Search results for "Artificial intelligence"
showing 10 items of 6122 documents
Análisis de la utilidad del algoritmo Gradient Boosting Machine (GBM) en la predicción del fracaso empresarial
2018
Este estudio, novedoso en cuanto a la utilizacion de la metodologia basada en la cultura de los algoritmos, prueba la capacidad de la tecnica ‘Gradient Boosting Machine’ (GBM) en la prediccion de l...
Early detection and classification of bearing faults using support vector machine algorithm
2017
Bearings are one of the most critical elements in rotating machinery systems. Bearing faults are the main reason for failures in electrical motors and generators. Therefore, early bearing fault detection is very important to prevent critical system failures in the industry. In this paper, the support vector machine algorithm is used for early detection and classification of bearing faults. Both time and frequency domain features are used for training the support vector machine learning algorithm. The trained classier can be employed for real-time bearing fault detection and classification. By using the proposed method, the bearing faults can be detected at early stages, and the machine oper…
Sensorless control of induction motors using an extended Kalman filter and linear quadratic tracking
2017
Induction motors are the most commonly used prime-movers in industrial applications. Many induction motors supplied by frequency converters are coupled with a physical angular rotor position/velocity sensor which makes the drive complex and require maintenance. This paper presents a sensorless control structure to avoid using a physical angular rotor position/velocity sensor. The proposed method estimates and control the angular rotor velocity using optimal control theory. The optimal controller used in this paper is based on linear quadratic tracking and the states of the machine are estimated using an extended Kalman filter. Both the controller and the estimator utilize the same internal …
Computational volumetric reconstruction of integral imaging with improved depth resolution considering continuously non-uniform shifting pixels
2018
Abstract In this paper, we propose a new computational volumetric reconstruction technique of three-dimensional (3D) integral imaging for depth resolution enhancement by using non-uniform and integer-valued shifting pixels. In a typical integral imaging system, 3D images can be recorded and visualized using a lenslet array. In previous studies, many computational reconstruction techniques such as computational volumetric reconstruction and pixel of elemental images rearrangement technique (PERT) have been reported. However, a computational volumetric reconstruction technique has low visual quality and depth resolution because low-resolution elemental images and uniformly distributed shiftin…
Integral-Imaging display from stereo-Kinect capture
2017
In this paper, we propose a new approach in order to improve the quality of microimages and display them onto an integral imaging monitor. Our main proposal is based on the stereo-hybrid 3D camera system. Originally, hybrid camera system has dissimilarity itself. We interpret our method in order to equalize the hybrid sensor's characteristics and 3D data modification strategy. We generate integral image by using synthetic back-projection mapping method. Finally, we project the integral image onto our proposed display system. We illustrate this procedure with some imaging experiments in order to prove an advantage of our approach.
Binocular function measures as predictors of user performance in stereoscopic augmented reality
2021
Inconsistency between the binocular and focus cues in stereoscopic augmented reality overburdens the visual system leading to its stress. However, a high individual variability of tolerance for visual stress makes it difficult to predict and generalize the user gain associated with the implementation of alternative visualization technologies. In this study, we investigated the relationship between the binocular function and perceptual judgments in augmented reality. We assessed the task completion time and accuracy of perceptual distance matching depending on the consistency of binocular and focus cues in the stereoscopic environment of augmented reality. The head-mounted display was driven…
B-Scan image analysis for position and shape defect definition in plates
2016
Definition of size, shape and location of defects into a mechanical component is of extreme importance in the manufacturing industry in general and particularly in high-tech applications, and in applications that can become dangerous due to the structural failure of mechanical components. In this paper, a laser-UT system has been used to define position and shape of internal defects in aluminum plates. An infrared pulsed laser is used to generate ultrasonic waves in a point of the plate and a CW laser interferometer is used as receiver to acquire the out-of-plane displacements due to the ultrasonic waves in another point of the plate. The method consists of acquiring a B-Scan map on which s…
Integral imaging with Fourier-plane recording
2017
Integral Imaging is well known for its capability of recording both the spatial and the angular information of threedimensional (3D) scenes. Based on such an idea, the plenoptic concept has been developed in the past two decades, and therefore a new camera has been designed with the capacity of capturing the spatial-angular information with a single sensor and after a single shot. However, the classical plenoptic design presents two drawbacks, one is the oblique recording made by external microlenses. Other is loss of information due to diffraction effects. In this contribution report a change in the paradigm and propose the combination of telecentric architecture and Fourier-plane recordin…
Data-driven Fault Diagnosis of Induction Motors Using a Stacked Autoencoder Network
2019
Current signatures from an induction motor are normally used to detect anomalies in the condition of the motor based on signal processing techniques. However, false alarms might occur if using signal processing analysis alone since missing frequencies associated with faults in spectral analyses does not guarantee that a motor is fully healthy. To enhance fault diagnosis performance, this paper proposes a machinelearning based method using in-built motor currents to detect common faults in induction motors, namely inter-turn stator winding-, bearing- and broken rotor bar faults. This approach utilizes single-phase current data, being pre-processed using Welch’s method for spectral density es…
Towards Open Domain Chatbots—A GRU Architecture for Data Driven Conversations
2018
Understanding of textual content, such as topic and intent recognition, is a critical part of chatbots, allowing the chatbot to provide relevant responses. Although successful in several narrow domains, the potential diversity of content in broader and more open domains renders traditional pattern recognition techniques inaccurate. In this paper, we propose a novel deep learning architecture for content recognition that consists of multiple levels of gated recurrent units (GRUs). The architecture is designed to capture complex sentence structure at multiple levels of abstraction, seeking content recognition for very wide domains, through a distributed scalable representation of content. To …