1,720,992 research outputs found
Improving Segmentation of Liver Tumors Using Deep Learning
No full textLiver tumor segmentation from computed tomography images is an essential task for the automated diagnosis and treatment of liver cancer. However, such task is di cult due to the variability of morphologies, di use boundaries, heterogeneous densities, and sizes of the lesions. In this work we develop a new system designed for the segmentation of tumors from images acquired by computed tomography, the proposed system uses a network based on convolutional neural networks (CNN). The results are compared with a segmentation carried out by medical experts
Reconstruction of PET Images Using Cross-Entropy and Field of Experts
No full textThe reconstruction of positron emission tomography data is a difficult task, particularly at low count rates because Poisson noise has a significant influence on the statistical uncertainty of positron emission tomography (PET) measurements. Prior information is frequently used to improve image quality. In this paper, we propose the use of a field of experts to model a priori structure and capture anatomical spatial dependencies of the PET images to address the problems of noise and low count data, which make the reconstruction of the image difficult. We reconstruct PET images by using a modified MXE algorithm, which minimizes a objective function with the cross-entropy as a fidelity term, while the field of expert model is incorporated as a regularizing term. Comparisons with the expectation maximization algorithm and a iterative method with a prior penalizing relative differences showed that the proposed method can lead to accurate estimation of the image, especially with acquisitions at low count rate
Reconstruction of PET Images Using Cross-Entropy and Field of Experts
No full textThe reconstruction of positron emission tomography data is a difficult task, particularly at low count rates because Poisson noise has a significant influence on the statistical uncertainty of positron emission tomography (PET) measurements. Prior information is frequently used to improve image quality. In this paper, we propose the use of a field of experts to model a priori structure and capture anatomical spatial dependencies of the PET images to address the problems of noise and low count data, which make the reconstruction of the image difficult. We reconstruct PET images by using a modified MXE algorithm, which minimizes a objective function with the cross-entropy as a fidelity term, while the field of expert model is incorporated as a regularizing term. Comparisons with the expectation maximization algorithm and a iterative method with a prior penalizing relative differences showed that the proposed method can lead to accurate estimation of the image, especially with acquisitions at low count rate
Prediction of time series using wavelet Gaussian process for wireless sensor networks
No full textThe detection and transmission of a physical variable over time, by a node of a sensor network to its sink node, represents a significant communication overload and consequently one of the main energy consumption processes. In this article we present an algorithm for the prediction of time series, with which it is expected to reduce the energy consumption of a sensor network, by reducing the number of transmissions when reporting to the sink node only when the prediction of the sensed value differs in certain magnitude, to the actual sensed value. For this end, the proposed algorithm combines a wavelet multiresolution transform with robust prediction using Gaussian process. The data is processed in wavelet domain, taking advantage of the transform ability to capture geometric information and decomposition in more simple signals or subbands. Subsequently, the decomposed signal is approximated by Gaussian process one for each subband of the wavelet, in this manner the Gaussian process is given to learn a much simple signal. Once the process is trained, it is ready to make predictions. We compare our method with pure Gaussian process prediction showing that the proposed method reduces the prediction error and is improves large horizons predictions, thus reducing the energy consumption of the sensor network
Inventory Model with Stochastic Demand Using Single-Period Inventory Model and Gaussian Process
No full textProper inventory management is vital to achieving sustainability within a supply chain and
is also related to a company’s cash flow through the funds represented by the inventory. Therefore, it
is necessary to balance excess inventory and insufficient inventory. However, this can be difficult
to achieve in the presence of stochastic demand because decisions must be made in an uncertain
environment and the inventory policy bears risks associated with each decision. This study reports
an extension of the single-period model for the inventory problem under uncertain demand. We
proposed incorporating a Gaussian stochastic process into the model using the associated posterior
distribution of the Gaussian process as a distribution for the demand. This enables the modeling of
data from historical inventory demand using the Gaussian process theory, which adapts well to small
datasets and provides measurements of the risks associated with the predictions made. Thus, unlike
other works that assume that demand follows an autoregressive or Brownian motion model, among
others, our approach enables adaptability to different complex forms of demand trends over time.
We offer several numerical examples that explore aspects of the proposed approach and compare our
results with those achieved using other state-of-the-art methods
Estimation of the lifespan distribution of gold nanoparticles stabilized with lipoic acid by accelerated degradation tests and wiener process
No full textAccelerated degradation tests (ADT) are widely used in the manufacturing industry to obtain information on the reliability of components and materials, by degrading the lifespan of the product by applying an acceleration factor that damage to the material. The main objective is to obtain fast information which is modeled to estimate the characteristics of the material life under normal conditions of use and to save time and expenses. The purpose of this work is to estimate the lifespan distribution of gold nanoparticles stabilized with lipoic acid (GNPs@LA) through accelerated degradation tests applying sodium chloride (NaCl) as an acceleration factor. For this, the synthesis of GNPs@LA was carried out, a constant stress ADT (CSADT) was applied, and the non-linear Wiener process was proposed with random effects, error measures, and different covariability for the adjustment of the degradation signals. The information obtained with the test and analysis allows us to obtain the life distribution in GNPs@LA, the results make it possible to determine the guaranteed time for possible commercialization and successful application based on the stability of the material. In addition, for the evaluation and selection of the model, the Akaike and Bootstrapping criteria were used
Implementation of a Multicriteria Analysis Model to Determine Anthropometric Characteristics of an Optimal Helmet of an Italian Scooter.
No full textAt the beginning of the sixties, the Italian scooters became popular in Italy, an age that was considered unimportant the safety of people. However, safety standards are now stronger, and helmet use is mandatory in most countries. That is why this paper try to analyze in greater detail the characteristics associated with the anthropometric measurements of a representative sample of a broader society for determining the ideal characteristics of a helmet associated with this type of vehicle. For this reason and considering the relevance of our study to a Smart City, we will use a multicriteria analysis and an intelligent data analysis in order to understand much better the ideal and suitable measurements to be able to design a helmet for an Italian scooter
A weighted and distributed algorithm for multi-hop localization
No full textMulti-hop wireless sensor networks are widely used in many location-dependent applications. Most applications assume the knowledge of geographic location of sensor nodes; however, in practical scenarios, the high accuracy on position estimates of sensor nodes is still a great challenge. In this research, we propose a hop-weighted scheme that can be useful in distance-based distributed multi-hop localization. The hop-weighted localization approach generates spatial locations around position estimates of unknown sensors and computes local functions that minimize distance errors among hop-weighted and static neighboring sensors. The iterative process of each unknown sensor to re-estimate its own location allows a significant reduction of initial position estimates. Simulations demonstrate that this weighted localization approach, when compared with other schemes, can be suitable to be used as a refinement stage to improve localization in both isotropic and anisotropic networks. Also, under rough initial position estimates, the proposed algorithm achieves root mean square error values less than the radio range of unknown sensors, in average, with only a few iterations
DETECCIÓN DE SOMNOLENCIA EN CONDUCTORES DE VEHÍCULOS POR MEDIO DE PROCESAMIENTO DE VIDEO
No full textLos accidentes automovilísticos son una de las principales causas de muerte y
lesiones a nivel mundial. Muchos son causados por fatiga y somnolencia de los
conductores. El presente estudio tiene como objetivo detectar somnolencia en
conductores de vehículos. La metodología del trabajo consistió en las siguientes
etapas: en primer lugar, se empleó un algoritmo para la detección del rostro del
sujeto dentro de la cabina de un automóvil durante la simulación de conducción para
identificar regiones que incluyan cada ojo. Posteriormente se construyó un
clasificador para distinguir las regiones de cada ojo como: abierto o cerrado.
Finalmente, se desarrolló un algoritmo para el seguimiento de las regiones de
interés para alimentar con imágenes al clasificador; para la detección se
somnolencia se utiliza un criterio basado en una cantidad de fotogramas
consecutivos presentando una identificación de ojos cerrados. El algoritmo presentó
un 91.4% de exactitud en la detección de somnolencia
- …
