Machine learning algorithms for wireless sensor networks: A survey

Accurate individual tree crown (ITC) segmentation from scanned point clouds is a fundamental task in forest biomass monitoring and forest ecology management. Light detection and ranging (LiDAR) as a mainstream tool for forest survey is advancing the pattern of forest data acquisition. In this study, we performed a novel deep learning framework directly processing the forest point clouds belonging to the four forest types (i.e., the nursery base, the monastery garden, the mixed forest, and the defoliated forest) to realize the ITC segmentation. The specific steps of our approach were as follows: first, a voxelization strategy was conducted to subdivide the collected point clouds with various tree species from various forest types into many voxels. These voxels containing point clouds were taken as training samples for the PointNet deep learning framework to identify the tree crowns at the voxel scale. Second, based on the initial segmentation results, we used the height-related gradient information to accurately depict the boundaries of each tree crown. Meanwhile, the retrieved tree crown breadths of individual trees were compared with field measurements to verify the effectiveness of our approach. Among the four forest types, our results revealed the best performance for the nursery base (tree crown detection rate r = 0.90; crown breadth estimation R2 > 0.94 and root mean squared error (RMSE) 0.88 and RMSE 0.85 and RMSE 0.79 and RMSE < 0.7 m. Our method presents a robust framework inspired by the deep learning technology and computer graphics theory that solves the ITC segmentation problem and retrieves forest parameters under various forest conditions.

https://www.mdpi.com/1999-4907/12/2/131/pdf

Individual Tree Crown Segmentation Directly from UAV-Borne LiDAR Data Using the PointNet of Deep Learning

Mobile elements trajectory optimization is one of the most important and efficient ways to enhance the performance of wireless sensor networks (WSNs). In the last 15 years, extensive research has been done in this area, but less effort has been devoted to providing a concise review of the broader area. This article surveys the role of mobile elements trajectory optimization in the performance improvement of WSNs. The complete survey has been done based on three major aspects: applications, trajectory techniques and domains used to formulate the trajectory. Under these three aspects, large numbers of schemes are discussed, along with their sub-aspects. A comparative analysis using eight important parameters, like trajectory pattern, number of mobile elements, speed, mobile element type, etc., is presented in a chronological fashion. The paper also points out the merits and demerits of each scheme described. Based on the current research, we have identified some research domains in this area that need more attention and further exploration.

A comprehensive survey on trajectory schemes for data collection using mobile elements in WSNs

Wireless sensor network is effective for data aggregation and transmission in IoT environment. Here, the sensor data often contain a significant amount of noises or redundancy exists, and thus, the data are aggregated to extract meaningful information and reduce the transmission cost. In this paper, a novel data aggregation scheme is proposed based on clustering of the nodes and extreme learning machine (ELM) which efficiently reduces redundant and erroneous data. Mahalanobis distance-based radial basis function is applied to the projection stage of the ELM to reduce the instability of the training process. Kalman filter is also used to filter the data at each sensor node before transmitted to the cluster head. Computer simulation with real datasets shows that the proposed scheme consistently outperforms the existing schemes in terms of clustering accuracy of the data and energy efficiency of WSN.

Efficient data aggregation with node clustering and extreme learning machine for WSN

Several studies have demonstrated the benefits of using a mobile sink (MS) to reduce energy consumption resulting from multi-hop data collection using a static sink in wireless sensor networks (WSNs) However, using MS may increase data delivery latency as it needs to visit each sensor node in the network to collect data This is a critical issue in delay-sensitive applications where all sensed data must be gathered within a given time constraint In this paper, we propose a distributed data gathering protocol utilizing MS for WSNs The proposed protocol designs a trajectory for the MS, which minimizes energy consumption and delay Our protocol operates in four main phases: data sensing, rendezvous point (RP) selection, trajectory design, and data gathering In data sensing, a number of deployed sensor nodes keep sensing the target field for a specific period of time to capture events Then, using a cluster-based RP selection algorithm, some sensor nodes are selected to become RPs based on local information The selected RPs are then used to determine a trajectory for the MS To do so, we propose three trajectory design algorithms that support different types of applications, namely reduced energy path (REP), reduced delay path (RDP), and delay bound path (DBP) The MS moves through the constructed path to accomplish its data gathering according to an effective scheduling technique that is introduced in this work We validate the proposed protocol via extensive simulations over several metrics such as energy, delay, and time complexity

Distributed trajectory design for data gathering using mobile sink in wireless sensor networks

In Rechargeable Wireless Sensor Networks (R-WSNs), in order to achieve the maximum data collection rate it is critical that sensors operate in very low duty cycles because of the sporadic availability of energy. A sensor has to stay in a dormant state in most of the time in order to recharge the battery and use the energy prudently. In addition, a sensor cannot always conserve energy if a network is able to harvest excessive energy from the environment due to its limited storage capacity. Therefore, energy exploitation and energy saving have to be traded off depending on distinct application scenarios. Since higher data collection rate or maximum data collection rate is the ultimate objective for sensor deployment, surplus energy of a node can be utilized for strengthening packet delivery efficiency and improving the data generating rate in R-WSNs. In this work, we propose an algorithm based on data aggregation to compute an upper data generation rate by maximizing it as an optimization problem for a network, which is formulated as a linear programming problem. Subsequently, a dual problem by introducing Lagrange multipliers is constructed, and subgradient algorithms are used to solve it in a distributed manner. At the same time, a topology controlling scheme is adopted for improving the network's performance. Through extensive simulation and experiments, we demonstrate that our algorithm is efficient at maximizing the data collection rate in rechargeable wireless sensor networks.

https://www.mdpi.com/1424-8220/16/8/1201/pdf

Maximum Data Collection Rate Routing Protocol Based on Topology Control for Rechargeable Wireless Sensor Networks

In rechargeable wireless sensor networks (R-WSNs), due to limited and dynamic energy supplyment, a sensor can not be always have enough energy when a network can gather excessive energy from the environment. At the same time, it is critical for higher data collection rate when sensors are working at a very low duty cycle due to sporadic availability of energy. Therefore, the sensors with surplus energy can be scheduled for strengthening packet delivery efficiency and improving data collection rate. Considering the data has some relation and redundancy, in this paper, an algorithm is proposed to achieve a high data generation rate for data-gathering trees based on data aggregation technology which can maximize data gather rate as an optimization problem for improving data generation rate in rechargeable wireless networks. An initial data-gathering tree is established and the maximum data collection rate routing is achieved by adjusting the heavily loaded and medium heavily loaded nodes. The data collection rate of the data-gathering tree produced by the proposed algorithm has been shown to be significantly higher than that of the initial tree. The simulation and experiments demonstrate that the proposed algorithm is efficient to maximize data collection rate in R-WSNs.

Maximum data collection rate routing for data gather trees with data aggregation in rechargeable wireless sensor networks

Diseases and insect pests of tea leaves cause huge economic losses to the tea industry every year, so the accurate identification of them is significant. Convolutional neural networks (CNNs) can automatically extract features from images of tea leaves suffering from insect and disease infestation. However, photographs of tea tree leaves taken in a natural environment have problems such as leaf shading, illumination, and small-sized objects. Affected by these problems, traditional CNNs cannot have a satisfactory recognition performance. To address this challenge, we propose YOLO-Tea, an improved model based on You Only Look Once version 5 (YOLOv5). Firstly, we integrated self-attention and convolution (ACmix), and convolutional block attention module (CBAM) to YOLOv5 to allow our proposed model to better focus on tea tree leaf diseases and insect pests. Secondly, to enhance the feature extraction capability of our model, we replaced the spatial pyramid pooling fast (SPPF) module in the original YOLOv5 with the receptive field block (RFB) module. Finally, we reduced the resource consumption of our model by incorporating a global context network (GCNet). This is essential especially when the model operates on resource-constrained edge devices. When compared to YOLOv5s, our proposed YOLO-Tea improved by 0.3%–15.0% over all test data. YOLO-Tea’s AP0.5, APTLB, and APGMB outperformed Faster R-CNN and SSD by 5.5%, 1.8%, 7.0% and 7.7%, 7.8%, 5.2%. YOLO-Tea has shown its promising potential to be applied in real-world tree disease detection systems.

/pdf/yolo-tea-a-tea-disease-detection-model-improved-by-yolov5-289z5d48.pdf

YOLO-Tea: A Tea Disease Detection Model Improved by YOLOv5

Internet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine

Tea diseases have a significant impact on the yield and quality of tea during the growth of tea trees. The shape and scale of tea diseases are variable, and the tea disease targets are usually small, with the intelligent detection processes of tea diseases also easily disturbed by the complex background of the growing region. In addition, some tea diseases are concentrated in the entire area of the leaves, needing to be inferred from global information. Common target detection models are difficult to solve these problems. Therefore, we proposed an improved tea disease detection model called TSBA-YOLO. We use the dataset of tea diseases collected at the Maoshan Tea Factory in China. The self-attention mechanism was used to enhance the ability of the model to obtain global information on tea diseases. The BiFPN feature fusion network and adaptively spatial feature fusion (ASFF) technology were used to improve the multiscale feature fusion of tea diseases and enhance the ability of the model to resist complex background interference. We integrated the Shuffle Attention mechanism to solve the problem of difficult identifications of small-target tea diseases. In addition, we used data-enhancement methods and transfer learning to expand the dataset and relocate the parameters learned from other plant disease datasets to enhance tea diseases detection. Finally, SIoU was used to further improve the accuracy of the regression. The experimental results show that the proposed model is good at solving a series of problems encountered in the intelligent recognition of tea diseases. The detection accuracy is ahead of the mainstream target detection models, and the detection speed reaches the real-time level.

/pdf/tsba-yolo-an-improved-tea-diseases-detection-model-based-on-3dtyunrk.pdf

Di Bai

Papers

Maximum Data Collection Rate Routing Protocol Based on Topology Control for Rechargeable Wireless Sensor Networks

Maximum data collection rate routing for data gather trees with data aggregation in rechargeable wireless sensor networks

YOLO-Tea: A Tea Disease Detection Model Improved by YOLOv5

Internet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine

TSBA-YOLO: An Improved Tea Diseases Detection Model Based on Attention Mechanisms and Feature Fusion