Haoran Zheng

Mr. Haoran Zheng

University of Auckland, Auckland, New Zealand
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 June 2024 in Foods
Verified
Journal Article
Open access
PDF file
SYShuai Yu
Shuai Yu
HZHaoran Zheng
Haoran Zheng
David I. WilsonDavid I. Wilson
David I. Wilson
WYWei Yu
Wei Yu
BYBrent Young
Brent Young
The appearance of dried fruit clearly influences the consumer’s perception of the quality of the product but is a subtle and nuanced characteristic that is difficult to quantitatively measure, especially online. This paper describes a method that combines several simple strategies to assess a suitable surrogate for the elusive quality using imaging, combined with multivariate statistics and machine learning. With such a convenient tool, this study also shows how one can vary the pretreatments and drying conditions to optimize the resultant product quality. Specifically, an image batch processing method was developed to extract color (hue, saturation, and value) and morphological (area, perimeter, and compactness) features. The accuracy of this method was verified using data from a case study experiment on the pretreatment of hot-air-dried kiwifruit slices. Based on the extracted image features, partial least squares and random forest models were developed to satisfactorily predict the moisture ratio (MR) during drying process. The MR of kiwifruit slices during drying could be accurately predicted from changes in appearance without using any weighing device. This study also explored determining the optimal drying strategy based on appearance quality using principal component analysis. Optimal drying was achieved at 60 °C with 4 mm thick slices under ultrasonic pretreatment. For the 70 °C, 6 mm sample groups, citric acid showed decent performance.

3 November 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
ZHZelun Huang
Zelun Huang
HZHaoran Zheng
Haoran Zheng
JHJunqiang Huang
Junqiang Huang
YYYang Yang
Yang Yang
YWYupeng Wu
Yupeng Wu
LWLiping Wang
Liping Wang
Objectives: Assessing implant stability is integral to dental implant therapy. This study aimed to construct a multi-task cascade convolution neural network to evaluate implant stability using cone-beam computed tomography (CBCT). Methods: A dataset of 779 implant coronal section images was obtained from CBCT scans, and matching clinical information was used for the training and test datasets. We developed a multi-task cascade network based on CBCT to assess implant stability. We used the MobilenetV2-DeeplabV3+ semantic segmentation network, combined with an image processing algorithm in conjunction with prior knowledge, to generate the volume of interest (VOI) that was eventually used for the ResNet-50 classification of implant stability. The performance of the multitask cascade network was evaluated in a test set by comparing the implant stability quotient (ISQ), measured using an Osstell device. Results: The cascade network established in this study showed good prediction performance for implant stability classification. The binary, ternary, and quaternary ISQ classification test set accuracies were 96.13%, 95.33%, and 92.90%, with mean precisions of 96.20%, 95.33%, and 93.71%, respectively. In addition, this cascade network evaluated each implant’s stability in only 3.76 s, indicating high efficiency. Conclusions: To our knowledge, this is the first study to present a CBCT-based deep learning approach CBCT to assess implant stability. The multi-task cascade network accomplishes a series of tasks related to implant denture segmentation, VOI extraction, and implant stability classification, and has good concordance with the ISQ.

30 May 2025 in Vehicles
Verified
Journal Article
Open access
PDF file
JFJingxiang Feng
Jingxiang Feng
PZPeiran Zhao
Peiran Zhao
HZHaoran Zheng
Haoran Zheng
JKJessada Konpang
Jessada Konpang
ASAdisorn Sirikham
Adisorn Sirikham
Phuri KalnaowakulPhuri Kalnaowakul
Phuri Kalnaowakul
Robust object detection in autonomous driving is challenged by inherent limitations of conventional frame-based cameras, such as motion blur and limited dynamic range. In contrast, event-based cameras, which operate asynchronously and capture rapid changes with high temporal resolution and expansive dynamic range, offer a promising augmentation. While the previous research on event-based object detection has predominantly focused on algorithmic enhancements via advanced preprocessing and network optimizations to improve detection accuracy, the practical engineering and integration challenges of deploying these sensors in real-world systems remain underexplored. To address this gap, our study investigates the integration of event-based cameras as a complementary sensor modality in autonomous driving. We adapted a conventional frame-based detection model (YOLOv8) for event-based inputs by training it on the GEN1 dataset, achieving a mean average precision (mAP) of 70.1%, a significant improvement over previous benchmarks. Additionally, we developed a real-time object detection pipeline optimized for event-based data, integrating it into the CARLA simulation environment and ROS for system prototyping. The model was further refined using transfer learning to better adapt to simulation conditions, and the complete pipeline was validated across diverse simulated scenarios to address practical challenges. These results underscore the feasibility of incorporating event cameras into existing perception systems, paving the way for their broader deployment in autonomous vehicle applications.

18 August 2025 in Frontiers in Dental Medicine
Verified
Journal Article
Open access
PDF file
LYLan Yang
Lan Yang
ZZZiCheng Zhu
ZiCheng Zhu
YLYongshan Li
Yongshan Li
JHJieying Huang
Jieying Huang
XWXiaoli Wang
Xiaoli Wang
JCJiang Chen
Jiang Chen
Objective: Traditional gingival thickness (GT) assessment methods provide only point measurements or simple classifications, lacking spatial distribution information. This study aimed to develop a CBCT-based 3D visualization system for gingival thickness using deep learning, providing a novel spatial assessment tool for implant surgery planning.Methods: CBCT and intraoral scanning (IOS) data from 50 patients with tooth loss were collected to establish a standardized dataset. DeepLabV3+ architecture was employed for semantic segmentation of gingival and bone tissues. A 3D visualization algorithm incorporating vertical scanning strategy, triangular mesh construction, and gradient color mapping was innovatively developed to transform 2D slices into continuous 3D surfaces.Results: The semantic segmentation model achieved a mIoU of 85.92 ± 0.43%. The 3D visualization system successfully constructed a comprehensive spatial distribution model of gingival thickness, clearly demonstrating GT variations from alveolar ridge to labial aspect through gradient coloration. The 3D model enabled millimeter-precision quantification, supporting multi-angle and multi-level GT assessment that overcame the limitations of traditional 2D measurements.Conclusion: This system represents a methodological advancement from qualitative to spatial quantitative GT assessment. The intuitive 3D visualization serves as an innovative preoperative tool that identifies high-risk areas and guides personalized surgical planning, enhancing predictability for aesthetic and complex implant cases.

6 June 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RHRuitong Han
Ruitong Han
CLChang-Bo Liu
Chang-Bo Liu
WSWanting Sun
Wanting Sun
SYShuai Yu
Shuai Yu
HZHaoran Zheng
Haoran Zheng
LDLin Deng
Lin Deng
In this study, a hierarchical multi-label classification method called HFFNet-2d is proposed for the automatic classification of scanning electron microscope (SEM) images of metal failure. The method combines the advantages of convolutional neural networks (CNN) and Vision Transformers (ViT) to effectively realize hierarchical feature extraction and classification of SEM images of fracture morphologies, enabling accurate identification of metal failure mechanisms at different scales. The dataset of high-quality SEM images in this work is sourced from reputable materials science publications for its comprehensive coverage of various failure modes and its suitability for training and validating the hierarchical multi-label classification model. The HFFNet-2d model can achieve a high accuracy of 97.71% in the first-level classification and 92.62% in the second-level sub-category identification. This performance surpasses the human experts on the same task. To ensure that the model predictions are sufficiently reliable, a multi-level gradcam algorithm is also introduced for checking the regions of interest of the Hierarchical model at two levels and the comparisons are made with human experts. It is anticipated that the optimization and extension of HFFNet-2d are conducive in diverse material systems and application scenarios to accelerate the intelligent process of material development and failure analysis, ultimately supporting the design of reliable and high-performance engineering materials.

1 January 2022 in Energy Engineering
Verified
Journal Article
Open access
PDF file
Xin ZhangXin Zhang
Xin Zhang
JJJinpeng Jiang
Jinpeng Jiang
HZHaoran Zheng
Haoran Zheng
JZJihong Zhang
Jihong Zhang
China consumes significant amount of natural gas in winter. The integrated community energy utilization system (ICEUS) cannot stabilize the output of electricity and heat if there is a shortage of natural gas. The operation cost of the system still needs improvement. An energy supply structure using garbage power as the core of ICEUS was established in the study. The optimal dispatching model of ICEUS was established using the regulating characteristic of the community load. The sine-cosine algorithm (SCA) based on nonlinear factors and segmented weight was presented to solve the optimal dispatching model of ICEUS. From the simulation results, compared with particle swarm optimization algorithm (PSO), SCA, exponential sine-cosine algorithm (ESCA), and parabolic sine-cosine algorithm (PSCA), the daily operation cost of ICEUS was reduced by the improved SCA by 4.4%, 2.9%, 2.6% and 4.1%, respectively, in winter. The same was true in summer. The daily system operating cost was effectively reduced by the algorithm proposed in the study. The cost benefits of the optimized ICEUS operation was realized.