Search results for: deep and shallow strategies

Authors: Yifan Fan, Xudong Luo, Pingping Lin

Abstract:

Nowadays, dialogue systems increasingly become the way for humans to access many computer systems. So, humans can interact with computers in natural language. A dialogue system consists of three parts: understanding what humans say in natural language, managing dialogue, and generating responses in natural language. In this paper, we survey deep learning based methods for dialogue management, response generation and dialogue evaluation. Specifically, these methods are based on neural network, long short-term memory network, deep reinforcement learning, pre-training and generative adversarial network. We compare these methods and point out the further research directions.

Keywords: dialogue management, response generation, deep learning, evaluation

Procedia PDF Downloads 144

Authors: Atef Ahmad Bleibel

Abstract:

Most codes of practice, like ACI 318-14, require the use of strut-and-tie modeling to analyze and design reinforced concrete deep beams. Though, investigations that conducted on deep beams do not include ring deep beams of influential parameters. This work presents an analytical parametric study using strut-and-tie modeling stated by ACI 318-14 to predict load capacity of 20 reinforced concrete ring deep beam specimens with different parameters. The parameters that were under consideration in the current work are ring diameter (Dc), number of supports (NS), width of ring beam (bw), concrete compressive strength (f'c) and width of bearing plate (Bp). It is found that the load capacity decreases by about 14-36% when ring diameter increases by about 25-75%. It is also found that load capacity increases by about 62-189% when number of supports increases by about 33-100%, while the load capacity increases by about 25-75% when the beam ring width increases by about 25-75%. Finally, it is found that load capacity increases by about 24-76% when compressive strength increases by about 24-76%, while the load capacity increases by about 5-16% when Bp increases by about 25-75%.

Keywords: load parameters, reinforced concrete, ring deep beam, strut and tie

Procedia PDF Downloads 85

Authors: Nivine Abbas, Sergio Lagomarsino, Serena Cattari

Abstract:

The resistance domain of a generally loaded rigid shallow foundation is normally represented as an interaction diagram limited by a failure surface in the three dimensional (3D) load space (N, V, M), where N is the vertical centric load component, V is the horizontal load component and M is the bending moment component. Usually, this resistance domain is constructed neglecting the foundation sliding mechanism that take place at the level of soil-foundation interface once the applied horizontal load exceeds the interface frictional resistance of the foundation. This issue is translated in the literature by the fact that the failure limit in the (2D) load space (N, V) is constructed as a parabola having an initial slope, at the center of the coordinate system, that depends, in some works, only of the soil friction angle, and in other works, has an empirical value. However, considering a given geometry of the foundation lying on a given soil type, the initial slope of the failure limit must change, for instance, when varying the roughness of the foundation surface at its interface with the soil. The present study discusses the effect of the soil-foundation interface condition on the construction of the resistance domain, and proposes a correction to be applied to the failure limit in order to overcome this effect.

Keywords: soil-foundation interface, sliding mechanism, soil shearing, resistance domain, rigid shallow foundation

Procedia PDF Downloads 433

Authors: Mohamed Elshobaki, Alessandro Valiani, Valerio Caleffi

Abstract:

In this paper, we solve 1-D shallow water equation for sub-critical and super-critical water flow at junction. The water flow at junction has been studied for the last 50 years from the physical-hydraulic point of views and for numerical computations need more attention. For numerical simulation, we need to establish an inner boundary condition at the junction to avoid an oscillation which rise from the waves interactions at the junction. Indeed, we introduce a new boundary condition at the junction based on the mass conservation, total head, and the admissible wave relations between the flow parameters in the three branches to predict the water depths and discharges at the junction. These boundary conditions are valid for sub-critical flow and super-critical flow.

Keywords: numerical simulation, junction flow, sub-critical flow, super-critical flow

Procedia PDF Downloads 481

Authors: Simin Sadeghi-Saeb

Abstract:

Metacognitive strategies consistently play important roles in reading comprehension. The metacognitive strategies involve the active monitoring and consequent regulation and orchestration of the cognitive processes in relation to the cognitive objects or data on which they bear. In this paper, the effect of instruction in using metacognitive strategies on reading academic materials, type of metacognitive strategies were mostly used by college university students before and after the instruction and the level they use those strategies before and after the instruction were studied. For these aims, 50 female college students were chosen. Then, they were divided randomly into two groups, experimental and control groups. At first session, students in both groups took the standard TOFEL exam. After the pre-test had been administered, the instruction began. After treatment, a post-test was taken. It is useful to state that after pre-test and post-test the same questionnaire was handed to the students of experimental group. The results of this research show that the instruction of metacognitive strategies has positive effect on the students' scores in reading comprehension tests. Furthermore, it showed that before and after the instruction, the students' usage of metacognitive strategies changed. Also, it demonstrated that the instruction affected the students' level of metacognitive strategies' usage.

Keywords: EFL students, English reading comprehension, instruction, metacognitive strategies

Procedia PDF Downloads 276

Authors: Collins Molua

Abstract:

This paper investigated the effect of Teaching Strategies on Academic Achievement in Secondary Physics Education as a quality assurance process for the teaching and learning of the subject. Teaching strategies investigated were the interactive, independent and dependent strategies. Three null hypotheses were tested at p< 0.05 using one instrument, physics achievement test(PAT).The data were analyzed using analysis of covariance (ANCOVA).Results showed that teaching strategies have significant effect on students achievement; the joint effect of the teaching strategies was also significant on students achievement in Physics. The interactive teaching strategies was recommended for teaching the subject and the students should be exposed to practical, computer literacy to stimulate interest and curiosity to enhance quality.

Keywords: quality, assurance, secondary education, strategies, physics

Procedia PDF Downloads 298

Authors: M. P. Rajeeshkumar, K. V. Aneesh Kumar, J. L. Otero-Ferrer, A. Lombarte, M. Hashim, N. Saravanane, V. N.Sanjeevan, V. M. Tuset

Abstract:

The anglerfishes are widely distributed from shallow to deep-water habitats and are highly diverse in morphology, behaviour, and niche occupancy patterns. To understand this interspecific variability and degree of niche overlap, we performed a functional analysis of five species inhabiting Indian waters where diversity of deep-sea anglerfishes is very high. The sensory capacities (otolith shape and eye size) were also studied to improve the understanding of coexistence of species. The analyses of fish body and otolith shape clustered species in two morphotypes related to phylogenetic lineages: i) Malthopsis lutea, Lophiodes lugubri and Halieutea coccinea were characterized by a dorso-ventrally flattened body with high swimming ability and relative small otoliths, and ii) Chaunax spp. were distinguished by their higher body depth, lower swimming efficiency, and relative big otoliths. The sensory organs did not show a pattern linked to depth distribution of species. However, the larger eye size in M. lutea suggested a nocturnal feeding activity, whereas Chaunax spp. had a large mouth and deeper body in response to different ecological niches. Therefore, the present study supports the hypothesis of spatial and temporal segregation of anglerfishes in the Indian waters, which can be explained from a functional approach and understanding from sensory capabilities.

Keywords: functional traits, otoliths, niche overlap, fishes, Indian waters

Procedia PDF Downloads 113

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 257

Authors: Yin Yuanling

Abstract:

A Deep Feedback Recurrent Neural Network (DFRNN) and Bidirectional Long Short-Term Memory (BiLSTM) are designed to address the problem of low accuracy of traditional relationship extraction models. This method combines a deep feedback-based recurrent neural network (DFRNN) with a bi-directional long short-term memory (BiLSTM) approach. The method combines DFRNN, which extracts local features of text based on deep feedback recurrent mechanism, BiLSTM, which better extracts global features of text, and Self-Attention, which extracts semantic information. Experiments show that the method achieves an F1 value of 76.69% on the CEC dataset, which is 0.0652 better than the BiLSTM+Self-ATT model, thus optimizing the performance of the deep learning method in the event relationship extraction task.

Keywords: event relations, deep learning, DFRNN models, bi-directional long and short-term memory networks

Procedia PDF Downloads 112

Authors: Delowar Hossain, Genci Capi

Abstract:

This paper concerns with the problem of deep learning parameters tuning using a genetic algorithm (GA) in order to improve the performance of deep learning (DL) method. We present a GA based DL method for robot object recognition and grasping. GA is used to optimize the DL parameters in learning procedure in term of the fitness function that is good enough. After finishing the evolution process, we receive the optimal number of DL parameters. To evaluate the performance of our method, we consider the object recognition and robot grasping tasks. Experimental results show that our method is efficient for robot object recognition and grasping.

Keywords: deep learning, genetic algorithm, object recognition, robot grasping

Procedia PDF Downloads 329

Authors: Xulu Yao, Moi Hoon Yap, Yanlong Zhang

Abstract:

As a branch of artificial neural network, deep learning is widely used in the field of image recognition, but the lack of its dataset leads to imperfect model learning. By analysing the data scale requirements of deep learning and aiming at the application in GUI generation, it is found that the collection of GUI dataset is a time-consuming and labor-consuming project, which is difficult to meet the needs of current deep learning network. To solve this problem, this paper proposes a semi-supervised deep learning model that relies on the original small-scale datasets to produce a large number of reliable data sets. By combining the cyclic neural network with the generated countermeasure network, the cyclic neural network can learn the sequence relationship and characteristics of data, make the generated countermeasure network generate reasonable data, and then expand the Rico dataset. Relying on the network structure, the characteristics of collected data can be well analysed, and a large number of reasonable data can be generated according to these characteristics. After data processing, a reliable dataset for model training can be formed, which alleviates the problem of dataset shortage in deep learning.

Keywords: GUI, deep learning, GAN, data augmentation

Procedia PDF Downloads 163

Authors: Chidiebere C. Agoha, Chukwuebuka N. Onwubuariri, Collins U.amasike, Tochukwu I. Mgbeojedo, Joy O. Njoku, Lawson J. Osaki, Ifeyinwa J. Ofoh, Francis B. Akiang, Dominic N. Anuforo

Abstract:

In order to interpret the airborne magnetic data and evaluate the approximate location, depth, and geometry of the magnetic sources within Obudu area using the standard Euler deconvolution method, very high-resolution aeromagnetic data over the area was acquired, processed digitally and analyzed using Oasis Montaj 8.5 software. Data analysis and enhancement techniques, including reduction to the equator, horizontal derivative, first and second vertical derivatives, upward continuation and regional-residual separation, were carried out for the purpose of detailed data Interpretation. Standard Euler deconvolution for structural indices of 0, 1, 2, and 3 was also carried out and respective maps were obtained using the Euler deconvolution algorithm. Results show that the total magnetic intensity ranges from -122.9nT to 147.0nT, regional intensity varies between -106.9nT to 137.0nT, while residual intensity ranges between -51.5nT to 44.9nT clearly indicating the masking effect of deep-seated structures over surface and shallow subsurface magnetic materials. Results also indicated that the positive residual anomalies have an NE-SW orientation, which coincides with the trend of major geologic structures in the area. Euler deconvolution for all the considered structural indices has depth to magnetic sources ranging from the surface to more than 2000m. Interpretation of the various structural indices revealed the locations and depths of the source bodies and the existence of geologic models, including sills, dykes, pipes, and spherical structures. This area is characterized by intrusive and very shallow basement materials and represents an excellent prospect for solid mineral exploration and development.

Keywords: Euler deconvolution, horizontal derivative, Obudu, structural indices

Procedia PDF Downloads 52

Authors: Azeddine El-Hassouny, Chandrashekhar Meshram, Geraldin Nanfack

Abstract:

In recent years, learning from data with noisy labels (Label Noise) has been a major concern in supervised learning. This problem has become even more worrying in Deep Learning, where the generalization capabilities have been questioned lately. Indeed, deep learning requires a large amount of data that is generally collected by search engines, which frequently return data with unreliable labels. In this paper, we investigate the Label Noise in Deep Learning using variational inference. Our contributions are : (1) exploiting Label Noise concept where the true labels are learnt using reparameterization variational inference, while observed labels are learnt discriminatively. (2) the noise transition matrix is learnt during the training without any particular process, neither heuristic nor preliminary phases. The theoretical results shows how true label distribution can be learned by variational inference in any discriminate neural network, and the effectiveness of our approach is proved in several target datasets, such as MNIST and CIFAR32.

Keywords: label noise, deep learning, discrete latent variable, variational inference, MNIST, CIFAR32

Procedia PDF Downloads 100

Authors: Jian-Jun Shu

Abstract:

It is common knowledge that many physical problems (such as non-linear shallow-water waves and wave motion in plasmas) can be described by the Korteweg-de Vries (KdV) equation, which possesses certain special solutions, known as solitary waves or solitons. As a marriage of the KdV equation and the classical Burgers (KdVB) equation, the Korteweg-de Vries-Burgers (KdVB) equation is a mathematical model of waves on shallow water surfaces in the presence of viscous dissipation. Asymptotic analysis is a method of describing limiting behavior and is a key tool for exploring the differential equations which arise in the mathematical modeling of real-world phenomena. By using variable transformations, the asymptotic expansion of the KdVB equation is presented in this paper. The asymptotic expansion may provide a good gauge on the validation of the corresponding numerical scheme.

Keywords: asymptotic expansion, differential equation, Korteweg-de Vries-Burgers (KdVB) equation, soliton

Procedia PDF Downloads 227

Authors: Tarek S. Duzan, Abdulaziz F. Ettir

Abstract:

Wave velocities, Core and Log petrophysical data were collected from recently drilled four new wells scattered through-out the Dahra/Jofra (PL-5) Reservoir. The collected data were analyzed for the relationships of Wave Velocities with rock property such as Porosity, permeability and Bulk Density. Lots of Literature review reveals a number of differing results and conclusions regarding wave velocities (Compressional Waves (Vp) and Shear Waves (Vs)) versus rock petrophysical property relationships, especially in carbonate reservoirs. In this paper, we focused on the relationships between wave velocities (Vp , Vs) and the ratio Vp/Vs with rock properties for shallow marine libyan carbonate reservoir (Real Case). Upon data analysis, a relationship between petrophysical properties and wave velocities (Vp, Vs) and the ratio Vp/Vs has been found. Porosity and bulk density properties have shown exponential relationship with wave velocities, while permeability has shown a power relationship in the interested zone. It is also clear that wave velocities (Vp , Vs) seems to be a good indicator for the lithology change with true vertical depth. Therefore, it is highly recommended to use the output relationships to predict porosity, bulk density and permeability of the similar reservoir type utilizing the most recent seismic data.

Keywords: conventional core analysis (porosity, permeability bulk density) data, VS wave and P-wave velocities, shallow carbonate reservoir in D/J field

Procedia PDF Downloads 310

Authors: Sidrah Ahmed

Abstract:

The river and lakes flows are modeled mathematically by shallow water equations that are depth-averaged Reynolds Averaged Navier-Stokes equations under Boussinesq approximation. The temperature stratification dynamics influence the water quality and mixing characteristics. It is mainly due to the atmospheric conditions including air temperature, wind velocity, and radiative forcing. The experimental observations are commonly taken along vertical scales and are not sufficient to estimate small turbulence effects of temperature variations induced characteristics of shallow flows. Wind shear stress over the water surface influence flow patterns, heat fluxes and thermodynamics of water bodies as well. Hence it is crucial to couple temperature gradients with shallow water model to estimate the atmospheric effects on flow patterns. The Ripa system has been introduced to study ocean currents as a variant of shallow water equations with addition of temperature variations within the flow. Ripa model is a hyperbolic system of partial differential equations because all the eigenvalues of the system’s Jacobian matrix are real and distinct. The time steps of a numerical scheme are estimated with the eigenvalues of the system. The solution to Riemann problem of the Ripa model is composed of shocks, contact and rarefaction waves. Solving Ripa model with Riemann initial data with the central schemes is difficult due to the eigen structure of the system.This works presents the comparison of four different finite difference schemes for the numerical solution of Riemann problem for Ripa model. These schemes include Lax-Friedrichs, Lax-Wendroff, MacCormack scheme and a higher order finite difference scheme with WENO method. The numerical flux functions in both dimensions are approximated according to these methods. The temporal accuracy is achieved by employing TVD Runge Kutta method. The numerical tests are presented to examine the accuracy and robustness of the applied methods. It is revealed that Lax-Freidrichs scheme produces results with oscillations while Lax-Wendroff and higher order difference scheme produce quite better results.

Keywords: finite difference schemes, Riemann problem, shallow water equations, temperature gradients

Procedia PDF Downloads 184

Authors: Muhammad Ali Sarwar, Muhammad Farooq, Nayab Hassan, Hammad Hassan

Abstract:

Pakistan is highly recognized for its agriculture and is well known for producing substantial amounts of wheat, cotton, and sugarcane. However, some factors contribute to a decline in crop quality and a reduction in overall output. One of the main factors contributing to this decline is the presence of weed and its late detection. This process of detection is manual and demands a detailed inspection to be done by the farmer itself. But by the time detection of weed, the farmer will be able to save its cost and can increase the overall production. The focus of this research is to identify and classify the four main types of weeds (Small-Flowered Cranesbill, Chick Weed, Prickly Acacia, and Black-Grass) that are prevalent in our region’s major crops. In this work, we implemented three different deep learning techniques: YOLO-v5, Inception-v3, and Deep CNN on the same Dataset, and have concluded that deep convolutions neural network performed better with an accuracy of 97.45% for such classification. In relative to the state of the art, our proposed approach yields 2% better results. We devised the architecture in an efficient way such that it can be used in real-time.

Keywords: deep convolution networks, Yolo, machine learning, agriculture

Procedia PDF Downloads 84

Authors: Ashkan Shafee, Ahmad Fahimifar

Abstract:

There is a growing demand for construction of high-rise buildings and infrastructures in large cities, which sometimes require deep excavations in the vicinity of pile foundations. In this study, a two-dimensional finite element analysis is used to gain insight into the response of pile groups adjacent to deep excavations in sand. The numerical code was verified by available experimental works, and a parametric study was performed on different working load combinations, excavation depth and supporting system. The results show that the simple two-dimensional plane strain model can accurately simulate the excavation induced changes on adjacent pile groups. It was found that further excavation than pile toe level and also inclined loading on adjacent pile group can severely affect the serviceability of the foundation.

Keywords: deep excavation, inclined loading, lateral deformation, pile group

Procedia PDF Downloads 243

Authors: Tesfaw Belayneh Abebe

Abstract:

Integrating low-altitude earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN) with the assistance of reconfigurable intelligent surfaces (RIS), we investigate the problem of how to enhance throughput through integrated LEO satellites and UAVs with the assistance of RIS. We propose a method to jointly optimize the associations with the LEO satellite, the 3D trajectory of the UAV, and the phase shifts of the RIS to maximize communication throughput for RIS-assisted integrated LEO satellite and UAV-enabled wireless communications, which is challenging due to the time-varying changes in the position of the LEO satellite, the high mobility of UAVs, an enormous number of possible control actions, and also the large number of RIS elements. Utilizing a multi-agent double deep Q-network (MADDQN), our approach dynamically adjusts LEO satellite association, UAV positioning, and RIS phase shifts. Simulation results demonstrate that our method significantly outperforms baseline strategies in maximizing throughput. Lastly, thanks to the integrated network and the RIS, the proposed scheme achieves up to 65.66x higher peak throughput and 25.09x higher worst-case throughput.

Keywords: integrating low-altitude earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs) within a non-terrestrial network (NTN), reconfigurable intelligent surfaces (RIS), multi-agent double deep Q-network (MADDQN)

Procedia PDF Downloads 19

Authors: Nouha Khediri, Mohammed Ben Ammar, Monji Kherallah

Abstract:

Recently, facial emotion recognition (FER) has become increasingly essential to understand the state of the human mind. Accurately classifying emotion from the face is a challenging task. In this paper, we present a facial emotion recognition approach named CV-FER, benefiting from deep learning, especially CNN and VGG16. First, the data is pre-processed with data cleaning and data rotation. Then, we augment the data and proceed to our FER model, which contains five convolutions layers and five pooling layers. Finally, a softmax classifier is used in the output layer to recognize emotions. Based on the above contents, this paper reviews the works of facial emotion recognition based on deep learning. Experiments show that our model outperforms the other methods using the same FER2013 database and yields a recognition rate of 92%. We also put forward some suggestions for future work.

Keywords: CNN, deep-learning, facial emotion recognition, machine learning

Procedia PDF Downloads 69

Authors: Gail Schofield, Antoine M. Dujon, Nicole Esteban, Rebecca M. Lester, Graeme C. Hays

Abstract:

Variation in diel movement patterns during migration provides information on the strategies used by animals to maximize energy efficiency and ensure the successful completion of migration. For instance, many flying and land-based terrestrial species stop to rest and refuel at regular intervals along the migratory route, or at transitory ‘stopover’ sites, depending on resource availability. However, in cases where stopping is not possible (such as over–or through deep–open oceans, or over deserts and mountains), non-stop travel is required, with animals needing to develop strategies to rest while actively traveling. Recent advances in biologging technologies have identified mid-flight micro sleeps by swifts in Africa during the 10-month non-breeding period, and the use of lateralized sleep behavior in orca and bottlenose dolphins during migration. Here, highly accurate locations obtained by Argos-linked Fastloc-GPS transmitters of adult green (n=8 turtles, 9487 locations) and loggerhead (n=46 turtles, 47,588 locations) sea turtles migrating around thousand kilometers (over several weeks) from breeding to foraging grounds across the Indian and Mediterranean oceans were used to identify potential resting strategies. Stopovers were only documented for seven turtles, lasting up to 6 days; thus, this strategy was not commonly used, possibly due to the lack of potential ‘shallow’ ( < 100 m seabed depth) sites along routes. However, observations of the day versus night speed of travel indicated that turtles might use other mechanisms to rest. For instance, turtles traveled an average 31% slower at night compared to day during oceanic crossings. Slower travel speeds at night might be explained by turtles swimming in a less direct line at night and/or deeper dives reducing their forward motion, as indicated through studies using Argos-linked transmitters and accelerometers. Furthermore, within the first 24 h of entering waters shallower than 100 m towards the end of migration (the depth at which sea turtles can swim and rest on the seabed), some individuals travelled 72% slower at night, repeating this behavior intermittently (each time for a one-night duration at 3–6-day intervals) until reaching the foraging grounds. If the turtles were, in fact, resting on the seabed at this point, they could be inactive for up to 8-hours, facilitating protracted periods of rest after several weeks of constant swimming. Turtles might not rest every night once within these shallower depths, due to the time constraints of reaching foraging grounds and restoring depleted energetic reserves (as sea turtles are capital breeders, they tend not to feed for several months during migration to and from the breeding grounds and while breeding). In conclusion, access to data-rich, highly accurate Argos-linked Fastloc-GPS provided information about differences in the day versus night activity at different stages of migration, allowing us, for the first time, to compare the strategies used by a marine vertebrate with terrestrial land-based and flying species. However, the question of what resting strategies are used by individuals that remain in oceanic waters to forage, with combinations of highly accurate Argos-linked Fastloc-GPS transmitters and accelerometry or time-depth recorders being required for sufficient numbers of individuals.

Keywords: argos-linked fastloc GPS, data loggers, migration, resting strategy, telemetry

Procedia PDF Downloads 132

Authors: Saba Ebrahimi, Saeed Ahmadian, Hedie Ashrafi

Abstract:

World-wide spread of coronavirus grows the concern about planning for the excess demand of hospital services in response to COVID-19 pandemic. The surge in the hospital services demand beyond the current capacity leads to shortage of ICU beds and ventilators in some parts of US. In this study, we forecast the required number of hospital beds and possible shortage of beds in US during COVID-19 pandemic to be used in the planning and hospitalization of new cases. In this paper, we used a data on COVID-19 deaths and patients’ hospitalization besides the data on hospital capacities and utilization in US from publicly available sources and national government websites. we used a novel ensemble modelling of deep learning networks, based on stacking different linear and non-linear layers to predict the shortage in hospital beds. The results showed that our proposed approach can predict the excess hospital beds demand very well and this can be helpful in developing strategies and plans to mitigate this gap.

Keywords: COVID-19, deep learning, ensembled models, hospital capacity planning

Procedia PDF Downloads 135

Authors: Pawan S. Nagda, Purnank S. Bhatt, Mit K. Shah

Abstract:

Earing defect in drawing process is highly undesirable not only because it adds on an additional trimming operation but also because the uneven material flow demands extra care. The objective of this work is to study the earing problem in the Deep Drawing of circular cup and to optimize the blank shape to reduce the earing. A finite element model is developed for 3-D numerical simulation of cup forming process in ABAQUS. Extra-deep-drawing (EDD) steel sheet has been used for simulation. Properties and tool design parameters were used as input for simulation. Earing was observed in the simulated cup and it was measured at various angles with respect to rolling direction. To reduce the earing defect initial blank shape was modified with the help of anisotropy coefficient. Modified blanks showed notable reduction in earing.

Keywords: anisotropy, deep drawing, earing, finite element simulation

Procedia PDF Downloads 359

Authors: Shiyin He, Zheng Huang

Abstract:

In this paper, deep learning methods are applied in bio-medical field to detect and count different types of cells in an automatic way instead of manual work in medical practice, specifically in bone marrow examination. The process is mainly composed of two steps, detection and recognition. Mask-Region-Convolutional Neural Networks (Mask-RCNN) was used for detection and image segmentation to extract cells and then Convolutional Neural Networks (CNN), as well as Deep Residual Network (ResNet) was used to classify. Result of cell detection network shows high efficiency to meet application requirements. For the cell recognition network, two networks are compared and the final system is fully applicable.

Keywords: cell detection, cell recognition, deep learning, Mask-RCNN, ResNet

Procedia PDF Downloads 161

Authors: Farshid Hajati, Federico Girosi, Shima Ghassempour

Abstract:

We present a Deep Belief Network (DBN) method for clustering health trajectories. Deep Belief Network (DBN) is a deep architecture that consists of a stack of Restricted Boltzmann Machines (RBM). In a deep architecture, each layer learns more complex features than the past layers. The proposed method depends on DBN in clustering without using back propagation learning algorithm. The proposed DBN has a better a performance compared to the deep neural network due the initialization of the connecting weights. We use Contrastive Divergence (CD) method for training the RBMs which increases the performance of the network. The performance of the proposed method is evaluated extensively on the Health and Retirement Study (HRS) database. The University of Michigan Health and Retirement Study (HRS) is a nationally representative longitudinal study that has surveyed more than 27,000 elderly and near-elderly Americans since its inception in 1992. Participants are interviewed every two years and they collect data on physical and mental health, insurance coverage, financial status, family support systems, labor market status, and retirement planning. The dataset is publicly available and we use the RAND HRS version L, which is easy to use and cleaned up version of the data. The size of sample data set is 268 and the length of the trajectories is equal to 10. The trajectories do not stop when the patient dies and represent 10 different interviews of live patients. Compared to the state-of-the-art benchmarks, the experimental results show the effectiveness and superiority of the proposed method in clustering health trajectories.

Keywords: health trajectory, clustering, deep learning, DBN

Procedia PDF Downloads 347

Authors: Zixi You

Abstract:

With the demand of multilingual speakers increasing in the job market, multi-language learning programs have become more and more popular among undergraduate students. A study on multi-language learning strategies is therefore highly demanded on both practical and theoretical levels. Based on previous classification of learning strategies in SLA, and an investigation of BA Modern Language program students (with post-A level L2 and ab initio L3 learning experience from year one), this study explores and compares different types of learning strategies used by multi-language speakers and learners, transferable learning strategies between L2 and L3, and factors affecting the transfer. The results indicate that all the 23 types of learning strategies of L2 are employed when learning L3 from ab initio level, yet with different tendencies. Learning strategy transfer from L2 to L3 (i.e., the learners attribute the applying of these L3 learning strategies to be a direct result of their L2 learning experience) are observed in all 23 types of learning strategies. Comparatively, six types of “cognitive strategies” have higher transfer tendency than others. With regard to the failure of the transfer of some particular L2 strategies and the development of independent L3 strategies of individual learners, factors such as language proficiency, language typology and learning environment have played important roles among others. The presentation of this study will provide audiences with detailed data, insightful analysis and discussion on both theoretical and practical aspects of multi-language learning that will benefit both students and educators.

Keywords: learning strategy, multi-language acquisition, second language acquisition, strategy transfer

Procedia PDF Downloads 554

Authors: Okoro Ikechukwu Ralph, Fuat Kara

Abstract:

The discoveries of hydrocarbon reserves has clearly drifted offshore, and in deeper waters - areas where the industry still has limited knowledge; and that were hitherto, regarded as being out of reach. This shift presents significant and increased challenges in technology requirements needed to guarantee safety of personnel, environment and equipment; ensure high reliability of installed equipment; and provide high level of confidence in security of investment and company reputation. Nowhere are these challenges more apparent than on subsea well integrity and production performance. The past two decades has witnessed enormous rise in deep and ultra-deep water offshore field developments for the recovery of hydrocarbons. Subsea installed equipment at the seabed has been the technology of choice for these developments. This paper discusses the role of Subsea Control module (SCM) as a vital factor for deep-water well integrity and production performance. A case study for Deep-water well integrity and production performance is analysed.

Keywords: offshore reliability, production performance, subsea control module, well integrity

Procedia PDF Downloads 486

Authors: Qassun S. Mohammed Shafiqu, Murtadha A. Abdulrasool

Abstract:

The design of shallow foundations to withstand different dynamic loads has given considerable attention in recent years. Dynamic loads may be due to the earthquakes, pile driving, blasting, water waves, and machine vibrations. But, predicting the behavior of shallow foundations during earthquakes remains a difficult task for geotechnical engineers. A database for dynamic and static parameters for different soils in seismic active zones in Iraq is prepared which has been collected from geophysical and geotechnical investigation works. Then, analysis of a typical 3-D soil-raft foundation system under earthquake loading is carried out using the database. And a parametric study has been carried out taking into consideration the influence of some parameters on the dynamic behavior of the raft foundation, such as raft stiffness, damping ratio as well as the influence of the earthquake acceleration-time records. The results of the parametric study show that the settlement caused by the earthquake can be decreased by about 72% with increasing the thickness from 0.5 m to 1.5 m. But, it has been noticed that reduction in the maximum bending moment by about 82% was predicted by decreasing the raft thickness from 1.5 m to 0.5 m in all sites model. Also, it has been observed that the maximum lateral displacement, the maximum vertical settlement and the maximum bending moment for damping ratio 0% is about 14%, 20%, and 18% higher than that for damping ratio 7.5%, respectively for all sites model.

Keywords: shallow foundation, seismic behavior, raft thickness, damping ratio

Procedia PDF Downloads 131

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

The increasing use of deep learning applications in production is becoming a competitive advantage. Predictive quality enables the assurance of product quality by using data-driven forecasts via machine learning models as a basis for decisions on test results. The use of real Bosch production data along the value chain of hydraulic valves is a promising approach to classifying the leakage of directional valves.

Keywords: artificial neural networks, classification, hydraulics, predictive quality, deep learning

Procedia PDF Downloads 210

Authors: Rakkrit Duangsoithong, Jermphiphut Jaruenpunyasak, Alba Garcia

Abstract:

The use of foot recognition can be applied in many medical fields such as the gait pattern analysis and the knee exercises of patients in rehabilitation. Generally, a camera-based foot recognition system is intended to capture a patient image in a controlled room and background to recognize the foot in the limited views. However, this system can be inconvenient to monitor the knee exercises at home. In order to overcome these problems, this paper proposes to use the deep learning method using Convolutional Neural Networks (CNNs) for foot recognition. The results are compared with the traditional classification method using LBP and HOG features with kNN and SVM classifiers. According to the results, deep learning method provides better accuracy but with higher complexity to recognize the foot images from online databases than the traditional classification method.

Keywords: foot recognition, deep learning, knee rehabilitation, convolutional neural network

Procedia PDF Downloads 135