Aerospace & Electronic Systems Society Short Course Program
AESS Chapters, IEEE Sections, Industry, Government, and Academia are encouraged to take advantage of the AESS Short Course Program. This program allows for the selection from an outstanding list of lecturers who are experts in their field and have delivered successful courses in the past. The courses cover a growing list of topics relevant to the technical areas of interest to AESS.
The course organization is generally expected to be performed through a local AESS Chapter. In most cases, funds for the course are to be raised via registration fees or training budgets of the supporting organizations. The AESS will advance reasonable seed funds to support the travel costs of the lecturer. Course revenues are expected to cover lecturer costs, the lecturer honorarium and venue and related course expenses.
The procedure for obtaining a lecturer is as follows: If a Chapter or Section has an interest in inviting one of the lecturers, it should first contact the lecturer directly in order to obtain his or her agreement to give the course on a particular date. Note that the course durations listed below are nominal and can be modified by mutual agreement. After this is accomplished, the Chapter or Section must notify the AESS Short Course Chair. If financial support (seed funding) from the AESS is required for the lecturer’s expenses, they must submit an estimate to the AESS Short Course Initiative Chair before incurring any expenses. This estimate must be provided at least 45 days before the planned meeting to provide time for feedback and for changes if needed. Written authorization from the AESS must be received before proceeding.
Short Course Lecturers are ambassadors of the AESS, who serve as an important demonstration of the value of membership in IEEE and AESS in particular. A short presentation on the benefits of Society membership is available and is to be included at the start of each short course. Lecturers should contact the AESS Operations Manager at (Click to show email) well in advance of each course to arrange for shipping AESS and IEEE Membership brochures and copies of society publications to hand out.
Following the course, the speaker and/or host are asked to prepare a short report suitable for publication and posting on the AESS web site. Pictures taken during the course are highly desirable.
The AESS Short Course committee has prepared a Short Course Program Guide to assist in the organization of an AESS Short Course.
The Short Course Program was conceived back in May 2015 by then VP Education, Joe Fabrizio. It was presented to the AESS Board of Governors as a new initiative. Joe then ran a pilot one-day course in November of 2015, which was successful in drawing in many participants and raised around $10,000 for the local chapter. The South Australia Chapter then ran a second “pilot” in 2017, bringing AESS Distinguished Lecturer, Lorenzo Lo Monte in to give a multi-day course, with equal success. The idea gained the support of the AESS Board of Governors, and a committee was put together (Lorenzo Lo Monte, Luke Rosenberg, Jason Williams) to create a Short Course Program Guide as a resource for all AESS Chapters.
During Covid, the Short Course program was less active, and Mark Davis agreed to trial a virtual Short Course. While this ran successfully and proved a viable method of giving short courses, there was less interaction than an in-person course.
Another model that has proven successful is for an individual company to request the Short Course be given exclusively to them. This allows for the course to be customised to the company and better matches their training needs.
The activities of many local AESS Chapters are often constrained by insufficient revenue, and they do not have an effective mechanism to improve this. The AESS has an excellent core of mature members willing to contribute to educational activities. By empowering members to offer fee-paying AESS short courses, chapters can raise funds and better engage with the local community. These courses can be offered to industry, Government, and academia that have training budgets for staff professional development.
Short Courses can provide the following benefits:
- Training: Many IEEE members are more interested in tutorials or short courses, rather than a single lecture. This is because IEEE members are typically engineers, students, or researchers who prefer to spend a block of time developing skills as part of a training course. Also, local industry is more willing to pay to send their employees for training/tutorial classes rather than a single lecture.
- Income for Chapters: Chapters that are willing to host a Short Course, provide local support, manage logistics, manage attendees, etc. will be able to raise some revenue for future IEEE activities.
- Serving the society membership: The Short Course Initiative will bring together many areas in the society: Membership, Education, Technical Panels, and Industry.
AESS Short Course Instructors
Click on Course Details to learn more about each short course.
Click on the name of an instructor to view "Bio" and other details.
Artificial Intelligence / Autonomous Systems and Human Autonomy Teaming
Duration: 1-3 Days
The course is designed to appeal to scientific and engineering professionals who wish to obtain and or increase knowledge in Artificial Intelligence / Autonomous Systems and Human Autonomy Teaming. Introduction to the main foundational concepts and techniques used in Artificial Intelligence (AI); including decision making, planning, machine learning, and cognition. Includes a range of real-world applications in which AI is currently used in aeronautical and aerospace systems. Presentation of theoretical concepts occurs. Systematic study of methods and research findings in the field of human perception, with an evaluation of theoretical interpretations.
Provides a basis for the understanding of these perceptual capabilities as components in Artificial Intelligence in aviation/aerospace systems. The field of human-autonomy teaming (HAT) is fast becoming a significant area of research, especially in aviation. HAT is highly interdisciplinary, bringing together methodologies and techniques from robotics, artificial intelligence, human-computer interaction, cognitive psychology, neuroscience, neuroergonomics, and other fields. The topics covered will include technologies that enable human-machine interactions, the psychology of interaction between people and machines, how to design and conduct HAT studies, and real-world applications such as assistive machines.
Covered are the advanced systematic study of methods and research findings in the field of human and computer perception, with an evaluation of theoretical interpretations. Algorithmic foundations of AI / ML. Additionally, introduction to Autonomous Systems will be covered. Surveys the fundamentals of autonomous aircraft system operations, from sensors, controls, and automation to safety procedures, human factors. Presentation of advanced theoretical concepts for artificial intelligence in the areas of knowledge representation and search techniques. The concept of the perceptron and neuron will be covered along with 1st, 2nd, and 3rd generation neural networks.
Machine Learning is also covered: hands-on, live and in-action machine learning problems will be solved: utilizing regression analysis, ANNs, RNNs, CNNs (Deep Learning), SNNs, RELs, SVMs, and Bayesian Belief Networks. This course presents the latest major commercial uses of UAS, and manned aircraft that will be going from 2-pilot operations to 1-pilot operations to unmanned operations.
Basic Algorithms for Target Tracking
Duration: 2 Days
This course goes through a variety of components that arise in target tracking algorithms, with a focus on single-scan algorithms. In many areas, reference is made to functions in the open-source copy leftfree Tracker Component Library (available online) so that attendees can rapidly apply the algorithms that are discussed. The presentation slides containing additional derivations will be made available.
2) Basic Estimation
• Mathematical Concepts
• Mathematical Coordinate Systems
• Signal Processing Topics
• Measurement Conversion
• Parameter Estimation
• Bayesian Estimation
• Assessing Estimator Performance
• Nonlinear Measurement Updates
• Track Initiation
• Linear Dynamic Models
3) Nonlinear Dynamics
• Deterministic Differential Equations
• Stochastic Dynamic Models
• Nonlinear Continuous-Time Propagation
• Celestial and Terrestrial Coordinate Systems
• Basic Orbital Dynamics
4) Estimation with Model Mismatches
• Simple Robustness Techniques
• Alternative Filters
• Multiple Model Algorithms
5) Target-Measurement Association
• Cost Functions for Measurement Assignment
• Single-Scan Assignment Algorithms
• Comments on Beams
• Single Scan Track Confirmation and Termination
• Offline Performance Prediction
• Multiframe Assignment
6) Estimation with High Nonlinearity
• Particle Filtering
• Particle Flow Filtering
• Track Initiation with Any Type of Measurement
Deep Learning for Radar Target Recognition
The focus of this course will be recent research results, technical challenges, and directions of Deep Learning (DL) based object classification using radar data (i.e., Synthetic Aperture Radar / SAR data). First, we will present an overview RF ATR research in the past (i.e., template-based approach conducted under DARPA MSTAR (Moving and Stationary Target Acquisition and Recognition) program and limitations of this approach. Then will provide an overview of various machine learning (ML) theories applied to RF data. Finally, we will demonstrate implementations and performance analysis of DL-based ATR on SAR data using Amazon’s Web Service (AWS) cloud computing, Google Collaboratory GPUs, and/or TensorFlow. Datasets to be used include AFRL public released MSTAR, CVDome, SAMPLE and North Eastern University RF signals data.
It is evident that significant research efforts have been devoted to applying DL algorithms on video imagery. However, very limited literature can be found on technical challenges and approaches to execute DL algorithms on radio frequency (RF) data. We will present hands-on implementation of DL-based radar object classification using PyTorch and TensorFlow tools. Unlike passive sensing (i.e., video collections), Radar enables imaging ground objects at far greater standoff distances and all-weather conditions. Existing non-DL based RF object recognition algorithms are less accurate and require impractically large computing resources. With adequate training data, DL enables more accurate, near real-time, and low-power object recognition system development. We will highlight implementations of DL-based (i.e., Convolution Neural Networks (CNN)) SAR object recognition algorithms in graphical processing units (GPUs) and energy efficient computing systems. The examples presented will demonstrate acceptable classification accuracy on relevant SAR data. Further, we will discuss special topics of interest (adversarial machine learning, transfer learning) on DL-based RF object recognition as requested by the researchers, practitioners, and students.
- The student will understand various machine learning algorithms
- The student will be able to identify object features in radar imagery
- The student will be able to construct a machine learning system to detect and classify targets from radar imagery
- The student will be able to compare technical challenges involving radar and video image classification
- The student can differentiate benefits of DL-based RF object classification as compared to existing algorithms (i.e., template-based approach)
- The student would become aware of software tools and data applicable to their research interests
Engineer/Researcher interested in applying Deep Learning on radar or electro-optical data for developing object recognition/self-driving car/autonomous/expert systems.
Course Level: The materials for this course will be intermediate; some understanding on machine learning will be useful but not a requirement.
Course Materials: I will be using our recently published (July 2020, Artech House) Textbook “Deep Learning for Radar and Communications ATR”.
Outline and time frame of the Short Course
Course Length: The course could be made for Half-day (4 hours of instruction) or Full-Day (8 hours of instruction).
1. Radio Frequency ATR: Past, Present, and Future: 20 min
2. Mathematics for Machine Learning / Deep Learning: 20 min
3. Review of ML Algorithms: 30 min
4. Deep Learning Algorithms: 30 min
5. RF Data for ML Research: 15 min
6. DL for Single Target Classification: 25 min
7. DL for Many Targets Classification: 20 min
8. RF Signals Classification: 15 min
9. RF ATR Performance Evaluation: 25 min
10. Emerging ML Algorithms for RF ATR: 35 min
Instructor Short Course History
Previous Offerings: I taught (on-site) this course at IEEE Radar Conference 2022 (NYC), 2021 at Atlanta (Video), RadarConf. 2019 (Boston). At Boston, I had the largest tutorial attendees (42 people) among all the tutorials. I also presented this tutorial at SPIE DCS 2018. The authors also presented a tutorial on “SAR Signal and Image Processing” at IEEE RadarConf 2010 (Washington D.C.). We also been selected for this tutorial offerings at RadarConf. 2020 (DC), and Tri-Service Radar Symposium 2020. I also provided four DL presentations. Currently, I am invited to offer this Short course at IEEE Bangalore, India (July 8, 2022).
Foliage Penetration Radar
This short course is designed to help participants understand how radar systems can detect and track fixed and moving objects, with an emphasis on forested environments. They will be presented the critical technologies and techniques for designing, and analyses for evaluating these emerging radar systems. Foliage Penetration (FOPEN) Radar is a technical approach to find and characterize man-made objections under dense foliage, as well as characterizing the foliage itself. It has wide application in both military surveillance and civilian geospatial imaging. The key enabling technology is an ultra wideband (UWB) waveform design, which has implications in the hardware specification, signal processing, and most importantly obtaining frequency allocation in the face of increasing use of the electromagnetic spectrum.
This short course is meant for graduate students and radar system engineers developing advanced radar technologies. The audience will be provided details of the design of VHF an UHF surveillance radars. A series of Matlab programs will be provided and discussed to illustrate the tradeoff techniques for airborne platforms.
Outline and time frame of the Short Course
Session I: (3 hours)
• The early history of FOPEN Radar: Battlefield surveillance and the early experiments in foliage penetration radar during the 1960s are covered. There were some very interesting developments in radar technology that enabled our ability to detect fixed and moving objects under dense foliage. During the early 1990s, FOPEN synthetic aperture radar (SAR) systems developed the critical technology for ultra wideband radar operation. The characteristics of these developments, which established a baseline for future FOPEN development, will be covered in detail.
• Phenomena: FOPEN has unique phenomena that affect system design and performance. Experimental data and simplistic models of foliage volumetric and polarimetric scatter, foliage losses and radio frequency interference are detailed, along with first order analytic techniques.
• Image Formation Processing: FOPEN SAR image formation requires ultra-wideband waveforms and wide-angle image collection. The image formation techniques and impact of motion measurement and compensation will be developed.
Session II: (3 hours)
• Radio Frequency Interference (RFI): The requirements for frequency avoidance on transmit, and RFI removal-on-receive is a major design consideration. A summary of the requirements for waveform design are developed, as well as several adaptive processing techniques to remove communications, radio and television effects on image quality.
• Automated Target Detection and Characterization: The signal processing flow to provide efficient target detection is summarized. Polarization and morphological filtering are presented that discriminate man-made versus natural objects. Results are presented in terms of receiver operating characteristics (ROC) performance.
• FOPEN SAR Design: Each critical subsystem for a FOPEN radar system is discussed in terms of the specification and ultra-wideband compensation for resolution and sensitivity. Principal performance metrics are covered, along with the impact of propagation phenomena on performance prediction.
Session III: (2 hours)
• FOPEN Moving Target Indication: The design of radar systems for ground moving target indication (GMTI) is presented, especially for objects that are moving under or behind forests. This section illustrates new technologies that are appearing in the literature that have promise for future multimode operation: the need to detect low minimum discernable velocity movement. Two techniques will be emphasized: Space Time Adaptive Processing (STAP), and Along Track Interferomentry (ATI).
• Bistatic FOPEN System: Multimode operation of GMTI and SAR is demanding on the antenna and signal processing architecture. The operation of bistatic SAR on a small, unmanned platform, in concert with a stationary GMTI illumination waveform, is presented. The “bistatic advantage” is analyzed and illustrated with detailed simulation.
Instructor Short Course History
This short course has been presented in Israel, Singapore, South Africa, and for US companies. The course expands on a history of tutorials presented at IEEE and other International Radar Conferences in United Kingdom, China, France, and Australia.
Ultra Wide Band Surveillance Radar
Ultra Wide Band Surveillance Radar is an emerging technology for detecting and characterizing targets and cultural features for military and geosciences applications. It is essential to have fine range and cross-range resolution to characterize objects near and under severe clutter. This Short Course is divided into two parts.
Part I - Basic Surveillance Radar Design and Technology: (1-day)
• The Early History of Battlefield Surveillance Radar: There were some very interesting developments in radar technology that enabled our ability to detect fixed and moving objects in dense clutter. Examples of airborne phased array antennas and UWB radars will be summarized.
• Surveillance Radar Target Detection: A summary of the radar range equation and target statistics is presented. Of particular interest is the use of frequency agility and ultra-wide band signals for limiting the statistical variation of target returns.
• Surveillance Radar Modes: Analysis for Displaced Phase Center Array, Doppler Beam Sharpening, Ground Moving Rarget Indication are illustrated from early phased array antenna radars.
• UWB Phased Array Antenna: Electronically scanned antennas (ESA) are widely used for surveillance of large areas. Wideband waveforms place a significant demand on the ESA design to maintain gain and sidelobe characteristics.
Part II - Advanced Surveillance Radar Architectures: (1 day)
• UWB Synthetic Aperture Radar (SAR): A brief description of several UWB surveillance SAR systems will be provided, along with illustrations of the SAR image and fixed object detection capability.
• Interferometric SAR Designs: They use of multiple channels for SAR have provided terrain height measurements and improved detection of moving targets with UWB waveforms.
• UWB Ground Moving Target Indication: Space time adaptive processing (STAP) has been used for detecting and tracking moving targets in clutter. This section will discuss two approaches for increasing the bandwidth and maintaining geolocation accuracy: wideband STAP and Along Track Interferometry.
• Ultra Wideband Frequency Allocation Issues: A summary of worldwide regulation on waveform design and processing for spectrum compliance.
• New research in Multi-mode Ultra-Wideband Radar: Illustration fo new technologies that have promise for future multimode operation: simultaneous SAR and GMTI in a multichannel radar.
Inertial Navigation Systems and Aiding
Duration: The course can be offered at different levels of depth, from one to five full days.
Inertial navigation systems (INS) are modern technologically sophisticated implementations of the age-old concept of dead reckoning. The basic philosophy is to begin with a knowledge of initial position, keep track of speed and direction, and thus be able to determine position continually as time progresses. Perhaps surprisingly, the rise of GNSS has actually expanded the need for inertial-based systems. Accelerometers and gyroscopes are the basic sensors utilized and since INS are essentially self-contained, they do not suffer from interference or unavailability that can affect radio-based systems such as GNSS. Furthermore, INS are highly complementary to GNSS since they provide high data rates, low data latencies and attitude-determination along with position and velocity.
We will start by highlighting the basic principles of operation of an inertial navigation system. We will focus initially on the concepts underlying the algorithms used to determine position, velocity and attitude from inertial sensor measurements. Key error characteristics will then be described as well such as the Schuler oscillation and vertical channel instability. We will also consider the impact of various sensor errors on system performance.
Navigation-grade inertial systems are characterized by so-called “free inertial” position error drift rates on the order of one nautical mile-per-hour of operation. Such performance implies a certain class of gyros and accelerometers and thus certain specifications on biases, scale factor errors and noise. For more than five decades, the Kalman filter has been the primary tool used to reduce inertial drift through the integration of various sensors. Specifically, the aiding sources (e.g., stellar, Doppler, GPS, etc) are used by the filter to estimate the errors in the free inertial processing. Thus, the heart of any aided-inertial Kalman filter is the inertial error model including, specifically, sensor errors. We will discuss these models and will proceed to explain how aiding source observations are then used by the filter, in conjunction with the models, to estimate the inertial errors. For example, a given aiding source may provide an independent measurement of position, yet somehow the filter is able to use this in order to estimate gyro biases in the inertial system.
The daunting matrix mathematics involved in the full algorithm can be extremely intimidating to the newcomer. In this course, the basic concepts of estimation theory will be reviewed and the Kalman Filter will be described first in terms of simple one-dimensional problems for which the full algorithm reduces to an approachable set of scalar equations. We will look at the performance of the filter in some simple case studies and by the end will have an intuitive feel for how the full filter operates. We will then apply the Kalman filter to the aiding of inertial systems. We will see how external sources of position and velocity (such as GPS) can be used first to measure inertial system error and then, with the aid of the Kalman filter, to estimate and correct inertial sensor error as well as system error.
Introduction to Airborne Radar
Duration: 3 Days
The third edition of Stimson’s Introduction to Airborne Radar has been acclaimed as ‘an absolute must have for all radar enthusiasts …. widely acknowledged as the only book to offer a complete overview of modern airborne radar principles of the last 15-20 years’. This three day course covers all of the material in the book in the same graphical style, explaining complex concepts in a clear and easily-understood manner, with numerous examples of modern systems and results.
- Basic concepts
- Essential groundwork
- Choice of radar frequency
- Pulsed operation
- The radar equation
- FMCW radar
- Pulse Doppler
- Air-to-air operation
- Imaging radar
- Electronic warfare
- Special topics and advanced concepts
- Representative radar systems
Hugh Griffiths holds the Thales/Royal Academy of Engineering Chair of RF Sensors at University College London, UK. He served as President of the IEEE AES Society for 2012/13, is a member of the IEEE AES Radar Systems Panel, and is Editor-in-Chief of the IET Radar, Sonar and Navigation journal. He has won numerous awards including the 2017 IEEE Picard Medal and the 2013 IET A F Harvey Prize.
Introduction to Electronic Warfare
Duration: The course can be offered at different levels of depth, from half-day to five full days.
This short course gives an introduction to Electronic Warfare, ranging from Electronic Attack, Electronic Support, to Electronic Protection techniques, including STAP. The course continues with Electronic Intelligence, radar reverse engineering, and signal analysis, followed by basic direction finding and principles of stealth and low observables. The course can be offered at different levels of depth, from half-day to five full days. The targeted audiences are industry professionals, government technical personnel, defense research institutions, and Radar/EW practitioners. The course is taught at an unclassified level.
Radar Systems Prototyping
Duration: half-day, full-day or two-day
Whether you are a student seeking real data to prove your Ph.D. thesis, or a researcher planning for experimentation in your grant proposal, or a system engineer in need of a radar prototype to demonstrate your innovative idea to a customer, you will be faced with prototyping a radar system with limited time and budget. There exist many books and tutorials on radar signal processing, but little is found on how to build your radar prototype that can support and run these algorithms.
This short course will provide you with practical skills and techniques needed to build your advanced radar prototype. The focus is not on how devices/algorithms work, but on how to relate the choice of microwave devices and signal processing algorithms to the desired radar specifications. You will learn how to interpret datasheets, how components/algorithms affect each other, and how signal processing dictates RF constraints, and how signal processing can fix your RF limitations.
The course will end with a step-by-step MIMO radar design example, starting from the requirements and ending with a schematic and bill of material. The short course can be offered as an half-day, full-day or two-day class.
Introduction to Systems Engineering
Duration: The course can be delivered in 1 day, or 2 days The 2-day course will include some practical exercises
Systems Engineering has emerged as being one of the most important and sought-after disciplines in the engineering world today as our systems under development become ever more complex. And engineering here means not only electrical & electronics engineering, but also mechanical engineering, civil engineering, manufacturing engineering, chemical engineering and similar. It applies to commercial systems as well as military and defense systems. Systems Engineering also applies to other than engineering, as other systems are in need of this discipline, such as banking and finance systems, IT systems, health-care systems, insurance management systems, even “help-desk” systems.
This course covers the essentials of systems engineering, starting with the basic requirements development and management, requirements validation, concept exploration & development, engineering development, risk management, testing, production planning, manufacturing implementation, operations, logistics planning (storage & shipping, upgrades, maintenance & repair, disposal) and interactions with program management.
Introduction to Track-to-Track Fusion and the Distributed Kalman Filter
The increasing trend towards connected sensors (“internet of things” and “ubiquitous computing”) derive a demand for powerful distributed estimation methodologies. In tracking applications, the “Distributed Kalman Filter” (DKF) provides an optimal solution under certain conditions. The optimal solution in terms of the estimation accuracy is also achieved by a centralized fusion algorithm which receives either all associated measurements or so-called “tracklets”. However, this scheme needs the result of each update step for the optimal solution whereas the DKF works at arbitrary communication rates since the calculation is completely distributed. Two more recent methodologies are based on the “Accumulated State Densities” (ASD) which augment the states from multiple time instants. In practical applications, tracklet fusion based on the equivalent measurement often achieves reliable results even if full communication is not available. The limitations and robustness of the tracklet fusion will be discussed.
Objective and Learning Outcomes
The objective is to provide theoretical insights by going through the derivation of the most important algorithms for track-to-track fusion (T2TF) such that the participant is able to understand the means, the conditions and possible pit falls. A well suited solution for T2TF depends on many parameters such as transmission bandwidth, update rates or the possibility to modify local tracks. The interested participant should be able to choose wisely when he or she is aware of the advantages and disadvantages of multiple algorithms.
The intended audience is a mixture of engineers, PhD students, post-docs and academics with some basic background in target tracking.
Outline and time frame of the Short Course
The short course is offered in an half-day and full-day option.
The outline contains some basic theoretical background on challenges in track-to-track fusion and then provides the derivation of the most important algorithms to solve it. This includes centralized fusion, naive fusion, covariance intersection, inverse covariance intersection, Distributed Kalman filter, Federated Kalman Filter, and Distributed ASD Filter
Instructor Short Course History
Felix Govaers received his Diploma in Mathematics and his Ph.D. with the title “Advanced data fusion in distributed sensor applications” in Computer Science, both at the University of Bonn, Germany. Since 2009 he works at Fraunhofer FKIE in the department for Sensor Data Fusion and Information Processing where he was leading the research group “Distributed Systems” from 2014 to 2017. Currently he is the deputy head of the department. The research of Felix Govaers is focused on data fusion for state estimation in non-linear scenarios and in sensor networks. This includes track- extraction, processing of delayed measurements as well as the Distributed Kalman filter and track-to-track fusion. Current research projects are in tensor decomposition based approaches to multi target tracking. He is also interested in advances in state estimation such as particle flow and homotopy filters and the random finite set theory approaches. Felix Govaers is an active member of the ISIF community since 2008, he has been organizing the ISIF co–sponsored SDF Workshop in Germany for many years as the Technical Program Chair. He is an active member of the ISIF Board of Directors since 2017. Since 2014 he also serves as an Associate Editor for the IEEE Transactions on Aerospace and Electronic Systems journal.
Machine and Deep Learning for Data Fusion
Duration: 1-2 days
In this short course, I will present some techniques for fusion and analytics to process big centralized warehouse data, inherently distributed data, and data residing on the cloud. The broad range of artificial intelligence and machine and deep learning techniques to be discussed will handle both structured transactional and sensor data as well as unstructured textual data such as human intelligence, emails, blogs, surveys, etc., and image data. Specifically, the Short Course will explore Deep Fusion to solve multi-sensor big data fusion problems applying deep learning and artificial intelligence technologies.
As a background, this short course is intended to provide an account of both the cutting-edge and the most commonly used approaches to high-level data fusion and predictive and text analytics. The demos to be presented are in the areas of distributed search and situation assessment, information extraction and classification, and sentiment analyses. There will be some hands-on exercises.
Some of the short course materials are based on the following two books by the speaker: 1) Subrata Das. (2008). “High-Level Data Fusion,” Artech House, Norwell, MA; and 2) Subrata Das. (2014). “Computational Business Analytics,” Chapman & Hall/CRC Press.
Topics include the following: High-Level Fusion, Traditional Machine Learning Algorithms, Popular Deep Learning Algorithms (e.g. Convolutional & Recursive Neural Networks, Deep Belief Networks and Restricted Boltzmann Machine, Stacked Autoencoder, ResNet, LSTM), Bagging and Boosting, Descriptive and Predictive Analytics, Text Analytics, Decision Support and Prescriptive Analytics, Cloud Computing, Distributed Fusion, Hadoop and MapReduce, Natural Language Query, Graphical Probabilistic Models, Bayesian Belief Networks, Text Classification, Supervised and Unsupervised Classification, Information Extraction, Natural Language Processing, Demos in R and Python.
Overall objective and learning outcomes of the Short Course: Prepare students, researchers, and industry practitioners with cutting-edge tools and technologies to face the new wave of data science challenges for data fusion.
Intended Audience: The intended audience include designers and developers of analytics systems for any vertical (e.g., defense, healthcare, finance and accounting, human resources, customer support, transportation) who work within business organizations around the world. They will find the course useful as a vehicle for moving towards a new generation of big data fusion and analytics approaches.
Duration: 1 day
Skywave OTH radars operate in the high frequency (HF) band (3-30 MHz) and exploit signal reflection from the ionosphere to detect and track targets at ranges of 1000 to 3000 km. The long-standing interest in OTH radar technology stems from its ability to provide persistent and cost-effective early-warning surveillance over vast geographical areas (millions of square kilometres). Specifically, the chief advantages of OTH radar are to cover geographical areas where it is not possible or convenient to site conventional microwave radars and to provide early-warning and wide-area surveillance that may be used for cueing line-of-sight sensors. Owing to the relatively lower signal bandwidths and large computing infrastructure relative to conventional line-of-sight radars on mobile military platforms, OTH radar is often at the forefront of demonstrating the operational effectiveness of advanced radar processing techniques before it is possible to implement these techniques in radar systems operating at higher frequencies.
The tutorial is organized into three parts. The first introduces the fundamental principles of OTH radar design and operation in the challenging HF environment. This serves to motivate and explain the architecture and nominal capabilities of modern OTH radar systems. The second describes experimentally-validated models of the skywave propagation channel as well as adaptive processing techniques for clutter and interference mitigation. The third delves into emerging applications, including OTH passive radar, blind signal separation, and multipath-driven geolocation for target echoes and HF emitters of interest. A highlight of the tutorial is the prolific inclusion of experimental results illustrating the practical application of robust signal processing techniques to real-world systems. Participants will receive a complimentary text book “High Frequency OTH Radar” McGraw-Hill, NY, 2013.
Passive Radars - New Frontiers and Challenges
Fundamentals of active and passive radars, multi-static concept of operation, illumination sources (FM, DAB, DVB-T, DVB-S, WiFi, GSM, LTE, GPS and many more), clutter modelling and clutter cancellation.EM propagation, signal modelling, matched and unmatched reception, signal processing,range and Doppler walk compensation, Detection limitations, multistatic tracking, PassiveSAR and IASR processing, trafic monitoring, pedestrian detection, sparse signalreconstruction,Object motion modeling, space object detection using DAB and DVB-T signals, Roadmaps.
Students, engineers, air traffic control staff, traffic monitoring staff, border guard, etc.
Duration: 1-2 days: (6 hours per day)Outline and time frame of the Short Course
• Physical basis
• Detection limitations
• Signal processing, detection and tracking
• Passive imaging
• Hardware considerations
• Road map presentation
Instructor Short Course History
NATO lecture series on Passive radar technology (Director) Passive radar tutorials on different radar conferences.
Duration: 5 days
• Good background in Mathematics, Physics.
• Some background in probability, random variables, and stochastic processes.
• Basic knowledge of signal analysis, Fourier analysis, digital filter design, statistical decision theory, and estimation theory.
• Basic knowledge of MATLAB programming.
Course format and dates
The course is given in five days over a week period, intensive format.
During the intensive five-day course, practical sessions also with the use of MATLAB will be interleaved with classic lectures. Practical sessions are intended to strengthen the understanding of the theory and are based on programming and running routines that implement algorithms that are explained during the lectures. The attendees will familiarize with the problems and will understand how to set system parameters to achieve desired performances.
The course can be reduced to two intensive days with a selection of the arguments offered in the five-day course.
Prof. Maria Sabrina Greco – University of Pisa – [email protected]
The course starts with an introductory description of basic radar concepts and terms. The radar equation needed for the basic understanding of radar is then developed, along with the concept of radar cross-section. The lectures then focus on the general schemes of coherent and incoherent radar systems and on the statistical models of the target received signals. Some fundamentals on the detection theory and the Neyman-Pearson criterion are provided and the detection strategies of target signals embedded in correlated Gaussian disturbance are developed along with their performance.
After a lecture on the statistical modeling of clutter, the course will focus on the radar ambiguity function, pulse compression and Doppler processing (MTI and MTD).
The course is concluded by some basic concept on tracking and Kalman filtering.
Principles of Modern Radar, Mark A. Richards, James A. Scheer, William A. Holm (Editors), Scitech, Raleigh, 2010.
Softwarization and Virtualization for Satellite Communications and Services
Duration: 1 day
As softwarization and virtualization are emerging as key components of modern networking architectures, application and extension of those concepts towards satellite communication systems represents a promising field, opening unprecedented opportunities. Indeed, adaptability and on-the-fly reconfigurability will represent the major functionalities enabled by satellite systems softwarization.
The course will aim at addressing the basic concepts and opportunities provided by Software Defined Networking (SDN) and Network Function Virtualization (NFV) in order to integrate them in the design of future satellite communication systems. The course will be divided into three sections. Section I will describe the softwarization and virtualization concepts and enabling technologies. In this section, after briefly describing the current state-of-the-art and directions in satellite communications, the course will focus on analyzing three basic concepts: Software Defined Radios (SDR), Software Defined Networks (SDN) and Network Function Virtualization (NFV). Section II will address the issues related to applying the previous concepts to the satellites architecture, describing several potential steps forward on satellite communications and networking - including flexible and programmable Radio-Frequency interfaces, network slicing, micro-services and containers over satellites, satellite network in a cloud. Finally, Section III will present some scenarios and examples, including the possibility to split the 5G Base Station (gNB) using Cubesat platforms, the design of highly reconfigurable satellites, 5G-satellites integration. All presented concepts will be associated with examples and when possible also short demonstrations using software emulators/simulators.
Overall objective and learning outcomes of the Short Course
Overall objective of the course is to make attendees familiar with concepts of softwarization and virtualization applied to the satellite environment.
Attendees will gain basic knowledge about the concepts of SDR, SDN, NFV
Attendees will understand the potential benefits and requirements of SDR, SDN, NFV
Attendees will understand how to integrate virtualization and softwarization within satellite communication systems
Attendees will be exposed to cutting edge technology and future scenarios in satellite communications
Attendees will learn how to experiment with the presented concepts by the usage of proper tools (e.g. mininet, Matlab, etc.)
The course is addressed to an audience familiar with the basics of communications and in particular satellite communications.
The course will be useful either for young attendees (M.Sc./Ph.D./Young Professional) interested in learning modern communication concepts and in understanding how satellite communication might evolve in the future, as well as for professionals and industry interested in knowing novel emerging paradigms in satellite communications.
Outline and Timeframe of the Short Course
The instructors of the course will be Prof. Fabrizio Granelli and Prof. Claudio Sacchi, that will alternatively address the audience. The level of detail in the different sections can be adapted to the background of the audience as well as the requests from the course organizers.
The table of contents (including indicative time-frame) of the course is the following:
Section I (Concepts and technologies) [3-4 hours]:
- Satellite communications: overview of present and current technologies
- Software Defined Radio
- Software Defined Networks (w/ hands-on on SDN using mininet)
- Network Function Virtualization
Section II (SDN/SDR and NFV in satellites) [2 hours]:
- Flexible RF interfaces
- Network Slicing (w/ hands-on examples using mininet)
- Micro-services and containers on satellites (w/ hands-on examples on docker environment)
- satellite network in a cloud
Section III (scenarios and examples) [2 hours]:
- 5G-satellites integration
- RRH-BBU split on Cubesats (w/ Matlab software examples on design of the link budget)
- Highly reconfigurable satellites
Instructor Short Course History
This course represents a novel initiative by the two instructors, based on joint research activities and ongoing lecturing efforts, in local courses as well as conference seminars.
The two instructors are well-known experts in their respective fields (F. Granelli in networking and C. Sacchi in satellite communications).
Prof. Sacchi is an expert speaker and gave several seminars on satellite communications around the world. He served as lead guest editor for the special issue of PROCEEDINGS OF THE IEEE, entitled: "Aerospace communications and networking in the next two decades: current trends and future perspectives" (issue published in November 2011) and for IEEE COMMUNICATIONS MAGAZINE for the Featured-Topic Special Issue: "Toward the Space 2.0 Era" (first part: published in March 2015).
Prof. Granelli was IEEE ComSoc Distinguished Lecturer for two terms (2012-2015) and visited several areas of the world discussing about recent developments in wireless networking. He gave several courses and tutorials in top level international conferences, including a very successful tutorial on "Softwarization and Virtualization in 5G - Concepts and Practice", which was held at IEEE WCNC 2018, IEEE ICC 2018, IEEE NFV SDN 2018, IEEE BlackSeaCom 2019 and 5G World Forum 2019 (Dresden, Germany). Based on the success of such tutorial series, which are being continued in IEEE Globecom 2019, he is co-writing a book by Elsevier due in 2020, called "Computing in Communication Networks".
Part of the content of the course will be based on such book and hands-on will be supported by a properly developed Virtual Machine developed to provide examples for the book reader - which will be freely distributed.