Search results for: deep mixing method

Authors: Zhaoxin Luo, Michael Zhu

Abstract:

In natural languages, there are always complex semantic hierarchies. Obtaining the feature representation based on these complex semantic hierarchies becomes the key to the success of the model. Several RNN models have recently been proposed to use latent indicators to obtain the hierarchical structure of documents. However, the model that only uses a single-layer latent indicator cannot achieve the true hierarchical structure of the language, especially a complex language like Chinese. In this paper, we propose a deep layered model that stacks arbitrarily many RNN layers equipped with latent indicators. After using EM and training it hierarchically, our model solves the computational problem of stacking RNN layers and makes it possible to stack arbitrarily many RNN layers. Our deep hierarchical model not only achieves comparable results to large pre-trained models on the Chinese short text classification problem but also achieves state of art results on the Chinese long text classification problem.

Keywords: nature language processing, recurrent neural network, hierarchical structure, document classification, Chinese

Procedia PDF Downloads 59

Authors: Farzaneh Sarbandi Farahani

Abstract:

Drought and decrease in the level of lakes in recent years due to global warming and excessive use of water resources feeding lakes are of great importance, and this research has provided a structure to investigate this issue. First, the information required for simulating lake drought is provided with strong references and necessary assumptions. Entity-Component-System (ECS) structure has been used for simulation, which can consider assumptions flexibly in simulation. Three major users (i.e., Industry, agriculture, and Domestic users) consume water from groundwater and surface water (i.e., streams, rivers and lakes). Lake Mead has been considered for simulation, and the information necessary to investigate its drought has also been provided. The results are presented in the form of a scenario-based design and optimal strategy selection. For optimal strategy selection, a deep reinforcement algorithm is developed to select the best set of strategies among all possible projects. These results can provide a better view of how to plan to prevent lake drought.

Keywords: drought simulation, Mead lake, entity component system programming, deep reinforcement learning

Procedia PDF Downloads 83

Authors: Anastassis Kozanitis, Diane Leduc, Alain Stockless

Abstract:

This paper presents preliminary results from a two-year funded research program looking to analyze and understand the relationship between high cognitive engagement, higher order cognitive processes employed in situations of complex learning tasks, and the use of active learning pedagogies in engineering undergraduate programs. A mixed method approach was used to gauge student engagement and their cognitive processes when accomplishing complex tasks. Quantitative data collected from the self-report cognitive engagement scale shows that deep learning approach is positively correlated with high levels of complex learning tasks and the level of student engagement, in the context of classroom active learning pedagogies. Qualitative analyses of in depth face-to-face interviews reveal insights into the mechanisms influencing students’ cognitive processes when confronted with open-ended problem resolution. Findings also support evidence that students will adjust their level of cognitive engagement according to the specific didactic environment.

Keywords: cognitive engagement, deep and shallow strategies, engineering programs, higher order cognitive processes

Procedia PDF Downloads 319

Authors: Latha Krishnan, Andrew Cobley

Abstract:

Epoxy resin is most widely used as matrices for composites of aerospace, automotive and electronic applications due to its outstanding mechanical properties. These properties are chiefly predetermined by the chemical structure of the prepolymer and type of hardener but can also be varied by the processing conditions such as prepolymer and hardener mixing, degassing and curing conditions. In this research, the effect of degassing on the curing behaviour and the void occurrence is experimentally evaluated for epoxy /anhydride resin system. The epoxy prepolymer was mixed with an anhydride hardener and accelerator in an appropriate quantity. In order to investigate the effect of degassing on the curing behaviour and void content of the resin, the uncured resin samples were prepared using three different methods: 1) no degassing 2) degassing on prepolymer and 3) degassing on mixed solution of prepolymer and hardener with an accelerator. The uncured resins were tested in differential scanning calorimeter (DSC) to observe the changes in curing behaviour of the above three resin samples by analysing factors such as gel temperature, peak cure temperature and heat of reaction/heat flow in curing. Additionally, the completely cured samples were tested in DSC to identify the changes in the glass transition temperature (Tg) between the three samples. In order to evaluate the effect of degassing on the void content and morphology changes in the cured epoxy resin, the fractured surfaces of cured epoxy resin were examined under the scanning electron microscope (SEM). Also, the changes in the mechanical properties of the cured resin were studied by three-point bending test. It was found that degassing at different stages of resin mixing had significant effects on properties such as glass transition temperature, the void content and void size of the epoxy/anhydride resin system. For example, degassing (vacuum applied on the mixed resin) has shown higher glass transition temperature (Tg) with lower void content.

Keywords: anhydride epoxy, curing behaviour, degassing, void occurrence

Procedia PDF Downloads 339

Authors: A. Belmokhtar, A. Yahiaoui, A. Benyoucef, M. Belbachir

Abstract:

We reported the synthesis and characterization of nanocomposite poly (4,4’ methylenedianiline) via chemical polymerization of monomers 4,4’ methylenedianiline by ammonium persulfate (APS) at room temperature catalyzed by Maghnite-H+. A facile method was demonstrated to grow poly (4,4’ methylenedianiline) nanocomposite, which was carried out by mixing Ammonium Persulfate (APS) aqueous and 4,4’ methylenedianiline solution in the presence of Maghnite-H+ at room temperature The effect of amount of catalyst and time on the polymerization yield of the polymers was studied. Structure was confirmed by elemental analysis, UV vis, RMN-1H, and voltammetry cyclique.

Keywords: charaterization, maghnite-h+, polymerization, poly (4, 4’ methylenedianiline)

Procedia PDF Downloads 284

Authors: Jyh Sheen, Yong-Lin Wang

Abstract:

This research dedicates to find a different measurement procedure of microwave dielectric properties of ceramic materials with high dielectric constants. For the composite of ceramic dispersed in the polymer matrix, the dielectric constants of the composites with different concentrations can be obtained by various mixture equations. The other development of mixture rule is to calculate the permittivity of ceramic from measurements on composite. To do this, the analysis method and theoretical accuracy on six basic mixture laws derived from three basic particle shapes of ceramic fillers have been reported for dielectric constants of ceramic less than 40 at microwave frequency. Similar researches have been done for other well-known mixture rules. They have shown that both the physical curve matching with experimental results and low potential theory error are important to promote the calculation accuracy. Recently, a modified of mixture equation for high dielectric constant ceramics at microwave frequency has also been presented for strontium titanate (SrTiO3) which was selected from five more well known mixing rules and has shown a good accuracy for high dielectric constant measurements. However, it is still not clear the accuracy of this modified equation for other high dielectric constant materials. Therefore, the five more well known mixing rules are selected again to understand their application to other high dielectric constant ceramics. The other high dielectric constant ceramic, TiO2 with dielectric constant 100, was then chosen for this research. Their theoretical error equations are derived. In addition to the theoretical research, experimental measurements are always required. Titanium dioxide is an interesting ceramic for microwave applications. In this research, its powder is adopted as the filler material and polyethylene powder is like the matrix material. The dielectric constants of those ceramic-polyethylene composites with various compositions were measured at 10 GHz. The theoretical curves of the five published mixture equations are shown together with the measured results to understand the curve matching condition of each rule. Finally, based on the experimental observation and theoretical analysis, one of the five rules was selected and modified to a new powder mixture equation. This modified rule has show very good curve matching with the measurement data and low theoretical error. We can then calculate the dielectric constant of pure filler medium (titanium dioxide) by those mixing equations from the measured dielectric constants of composites. The accuracy on the estimating dielectric constant of pure ceramic by various mixture rules will be compared. This modified mixture rule has also shown good measurement accuracy on the dielectric constant of titanium dioxide ceramic. This study can be applied to the microwave dielectric properties measurements of other high dielectric constant ceramic materials in the future.

Keywords: microwave measurement, dielectric constant, mixture rules, composites

Procedia PDF Downloads 361

Authors: Nouri Sabrina, Benzeghiba Mohamed, Ghezal Abderrahmane

Abstract:

Numerical parametric study is conducted to study the effects of ampoule rotation on the flows and the dopant segregation in vertical Bridgman (VB) crystal growth. Calculations were performed in unsteady state. The extended Darcy model, which includes the time derivative and Coriolis terms, has been employed in the momentum equation. It was found that the convection, and dopant segregation can be affected significantly by ampoule rotation, and the effect is similar to that by an axial magnetic field. Ampoule rotation decreases the intensity of convection and stretches the flow cell axially. When the convection is weak, the flow can be suppressed almost completely by moderate ampoule rotation and the dopant segregation becomes diffusion-controlled. For stronger convection, the elongated flow cell by ampoule rotation may bring dopant mixing into the bulk melt reducing axial segregation at the early stage of the growth. However, if the cellular flow cannot be suppressed completely, ampoule rotation may induce larger radial segregation due to poor mixing.

Keywords: numerical simulation, heat and mass transfer, vertical solidification, chemical segregation

Procedia PDF Downloads 343

Authors: Samaneh Yavari, Christiane Pferrer, Elisabeth Engelke, Alexander Starke, Juergen Rehage

Abstract:

Background: Nowadays, bovine limb interventions, especially any claw surgeries, raises selection of the most qualified and appropriate local anesthesia technique applicable for any superficial or deep interventions of the limbs. Currently, two local anesthesia methods of Intravenous Regional Anesthesia (IVRA), as well as Nerve Blocks, have been routine to apply. However, the lack of studies investigating the quality and duration as well as quantity and onset of full (complete) local anesthesia, is noticeable. Therefore, the aim of our study was comparing the onset and quality of both IVRA and our modified NBA at the hind limb of dairy cows. For this abstract, only the onset of full local anesthesia would be consider. Materials and Methods: For that reason, we used six healthy non pregnant non lactating Holestein Frisian cows in a cross-over study design. Those cows divided into two groups to receive IVRA and our modified four-point NBA. For IVRA, 20 ml procaine without epinephrine was injected into the vein digitalis dorsalis communis III and for our modified four-point NBA, 10-15 ml procaine without epinephrine preneurally to the nerves, superficial and deep peroneal as well as lateral and medial branches of metatarsal nerves. For pain stimulation, electrical stimulator Grass S48 was applied. Results: The results of electrical stimuli revealed the faster onset of full local anesthesia (p < 0.05) by application of our modified NBA in comparison to IVRA about 10 minutes. Conclusion and discussion: Despite of available references showing faster onset of foot local anesthesia of IVRA, our study demonstrated that our modified four point NBA not only can be well known as a standard foot local anesthesia method applicable to desensitize the hind limb of dairy cows, but also, selection of this modified validated local anesthesia method can lead to have a faster start of complete desensitization of distal hind limb that is remarkable in any bovine limb interventions under time constraint.

Keywords: IVRA, four point NBA, dairy cow, hind limb, full onset

Procedia PDF Downloads 147

Authors: Katsumi Hirano, Yusuke Kakuta, Koji Yoshida, Shozo Itagaki, Masahiko Kajioka, Toshihiko Okada

Abstract:

A conversion technology of cellulosic biomass and waste plastics to liquid fuel at low pressure and low temperature has been investigated. This study aims at the production of the liquefied fuel (CPLF) of substituting diesel oil by mixing cellulosic biomass and waste plastics in the presence of solvent. Co-liquefaction of cellulosic biomass (Japan cedar) and polypropylene (PP) using wood tar or mineral oil as solvent at 673K with an autoclave was carried out. It was confirmed that the co-liquefaction gave CPLF in a high yield among the cases of wood or of polypropylene Which was ascribed the acceleration of decomposition of plastics by radicals derived from the decomposition of wood. The co-liquefaction was also conducted by a small twin screw extruder. It was found that CPLF was obtained in the co-liquefaction, And the acceleration of decomposition of plastics in the presence of cellulosic biomass. The engine test of CPLF showed that the engine performances, Compression ignition and combustion　characteristics were almost similar to those of diesel fuel at any mixing ratio of CPLF and any load, Therefore, CPLF could be practically used as alternative fuel for diesel engines.

Keywords: Cellulosic Biomass, Co-liquefaction, Solvent, Waste Plastics

Procedia PDF Downloads 365

Authors: Kazem Bashirnezhad, Seyed Ahmad Kebriyaee, saeed hoseyngholizadeh moghadam

Abstract:

The urea–SCR catalyst system has the advantages of high NOx conversion efficiency and a wide range of operating conditions. The key factors for successful implementation of urea–SCR technology is good mixing of urea (ammonia) and gas to reduce ammonia slip. Urea mixer components are required to facilitate evaporation and mixing, because it is difficult to evaporate urea in the liquid state; the injection parameters are the most critical factors affecting mixer performance. In this study, The effect of urea injection on NOx emissions in a six-cylinder, four-stroke internal combustion engine fueled with B80 biodiesel has been experimentally investigated. The results reveal that urea injection leads to a reduction of NOx emissions of B80 biodiesel fuel. Moreover, the influence of injection parameters on NOx reductions has been studied. The findings show that by increasing the injection temperature, more reduction in NOx emissions has been occurred. Also, urea mass flow rate increment leads to more NOx reduction. The same result has been obtained by an increase in spray angle.

Keywords: urea, NOx emissions, diesel engines, biodiesels

Procedia PDF Downloads 488

Authors: Alina Muradyan, Lina Babayan, Arsen Nanyan, Gohar Galstyan, Vigen Khachatryan

Abstract:

We present a photometric method for identifying stars, galaxies and quasars in multi-color surveys, which uses a library of ∼> 65000 color templates for comparison with observed objects. The method aims for extracting the information content of object colors in a statistically correct way, and performs a classification as well as a redshift estimation for galaxies and quasars in a unified approach based on the same probability density functions. For the redshift estimation, we employ an advanced version of the Minimum Error Variance estimator which determines the redshift error from the redshift dependent probability density function itself. The method was originally developed for the Calar Alto Deep Imaging Survey (CADIS), but is now used in a wide variety of survey projects. We checked its performance by spectroscopy of CADIS objects, where the method provides high reliability (6 errors among 151 objects with R < 24), especially for the quasar selection, and redshifts accurate within σz ≈ 0.03 for galaxies and σz ≈ 0.1 for quasars. For an optimization of future survey efforts, a few model surveys are compared, which are designed to use the same total amount of telescope time but different sets of broad-band and medium-band filters. Their performance is investigated by Monte-Carlo simulations as well as by analytic evaluation in terms of classification and redshift estimation. If photon noise were the only error source, broad-band surveys and medium-band surveys should perform equally well, as long as they provide the same spectral coverage. In practice, medium-band surveys show superior performance due to their higher tolerance for calibration errors and cosmic variance. Finally, we discuss the relevance of color calibration and derive important conclusions for the issues of library design and choice of filters. The calibration accuracy poses strong constraints on an accurate classification, which are most critical for surveys with few, broad and deeply exposed filters, but less severe for surveys with many, narrow and less deep filters.

Keywords: VO, ArVO, DFBS, FITS, image processing, data analysis

Procedia PDF Downloads 67

Authors: Kyong-Ku Yun, Dae-Ae Kim, Kyeo-Re Lee, Kyong Namkung, Seung-Yeon Han

Abstract:

Micro silica is collected as a by-product of the silicon and ferrosilicon alloy production in electric arc furnace using highly pure quartz, wood chips, coke and the like. It consists of about 85% of silicon which has spherical particles with an average particle size of 150 μm. The bulk density of micro silica varies from 150 to 700kg/m^3 and the fineness ranges from 150,000 to 300,000cm^2/g. An amorphous structure with a high silicon oxide content of micro silica induces an active reaction with calcium hydroxide (Ca(OH)₂) generated by the cement hydrate of a large surface area (about 20 m^² / g), and they are also known to form calcium, silicate, hydrate conjugate (C-S-H). Micro silica tends to act as a filler because of the fine particles and the spherical shape. These particles do not get covered by water and they fit well in the space between the relatively rough cement grains which does not freely fluidize concrete. On the contrary, water demand increases since micro silica particles have a tendency to absorb water because of the large surface area. The overall effect of micro silica depends on the amount of micro silica added with other parameters in the water-(cement + micro silica) ratio, and the availability of superplasticizer. In this research, it was studied on cellular sprayed concrete. This method involves a direct re-production of ready mixed concrete into a high performance at a job site. It could reduce the cost of construction by an adding a cellular and a micro silica into a ready mixed concrete truck in a field. Also, micro silica which is difficult with mixing due to high fineness in the field can be added and dispersed in concrete by increasing the fluidity of ready mixed concrete through the surface activity of cellular. Increased air content is converged to a certain level of air content by spraying and it also produces high-performance concrete by remixing of powders in the process of spraying. As it does not use a field mixing equipment the cost of construction decrease and it can be constructed after installing special spray machine in a commercial pump car. Therefore, use of special equipment is minimized, providing economic feasibility through the utilization of existing equipment. This study was carried out to evaluate a highly reliable method of confirming dispersion through a high performance cellular sprayed concrete. A mixture of 25mm coarse aggregate and river sand was applied to the concrete. In addition, by applying silica fume and foam, silica fume dispersion is confirmed in accordance with foam mixing, and the mean and standard deviation is obtained. Then variation coefficient is calculated to finally evaluate the dispersion. Comparison and analysis of before and after spraying were conducted on the experiment variables of 21L, 35L foam for each 7%, 14% silica fume respectively. Taking foam and silica fume as variables, the experiment proceed. Casting a specimen for each variable, a five-day sample is taken from each specimen for EDS test. In this study, it was examined by an experiment materials, plan and mix design, test methods, and equipment, for the evaluation of dispersion in accordance with micro silica and foam.

Keywords: micro silica, distribution, ready mixed concrete, foam

Procedia PDF Downloads 211

Authors: Balwinder Singh

Abstract:

The present research is a paper on the characterization of aluminum alloy-6063 hybrid metal matrix composites using three different reinforcement materials (SiC, red mud, and fly ash) through stir casting method. The red mud was used in solid form, and particle size range varies between 103-150 µm. During this investigation, fly ash is received from Guru Nanak Dev Thermal Plant (GNDTP), Bathinda. The study has been done by using Taguchi’s L9 orthogonal array by taking fraction wt.% (SiC 5%, 7.5%, and 10% and Red Mud and Fly Ash 2%, 4%, and 6%) as input parameters with their respective levels. The study of the mechanical properties (tensile strength, impact strength, and microhardness) has been done by using Analysis of Variance (ANOVA) with the help of MINITAB 17 software. It is revealed that silicon carbide is the most significant parameter followed by red mud and fly ash affecting the mechanical properties, respectively. The fractured surface morphology of the composites using Field Emission Scanning Electron Microscope (FESEM) shows that there is a good mixing of reinforcement particles in the matrix. Energy-dispersive X-ray spectroscopy (EDS) was performed to know the presence of the phases of the reinforced material.

Keywords: reinforcement, silicon carbide, fly ash, red mud

Procedia PDF Downloads 153

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 93

Authors: Ankit Kamboj, Shikha Talwar, Nilesh Powar

Abstract:

To successfully deliver our products in the market, the employees need to be in a safe environment, especially in an industrial and manufacturing environment. The consequences of delinquency in wearing safety glasses while working in industrial plants could be high risk to employees, hence the need to develop a real-time automatic detection system which detects the persons (violators) not wearing safety glasses. In this study a convolutional neural network (CNN) algorithm called faster region based CNN (Faster RCNN) with rotated bounding box has been used for detecting safety glasses on persons; the algorithm has an advantage of detecting safety glasses with different orientation angles on the persons. The proposed method of rotational bounding boxes with a convolutional neural network first detects a person from the images, and then the method detects whether the person is wearing safety glasses or not. The video data is captured at the entrance of restricted zones of the industrial environment (manufacturing plant), which is further converted into images at 2 frames per second. In the first step, the CNN with pre-trained weights on COCO dataset is used for person detection where the detections are cropped as images. Then the safety goggles are labelled on the cropped images using the image labelling tool called roLabelImg, which is used to annotate the ground truth values of rotated objects more accurately, and the annotations obtained are further modified to depict four coordinates of the rectangular bounding box. Next, the faster RCNN with rotated bounding box is used to detect safety goggles, which is then compared with traditional bounding box faster RCNN in terms of detection accuracy (average precision), which shows the effectiveness of the proposed method for detection of rotatory objects. The deep learning benchmarking is done on a Dell workstation with a 16GB Nvidia GPU.

Keywords: CNN, deep learning, faster RCNN, roLabelImg rotated bounding box, safety goggle detection

Procedia PDF Downloads 124

Authors: Yeong-Gyeong Choi, Kyoung-Seok Kim

Abstract:

This study, literature review research, intends to deal with the problem of conceptual ambiguity among research on emotional labor, and to look into the evolutionary trends and changing aspects of defining the concept of emotional labor. In addition, in existing studies, deep acting and surface acting are highly related to a positive outcome variable and a negative outcome variable, respectively. It was confirmed that for employees performing emotional labor, deep acting and surface acting are highly related to OCB and CWB, respectively. While positive emotion that employees come to experience during job performance process can easily trigger a positive non-task behavior such as OCB, negative emotion that employees experience through excessive workload or unfair treatment can easily induce a negative behavior like CWB. The two management behaviors of emotional labor, surface acting and deep acting, can have either a positive or negative effect on non-task behavior of employees, depending on which one they would choose. Thus, the purpose of this review paper is to clarify the relationship between emotional labor and non-task behavior more specifically.

Keywords: emotion labor, non-task behavior, OCB, CWB

Procedia PDF Downloads 343

Authors: M. Seguini, D. Nedjar

Abstract:

An accuracy nonlinear analysis of a deep beam resting on elastic perfectly plastic soil is carried out in this study. In fact, a nonlinear finite element modeling for large deflection and moderate rotation of Euler-Bernoulli beam resting on linear and nonlinear random soil is investigated. The geometric nonlinear analysis of the beam is based on the theory of von Kàrmàn, where the Newton-Raphson incremental iteration method is implemented in a Matlab code to solve the nonlinear equation of the soil-beam interaction system. However, two analyses (deterministic and probabilistic) are proposed to verify the accuracy and the efficiency of the proposed model where the theory of the local average based on the Monte Carlo approach is used to analyze the effect of the spatial variability of the soil properties on the nonlinear beam response. The effect of six main parameters are investigated: the external load, the length of a beam, the coefficient of subgrade reaction of the soil, the Young’s modulus of the beam, the coefficient of variation and the correlation length of the soil’s coefficient of subgrade reaction. A comparison between the beam resting on linear and nonlinear soil models is presented for different beam’s length and external load. Numerical results have been obtained for the combination of the geometric nonlinearity of beam and material nonlinearity of random soil. This comparison highlighted the need of including the material nonlinearity and spatial variability of the soil in the geometric nonlinear analysis, when the beam undergoes large deflections.

Keywords: finite element method, geometric nonlinearity, material nonlinearity, soil-structure interaction, spatial variability

Procedia PDF Downloads 411

Authors: Chamindi Dilkushi Senaratne

Abstract:

Borrowing is the morphological, syntactic and (usually) phonological integration of lexical items from one language into the structure of another language. Borrowings show complete linguistic integration and due to the frequency of use become fossilized in the recipient language differentiating them from switches and mixes. Code mixes are different to borrowings. Code mixing takes place when speakers use lexical items in casual conversation to serve a variety of functions. This study presents an analysis of lexical items used in English newspapers in Sri Lanka in 2017 which reveal characteristics of borrowing or code mixes. Both phenomena arise due to language contact. The study will also use data from social media websites that comment on newspaper articles available on the web. The study reiterates that borrowings are distinguishable from code mixes and that they are two different phenomena that occur in language contact situations. The study also shows how existing morphological processes are used to create new vocabulary in language use. The study sheds light into how existing morphological processes are used by the bilingual to be creative, innovative and convey a bilingual identity.

Keywords: borrowing, code mixing, morphological processes

Procedia PDF Downloads 215

Authors: Deepalekshmi Ponnamma, Erturk Alper, Pradeep Sharma, Mariam Al Ali AlMaadeed

Abstract:

Integrating efficient energy harvesting materials into soft, flexible and eco-friendly substrates could yield significant breakthroughs in wearable and flexible electronics. Here we present a hybrid filler combination of titanium dioxide nanotubes and the carbon nanostructures-carbon nanotubes and reduced graphene oxide- synthesized by hydrothermal method and then introduced into a semi crystalline polymer, polyvinylidene fluoride (PVDF). Simple mixing method is adopted for the PVDF nanocomposite fabrication after ensuring a high interaction among the fillers. The films prepared were mainly tested for the piezoelectric responses and for the mechanical stretchability. The results show that the piezoelectric constant has increased while changing the total filler concentration. We propose integration of these materials in fabricating energy conversion devices useful in flexible and wearable electronics.

Keywords: dielectric property, hydrothermal growth, piezoelectricity, polymer nanocomposite

Procedia PDF Downloads 345

Authors: Omer Cahana, Maya Herman, Ofer Levi

Abstract:

Magnetic resonance imaging (MRI) is a long medical scan that stems from a long acquisition time. This length is mainly due to the traditional sampling theorem, which defines a lower boundary for sampling. However, it is still possible to accelerate the scan by using a different approach, such as compress sensing (CS) or parallel imaging (PI). These two complementary methods can be combined to achieve a faster scan with high-fidelity imaging. In order to achieve that, two properties have to exist: i) the signal must be sparse under a known transform domain, ii) the sampling method must be incoherent. In addition, a nonlinear reconstruction algorithm needs to be applied to recover the signal. While the rapid advance in the deep learning (DL) field, which has demonstrated tremendous successes in various computer vision task’s, the field of MRI reconstruction is still in an early stage. In this paper, we present an extension of the state-of-the-art model in MRI reconstruction -VarNet. We utilize VarNet by using dilated convolution in different scales, which extends the receptive field to capture more contextual information. Moreover, we simplified the sensitivity map estimation (SME), for it holds many unnecessary layers for this task. Those improvements have shown significant decreases in computation costs as well as higher accuracy.

Keywords: MRI, deep learning, variational network, computer vision, compress sensing

Procedia PDF Downloads 150

Authors: Charles Lee

Abstract:

The Principal Orthogonal Decomposition (POD) technique has been used as a model reduction tool for many applications in engineering and science. In principle, one begins with an ensemble of data, called snapshots, collected from an experiment or laboratory results. The beauty of the POD technique is that when applied, the entire data set can be represented by the smallest number of orthogonal basis elements. It is the such capability that allows us to reduce the complexity and dimensions of many physical applications. Mathematical formulations and numerical schemes for the POD method will be discussed along with applications in NASA’s Deep Space Large Antenna Arrays, Satellite Image Reconstruction, Cancer Detection with DNA Microarray Data, Maximizing Stock Return, and Medical Imaging.

Keywords: reduced-order methods, principal component analysis, cancer detection, image reconstruction, stock portfolios

Procedia PDF Downloads 77

Authors: Muhammad Naseem Baig, Abdul Qudoos Khan, Jamal Ali

Abstract:

Ground deformations in deep excavations are affected by wall stiffness and pile embedment ratio. This paper presents the findings of a parametric study of 64ft deep excavation in mixed stiff soil conditions supported by a cantilever pile wall. A series of finite element analyses have been carried out in Plaxis 2D by varying pile embedment ratio and wall stiffness. It has been observed that maximum wall deflections decrease by increasing the embedment ratio up to 1.50; however, any further increase in pile length does not improve the performance of wall. Similarly, increasing wall stiffness reduces the wall deformations and affects the deflection patterns of wall. The finite element analysis results are compared with field data of 25 case studies of cantilever walls. Analysis results fall within the range of normalized wall deflections of 25 case studies. It has been concluded that deep excavations can be supported by cantilever walls provided the system stiffness is increased significantly.

Keywords: excavations, support systems, wall stiffness, cantilever walls

Procedia PDF Downloads 205

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network

Procedia PDF Downloads 65

Authors: Radhika Ranjan Roy

Abstract:

Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.

Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve

Procedia PDF Downloads 73

Authors: Ali Hamza

Abstract:

Accurate segmentation of breast ultrasound images is of paramount importance in enhancing the diagnostic capabilities of breast cancer detection. This study presents an approach utilizing the U-Net architecture for segmenting breast ultrasound images aimed at improving the accuracy and reliability of mass identification within the breast tissue. The proposed method encompasses a multi-stage process. Initially, preprocessing techniques are employed to refine image quality and diminish noise interference. Subsequently, the U-Net architecture, a deep learning convolutional neural network (CNN), is employed for pixel-wise segmentation of regions of interest corresponding to potential breast masses. The U-Net's distinctive architecture, characterized by a contracting and expansive pathway, enables accurate boundary delineation and detailed feature extraction. To evaluate the effectiveness of the proposed approach, an extensive dataset of breast ultrasound images is employed, encompassing diverse cases. Quantitative performance metrics such as the Dice coefficient, Jaccard index, sensitivity, specificity, and Hausdorff distance are employed to comprehensively assess the segmentation accuracy. Comparative analyses against traditional segmentation methods showcase the superiority of the U-Net architecture in capturing intricate details and accurately segmenting breast masses. The outcomes of this study emphasize the potential of the U-Net-based segmentation approach in bolstering breast ultrasound image analysis. The method's ability to reliably pinpoint mass boundaries holds promise for aiding radiologists in precise diagnosis and treatment planning. However, further validation and integration within clinical workflows are necessary to ascertain their practical clinical utility and facilitate seamless adoption by healthcare professionals. In conclusion, leveraging the U-Net architecture for breast ultrasound image segmentation showcases a robust framework that can significantly enhance diagnostic accuracy and advance the field of breast cancer detection. This approach represents a pivotal step towards empowering medical professionals with a more potent tool for early and accurate breast cancer diagnosis.

Keywords: mage segmentation, U-Net, deep learning, breast cancer detection, diagnostic accuracy, mass identification, convolutional neural network

Procedia PDF Downloads 79

Authors: Yulia Hastuti, Ratna Dewi, Muhammad Sandi

Abstract:

Many methods of soil stabilization that can be done such as by mixing chemicals. In this research, stabilization by mixing the soil using two types of chemical admixture, those are gypsum with a variation of 5%, 10%, and 15% and Soil binder with a concentration of 20 gr / lot of water, 25 gr / lot of water, and 30 gr / lot of water aimed to determine the effect on the soil plasticity index values and comparing the value of shear strength parameters of the mixture with the original soil conditions using a Triaxial UU test. Based on research done shows that with increasing variations in the mix, then the value of plasticity index decreased, which was originally 42% (very high degree of swelling) becomes worth 11.24% (lower Swelling degree) when a mixture of gypsum 15% and 30 gr / Lt water soil binder. As for the value shear, strength parameters increased in all variations of mixture. Admixture with the highest shear strength parameter's value is at 15% the mixture of gypsum and 20 gr / litre of water of soil binder with the 14 day treatment period, which has enhanced the cohesion value of 559.01%, the friction angle by 1157.14%. And a shear strength value of 568.49%. It can be concluded that the admixture of gypsum and soil binder correctly, can increase the value of shear strength parameters significantly and decrease the value of plasticity index of the soil.

Keywords: expansive soil, gypsum, soil binder, shear strength

Procedia PDF Downloads 465

Authors: A. Manallah, C. Meier

Abstract:

Confocal spectral interferometry (CSI) is an innovative optical method for determining microtopography of surfaces and thickness of transparent layers, based on the combination of two optical principles: confocal imaging, and spectral interferometry. Confocal optical system images at each instant a single point of the sample. The whole surface is reconstructed by plan scanning. The interference signal generated by mixing two white-light beams is analyzed using a spectrometer. In this work, five ‘rugotests’ of known standard roughnesses are investigated. The topography is then measured and illustrated, and the equivalent roughness is determined and compared with the standard values.

Keywords: confocal spectral interferometry, nondestructive testing, optical metrology, surface topography, roughness

Procedia PDF Downloads 269

Authors: Mario Isaza-Ruget, Claudia C. Colmenares-Mejia, Nancy Yomayusa, Camilo A. González, Andres Cely, Jossie Murcia

Abstract:

Quantification of risks associated with complications development from chronic kidney disease (CKD) through accurate survival models can help with patient management. A retrospective cohort that included patients diagnosed with CKD from a primary care program and followed up between 2013 and 2018 was carried out. Time-dependent and static covariates associated with demographic, clinical, and laboratory factors were included. Deep Learning (DL) survival analyzes were developed for three CKD outcomes: CKD stage progression, >25% decrease in Estimated Glomerular Filtration Rate (eGFR), and Renal Replacement Therapy (RRT). Models were evaluated and compared with Random Survival Forest (RSF) based on concordance index (C-index) metric. 2.143 patients were included. Two models were developed for each outcome, Deep Neural Network (DNN) model reported C-index=0.9867 for CKD stage progression; C-index=0.9905 for reduction in eGFR; C-index=0.9867 for RRT. Regarding the RSF model, C-index=0.6650 was reached for CKD stage progression; decreased eGFR C-index=0.6759; RRT C-index=0.8926. DNN models applied in survival analysis context with considerations of longitudinal covariates at the start of follow-up can predict renal stage progression, a significant decrease in eGFR and RRT. The success of these survival models lies in the appropriate definition of survival times and the analysis of covariates, especially those that vary over time.

Keywords: artificial intelligence, chronic kidney disease, deep neural networks, survival analysis

Procedia PDF Downloads 130

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring . SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, deep learning, convolutional neural network, deep neural network, SAR polarimetry

Procedia PDF Downloads 84

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 118