Recently updated on: 2026-01-08
Optimal Deployment of Solar Insecticidal Lamps with Cameras in Smart Agriculture
This paper proposes a solar insecticidal lamp(SIL) video IoT system integrating cameras and its optimized deployment method, aiming to simultaneously address the dual challenges of green pest control in farmland and theft and vandalism prevention for high-value equipment. The paper details the architecture design of SIL-IoVTs, where cameras are integrated into some insecticidal lamp nodes to form novel SILC nodes, constructing a hybrid coverage network with both full and directional sensing models. Based on this, the paper innovatively establishes a joint optimization model that simultaneously satisfies regional and target coverage, and proposes an efficient two-layer optimization algorithm to solve this NP-hard problem with the goal of minimizing the total system cost. Extensive simulation experiments compare the performance of the algorithm with existing solutions under different parameters and market prices, verifying the effectiveness and advancement of the proposed method in significantly reducing system deployment costs. The proposed optimization model and algorithm provide important theoretical and technical support for the practical application of collaborative management of pest control and equipment safety in smart agriculture.
[1] Pengju Si, Yuhao Zhang, Hui Zhang, Qin Su, Xiaoyuan Jing, Lei Shu, “Optimal Deployment of Solar Insecticidal Lamps with Cameras in Smart Agriculture,” in IEEE Transactions on Green Communications and Networking, doi: 10.1109/TGCN.2025.3592412.
SILDSO: Dynamic Switching Optimization Scheme for Solar Insecticidal Lamp Based on Multi-Pest Phototactic Rhythm
This paper systematically addresses the critical issue of energy management in SIL-IoT that neglects the rhythmic behavioral diversity of multiple pests. The limitations of conventional single-pest models are overcome through the first-time integration of nocturnal activity characteristics from major rice pests, including Cnaphalocrocis medinalis and Chilo suppressalis. An optimized dynamic switching control and energy management scheme is subsequently proposed based on a hybrid model of pest phototactic rhythm. By comprehensively considering energy consumption, residual energy, and energy cost, the proposed scheme was validated through simulations of an intelligent PSO-based switching control scheme, demonstrating significant performance improvements and excellent robustness under various initial energy conditions. Simulation results demonstrate that, compared with the conventional switching control scheme, the dynamic switching control scheme achieves the 17.7% improvement in the average insecticidal rate.
[1] Yao H, Shu L, Yang X, et al. SILDSO: Dynamic Switching Optimization Scheme for Solar Insecticidal Lamp Based on Multi-Pest Phototactic Rhythm[J]. Sensors, 2025, 25(23): 7332.
TeaWeeding-Action: a vision-based dataset for weeding behavior recognition in tea plantations
This study introduces a novel publicly available computer vision dataset specifically designed for weeding behavior analysis in tea plantations. Targeting the pressing challenges posed by weed infestations and aligning with global food security strategies, the dataset aims to advance intelligent weeding behavior recognition systems. The collection comprises 108 high-definition video sequences and 6,473 annotated images, capturing a wide range of weeding activities in real tea plantation environments. Data acquisition followed a hybrid approach combining field recordings with web-crawled resources, and encompasses six categories of weeding behaviors: manual weeding, tool-assisted weeding, machine-based weeding, tool-specific actions (including hoe and rake), handheld weeding machine use, and non-working states. A key innovation of the dataset lies in its multi-view acquisition strategy, integrating frontal, lateral, and top-down perspectives to ensure robust three-dimensional understanding of weeding behaviors. Annotations are provided in both COCO and YOLO formats, ensuring compatibility with mainstream object detection frameworks. Benchmark evaluations conducted with advanced algorithms such as YOLOv8, SSD, and Faster R-CNN demonstrate the effectiveness of the dataset, with Faster R-CNN achieving a mean Average Precision (mAP) of 82.24%. The proposed dataset establishes a valuable foundation for the development of intelligent weeding robots, precision agriculture monitoring systems, and computer vision applications in complex agricultural environments.
[1] Ru Han, Xinyi Liang, Lei Shu, Xiaoyuan Jing , Fan Yang, Renjie Tian, “TeaWeeding-Action: a vision-based dataset for weeding behavior recognition in tea plantations.” Frontiers in Plant Science, 2025 16:1722007. doi: 10.3389/fpls.2025.1722007
TeaPickingNet: Towards Robust Recognition of Fine-Grained Picking Actions in Tea Gardens Using an Attention-Enhanced Framework
This paper proposes a novel deep learning framework for picking behavior recognition tailored to complex tea plantation environments. We first construct a large-scale, annotated dataset comprising 12,195 images across 7 behavior categories, collected from both field and web sources, capturing a diverse range of geographic, temporal, and environmental conditions. To address occlusion and multi-scale detection challenges, we enhance YOLOv5 by integrating an Exponential Moving Average attention mechanism, Complete Intersection over Union loss, and Atrous Spatial Pyramid Pooling, achieving a 73.6% mAP@0.5, representing an 11.6% relative improvement over the baseline model, which indicates a notable enhancement in detection accuracy under complex tea garden conditions. Furthermore, we propose an SE-Faster R-CNN model by embedding Squeeze-and-Excitation channel attention modules and anchor box optimization strategies, which significantly boosts performance in complex scenarios. A lightweight visual interface for real-time image and video-based detection is also developed to enhance the practical deployability of the system. Experimental results demonstrate the effectiveness, robustness, and real-time potential of the proposed system in recognizing tea garden behaviors under real field conditions.
[1] Ru Han, Ye Zheng, Lei Shu, and Grzegorz Cielniak, “TeaPickingNet: Towards Robust Recognition of Fine-Grained Picking Actions in Tea Gardens Using an Attention-Enhanced Framework.” Agriculture, 2025 15, no. 23: 2441. doi: 10.3390/agriculture15232441
An Image Dataset for Analyzing Tea Picking Behavior in Tea Plantations
As the practice of tea picking in China gradually shifts towards intelligent and mechanized methods, artificial intelligence recognition technology has become a crucial tool, showing great potential in recognizing large-scale tea picking operations and various picking behaviors. Constructing a comprehensive database is essential for these advancements. The newly developed Tea Garden Harvest Dataset offers several advantages that have a positive impact on tea garden management: 1) Enhanced image diversity: through advanced data augmentation techniques such as rotation, cropping, enhancement, and flipping, our dataset provides a rich variety of images. This diversity improves the model’s ability to accurately recognize tea picking behaviors under different environments and conditions. 2) Precise annotations: every image in our dataset is meticulously annotated with boundary box coordinates, object categories, and sizes. This detailed annotation helps to better understand the target features, enhancing the model’s learning process and overall performance. 3) Multi-Scale training capability: our dataset supports multi-scale training, allowing the model to adapt to targets of different sizes.
[1] Ru Han, Ye Zheng, Renjie Tian, Lei Shu, Xiaoyuan Jing and Fan Yang, “An image dataset for analyzing tea picking behavior in tea plantations.” Frontiers in Plant Science, 2025 15:1473558. doi: 10.3389/fpls.2024.1473558.
A Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things with Respect to Partial Coverage and Energy Harvesting Requirements
Coverage is a fundamental issue in the Solar Insecticidal Lamps IoTs (SIL-IoTs). Compared to complete coverage, partial coverage emerges as the preferred strategy for deploying SILs within a limited budget, as this deployment solution offers the highest cost-effectiveness. In this paper, we concentrate on studying the constrained SILs deployment problem, taking into account partial coverage and energy harvesting requirements, which we refer to as the cSILDP-PCEH problem. In this context, the positions for deploying SILs are restricted to a weighted set of candidate locations on the ridges. The weight assigned to each candidate location reflects the energy harvesting potential of the SIL deployed at that position. Our objective is to deploy a group of SILs in a subset of these candidate locations, ensuring a high overall energy harvesting potential, network connectivity, and achieving partial coverage. Due to the NP-hard nature of the problem, we introduce an approximation algorithm with a provable performance ratio tailored to our problem. Finally, we conduct a theoretical analysis of our proposed algorithm and perform extensive simulations. The simulation results demonstrate that the proposed algorithm achieves a minimum improvement of 16.45% in energy harvesting potential while preserving network connectivity and maintaining a comparable coverage level.
Fig 1. Diagram illustrating the low effective coverage of SILs as a consequence of the mandatory requirement for complete coverage.
Fig 2. Optimal deployment solution of SILs by five algorithms
[1] F. Yang, X. Tian, Z. Zhang, L. Shu and X. Jing, “A Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things with Respect to Partial Coverage and Energy Harvesting Requirements,” in IEEE Transactions on Sustainable Computing, doi: 10.1109/TSUSC.2025.3591808.
SILIC-Intelligent on-off Control for Networked Solar Insecticidal Lamps
The Solar Insecticidal Lamp (SIL) is an innovative green control device. Nevertheless, a major challenge is often encountered when carrying out insecticidal work. The substantial energy consumption required to turn on the SIL, coupled with the extension of insecticidal working time during the low pest activity periods, can result in low energy efficiency. Especially when the energy storage level is below 50%, the inefficient use of energy significantly reduces the effectiveness of pest control. Consequently, an ineffective on/off scheme for these lamps may lead to suboptimal energy utilization.
In this paper, we introduce the Solar Insecticidal Lamp Intelligent Energy Management Scheme (SIL-IEMS) to address the challenge of inefficient energy utilization in the Solar Insecticidal Lamp Internet of Things (SIL-IoT). SIL-IEMS primarily utilizes genetic algorithm(GA) and greedy algorithms to optimize insecticidal working time by considering constraints such as residual energy and the number of trap pests.
[1] Heyang Yao, Lei Shu*, Yuli Yang, Miguel Martínez-García, Wei Lin. SILIC: Intelligent On/Off Control for Networked Solar Insecticidal Lamps[J]. IEEE-CAA Journal of Automatica Sinica. 2024.
An Insecticidal Counting Method Based on Discharge Sound and Discharge Voltage of Solar Insecticidal Lamp
Aiming at the problem of inaccuracy of existing pest counting methods for solar insecticidal lamps, a pest counting method for solar insecticidal lamps based on the fusion of voltage and sound is designed. To solve the problem of repeated counting of a single pest, the sound analog data is processed and a method of counting adjacent pulse intervals based on MFCC features is proposed, which effectively reduces repeated counting. Machine learning is used to make decisions on both voltage and sound counting methods to count the final number of pests killed. Based on the designed method, it is validated in an agricultural environment and its accuracy is 93.28%.
[1] Z. Jiang, L Shu*, X. Yang, K. Huang, H. Yao and Q. Su, “An Insecticidal Counting Method Based on Discharge Sound and Discharge Voltage of Solar Insecticidal Lamp” in IEEE Transactions on Consumer Electronics.
Rethinking Sustainable Sensing in Agricultural Internet of Things: From Power Supply Perspective
Agricultural Internet of Things (IoT) is expected to address several challenges facing the current agriculture industry, including food production, food safety, ecological environment protection, and food waste. However, before achieving this blueprint, a fundamental problem that should be addressed is the sustainability. Unfortunately, solar energy harvesting, which is today’s common approach for sustainable agricultural IoT, has many limitations and can barely support future development. This article bridges this gap by proposing a versatile power supply paradigm, called PowerEdge, that organically integrates ambient energy harvesting, distributed energy storage, wireless power transfer, and intelligent reflecting surface techniques to achieve sustainable smart agricultural operations. A proof of concept with commercially available products is also presented, along with extensive experimental studies in five scenarios. Several interesting novel observations are found. Finally, four technical challenges and four open research issues associated with the proposed solution are discussed.
[1] Ye Liu, Dong Li, Bangsong Du, Lei Shu and Guangjie Han, “Rethinking Sustainable Sensing in Agricultural Internet of Things: From Power Supply Perspective,” in IEEE Wireless Communications, vol. 29, no. 4, pp. 102-109, August 2022, doi: 10.1109/MWC.004.2100426.
Pests Phototactic Rhythm Driven Solar Insecticidal Lamp Device Evolution: Mathematical Model Preliminary Result and Future Directions
This study presents for the first time the Solar Insecticidal Lamp versions 1.0 to 5.0, pioneering the mathematical model of pest phototactic rhythm based on four major pests and integrating this model with the solar insecticidal lamp. The research accurately predicts the nocturnal activity peaks of pests, providing a solid scientific basis for optimizing the operation times of devices such as solar insecticidal lamps. This innovative model not only significantly enhances the energy efficiency of solar insecticidal lamps but also marks a major advancement in the field of agricultural electronics, contributing essential technical support for the intelligent and sustainable development of agriculture. Additionally, the study explores the differences between static mathematical models and dynamic artificial intelligence (AI) models and looks ahead to the potential of applying dynamic AI models in solar insecticidal lamp. This forward-thinking consideration opens a new chapter in agricultural pest management technology, heralding innovative developments in intelligent pest management and introducing new research directions and application prospects in the field of agricultural technology.
[1] Heyang Yao, Lei Shu, Wei Lin, Kai Huang, Miguel Martínez-García, Xiuguo Zou, “Pests Phototactic Rhythm Driven Solar Insecticidal Lamp Device Evolution: Mathematical Model Preliminary Result and Future Directions,” IEEE Open Journal of the Industrial Electronics Society, 2024
A Trajectory-Inspired Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things under Coverage and Maintenance Cost Considerations
As a special type of node, Solar Insecticidal Lamps (SILs) require regular maintenance to ensure effective insecticidal performance and accurate collection of pest information. While hiring professionals for management and maintenance is a viable solution, it comes with the drawback of high maintenance costs. An effective approach to reducing these costs is deploying SILs along routes frequently traversed by Agricultural Workers (AWs), as these tasks can be easily incorporated into their routine. Therefore, inspired by the trajectory of high-density AWs, this paper focuses on studying the constrained SIL Deployment Problem under Coverage and Maintenance Cost considerations. In this problem, SIL nodes are deployed at a limited set of weighted Candidate Locations (CLs) situated on the ridges. The objective of cSILDP-CMC is to select a subset of CLs for SIL placement, maximizing coverage while keeping the total maintenance cost within the allocated budget.
[1] Fan. Yang, Lei. Shu, “A Trajectory-Inspired Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things under Coverage and Maintenance Cost Considerations,” in IEEE Transaction on AgriFood Electronic. DOI: 10.1109/TAFE.2024.3349566
Security and Privacy in Solar Insecticidal Lamps Internet of Things: Requirements and Challenges
In this paper, we describe the overall security requirements of SIL-IoT and present an extensive survey of security and privacy solutions for SIL-IoT. We investigate the background and logical architecture of SIL-IoT, discuss SIL-IoT security scenarios, and analyze potential attacks. Starting from the security requirements of SIL-IoT we divide them into six categories, namely privacy, authentication, confidentiality, access control, availability, and integrity. Next, we describe the SIL-IoT privacy and security solutions, as well as the blockchain-based solutions. Based on the current survey, we finally discuss the challenges and future research directions of SIL-IoT.
[1] Qingsong Zhao, Lei Shu*, Kailiang Li, Mohamed Amine Ferrag, Ximeng Liu, and Yanbin Li. Security and Privacy in Solar Insecticidal Lamps Internet of Things: Requirements and Challenges[J]. IEEE/CAA Journal of Automatica Sinica. 2023. doi: 10.1109/JAS.2023.123870
A Novel Accurate Insecticidal Counting Method Based on Solar Insecticidal Lamp using Machine Learning
The contributions of this study are as follows:
1) The testbed about SIL is modified with special design by changing high voltage package and adding sound sensor module as well as voltage comparator module, which can meet the requirements of both key parameter acquisition and low cost;
2) The relationship between insecticidal counting and Pulse Number of Insecticidal Discharges (PNID) as well as Pulse Number of Insecticidal Sounds (PNIS) is investigated and exhibited a significant positive correlation;
3) The machine learning (ML) algorithm is introduced into this application with an accuracy of 0.85, which is greatly beneficial to the popularization and application of this counting technology.
Fig. 1. Inspiration from the sound wave diagram in (c) of the two different insecticidal phenomena in (a) and (b).
[1] Kai Huang, Lei Shu, Kailiang Li, Yuyu Feng, Xing Yang, Ye Liu, Fan Yang, and Yan Zhu. A Novel Accurate Insecticidal Counting Method Based on Solar Insecticidal Lamp using Machine Learning[J].IEEE Transactions on Consumer Electronics, 2023.
A Scheme for Pest-Dense Area Localization with Solar Insecticidal Lamps Internet of Things under Asymmetric Links
Propose an algorithm named as PALS for the pest-dense area localization under asymmetric links with SIL-IoTs large-deployment scenarios. The cross-detection and the elimination of pest-dense area errors are introduced in detail. Accurately locating pest-dense areas under asymmetric links provides further theoretical support for accurate pest control in agricultural production scenarios.
Fig 1. Diagram of the PALS strategy for locating pest-dense areas. (a) find the inner and outer boundary nodes and determine the critical edge. (b) take the critical edge as the starting position, and explore for the next edge according to the left-hand rule. (c) get a boundary face until reaching the starting critical edge AB. (d) start the second round of exploration with the backup node information. (e) after two round of exploration is completed, a boundary of a pest-dense area is obtained.
[1] Yuan Li†, Bangsong Du†, Lin Luo, Yusheng Luo, Xing Yang, Ye Liu ,Lei Shu*,A Scheme for Pest-Dense Area Localization with Solar Insecticidal Lamps Internet of Things under Asymmetric Links, IEEE Transactions on AgriFood Electronics, 2023.
The phototactic rhythm of pests for the Solar Insecticidal Lamp: A review
1) We present background knowledge on pest phototactic rhythm from the pest management perspective and the current state of research on pest phototactic rhythm as summarised in our work. The application and benefits of pest phototropic rhythms in pest management are discussed in the pest’s characteristics and the smart agriculture challenge issues.
2) To deeply understand the phototactic rhythm of pests in different crops, a comprehensive research outline on the phototactic rhythm of pests is summarized. Among them, crops are divided into two main varieties: food crops (e.g., rice, soybean, and maize) and economic crops (e.g., cotton, vegetable, orchards, tea).
3) The key factors of pest phototropic rhythms are analyzed to provide data support for the agricultural planters. The key factors include the following four main aspects: meteorological conditions (e.g., temperature, humidity, precipitation, light intensity), insecticidal devices(e.g., wavelength and height of insecticidal devices), physiological states (e.g., sex, age, and dark adaptation), and others(e.g., crop varieties and natural enemies).
4) Finally, some research challenges about the pests phototactic rhythm are discussed.
Fig. 1 The related work on phototactic rhythm of pests
[1] Heyang Yao, Lei Shu, Fan Yang, Yinghao Jin, Yuli Yang. “The phototactic rhythm of pests for the Solar Insecticidal Lamp: A review.” Frontiers in Plant Science, 13 (2023): 5532. doi=10.3389/fpls.2022.1018711
Image dataset of tea chrysanthemums in complex outdoor scenes
The Scientific Value and Potential Applications of the Dataset: Due to the different flowering periods of tea chrysanthemums, it is quite difficult to obtain outdoor tea chrysanthemum images, resulting in insufficient data and insufficient training accuracy. At the same time, considering the changes in lighting, occlusion, and object scale, establishing a relevant chrysanthemum detection model for tea chrysanthemums in complex outdoor environments is a challenge. In this context, providing relevant data for researchers to further study the problems of large individual differences in tea chrysanthemums, complex environments, easy occlusion, and the difficulty in detecting chrysanthemum flowers, I need to provide relevant data to enable researchers to further investigate these issues. This will facilitate the acceleration of practical applications of deep learning algorithms in agriculture.
Fig. 1. The category to which the sample images belong and their number in the related chrysanthemum dataset: (A) Jinsihuangju-01314, (B) Hangbaiju-00063, (C) Bo-chrysanthemum-11093, (D) Wuyuanhuangju-03285, (E) Gongju-00002, and (F) Chuju-0011.
Fig. 2 (A) TES-1333R Solar Power Meter, (B) Mi 10 phone, and (C) Image acquisition scene, (D) Schematic diagram of the camera angles.
[1] Siyang Zang, Lei Shu, Kai Huang, Zhiyong Guan, Ru Han, Ravi Valluru, Xiaochan Wang, Jiaxu Bao, Ye Zheng, Yifan Chen. Image Dataset of Tea Chrysanthemums in Complex Outdoor Scenes. Frontiers in Plant Science, 2023, 14. DOI=10.3389/fpls.2023.1134911.
Insecticidal counting dataset based on one solar insecticidal lamp and two cameras
- Establish the relevant insecticidal counting model to accurately describe the insecticidal quantity by machine learning, and further describe the pests population density in the area where SIL are deployed. After finishing the insecticidal counting, the insecticidal quantity at different times can further facilitate the research on SIL energy management, including the time and duration of turning on and off the lamp.
Fig. 1 LM393 voltage comparator module (A), Printed Circuit Board (PCB) (B), Risym sound sensor module (C), and insecticidal lamp monitored by two cameras (D) are the major components of the testbed (E).
[1] Kai Huang, Lei Shu, Kailiang Li, Yuyu Feng, Zitian Jiang, Yan Zhu. Insecticidal Counting Dataset Based on One Solar Insecticidal Lamp and Two Cameras. Frontiers in Plant Science, 2022, 13. DOI=10.3389/fpls.2022.995118
SILOS: An Intelligent Fault Detection Scheme for Solar Insecticidal Lamp IoTs with Improved Energy Efficiency
- To the best of our knowledge, this is the first study that addresses the above issues (i.e., fault description and lightweight fault self-detection according to existing modules of SIL-IoTs nodes) by a systematic fault self-detection scheme (SILOS), including hardware design and a fault self-detection model.
- We developed an improved SIL-IoTs node with enhanced functionality to measure faulty conditions and reduce faults of SIL-IoTs.
- Based on the fault dictionary concept, faults of SIL-IoTs nodes are summarized and labeled systematically for the first time. Due to the limited energy and large-scale deployment of SIL-IoTs nodes, a concise report rather than all measured data is more suitable for fault detection. Therefore, faults of SIL-IoTs nodes are coded as one byte to reduce delay, energy consumption, and network traffic.
- An energy/resource efficient implementation of our proposed binary-based sliding window fault self-detection algorithm is performed on the microcontroller (e.g., limited data storage and computing capacities, including 20MHz CPU speed, 32KB program memory size, and 2KB RAM size).
[1] Xing Yang, Lei Shu*, Kailiang Li, Zhiqiang Huo, Sheng Shu, Edmond Nurellari , “SILOS: An Intelligent Fault Detection Scheme for Solar Insecticidal Lamp IoTs with Improved Energy Efficiency”, IEEE Internet of Things Journal, 2022.
A Partition-based Mobile Crowd Sensing-enabled Task Allocation for Solar Insecticidal Lamp Internet of Things Maintenance
1) Unlike MCS applied in an urban area, task allocation in a rural area cannot use commercial maps to plan paths directly. Inspired by the natural partition of farmland, this work establishes a novel mathematical farmland model by transforming a plane geographic map of farmland to a set of points.
2) We transfer the SILMP into an orienteering and combinatorial optimization problem to allocate appropriate tasks to participants toward efficient maintenance of the SILs. The purpose of optimization is to maximize the insecticide efficiency of SILs while minimizing total task cost. Then, using the natural partitioning of farms and the concept of face routing, we propose Partition-based Optimal Path Planning (POPP) to rapidly identify the optimum path and Cost-Efficiency-Balance-based Task Allocation (CEBT) to meet the designed goal.
3) The performance of the proposed methods is evaluated using synthetic data based on both the agriculture model and the mobility model.
[1] Yuanhao Sun, Edmond Nurellari, Weimin Ding, Lei Shu, Zhiqiang Huo, “A Partition-based Mobile Crowd Sensing-enabled Task Allocation for Solar Insecticidal Lamp Internet of Things Maintenance”, IEEE Internet of Things Journal, 2022. DOI: 10.1109/JIOT.2022.3175732
SA1D-CNN: A Separable and Attention Based Lightweight Sensor Fault Diagnosis Method for Solar Insecticidal Lamp Internet of Things
1) A lightweight 1D-CNN-based sensor fault diagnosis scheme for SIL-IoTs nodes is proposed, namely, separable and attention 1D-CNN (SA1D-CNN). By diagnosing faults in SIL-IoTs nodes, fault states are transmitted to the cloud rather than all measurements. In this work, we focus on a lightweight fault diagnosis scheme rather than an exhaustive survey of fault types in SIL-IoTs nodes.
2) Because data fluctuation cases are caused by high voltage pulse discharge of the SIL (no-fault state and may lead to the misdiagnosis of faults), we propose the time-channel attention module (TCAM) to enhance fault-related features and suppress irrelevant features.
3) To reduce diagnostic delay and data transmission, a lightweight and easy implementing fault diagnosis model (namely SA1D-CNN) is embedded and performed in the SIL-IoTs node for the first time. SA1D-CNN is composed of depthwise separable convolution and TCAM.
4）The diagnostic accuracy of the proposed method is verified in SIL-IoTs nodes. The results indicate that the proposed method has the best trade-off performance between diagnostic accuracy and computationally efficiency than the referenced algorithms.
[1] Xing Yang, Lei Shu, Kailiang Li, Zhiqiang Huo, Yu Zhang. SA1D-CNN: A Separable and Attention Based Lightweight Sensor Fault Diagnosis Method for Solar Insecticidal Lamp Internet of Things[J]. IEEE Open Journal of the Industrial Electronics Society, 2022. doi: 10.1109/OJIES.2022.3172899.
Target-Barrier Coverage Improvement in an Insecticidal Lamps Internet of UAVs
We combine the advantages of UAVs and ILs-IoTs to construct a new IL-IoUAVs framework in the practical applications of pest control for smart agriculture.
We formulate the optimisation problem of the deployment as the minimisation of the number of IL-UAVs for constructing the target-barrier coverage, which the first study of the probabilistic sensing model in the target-barrier coverage problem, to the best of our knowledge.
We propose a deterministic deployment strategy to solve the optimisation problem for the deployment of IL-UAVs. After we make the analysis of the target-barrier circles and its properties, a merged algorithm is derived to construct the optimal $\epsilon$-target-barrier coverage.
Fig. 1: Our designed IL-UAV node and the architecture of an IL-IoUAV.
Pengju Si, Zhumu Fu, Lei Shu*, Yuli Yang, Kai Huang and Ye Liu. Target-Barrier Coverage Improvement in an Insecticidal Lamps Internet of UAVs[J]. IEEE Transactions on Vehicular Technology, 2022.
Physical Security and Safety of IoT Equipment: A Survey of Recent Advances and Opportunities
Xing Yang, Lei Shu*, Ye Liu, GP. Hancke, Ferrag Mohamedamine, Kai Huang. Physical Security and Safety of IoT Equipment: A Survey of Recent Advances and Opportunities[J]. IEEE Transaction on Industrial Informatics, 2021.
On Enabling Mobile Crowd Sensing for Data Collection in Smart Agriculture - A Vision
(i) Based on the deployed MCS system, we review the typical MCS’s systems for different urban scenarios. Compared with the existing agricultural data collection methods, i. e., RSS, UAV, WSN, and CS, we find that AMCSs have significant benefits in flexibility, collecting implicit data, and low-cost requirements. However, we also note that AMCSs may still possess limitations regarding data integrity and quality to be considered a future work.
(ii) We analyze the crucial factors of combining MCS with agriculture. These factors, including the number of potential users, developed agriculture-related APPs, farmer’s experience, and cooperation between agribusiness and farmers, exist implicit relationships. Farmers, who collaborate with agribusiness, are willing to participate in the sensing task of AMCS-enabled agriculture, sharing their collected data to the AMCS platform with the APPs. Thus, agribusiness can also acquire extensive and valuable data from the AMCS platform or even farmers directly to improve their equipment and techniques. Meanwhile, agribusiness can offer more advanced technical guidance to help farmers increase income. Thus, positive feedback will form in this way.
(iii) We propose seven application scenarios of AMCS based on existing agricultural problems. By analyzing agricultural characteristics, we present several general research issues of AMCS for the future. Specially, we take the problem of maintaining SILs as a special case to discuss the specific research in a natural scene.
Yuanhao Sun, Weimin Ding, Lei Shu, Kailiang Li, Yu Zhang, Zhangbing Zhou, Guangjie Han, On Enabling Mobile Crowd Sensing for Data Collection in Smart Agriculture – A Vision[J]. IEEE Systems Journal, 2021.
Design and Prospect of Anti-theft and Anti-destruction of Nodes in Solar Insecticidal Lamps Internet of Things
Based on the serious fact of theft and destruction of solar insecticidal lamp (SIL) in a long time, the anti-theft and anti-destruction hardware system of SIL is designed (Fig.1), and unmanned aerial vehicle insecticidal lamp (UAV-IL) (Fig.2), as an auxiliary equipment, is added to realize the anti-theft and anti-destruction of SIL in Solar Insecticidal Lamps Internet of Things (SIL-IoTs).
Kai Huang, Lei Shu*, Kailiang Li, Xing Yang, Yan Zhu, Xiaochan Wang, Qin Su. Design and Prospect of Anti-theft and Anti-destruction of Nodes in Solar Insecticidal Lamps Internet of Things[J]. Smart Agriculture, 2021. DOI: 10.12133/j.smartag.2021.3.2.202102-SA034. (In Chinese with English abstract)
(黄凯, 舒磊, 李凯亮, 杨星, 朱艳, 汪小旵, 苏勤. 太阳能杀虫灯物联网节点的防盗防破坏设计及展望[J]. 智慧农业(中英文), 2021, 3(1): 129-143.)
Optimal Deployment of Solar Insecticidal Lamps over Constrained Locations in Mixed-Crop Farmlands
Fan Yang, Lei Shu*, Yuli Yang, Guangjie Han, Simon Pearson, Kailiang Li. Optimal Deployment of Solar Insecticidal Lamps over Constrained Locations in Mixed-Crop Farmlands[J]. IEEE Internet of Things Journal, 2021, 8(16):13095-13114.
A Survey on Smart Agriculture: Development Modes, Technologies, and Security and Privacy Challenges
1) The development status of smart agriculture is summarized and classified into three typical development modes: precision agriculture, facility agriculture, and order agriculture. Furthermore, 7 key technologies and 11 key applications are
discussed.
2) Security and privacy countermeasures are summarized as (1) authentication and access control, (2) privacy-preserving, (3) blockchain-based solutions for data integrity, (4) cryptography and key management, (5) physical countermeasures, and (6) intrusion detection systems.
3) Potential security challenges of smart agriculture are highlighted and divided into two aspects: (1) agricultural production and (2) information technology.
4) Agricultural equipment will also affect the security strategy. For instance, it is suggested that high voltage discharge interference of Solar Insecticidal Lamps Internet of Things should be considered as attacks or have an impact on security strategy. We found that high voltage discharge interference has an impact on data acquisition from the results of our additional experiments in this paper.
Xing Yang, Lei Shu*, Jianing Chen, Mohamed Amine Ferrag, Jun Wu, Edmond Nurellari, Kai Huang. A Survey on Smart Agriculture: Development Modes, Technologies, and Security and Privacy Challenges[J]. IEEE-CAA Journal of Automatica Sinica, 2021, 8(2): 273-302.
Improved Coverage and Connectivity via Weighted Node Deployment in Solar Insecticidal Lamp Internet of Things
Fan Yang, Lei Shu*, Yuli Yang, Ye Liu, Timothy Gordon. Improved Coverage and Connectivity via Weighted Node Deployment in Solar Insecticidal Lamp Internet of Things[J]. IEEE Internet of Things Journal, 8(12):10170-10186.
Collaborative Industrial Internet of Things for Noise Mapping：Prospects and Research Opportunities
Exposure to environmental noise has harmful effects on human health from both physiological and mental aspects, such as annoyance, sleep disorders, cardiovascular disease, or even permanent hearing impairment. This problem is further exacerbated in the industrial environments, where millions of workers are exposed to occupational noise. Therefore, noise mapping is essential and the first step to solve noise pollution problem.
However, either sound level meter-based measurement or computational model-based simulation, the two main noise mapping approaches at present, has its own limitations. To promote the development of noise mapping techniques, this article presents:
- The framework of collaborative Industrial Internet of Things (IIoT) for next-generation noise mapping, especially in industrial parks.
- Moreover, other potential applications beyond noise mapping for smart factory are listed.
- Lastly, the fundamental issues and suggestions for future research are discussed in detail.
Ye Liu, Lei Shu*, Zhiqiang Huo, Kim-Fung Tsang, Gerhard P. Hancke. Collaborative Industrial Internet of Things for Noise Mapping：Prospects and Research Opportunities. IEEE Industrial Electronics Magazine, 2021, 15(2):52-64.
High Voltage Discharge Exhibits Severe Effect on ZigBee-based Device in Solar Insecticidal Lamps Internet of Things
The main contributions are summarized as follows for many research communities, e.g., Internet of Things (IoTs), WSNs, reliability, and security:
1) If there is not a special design for a device that can release high voltage pulse discharge, we should not deploy the WSNs node nearby the device;
2) The use of the above device, as a method to attack WSNs, can lead to the abnormal working state.
[1] Kai Huang, Kailiang Li, Lei Shu*, Xing Yang. Demo Abstract: High Voltage Discharge Exhibits Severe Effect on ZigBee-based Device in Solar Insecticidal Lamps Internet of Things. IEEE International Conference on Computer Communications (IEEE INFOCOM 2020), July 7th-9th, 2020, Virtual Conference.
[2] Kai Huang, Kailiang Li, Lei Shu*, Xing Yang, Timothy Gordon, Xiaochan Wang*. High Voltage Discharge Exhibits Severe Effect on ZigBee-based Device in Solar Insecticidal Lamps Internet of Things. IEEE Wireless Communications, 2020, 27(6): 140-145.
Photovoltaic Agricultural Internet of Things towards Realizing the Next Generation of Smart Farming
Kai Huang, Lei Shu*, Kailiang Li, Fan Yang, Guangjie Han, Xiaochan Wang*, Simon Pearson. Photovoltaic Agricultural Internet of Things towards Realizing the Next Generation of Smart Farming[J], IEEE Access, 2020, 8: 76300-76312.
From Industry 4.0 to Agriculture 4.0: Current Status, Enabling Technologies, and Research Challenges
Ye Liu, Xiaoyuan Ma, Lei Shu, Gerhard Hancke, Adnan M. Abu-Mahfouz, From Industry 4.0 to Agriculture 4.0: Current Status, Enabling Technologies, and Research Challenges[J]. IEEE Transactions on Industrial Informatics, 2021, 17(6):4322-4334.
Internet of Things for Noise Mapping in Smart Cities: State-of-the-Art and Future Directions
Ye Liu, Xiaoyuan Ma, Lei Shu, Qing Yang, Yu Zhang, Zhiqiang Huo, Zhangbing Zhou, Internet of Things for Noise Mapping in Smart Cities: State-of-the-Art and Future Directions[J]. IEEE Network, 2020, 34(4):112-118.
A Partition-Based Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things
Fan Yang, Lei Shu*, Kai Huang, Kailiang Li, Guangjie Han, Ye Liu. A Partition-Based Node Deployment Strategy in Solar Insecticidal Lamps Internet of Things[J]. IEEE Internet of Things Journal, 2020, 7(11): 11223-11237.
Security and Privacy for Green IoT-based Agriculture: Review, Blockchain solutions, and Challenges
Mohamed Amine Ferrag, Lei Shu*, Xing Yang, Abdelouahid Derhab, Leandros Maglaras. Security and Privacy for Green IoT-Based Agriculture: Review, Blockchain Solutions, and Challenges[J]. IEEE Access, 2020, 8: 32031-32053.
Characteristics analysis and challenges for fault diagnosis in solar insecticidal lamps Internet of Things
Xing Yang, Lei Shu*, Kai Huang, Kailiang Li, Zhiqiang Huo, Yanfei Wang, Xinyi Wang, Qiaoling Lu, Yacheng Zhang. Characteristics Analysis and Challenges for Fault Diagnosis in Solar Insecticidal Lamps Internet of Things[J], Smart Agriculture, 2020, 2(02): 11-27. (In Chinese with English abstract)
(杨星, 舒磊, 黄凯, 李凯亮, 霍志强, 王彦飞, 王心怡, 卢巧玲, 张亚成. 太阳能杀虫灯物联网故障诊断特征分析及潜在挑战[J]. 智慧农业(中英文), 2020, 2(2): 11-27.)
Solar Insecticidal Lamps Internet of Things: Review and Open Research Issues
Kailiang Li, Lei Shu, Kai Huang, Yuanhao Sun, Fan Yang, Yu Zhang, Zhiqiang Huo, Yanfei Wang, Xinyi Wang, Qiaoling Lu, Yacheng Zhang. Research and Prospect of Solar Insecticidal Lamps Internet of Things[J]. Smart Agriculture, 2019, 1(3) : 13-28. (In Chinese with English abstract)
(李凯亮, 舒磊, 黄凯, 孙元昊, 杨帆, 张宇, 霍志强, 王彦飞, 王心怡, 卢巧玲, 张亚成. 太阳能杀虫灯物联网研究现状与展望[J]. 智慧农业(中英文), 2019, 1(3): 13-28.)