Network Algorithm For Detection Research Articles

A High‐Scalability Graph Modification System for Large‐Scale Networks

AbstractModifying network results is the most intuitive way to inject domain knowledge into network detection algorithms to improve their performance. While advances in computation scalability have made detecting large‐scale networks possible, the human ability to modify such networks has not scaled accordingly, resulting in a huge ‘interaction gap’. Most existing works only support navigating and modifying edges one by one in a graph visualization, which causes a significant interaction burden when faced with large‐scale networks. In this work, we propose a novel graph pattern mining algorithm based on the minimum description length (MDL) principle to partition and summarize multi‐feature and isomorphic sub‐graph matches. The mined sub‐graph patterns can be utilized as mediums for modifying large‐scale networks. Combining two traditional approaches, we introduce a new coarse‐middle‐fine graph modification paradigm (i.e. query graph‐based modification sub‐graph pattern‐based modification raw edge‐based modification). We further present a graph modification system that supports the graph modification paradigm for improving the scalability of modifying detected large‐scale networks. We evaluate the performance of our graph pattern mining algorithm through an experimental study, demonstrate the usefulness of our system through a case study, and illustrate the efficiency of our graph modification paradigm through a user study.

Research on Virus Propagation Network Intrusion Detection Based on Graph Neural Network

The field of network security is highly concerned with intrusion detection, which safeguards the security of computer networks. The invention and application of intrusion detection technology play indispensable roles in network security, and it is crucial to investigate and comprehend this topic. Recently, with the continuous occurrence of intrusion incidents in virus propagation networks, traditional network detection algorithms for virus propagation have encountered limitations and have struggled to detect these incidents effectively and accurately. Therefore, updating the intrusion detection algorithm of the virus-spreading network is imperative. This paper introduces a novel system for virus propagation, whose core is a graph-based neural network. By organically combining two modules—a standardization module and a computation module—this system forms a powerful GNN model. The standardization module uses two methods, while the calculation module uses three methods. Through permutation and combination, we obtain six GNN models with different characteristics. To verify their performance, we conducted experiments on the selected datasets. The experimental results show that the proposed algorithm has excellent capabilities, high accuracy, reasonable complexity, and excellent stability in the intrusion detection of virus-spreading networks, making the network more secure and reliable.

Computer Network Information Security and Protection Strategy Based on Big Data Environment

This paper proposed a study on computer network information security and protection strategy based on a big data environment. The research purpose was to use big data technology to network information security protection technology and seek more efficient network information protection technology. The algorithm proposed in this article was a time-series network detection algorithm based on big data, which could improve the early warning rate of abnormal network information, reduce the early warning time, and improve the detection accuracy and interception rate of virus information. The results of this study could effectively show that big data technology had excellent performance in computer network information security protection, which also led to an advanced reform path for future network information security protection technology.

НЕЙРОСЕТЕВОЙ АЛГОРИТМ ДЕТЕКТИРОВАНИЯ СИГНАЛОВ С ДВОИЧНОЙ ПОЗИЦИОННО-ИМПУЛЬСНОЙ МОДУЛЯЦИЕЙ

In the work, a neural network method for detecting signals with binary position-pulse modulation was studied. The detection process was reduced to distinguishing signals by a neural network, the architecture of which included convolutional and fully-connected layers. The network was trained on the basis of a set of labeled realizations of a sum of signals with noise, which were represented by discrete samples. The TensorFlow library was used to model and train the network. A bell video pulse and a quasi-radio signal with a bell modulating function were used as possible signal models. The functioning efficiency of the trained neural network was studied by the methods of statistical modeling on a computer. The detection quality of the neural network algorithm is compared with the classical one synthesized in the framework of the statistical decision theory. The possibility of training a neural network detector with an unknown duration of the received signals is investigated. The efficiency of the neural network detector is compared with the quasi-optimal one, which does not take into account the possible unknown of the signal duration. It is shown that the neural network detection algorithm is significantly inferior to the optimal one synthesized by the maximum likelihood method. However, in the presence of a priori uncertainty about the signal duration, the quasi-optimal detector is inferior in efficiency to the neural network one. Recommendations are formulated for a reasonable choice of the detector, depending on the required quality of its work.

A Min-Pooling Detection Method for Ship Targets in Noisy SAR Images

As the application of deep learning in general optical images becomes more and more widespread, the field of remote sensing images also begins to pay attention to the application of deep learning methods. Although deep learning detection algorithms have achieved better results than traditional detection algorithms, the detection results for poorly imaged SAR images still need improvement, and processing poorly imaged noisy SAR images is still a big challenge for existing algorithms. To address the problem of low precision and recall of existing algorithms for noisy SAR image detection, we propose a convolutional neural network detection algorithm based on min-pooling. First, we design a feature processing layer with min-pooling as the main structure to suppress the noise and then use a feature fusion layer to compensate for the missing information caused by pooling. To avoid problems such as redundancy in computation caused by the anchor-base algorithm, we choose the anchor-free algorithm as the main structure of ship detection. Finally, the model is evaluated using ordinary SAR image datasets and noisy SAR image datasets. Experiment results show that our proposed method has a better detection effect for noisy SAR images than other object detection models.

Evaluating and testing neural-network algorithm capabilities for automating image data analysis for remote sensing of the Earth

Subject of study. Results of comparative analysis and testing of the application capabilities of several neural network detection algorithms, programming interfaces, and machine learning libraries for real-time analysis of graphical data from scanning thermal imaging surveying systems are presented. Method. The availability of programming interfaces for integration and adaptation of algorithms into the developed software, data processing rate, and object detection accuracy were selected as the main criteria for assessing the detection algorithms. These criteria were evaluated using practical experiments involving training and running neural network algorithms on test software using computers with different configurations. Main results. Modern neural network algorithms were demonstrated to enable image data processing with detection accuracy for specified object classes, which is sufficient for the automation of image recognition aimed at real-time processing of images from scanning thermal imaging surveying systems. Practical significance. The results of the investigation and tests presented in this study can be advantageous and reduce the time required for developers to find base neural network algorithms suitable for a practical implementation of automation aimed at image processing. Implementation of the considered algorithms in the developed software enables image analysis and processing in real time during surveillance owing to a reduction in the amount of data processed by the operator, thus enabling the removal of the post-processing stage from the technological sequence of the surveillance.

Xiaomila Green Pepper Target Detection Method under Complex Environment Based on Improved YOLOv5s

Real-time detection of fruit targets is a key technology of the Xiaomila green pepper (Capsicum frutescens L.) picking robot. The complex conditions of orchards make it difficult to achieve accurate detection. However, most of the existing deep learning network detection algorithms cannot effectively detect Xiaomila green pepper fruits covered by leaves, branches, and other fruits in natural scenes. As detailed in this paper, the Red, Green, Blue (RGB) images of Xiaomila green pepper in the green and mature stage were collected under natural light conditions for building the dataset and an improved YOLOv5s model (YOLOv5s-CFL) is proposed to improve the efficiency and adaptability of picking robots in the natural environment. First, the convolutional layer in the Cross Stage Partial (CSP) is replaced with GhostConv, the detection speed is improved through a lightweight structure, and the detection accuracy is enhanced by adding a Coordinate Attention (CA) layer and replacing Path Aggregation Network (PANet) in the neck with Bidirectional Feature Pyramid Network (BiFPN). In the experiment, the YOLOv5s-CFL model was used to detect the Xiaomila, and the detection results were analyzed and compared with those of the original YOLOv5s, YOLOv4-tiny, and YOLOv3-tiny models. With these improvements, the Mean Average Precision (mAP) of YOLOv5s-CFL is 1.1%, 6.8%, and 8.9% higher than original YOLOv5s, YOLOv4-tiny, and YOLOv3-tiny, respectively. Compared with the original YOLOv5 model, the model size is reduced from 14.4 MB to 13.8 MB, and the running speed is reduced from 15.8 to 13.9 Gflops. The experimental results indicate that the lightweight model improves the detection accuracy and has good real-time performance and application prospects in the field of picking robots.

Network-specific selectivity of functional connections in the neonatal brain.

The adult human brain is organized into functional brain networks, groups of functionally connected segregated brain regions. A key feature of adult functional networks is long-range selectivity, the property that spatially distant regions from the same network have higher functional connectivity than spatially distant regions from different networks. Although it is critical to establish the status of functional networks and long-range selectivity during the neonatal period as a foundation for typical and atypical brain development, prior work in this area has been mixed. Although some studies report distributed adult-like networks, other studies suggest that neonatal networks are immature and consist primarily of spatially isolated regions. Using a large sample of neonates (n= 262), we demonstrate that neonates have long-range selective functional connections for the default mode, fronto-parietal, and dorsal attention networks. An adult-like pattern of functional brain networks is evident in neonates when network-detection algorithms are tuned to these long-range connections, when using surface-based registration (versus volume-based registration), and as per-subject data quantity increases. These results help clarify factors that have led to prior mixed results, establish that key adult-like functional network features are evident in neonates, and provide a foundation for studies of typical and atypical brain development.

Network Clustering Algorithm Based on Fast Detection of Central Node

Based on scale-free and density-based complex networks and numerical clustering algorithm, a graph clustering algorithm based on fast detection of central nodes is proposed. Through the calculation of local density and comprehensive clustering of nodes in the network, the clustering center in the network can be found quickly and noncentral nodes can be divided into the clustering center according to the nearest neighbor principle, thus avoiding parameter limitations such as the number of clustering to be set in advance using conventional classic social network detection algorithm. The experimental comparison and analysis in the real network indicate that the graph clustering algorithm based on fast detection of the central node is highly effective and efficient.

Identification of Priority Sites to Support Management of Commercially Important Sea Cucumber Species by Applying Infomap and Habitat Filters to Larval Dispersal Data

Stocks of commercially valuable sea cucumber species have declined in most tropical countries, which supply majority of the global demand. This work aimed to locate priority sites for the management ofHolothuria scabraandStichopus horrensin the western central Philippines. A passive larval dispersal model was run under four monsoonal regimes (Northeast monsoon, dry-transition, Southwest monsoon, and early Northeast monsoon), and the results subjected to theInfomapnetwork detection algorithm. Three clusters of closely related geographical nodes were identified [southeastern Palawan (Group I), western Panay and eastern Mindoro (Group II), and northern and western Palawan with western Mindoro (Group III)]. Remotely sensed habitat data were used to parameterize the degree of connectivity observed among sites (H. scabraspawning and settlement requires the presence of seagrass and mangrove, whileS. horrensrequires corals and seagrass). Local retention, self-recruitment, settlement success and sink diversity were then calculated for each node with suitable habitat. The locations were ranked according to each metric and those with higher larval export rates, a higher diversity of larval sources and a high degree of successful larval contribution to other sites were deemed crucial for the management of wild populations. Sixteen high-priority sites were identified, distributed mainly along northern Palawan and western Panay. Six sites were common for both species at different seasons, and no single location fulfilled all stated criteria across the four seasons and both sea cucumber species considered. The priority sites for management could serve as broodstock selection and juvenile restocking areas for aquaculture production clusters, which when properly implemented, could lead to an increase in sea cucumber production and contribute to natural populations. On a broader scale, the designation of closely related clusters and incorporation of habitat requirements to dispersal data provided critical input for the delineation of ecologically meaningful management units for sea cucumbers within the region.

AF-EMS Detector: Improve the Multi-Scale Detection Performance of the Anchor-Free Detector

As a precursor step for computer vision algorithms, object detection plays an important role in various practical application scenarios. With the objects to be detected becoming more complex, the problem of multi-scale object detection has attracted more and more attention, especially in the field of remote sensing detection. Early convolutional neural network detection algorithms are mostly based on artificially preset anchor-boxes to divide different regions in the image, and then obtain the prior position of the target. However, the anchor box is difficult to set reasonably and will cause a large amount of computational redundancy, which affects the generality of the detection model obtained under fixed parameters. In the past two years, anchor-free detection algorithm has achieved remarkable development in the field of detection on natural image. However, there is no sufficient research on how to deal with multi-scale detection more effectively in anchor-free framework and use these detectors on remote sensing images. In this paper, we propose a specific-attention Feature Pyramid Network (FPN) module, which is able to generate a feature pyramid, basing on the characteristics of objects with various sizes. In addition, this pyramid suits multi-scale object detection better. Besides, a scale-aware detection head is proposed which contains a multi-receptive feature fusion module and a size-based feature compensation module. The new anchor-free detector can obtain a more effective multi-scale feature expression. Experiments on challenging datasets show that our approach performs favorably against other methods in terms of the multi-scale object detection performance.

Bag of tricks for fabric defect detection based on Cascade R-CNN

In this paper, a bag of tricks is proposed to improve the precision of fabric defect detection. Although the general state-of-the-art convolutional neural network detection algorithm can achieve a better detection effect, in fact, the detection precision still has enough room to improve on fabric defect detection. Therefore, we propose three tricks to further improve the precision. Firstly, we use multiscale training, which scales the single input image into a number of images of different resolutions for training, so as to be able to adapt to the box distribution of different scales. Secondly, we use the dimension clusters method. By observing the distribution of the width and the height of the defect size in the fabric dataset, we find that the distribution of the defect size in the dataset is extremely unbalanced and the size span is large. We believe that the training results of the default prior boxes setting might not be optimal, so we conduct dimensional clustering for the width and height of the defect size of the dataset, so as to make the network model easier to learn. Thirdly, we use soft non-maximum suppression instead of traditional non-maximum suppression to avoid the situation that the same kinds of defect category in the dataset are overlapped and eliminated as repeated detection. With this bag of tricks, we effectively improve the precision of fabric defect detection by 8.9% mAP on the basis of the baseline of state-of-the-art convolutional neural network detection algorithm.

Toward Global Earthquake Early Warning with the MyShake Smartphone Seismic Network, Part 1: Simulation Platform and Detection Algorithm

Abstract The MyShake project aims to build a global smartphone seismic network to facilitate large-scale earthquake early warning and other applications by leveraging the power of crowdsourcing. The MyShake mobile application first detects earthquake shaking on a single phone. The earthquake is then confirmed on the MyShake servers using a “network detection” algorithm that is activated by multiple single-phone detections. In this part one of the two article series, we present a simulation platform and a network detection algorithm to test earthquake scenarios at various locations around the world. The proposed network detection algorithm is built on the classic density-based spatial clustering of applications with noise spatial clustering algorithm, with modifications to take temporal characteristics into account and the association of new triggers. We test our network detection algorithm using real data recorded by MyShake users during the 4 January 2018 M 4.4 Berkeley and the 10 June 2016 M 5.2 Borrego Springs earthquakes to demonstrate the system’s utility. In order to test the entire detection procedure and to understand the first order performance of MyShake in various locations around the world representing different population and tectonic characteristics, we then present a software platform that can simulate earthquake triggers in hypothetical MyShake networks. Part two of this paper series explores our MyShake early warning simulation performance in selected regions around the world.

Toward Global Earthquake Early Warning with the MyShake Smartphone Seismic Network, Part 2: Understanding MyShake Performance around the World

Abstract The MyShake project aims to build a global smartphone seismic network to facilitate large-scale earthquake early warning (EEW) and other applications by leveraging the power of crowdsourcing. The MyShake mobile application first detects earthquake shaking on a single phone. The earthquake is then confirmed on the MyShake servers using a “network detection” algorithm that is activated by multiple single-phone detections. In part two of this two-article series, we report the first-order performance of MyShake’s EEW capability in various selected locations around the world. Because of the present sparseness of the MyShake network in most parts of the world, we use our simulation platform to understand and evaluate the system’s performance in various tectonic settings. We assume that 0.1% of the population in each region has the MyShake mobile application installed on their smartphone and use historical earthquakes from the last 20 yr to simulate triggering scenarios with different network configurations in various regions. Then, we run the detection algorithm with these simulated triggers to understand the performance of the system. The system performs best in regions featuring high population densities and onshore, upper crustal earthquakes M<7.0. In these cases, alerts can be generated ∼4–6 s after the origin time, magnitude errors are within ∼0.5 magnitude units, and epicenters are typically within 10 km of true locations. When the events are offshore or in sparsely populated regions, the alerts are slower and the uncertainties in magnitude and location increase. Furthermore, even with 0.01% of the population as the MyShake users, in regions of high population density, the system still performs well for earthquakes larger than M 5.5. The details of the simulation platform and the network detection algorithm are available in part 1 of this two-article series.

Current microseismicity and generating faults in the Gyeongju area, southeastern Korea

A study of microseismicity in a 15×20km2 subregion of Gyeongju, southeastern Korea, establishes a direct link between minor earthquakes and known fault structures. The study area has a complex history of tectonic deformation and has experienced large historic earthquakes, with small earthquakes recorded since the beginning of modern instrumental monitoring. From 5years of continuously recorded local seismic data, 311 previously unidentified microearthquakes can be reliably located using the double-difference algorithm. These newly discovered events occur in linear streaks that can be spatially correlated with active faults, which could pose a serious hazard to nearby communities. At-risk infrastructure includes the largest industrial park in South Korea, nuclear power plants, and disposal facilities for radioactive waste. The current work suggests that the southern segment of the Yeonil Tectonic Line and segments of the Seokup and Waup Basin boundary faults are active. For areas with high rates of microseismic activity, reliably located hypocenters are spatially correlated with mapped faults; in less active areas, earthquake clusters tend to occur at fault intersections. Microearthquakes in stable continental regions are known to exist, but have been largely ignored in assessments of seismic hazard because their magnitudes are well below the detection thresholds of seismic networks. The total number of locatable microearthquakes could be dramatically increased by lowering the triggering thresholds of network detection algorithms. The present work offers an example of how microearthquakes can be reliably detected and located with advanced techniques. This could make it possible to create a new database to identify subsurface fault geometries and modes of fault movement, which could then be considered in the assessments of seismic hazard in regions where major earthquakes are rare.

Physician Networks and Ambulatory Care-sensitive Admissions.

Research on the quality and cost of care traditionally focuses on individual physicians or medical groups. Social network theory suggests that the care a patient receives also depends on the network of physicians with whom a patient's physician is connected. The objectives of the study are: (1) identify physician networks; (2) determine whether the rate of ambulatory care-sensitive hospital admissions (ACSAs) varies across networks--even different networks at the same hospital; and (3) determine the relationship between ACSA rates and network characteristics. We identified networks by applying network detection algorithms to Medicare 2008 claims for 987,000 beneficiaries in 5 states. We estimated a fixed-effects model to determine the relationship between networks and ACSAs and a multivariable model to determine the relationship between network characteristics and ACSAs. We identified 417 networks. Mean size: 129 physicians; range, 26-963. In the fixed-effects model, ACSA rates varied significantly across networks: there was a 46% difference in rates between networks at the 25th and 75th performance percentiles. At 95% of hospitals with admissions from 2 networks, the networks had significantly different ACSA rates; the mean difference was 36% of the mean ACSA rate. Networks with a higher percentage of primary-care physicians and networks in which patients received care from a larger number of physicians had higher ACSA rates. Physician networks have a relationship with ACSAs that is independent of the physicians in the network. Physician networks could be an important focus for understanding variations in medical care and for intervening to improve care.