès ouvert
2026
article
OpenAlex
Jianbo SHAO, Yu LONG, Hongbo Du, Xianfeng LI et autres
To evaluate the potential impact of high-density planting as a yield-enhancing measure on soil health, the flue-cured tobacco variety Yunyan 99 was used as the material in this study, and two planting modes of conventional density and high density were established in …
cn
(code pays fourni par la source)
2025
article
OpenAlex
Shitao Peng, Li Long-Chuang, Yin Ye, Hong Ning-ning et autres
cn
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Francesco Bianconi, Muhammad Usama Khan, Hongbo Du, Sabah Jassim
Breast ultrasound images play a pivotal role in assessing the nature of suspicious breast lesions, particularly in patients with dense tissue. Computerized analysis of breast ultrasound images has the potential to assist the physician in the clinical decision-making and improve subjective interpretation. …
it, gb
(code pays fourni par la source)
2025
conference-paper
OpenAlex
Feng Wang, H. Zheng, Yilong Zhao, Hongbo Du
The layout of explosion-proof electrical equipment on offshore oil platforms is dense, which can lead to problems such as improper sensor settings, making sensors susceptible to environmental interference, low reliability of single sensor data, and the possibility of false alarms or missed …
cn
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Yuan Zhang, Feng Lu, Jun Shan, Quan Jiang et autres
Background: Accurate preoperative assessment of sentinel lymph node (SLN) is critical for treatment planning in breast cancer (BC). While SLN biopsy (SLNB) remains the gold standard, it is invasive and may be unnecessary for all patients, particularly those with clinically node-negative disease. …
cn, sg, fr, gb
(code pays fourni par la source)
2025
conference-paper
OpenAlex
Muhammad Usama Khan, Francesco Bianconi, Hongbo Du, Sabah Jassim
Breast ultrasound imaging (BUS) plays a major role in the diagnosis of breast cancer. Consequently, computerised analysis of BUS images is being intensively investigated as a means to assist physicians in clinical decision making. The traditional approach involves the use of manually-designed …
it, gb
(code pays fourni par la source)
Accès ouvert
2025
article
OpenAlex
Hongbo Du, Chongchong Lu, Jianfeng Du, Yong Liu et autres
Livestock and poultry manure, as a significant organic resource, had an enormous annual production but a utilization rate of less than 50%. Improperly managed manure had become the primary source of agricultural non-point pollution, posing severe challenges to the ecological environment. Achieving …
cn
(code pays fourni par la source)
2025
article
OpenAlex
Shihao Zheng, Tianyu Xue, Chengyuan Xue, Size Li et autres
cn
(code pays fourni par la source)
Accès ouvert
2025
conference-paper
OpenAlex
Grace Oluchi Diri, Philip Obiorah, Hongbo Du
Aim/Purpose This paper presents a comparative analysis of sentiment classification models, focusing on the performance differences between lexicon-based sentiment analysis, traditional machine learning techniques, and transformer-based deep learning approaches across multiple benchmark datasets. Background While numerous methods exist for sentiment analysis, a …
gb
(code pays fourni par la source)
2024
article
OpenAlex
Qize Xie, Hongbo Du, Qing Yang, Zhi Liu et autres
ABSTRACT Phenotypic trait identification is crucial in cultivating new soybean varieties with high yield and quality. The traditional soybean phenotypic trait identification relies on manual pod counting and plant height measuring with a ruler. The heavy workload causes the data collected by …
cn, us
(code pays fourni par la source)