Search results for: Deep submicron

Authors: Jie Zhang, Qianyu Guo, Tieyi Zhang, Zhiyong Feng, Xiaohong Li

Abstract:

The widespread popularity of mobile devices and the development of artificial intelligence (AI) have led to the widespread adoption of deep learning (DL) in Android apps. Compared with traditional Android apps (traditional apps), deep learning based Android apps (DL-based apps) need to use more third-party application programming interfaces (APIs) to complete complex DL inference tasks. However, existing methods (e.g., FlowDroid) for detecting sensitive information leakage in Android apps cannot be directly used to detect DL-based apps as they are difficult to detect third-party APIs. To solve this problem, we design DLtrace, a new static information flow analysis tool that can effectively recognize third-party APIs. With our proposed trace and detection algorithms, DLtrace can also efficiently detect privacy leaks caused by sensitive APIs in DL-based apps. Additionally, we propose two formal definitions to deal with the common polymorphism and anonymous inner-class problems in the Android static analyzer. Using DLtrace, we summarize the non-sequential characteristics of DL inference tasks in DL-based apps and the specific functionalities provided by DL models for such apps. We conduct an empirical assessment with DLtrace on 208 popular DL-based apps in the wild and found that 26.0% of the apps suffered from sensitive information leakage. Furthermore, DLtrace outperformed FlowDroid in detecting and identifying third-party APIs. The experimental results demonstrate that DLtrace expands FlowDroid in understanding DL-based apps and detecting security issues therein.

Keywords: Mobile computing, deep learning apps, sensitive information, static analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 496

Authors: A. Chakraborty, T. Gupta

Abstract:

Several studies have shown the association between ambient particulate matter (PM) and adverse health effects and climate change, thus highlighting the need to limit the anthropogenic sources of PM. PM Exposure is commonly monitored as mass concentration of PM10 (particle aerodynamic diameter < 10μm) or PM2.5 (particle aerodynamic diameter < 2.5μm), although increasing toxicity with decreasing aerodynamic diameter has been reported due to increased surface area and enhanced chemical reactivity with other species. Additionally, the light scattering properties of PM increases with decreasing size. Hence, it is important to study the chemical characterization of finer fraction of the particulate matter and to identify their sources so that they can be controlled appropriately to a large extent at the sources before reaching to the receptors.

Keywords: PM1, PCA, source apportionment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1615

Authors: Merve Küçük, M. Lütfi Öveçoğlu

Abstract:

Zinc oxide particles were synthesized using the sol-gel method and dip coated on polyester fabric. X-ray diffraction (XRD) analysis revealed a single crystal phase of ZnO particles. Chemical characteristics of the polyester fabric surface were investigated using attenuated total reflection-Fourier transform infrared (ATR-FTIR) measurements. Morphology of ZnO coated fabric was analyzed using field emission scanning electron microscopy (FESEM). After particle analysis, the aqueous ZnO solution resulted in a narrow size distribution at submicron levels. The deposit of ZnO on polyester fabrics yielded a homogeneous spread of spherical particles. Energy dispersive X-ray spectroscopy (EDX) results also affirmed the presence of ZnO particles on the polyester fabrics.

Keywords: Dip coating, polyester fabrics, sol-gel, zinc oxide.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1471

Authors: H. L. Ku, K. C. Yang, S. Y. Jhou, S. C. Lee, C. S. Lin

Abstract:

Characterized as rich mineral substances, low temperature, few bacteria, and stability with numerous implementation aspects on aquaculture, food, drinking, and leisure, the deep sea water (DSW) development has become a new industry in the world. It has been report that marine algae contain various biologically active compounds. This research focued on the affections in cultivating Sagrassum cristaefolium with different concentration of deep sea water(DSW) and surface sea water(SSW). After two and four weeks, the total phenolic contents were compared in Sagrassum cristaefolium culturing with different ways, and the reductive activity of them was also be tried with potassium ferricyanide. Those fresh seaweeds were dried with oven and were ground to powder. Progressively, the marine algae we cultured was extracted by water under the condition with heating them at 90Ôäâ for 1hr.The total phenolic contents were be executed using Folin–Ciocalteu method. The results were explaining as follows: the highest total phenolic contents and the best reductive ability of all could be observed on the 1/4 proportion of DSW to SSW culturing in two weeks. Furthermore, the 1/2 proportion of DSW to SSW also showed good reductive ability and plentiful phenolic compositions. Finally, we confirmed that difference proportion of DSW and SSW is the major point relating to ether the total phenolic components or the reductive ability in the Sagrassum cristaefolium. In the future, we will use this way to mass production the marine algae or other micro algae on industry applications.

Keywords: deep sea water(DSW), surface sea water(SSW), phenolic contents, reductive ability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1574

Authors: A. M. Gsiea, J. P. Goss, P. R. Briddon, Ramadan. M. Al-habashi, K. M. Etmimi, Khaled. A. S. Marghani

Abstract:

Using first-principles methods based on density functional theory and pseudopotentials, we have performed a details study of native defects in ZnO. Native point defects are unlikely to be cause of the unintentional n-type conductivity. Oxygen vacancies, which considered most often been invoked as shallow donors, have high formation energies in n-type ZnO, in edition are a deep donors. Zinc interstitials are shallow donors, with high formation energies in n-type ZnO, and thus unlikely to be responsible on their own for unintentional n-type conductivity under equilibrium conditions, as well as Zn antisites which have higher formation energies than zinc interstitials. Zinc vacancies are deep acceptors with low formation energies for n-type and in which case they will not play role in p-type coductivity of ZnO. Oxygen interstitials are stable in the form of electrically inactive split interstitials as well as deep acceptors at the octahedral interstitial site under n-type conditions. Our results may provide a guide to experimental studies of point defects in ZnO.

Keywords: DFT, Native, n-Type, ZnO.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4501

Authors: Chinlun Lai, Lunjyh Jiang

Abstract:

Due to the heavy burden and pressure of caring for infants, an integrated automatic baby watching system based on IoT smart sensing and deep learning machine vision techniques is proposed in this paper. By monitoring infant body conditions such as heartbeat, breathing, body temperature, sleeping posture, as well as the surrounding conditions such as dangerous/sharp objects, light, noise, humidity and temperature, the proposed system can analyze and predict the obvious/potential dangerous conditions according to observed data and then adopt suitable actions in real time to protect the infant from harm. Thus, reducing the burden of the caregiver and improving safety efficiency of the caring work. The experimental results show that the proposed system works successfully for the infant care work and thus can be implemented in various life fields practically.

Keywords: Baby care system, internet of things, deep learning, machine vision.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1838

Authors: Roman Knizek, Denisa Karhankova, Ludmila Fridrichova

Abstract:

For their exceptional properties nanofibers, respectively, nanofiber layers are achieving an increasingly wider range of uses. Nowadays nanofibers are used mainly in the field of air filtration where they are removing submicron particles, bacteria, and viruses. Their efficiency is not changed in time, and the power consumption is much lower than that of electrically charged filters. Nanofibers are primarily used for converting and storage of energy in both air and liquid filtration, in food and packaging, protecting the environment, but also in health care which is made possible by their newly discovered properties. However, a major problem of the nanofiber layer is practically zero abrasion resistance; it is, therefore, necessary to laminate the nanofiber layer with another suitable material. Unfortunately, lamination of nanofiber layers is a major problem since the nanofiber layer contains small pores through which it is very difficult for adhesion to pass through. Therefore, there is still only a small percentage of products with these unique fibers 5.

Keywords: Nanofiber layer, nanomembrane, lamination, electrospinning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1286

Authors: T. Damak, O. Kriaa, A. Baccar, M. A. Ben Ayed, N. Masmoudi

Abstract:

In the last few years, Automatic Number Plate Recognition (ANPR) systems have become widely used in the safety, the security, and the commercial aspects. Forethought, several methods and techniques are computing to achieve the better levels in terms of accuracy and real time execution. This paper proposed a computer vision algorithm of Number Plate Localization (NPL) and Characters Segmentation (CS). In addition, it proposed an improved method in Optical Character Recognition (OCR) based on Deep Learning (DL) techniques. In order to identify the number of detected plate after NPL and CS steps, the Convolutional Neural Network (CNN) algorithm is proposed. A DL model is developed using four convolution layers, two layers of Maxpooling, and six layers of fully connected. The model was trained by number image database on the Jetson TX2 NVIDIA target. The accuracy result has achieved 95.84%.

Keywords: Automatic number plate recognition, character segmentation, convolutional neural network, CNN, deep learning, number plate localization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1215

Authors: Ming-Hsiung Wu, Yu-Hsi Yuan

Abstract:

The aim of the research is to understand whether the accuracy of customer detection of employee emotional labor strategy would influence the overall service satisfaction. From path analysis, it was found that employee-s positive emotions positively influenced service quality. Service quality in turn influenced Customer detection of employee emotional deep action strategy and Customer detection of employee emotional surface action strategy. Lastly, Customer detection of employee emotional deep action strategy and Customer detection of employee emotional surface action strategy positively influenced service satisfaction. Based on the analysis results, suggestions are proposed to provide reference for human resource management and use in relative fields.

Keywords: Emotional labor, Emotional deep action strategy, Emotional surface action strategy, Service satisfaction

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1547

Authors: M. Sadeghi, A.H. Jafari, S.M.P. Firoozabadi

Abstract:

Deep Brain Stimulation or DBS is a surgical treatment for Parkinson-s Disease with three stimulation parameters: frequency, pulse width, and voltage. The parameters should be selected appropriately to achieve effective treatment. This selection now, performs clinically. The aim of this research is to study chaotic behavior of recorded tremor of patients under DBS in order to present a computational method to recognize stimulation optimum voltage. We obtained some chaotic features of tremor signal, and discovered embedding space of it has an attractor, and its largest Lyapunov exponent is positive, which show tremor signal has chaotic behavior, also we found out, in optimal voltage, entropy and embedding space variance of tremor signal have minimum values in comparison with other voltages. These differences can help neurologists recognize optimal voltage numerically, which leads to reduce patients' role and discomfort in optimizing stimulation parameters and to do treatment with high accuracy.

Keywords: Chaos, Deep Brain Stimulation, Parkinson's Disease, Stimulation Parameters, tremor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1779

Authors: Chad Goldsworthy, B. Rajeswari Matam

Abstract:

The use of deep learning for species identification in camera trap images has revolutionised our ability to study, conserve and monitor species in a highly efficient and unobtrusive manner, with state-of-the-art models achieving accuracies surpassing the accuracy of manual human classification. The high imbalance of camera trap datasets, however, results in poor accuracies for minority (rare or endangered) species due to their relative insignificance to the overall model accuracy. This paper investigates the use of Focal Loss, in comparison to the traditional Cross Entropy Loss function, to improve the identification of minority species in the “255 Bird Species” dataset from Kaggle. The results show that, although Focal Loss slightly decreased the accuracy of the majority species, it was able to increase the F1-score by 0.06 and improve the identification of the bottom two, five and ten (minority) species by 37.5%, 15.7% and 10.8%, respectively, as well as resulting in an improved overall accuracy of 2.96%.

Keywords: Convolutional neural networks, data imbalance, deep learning, focal loss, species classification, wildlife conservation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1336

Authors: Susmita Sahoo, Madhumanti Datta, Rajib Kar

Abstract:

The resistive-inductive-capacitive behavior of long interconnects which are driven by CMOS gates are presented in this paper. The analysis is based on the ¤Ç-model of a RLC load and is developed for submicron devices. Accurate and analytical expressions for the output load voltage, the propagation delay and the short circuit power dissipation have been proposed after solving a system of differential equations which accurately describe the behavior of the circuit. The effect of coupling capacitance between input and output and the short circuit current on these performance parameters are also incorporated in the proposed model. The estimated proposed delay and short circuit power dissipation are in very good agreement with the SPICE simulation with average relative error less than 6%.

Keywords: Delay, Inverter, Short Circuit Power, ¤Ç-Model, RLCInterconnect, VLSI

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1651

Authors: A. Pourkamali Anaraki, M. Shahabizadeh, B. Babaee

Abstract:

The plastic forming process of sheet plate takes an important place in forming metals. The traditional techniques of tool design for sheet forming operations used in industry are experimental and expensive methods. Prediction of the forming results, determination of the punching force, blank holder forces and the thickness distribution of the sheet metal will decrease the production cost and time of the material to be formed. In this paper, multi-stage deep drawing simulation of an Industrial Part has been presented with finite element method. The entire production steps with additional operations such as intermediate annealing and springback has been simulated by ABAQUS software under axisymmetric conditions. The simulation results such as sheet thickness distribution, Punch force and residual stresses have been extracted in any stages and sheet thickness distribution was compared with experimental results. It was found through comparison of results, the FE model have proven to be in close agreement with those of experiment.

Keywords: Deep drawing, Finite element method, Simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5019

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

Abstract:

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

Keywords: Excavations, support systems, wall stiffness, cantilever walls.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 375

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: Visual search, deep learning, convolutional neural network, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 774

Authors: P. Bogas

Abstract:

As a scientific contribution to this discussion, a pedagogical intervention of a quasi-experimental nature was developed, with a mixed methodology, evaluating the intervention within a single curricular unit of Marketing, using cases based on real challenges of brands, business simulation and customer projects. Primary and secondary experiences were incorporated in the intervention: the primary experiences are the experiential activities themselves; the secondary experiences resulted from the primary experience, such as reflection and discussion in work teams. A diversified learning relationship was encouraged through the various connections between the different members of the learning community. The present study concludes that in the same context, the students' response can be described as: students who reinforce the initial deep approach, students who maintain the initial deep approach level and others who change from an emphasis on the deep approach to one closer to superficial. This typology did not always confirm studies reported in the literature, namely, whether the initial level of deep processing would influence the superficial and the opposite. The result of this investigation points to the inclusion of pedagogical and didactic activities that integrate different motivations and initial strategies, leading to a possible adoption of deep approaches to learning, since it revealed statistically significant differences in the difference in the scores of the deep/superficial approach and the experiential level. In the case of real challenges, the categories of “attribution of meaning and meaning of studied” and the possibility of “contact with an aspirational context” for their future professional stand out. In this category, the dimensions of autonomy that will be required of them were also revealed when comparing the classroom context of real cases and the future professional context and the impact they may have on the world. Regarding to the simulated practice, two categories of response stand out: on the one hand, the motivation associated with the possibility of measuring the results of the decisions taken, an awareness of oneself and, on the other hand, the additional effort that this practice required for some of the students.

Keywords: Experiential learning, higher education, marketing, mixed methods, reflective thinking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 236

Authors: P. R. Prabhu, S. M. Kulkarni, S. S. Sharma

Abstract:

Deep cold rolling (DCR) and low plasticity burnishing (LPB) process are cold working processes, which easily produce a smooth and work-hardened surface by plastic deformation of surface irregularities. The present study focuses on the surface roughness and surface hardness aspects of AISI 4140 work material, using fractional factorial design of experiments. The assessment of the surface integrity aspects on work material was done, in order to identify the predominant factors amongst the selected parameters. They were then categorized in order of significance followed by setting the levels of the factors for minimizing surface roughness and/or maximizing surface hardness. In the present work, the influence of main process parameters (force, feed rate, number of tool passes/overruns, initial roughness of the work piece, ball material, ball diameter and lubricant used) on the surface roughness and the hardness of AISI 4140 steel were studied for both LPB and DCR process and the results are compared. It was observed that by using LPB process surface hardness has been improved by 167% and in DCR process surface hardness has been improved by 442%. It was also found that the force, ball diameter, number of tool passes and initial roughness of the workpiece are the most pronounced parameters, which has a significant effect on the work piece-s surface during deep cold rolling and low plasticity burnishing process.

Keywords: Deep cold rolling, burnishing, surface roughness, surface hardness, design of experiments, AISI4140 steel.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3729

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: Deep learning, long-short-term memory, energy, renewable energy load forecasting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1536

Authors: M. S. Al-Assiri, M. M. El-Desoky, Ahmed A. Ibrahim, M. Abaker, A. A. Bahgat

Abstract:

Nanocrystalline thin film of Na0.1V2O5.nH2O xerogel obtained by sol gel synthesis was used as gas sensor. Gas sensing properties of different gases such as hydrogen, petroleum and humidity were investigated. Applying XRD and TEM the size of the nanocrystals is found to be 7.5 nm. SEM shows a highly porous structure with submicron meter-sized voids present throughout the sample. FTIR measurement shows different chemical groups identifying the obtained series of gels. The sample was n-type semiconductor according to the thermoelectric power and electrical conductivity. It can be seen that the sensor response curves from 130oC to 150oC show a rapid increase in sensitivity for all types of gas injection, low response values for heating period and the rapid high response values for cooling period. This result may suggest that this material is able to act as gas sensor during the heating and cooling process.

Keywords: Sol gel, Thermoelectric power, XRD, TEM, Gas sensing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1742

Authors: N. Massoum, A. Guen. Bouazza, B. Bouazza, A. El Ouchdi

Abstract:

The progress of industry integrated circuits in recent years has been pushed by continuous miniaturization of transistors. With the reduction of dimensions of components at 0.1 micron and below, new physical effects come into play as the standard simulators of two dimensions (2D) do not consider. In fact the third dimension comes into play because the transverse and longitudinal dimensions of the components are of the same order of magnitude. To describe the operation of such components with greater fidelity, we must refine simulation tools and adapted to take into account these phenomena. After an analytical study of the static characteristics of the component, according to the different operating modes, a numerical simulation is performed of field-effect transistor with submicron gate MESFET GaInP. The influence of the dimensions of the gate length is studied. The results are used to determine the optimal geometric and physical parameters of the component for their specific applications and uses.

Keywords: Monte Carlo simulation, transient electron transport, MESFET device.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1620

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: Deep learning, field programmable gate array, FPGA, hardware acceleration, convolutional neural networks, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 823

Authors: Zhong Ma, Zhuping Wang, Congxin Liu, Xiangzeng Liu

Abstract:

Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.

Keywords: Satellite imagery classification, deep convolution network, genetic algorithm, hyper-parameter optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2291

Authors: Fidel Lòpez Saca, Carlos Avilés-Cruz, Miguel Magos-Rivera, José Antonio Lara-Chávez

Abstract:

Automated object recognition and identification systems are widely used throughout the world, particularly in assembly lines, where they perform quality control and automatic part selection tasks. This article presents the design and implementation of an object recognition system in an assembly line. The proposed shapes-color recognition system is based on deep learning theory in a specially designed convolutional network architecture. The used methodology involve stages such as: image capturing, color filtering, location of object mass centers, horizontal and vertical object boundaries, and object clipping. Once the objects are cut out, they are sent to a convolutional neural network, which automatically identifies the type of figure. The identification system works in real-time. The implementation was done on a Raspberry Pi 3 system and on a Jetson-Nano device. The proposal is used in an assembly course of bachelor’s degree in industrial engineering. The results presented include studying the efficiency of the recognition and processing time.

Keywords: Deep-learning, image classification, image identification, industrial engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 667

Authors: H.Seidi, M.Jalali Azizpour, S.A.Zahedi

Abstract:

Today, Hydroforming technology provides an attractive alternative to conventional matched die forming, especially for cost-sensitive, lower volume production, and for parts with irregular contours. In this study the critical fluid pressures which lead to rupture in the workpiece has been investigated by theoretical and finite element methods. The axisymmetric analysis was developed to investigate the tearing phenomenon in cylindrical Hydroforming Deep Drawing (HDD). By use of obtained equations the effect of anisotropy, drawing ratio, sheet thickness and strain hardening exponent on tearing diagram were investigated.

Keywords: Hydroforming deep drawing, Pressure path, Axisymmetric analysis, Finite element simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1626

Authors: Jie Liu, Xudong Luo, Pingping Lin, Yifan Fan

Abstract:

Facebook, Twitter, Weibo, and other social media and significant e-commerce sites generate a massive amount of online texts, which can be used to analyse people’s opinions or sentiments for better decision-making. So, sentiment analysis, especially the fine-grained sentiment analysis, is a very active research topic. In this paper, we survey various methods for fine-grained sentiment analysis, including traditional sentiment lexicon-based methods, ma-chine learning-based methods, and deep learning-based methods in aspect/target/attribute-based sentiment analysis tasks. Besides, we discuss their advantages and problems worthy of careful studies in the future.

Keywords: sentiment analysis, fine-grained, machine learning, deep learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2273

Authors: Boonyarat Chaleephay

Abstract:

The purpose of this research paper was to describe the relationship of acupressure points on the anterior surface of the upper limb in accordance with Applied Thai Traditional Massage (ATTM) and the deep structures located at those acupressure points. There were 2 population groups; normal subjects and cadaver specimens. Eighteen males with age ranging from 20-40 years old and seventeen females with ages ranging from 30-97 years old were studies. This study was able to obtain a fundamental knowledge concerning acupressure point and the deep structures that related to those acupressure points. It might be used as the basic knowledge for clinically applying and planning treatment as well as teaching in ATTM.

Keywords: Acupressure point (AP), Applie Thai Traditional Medicine (ATTM), Paresthesia, Numbness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2129

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: Metaphor detection, deep learning, representation learning, embeddings.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 475

Authors: Chien-Wan Hun, Shao-Fu Chang, Jheng-En Yang, Chien-Chon Chen, Wern-Dare Jheng

Abstract:

This research provides a systematic way to study and better understand double nano-tubular structure of alunina (Al2O3) and titania (TiO2). The TiO2 NT was prepared by immersing Al2O3 template in 0.02 M titanium fluoride (TiF4) solution (pH=3) at 25 °C for 120 min, followed by annealing at 450 °C for 1 h to obtain anatase TiO2 NT in the Al2O3 template. Large-scale development of film for nanotube-based CO2 capture and conversion can potentially result in more efficient energy harvesting. In addition, the production process will be relatively environmentally friendly. The knowledge generated by this research will significantly advance research in the area of Al2O3, TiO2, CaO, and Ca2O3 nano-structure film fabrication and applications for CO2 capture and conversion. This green energy source will potentially reduce reliance on carbon-based energy resources and increase interest in science and engineering careers.

Keywords: Alumina, titania, nano-tubular, film, CO2.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1525

Authors: Endrick Barnacin, Jean-Luc Henry, Jimmy Nagau, Jack Molinié

Abstract:

Palynology is a field of interest in many disciplines due to its multiple applications: chronological dating, climatology, allergy treatment, and honey characterization. Unfortunately, the analysis of a pollen slide is a complicated and time consuming task that requires the intervention of experts in the field, which are becoming increasingly rare due to economic and social conditions. In this context, the automation of this task is urgent. In this work, we compare classical feature extraction methods (Shape, GLCM, LBP, and others) and Deep Learning (CNN and Transfer Learning) to perform a recognition task over 80 regional pollen species. It has been found that the use of Transfer Learning seems to be more precise than the other approaches.

Keywords: Image segmentation, stuck particles separation, Sobel operator, thresholding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 138

Authors: Shaibu Baanni Azumah, Ignatius Tindjina, Stella Obanyi, Tara N. Wood

Abstract:

This study examined the effect of Urea Deep Placement (UDP) technology on the output of irrigated rice farmers in the northern region of Ghana. Multi-stage sampling technique was used to select 142 rice farmers from the Golinga and Bontanga irrigation schemes, around Tamale. A treatment effect model was estimated at two stages; firstly, to determine the factors that influenced farmers’ decision to adopt the UDP technology and secondly, to determine the effect of the adoption of the UDP technology on the output of rice farmers. The significant variables that influenced rice farmers’ adoption of the UPD technology were sex of the farmer, land ownership, off-farm activity, extension service, farmer group participation and training. The results also revealed that farm size and the adoption of UDP technology significantly influenced the output of rice farmers in the northern region of Ghana. In addition to the potential of the technology to improve yields, it also presents an employment opportunity for women and youth, who are engaged in the deep placement of Urea Super Granules (USG), as well as in the transplantation of rice. It is recommended that the government of Ghana work closely with the IFDC to embed the UDP technology in the national agricultural programmes and policies. The study also recommends an effective collaboration between the government, through the Ministry of Food and Agriculture (MoFA) and the International Fertilizer Development Center (IFDC) to train agricultural extension agents on UDP technology in the rice producing areas of the country.

Keywords: Northern Ghana, output, irrigation rice farmers, treatment effect model, urea deep placement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1084