Program for 2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin)
Sunday, September 8
Sunday, September 8 10:15 - 11:45
- Crypto based Multi-Variable Fingerprinting for Protecting DSP cores
- Enhanced Functional Obfuscation of DSP core using Flip-Flops and Combinational logic
- An Approach for Biometric Verification Based on Human Body Communication using Convolutional Neural Network
- Secure firmware update in embedded systems
- FPGA Design and Implementation of an AES Algorithm based on Iterative Looping Architecture
- A Machine-Learning Based Emotion Recognition System in Patients with Parkinson's Disease
- Contactless measurement of physiological parameters
- Multi-person remote heart-rate measurement from human faces - a CNN based approach
- The Decision Support System Developed for the Stroke Patients Support Platform
Sunday, September 8 11:45 - 12:15
Sunday, September 8 12:15 - 13:15
Mobile technology has gone a long way since the days when devices were produced unchecked, had a small number of capabilities and were of questionable quality. Such current and future devices are expected to revolutionize health care as we know it through mobile health. Not just enabling patients in remote places to get the health care they need, but also enabling everybody to get some treatments at home without visiting the physician's office. This could allow the early release of specific patients from the hospital when the treatment and rehabilitation could be done at home under the remote care of the physician or practitioner while the data is being captured and included in the patient's medical records. This may also revolutionize the existing overall model of the interaction of patients with their physicians and other health care practitioners. In this session, the audience and the panelists will discuss the promises and the challenges of this emerging field.
Sunday, September 8 13:15 - 14:00
Welcoming Ceremony during Lunch; Wahab Almuhtadi, President IEEE CE Society
Jens Heithecker and Dirk Koslowski, IFA
Sunday, September 8 14:00 - 14:45
Cybersecurity is one of the key risks for any business today. Growing attack surface includes amateur threats, such as phishing, and sophisticated distributed denial of service attacks. Prevention is nearly impossible. Given enough time attackers will get in: cost of attack is low and automated probing will find a weakness. Advanced persistent threats show hackers are patient. Defense depends on security analysts who are rare, without training, and with high turnover. AI/ML can help with detection of threat signatures across the corporation and with advisory to security analysts. AI/ML can drive down response times from (hundreds of) hours to seconds and scale analyst effectiveness from 1 or 2 incidents to 1000s. With adequate knowledgebase, it can preserve corporate knowledge and transfer response learnt by AI to new analysts. To advance the adoption of AI/ML applied to cybersecurity, HPE is partnering with IEEE, SEI, and universities around the world. We are defining an annual grand challenge in applying AI/ML to cybersecurity, comprised of: 1) arena/rodeo to operate the challenge; 2) standards for operational metrics (preventing attacks; ensuring AI performs as expected); training data; workflows integrating AI into current processes; and human-machine teaming model; 3) knowledgebase for network traffic capture; policy for AI/ML configuration; AI strategies; execution environment; and capturing security analyst knowledge. Over years, grand challenge will result in a repository of training data, sharing data logs and attack details. As a result it will increase adoption of AI/ML in cybersecurity and reduce attacks.
- 14:00 Applying AI/ML to cybersecurity
Sunday, September 8 14:00 - 15:30
- Monitoring System for a Single Aged Person by Using Smart Meter - Demonstration Test -
- Assisted Living as an Additional Service Integrated in a Smart Home and Offered to the Users
- Effect of Invisible Exertions on Computed Tomography Radiologists in Saudi Hospitals
- System Design and Effectiveness of RFID Introduction into Large Hospitals
- Wearable System for Early Identification of Parkinson's Disease Symptoms Through the Evaluation of the Gait Training
- Re-purposing computers as a cluster for academic institutions
- The Extended LM method For Multiple Frequencies Micro-Doppler Radar for Human Heartbeat Sensing
- A Multiple Coefficients Trial Method to Solve Combinatorial Optimization Problems for Simulated-annealing-based Ising Machines
Sunday, September 8 14:45 - 15:30
Keynote 2: Tiziana Catarci - "Why did my laundry turn pink?" (Towards usability evaluation in home appliances and consumer electronics) (University of Rome 'La Sapienza', Italy)
The modern revolution in Information Technology (IT) has allowed us to interact in advanced ways with a plethora of technological artefacts. This has led to new shapes of user interfaces (UIs) and styles of interaction. Today's UIs range from simple mobile input devices with touchscreens and clickable symbols, to home appliances with physical buttons and smart displays, to immersive environments with augmented and virtual reality. The general feeling is that such an increased interactivity is a positive feature. However, differently from the majority of web and software tools, consumer electronics products are sold for a large part based on the functionalities they offer, and an excess of functionalities is likely to lead to less usable products. In addition, consumer electronics products are becoming more and more networked and part of a large ecosystem of connected devices, and today many of the most serious usability problems are caused by the ecosystem as a whole, not by the UIs of the individual products. Since the majority of end-users of consumer electronics products simply want their tasks done in the best way, a possibility to make such products more usable is the transfer of (part of) the task execution workload from the user to the system, as it is done in so-called smart systems. Then, the possible gain in usability needs to be precisely evaluated. Unfortunately, traditional user evaluation techniques from the Human-Computer Interaction (HCI) field fail to properly measure the usability of consumer electronics products, for which it would be required to observe the end-users conducting their own activities with the products for extended time frames. This is very expensive in terms of the time required to collect the data, strongly limiting the number of user tests that can be performed and, consequently, reducing the reliability of the evaluation techniques. To mitigate the above issues, it is becoming common practice to capture the interactions with UIs during daily use and save them into log files for later analysis using dedicated log studies. In this talk, after having introduced an HCI perspective over consumer electronics, we analyze the transition that is taking place in the HCI field towards the use of log studies in order to build frameworks for capturing actual user behavior (and not recalled behaviors or subjective impressions) and, consequently, effectively evaluating the usability of any kind of modern interactive device.
- 14:45 Why did my laundry turn pink? (Towards usability evaluation in home appliances and consumer electronics)
Sunday, September 8 15:30 - 16:00
Sunday, September 8 16:15 - 17:00
Keynote 3: Klaus-Robert Müller - "Machine learning and AI for the sciences - towards understanding" (Machine Learning Laboratory, Berlin Institute of Technology, Berlin, Germany)
In recent years machine learning (ML) and Artificial Intelligence (AI) methods have begun to play a more and more enabling role in the sciences and in industry. In particular, the advent of large and/or complex data corpora has given rise to new technological challenges and possibilities. The talk will connect two topics (1) explainable AI (XAI) and (2) ML applications in sciences (e.g. Medicine and Quantum Chemistry) for gaining new insight. Specifically I will first introduce XAI methods (such as LRP) that are now readily available and allow for an understanding of the inner workings of nonlinear ML methods ranging from kernel methods to deep learning methods including LSTMs. In particular XAI allows to unmask clever Hans predictors. Then, ML for Quantum Chemistry is discussed, showing that ML methods can lead to highly useful predictors of quantum mechanical properties of molecules (and materials) reaching quantum chemical accuracies both across chemical compound space and in molecular dynamics simulations. Notably, these ML models do not only speed up computation by several orders of magnitude but can give rise to novel chemical insight. Finally, I will analyse morpholocal and molecular data for cancer diagnosis; also here highly interesting novel insights can be obtained. Note that while XAI is used for gaining a better understanding in the sciences, the introduced XAI techniques are readily useful in other application domains and industry as well.
- 16:15 Machine learning and AI for the sciences - towards understanding
Sunday, September 8 16:15 - 17:45
- Light field image compression using Versatile Video Coding
- Artifacts reduction for very low bitrate image compression with generative adversarial networks
- Hybridization of structured light and Time-of-Flight sensing using maximum a posteriori Markov Random Fields
- Video delivery subsystem for multi-SoC automotive machine vision platforms
- Super-resolution Image Reconstruction Utilizing High-Precision Skin Color for Face Images
Sunday, September 8 17:05 - 18:55
- Hardware Steganography for IP Core Protection of Fault Secured DSP Cores
- IP Core Identification in FPGA Configuration Files using Machine Learning Techniques
- Read Threshold Calibration for Non-Volatile Flash Memories
- Lifetime-Optimal Buffer Management on Flash-based Swap Framework for Smart TV
- Fast and Light-weight Binarized Neural Network Implemented in an FPGA using LUT-based Signal Processing and its Time-domain Extension for Multi-bit Processing
- Robust Digital Signature to Protect IP Core against Fraudulent Ownership and Cloning
Sunday, September 8 17:50 - 19:20
- DASH Transport Emulator System Supporting Multi-Broadcast Standards
- Video Captioning Based on Joint Image-Audio Deep Learning Techniques
- Hierarchical Model for Multimedia Content Classification
- Porting Adaptive Multiple Transforms of a Versatile Video Coding decoder using OpenMP
- Automated traffic congestion estimation via public video feeds
Monday, September 9
Monday, September 9 10:15 - 11:00
With the promise of making life easier, more convenient and fun, consumers are turning to more and more devices to simplify their lives. And yet, consumer technology is really just a mosaic of badly integrated applications. At TELUS, putting customers first isn't just about ease of use. Instead, incorporating security and privacy from the onset, or by design, is an absolute necessity to safeguarding our customers' lives.
- 10:15 Security and Privacy by Design
Monday, September 9 10:15 - 11:45
- A 37 to 40 GHz Transceiver for Fifth Generation Communication Systems
- Deep-learning Based Adaptive Beam Management Technique for Mobile High-speed 5G mmWave Networks
- Reception Complexity and Power Consumption reduction with ASK in 3-layer LDM
- Double Threshold Soft Decision Rule for Improving Performance of Cognitive Radio Networks
- Evaluation of the BER Performance of LoRa Communication using BICM Decoding
Monday, September 9 11:00 - 11:45
In the consumer goods industry, manufacturers are generally divided into "white goods" (particularly household appliances), "brown goods" (consumer electronics),"gray goods" (Information and communication technology) and in Germany also in so-called "red goods" (thermal technology). These companies are geared towards the specific needs of their end users (B2C), however, they also need to consider the specific interests of their retailers (B2B). Trendsetting product innovations with great application benefits and tailor-made functionality are topics that help them penetrate the market. The complexity management plays an important role in this process. Only those who rapidly build product and production architectures in line with the market needs and establish at the same time an agile organization can withstand the high pressure of global competition.
Monday, September 9 11:45 - 12:15
Monday, September 9 12:15 - 13:15
Panel 2: Women in technologies: Technology advances rapidly, how does it affect a woman's role and share in technology?
We are facing rapid development in every field of technology, yet, the gender issue remains unresolved. Do we make a mountain out of a molehill, or we need to take the matter more seriously? How organizations like IEEE, ACM, or VDE can help? Does it require change at every level of the society, or the engineers can provide a unique solution that will set a rule?
Be active part of this session, and help us find a point of view that is revolutionary.
This tutorial presents a way to identify the principle behind a solution. Through a process of clarifying the problem-solution relationship in technical writing, a better logic for the paper is built. A solid logic directly benefits the author(s) by making reviewers understand the contribution of the paper easily, leading to a higher acceptance rate. It is emphasized that the earlier mentioned clarification process to establish a solid logic often unveils a more general principle behind a solution, which may open a door to another research. Some examples to convince the audience support the value of technical writing.
Monday, September 9 13:15 - 14:00
Keynote 6: Vasilis Ntziachristos - "Optical and optoacoustic imaging: the revolution of label free observations" (Technical University Munich & Helmholtz Zentrum München, Germany)
Optical imaging is unequivocally the most versatile and widely used visualization modality in the life sciences. Yet it has been significantly limited by photon scattering, which complicates the visualization of tissue beyond a few hundred microns. For the past few years, there has been an emergence of powerful new optical and optoacoustic imaging methods that offer high resolution imaging beyond the penetration limits of microscopic methods. The talk discusses progress in multi-spectral opto-acoustic tomography (MSOT) and mesoscopy (MSOM) that bring unprecedented optical imaging performance in visualizing anatomical, physiological and molecular biomarkers. Advances in light technology, detection methods and algorithms allow for highly-performing visualization in biology and medicine through several millimetres to centimetres of tissue and real-time imaging. The talk demonstrates implementations in the time and frequency domain, showcase how it is possible to accurately solve fluence and spectral coloring issues for yielding quantitative measurements of tissue oxygenation and hypoxia and demonstrate quantitative in-vivo measurements of inflammation, metabolism, angiogenesis in label free mode. In parallel, progress with clinical systems and the complementarity with ultrasound imaging, fluorescence molecular imaging and other modalities is discussed. Finally the talk offers insights into new miniaturized detection methods based on ultrasound detection using optical fibers, which could be used for minimally invasive applications.
- 13:15 Optical and optoacoustic imaging: the revolution of label free observations
Monday, September 9 13:15 - 14:45
- Examining Carrier Sense Multiple Access to Enhance LoRa IoT Network Performance for Smart City Applications
- Vision-Based Road-Following Using Results of Semantic Segmentation for Autonomous Navigation
- Brand usage detection via Audio Streams
- The auto-pilot robot based on computer vision in deep learning
- Data generators: a short survey of techniques and use cases with focus on testing
- Development Environment Proposal for Automotive Vision-Based Algorithms
- Enriching Tourist UX via a Location Based AR Treasure Hunt Game
- Investigating Tangible User Interaction in Mixed-Reality Robotic Games
- Using Class-Dependent Post-Processing to Improve AI for Automotive Front View Camera
Monday, September 9 13:15 - 14:00
Monday, September 9 14:00 - 14:45
Keynote 7: Peter Peumans - "When healthcare becomes personal: technology giving power to the patient" (IMEC, Belgium)
ABSTRACT Patient care is changing rapidly from a generic to a much more personalized approach. In addition, healthcare systems are shifting their focus from diagnosis to early disease interception and even disease prevention. Such a personalized and preventative approach to healthcare requires disruptive technology solutions to closely monitor one's health.
This talk will discuss the trends in health care and life science technologies that enable early diagnosis, disease prevention and effective personalized therapies. Examples of such technologies are high-precision medical-quality wearables and connected health sensors, and systems to integrate complex lab analytics and diagnostics into a consumer-friendly package.
Dr. Peumans holds a Ph.D. in electrical engineering from Princeton University, and a bachelor's and master's degree from the Katholieke Universiteit Leuven. Prior to joining imec, Dr. Peumans was a professor of electrical engineering at Stanford University. He is the recipient of an NSF CAREER award and a Belgian-American Educational Foundation honorary fellowship. He currently leads imec's life science technologies program.
- 14:00 When healthcare becomes personal: technology giving power to the patient
Monday, September 9 14:50 - 16:20
- Case Study of Photovoltaic Energy Surplus Absorption by Charging Lithium-Ion Batteries Considering Charge-Discharge Energy Efficiency
- Mapping Constrained Slot-Placement Problems to Ising Models and its Evaluations by an Ising Machine
- Efficient Ising Model Mapping for Induced Subgraph Isomorphism Problems Using Ising Machines
- Power-Efficient Video Streaming on Mobile Devices Using Optimal Spatial Scaling
- Monitoring of photovoltaic systems for self-consumption without over-consumption
- Implementation of Yolo-v2 Image Recognition and Other Testbenches for a CNN Accelerator
- Semantic Segmentation-Based Real-Time Shallow Depth-of-Field Imaging Using a Single Smartphone Camera
- Optimization of Head-related Transfer Function (HRTF) Models
- Optimizing Deep Learning Based Semantic Video Segmentation on Embedded GPUs
- Multiunit automotive perception framework: Synergy between AI and deterministic processing
Monday, September 9 15:30 - 16:00
Monday, September 9 16:50 - 18:20
- Intelligent SOMA interactive gaming system
- Real-Time Streaming of Sequential Volumetric Data for Augmented Reality Synchronized with Broadcast Video
- Creating AR models for challenging sizes
- A Makerspace Foot Pedal and Shoe Add-On for Seated Virtual Reality Locomotion
- Unity3D-based app for 360VR subjective quality assessment with customizable questionnaires
Monday, September 9 16:50 - 18:40
- Facial Expression Recognition Using Robust Local Directional Strength Pattern Features and Recurrent Neural Network
- Accuracy Improvement of Fashion Style Estimation with Attention Control of a Classifier
- Estimating Power Consumption of Air-conditioners Using a Sequence-to-sequence Model
- Digital Content Enrichment for Mobile Devices: The Case of the Folklore Museum of Xanthi
- Deep Fashion Recommendation System with Style Feature Decomposition
- Dementia Screening System based on SNS Agency Robot
Monday, September 9 20:00 - 22:00
Tuesday, September 10
Tuesday, September 10 10:15 - 11:45
- Model-Based Load Testing in the IoT System
- IoT Based People Detection for Emergency Scenarios
- Monitoring Sake Brewing Processes with Compact Wireless Sensors
- AMANDA: An Autonomous Self-Powered Miniaturized Smart Sensing Embedded System
- Assistive Technology through Internet of Things and Edge Computing
- Augmented reality for cultural heritage education
- Virtual Learning Environment for an Industrial Assembly Task
- Virtual Reality for training the public towards unexpected emergency situations
- On the Usability of Consumer Locomotion Techniques in Serious Games: Comparing Arm Swinging, Treadmills and Walk-in-Place
Tuesday, September 10 11:45 - 12:15
Tuesday, September 10 12:00 - 13:15
- Deep Learning Based Classification of Pedestrian Vulnerability Trained on Synthetic Datasets
- Automatic Headlight Leveling System with a Modular Design for the Automotive Aftermarket
- Real-Time Multiple Pedestrian Tracking Based on Object Identification
- Integral image computation algorithm for GPU-enabled automotive platforms
Tuesday, September 10 12:15 - 13:15
We are leaving the futuristic novels lives. There is a rumors that Elon Musk based some of his visions based on his favorite SciFi books. Join this panel and let us know about your visions and favorite novels.
Tuesday, September 10 13:15 - 14:00
Keynote 8 during Lunch: Robert Riener - "Rehabilitation robots that cooperate and motivate" (ETH and University of Zurich, Switzerland)
Robots can be very useful to restore movement abilities of upper and lower limbs. First, they can promote neurorehabilitation as training devices after neurological injuries such as spinal cord injury (SCI), traumatic brain injury and stroke. Second, they can be used as assistive devices to support patients or elders with gait impairments in daily life situations. However, current mechatronic solutions are still too bulky and their sensory technologies and control strategies are still too primitive to allow the correct motion intention. Therefore, they do not provide effective assist-as-needed support and are too inconvenient to use. In this talk I will present new patient-cooperative controllers, intention detection strategies and virtual reality technologies that will improve the rehabilitation of arm movements and gait. I will also present the Cybathlon, which is a new kind of Olympics-style championship, where people with physical disabilities compete against each other at tasks of daily life, with the aid of robotic technologies. The next Cybathlon will take place in Zurich, on May 2nd and 3rd 2020.
- 13:15 Rehabilitation robots that cooperate and motivate
Key point of each home-automation is to be controlled by a browser. Any browser. Plus - three levels: Level 1. Connect sensors to computer Level 2. Connect multiple computers to aggregating server Level 3. Present data to end user via browser This tutorial will talk about ways to achieve these three levels. Player 1 - ready to participate? We dare you!!!
Tuesday, September 10 14:00 - 14:45
Keynote 9: Daniel Wilms - "Standardization as enabler towards a data centric architecture in automotive" (BMW Group Research, New Technologies, Innovations, Germany)
With the growing number of connected vehicles, changing customer expectations and the opportunities in creating innovation through the combination of digital information, the management and understanding of data gets more and more important. In this context, the domain specific knowledge, which is needed for standardization of data models is a key asset for a successful adaptation in the long run. The presentation will give an overview of some of the standardization activities at BMW Research in regard to vehicle signals and show examples on how it is already used within the company.
- 14:00 Standardization as enabler towards a data centric architecture in automotive
Tuesday, September 10 14:00 - 15:30
- An Immersive Service Guide for Home Appliances
- Open IoT Infrastructures for In-Home Energy Management and Control
- Health Monitoring and Auto-Scaling RabbitMQ Queues within the Smart Home System
- Performing Administrative Tasks on Multiple Home Automation Gateways
- Effective Photometric Alignment for Surround View Monitoring System
- Parallelization Of Object-oriented Machine Vision Algorithms For Embedded GPUs
- HIL Based Solution for ADAS Software Development and Verification
- An Automated Testing Methodology For Digital TV Middleware Implementations
- Cybersecurity Risk Assessment for IoT Platforms
- A Route Recommendation Method Based on Personal Preferences by Monte-Carlo Tree Search
- Adapting Live TV application for mobile devices
- Integrating AMV ALPHA to The Bonseyes Artificial Intelligence Marketplace
Tuesday, September 10 14:45 - 15:30
Keynote 10: Akihiko K. Sugiyama - "Phase: Unexplored Wilderness in Signal Enhancement" (Yahoo Japan Corporation, Japan)
his lecture presents importance and possibilities of phase information in signal enhancement. Phase has not been given as much attention in signal enhancement as its counterpart; i.e. magnitude. This is partially because Wang and Lim experimentally showed in 1982 that except for some conditions, accurate phase does not help improve the SNR. After three decades, signal processing applications have significantly expanded and with these new applications, some of the conditions Wang and Lim did not take into consideration have come up in the spotlight. Two examples of those new applications covered in this talk are impact noise suppression and mechanical noise suppression. Consumer products that need these applications have a huge market today. Different uses of phase information in those applications are presented with audio demonstrations.
Akihiko Sugiyama (a.k.a. Ken Sugiyama), affiliated with Yahoo! JAPAN Research, has been engaged in a wide variety of research projects in signal processing such as audio coding and interference/noise control. His team developed the world's first Silicon Audio in 1994, a precursor of iPod. He served as the Chair of Audio and Acoustic Signal Processing Technical Committee, IEEE Signal Processing Society (SPS) [2011-2012], as associate editors for several journals such as IEEE Trans. Signal Processing [1994-1996], as the Secretary and a Member at Large to the Conference Board of SPS [2010-2011], as a member of the Awards Board of SPS [2015-2017], as the Chair of Japan Chapter of SPS [2010-2011], and a member of IEEE Fellow Committee. He was a Technical Program Chair for ICASSP2012. He has contributed to 17 chapters of books and is the inventor of 217 registered patents with more pending applications in the field of signal processing in Japan and overseas. He received 17 awards such as the 2002 IEICE Best Paper Award, the 2006 IEICE Achievement Award, and the 2013 Ichimura Industry Award. He has delivered 117 invited talks in 48 cities of 20 countries. He is Fellow of IEEE and IEICE, and a Distinguished Lecturer for IEEE SPS [2014-2015] and for IEEE CE (Consumer Electronics Society) [2017-2018].
- 14:45 Phase: Unexplored Wilderness in Signal Enhancement
Tuesday, September 10 15:30 - 16:00
Tuesday, September 10 15:45 - 17:00
Tuesday, September 10 16:00 - 17:00
Tuesday, September 10 17:05 - 19:00
Wednesday, September 11
Wednesday, September 11 10:15 - 16:15
In this instructor-led workshop supported by NVIDIA Deep Learning Institute (DLI), you will explore the fundamentals of deep learning by training neural networks and using results to improve performance and capabilities. You'll learn the basics of deep learning by training and deploying neural networks. Among other, you will be enabled to (1) implement common deep learning workflows, such as image classification and object detection; (2) experiment with data, training parameters, network structure, and other strategies to increase performance and capability; (3) deploy neural networks to start solving real-world problems. Upon completion, you'll be able to start solving problems on your own with deep learning. Each participant is awarded an official NVIDIA DLI certificate of course completion.
Note: Apply at the registration desk when collecting your badge! You will need your own laptop for the workshop, power and internet connection will be provided.