scholarly journals Ensemble of Deep Capsule Neural Networks: An Application to Pneumonia Prediction

Author(s):  
Jyostna Bodapati ◽  
Rohith V N ◽  
Venkatesulu Dondeti

Abstract Pneumonia is the primary cause of death in children under the age of 5 years. Faster and more accurate laboratory testing aids in the prescription of appropriate treatment for children suspected of having pneumonia, lowering mortality. In this work, we implement a deep neural network model to efficiently evaluate pediatric pneumonia from chest radio graph images. Our network uses a combination of convolutional and capsule layers to capture abstract details as well as low level hidden features from the the radio graphic images, allowing the model to generate more generic predictions. Furthermore, we combine several capsule networks by stacking them together and connected them with dense layers. The joint model is trained as a single model using joint loss and the weights of the capsule layers are updated using the dynamic routing algorithm. The proposed model is evaluated using benchmark pneumonia dataset\cite{kermany2018identifying}, and the outcomes of our experimental studies indicate that the capsules employed in the network enhance the learning of disease level features that are essential in diagnosing pneumonia. According to our comparison studies, the proposed model with Convolution base from InceptionV3 attached with Capsule layers at the end surpasses several existing models by achieving an accuracy of 94.84\%. The proposed model is superior in terms of various performance measures such as accuracy and recall, and is well suited to real-time pediatric pneumonia diagnosis, substituting manual chest radiography examination.

2014 ◽  
Vol 6 (1) ◽  
pp. 1032-1035 ◽  
Author(s):  
Ramzi Suleiman

The research on quasi-luminal neutrinos has sparked several experimental studies for testing the "speed of light limit" hypothesis. Until today, the overall evidence favors the "null" hypothesis, stating that there is no significant difference between the observed velocities of light and neutrinos. Despite numerous theoretical models proposed to explain the neutrinos behavior, no attempt has been undertaken to predict the experimentally produced results. This paper presents a simple novel extension of Newton's mechanics to the domain of relativistic velocities. For a typical neutrino-velocity experiment, the proposed model is utilized to derive a general expression for . Comparison of the model's prediction with results of six neutrino-velocity experiments, conducted by five collaborations, reveals that the model predicts all the reported results with striking accuracy. Because in the proposed model, the direction of the neutrino flight matters, the model's impressive success in accounting for all the tested data, indicates a complete collapse of the Lorentz symmetry principle in situation involving quasi-luminal particles, moving in two opposite directions. This conclusion is support by previous findings, showing that an identical Sagnac effect to the one documented for radial motion, occurs also in linear motion.


Author(s):  
Tuan A. Pham ◽  
Melis Sutman

The prediction of shear strength for unsaturated soils remains to be a significant challenge due to their complex multi-phase nature. In this paper, a review of prior experimental studies is firstly carried out to present important pieces of evidence, limitations, and some design considerations. Next, an overview of the existing shear strength equations is summarized with a brief discussion. Then, a micromechanical model with stress equilibrium conditions and multi-phase interaction considerations is presented to provide a new equation for predicting the shear strength of unsaturated soils. The validity of the proposed model is examined for several published shear strength data of different soil types. It is observed that the shear strength predicted by the analytical model is in good agreement with the experimental data, and get high performance compared to the existing models. The evaluation of the outcomes with two criteria, using average relative error and the normalized sum of squared error, proved the effectiveness and validity of the proposed equation. Using the proposed equation, the nonlinear relationship between shear strength, saturation degree, volumetric water content, and matric suction are observed.


2020 ◽  
pp. 93-98
Author(s):  
Viktar V. Tur ◽  
Radoslaw Duda ◽  
Dina Khmaruk ◽  
Viktar Basav

In this paper, a modified strains development model (MSDM) for expansive concrete-filled steel tube (ECFST) was formulated and verified on the experimental data, obtained from testing specimens on the expansion stage. The modified strain development model for restraint strains and self-stresses values estimation in concrete with high expansion energy capacity under any type of the symmetrical and unsymmetrical finite stiffness restraint conditions was proposed. Based on proposed MSDM a new model for expansive concrete-filled steel tubes is developed. The main difference between this model and other previously developed models consists in taking into account in the basic equations an induced force in restrain that is considered as an external load applied to the concrete core of the member. For verification of the proposed model-specific experimental studies were performed. As follows from comparison results restrained expansion strains values calculated following the proposed model shows good compliance with experimental data. The values predicted by the proposed MSDM for concrete-filled steel and obtained experimental data demonstrated good agreement that confirms the validity of the former.


Author(s):  
Marius C. Barbu ◽  
Roman Reh ◽  
Ayfer Dönmez Çavdar

It would seem that with appropriate treatment almost any agricultural residue may be used as a suitable raw material for the wood-based panels like particle- and fiberboard production. The literature on wood-ligno-cellulose plant composite boards highlights steady interest for the design of new structures and technologies towards products for special applications with higher physical-mechanical properties at relatively low prices. Experimental studies have revealed particular aspects related to the structural composition of ligno-cellulose materials, such as the ratio between the different composing elements, their compatibility, and the types and characteristics of the used resins. Various technologies have been developed for designing and processing composite materials by pressing, extrusion, airflow forming, dry, half-dry, and wet processes, including thermal, chemical, thermo-chemical, thermo-chemo-mechanical treatments, etc. Researchers have undertaken to determine the manufacturing parameters and the physical-mechanical properties of the composite boards and to compare them with the standard PB, MDF, HB, SB made from single-raw material (wood). A great emphasis is placed on the processability of the ligno-cellulose composite boards by classical methods, by modified manufacturing processes, on the types of tools and processing equipment, the automation of the manufacturing technologies, the specific labor conditions, etc. The combinations of wood and plant fibers are successful, since there is obvious compatibility between the macro- and microscopic structures, their chemical composition, and the relatively low manufacturing costs and high performances, as compared to synthetic fiber-based composite materials.


2019 ◽  
Vol 9 (18) ◽  
pp. 3908 ◽  
Author(s):  
Jintae Kim ◽  
Shinhyeok Oh ◽  
Oh-Woog Kwon ◽  
Harksoo Kim

To generate proper responses to user queries, multi-turn chatbot models should selectively consider dialogue histories. However, previous chatbot models have simply concatenated or averaged vector representations of all previous utterances without considering contextual importance. To mitigate this problem, we propose a multi-turn chatbot model in which previous utterances participate in response generation using different weights. The proposed model calculates the contextual importance of previous utterances by using an attention mechanism. In addition, we propose a training method that uses two types of Wasserstein generative adversarial networks to improve the quality of responses. In experiments with the DailyDialog dataset, the proposed model outperformed the previous state-of-the-art models based on various performance measures.


Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1620 ◽  
Author(s):  
Ganjar Alfian ◽  
Muhammad Syafrudin ◽  
Norma Latif Fitriyani ◽  
Muhammad Anshari ◽  
Pavel Stasa ◽  
...  

Extracting information from individual risk factors provides an effective way to identify diabetes risk and associated complications, such as retinopathy, at an early stage. Deep learning and machine learning algorithms are being utilized to extract information from individual risk factors to improve early-stage diagnosis. This study proposes a deep neural network (DNN) combined with recursive feature elimination (RFE) to provide early prediction of diabetic retinopathy (DR) based on individual risk factors. The proposed model uses RFE to remove irrelevant features and DNN to classify the diseases. A publicly available dataset was utilized to predict DR during initial stages, for the proposed and several current best-practice models. The proposed model achieved 82.033% prediction accuracy, which was a significantly better performance than the current models. Thus, important risk factors for retinopathy can be successfully extracted using RFE. In addition, to evaluate the proposed prediction model robustness and generalization, we compared it with other machine learning models and datasets (nephropathy and hypertension–diabetes). The proposed prediction model will help improve early-stage retinopathy diagnosis based on individual risk factors.


2014 ◽  
Vol 571-572 ◽  
pp. 717-720
Author(s):  
De Kun Hu ◽  
Yong Hong Liu ◽  
Li Zhang ◽  
Gui Duo Duan

A deep Neural Network model was trained to classify the facial expression in unconstrained images, which comprises nine layers, including input layer, convolutional layer, pooling layer, fully connected layers and output layer. In order to optimize the model, rectified linear units for the nonlinear transformation, weights sharing for reducing the complexity, “mean” and “max” pooling for subsample, “dropout” for sparsity are applied in the forward processing. With large amounts of hard training faces, the model was trained via back propagation method with stochastic gradient descent. The results of shows the proposed model achieves excellent performance.


2005 ◽  
Vol 15 (01n02) ◽  
pp. 153-168 ◽  
Author(s):  
A. KHONSARI ◽  
H. SARBAZI-AZAD ◽  
M. OULD-KHAOUA

Recent studies have revealed that deadlocks are generally infrequent in the network. Thus the hardware resources, e.g. virtual channels, dedicated for deadlock avoidance are not utilised most of the time. This consideration has motivated the development of novel adaptive routing algorithms with deadlock recovery. This paper describes a new analytical model to predict message latency in hypercubes with a true fully adaptive routing algorithm with progressive deadlock recovery. One of the main features of the proposed model is the use of results from queueing systems with impatient customers to capture the effects of the timeout mechanism used in this routing algorithm for deadlock detection. The validity of the model is demonstrated by comparing analytical results with those obtained through simulation experiments.


Author(s):  
S. M. Abdullah Al Shuaeb ◽  
Shamsul Alam ◽  
Md. Mizanur Rahman ◽  
Md. Abdul Matin

Students’ academic achievement plays a significant role in the polytechnic institute. It is an important task for the technical student to achieve good results. It becomes more challenging by virtue of the huge amount of data in the polytechnic student databases. Recently, the lack of monitoring of academic activities and their performance has not been harnessed. This is not a good way to evaluate the academic performance of polytechnic students in Bangladesh at present. The study on existing academic prediction systems is still not enough for the polytechnic institutions. Consequently, we have proposed a novel technique to improve student academic performance. In this study, we have used the deep neural network for predicting students' academic final marks. The main objective of this paper is to improve students' results. This paper also explains how the prediction deep neural network model can be used to recognize the most vital attributes in a student's academic data namely midterm_marks, class_ test, attendance, assignment, and target_ marks. By using the proposed model, we can more effectively improve polytechnic student achievement and success.


Sign in / Sign up

Export Citation Format

Share Document