Publications by authors named "Zelong Cai"

During the production process of inkjet printing labels, printing defects can occur, affecting the readability of product information. The distinctive shapes and subtlety of printing defects present a significant challenge for achieving high accuracy and rapid detection in existing deep learning-based defect detection systems. To overcome this problem, we propose an improved model based on the structure of the YOLOv5 network to enhance the detection performance of printing defects.

View Article and Find Full Text PDF

The role of vapor- and liquid-phase AsO in deactivating commercial VO-WO/TiO catalyst during the NH-selective catalytic reduction (SCR) process was explored and compared. AsO was loaded via vapor deposition (As(vap)) and the wet impregnation (As(imp)) method, respectively. Results demonstrated that the poisoning extent of vapor arsenic was much stronger than in the liquid state.

View Article and Find Full Text PDF

Axillary lymph nodes (ALN) status is an essential component in tumor staging and treatment planning for patients with breast cancer. The aim of present study was to evaluate the predictive value of preoperative multidetector-row computed tomography (MDCT) for ALN metastasis in breast cancer patients. A total of 148 cases underwent preoperative MDCT examination and ALN surgery were eligible for the study.

View Article and Find Full Text PDF

The study aimed to explore the abnormal activation of special brain areas associated with methamphetamine craving using functional magnetic resonance imaging (fMRI) and to reveal the neurobiological basis of addiction. Twenty-six methamphetamine addicts and 26 healthy subjects were scanned by brain fMRI while watching pictures of happy, sad, or methamphetamine to acquire resource data. SPM5 was used to analyze fMRI data to get related brain activation map, and it was found that methamphetamine addicts had high brain activation in cingulate and low activation in frontal lobe when watching methamphetamine-cue pictures.

View Article and Find Full Text PDF

Objective: Using a block-designed BOLD-fMRI to explore the neural basis of spatial working memory impairment in patients with subclinical hypothyroidism (SCH) performing an n-back task.

Methods: Sixteen patients with SCH before and after being treated with levothyroxine (LT4) for 6 months and 16 matched euthyroid subjects were scanned by fMRI under the n-back task.

Results: The fMRI scan found that a neural network consisting of bilateral dorsolateral prefrontal cortex (DLPFC), bilateral premotor area (PreMA), supplementary motor area/anterior cingulate cortex, bilateral parietal lobe (PA) and right caudate nucleus/thalamus was activated, with right hemisphere dominance.

View Article and Find Full Text PDF