scholarly journals Towards Self-supervised Learning for Multi-function Radar Behavior State Detection and Recognition

Author(s):  
HanCong Feng

<div>The analysis of intercepted multi-function radar (MFR) signals has gained considerable attention in the field of cognitive electronic reconnaissance. With the rapid development of MFR, the switch between different work modes is becoming more flexible, increasing the agility of pulse parameters. Most of the existing approaches for recognizing MFR behaviors heavily depend on prior information, which can hardly be obtained in a non-cooperative way. This study develops a novel hierarchical contrastive self-supervise-based method for segmenting and clustering MFR pulse sequences. First, a convolutional neural network (CNN) with a limited receptive field is trained in a contrastive way to distinguish between pulse descriptor words (PDW) in the original order and the samples created by random permutations to detect the boundary between each radar word and perform segmentation. Afterward, the K-means++ algorithm with cosine distances is established to cluster the segmented PDWs according to the output vectors of the CNN’s last layer for radar words extraction. This segmenting and clustering process continues to go in the extracted radar word sequence, radar phase sequence, and so on, finishing the automatic extraction of MFR behavior states in the MFR hierarchical model. Simulation results show that without using any labeled data, the proposed method can effectively mine distinguishable patterns in the sequentially arriving PDWs and recognize the MFR behavior states under corrupted, overlapped pulse parameters.</div>

2022 ◽  
Author(s):  
HanCong Feng

<div>The analysis of intercepted multi-function radar (MFR) signals has gained considerable attention in the field of cognitive electronic reconnaissance. With the rapid development of MFR, the switch between different work modes is becoming more flexible, increasing the agility of pulse parameters. Most of the existing approaches for recognizing MFR behaviors heavily depend on prior information, which can hardly be obtained in a non-cooperative way. This study develops a novel hierarchical contrastive self-supervise-based method for segmenting and clustering MFR pulse sequences. First, a convolutional neural network (CNN) with a limited receptive field is trained in a contrastive way to distinguish between pulse descriptor words (PDW) in the original order and the samples created by random permutations to detect the boundary between each radar word and perform segmentation. Afterward, the K-means++ algorithm with cosine distances is established to cluster the segmented PDWs according to the output vectors of the CNN’s last layer for radar words extraction. This segmenting and clustering process continues to go in the extracted radar word sequence, radar phase sequence, and so on, finishing the automatic extraction of MFR behavior states in the MFR hierarchical model. Simulation results show that without using any labeled data, the proposed method can effectively mine distinguishable patterns in the sequentially arriving PDWs and recognize the MFR behavior states under corrupted, overlapped pulse parameters.</div>


2021 ◽  
Vol 13 (14) ◽  
pp. 2810
Author(s):  
Joanna Gudowicz ◽  
Renata Paluszkiewicz

The rapid development of remote sensing technology for obtaining high-resolution digital elevation models (DEMs) in recent years has made them more and more widely available and has allowed them to be used for morphometric assessment of concave landforms, such as valleys, gullies, glacial cirques, sinkholes, craters, and others. The aim of this study was to develop a geographic information systems (GIS) toolbox for the automatic extraction of 26 morphometric characteristics, which include the geometry, hypsometry, and volume of concave landforms. The Morphometry Assessment Tools (MAT) toolbox in the ArcGIS software was developed. The required input data are a digital elevation model and the form boundary as a vector layer. The method was successfully tested on an example of 21 erosion-denudation valleys located in the young glacial area of northwest Poland. Calculations were based on elevation data collected in the field and LiDAR data. The results obtained with the tool showed differences in the assessment of the volume parameter at the average level of 12%, when comparing the field data and LiDAR data. The algorithm can also be applied to other types of concave forms, as well as being based on other DEM data sources, which makes it a universal tool for morphometric evaluation.


2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Feng Yang ◽  
Guixin Dong ◽  
Chaoran Cui ◽  
Xiaojie Li ◽  
Yaxi Su ◽  
...  

In recent years, with the rapid development of digital currency, digital currency brings us convenience and wealth, but also breeds some illegal and criminal behaviors. Different from traditional currencies, digital currency provides concealment to criminals while also exposing their behavior. The analysis of their behavior can be used to detect whether the current digital currency transaction is legal. There is a problem that most digital currency transactions are in compliance with laws and regulations, and only a small part of them uses digital currency to conduct illegal activities. It belongs to the problem of sample imbalance. It is quite challenging to accurately distinguish which transactions are legal and which are illegal in the massive digital currency transactions. For this reason, this study combines the mutual information and the traditional cross-entropy loss function and obtains the loss function based on the mutual information prior. The loss function based on the mutual information prior is that the bias of the category prior distribution is added after the output of the model (before the softmax), which makes the model consider category prior information to a certain extent when predicting. The experimental results show that the use of the loss function based on mutual information prior to the detection of digital currency illegal behavior has a good effect in SVM, DNN, GCN, and GAT methods.


2019 ◽  
Vol 62 (6) ◽  
pp. 1755-1765
Author(s):  
Sunan Zhang ◽  
Jianyan Tian ◽  
Amit Banerjee ◽  
Jiangli Li

Abstract. With the rapid development of large-scale breeding, manual long-term monitoring of the daily activities and health of livestock is costly and time-consuming. Therefore, the application of bio-acoustics to automatic monitoring has received increasing attention. Although bio-acoustical techniques have been applied to the recognition of animal sounds in many studies, there is a dearth of studies on the automatic recognition of abnormal sounds from farm animals. In this study, an automatic detection and recognition system based on bio-acoustics is proposed to hierarchically recognize abnormal animal states in a large-scale pig breeding environment. In this system, we extracted the mel-frequency cepstral coefficients (MFCC) and subband spectrum centroid (SSC) as composite feature parameters. At the first level, support vector data description (SVDD) is used to detect abnormal sounds in the acoustic data. At the second level, a back-propagation neural network (BPNN) is used to classify five kinds of abnormal sounds in pigs. Furthermore, improved spectral subtraction is developed to reduce the noise interference as much as possible. Experimental results show that the average detection accuracy and the average recognition accuracy of the proposed system are 94.2% and 95.4%, respectively. The effectiveness of the proposed sound detection and recognition system was also verified through tests at a pig farm. Keywords: Abnormal sounds, MFCC, SSC, States of pigs, SVDD.


Soil Research ◽  
2001 ◽  
Vol 39 (4) ◽  
pp. 837
Author(s):  
V. J. Bidwell ◽  
H. R. Thorpe

Significant fluctuations in soil water flux were observed in the drainage hydrographs from lysimeters (1220 mm diam., 900 mm deep) of undisturbed field soil, recorded at 5-min intervals, in response to intermittent 1-min pulses of irrigation water (3.4 or 6.8 mm) at irregular time intervals (4–17 min). The hypothetical process for this phenomenon was flow through soil macropores, in association with non-linear sorption into soil micropores. The kinematic wave approach to analysing macropore flow was modelled as a series of bi-continuum cells, which can be expressed as a set of non-linear ordinary differential equations. This non-linear state-space description enables the use of MATLAB software for convenient coding of the model and numerical integration of the model response to transient water flux input. Model simulation of drainage response to the irrigation pulse sequences showed good prediction of the wetting and draining fronts of the hydrograph but gave only indicative prediction of the magnitudes and wavelengths of the flow fluctuations. The model demonstrates the sensitivity of macropore flow to variations in the intervals between irrigation pulses, and supports previous evidence of fluctuations in macropore flow even for single water flux input pulses under laboratory conditions.


2013 ◽  
Vol 791-793 ◽  
pp. 1203-1207
Author(s):  
Zhi Guo Liu ◽  
Jun Yu Li ◽  
Xiu Li Ren

With the development of computer hardware and software, the simulation of computer virtual simulation has been rapid development. The running process of computer simulation platform need to deal with massive data, and in general software testing technology can not meet the requirements. On the basis of this, an application computer virtual platforms parallel test method is proposed. Firstly, this paper gives a brief introduction for the process of computer simulation, and then the testing method can carry out software programming, it will realize the virtual process of serial FIFO buffer and register through reading and writing function. In order to develop basketball virtual platform as an example, the use of Simulink modules in MATLAB compare the serial and parallel testing of two testing methods used by software debugging time. Finally, we find that the parallel test is the best scheme of computer virtual platform software test, to provide theoretical reference for the design of software testing process.


2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Chunlan Li

With the rapid development of computer science, a large number of images and an explosive amount of information make it difficult to filter and effectively extract information. This article focuses on the inability of effective detection and recognition of English text content to conduct research, which is useful for improving the application of intelligent analysis significance. This paper studies how to improve the neural network model to improve the efficiency of image text detection and recognition under complex background. The main research work is as follows: (1) An improved CTPN multidirectional text detection algorithm is proposed, and the algorithm is applied to the multidirectional text detection and recognition system. It uses the multiangle rotation of the image to be detected, then fuses the candidate text boxes detected by the CTPN network, and uses the fusion strategy to find the best area of the text. This algorithm solves the problem that the CTPN network can only detect the text in the approximate horizontal direction. (2) An improved CRNN text recognition algorithm is proposed. The algorithm is based on CRNN and combines traditional text features and depth features at the same time, making it possible to recognize occluded text. The algorithm was tested on the IC13 and SVT data sets. Compared with the CRNN algorithm, the recognition accuracy has been improved, and the detection and recognition accuracy has increased by 0.065. This paper verifies the effectiveness of the improved algorithm model on multiple data sets, which can effectively detect various English texts, and greatly improves the detection and recognition performance of the original algorithm.


Author(s):  
Zhen Tian ◽  
Ming Cen ◽  
Yinguo Li

Environment perception is crucial for the development of autonomous driving and advanced driver assistance systems. The cooperative perception using the infrastructure sensors can significantly expand the field of view of on-board sensors and improve the accuracy of target tracking. In this paper, we propose a hybrid vehicular perception system that incorporates both received feature-level information from infrastructure sensors and track-level data from the multi-access edge computing server (MEC-Server). An infrastructure-enhanced multiple-model probability hypothesis density is proposed to handle the feature-level data from heterogeneous infrastructure sensors. The problem of kinematic state estimation is improved with the prior information of the road environment. Furthermore, a generic communication interface between the infrastructure sensor and MEC-Server is designed, which allows the object data to have the same notion of locality through the use of a generic object state model. Simulation results show that the presented algorithm provides higher accuracy and reliability after considering the prior information of the road environment.


Author(s):  
Alejandra Sarahi Sanchez-Moreno ◽  
Hector Manuel Perez-Meana ◽  
Jesus Olivares-Mercado ◽  
Gabriel Sanchez-Perez ◽  
Karina Toscano-Medina

Facial recognition systems has captivated research attention in recent years. Facial recognition technology is often required in real-time systems. With the rapid development, diverse algorithms of machine learning for detection and facial recognition have been proposed to address the challenges existing. In the present paper we proposed a system for facial detection and recognition under unconstrained conditions in video sequences. We analyze learning based and hand-crafted feature extraction approaches that have demonstrated high performance in task of facial recognition. In the proposed system, we compare different traditional algorithms with the avant-garde algorithms of facial recognition based on approaches discussed. The experiments on unconstrained datasets to study the face detection and face recognition show that learning based algorithms achieves a remarkable performance to face the challenges in real-time systems.


Sign in / Sign up

Export Citation Format

Share Document