Xiaowu Li

Dr. Xiaowu Li

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
4 October 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
XLXiaowu Li
Xiaowu Li
KSKun Sun
Kun Sun
HFHongbo Fan
Hongbo Fan
ZHZihan He
Zihan He
Accurate cattle pose estimation is essential for Precision Livestock Farming (PLF). Computer vision-based, non-contact cattle pose estimation technology can be applied for behaviour recognition and lameness detection. Existing methods still face challenges in achieving fast cattle pose estimation in complex scenarios. In this work, we introduce the FasterNest Block and Depth Block to enhance the performance of cattle pose estimation based on the RTMPose model. First, the accuracy of cattle pose estimation relies on the capture of high-level image features. The FasterNest Block, with its three-branch structure, effectively utilizes high-level feature map information, significantly improving accuracy without a significant decrease in inference speed. Second, large kernel convolutions can increase the computation cost of the model. Therefore, the Depth Block adopts a method based on depthwise separable convolutions to replace large kernel convolutions. This addresses the insensitivity to semantic information while reducing the model’s parameter. Additionally, the SimAM module enhances the model’s spatial learning capabilities without introducing extra parameters. We conducted tests on various datasets, including our collected complex scene dataset (cattle dataset) and the AP-10K public dataset. The results demonstrate that our model achieves the best average accuracy with the lowest model parameters and computational requirements, achieving 82.9% on the cattle test set and 72.0% on the AP-10K test set. Furthermore, in conjunction with the object detection model RTMDet-m, our model reaches a remarkable inference speed of 39FPS on an NVIDIA GTX 2080Ti GPU using the PyTorch framework, making it the fastest among all models. This work provides adequate technical support for fast and accurate cattle pose estimation in complex farm environments.

17 February 2025 in Expert Systems with Applications
Verified
Journal Article
Closed access
RLRunxin Li
Runxin Li
XYXiong Yang
Xiong Yang
XLXiaowu Li
Xiaowu Li
GSGuofeng Shu
Guofeng Shu
LJLianyin Jia
Lianyin Jia
ZSZhenhong Shang
Zhenhong Shang

22 October 2025 in Electronics
Verified
Journal Article
Open access
PDF file
ZLZiyi Li
Ziyi Li
XLXiaowu Li
Xiaowu Li
JSJinxia Shang
Jinxia Shang
Forest fire monitoring is of great significance for ecological protection and public safety. This study proposes a monitoring technology based on LoRa-Mesh (Long Range-Mesh) wireless communication, integrating temperature and humidity sensing, image acquisition, fire identification, data transmission, and energy-saving optimization. To address the limitations of traditional LoRa networks in flexibility and energy consumption, a Layered Dynamic Synchronization Energy-saving (LDSE) protocol is designed. By constructing a hierarchical network, employing implicit route exploration, multi-channel and multi-path communication, and time synchronization optimization, the protocol significantly reduces packet loss rate and system energy consumption. Experimental results demonstrate that the LDSE protocol outperforms the traditional Ad hoc On-Demand Distance Vector Routing Protocol (AODV) in terms of packet loss rate, energy consumption, and latency. Additionally, the proposed energy-saving algorithm significantly reduces system power consumption, with the node sleep-relay mode exhibiting optimal energy efficiency. Experimental verification confirms that the system achieves high reliability, low power consumption, and efficient data transmission, providing an effective IoT solution for forest fire prevention.

1 February 2024 in Electronics
Verified
Journal Article
Open access
PDF file
XLXiaowu Li
Xiaowu Li
JXJunjie Xu
Junjie Xu
RLRunxin Li
Runxin Li
LJLianyin Jia
Lianyin Jia
Jinguo YouJinguo You
Jinguo You
LoRaWAN is an emerging Low-Power Wide-Area Network (LPWAN) technology, widely adopted in various Internet of Things (IoT) applications due to its long transmission range, low power consumption, and robust anti-interference capabilities. However, using the ALOHA medium access control (MAC) protocol in LoRaWAN significantly reduces the packet delivery rate, particularly in high-density networks where end devices (EDs) access the network randomly. It seriously affects the overall network performance. This paper introduces the Circular Region Grouped Bit-Slot CGBS-LoRa MAC protocol to address this challenge. The protocol takes a proactive approach by allocating transmission parameters for end devices, executing regional segmentation based on the distance between EDs and the gateway using different spreading factors. Concurrently, improving the ALOHA access method ensures the efficient communication of EDs in the region. Experimental results demonstrate that our proposed protocol markedly improves the scalability of LoRa networks and minimizes device collisions compared to three other MAC protocols. Even as the LoRaWAN network expands, the proposed protocol maintains a high packet delivery rate and low latency.

7 June 2024 in IEEE Access
Verified
Journal Article
Open access
RLRunxin Li
Runxin Li
ZOZexian Ouyang
Zexian Ouyang
ZSZhenhong Shang
Zhenhong Shang
LJLianyin Jia
Lianyin Jia
XLXiaowu Li
Xiaowu Li
Multi-label learning is a subfield of machine learning that addresses the issue of each instance belonging to numerous class labels at the same time. However, in some real applications, we can only receive a partial set of labels for each instance due to the difficulty and high cost of labeling data. The vast majority of existing multi-label classification methods on missing labels rely on first- or second-order label correlation learning to fill in the original label space while building multi-label learning models with label-specific features; nevertheless, the single label correlation learning mechanism used in these methods is insufficient to maintain the consistency of the feature-label space. To address this issue, we propose the CLSML approach, which incorporates higher-order label correlation learning constraints in the classifier training model to complete missing labels while training the classifier. In addition, to improve the consistency of the feature-label space, we develop a two-stage second-order label correlation learning technique based on cosine similarity to further confine the label output. Furthermore, we employ the l 1 -norm regularizer to learn label-specific feature representations, followed by the l 2,1 -norm regularizer to constrain the row sparsity of the classification matrix and select label-common features. Experimental results comparing ten cutting-edge multi-label learning algorithms with missing labels on fourteen multi-label benchmark datasets demonstrate the effectiveness of our suggested approach.

9 July 2026 in Electronics
Verified
Journal Article
Open access
PDF file
XLXiaowu Li
Xiaowu Li
ZWZhichao Wang
Zhichao Wang
JSJinxia Shang
Jinxia Shang
Indoor passage monitoring requires people-count estimation, behavior recognition and identity association while avoiding privacy-invasive sensing. This paper reports an RFID-only corridor-style passage-monitoring framework that combines wearable EPC identity tags, a wall-mounted passive tag array and distance-aware RSSI temporal modeling. Identity-tag readings and multi-channel tag-array RSSI sequences are aligned on a unified reader-timestamp timeline. An effective behavior duration (EBD) mechanism is used as a rule-based valid-window screening step before model inference. Target count, behavior state and identity association are then estimated using distance-aware LSTM temporal fusion. The RSSI attenuation relationship is used as a physical motivation for feature design and distance-mode interpretation, rather than as an explicit loss constraint or separately validated physical prior. A subject-independent dataset was collected with 18 array tags and 18 volunteers across single-person, multi-person, crossing and following scenarios, yielding 11,148 EBD-valid windows. Under the EBD-valid event-window protocol, the proposed method achieves a mean absolute error (MAE) of 0.226, a root mean square error (RMSE) of 0.357, a Macro-F1 of 0.934 and an identity-association accuracy of 0.961. Relative to threshold rules, traditional machine learning and a single-branch LSTM evaluated on the same dataset, the MAE is reduced by 59.5%, 46.1% and 28.9%, respectively, and the RMSE is reduced by 55.8%, 43.5% and 28.9%, respectively. The results indicate that native RFID identity, spatial tag-array sensing, EBD screening and distance-aware temporal modeling can jointly support privacy-preserving passage monitoring under controlled corridor-like conditions.