Yishen Lin

Dr. Yishen Lin


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
10 January 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
YLYishen Lin
Yishen Lin
LYLin Yishen Lin Yishen
Lin Yishen Lin Yishen
YLYun Liang
Yun Liang
YLYunfan Liu
Yunfan Liu
WJWeipeng Jiang
Weipeng Jiang
Citrus fruits hold pivotal positions within the agricultural sector. Accurate yield estimation for citrus fruits is crucial in orchard management, especially when facing challenges of fruit occlusion due to dense foliage or overlapping fruits. This study addresses the issues of low detection accuracy and the significant instances of missed detections in citrus fruit detection algorithms, particularly in scenarios of occlusion. It introduces AG-YOLO, an attention-based network designed to fuse contextual information. Leveraging NextViT as its primary architecture, AG-YOLO harnesses its ability to capture holistic contextual information within nearby scenes. Additionally, it introduces a Global Context Fusion Module (GCFM), facilitating the interaction and fusion of local and global features through self-attention mechanisms, significantly improving the model’s occluded target detection capabilities. An independent dataset comprising over 8000 outdoor images was collected for the purpose of evaluating AG-YOLO’s performance. After a meticulous selection process, a subset of 957 images meeting the criteria for occlusion scenarios of citrus fruits was obtained. This dataset includes instances of occlusion, severe occlusion, overlap, and severe overlap, covering a range of complex scenarios. AG-YOLO demonstrated exceptional performance on this dataset, achieving a precision (P) of 90.6%, a mean average precision (mAP)@50 of 83.2%, and an mAP@50:95 of 60.3%. These metrics surpass existing mainstream object detection methods, confirming AG-YOLO’s efficacy. AG-YOLO effectively addresses the challenge of occlusion detection, achieving a speed of 34.22 frames per second (FPS) while maintaining a high level of detection accuracy. This speed of 34.22 FPS showcases a relatively faster performance, particularly evident in handling the complexities posed by occlusion challenges, while maintaining a commendable balance between speed and accuracy. AG-YOLO, compared to existing models, demonstrates advantages in high localization accuracy, minimal missed detection rates, and swift detection speed, particularly evident in effectively addressing the challenges posed by severe occlusions in object detection. This highlights its role as an efficient and reliable solution for handling severe occlusions in the field of object detection.

31 August 2024
Verified
Book Chapter
Open access
PDF file
LLLili Liao
Lili Liao
YLYishen Lin
Yishen Lin
HYHe Yi
He Yi
CZChunyan Zhu
Chunyan Zhu
YHYuzhong Huangfu
Yuzhong Huangfu
QLQing Li
Qing Li
This study introduces a bespoke cloud-based platform engineered to streamline the administration of rural revitalization endeavors in the tobacco sector. It confronts prevalent issues such as operational inefficiencies and elevated risks linked to these ventures. The platform embraces a comprehensive digital management approach, utilizing a suite of advanced technologies including micro-service frameworks, extensive data analytics, intermediary cloud services, cloud-based data storage, and sophisticated data-driven algorithms. The system facilitates a fully digitized oversight across all stages of a project’s lifespan—ranging from the initial application, strategic decision-making, and active execution to real-time tracking, evaluation, and regulatory compliance checks. The inception of this cloud-based infrastructure is anticipated to substantially uplift the efficacy of project management and curtail economic uncertainties, thus bolstering the rural revitalization initiatives.

29 September 2024
Verified
Book Chapter
Open access
PDF file
XLXiaoting Liang
Xiaoting Liang
CZChunyan Zhu
Chunyan Zhu
YLYishen Lin
Yishen Lin
The classroom teaching revolution aims to enhance higher education quality by positioning classroom teaching as the core battleground. Based on the “Guidelines for Curriculum Ideology and Politics Construction in Higher Education,” this paper reforms the “Forest Plants” course within the provincial high-level forestry technology group. The reform builds a robust teaching team, innovates methods, and optimizes resources, integrating ecological civilization elements and new media technology. Advanced technologies like digital platforms, big data, 5G, VR, and AR create immersive experiences, boosting student interest and participation. The goal is to cultivate high-quality forestry science professionals with the principles of “Lucid waters and lush mountains are invaluable assets” and “Protection first.” Ideological and political education is embedded throughout the course, exploring new multi-dimensional evaluation methods to enhance students’ skills and capabilities. This study uses industry-academia collaboration to update resources and construct a new teaching model, supporting high-standard planning, construction, and development in vocational education.

21 October 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
QGQiliang Gan
Qiliang Gan
ZLZhuangbi Lin
Zhuangbi Lin
YLYishen Lin
Yishen Lin
Daily parking demand varies with calendar patterns, weather, and recent demand states, creating substantial uncertainty. Reliable prediction intervals support parking-resource scheduling. Existing similar-day methods mainly use retrieved neighbors for point forecasting, but seldom exploit retrieval-based uncertainty information that reflects the reliability of historical analogs and can inform interval construction. This study proposes a framework for daily parking-demand interval forecasting with similar-day matching diagnostics. Similar-day retrieval and kernel-weighted aggregation generate point forecasts and seven diagnostics of matching quality, neighbor-demand consistency, recent demand variation, and historical sample support. A residual conditional quantile model combines these diagnostics with conventional covariates to construct asymmetric, day-specific initial intervals. Rolling conformalized quantile regression (CQR) calibrates recent coverage, while adaptive conformal inference (ACI) updates the miscoverage rate from observed coverage errors. Rolling experiments on three real parking facilities show that, with both methods achieving empirical coverage close to 80%, the proposed method reduces macro-average relative interval width and Winkler score by 6.78% and 10.22%, respectively, compared with Conformal PID (proportional–integral–derivative) control, the best external baseline by macro-average Winkler score. The framework provides day-specific uncertainty estimates, with potential applications in next-day parking-resource planning.