scholarly journals Polyp and Surgical Instrument Segmentation with Double Encoder-Decoder Networks

2021 ◽  
Vol 1 (1) ◽  
pp. 5-7
Author(s):  
Adrian Galdran
Keyword(s):  
Neural Network ◽  
Optimization Procedure ◽  
Experimental Results ◽  
Surgical Instruments ◽  
Surgical Instrument ◽  
Post Processing ◽  
Endoscopic Images ◽  
Good Agreement

This paper describes a solution for the MedAI competition, in which participants were required to segment both polyps and surgical instruments from endoscopic images. Our approach relies on a double encoder-decoder neural network which we have previously applied for polyp segmentation, but with a series of enhancements: a more powerful encoder architecture, an improved optimization procedure, and the post-processing of segmentations, based on tempered model ensembling. Experimental results show that our method produces segmentations that show a good agreement with manual delineations provided by medical experts.

An Optimization Procedure in a Sirocco Fan Using Experimental Data

1997 ◽  
Author(s):  
H. S. Min ◽  
H. S. Rew ◽  
C. O. Ahn
Keyword(s):  
Neural Network ◽  
Taguchi Method ◽  
Flow Rate ◽  
Noise Level ◽  
Optimization Procedure ◽  
Design Variables ◽  
The Neural Network ◽  
Sirocco Fan ◽  
Important Design ◽  
Good Agreement

Abstract The flow rate and the specific noise level of 18 sirocco fans were measured and these data were analyzed by the Taguchi method and the neural network. The optimal design value obtained by the neural network generally showed good agreement with that by the Taguchi method. The effects of eight important design variables on the flow rate and the specific noise level were discussed.

Computing and Analyzing the Sensitivity of Radial-Basis Function Neural Network

2013 ◽  
Vol 321-324 ◽  
pp. 1957-1961
Author(s):  
Jie Li ◽  
Jun Li ◽  
Ying Liu
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Uniform Distribution ◽  
Basis Function ◽  
Experimental Results ◽  
Radial Basis ◽  
The Relationship ◽  
Theoretical Results ◽  
Input Error ◽  
Good Agreement

This paper proposes an algorithm to compute the sensitivity of the Radial-Basis Function Neural Network (RBFNN) due to the errors of the inputs and others parameters of the net works. For simplicity and practicality, all inputs and weights are assumed to be independent and identically distributed (i.i.d) with uniform distribution. A number of simulations are conducted and the good agreement between the experimental results and the theoretical results verifies the reliability and feasibility of the proposed algorithm. The relationship between the sensitivity of RBFNN and input error and the perturbation of others parameters is given.

Inducing Frictional Force to Enhance the Transient Response in Beams

2019 ◽  
Vol 22 (2) ◽  
pp. 88-93
Author(s):  
Hamed Khanger Mina ◽  
Waleed K. Al-Ashtrai
Keyword(s):  
Numerical Analysis ◽  
Transient Response ◽  
Frictional Force ◽  
Damping Ratio ◽  
Experimental Results ◽  
Damping Capacity ◽  
Tightening Force ◽  
Contact Areas ◽  
Good Agreement ◽  
Ansys Workbench

This paper studies the effect of contact areas on the transient response of mechanical structures. Precisely, it investigates replacing the ordinary beam of a structure by two beams of half the thickness, which are joined by bolts. The response of these beams is controlled by adjusting the tightening of the connecting bolts and hence changing the magnitude of the induced frictional force between the two beams which affect the beams damping capacity. A cantilever of two beams joined together by bolts has been investigated numerically and experimentally. The numerical analysis was performed using ANSYS-Workbench version 17.2. A good agreement between the numerical and experimental results has been obtained. In general, results showed that the two beams vibrate independently when the bolts were loosed and the structure stiffness is about 20 N/m and the damping ratio is about 0.008. With increasing the bolts tightening, the stiffness and the damping ratio of the structure were also increased till they reach their maximum values when the tightening force equals to 8330 N, where the structure now has stiffness equals to 88 N/m and the damping ratio is about 0.062. Beyond this force value, increasing the bolts tightening has no effect on stiffness of the structure while the damping ratio is decreased until it returned to 0.008 when the bolts tightening becomes immense and the beams behave as one beam of double thickness.

PHOTOINDUCED NONLINEAR OCTUPOLAR POLARIZATION: TRANSIENT AND PERMANENT REGIMES

1996 ◽  
Vol 05 (04) ◽  
pp. 653-670 ◽  
Author(s):  
CÉLINE FIORINI ◽  
JEAN-MICHEL NUNZI ◽  
FABRICE CHARRA ◽  
IFOR D.W. SAMUEL ◽  
JOSEPH ZYSS
Keyword(s):  
Theoretical Analysis ◽  
Second Harmonic ◽  
Experimental Results ◽  
Polar Field ◽  
Rotational Spectrum ◽  
Dual Frequency ◽  
One Dimensional ◽  
Ethyl Violet ◽  
Disperse Red 1 ◽  
Good Agreement

An original poling method using purely optical means and based on a dual-frequency interference process is presented. We show that the coherent superposition of two beams at fundamental and second-harmonic frequencies results in a polar field with an irreducible rotational spectrum containing both a vector and an octupolar component. This enables the method to be applied even to molecules without a permanent dipole such as octupolar molecules. After a theoretical analysis of the process, we describe different experiments aiming at light-induced noncentrosymmetry performed respectively on one-dimensional Disperse Red 1 and octupolar Ethyl Violet molecules. Macroscopic octupolar patterning of the induced order is demonstrated in both transient and permanent regimes. Experimental results show good agreement with theory.

scholarly journals Robust and fast post-processing of single-shot spin qubit detection events with a neural network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tom Struck ◽  
Javed Lindner ◽  
Arne Hollmann ◽  
Floyd Schauer ◽  
Andreas Schmidbauer ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Bayesian Inference ◽  
Rabi Oscillation ◽  
Detection Methods ◽  
Measured Signal ◽  
Single Shot ◽  
Post Processing ◽  
Readout Signal ◽  
Spin Qubit

AbstractEstablishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

scholarly journals Comparison of Experimental and Numerical Transient Drop Deformation during Transition through Orifices in High-Pressure Homogenizers

2021 ◽  
Vol 5 (3) ◽  
pp. 32
Author(s):  
Benedikt Mutsch ◽  
Peter Walzel ◽  
Christian J. Kähler
Keyword(s):  
High Pressure ◽  
Visual Analysis ◽  
Imaging Technique ◽  
Extensional Flow ◽  
Droplet Breakup ◽  
Experimental Results ◽  
Drop Deformation ◽  
Droplet Deformation ◽  
Shadow Imaging ◽  
Good Agreement

The droplet deformation in dispersing units of high-pressure homogenizers (HPH) is examined experimentally and numerically. Due to the small size of common homogenizer nozzles, the visual analysis of the transient droplet generation is usually not possible. Therefore, a scaled setup was used. The droplet deformation was determined quantitatively by using a shadow imaging technique. It is shown that the influence of transient stresses on the droplets caused by laminar extensional flow upstream the orifice is highly relevant for the droplet breakup behind the nozzle. Classical approaches based on an equilibrium assumption on the other side are not adequate to explain the observed droplet distributions. Based on the experimental results, a relationship from the literature with numerical simulations adopting different models are used to determine the transient droplet deformation during transition through orifices. It is shown that numerical and experimental results are in fairly good agreement at limited settings. It can be concluded that a scaled apparatus is well suited to estimate the transient droplet formation up to the outlet of the orifice.

scholarly journals Enhanced Convolutional-Neural-Network Architecture for Crop Classification

2021 ◽  
Vol 11 (9) ◽  
pp. 4292
Author(s):  
Mónica Y. Moreno-Revelo ◽  
Lorena Guachi-Guachi ◽  
Juan Bernardo Gómez-Mendoza ◽  
Javier Revelo-Fuelagán ◽  
Diego H. Peluffo-Ordóñez
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Classification Model ◽  
Classification Error ◽  
Small Scale ◽  
Post Processing ◽  
Average Accuracy ◽  
Processing Step ◽  
Crop Classification

Automatic crop identification and monitoring is a key element in enhancing food production processes as well as diminishing the related environmental impact. Although several efficient deep learning techniques have emerged in the field of multispectral imagery analysis, the crop classification problem still needs more accurate solutions. This work introduces a competitive methodology for crop classification from multispectral satellite imagery mainly using an enhanced 2D convolutional neural network (2D-CNN) designed at a smaller-scale architecture, as well as a novel post-processing step. The proposed methodology contains four steps: image stacking, patch extraction, classification model design (based on a 2D-CNN architecture), and post-processing. First, the images are stacked to increase the number of features. Second, the input images are split into patches and fed into the 2D-CNN model. Then, the 2D-CNN model is constructed within a small-scale framework, and properly trained to recognize 10 different types of crops. Finally, a post-processing step is performed in order to reduce the classification error caused by lower-spatial-resolution images. Experiments were carried over the so-named Campo Verde database, which consists of a set of satellite images captured by Landsat and Sentinel satellites from the municipality of Campo Verde, Brazil. In contrast to the maximum accuracy values reached by remarkable works reported in the literature (amounting to an overall accuracy of about 81%, a f1 score of 75.89%, and average accuracy of 73.35%), the proposed methodology achieves a competitive overall accuracy of 81.20%, a f1 score of 75.89%, and an average accuracy of 88.72% when classifying 10 different crops, while ensuring an adequate trade-off between the number of multiply-accumulate operations (MACs) and accuracy. Furthermore, given its ability to effectively classify patches from two image sequences, this methodology may result appealing for other real-world applications, such as the classification of urban materials.

scholarly journals Artificial Neural Network Simulation of Energetic Performance for Sorption Thermal Energy Storage Reactors

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3294
Author(s):  
Carla Delmarre ◽  
Marie-Anne Resmond ◽  
Frédéric Kuznik ◽  
Christian Obrecht ◽  
Bao Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Energy Storage ◽  
Thermal Energy ◽  
Temperature Difference ◽  
Thermal Energy Storage ◽  
Heat Storage ◽  
Experimental Results ◽  
Physical Models ◽  
Artificial Neural

Sorption thermal heat storage is a promising solution to improve the development of renewable energies and to promote a rational use of energy both for industry and households. These systems store thermal energy through physico-chemical sorption/desorption reactions that are also termed hydration/dehydration. Their introduction to the market requires to assess their energy performances, usually analysed by numerical simulation of the overall system. To address this, physical models are commonly developed and used. However, simulation based on such models are time-consuming which does not allow their use for yearly simulations. Artificial neural network (ANN)-based models, which are known for their computational efficiency, may overcome this issue. Therefore, the main objective of this study is to investigate the use of an ANN model to simulate a sorption heat storage system, instead of using a physical model. The neural network is trained using experimental results in order to evaluate this approach on actual systems. By using a recurrent neural network (RNN) and the Deep Learning Toolbox in MATLAB, a good accuracy is reached, and the predicted results are close to the experimental results. The root mean squared error for the prediction of the temperature difference during the thermal energy storage process is less than 3K for both hydration and dehydration, the maximal temperature difference being, respectively, about 90K and 40K.

Simulation of Sphere’s Motion Induced by Shock Waves

2012 ◽  
Vol 134 (10) ◽  
Author(s):  
Dan Igra ◽  
Ozer Igra ◽  
Lazhar Houas ◽  
Georges Jourdan
Keyword(s):  
Shock Waves ◽  
Drag Coefficient ◽  
Drag Force ◽  
Stationary Flow ◽  
Experimental Results ◽  
Experimental Findings ◽  
Sphere Drag ◽  
Simulation Scheme ◽  
Good Agreement

Simulations of experimental results appearing in Jourdan et al. (2007, “Drag Coefficient of a Sphere in a Non-Stationary Flow: New Results,”Proc. R. Soc. London, Ser. A, 463, pp. 3323–3345) regarding acceleration of a sphere by the postshock flow were conducted in order to find the contribution of the various parameters affecting the sphere drag force. Based on the good agreement found between present simulations and experimental findings, it is concluded that the proposed simulation scheme could safely be used for evaluating the sphere’s motion in the postshock flow.

scholarly journals Research of Personalized Recommendation Technology Based on Knowledge Graphs

2021 ◽  
Vol 11 (15) ◽  
pp. 7104
Author(s):  
Xu Yang ◽  
Ziyi Huan ◽  
Yisong Zhai ◽  
Ting Lin
Keyword(s):  
Neural Network ◽  
Hot Spot ◽  
Experimental Results ◽  
Graph Representation ◽  
Personalized Recommendation ◽  
Knowledge Graph ◽  
Learning Technology ◽  
Data Set ◽  
Model Based ◽  
Knowledge Graphs

Nowadays, personalized recommendation based on knowledge graphs has become a hot spot for researchers due to its good recommendation effect. In this paper, we researched personalized recommendation based on knowledge graphs. First of all, we study the knowledge graphs’ construction method and complete the construction of the movie knowledge graphs. Furthermore, we use Neo4j graph database to store the movie data and vividly display it. Then, the classical translation model TransE algorithm in knowledge graph representation learning technology is studied in this paper, and we improved the algorithm through a cross-training method by using the information of the neighboring feature structures of the entities in the knowledge graph. Furthermore, the negative sampling process of TransE algorithm is improved. The experimental results show that the improved TransE model can more accurately vectorize entities and relations. Finally, this paper constructs a recommendation model by combining knowledge graphs with ranking learning and neural network. We propose the Bayesian personalized recommendation model based on knowledge graphs (KG-BPR) and the neural network recommendation model based on knowledge graphs(KG-NN). The semantic information of entities and relations in knowledge graphs is embedded into vector space by using improved TransE method, and we compare the results. The item entity vectors containing external knowledge information are integrated into the BPR model and neural network, respectively, which make up for the lack of knowledge information of the item itself. Finally, the experimental analysis is carried out on MovieLens-1M data set. The experimental results show that the two recommendation models proposed in this paper can effectively improve the accuracy, recall, F1 value and MAP value of recommendation.

Sign in / Sign up

Export Citation Format

Share Document