intelligent transportation systems use GNSS receivers as basic technological components. In urban applications one faces the problem of GNSS multipath and particularly of non-line-of-sight (NLOS) satellites. The devel...
详细信息
ISBN:
(纸本)9798350399462
intelligent transportation systems use GNSS receivers as basic technological components. In urban applications one faces the problem of GNSS multipath and particularly of non-line-of-sight (NLOS) satellites. The development of GNSS receiver technologies for mass market encompasses the capability NLOS satellites processing by innovative techniques, not only based on the signal to Noise Ratio, but also on vision or city model. This is particularly needed for urban positioning of cars for applications which require high accuracy and integrity, typically driving automation. This article deals with the detection of NLOS satellites among those tracked by an automotive-range receiver. We aim at developing a method jointly based on the analysis of video stream and a 3D map model of the environment. The article provides a literature review, an evaluation of some existing techniques and a preliminary analysis of the implementation of the retained algorithm on a prototype developed in the frame of a European H2020 "Fundamental Elements call" project.
In this paper, based on compressed sensing and neural networks, we present an intelligent sparse channel estimation technique for Massive MIMO systems. We show that our approach improves considerably the estimation ac...
详细信息
Autonomous mobile systems exploring unknown environments face the challenge of optimizing their routes to minimize time and distance traveled. This paper explores integrating SLAM algorithms with optimized routing tec...
详细信息
In order to overcome environmental concerns and reduce aircraft operating cost, the concept of More Electric Aircraft (MEA) has been presented to in-crease aircraft efficiency and reduce maintenance requirement by inc...
详细信息
The proceedings contain 175 papers. The topics discussed include: an optimized inverse neural network control augmented with feedback PI controller for time-varying systems;image encryption using neural network based ...
ISBN:
(纸本)9798331528201
The proceedings contain 175 papers. The topics discussed include: an optimized inverse neural network control augmented with feedback PI controller for time-varying systems;image encryption using neural network based chaotic systems;investigating the impact of update frequency on PID controller performance in autonomous robotics;deep learning framework for constellation signal classification in underwater optical wireless communication systems;fuzzy based web automation for smart power supply controller;ensembled machine learning models for antenna optimization in wireless communication/ biomedical applications;vertically integrated substrate integrated cavity based filtering antenna;network intrusion detection system using autoencoders;and a comparative study of Wallace tree multiplier and binary multiplier performance.
intelligent HR systems have become a transformative force for global organizations, driven by AI, machine learning, and data analytics to embrace Industry 4.0 opportunities. This paper explores their implications, hig...
详细信息
The 1-ms visual feedback system is critical for seamless actuation in robotics, as any delay affects its performance in handling dynamic situations. Specular reflections cause problems in many visual technologies, mak...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
The 1-ms visual feedback system is critical for seamless actuation in robotics, as any delay affects its performance in handling dynamic situations. Specular reflections cause problems in many visual technologies, making specular detection crucial in 1-ms visual feedback systems. However, existing real-time methods, which target Neumann architecture, fail to achieve the 1-ms delay due to spatial memory paths resulting from extensive frame-based processing. This research aims to develop a 1-ms specular detection system from both algorithm and architecture perspectives, proposing 1) temporal clustering and temporal reference based specular detection method, which leverages temporal domain information to address the requirements of frame-based processing;and 2) global-local integrated specular detection architecture, which enables the coexistence of local and global processing within a 1-ms stream-based architecture. The proposed methods are implemented on FPGA. The evaluation shows that the proposed system supports sensing and processing a 1000-fps sequence with a delay of 0.941 ms/frame.
Satellite based Navigation systems and Inertial Navigation systems (INS) are conventionally used for Aircraft Navigation. Instrumentation landing systems (ILS) needs equipment on runway as well as on the aircraft. Whe...
详细信息
We propose an object recognition system for vehicles controlled by "Automated Driving systems (ADS)."In particular, the proposed system aims at operating "Minimum Risk Maneuver (MRM)"for the ADS on...
详细信息
Spiking neural networks (SNNs) have gained attention in recent years due to their ability to handle sparse and event-based data better than regular artificial neural networks (ANNs). Since the structure of SNNs is les...
详细信息
ISBN:
(纸本)9798350383638;9798350383645
Spiking neural networks (SNNs) have gained attention in recent years due to their ability to handle sparse and event-based data better than regular artificial neural networks (ANNs). Since the structure of SNNs is less suited for typically used accelerators such as GPUs than conventional ANNs, there is a demand for custom hardware accelerators for processing SNNs. In the past, the main focus was on platforms that resemble the structure of multiprocessor systems. In this work, we propose a lightweight neuron layer architecture that allows network structures to be directly mapped onto digital hardware. Our approach is based on differential time coding of spike sequences and the decoupling of processing time and spike timing that allows the SNN to be processed on different hardware platforms. We present synthesis and performance results showing that this architecture can be implemented for networks of more than 1000 neurons with high clock speeds on a State-of-the-Art FPGA. We furthermore show results on the robustness of our approach to quantization. These results demonstrate that high-accuracy inference can be performed with bit widths as low as 4.
暂无评论