Search results for: deep layer

Authors: P. V. Leksin, A. A. Kamashev, N. N. Garifyanov, I. A. Garifullin, Ya. V. Fominov, J. Schumann, Y. Krupskaya, V. Kataev, O. G. Schmidt, B. Büchner

Abstract:

We report on experimental evidence for the occurrence of the long range triplet correlations (LRTC) of the superconducting (SC) condensate in the spin-valve heterostructures CoOx/Fe1/Cu/Fe2/Pb. The LRTC generation in this layer sequence is accompanied by a Tc suppression near the orthogonal mutual orientation of the Fe1 and Fe2 layers’ magnetization. This Tc drop reaches its maximum of 60mK at the Fe2 layer thickness dFe2 = 0.6 nm and falls down when dFe2 is increased. The modification of the Fe/Pb interface by using a thin Cu intermediate layer between Fe and Pb layers reduces the SC transition width without preventing the interaction between Pb and Fe2 layers. The dependence of the SSVE magnitude on Fe1 layer thickness dFe1 reveals maximum of the effect when dFe1 and dFe2 are equal and the dFe2 value is minimal. Using the optimal Fe layers thicknesses and the intermediate Cu layer between Pb and Fe2 layer we realized almost full switching from normal to superconducting state due to SSVE.

Keywords: superconductivity, ferromagnetism, heterostructures, proximity effect

Procedia PDF Downloads 416

Authors: A. Apostolopoulou, D. Sygkridou, A. N. Kalarakis, E. Stathatos

Abstract:

Mesoscopic perovskite solar cells (mp-PSCs) with mesoporous bilayer were fabricated under ambient conditions. The bilayer was formed by capping the mesoporous TiO₂ layer with a layer of In₂O₃. CH₃NH₃I_3-xCl_x mixed halide perovskite was prepared through the one-step method and was used as the light absorber. The mp-PSCs with the composite TiO₂/In₂O₃ mesoporous layer exhibited optimized electrical parameters, compared with the PSCs that employed only a TiO₂ mesoporous layer, with a current density of 23.86 mA/cm², open circuit voltage of 0.863 V, fill factor of 0.6 and a power conversion efficiency of 11.2%. These results indicate that the formation of a proper semiconductor capping layer over the basic TiO₂ mesoporous layer can facilitate the electron transfer, suppress the recombination and subsequently lead to higher charge collection efficiency.

Keywords: ambient conditions, high efficiency solar cells, mesoscopic perovskite solar cells, TiO₂ / In₂O₃ bilayer

Procedia PDF Downloads 270

Authors: Arun Kumar Singh, Rupesh M. Das, Shailendra Saini

Abstract:

The present work is an attempt to evaluate the sub-auroral ionospheric behavior under changing space weather conditions especially during high solar activity year 2014. In view of this, the GPS TEC along with Ionosonde data over Indian permanent scientific base 'Maitri', Antarctica (70°46′00″ S, 11°43′56″ E) has been utilized. The results suggested that the nature of ionospheric responses to the geomagnetic disturbances mainly depended upon the status of high latitudinal electro-dynamic processes along with the season of occurrence. Fortunately, in this study, both negative and positive ionospheric impact to the geomagnetic disturbances has been observed in a single year but in different seasons. The study reveals that the combination of equator-ward plasma transportation along with ionospheric compositional changes causes a negative ionospheric impact during summer and equinox seasons. However, the combination of pole-ward contraction of the oval region along with particle precipitation may lead to exhibiting positive ionospheric response during the winter season. Other than this, some Ionosonde based new experimental evidence also provided clear evidence of particle precipitation deep up to the low altitudinal ionospheric heights, i.e., up to E-layer by the sudden and strong appearance of E-layer at 100 km altitudes. The sudden appearance of E-layer along with a decrease in F-layer electron density suggested the dominance of NO⁺ over O⁺ at a considered region under geomagnetic disturbed condition. The strengthening of E-layer is responsible for modification of auroral electrojet and field-aligned current system. The present study provided a good scientific insight on sub-auroral ionospheric to the changing space weather condition.

Keywords: high latitude ionosphere, space weather, geomagnetic storms, sub-storm

Procedia PDF Downloads 169

Authors: Woosuk Lee

Abstract:

We controlled the electron injection rate in inverted quantum dot light-emitting diode (QLED) by inserting PEIE layer between ZnO electron transport layer(ETL) and quantum dots(QDs) layer and successfully demonstrated high efficiency of QLEDs. The inverted QLED has the layer structure of ITO(cathode)/ ZnO NPs/PEIE/QDs/PEIE/P-TPD/MoO3/Al(anode). The PEIE between poly-TPD hole transport layer (HTL) and quantum dot emitting layer protects QD EML during HTL coating process and improves the surface morphology. In addition, the hole injection barrier is reduced by upshifting the valence band maximum (VBM) of QDs. An additional layer of PEIE was introduced between ZnO and QD to balance charge within QD emissive layer in device, which serves as an effective electron blocking layer without changing device operating condition such as turn-on voltage and emissive spectra. As a result, the optimized QLED with 5nm PEIE shows a ~36% improved current efficiency and external quantum efficiency (EQE) compared to the QLED without PEIE.(maximum current efficiency, and EQE are achieved 70cd/A and 17.3%, respectively). In particular, the maximum brightness of the optimized QLED dramatically improved by a factor of 2.3 relative to the QLED without PEIE. The main reasons for these QLED performance improvement are due to the suppressing the leakage current across the device and well confined exciton by inserting PEIE layers.

Keywords: quantum dot light-emitting diodes, interfacial layer, charge-injection balance, suppressing QD charging

Procedia PDF Downloads 183

Authors: Xuewei Li, Jingfeng Yuan, Jianliang Zhou

Abstract:

The 21st century has been called the century of human exploitation of underground space. Due to the characteristics of large quantity, tight schedule, low safety reserve and high uncertainty of deep foundation pit engineering, accidents frequently occur in deep foundation pit engineering, causing huge economic losses and casualties. With the successful application of information technology in the construction industry, building information modeling has become a research hotspot in the field of architectural engineering. Therefore, the application of building information modeling (BIM) and other information communication technologies (ICTs) in construction safety management is of great significance to improve the level of safety management. This research summed up the mechanism of the deep foundation pit engineering accident through the fault tree analysis to find the control factors of deep foundation pit engineering safety management, the deficiency existing in the traditional deep foundation pit construction site safety management. According to the accident cause mechanism and the specific process of deep foundation pit construction, the hazard information of deep foundation pit engineering construction site was identified, and the hazard list was obtained, including early warning information. After that, the system framework was constructed by analyzing the early warning information demand and early warning function demand of the safety management system of deep foundation pit. Finally, the safety management system of deep foundation pit construction site based on BIM through combing the database and Web-BIM technology was developed, so as to realize the three functions of real-time positioning of construction site personnel, automatic warning of entering a dangerous area, real-time monitoring of deep foundation pit structure deformation and automatic warning. This study can initially improve the current situation of safety management in the construction site of deep foundation pit. Additionally, the active control before the occurrence of deep foundation pit accidents and the whole process dynamic control in the construction process can be realized so as to prevent and control the occurrence of safety accidents in the construction of deep foundation pit engineering.

Keywords: Web-BIM, safety management, deep foundation pit, construction

Procedia PDF Downloads 153

Authors: Joseph Uzuazomaro Oju

Abstract:

The ease at which manipulated media can be created, and the increasing difficulty in identifying fake media makes it a great threat. Most of the applications used for the creation of these high-quality fake videos and images are built with deep learning. Hence, the use of deep learning in creating a detection mechanism cannot be overemphasized. Any successful fake media that is being detected before it reached the populace will save people from the self-doubt of either a content is genuine or fake and will ensure the credibility of videos and images. The methodology introduced in this paper approaches the manipulated media detection challenge using a combo of VGG-19 and a deep capsule network. In the case of videos, they are converted into frames, which, in turn, are resized and cropped to the face region. These preprocessed images/videos are fed to the VGG-19 network to extract the latent features. The extracted latent features are inputted into a deep capsule network enhanced with a 3D -convolution dynamic routing agreement. The 3D –convolution dynamic routing agreement algorithm helps to reduce the linkages between capsules networks. Thereby limiting the poor learning shortcoming of multiple capsule network layers. The resultant output from the deep capsule network will indicate a media to be either genuine or fake.

Keywords: deep capsule network, dynamic routing, fake media detection, manipulated media

Procedia PDF Downloads 132

Authors: Monette S. De Castro, Veneranda A. Magpantay, Christine B. Adiova, Mark D. Arboleda

Abstract:

One-hundred-layer chicken farmers were randomly selected and interviewed using structured questionnaires to assess the production system and management practices in layer chicken farms. The respondents belonged to the commercial scale operation. Results showed that the predominant rearing and housing systems were intensive/complete confinement and open-sided, while slatted was the common type of flooring used during the brood-grow period. Dekalb and Lohmann were the common chicken layer strains reared by farmers. The majority of commercial chicken layer farms preferred ready-to-lay (RTL) pullets as their replacement stocks. Selling was the easiest way for farmers to dispose of and utilize poultry manure, while veterinary waste and mortality were disposed of in pits. Biosecurity practices employed by the farmers conformed with the ASEAN Biosecurity Management Manual for Commercial Poultry Farming. Flies and odor were the major problems in most layer farms that are associated with their farm wastes. Therefore, the application of new technologies and husbandry practices through training and actual demonstrations could be implemented to further improve the layer chicken raising in the province.

Keywords: layer chicken farms, marketing, production system, waste management

Procedia PDF Downloads 74

Authors: Radia Kamel

Abstract:

Considerable progress has been made in the development of bulk-heterojunction organic solar cells (OSCs) based on a blend of p-type and n-type organic semiconductors. To optimize the interfacial properties between the active layer and the electrode, a cathode buffer layer (CBL) is introduced. This layer can reduce the leakage current, increasing the open-circuit voltage and the fill factor while improving the OSC stability. In this work, the performance of PM6:Y6 OSC with 1-Chloronaphthalene as an additive is examined. To accomplish this, three CBLs PNDIT-F3N-Br, ZrAcac, and PDINO, are compared using the conventional configuration. The device with PNDIT-F3N-Br as CBL exhibits the highest power conversion efficiency of 16.04%. The results demonstrate that modifying the cathode buffer layer is crucial for achieving high-performance OSCs.

Keywords: bulk heterojunction, cathode buffer layer, efficiency, organic solar cells

Procedia PDF Downloads 167

Authors: Mohamad Kassab, Amal El Fallah Seghrouchni, Frederic Barbaresco, Raed Abu Zitar

Abstract:

Detecting objects such as drones is a challenging task as their relative size and maneuvering capabilities deceive machine learning models and cause them to misclassify drones as birds or other objects. In this work, we investigate applying several deep learning techniques to benchmark real data sets of flying drones. A deep learning paradigm is proposed for the purpose of mitigating the complexity of those systems. The proposed paradigm consists of a hybrid between the AdderNet deep learning paradigm and the Single Shot Detector (SSD) paradigm. The goal was to minimize multiplication operations numbers in the filtering layers within the proposed system and, hence, reduce complexity. Some standard machine learning technique, such as SVM, is also tested and compared to other deep learning systems. The data sets used for training and testing were either complete or filtered in order to remove the images with mall objects. The types of data were RGB or IR data. Comparisons were made between all these types, and conclusions were presented.

Keywords: drones detection, deep learning, birds versus drones, precision of detection, AdderNet

Procedia PDF Downloads 182

Authors: Thomas Adi Purnomo Sidhi

Abstract:

Nowadays, network is an essential need in almost every part of human daily activities. People now can seamlessly connect to others through the Internet. With advanced technology, our personal data now can be more easily accessed. One of many components we are concerned for delivering the best network is a security issue. This paper is proposing a method that provides more options for security. This research aims to improve network security by focusing on the physical layer which is the first layer of the OSI model. The layer consists of the basic networking hardware transmission technologies of a network. With the use of observation method, the research produces a schematic design for enhancing the network security through the gray code converter.

Keywords: network, network security, grey code, physical layer

Procedia PDF Downloads 504

Authors: P. S. Jagadeesh Kumar, Yang Yung, Mingmin Pan, Xianpei Li, Wenli Hu

Abstract:

Glaucoma is impelled by optic nerve mutilation habitually represented as cupping and visual field injury frequently with an arcuate pattern of mid-peripheral loss, subordinate to retinal ganglion cell damage and death. Glaucoma is the second foremost cause of blindness and the chief cause of permanent blindness worldwide. Consequently, all-embracing study into the analysis and empathy of glaucoma is happening to escort deep learning based neural network intrusions to deliberate this substantial optic neuropathy. This paper advances an ophthalmic hashing based supervision of glaucoma and corneal disorders preeminent on deep graphical model. Ophthalmic hashing is a newly proposed method extending the efficacy of visual hash-coding to predict glaucoma corneal disorder matching, which is the faster than the existing methods. Deep graphical model is proficient of learning interior explications of corneal disorders in satisfactory time to solve hard combinatoric incongruities using deep Boltzmann machines.

Keywords: corneal disorders, deep Boltzmann machines, deep graphical model, glaucoma, neural networks, ophthalmic hashing

Procedia PDF Downloads 250

Authors: Ryoma Tokonami, Teruya Goto, Tatsuhiro Takahashi,

Abstract:

For enhancing the mechanical property ofcarbon fiber reinforced plastic (CFRP), the surface modification of carbon fiber (CF) by multi-walled carbon nanotube (MWCNT) has received considerable attention using direct MWCNT growth on CF with a catalysis, MWCNT electrophoresis, and layer-by-layer of MWCNT with reactive polymers, etc. Among above approaches, the layer-by-layer method is the simplest process, however, the amount of MWCNTs on CF is very little, resulting in the small amount of improvement of the mechanical property of the composite. The remaining amount of MWCNT on CF after melt mixing of CF (short fiber) with thermoplastic matrix polymer was not examined clearly in the former studies. The present research aims to propose an effective layer-by-layer chemical grafting of a highly reactive oxazoline polymer, which has not been used before, and MWCNTs onto CF using the highly reactivity of oxazoline and COOH on the surface of CF and MWCNTs.With layer-by-layer method, the first uniform chemically bonded mono molecular layer on carbon fiber was formed by chemical surface reaction of carbon fiber, a reactive oxazoline polymer solution between COOH of carbon fiber and oxazoline. The second chemically bonded uniform layer of MWCNTs on the first layer was prepared through the first layer coated carbon fiber in MWCNT dispersion solution by chemical reaction between oxazoline and COOH of MWCNTs. The quantitative analysis of MWCNTs on carbon fiber was performed, showing 0.44 wt.% of MWCNTs based on carbon fiber, which is much larger amount compared with the former studies in layer-by-layer method. In addition, MWCNTs were also observed uniform coating on carbon fiber by scanning electron micrograph (SEM). Carbon fiber composites were prepared by melting mixing using polystyrene (PS) as a thermoplastic matrix because of easy removal of PS by solvent for additional analysis, resulting the 20% of enhancement of tensile strength and modulus by tensile strength test. It was confirmed bySEM the layer-by-layer structure on carbon fibers were remained after the melt mixing by removing PS with a solvent. As a conclusion, the effectiveness for the enhancement of the mechanical properties of CF(short fiber)/PS composite using the highly reactive oxazoline polymer for the first layer and MWCNT for the second layer, which act as the physical anchor, was demonstrated.

Keywords: interface, layer-by-layer, multi walled carbon nanotubes (MWCNTs), oxazoline

Procedia PDF Downloads 203

Authors: Wentian Shi, Daming Shi, Maysam Orouskhani, Feng Tian

Abstract:

Whereas currently the most prevalent deep learning methods require a large amount of data for training, few-shot learning tries to learn a model from limited data without extensive retraining. In this paper, we present a loss function based on triplet loss for solving few-shot problem using metric based learning. Instead of setting the margin distance in triplet loss as a constant number empirically, we propose an adaptive margin distance strategy to obtain the appropriate margin distance automatically. We implement the strategy in the deep siamese network for deep metric embedding, by utilizing an optimization approach by penalizing the worst case and rewarding the best. Our experiments on image recognition and co-segmentation model demonstrate that using our proposed triplet loss with adaptive margin distance can significantly improve the performance.

Keywords: few-shot learning, triplet network, adaptive margin, deep learning

Procedia PDF Downloads 171

Authors: F. Ainlhout, S. Boutaleb, M. C. Diaz-Barradas, M. Zunzunegui

Abstract:

Argania spinosa is an endemic tree of the southwest of Morocco, occupying 828,000 Ha, distributed mainly between Mediterranean vegetation and the desert. This tree can grow in extremely arid regions in Morocco, where annual rainfall ranges between 100-300 mm where no other tree species can live. It has been designated as a UNESCO Biosphere reserve since 1998. Argania tree is of great importance in human and animal feeding of rural population as well as for oil production, it is considered as a multi-usage tree. Admine forest located in the suburbs of Agadir city, 5 km inland, was selected to conduct this work. The aim of the study was to investigate the temporal variation in root-zone moisture dynamic in response to variation in climatic conditions and vegetation water uptake, using a geophysical technique called Electrical resistivity imaging (ERI). This technique discriminates resistive woody roots, dry and moisture soil. Time-dependent measurements (from April till July) of resistivity sections were performed along the surface transect (94 m Length) at 2 m fixed electrode spacing. Transect included eight Argan trees. The interactions between the tree and soil moisture were estimated by following the tree water status variations accompanying the soil moisture deficit. For that purpose we measured midday leaf water potential and relative water content during each sampling day, and for the eight trees. The first results showed that ERI can be used to accurately quantify the spatiotemporal distribution of root-zone moisture content and woody root. The section obtained shows three different layers: middle conductive one (moistured); a moderately resistive layer corresponding to relatively dry soil (calcareous formation with intercalation of marly strata) on top, this layer is interspersed by very resistant layer corresponding to woody roots. Below the conductive layer, we find the moderately resistive layer. We note that throughout the experiment, there was a continuous decrease in soil moisture at the different layers. With the ERI, we can clearly estimate the depth of the woody roots, which does not exceed 4 meters. In previous work on the same species, analyzing the δ18O in water of xylem and in the range of possible water sources, we argued that rain is the main water source in winter and spring, but not in summer, trees are not exploiting deep water from the aquifer as the popular assessment, instead of this they are using soil water at few meter depth. The results of the present work confirm the idea that the roots of Argania spinosa are not growing very deep.

Keywords: Argania spinosa, electrical resistivity imaging, root system, soil moisture

Procedia PDF Downloads 328

Authors: Allamula Ashok, Peela Lasya, Daljin Jacob, P. Muhammed Razi, Satyesh Kumar Yadav

Abstract:

We report zinc (Zn) as a seed layer material and a need for a specific disposition sequence to grow ultrathin silver (Ag) films on quartz (SiO₂). Ag films of thickness 4, 6, 8 and 10 nm were deposited by DC magnetron sputtering without and with Zn seed layer thickness of 1, 2 and 4 nm. The effect of Zn seed layer thickness and its annealing on the surface morphology, sheet resistance, and stability of ultrathin Ag films is investigated. We show that by increasing Zn seed layer thickness from 1 to 2 nm, there is a 5-order reduction in sheet resistance of 6 nm Ag films. We find that annealing of the seed layer is crucial to achieving stability of ultrathin Ag films. 6 nm Ag film with 2 nm Zn is unstable to 100 oC annealing, while the 6 nm Ag film with annealed 2 nm Zn seed layer is stable. 2 nm Zn seeded 8 nm Ag film maintained a constant sheet resistance of 7 Ω/□ for all 6 months of exposure to ambient conditions. Among the ultrathin film grown, 8nm Ag film with 2nm Zn seed layer had the best figure of merit with sheet resistance of 7 Ω/□, mean absolute surface roughness (Ra) ~1 nm, and optical transparency of 61 %. Such stable exposed ultrathin Ag films can find applications as catalysts, sensors, and transparent and conductive electrodes for solar cells, LEDs and plasmonic devices.

Keywords: ultrathin Ag films, magnetron sputtering, thermal stability, seed layer, exposed silver, zinc.

Procedia PDF Downloads 39

Authors: Apolinar Picado, Ronald Solís, Rafael Gamero

Abstract:

The thin-layer drying characteristics of instant coffee solution were investigated in a laboratory tunnel dryer. Drying experiments were carried out at three temperatures (80, 100 and 120 °C) and an air velocity of 1.2 m/s. Drying experimental data obtained are fitted to six (6) thin-layer drying models using the non-linear least squares regression analysis. The acceptability of the thin-layer drying model has been based on a value of the correlation coefficient that should be close to one, and low values for root mean square error (RMSE) and chi-square (x²). According to this evaluation, the most suitable model for describing drying process of thin-layer instant coffee solution is the Page model. Further, the effective moisture diffusivity and the activation energy were computed employing the drying experimental data. The effective moisture diffusivity values varied from 1.6133 × 10⁻⁹ to 1.6224 × 10⁻⁹ m²/s over the temperature range studied and the activation energy was estimated to be 162.62 J/mol.

Keywords: activation energy, diffusivity, instant coffee, thin-layer models

Procedia PDF Downloads 262

Authors: Bryan D. Llenarizas, Maria Carla F. Manzano

Abstract:

The rapid growth of electricity demand has led to a pursuit of alternative energy sources with high power output and not harmful to the environment. The fuel cell is a device that generates electricity via chemical reactions between the fuel and oxidant. Fuel cells have been known for decades, but the development of high-power output and durability was still one of the drawbacks of this energy source. This study investigates the potential of layer-by-layer composite for fuel cell applications. A two-electrode electrochemical cell was used for the galvanostatic electrochemical deposition method to fabricate a Polypyrrole/rGO|Polypyrrole/ZnO layer-by-layer composite material for fuel cell applications. In the synthesis, the first layer comprised 0.1M pyrrole monomer and 1mg of rGO, while the second layer had 0.1M pyrrole monomer and variations of ZnO concentration ranging from 0.08M up to 0.12M. A constant current density of 8mA/cm² was applied for 1 hour in fabricating each layer. Scanning electron microscopy (SEM) for the fabricated LBL material shows a globular surface with white spots. These white spots are the ZnO particles confirmed by energy-dispersive X-ray spectroscopy, indicating a successful deposition of the second layer onto the first layer. The observed surface morphology was consistent for each variation of ZnO concentrations. AC measurements were conducted to obtain the AC resistance of the fabricated film. Results show a decrease in AC resistance as the concentration of ZnO increases.

Keywords: anode, composite material, electropolymerization, fuel cell, galvanostatic, polypyrrole

Procedia PDF Downloads 81

Authors: Romisaa Ali

Abstract:

The Policy Gradient approach is one of the deep reinforcement learning families that combines deep neural networks (DNN) with reinforcement learning RL to discover the optimum of the control problem through experience gained from the interaction between the robot and its surroundings. In contrast to earlier policy gradient algorithms, which were unable to handle these two types of error because of over-or under-estimation introduced by the deep neural network model, this article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.

Keywords: deep neural networks, deep reinforcement learning, proximal policy optimization, state-of-the-art, trust region policy optimization

Procedia PDF Downloads 169

Authors: Sarita Agarwal, Deepika Delsa Dean

Abstract:

Like the task of transferring photo images to artistic images, image-to-image translation aims to translate the data to the imitated data which belongs to the target domain. Neural Style Transfer and CycleGAN are two well-known deep learning architectures used for photo image-to-art image transfer. However, studies involving these two models concentrate on one-to-one domain translation, not one-to-multi domains translation. Our study tries to investigate deep learning architectures, which can be controlled to yield multiple artistic style translation only by adding a conditional vector. We have expanded CycleGAN and constructed Conditional CycleGAN for 5 kinds of categories translation. Our study found that the architecture inserting conditional vector into the middle layer of the Generator could output multiple artistic images.

Keywords: genetic counseling, FMR1 gene, fragile x-associated primary ovarian insufficiency, premutation

Procedia PDF Downloads 130

Authors: Alipanah Masoud, Sheihkei Iman

Abstract:

One day old chicken quality has great deal of contributions in increasing daily weight gain as well as economical productivity of broilers production. On the other hand, eggs are kept in different times in layer hens flocks and subsequently are transported to incubation units. In order to evaluate effects of two factors layer hen age and storage period of eggs on one day old broilers weight gain during feeding, eggs for layer hen gathered on 32 weeks old (young hen) and 74 weeks old (older ones) were used. Storage period for samples was set as 1 and 9 days. Data were analysed in completely randomized design in four replicates by software SAS. Results indicated that one day old broiler chickens from young had less weight gain, although they exhibited higher weight gain during next weeks. At the same time, there was no difference between chickens from eggs stored for nine days and those from stored for one day.

Keywords: egg, chicken, hatchability, layer

Procedia PDF Downloads 420

Authors: Partha Sarathi Majee, S. Bhattacharyya

Abstract:

Migration of a core-shell soft particle under the influence of an external electric field in an electrolyte solution is studied numerically. The soft particle is coated with a positively charged polyelectrolyte layer (PEL) and the rigid core is having a uniform surface charge density. The Darcy-Brinkman extended Navier-Stokes equations are solved for the motion of the ionized fluid, the non-linear Nernst-Planck equations for the ion transport and the Poisson equation for the electric potential. A pressure correction based iterative algorithm is adopted for numerical computations. The effects of convection on double layer polarization (DLP) and diffusion dominated counter ions penetration are investigated for a wide range of Debye layer thickness, PEL fixed surface charge density, and permeability of the PEL. Our results show that when the Debye layer is in order of the particle size, the DLP effect is significant and produces a reduction in electrophoretic mobility. However, the double layer polarization effect is negligible for a thin Debye layer or low permeable cases. The point of zero mobility and the existence of mobility reversal depending on the electrolyte concentration are also presented.

Keywords: debye length, double layer polarization, electrophoresis, mobility reversal, soft particle

Procedia PDF Downloads 345

Authors: Ayu Minamizawa, Jae-Ho Kim, Susumu Yonezawa

Abstract:

Aqueous peroxotitanium acid solution was prepared by the reaction between H₂O₂ solution and TiO₂ fluorinated using F₂ gas. The coating of TiO₂/SiO₂ multilayer on the surface of polycarbonate (PC) resin was carried out step by step using the TEOS solution and aqueous peroxotitanium acid solution. We confirmed each formation of SiO₂ and TiO₂ layer by scanning electron microscopy and energy-dispersive X-ray spectroscopy, and x-ray photoelectron spectroscopy results. The formation of a TiO₂ thin layer on SiO₂ coated on polycarbonate (PC) was carried out at 120 ℃ and for 15 min ~ 3 h with aqueous peroxotitanium acid solution using a hydrothermal synthesis autoclave reactor. The morphology TiO₂ coating layer largely depended on the reaction time, as shown in the results of SEM-EDS analysis. Increasing the reaction times, the TiO₂ layer expanded uniformly. Moreover, the surface fluorination of the SiO₂ layer can promote the formation of the TiO₂ layer on the surface.

Keywords: aqueous peroxotitanium acid solution, photocatalytic activity, polycarbonate, surface fluorination

Procedia PDF Downloads 118

Authors: Ilya Simanovskii

Abstract:

Nonlinear convective flows developed under the joint action of buoyant and thermo-capillary effects in a two-layer system with periodic boundary conditions on the lateral walls have been investigated. The influence of an interfacial heat release on oscillatory regimes has been studied. The computational regions with different lengths have been considered. It is shown that the development of oscillatory instability can lead to the appearance of different no steady flows.

Keywords: interface, instabilities, two-layer systems, bioinformatics, biomedicine

Procedia PDF Downloads 401

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 114

Authors: P. R. Prabhu, S. M. Kulkarni, S. S. Sharma, K. Jagannath, Achutha Kini U.

Abstract:

In the present study, response surface methodology has been used to optimize turn-assisted deep cold rolling process of AISI 4140 steel. A regression model is developed to predict surface hardness and surface roughness using response surface methodology and central composite design. In the development of predictive model, deep cold rolling force, ball diameter, initial roughness of the workpiece, and number of tool passes are considered as model variables. The rolling force and the ball diameter are the significant factors on the surface hardness and ball diameter and numbers of tool passes are found to be significant for surface roughness. The predicted surface hardness and surface roughness values and the subsequent verification experiments under the optimal operating conditions confirmed the validity of the predicted model. The absolute average error between the experimental and predicted values at the optimal combination of parameter settings for surface hardness and surface roughness is calculated as 0.16% and 1.58% respectively. Using the optimal processing parameters, the hardness is improved from 225 to 306 HV, which resulted in an increase in the near surface hardness by about 36% and the surface roughness is improved from 4.84µm to 0.252 µm, which resulted in decrease in the surface roughness by about 95%. The depth of compression is found to be more than 300µm from the microstructure analysis and this is in correlation with the results obtained from the microhardness measurements. Taylor Hobson Talysurf tester, micro Vickers hardness tester, optical microscopy and X-ray diffractometer are used to characterize the modified surface layer.

Keywords: hardness, response surface methodology, microstructure, central composite design, deep cold rolling, surface roughness

Procedia PDF Downloads 420

Authors: Yanjun Chen, Chuanping Hu, Jie Shao, Lin Mei, Chongyang Zhang

Abstract:

Traditional image classification is based on encoding scheme (e.g. Fisher Vector, Vector of Locally Aggregated Descriptor) with low-level image features (e.g. SIFT, HoG). Compared to these low-level local features, deep convolutional features obtained at the mid-level layer of convolutional neural networks (CNN) have richer information but lack of geometric invariance. For scene classification, there are scattered objects with different size, category, layout, number and so on. It is crucial to find the distinctive objects in scene as well as their co-occurrence relationship. In this paper, we propose a method to take advantage of both deep convolutional features and the traditional encoding scheme while taking object-centric and scene-centric information into consideration. First, to exploit the object-centric and scene-centric information, two CNNs that trained on ImageNet and Places dataset separately are used as the pre-trained models to extract deep convolutional features at multiple scales. This produces dense local activations. By analyzing the performance of different CNNs at multiple scales, it is found that each CNN works better in different scale ranges. A scale-wise CNN adaption is reasonable since objects in scene are at its own specific scale. Second, a fisher kernel is applied to aggregate a global representation at each scale and then to merge into a single vector by using a post-processing method called scale-wise normalization. The essence of Fisher Vector lies on the accumulation of the first and second order differences. Hence, the scale-wise normalization followed by average pooling would balance the influence of each scale since different amount of features are extracted. Third, the Fisher vector representation based on the deep convolutional features is followed by a linear Supported Vector Machine, which is a simple yet efficient way to classify the scene categories. Experimental results show that the scale-specific feature extraction and normalization with CNNs trained on object-centric and scene-centric datasets can boost the results from 74.03% up to 79.43% on MIT Indoor67 when only two scales are used (compared to results at single scale). The result is comparable to state-of-art performance which proves that the representation can be applied to other visual recognition tasks.

Keywords: deep convolutional features, Fisher Vector, multiple scales, scale-specific normalization

Procedia PDF Downloads 331

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 43

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 134

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: deep neural models, natural language inference, recognizing textual entailment (RTE), sentence-to-sentence relation

Procedia PDF Downloads 348

Authors: Lokes Parvatha Kumaran S., Sakthi Jay Mahenthar C., Sathyaprakash P., Jayakumar V., Shobanadevi A.

Abstract:

With the evolution of technology, the need to solve complex computational problems like machine learning and deep learning has shot up. But even the most powerful classical supercomputers find it difficult to execute these tasks. With the recent development of quantum computing, researchers and tech-giants strive for new quantum circuits for machine learning tasks, as present works on Quantum Machine Learning (QML) ensure less memory consumption and reduced model parameters. But it is strenuous to simulate classical deep learning models on existing quantum computing platforms due to the inflexibility of deep quantum circuits. As a consequence, it is essential to design viable quantum algorithms for QML for noisy intermediate-scale quantum (NISQ) devices. The proposed work aims to explore Variational Quantum Circuits (VQC) for Deep Reinforcement Learning by remodeling the experience replay and target network into a representation of VQC. In addition, to reduce the number of model parameters, quantum information encoding schemes are used to achieve better results than the classical neural networks. VQCs are employed to approximate the deep Q-value function for decision-making and policy-selection reinforcement learning with experience replay and the target network.

Keywords: quantum computing, quantum machine learning, variational quantum circuit, deep reinforcement learning, quantum information encoding scheme

Procedia PDF Downloads 134