Muutke küpsiste eelistusi

E-raamat: Deep Learning for Radar and Communications Automatic Target Recognition

, ,
  • Formaat: 290 pages
  • Ilmumisaeg: 31-Jan-2020
  • Kirjastus: Artech House Publishers
  • ISBN-13: 9781630816391
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 129,87 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Deep Learning for Radar and Communications Automatic Target RecognitionSuurem pilt
  • Formaat: 290 pages
  • Ilmumisaeg: 31-Jan-2020
  • Kirjastus: Artech House Publishers
  • ISBN-13: 9781630816391
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

"This exciting resource identifies technical challenges, benefits, and directions of Deep Learning (DL) based object classification using radar data (i.e., Synthetic Aperture Radar / SAR and High range resolution Radar / HRR data). An overview of machinelearning (ML) theory to include a history, background primer, and example and performance of ML algorithm (i.e., DL method) on video imagery is provided. Radar data with issues of collection, application, and examples for SAR/HRR data and communication signals analysis is also discussed. Practical considerations of deploying such techniques, including performance evaluation, hardware issues, and the future unresolved issues are presented."--Amazon.com

This book reviews techniques and challenges in artificial intelligence and machine learning (AI/ML) and machine learning and deep learning (ML/DL), as developed and applied in synthetic aperture radar (SAR), high-range resolution (HRR) radar, and radio frequency (RF) applications. The book offers a primer on ML history, theory, and examples, then examines the latest work in DL-based object classification using radar data, as well as techniques for RF data exploitation. B&w images, charts, and diagrams are included. Annotation ©2020 Ringgold, Inc., Portland, OR (protoview.com)
Foreword xi
Preface xiii
Chapter 1 Machine Learning and Radio Frequency: Past, Present, and Future
1(28)
1.1 Introduction
1(13)
1.1.1 Radio Frequency Signals
1(3)
1.1.2 Radio Frequency Applications
4(3)
1.1.3 Radar Data Collection and Imaging
7(7)
1.2 ATR Analysis
14(1)
1.2.1 ATR History
14(1)
1.2.2 ATR from SAR
15(1)
1.3 Radar Object Classification: Past Approach
15(4)
1.3.1 Template-Based ATR
15(2)
1.3.2 Model-Based ATR
17(2)
1.4 Radar Object Classification: Current Approach
19(1)
1.5 Radar Object Classification: Future Approach
20(3)
1.5.1 Data Science
21(1)
1.5.2 Artificial Intelligence
22(1)
1.6 Book Organization
23(1)
1.7 Summary
24(5)
References
24(5)
Chapter 2 Mathematical Foundations for Machine Learning
29(22)
2.1 Linear Algebra
29(5)
2.1.1 Vector Addition, Multiplication, and Transpose
29(1)
2.1.2 Matrix Multiplication
30(1)
2.1.3 Matrix Inversion
31(1)
2.1.4 Principal Components Analysis
31(3)
2.1.5 Convolution
34(1)
2.2 Multivariate Calculus for Optimization
34(5)
2.2.1 Vector Calculus
35(1)
2.2.2 Gradient Descent Algorithm
36(3)
2.3 Backpropagation
39(4)
2.4 Statistics and Probability Theory
43(6)
2.4.1 Basic Probability
44(1)
2.4.2 Probability Density Functions
44(2)
2.4.3 Maximum Likelihood Estimation
46(1)
2.4.4 Bayes' Theorem
47(2)
2.5 Summary
49(2)
References
49(2)
Chapter 3 Review of Machine Learning Algorithms
51(46)
3.1 Introduction
51(8)
3.1.1 ML Process
52(2)
3.1.2 Machine Learning Methods
54(5)
3.2 Supervised Learning
59(23)
3.2.1 Linear Classifier
60(10)
3.2.2 Nonlinear Classifier
70(12)
3.3 Unsupervised Learning
82(6)
3.3.1 K-Means Clustering
82(2)
3.3.2 K-Medoid Clustering
84(1)
3.3.3 Random Forest
85(1)
3.3.4 Gaussian Mixture Models
86(2)
3.4 Semisupervised Learning
88(5)
3.4.1 Generative Approaches
88(1)
3.4.2 Graph-Based Methods
89(4)
3.5 Summary
93(4)
References
94(3)
Chapter 4 A Review of Deep Learning Algorithms
97(44)
4.1 Introduction
97(8)
4.1.1 Deep Neural Networks
98(2)
4.1.2 Autoencoder
100(5)
4.2 Neural Networks
105(18)
4.2.1 Feed Forward Neural Networks
105(9)
4.2.2 Sequential Neural Networks
114(5)
4.2.3 Stochastic Neural Networks
119(4)
4.3 Reward-Based Learning
123(7)
4.3.1 Reinforcement Learning
123(3)
4.3.2 Active Learning
126(1)
4.3.3 Transfer Learning
126(4)
4.4 Generative Adversarial Networks
130(6)
4.5 Summary
136(5)
References
137(4)
Chapter 5 Radio Frequency Data for ML Research
141(24)
5.1 Introduction
141(1)
5.2 Big Data
141(9)
5.2.1 Data at Rest versus Data in Motion
142(1)
5.2.2 Data in Open versus Data of Importance
143(3)
5.2.3 Data in Collection versus Data from Simulation
146(2)
5.2.4 Data in Use versus Data as Manipulated
148(2)
5.3 Synthetic Aperture Radar Data
150(1)
5.4 Public Release SAR Data for ML Research
151(5)
5.4.1 MSTAR: Moving and Stationary Target Acquisition and Recognition Data Set
151(2)
5.4.2 CVDome
153(1)
5.4.3 SAMPLE
154(2)
5.5 Communication Signals Data
156(2)
5.5.1 RF Signal Data Library
157(1)
5.5.2 Northeastern University Data Set RF Fingerprinting
158(1)
5.6 Challenge Problems with RF Data
158(3)
5.7 Summary
161(4)
References
161(4)
Chapter 6 Deep Learning for Single-Target Classification in SAR Imagery
165(22)
6.1 Introduction
165(3)
6.1.1 Machine Learning SAR Image Classification
166(1)
6.1.2 Deep Learning SAR Image Classification
167(1)
6.2 SAR Data Preprocessing for Classification
168(1)
6.3 SAR Data Sets
169(3)
6.3.1 MSTAR SAR Data Set
169(2)
6.3.2 CVDome SAR Data Set
171(1)
6.4 Deep CNN Learning
172(9)
6.4.1 DNN Model Design
172(1)
6.4.2 Experimentation: Training and Verification
173(1)
6.4.3 Evaluation: Testing and Validation
174(1)
6.4.4 Confusion Matrix Analysis
175(6)
6.5 Summary
181(6)
References
183(4)
Chapter 7 Deep Learning for Multiple Target Classification in SAR Imagery
187(18)
7.1 Introduction
187(1)
7.2 Challenges with Multiple-Target Classification
188(5)
7.2.1 Constant False Alarm Rate Detector
189(1)
7.2.2 Region-Based Convolutional Neural Networks (R-CNN)
190(1)
7.2.3 You Only Look Once
190(1)
7.2.4 R-CNN Implementation
191(2)
7.3 Multiple-Target Classification
193(6)
7.3.1 Preprocessing
194(1)
7.3.2 Two-Dimensional Discrete Wavelet Transforms for Noise Reduction
194(2)
7.3.3 Noisy SAR Imagery Preprocessing by Ll-Norm Minimization
196(1)
7.3.4 Wavelet-Based Preprocessing and Target Detection
197(2)
7.4 Target Classification
199(1)
7.5 Multiple-Target Classification: Results and Analysis
200(2)
7.6 Summary
202(3)
References
202(3)
Chapter 8 RF Signal Classification
205(26)
8.1 Introduction
205(2)
8.2 RF Communications Systems
207(13)
8.2.1 RF Signals Analysis
208(3)
8.2.2 RF Analog Signals Modulation
211(1)
8.2.3 RF Digital Signals Modulation
212(1)
8.2.4 RF Shift Keying
213(2)
8.2.5 RFWiFi
215(2)
8.2.6 RF Signal Detection
217(3)
8.3 DL-Based RF Signal Classification
220(4)
8.3.1 Deep Learning for Communications
220(1)
8.3.2 Deep Learning for I/Q systems
220(3)
8.3.3 Deep Learning for RF-EO Fusion Systems
223(1)
8.4 DL Communications Research Discussion
224(3)
8.5 Summary
227(4)
References
228(3)
Chapter 9 Radio Frequency ATR Performance Evaluation
231(32)
9.1 Introduction
231(1)
9.2 Information Fusion
231(4)
9.3 Test and Evaluation
235(4)
9.3.1 Experiment Design
237(1)
9.3.2 System Development
238(1)
9.3.3 Systems Analysis
239(1)
9.4 ATR Performance Evaluation
239(7)
9.4.1 Confusion Matrix
241(2)
9.4.2 Object Assessment from Confusion Matrix
243(2)
9.4.3 Threat Assessment from Confusion Matrix
245(1)
9.5 Receiver Operating Characteristic Curve
246(7)
9.5.1 Receiver Operating Characteristic Curve from Confusion Matrix
246(4)
9.5.2 Precision-Recall from Confusion Matrix
250(2)
9.5.3 Confusion Matrix Fusion
252(1)
9.6 Metric Presentation
253(3)
9.6.1 National Imagery Interpretability Rating Scale
253(3)
9.6.2 Display of Results
256(1)
9.7 Conclusions
256(7)
References
257(6)
Chapter 10 Recent Topics in Machine Learning for Radio Frequency ATR
263(18)
10.1 Introduction
263(1)
10.2 Adversarial Machine Learning
264(6)
10.2.1 AML for SAR ATR
264(1)
10.2.2 AML for SAR Training
265(5)
10.3 Transfer Learning
270(2)
10.4 Energy-Efficient Computing for AI/ML
272(3)
10.4.1 IBM's TrueNorth Neurosynaptic Processor
274(1)
10.4.2 Energy-Efficient Deep Networks
275(1)
10.4.3 MSTAR SAR Image Classification with TrueNorth
275(1)
10.5 Near-Real-Time Training Algorithms
275(2)
10.6 Summary
277(4)
References
278(3)
About the Authors 281(2)
Index 283
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97816308163912e.html
Märksõnad: