Search

In this paper, a node detection method is proposed to detect the damaged parts of armor automatically. The traditional detection of armor damage is judged by experience first, and then the parts are decomposed and confirmed, which makes the problem solving time long and efficiency low. In this paper, the in-mold electronic decoration technology is used on the surface of armor, and the node displacement changes after the surface film is damaged are used to achieve the purpose of damage detection. By using the wavelet analysis, the singularity of the wavelet function can be found and the damaged part can be determined. The Lipschitz index can be used to judge the singularity of the wavelet function to detect the local damage on the armor surface. Finally, the changes of Lipschitz index of the signal with different damage degrees on the helmet deck were simulated. In terms of influencing factors of optimization process, moldex3D was used to simulate and analyze the damaged parts of armor—different injection molding parameter schemes were set to optimize the armor film. In the first stage, the displacement change at the damaged location is detected by the probe node through simulation. In the second stage, the armor was simulated by setting appropriate process parameters such as melt temperature, filling time, filling pressure, and filling time. In the third stage, the wavelet analysis and a Lipschitz index were used to detect the location of damaged nodes. In the fourth stage, the change curve of wavelet analysis is verified by the analysis experiment. Through the experimental verification, it can be seen that the position displacement of the damaged armor changes and the singularity is generated on the wavelet function to achieve the purpose of damage detection. The influencing factors of the film injection molding are temperature and pressure. Through the simulation analysis, we optimize the injection molding parameters of the film, thus improving the damage resistance of the armor. Finally, the optimal parameters of vulnerable parts are obtained and the optimization scheme is determined. [ABSTRACT FROM AUTHOR]

The extraction and analysis of plant phenotypic characteristics are critical issues for many precision agriculture applications. An improved YOLOv5 model was proposed in this study for accurate node detection and internode length estimation of crops by using an end-to-end approach. In this improved YOLOv5, a feature extraction module was added in front of each detection head, and the bounding box loss function used in the original network of YOLOv5 was replaced by the SIoU bounding box loss function. The results of the experiments on three different crops (chili, eggplant, and tomato) showed that the improved YOLOv5 reached 90.5% AP (average precision) and the average detection time was 0.019 s per image. The average error of the internode length estimation was 41.3 pixels, and the relative error was 7.36%. Compared with the original YOLOv5, the improved YOLOv5 had an average error reduction of 5.84 pixels and a relative error reduction of 1.61%. [ABSTRACT FROM AUTHOR]

Network analysis is an indispensable part of today’s academic field. Among the different types of networks, the more complex hypergraphs can provide an excellent challenge and new angles for analysis. This study proposes a variant of the critical node detection problem for hypergraphs using weighted node degree centrality as a form of importance metric. An analysis is done on both generated synthetic networks and real-world derived data on the topic of United States House and Senate committees, using a newly designed algorithm. The numerical results show that the combination of the critical node detection on hypergraphs with the weighted node degree centrality provides promising results and the topic is worth exploring further.

The extraction and analysis of plant phenotypic characteristics are critical issues for many precision agriculture applications. An improved YOLOv5 model was proposed in this study for accurate node detection and internode length estimation of crops by using an end-to-end approach. In this improved YOLOv5, a feature extraction module was added in front of each detection head, and the bounding box loss function used in the original network of YOLOv5 was replaced by the SIoU bounding box loss function. The results of the experiments on three different crops (chili, eggplant, and tomato) showed that the improved YOLOv5 reached 90.5% AP (average precision) and the average detection time was 0.019 s per image. The average error of the internode length estimation was 41.3 pixels, and the relative error was 7.36%. Compared with the original YOLOv5, the improved YOLOv5 had an average error reduction of 5.84 pixels and a relative error reduction of 1.61%.

Previous research on influence maximization are mostly based on static graph optimization, but in reality, the net- work data volume increase rapidly with time,so the system cannot obtain the connection between nodes in the whole network in real time. Based on the traditional MaxG detection model, this paper proposed the RAS-MaxG detection algorithm, which combined the regular area scale and node neighborhood level to calculate the node influence. Finally, the experimental results on real datasets show that the proposed detection algorithm has better performance in the final influence coverage. [ABSTRACT FROM AUTHOR]

Wireless sensor networks is an attractive concept that is being implemented in all fields of work with diverse applications. Hence it is not a surprise that there are several wireless routing algorithms available and they mainly focus on reducing the consumption of energy in WSN, the direction of the fact that a sensor node point work on batteries. But algorithms do not study on these energy deficient nodes and their collision effects. There are various reasons for node failure that can fall under mechanical or electrical problems, battery depletion, environmental degradation or hostile tampering. But the most common failure of nodes occur due to limited energy availability. Failure caused due to a group of nodes can minimize the network paths. These activities can lead to failures in the subset of acting nodes resulting in a disconnected or no path situation from the network. This algorithm introduces the multipath node disjoint routing by combining local and global procedures for adaptive route. The capable nodes in the network are located using Lyapunoy optimization technique through network coding technique that enhances the operation and lifetime of the entire network. Through weight of the packet and along with the packet receiving ratio the algorithm separates the packets and route them to a different path to the base station thereby improving delivery and optimizing time and energy. Simulations are conducted in a NS3 environment and proved that this algorithm is efficient in performance than the existing methods. [ABSTRACT FROM AUTHOR]

Sinkhole malicious nodes attacks are quite hard to handle in wireless sensor networks, due to the reason that the results of the attacks may cut off the communications by spreading false hops, absorbing data packets. Those terrible attacks are formed from the unique destroying method, which will preferentially destroy the nodes with higher communication function and shorter distance from the Sink node (Base station). In this paper, we propose a secure and energy-efficient detection scheme which can detect the malicious nodes more precisely than the traditional methods. In particularly, a new measure method is introduced in this paper, which is the frequency of each node by establishing M routes with optimal hops from per node to the Sink node. Using the proposed measure and dynamic programming, the malicious nodes can easily tell apart from the network according to the various satisfaction levels and hop difference. Compared with the traditional algorithms, simulation results show that our scheme can significantly promote the detection rate and the false positive rate. The detection rate increased about by 6–30%, the false positive rate decreased about by 5–25%. We also obtain a high energy-saving results in wireless sensor networks. [ABSTRACT FROM AUTHOR]

Network analysis is an indispensable part of today's academic field. Among the different types of networks, the more complex hypergraphs can provide an excellent challenge and new angles for analysis. This study proposes a variant of the critical node detection problem for hypergraphs using weighted node degree centrality as a form of importance metric. An analysis is done on both generated synthetic networks and real-world derived data on the topic of United States House and Senate committees, using a newly designed algorithm. The numerical results show that the combination of the critical node detection on hypergraphs with the weighted node degree centrality provides promising results and the topic is worth exploring further., Competing Interests: The authors declare there are no competing interests., (©2023 Képes.)

Seedling vigor in tomatoes determines the quality and growth of fruits and total plant productivity. It is well known that the salient effects of environmental stresses appear on the internode length; the length between adjoining main stem node (henceforth called node). In this study, we develop a method for internode length estimation using image processing technology. The proposed method consists of three steps: node detection, node order estimation, and internode length estimation. This method has two main advantages: (i) as it uses machine learning approaches for node detection, it does not require adjustment of threshold values even though seedlings are imaged under varying timings and lighting conditions with complex backgrounds; and (ii) as it uses affinity propagation for node order estimation, it can be applied to seedlings with different numbers of nodes without prior provision of the node number as a parameter. Our node detection results show that the proposed method can detect 72% of the 358 nodes in time-series imaging of three seedlings (recall = 0.72, precision = 0.78). In particular, the application of a general object recognition approach, Bag of Visual Words (BoVWs), enabled the elimination of many false positives on leaves occurring in the image segmentation based on pixel color, significantly improving the precision. The internode length estimation results had a relative error of below 15.4%. These results demonstrate that our method has the ability to evaluate the vigor of tomato seedlings quickly and accurately. [ABSTRACT FROM AUTHOR]

Seedling vigor in tomatoes determines the quality and growth of fruits and total plant productivity. It is well known that the salient effects of environmental stresses appear on the internode length; the length between adjoining main stem node (henceforth called node). In this study, we develop a method for internode length estimation using image processing technology. The proposed method consists of three steps: node detection, node order estimation, and internode length estimation. This method has two main advantages: (i) as it uses machine learning approaches for node detection, it does not require adjustment of threshold values even though seedlings are imaged under varying timings and lighting conditions with complex backgrounds; and (ii) as it uses affinity propagation for node order estimation, it can be applied to seedlings with different numbers of nodes without prior provision of the node number as a parameter. Our node detection results show that the proposed method can detect 72% of the 358 nodes in time-series imaging of three seedlings (recall = 0.72, precision = 0.78). In particular, the application of a general object recognition approach, Bag of Visual Words (BoVWs), enabled the elimination of many false positives on leaves occurring in the image segmentation based on pixel color, significantly improving the precision. The internode length estimation results had a relative error of below 15.4%. These results demonstrate that our method has the ability to evaluate the vigor of tomato seedlings quickly and accurately.