Search results for: deep deterministic policy gradient (DDPG)

Authors: Khalak Bin Khair, Saqib Jahir, Mohammed Ibrahim, Fahad Bin, Debajyoti Karmaker

Abstract:

Object detection is a computer technology that deals with searching through digital images and videos for occurrences of semantic elements of a particular class. It is associated with image processing and computer vision. On top of object detection, we detect camouflage objects within an image using Deep Learning techniques. Deep learning may be a subset of machine learning that's essentially a three-layer neural network Over 6500 images that possess camouflage properties are gathered from various internet sources and divided into 4 categories to compare the result. Those images are labeled and then trained and tested using vgg16 architecture on the jupyter notebook using the TensorFlow platform. The architecture is further customized using Transfer Learning. Methods for transferring information from one or more of these source tasks to increase learning in a related target task are created through transfer learning. The purpose of this transfer of learning methodologies is to aid in the evolution of machine learning to the point where it is as efficient as human learning.

Keywords: deep learning, transfer learning, TensorFlow, camouflage, object detection, architecture, accuracy, model, VGG16

Procedia PDF Downloads 149

Authors: Ajay Kumar Choubey, Geeta Agnihotri, C. Sasikumar, Rashmi Dwivedi

Abstract:

Deep-drawing operations are performed widely in industrial applications. It is very important for efficiency to achieve parts with no or minimum defects. Deep drawn parts are used in high performance, high strength and high reliability applications where tension, stress, load and human safety are critical considerations. Wrinkling is a kind of defect caused by stresses in the flange part of the blank during metal forming operations. To avoid wrinkling appropriate blank-holder pressure/force or drawbead can be applied. Now-a-day computer simulation plays a vital role in the field of manufacturing process. So computer simulation of manufacturing has much advantage over previous conventional process i.e. mass production, good quality of product, fast working etc. In this study, a two dimensional elasto-plastic Finite Element (F.E.) model for Mild Steel material blank has been developed to study the behavior of the flange wrinkling and deep drawing parameters under different Blank-Holder Pressure (B.H.P.). For this, commercially available Finite Element software ANSYS 14 has been used in this study. Simulation results are critically studied and salient conclusions have been drawn.

Keywords: ANSYS, deep drawing, BHP, finite element simulation, wrinkling

Procedia PDF Downloads 449

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 92

Authors: Hesheng Wang, Haoyu Wang, Chungang Zhuang

Abstract:

Estimating the 6D pose of objects is a core step for robot bin-picking tasks. The problem is that various objects are usually randomly stacked with heavy occlusion in real applications. In this work, we propose a method to regress 6D poses by predicting three points for each object in the 3D point cloud through deep learning. To solve the ambiguity of symmetric pose, we propose a labeling method to help the network converge better. Based on the predicted pose, an iterative method is employed for pose optimization. In real-world experiments, our method outperforms the classical approach in both precision and recall.

Keywords: pose estimation, deep learning, point cloud, bin-picking, 3D computer vision

Procedia PDF Downloads 161

Authors: Philipp Galkin

Abstract:

Government policy is a critical factor in the understanding of energy markets. Regardless, it is rarely approached systematically from a research perspective. Gaining a precise understanding of what policies exist, their intended outcomes, geographical extent, duration, evolution, etc. would enable the research community to answer a variety of questions that, for now, are either oversimplified or ignored. Policy, on its surface, also seems a rather unstructured and qualitative undertaking. There may be quantitative components, but incorporating the concept of policy analysis into quantitative analysis remains a challenge. The KAPSARC Energy Policy Database (KEPD) is intended to address these two energy policy research limitations. Our approach is to represent policies within a quantitative library of the specific policy measures contained within a set of legal documents. Each of these measures is recorded into the database as a single entry characterized by a set of qualitative and quantitative attributes. Initially, we have focused on the major laws at the national level that regulate coal in China. However, KAPSARC is engaged in various efforts to apply this methodology to other energy policy domains. To ensure scalability and sustainability of our project, we are exploring semantic processing using automated computer algorithms. Automated coding can provide a more convenient input data for human coders and serve as a quality control option. Our initial findings suggest that the methodology utilized in KEPD could be applied to any set of energy policies. It also provides a convenient tool to facilitate understanding in the energy policy realm enabling the researcher to quickly identify, summarize, and digest policy documents and specific policy measures. The KEPD captures a wide range of information about each individual policy contained within a single policy document. This enables a variety of analyses, such as structural comparison of policy documents, tracing policy evolution, stakeholder analysis, and exploring interdependencies of policies and their attributes with exogenous datasets using statistical tools. The usability and broad range of research implications suggest a need for the continued expansion of the KEPD to encompass a larger scope of policy documents across geographies and energy sectors.

Keywords: China, energy policy, policy analysis, policy database

Procedia PDF Downloads 323

Authors: Soofiyan Atar, Adil Shaikh, Sahil Rajpurkar, Pragnesh Bhalala, Aniket Desai, Irfan Siddavatam

Abstract:

Deep reinforcement learning (deep RL) algorithms leverage the symbolic power of complex controllers by automating it by mapping sensory inputs to low-level actions. Deep RL eliminates the complex robot dynamics with minimal engineering. Deep RL provides high-risk involvement by directly implementing it in real-world scenarios and also high sensitivity towards hyperparameters. Tuning of hyperparameters on a pneumatic quadruped robot becomes very expensive through trial-and-error learning. This paper presents an automated learning control for a pneumatic quadruped robot using sample efficient deep Q learning, enabling minimal tuning and very few trials to learn the neural network. Long training hours may degrade the pneumatic cylinder due to jerk actions originated through stochastic weights. We applied this method to the pneumatic quadruped robot, which resulted in a hopping gait. In our process, we eliminated the use of a simulator and acquired a stable gait. This approach evolves so that the resultant gait matures more sturdy towards any stochastic changes in the environment. We further show that our algorithm performed very well as compared to programmed gait using robot dynamics.

Keywords: model-based reinforcement learning, gait stability, supervised learning, pneumatic quadruped

Procedia PDF Downloads 316

Authors: Kuniyoshi Abe

Abstract:

Bi-conjugate gradient (Bi-CG) is a well-known method for solving linear equations Ax = b, for x, where A is a given n-by-n matrix, and b is a given n-vector. Typically, the dimension of the linear equation is high and the matrix is sparse. A number of hybrid Bi-CG methods such as conjugate gradient squared (CGS), Bi-CG stabilized (Bi-CGSTAB), BiCGStab2, and BiCGstab(l) have been developed to improve the convergence of Bi-CG. Bi-CGSTAB has been most often used for efficiently solving the linear equation, but we have seen the convergence behavior with a long stagnation phase. In such cases, it is important to have Bi-CG coefficients that are as accurate as possible, and the stabilization strategy, which stabilizes the computation of the Bi-CG coefficients, has been proposed. It may avoid stagnation and lead to faster computation. Motivated by a large number of processors in present petascale high-performance computing hardware, the scalability of Krylov subspace methods on parallel computers has recently become increasingly prominent. The main bottleneck for efficient parallelization is the inner products which require a global reduction. The resulting global synchronization phases cause communication overhead on parallel computers. The parallel variants of Krylov subspace methods reducing the number of global communication phases and hiding the communication latency have been proposed. However, the numerical stability, specifically, the convergence speed of the parallel variants of Bi-CGSTAB may become worse than that of the standard Bi-CGSTAB. In this paper, therefore, we compare the convergence speed between the standard Bi-CGSTAB and the parallel variants by numerical experiments and show that the convergence speed of the standard Bi-CGSTAB is faster than the parallel variants. Moreover, we propose the stabilization strategy for the parallel variants.

Keywords: bi-conjugate gradient stabilized method, convergence speed, Krylov subspace methods, linear equations, parallel variant

Procedia PDF Downloads 164

Authors: Marlin Killen

Abstract:

The American Association of University Professors (AAUP) describes academic freedom as essential to the purposes of research and teaching. The importance of academic freedom as a bedrock foundation that supports the work of the professoriate cannot be overstated, and there have been innumerable challenges that have attempted to curtail it. These challenges come from a variety of sources that span legal, ethical, cultural, institutional, and professional perspective and are amplified by social media, traditional media, and political action efforts. Because of these challenges, the development of a comprehensive institutional policy on academic freedom that addresses the principles, practices, and appropriate responses to modern challenges can be a daunting task. This presentation will focus on a case study of a university’s effort to develop an updated, evolving policy on academic freedom that provides a framework and remedies for contemporary challenges to this critical function in higher education.

Keywords: academic freedom, academic freedom policy, higher education policy

Procedia PDF Downloads 199

Authors: Dorna Kargar, Mehrasa Masih

Abstract:

Due to its special geological and geographical conditions, Iran has always been exposed to various natural hazards. Earthquake is one of the natural hazards with random nature that can cause significant financial damages and casualties. This is a serious threat, especially in areas with active faults. Therefore, considering the population density in some parts of the country, locating and zoning high-risk areas are necessary and significant. In the present study, seismic hazard assessment via probabilistic and deterministic method for Tehran, the capital of Iran, which is located in Alborz-Azerbaijan province, has been done. The seismicity study covers a range of 200 km from the north of Tehran (X=35.74° and Y= 51.37° in LAT-LONG coordinate system) to identify the seismic sources and seismicity parameters of the study region. In order to identify the seismic sources, geological maps at the scale of 1: 250,000 are used. In this study, we used Kijko-Sellevoll's method (1992) to estimate seismicity parameters. The maximum likelihood estimation of earthquake hazard parameters (maximum regional magnitude Mmax, activity rate λ, and the Gutenberg-Richter parameter b) from incomplete data files is extended to the case of uncertain magnitude values. By the combination of seismicity and seismotectonic studies of the site, the acceleration with antiseptic probability may happen during the useful life of the structure is calculated with probabilistic and deterministic methods. Applying the results of performed seismicity and seismotectonic studies in the project and applying proper weights in used attenuation relationship, maximum horizontal and vertical acceleration for return periods of 50, 475, 950 and 2475 years are calculated. Horizontal peak ground acceleration on the seismic bedrock for 50, 475, 950 and 2475 return periods are 0.12g, 0.30g, 0.37g and 0.50, and Vertical peak ground acceleration on the seismic bedrock for 50, 475, 950 and 2475 return periods are 0.08g, 0.21g, 0.27g and 0.36g.

Keywords: peak ground acceleration, probabilistic and deterministic, seismic hazard assessment, seismicity parameters

Procedia PDF Downloads 70

Authors: Andra Blumberga, Uldis Bariss, Anna Kubule, Dagnija Blumberga

Abstract:

European Union Energy Efficiency Directive provides a set of binding energy efficiency measures to reach. Each of the member states can use either energy efficiency obligation scheme or alternative policy measures or combination of both. Latvian government has decided to divide savings among obligation scheme (65%) and alternative measures (35%). This decision might lead to significant energy tariff increase hence impact on the national economy. To assess impact of alternative policy measures focusing on energy management scheme based on ISO 50001 and ability to decrease share of obligation scheme a System Dynamics modeling was used. Simulation results show that energy efficiency goal can be met with alternative policy measure to large energy consumers in industrial, tertiary and public sectors by applying the energy tax exemption for implementers of energy management system. A delay in applying alternative policy measures plays very important role in reaching the energy efficiency goal. One year delay in implementation of this policy measure reduces cumulative energy savings from 2016 to 2017 from 5200 GWh to 3000 GWh in 2020.

Keywords: system dynamics, energy efficiency, policy measure, energy management system, obligation scheme

Procedia PDF Downloads 282

Authors: Saikat Datta

Abstract:

Incompressible laminar time-varying flow is investigated over a rounded backward-facing step for a triangular piston motion at the inlet of a straight channel with very high acceleration, followed by a slow deceleration experimentally and through numerical simulation. The backward-facing step is an important test-case as it embodies important flow characteristics such as separation point, reattachment length, and recirculation of flow. A sliding piston imparts two successive triangular velocities at the inlet, constant acceleration from rest, 0≤t≤t0, and constant deceleration to rest, t0≤tKeywords: laminar boundary layer separation, rounded backward facing step, separation bubble, unsteady separation, unsteady vortex flows

Procedia PDF Downloads 66

Authors: Xueqing Ivy Chen, Christo De Coning

Abstract:

It is clear from practice that a gap exists between Result-Based Monitoring and Evaluation (RBME) as a discipline, and Knowledge Management (KM) on the other hand. Whereas various government departments have institutionalised these functions, KM and M&E has functioned in isolation from each other in a practical sense in the public sector. It’s therefore necessary to explore the relationship between KM and M&E and the necessity for integration, so that a convergence of these disciplines can be established. An integration of KM and M&E will lead to integration and improvement of evidence-based information and policy decision-making. M&E and KM process models are available but the complementarity between specific process steps of these process models are not exploited. A need exists to clarify the relationships between these functions in order to ensure evidence based information and policy decision-making. This paper will depart from the well-known policy process models, such as the generic model and consider recent on the interface between policy, M&E and KM.

Keywords: result-based monitoring and evaluation, RBME, knowledge management, KM, evident based decision making, public policy, information systems, institutional arrangement

Procedia PDF Downloads 152

Authors: Ghada Moussa, Mamoud Owais

Abstract:

Transit Route Network Design Problem (TrNDP) is the most important component in Transit planning, in which the overall cost of the public transportation system highly depends on it. The main purpose of this study is to develop a novel solution methodology for the TrNDP, which goes beyond pervious traditional sophisticated approaches. The novelty of the solution methodology, adopted in this paper, stands on the deterministic operators which are tackled to construct bus routes. The deterministic manner of the TrNDP solution relies on using linear and integer mathematical formulations that can be solved exactly with their standard solvers. The solution methodology has been tested through Mandl’s benchmark network problem. The test results showed that the methodology developed in this research is able to improve the given network solution in terms of number of constructed routes, direct transit service coverage, transfer directness and solution reliability. Although the set of routes resulted from the methodology would stand alone as a final efficient solution for TrNDP, it could be used as an initial solution for meta-heuristic procedures to approach global optimal. Based on the presented methodology, a more robust network optimization tool would be produced for public transportation planning purposes.

Keywords: integer programming, transit route design, transportation, urban planning

Procedia PDF Downloads 273

Authors: Ahmed Krobba, Meriem Touzene, Mohamed Debeyche

Abstract:

The wireless communications system (5G) will provide more diverse applications and higher quality services for users compared to the long-term evolution 4G (LTE). 5G uses a higher carrier frequency, which suffers from information loss in 5G coverage. Most 5G users often cannot obtain high-quality communications due to transmission channel noise and channel complexity. Physical Uplink Control Channel (PUCCH-NR: Physical Uplink Control Channel New Radio) plays a crucial role in 5G NR telecommunication technology, which is mainly used to transmit link control information uplink (UCI: Uplink Control Information. This study based of evaluating the performance of channel physical uplink control PUCCH-NR under low Signal-to-Noise Ratios with various antenna numbers reception. We propose the artificial intelligence approach based on deep neural networks (Deep Learning) to estimate the PUCCH-NR channel in comparison with this approach with different conventional methods such as least-square (LS) and minimum-mean-square-error (MMSE). To evaluate the channel performance we use the block error rate (BLER) as an evaluation criterion of the communication system. The results show that the deep neural networks method gives best performance compared with MMSE and LS

Keywords: 5G network, uplink (Uplink), PUCCH channel, NR-PUCCH channel, deep learning

Procedia PDF Downloads 82

Authors: Manjula Weerasekera, Chris Sissons, Lisa Wong, Sally Anderson, Ann Holmes, Richard Cannon

Abstract:

The aim of this study was to characterize bacterial population and yeasts in saliva by Polymerase chain reaction followed by denaturing gradient gel electrophoresis (PCR-DGGE) and measure yeast levels by culture. PCR-DGGE was performed to identify oral bacteria and yeasts in 24 saliva samples. DNA was extracted and used to generate DNA amplicons of the V2–V3 hypervariable region of the bacterial 16S rDNA gene using PCR. Further universal primers targeting the large subunit rDNA gene (25S-28S) of fungi were used to amplify yeasts present in human saliva. Resulting PCR products were subjected to denaturing gradient gel electrophoresis using Universal mutation detection system. DGGE bands were extracted and sequenced using Sanger method. A potential relationship was evaluated between groups of bacteria identified by cluster analysis of DGGE fingerprints with the yeast levels and with their diversity. Significant interpersonal variation of salivary microbiome was observed. Cluster and principal component analysis of the bacterial DGGE patterns yielded three significant major clusters, and outliers. Seventeen of the 24 (71%) saliva samples were yeast positive going up to 10³ cfu/mL. Predominately, C. albicans, and six other species of yeast were detected. The presence, amount and species of yeast showed no clear relationship to the bacterial clusters. Microbial community in saliva showed a significant variation between individuals. A lack of association between yeasts and the bacterial fingerprints in saliva suggests the significant ecological person-specific independence in highly complex oral biofilm systems under normal oral conditions.

Keywords: bacteria, denaturing gradient gel electrophoresis, oral biofilm, yeasts

Procedia PDF Downloads 222

Authors: J. A. Louw Coetzee, Josua P. Meyer

Abstract:

The thermodynamic properties of different refrigerants in combination with the variation in geometrical properties (hydraulic diameter, aspect ratio, and inclination angle) of a rectangular microchannel determine the two-phase frictional pressure gradient. The effect of aspect ratio on frictional pressure drop had not been investigated enough during adiabatic two-phase flow and condensation in rectangular microchannels. This experimental study was concerned with measurement of the frictional pressure gradient in a rectangular microchannel, with hydraulic diameter of 900 μm. The aspect ratio of this microchannel was varied over a range that stretched from 0.3 to 3 in order to capture the effect of aspect ratio variation. A commonly used refrigerant, R134a, was used in the tests that spanned over a mass flux range of 100 to 1000 kg m-2 s-1 as well as the whole vapour quality range. This study formed part of a refrigerant condensation experiment and was therefore conducted at a saturation temperature of 40 °C. The study found that there was little influence of the aspect ratio on the frictional pressure drop at the test conditions. The data was compared to some of the well known micro- and macro-channel two-phase pressure drop correlations. Most of the separated flow correlations predicted the pressure drop data well at mass fluxes larger than 400 kg m-2 s-1 and vapour qualities above 0.2.

Keywords: aspect ratio, microchannel, two-phase, pressure gradient

Procedia PDF Downloads 366

Authors: Ming Luo

Abstract:

In this real world, a manufacturer may produce more than one product. The products produced by the same manufacturer may share the same type of parts, similar design, and be produced in the same factory, i.e. some common causes. From the perspective of warranty management, the frequencies of those products’ warranty claims may have statistical dependence caused by the common causes. Warranty policy optimisation in the existing research, majorly, has not considered such dependence, which may increase bias in decision making. In the market, renewing warranty policies are provided to some unrepairable products and consumer electronic products. This paper optimises the renewing warranty policy collectively in a multi-product scenario with a consideration of the dependence among the warranty claims of the products produced by the same manufacturer. The existence of the optimal solution is proved. Numerical examples are used to validate the applicability of the proposed methods.

Keywords: mean-risk framework, modern portfolio theory, renewing warranty policy, warranty policy optimisation

Procedia PDF Downloads 299

Authors: Azene Zenebe

Abstract:

Deep learning is a subset of machine learning which incorporates techniques for the construction of artificial neural networks and found to be useful for modeling complex problems with large dataset. Deep learning requires a very high power computational and longer time for training. By aggregating computing power, high performance computer (HPC) has emerged as an approach to resolving advanced problems and performing data-driven research activities. Cyber threat intelligence (CIT) is actionable information or insight an organization or individual uses to understand the threats that have, will, or are currently targeting the organization. Results of review of literature will be presented along with results of experimental study that compares the performance of tree-based and function-base machine learning including deep learning algorithms using secondary dataset collected from darknet.

Keywords: deep-learning, cyber security, cyber threat modeling, tree-based machine learning, function-based machine learning, data science

Procedia PDF Downloads 154

Authors: S. K. Ashiquer Rahman

Abstract:

The proper policy handling might not able to attain the target since some of recessions, e.g., pandemic-led crises, the variables shocks of the economics. At the level of this situation, the Central bank implements the monetary policy to choose increase the exogenous expenditure and level of money supply consecutively for booster level economic growth, whether the monetary policy is relatively more effective than fiscal policy in altering real output growth of a country or both stand for relatively effective in the direction of output growth of a country. The dispute with reference to the relationship between the monetary policy and fiscal policy is centered on the inflationary penalty of the shortfall financing by the fiscal authority. The latest variables socks of economics as well as the pandemic-led crises, central banks around the world predicted just about a general dilemma in relation to increase rates to face the or decrease rates to sustain the economic movement. Whether the prices hang about fundamentally unaffected, the aggregate demand has also been hold a significantly negative attitude by the outbreak COVID-19 pandemic. To empirically investigate the effects of economics shocks associated COVID-19 pandemic, the paper considers the effectiveness of the monetary policy and fiscal policy that linked to the adjustment mechanism of different economic variables. To examine the effects of economics shock associated COVID-19 pandemic towards the effectiveness of Monetary Policy and Fiscal Policy in the direction of output growth of a Country, this paper uses the Simultaneous equations model under the estimation of Two-Stage Least Squares (2SLS) and Ordinary Least Squares (OLS) Method.

Keywords: IS-LM framework, pandemic. Economics variables shocks, simultaneous equations model, output growth

Procedia PDF Downloads 95

Authors: Amal Khalifa, Nicolas Vana Santos

Abstract:

Steganography has been known for centuries as an efficient approach for covert communication. Due to its popularity and ease of access, image steganography has attracted researchers to find secure techniques for hiding information within an innocent looking cover image. In this research, we propose a novel deep-learning approach to digital image steganography. The proposed method, DeepWaveletFusion, uses convolutional neural networks (CNN) to hide a secret image into a cover image of the same size. Two CNNs are trained back-to-back to merge the Discrete Wavelet Transform (DWT) of both colored images and eventually be able to blindly extract the hidden image. Based on two different image similarity metrics, a weighted gain function is used to guide the learning process and maximize the quality of the retrieved secret image and yet maintaining acceptable imperceptibility. Experimental results verified the high recoverability of DeepWaveletFusion which outperformed similar deep-learning-based methods.

Keywords: deep learning, steganography, image, discrete wavelet transform, fusion

Procedia PDF Downloads 90

Authors: Maryam Zarabian, Hector Guzman, Pedro Pereira-Almao, Abraham Fapojuwo

Abstract:

Dry reforming of methane (DRM) has sparked significant industrial and scientific interest not only as a viable alternative for addressing the environmental concerns of two main contributors of the greenhouse effect, i.e., carbon dioxide (CO₂) and methane (CH₄), but also produces syngas, i.e., a mixture of hydrogen (H₂) and carbon monoxide (CO) utilized by a wide range of downstream processes as a feedstock for other chemical productions. In this study, we develop an AI-enable syngas production model to tackle the problem of achieving an equivalent H₂/CO ratio [1:1] with respect to the most efficient conversion. Firstly, the unsupervised density-based spatial clustering of applications with noise (DBSAN) algorithm removes outlier data points from the original experimental dataset. Then, random forest (RF) and deep neural network (DNN) models employ the error-free dataset to predict the DRM results. DNN models inherently would not be able to obtain accurate predictions without a huge dataset. To cope with this limitation, we employ reusing pre-trained layers’ approaches such as transfer learning and greedy layer-wise pretraining. Compared to the other deep models (i.e., pure deep model and transferred deep model), the greedy layer-wise pre-trained deep model provides the most accurate prediction as well as similar accuracy to the RF model with R² values 1.00, 0.999, 0.999, 0.999, 0.999, and 0.999 for the total outlet flow, H₂/CO ratio, H₂ yield, CO yield, CH₄ conversion, and CO₂ conversion outputs, respectively.

Keywords: artificial intelligence, dry reforming of methane, artificial neural network, deep learning, machine learning, transfer learning, greedy layer-wise pretraining

Procedia PDF Downloads 86

Authors: Azubuike Ekwere

Abstract:

The shallow and deep aquiferous horizons of the fractured and weathered crystalline basement Oban Massif of south-eastern Nigeria were studied during the dry and wet seasons. The criteria were ascertaining hydrochemistry relative to seasonal and spatial variations across the study area. Results indicate that concentrations of major cations and anions exhibit the order of abundance; Ca>Na>Mg>K and HCO3>SO4>Cl respectively, with minor variations across sampling seasons. Major elements Ca, Mg, Na and K were higher for the shallow aquifers than the deep aquifers across seasons. The major anions Cl, SO4, HCO3, and NO3 were higher for the deep aquifers compared to the shallow ones. Two water types were identified for both aquifer types: Ca-Mg-HCO3 and Ca-Na-Cl-SO4. Most of the parameters considered were within the international limits for drinking, domestic and irrigation purposes. Assessment by use of sodium absorption ratio (SAR), percent sodium (%Na) and the wilcox diagram reveals that the waters are suitable for irrigation purposes.

Keywords: shallow aquifer, deep aquifer, seasonal variation, hydrochemistry, Oban massif, Nigeria

Procedia PDF Downloads 662

Authors: Abdelmounaim Zanaz, Sylvie Yotte, Fazia Fouchal, Alaa Chateauneuf

Abstract:

This paper presents a methodology for probabilistic assessment of bearing capacity and prediction of failure mechanism of masonry vaults at the ultimate state with consideration of the natural variability of Young’s modulus of stones. First, the computation model is explained. The failure mode is the most reported mode, i.e. the four-hinge mechanism. Based on this assumption, the study of a vault composed of 16 segments is presented. The Young’s modulus of the segments is considered as random variable defined by a mean value and a coefficient of variation CV. A relationship linking the vault bearing capacity to the modulus variation of voussoirs is proposed. The failure mechanisms, in addition to that observed in the deterministic case, are identified for each CV value as well as their probability of occurrence. The results show that the mechanism observed in the deterministic case has decreasing probability of occurrence in terms of CV, while the number of other mechanisms and their probability of occurrence increase with the coefficient of variation of Young’s modulus. This means that if a significant change in the Young modulus of the segments is proven, taken it into account in computations becomes mandatory, both for determining the vault bearing capacity and for predicting its failure mechanism.

Keywords: masonry, mechanism, probability, variability, vault

Procedia PDF Downloads 442

Authors: Saeed Poormoaied, Zumbul Atan

Abstract:

Emergency shipments provide a powerful mechanism to alleviate the risk of imminent stock-outs and can result in substantial benefits in an inventory system. Customer satisfaction and high service level are immediate consequences of utilizing emergency shipments. In this paper, we consider a single-echelon periodic review inventory system consisting of a single local warehouse, being replenished from a central warehouse with ample capacity in an infinite horizon setting. Since the structure of the optimal policy appears to be complicated, we analyze this problem under an order-up-to-S inventory control policy framework, the (S, T) policy, with the emergency shipment consideration. In each period of the periodic review policy, there is a single opportunity at any point of time for the emergency shipment so that in case of stock-outs, an emergency shipment is requested. The goal is to determine the timing and amount of the emergency shipment during a period (emergency shipment policy) as well as the base stock periodic review policy parameters (replenishment policy). We show that how taking advantage of having an emergency shipment during periods improves the performance of the classical (S, T) policy, especially when fixed and unit emergency shipment costs are small. Investigating the structure of the objective function, we develop an exact algorithm for finding the optimal solution. We also provide a heuristic and an approximation algorithm for the periodic review inventory system problem. The experimental analyses indicate that the heuristic algorithm is computationally more efficient than the approximation algorithm, but in terms of the solution efficiency, the approximation algorithm performs very well. We achieve up to 13% cost savings in the (S, T) policy if we apply the proposed emergency shipment policy. Moreover, our computational results reveal that the approximated solution is often within 0.21% of the globally optimal solution.

Keywords: emergency shipment, inventory, periodic review policy, approximation algorithm.

Procedia PDF Downloads 141

Authors: Alessandro Marano

Abstract:

The author describes the use of deep plane face lifting and platysmaplasty to treat sagging neck with minimal scars. Series of case study. The author uses a selective deep plane face lift with a minimal access scar that not extend behind the ear lobe, neck liposuction and platysmaplasty to restore the sagging neck; the scars are minimal and no require drainage post-op. The deep plane face lifting can achieve a good result restoring vertical vectors in aging and sagging face, neck district can be treated without cutting the skin behind the ear lobe combining the SMAS vertical suspension and platysmaplasty; surgery can be performed in local anesthesia with sedation in day surgery and fast recovery. Restoring neck sagging without extend scars behind ear lobe is possible in selected patients, procedure is fast, safe, no drainage required, patients are satisfied and healing time is fast and comfortable.

Keywords: face lifting, aesthetic, face, neck, platysmaplasty, deep plane

Procedia PDF Downloads 101

Authors: Thanomsin Chakreeves, Atichat Preittigun, Ajchara Phu-ang

Abstract:

This paper presents a stakeholder analysis of agricultural drone policies that meet the government's goal of building an agricultural drone ecosystem in Thailand. Firstly, case studies from other countries are reviewed. The stakeholder analysis method and qualitative data from the interviews are then presented including data from the Institute of Innovation and Management, the Office of National Higher Education Science Research and Innovation Policy Council, agricultural entrepreneurs and farmers. Study and interview data are then employed to describe the current ecosystem and to guide the implementation of agricultural drone policies that are suitable for the ecosystem of Thailand. Finally, policy recommendations are then made that the Thai government should adopt in the future.

Keywords: drone public policy, drone ecosystem, policy development, agricultural drone

Procedia PDF Downloads 147

Authors: Katherine Carl Payne, Moshe Dror

Abstract:

The problem of minimum cost routing has been extensively explored in a variety of contexts. While there is a prevalence of routing applications based on least distance, time, and related attributes, exertion-based routing has remained relatively unexplored. In particular, the network structures traditionally used to construct minimum cost paths are not suited to representing exertion or finding paths of least exertion based on road gradient. In this paper, we introduce a topographical network or “topograph” that enables minimum cost routing based on the exertion metric on each arc in a given road network as it is related to changes in road gradient. We describe an algorithm for topograph construction and present the implementation of the topograph on a road network of the state of California with ~22 million nodes.

Keywords: topograph, RPE, routing, GIS

Procedia PDF Downloads 546

Authors: Bandar Alahmadi, Manohar Mareboyana, Lethia Jackson

Abstract:

Today, there are many applications that are using computer vision models, such as face recognition, image classification, and object detection. The accuracy of these models is very important for the performance of these applications. One challenge that facing the computer vision models is the adversarial examples attack. In computer vision, the adversarial example is an image that is intentionally designed to cause the machine learning model to misclassify it. One of very well-known method that is used to attack the Convolution Neural Network (CNN) is Fast Gradient Sign Method (FGSM). The goal of this method is to find the perturbation that can fool the CNN using the gradient of the cost function of CNN. In this paper, we introduce a novel model that can attack Regional-Convolution Neural Network (R-CNN) that use FGSM. We first extract the regions that are detected by R-CNN, and then we resize these regions into the size of regular images. Then, we find the best perturbation of the regions that can fool CNN using FGSM. Next, we add the resulted perturbation to the attacked region to get a new region image that looks similar to the original image to human eyes. Finally, we placed the regions back to the original image and test the R-CNN with the attacked images. Our model could drop the accuracy of the R-CNN when we tested with Pascal VOC 2012 dataset.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 193

Authors: Aikaterini Tsalampouni

Abstract:

The European Union has long been the most developed model of economic and political integration that has brought a common market, a common currency and a standardization of national policies in certain areas in consistent with EU values and principles. To this direction, there is a parallel process of social integration that effect public policy decisions of member states. Even though social policy, i.e. social protection and moreover healthcare policy, still remains in state's responsibility to develop, EU applies different mechanisms in order to influence health policy systems, since from a more federalist point of view, EU ought to expand its regulatory and legislative roles in as many policy areas as possible. Recently, the pandemic has become a turning point for health care provision and at the same time has also highlighted the need to strengthen the EU’s role in coordinating health care. This paper analyses the EU health policy in general, as well as the response to COVID-19 pandemic with an attempt to identify indications of interaction between EU policies and the promotion of sustainable and resilient health systems. More analytically, the paper investigates the EU binding legal instruments, non-binding legal instruments, monitoring and assessment instruments and instruments for co-financing concerning health care provision in member states and records the evolution of health policies before and during the COVID-19 pandemic. The paper concludes by articulating some remarks regarding the improvement of health policy in EU. Since the ability to deal with a pandemic depends on continuous and increased investment in health systems, the involvement of the EU can lead to a policy convergence, necessary for the resilience of the systems, maintaining at the same time, a strong health policy framework in Europe.

Keywords: EU health policy, EU response to COVID-19, European Health Union, health systems in Europe

Procedia PDF Downloads 114

Authors: Yadav Shyamjeet Maniram

Abstract:

Despite reports of more than seventy million population of India affected by rare diseases, it rarely figured on the agenda of the Indian scientist and policymakers. Hitherto ignored, a fresh initiative is being attempted to establish the first national registry for rare diseases. Though there are registries for rare diseases, established by the clinicians and patient advocacy groups, they are isolated, scattered and lacks information sharing mechanism. It is the first time that there is an effort from the government of India to make an initiative on the rare disease registries, which would be more formal and systemic in nature. Since there is lack of epidemiological evidence for the rare disease in India, it is interesting to note how rare disease policy is being attempted in the vacuum of evidence required for the policy process. The objective of this study is to analyse rare disease registry creation and implementation from the parameters of evolutionary policy perspective in the absence of evidence for the policy process. This study will be exploratory and qualitative in nature, primarily based on the interviews of stakeholders involved in the rare disease registry creation and implementation. Some secondary data will include various documents related to rare disease registry. The expected outcome of this study would be on the role of stakeholders in the generation of evidence for the rare disease registry creation and implementation. This study will also try to capture negotiations and deliberations on the ethical issues in terms of data collection, preservation, and protection.

Keywords: evolutionary policy perspective, evidence for policy, rare disease policy, rare disease in India

Procedia PDF Downloads 207