Cumulative confidence-driven task offloading for object detection in maritime Internet of Things
Maritime mobile edge computing (MMEC) technology facilitates the deployment of computationally intensive object detection tasks on Maritime Internet of Things (MIoT) devices with limited computing resources. However, the dynamic marine network and environmental interference in feature extraction adv...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2025.1629563/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849720570793426944 |
|---|---|
| author | Yanglong Sun Wenqian Luo Weijian Xu Qiang Mei Haixia Peng Linhai Wei |
| author_facet | Yanglong Sun Wenqian Luo Weijian Xu Qiang Mei Haixia Peng Linhai Wei |
| author_sort | Yanglong Sun |
| collection | DOAJ |
| description | Maritime mobile edge computing (MMEC) technology facilitates the deployment of computationally intensive object detection tasks on Maritime Internet of Things (MIoT) devices with limited computing resources. However, the dynamic marine network and environmental interference in feature extraction adversely affect detection accuracy and cause delay. In this paper, we propose a cumulative confidence-driven joint scheduling strategy for image detection tasks in MMEC scenarios. The strategy employs lightweight and full models as the detection framework. Through an adaptive decision-making scheme for marine device image recognition, the proposed strategy accumulates results from different models within the framework to ensure quality of service (QoS). To obtain a dynamic offloading strategy that minimizes the total system cost of latency and energy consumption, the problem is divided into two subproblems, and a chemical reaction optimization algorithm is used to reduce the computational complexity. Then, a state normalization action project deep deterministic policy gradient (SNAP-DDPG) algorithm is proposed to handle environmental dynamics, achieving minimized system cost with satisfied QoS. The simulation results indicate that, compared to existing algorithms, the proposed SNAP-DDPG algorithm keeps object detection confidence, with latency reduced by 34.78%. |
| format | Article |
| id | doaj-art-ceeb776bdfa94f949e0efe6ad048f56b |
| institution | DOAJ |
| issn | 2296-7745 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj-art-ceeb776bdfa94f949e0efe6ad048f56b2025-08-20T03:11:54ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452025-07-011210.3389/fmars.2025.16295631629563Cumulative confidence-driven task offloading for object detection in maritime Internet of ThingsYanglong Sun0Wenqian Luo1Weijian Xu2Qiang Mei3Haixia Peng4Linhai Wei5Navigation Institute, Jimei University, Xiamen, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen, ChinaSchool of Ocean Information Engineering, Jimei University, Xiamen, ChinaNavigation Institute, Jimei University, Xiamen, ChinaSchool of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, ChinaIoT Laboratory, Longyan Research Center, Fujian Xinzhi Information Technology Co., LTD, Longyan, ChinaMaritime mobile edge computing (MMEC) technology facilitates the deployment of computationally intensive object detection tasks on Maritime Internet of Things (MIoT) devices with limited computing resources. However, the dynamic marine network and environmental interference in feature extraction adversely affect detection accuracy and cause delay. In this paper, we propose a cumulative confidence-driven joint scheduling strategy for image detection tasks in MMEC scenarios. The strategy employs lightweight and full models as the detection framework. Through an adaptive decision-making scheme for marine device image recognition, the proposed strategy accumulates results from different models within the framework to ensure quality of service (QoS). To obtain a dynamic offloading strategy that minimizes the total system cost of latency and energy consumption, the problem is divided into two subproblems, and a chemical reaction optimization algorithm is used to reduce the computational complexity. Then, a state normalization action project deep deterministic policy gradient (SNAP-DDPG) algorithm is proposed to handle environmental dynamics, achieving minimized system cost with satisfied QoS. The simulation results indicate that, compared to existing algorithms, the proposed SNAP-DDPG algorithm keeps object detection confidence, with latency reduced by 34.78%.https://www.frontiersin.org/articles/10.3389/fmars.2025.1629563/fullMaritime Internet of Thingsedge computingYOLOtask offloadingreinforcement learning |
| spellingShingle | Yanglong Sun Wenqian Luo Weijian Xu Qiang Mei Haixia Peng Linhai Wei Cumulative confidence-driven task offloading for object detection in maritime Internet of Things Frontiers in Marine Science Maritime Internet of Things edge computing YOLO task offloading reinforcement learning |
| title | Cumulative confidence-driven task offloading for object detection in maritime Internet of Things |
| title_full | Cumulative confidence-driven task offloading for object detection in maritime Internet of Things |
| title_fullStr | Cumulative confidence-driven task offloading for object detection in maritime Internet of Things |
| title_full_unstemmed | Cumulative confidence-driven task offloading for object detection in maritime Internet of Things |
| title_short | Cumulative confidence-driven task offloading for object detection in maritime Internet of Things |
| title_sort | cumulative confidence driven task offloading for object detection in maritime internet of things |
| topic | Maritime Internet of Things edge computing YOLO task offloading reinforcement learning |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2025.1629563/full |
| work_keys_str_mv | AT yanglongsun cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings AT wenqianluo cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings AT weijianxu cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings AT qiangmei cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings AT haixiapeng cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings AT linhaiwei cumulativeconfidencedriventaskoffloadingforobjectdetectioninmaritimeinternetofthings |