ABSTRACT
Neuromorphic event-based cameras communicate transients in luminance instead of frames, providing visual information with a fine temporal resolution, high dynamic range and high signal-to-noise ratio. Enriching event data with color information allows for the reconstruction of colorful frame-like intensity maps, supporting improved performance and visually appealing results in various computer vision tasks. In this work, we simulated a biologically inspired color fusion system featuring a three-stage convolutional neural network for reconstructing color intensity maps from event data and sparse color cues. While current approaches for color fusion use full RGB frames in high resolution, our design uses event data and low-spatial and tonal-resolution quantized color cues, providing a high-performing small model for efficient colorful image reconstruction. The proposed model outperforms existing coloring schemes in terms of SSIM, LPIPS, PSNR, and CIEDE2000 metrics. We demonstrate that auxiliary limited color information can be used in conjunction with event data to successfully reconstruct both color and intensity frames, paving the way for more efficient hardware designs.
Subject(s)
Benchmarking , Neural Networks, Computer , Equipment Design , Signal-To-Noise Ratio , Image Processing, Computer-AssistedABSTRACT
Facilitated by advances in real-time sensing, low and high-level control, and machine learning, autonomous vehicles draw ever-increasing attention from many branches of knowledge. Neuromorphic (brain-inspired) implementation of robotic control has been shown to outperform conventional control paradigms in terms of energy efficiency, robustness to perturbations, and adaptation to varying conditions. Here we propose LiDAR-driven neuromorphic control of both vehicle's speed and steering. We evaluated and compared neuromorphic PID control and online learning for autonomous vehicle control in static and dynamic environments, finally suggesting proportional learning as a preferred control scheme. We employed biologically plausible basal-ganglia and thalamus neural models for steering and collision-avoidance, finally extending them to support a null controller and a target-reaching optimization, significantly increasing performance.
Subject(s)
Automobile Driving , Robotics , Autonomous Vehicles , Machine Learning , Neural Networks, ComputerABSTRACT
Background: EEG-driven research is paramount in cognitive-neuropsychological studies, as it provides a non-invasive window to the underlying neural mechanisms of cognition and behavior. A myriad collection of software and hardware frameworks has been developed to alleviate some of the technical barriers involved in EEG-driven research. Methods: we propose an integrated development environment which encompasses the entire technical "data-collection pipeline" of cognitive-neuropsychological research, including experiment design, data acquisition, data exploration and analysis in a state-of-the-art user interface. Our framework is based on a unique integration between a python-based web framework, time-oriented databases and object-based data schemes. Results: we demonstrated our framework with the recording and analysis of an n-Back task completed by 15 elderly (ages 50 to 80) participants. This case study demonstrates the highly utilized nature of our integrated framework with a challenging target population. Furthermore, our results may provide new insights into the correlation between brain activity and working memory performance in elderly people, who are prone to experience accelerated decline in executive prefrontal cortex functioning. Conclusion: our framework extends the range of EEG-driven experimental methods for assessing cognition available for cognitive-neuroscientists, allowing them to concentrate on the creative part of their work instead of technical aspects.
ABSTRACT
Microfluidic devices developed over the past decade feature greater intricacy, increased performance requirements, new materials, and innovative fabrication methods. Consequentially, new algorithmic and design approaches have been developed to introduce optimization and computer-aided design to microfluidic circuits: from conceptualization to specification, synthesis, realization, and refinement. The field includes the development of new description languages, optimization methods, benchmarks, and integrated design tools. Here, recent advancements are reviewed in the computer-aided design of flow-, droplet-, and paper-based microfluidics. A case study of the design of resistive microfluidic networks is discussed in detail. The review concludes with perspectives on the future of computer-aided microfluidics design, including the introduction of cloud computing, machine learning, new ideation processes, and hybrid optimization.