Search results for "Encoder"
showing 10 items of 61 documents
The Dreaming Variational Autoencoder for Reinforcement Learning Environments
2018
Reinforcement learning has shown great potential in generalizing over raw sensory data using only a single neural network for value optimization. There are several challenges in the current state-of-the-art reinforcement learning algorithms that prevent them from converging towards the global optima. It is likely that the solution to these problems lies in short- and long-term planning, exploration and memory management for reinforcement learning algorithms. Games are often used to benchmark reinforcement learning algorithms as they provide a flexible, reproducible, and easy to control environment. Regardless, few games feature a state-space where results in exploration, memory, and plannin…
A Nonlinear Label Compression and Transformation Method for Multi-label Classification Using Autoencoders
2016
Multi-label classification targets the prediction of multiple interdependent and non-exclusive binary target variables. Transformation-based algorithms transform the data set such that regular single-label algorithms can be applied to the problem. A special type of transformation-based classifiers are label compression methods, which compress the labels and then mostly use single label classifiers to predict the compressed labels. So far, there are no compression-based algorithms that follow a problem transformation approach and address non-linear dependencies in the labels. In this paper, we propose a new algorithm, called Maniac (Multi-lAbel classificatioN usIng AutoenCoders), which extra…
PON Monitoring Technique Based on 2D Encoders and Wavelength-to-Time Mapping
2020
A PON monitoring technique is demonstrated based on an OTDR-like device and FBG-encoders having a unique combination of central wavelength and reflection bandwidth. This results in more compact and cost-efficient encoders than previous proposals.
Low-cost motion control solution for industrial manufacturing systems
2011
This paperwork deals with a low-cost actuation solution, based upon induction motors, which was seldom used in the motion control systems, especially for the machine tools feed drives. A simulation approach, based upon a mathematical model of the induction motor, for tuning the controllers of the systems is presented. Experimental researches developed upon a two axes motion control system, both axes being driven by alternating current asynchronous motors were also performed in order to test the proposed strategies. The asynchronous motors, used as actuation devices were equipped with incremental rotary encoders and controlled by vector frequency inverters and DSP motion control cards were u…
Positioning system for assembly and manufacturing tasks
2019
The paper presents a two-axis positioning system using asynchronous motors as actuation devices. Theuse of asynchronous motors reduces the overall cost of the system, while providing actuating torques superior to the ones provided by stepping motors. The system is controlled by mean of a programmable logic controller (PLC) and two voltage-frequency inverters fitted with motion control cards. In contrasts to a stepping motor system, which works in open loop mode, the proposed system uses closed loop control on each axis. The motion loop is closed by means of an incremental encoder.
Development of Motorized Slewing Mirror Stage for the UFFO Project
2013
The Ultra-Fast Flash Observatory (UFFO) is a space observatory for optical follow-ups of gamma ray bursts (GRBs), aiming to explore the first 60 seconds of GRBs optical emission. UFFO is utilized to catch early optical emissions from GRBs within few sec after trigger using a Gimbal mirror which redirects the optical path rather than slewing entire spacecraft. We have developed a 15 cm two-axis Gimbal mirror stage for the UFFO-Pathfinder which is going to be on board the Lomonosov satellite which is to be launched in 2013. The stage is designed for fast and accurate motion with given budgets of 3 kg of mass and 3 Watt of power. By employing stepping motors, the slewing mirror can rotate fast…
A New Method of Velocity Estimation Based on Variable Temporal Basis Using Incremental Encoder
1997
Abstract This paper deals with analysis and synthesis of algorithms for digital conditioning of signals generated by incremental encoders to estimate velocity of rotating devices for control purposes. Main objectives are to obtain high accuracy at low and high velocity and low tracking delays during accelerations. A digital conditioning method is described, Which uses a polynomial of order n whose coefficients are updated so as to fit the n+1 most recent velocity data acquired on a variable temporal basis. Digital sinlulations and experimental findings are shown with the ainl to validate the proposed estimation method and compare it with other methods.
Discovering web services in social web service repositories using deep variational autoencoders
2020
Abstract Web Service registries have progressively evolved to social networks-like software repositories. Users cooperate to produce an ever-growing, rich source of Web APIs upon which new value-added Web applications can be built. Such users often interact in order to follow, comment on, consume and compose services published by other users. In this context, Web Service discovery is a core functionality of modern registries as needed Web Services must be discovered before being consumed or composed. Many efforts to provide effective keyword-based service discovery mechanisms are based on Information Retrieval techniques as services are described using structured or unstructured textdocumen…
Deep Completion Autoencoders for Radio Map Estimation
2022
Radio maps provide metrics such as power spectral density for every location in a geographic area and find numerous applications such as UAV communications, interference control, spectrum management, resource allocation, and network planning to name a few. Radio maps are constructed from measurements collected by spectrum sensors distributed across space. Since radio maps are complicated functions of the spatial coordinates due to the nature of electromagnetic wave propagation, model-free approaches are strongly motivated. Nevertheless, all existing schemes for radio occupancy map estimation rely on interpolation algorithms unable to learn from experience. In contrast, this paper proposes a…
Rapid parameter estimation of discrete decaying signals using autoencoder networks
2021
Machine learning: science and technology 2(4), 045024 (2021). doi:10.1088/2632-2153/ac1eea