Search results for: Convolutional codes

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 822

Authors: Le-Ren Chang-Chien, Yin-Juin Lin, Chin-Chung Wu

Abstract:

Utilities use operating reserve for frequency regulation.To ensure that the operating frequency and system security are well maintained, the operating grid codes always specify that the reserve quantity and response rate should meet some prescribed levels. This paper proposes a methodology to evaluate system's contingency reserve for an isolated power network. With the presented algorithm to estimate system's frequency response characteristic, an online allocation of contingency reserve would be feasible to meet the grid codes for contingency operation. Test results from the simulated conditions, and from the actual operating data verify the merits of the proposed methodology to system's frequency control, and security.

Keywords: Contingency, frequency control, operating reserve.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1604

Authors: Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen

Abstract:

The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluates the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.

Keywords: lexical semantics, feature representation, semantic decision, convolutional neural network, electronic medical record

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 512

Authors: H. M. Behairy, M. S. Khorsheed

Abstract:

Among other factors that characterize satellite communication channels is their high bit error rate. We present a system for still image transmission over noisy satellite channels. The system couples image compression together with error control codes to improve the received image quality while maintaining its bandwidth requirements. The proposed system is tested using a high resolution satellite imagery simulated over the Rician fading channel. Evaluation results show improvement in overall system including image quality and bandwidth requirements compared to similar systems with different coding schemes.

Keywords: Image Transmission, Image Compression, Channel Coding, Error-Control Coding, DCT, Convolution Codes, Viterbi Algorithm, PCGC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1811

Authors: Grigorios D. Dimitroulakos, N. D. Zervas, N. Sklavos, Costas E. Goutis

Abstract:

In this paper, the implementation of low power, high throughput convolutional filters for the one dimensional Discrete Wavelet Transform and its inverse are presented. The analysis filters have already been used for the implementation of a high performance DWT encoder [15] with minimum memory requirements for the JPEG 2000 standard. This paper presents the design techniques and the implementation of the convolutional filters included in the JPEG2000 standard for the forward and inverse DWT for achieving low-power operation, high performance and reduced memory accesses. Moreover, they have the ability of performing progressive computations so as to minimize the buffering between the decomposition and reconstruction phases. The experimental results illustrate the filters- low power high throughput characteristics as well as their memory efficient operation.

Keywords: Discrete Wavelet Transform; JPEG2000 standard; VLSI design; Low Power-Throughput-optimized filters

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1227

Authors: Jutta Hämmerle-Uhl, Georg Penn, Gerhard Pötzelsberger, Andreas Uhl

Abstract:

Iris codes contain bits with different entropy. This work investigates different strategies to reduce the size of iris code templates with the aim of reducing storage requirements and computational demand in the matching process. Besides simple subsampling schemes, also a binary multi-resolution representation as used in the JBIG hierarchical coding mode is assessed. We find that iris code template size can be reduced significantly while maintaining recognition accuracy. Besides, we propose a two-stage identification approach, using small-sized iris code templates in a pre-selection stage, and full resolution templates for final identification, which shows promising recognition behaviour.

Keywords: Iris recognition, compact iris code, fast matching, best bits, pre-selection identification, two-stage identification.

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

Authors: Luciano Garelli, Marco Schauer, Jorge D’Elia, Mario A. Storti, Sabine C. Langer

Abstract:

This paper discuss a coupling strategy of two different software packages to provide fluid structure interaction (FSI) analysis. The basic idea is to combine the advantages of the two codes to create a powerful FSI solver for two and three dimensional analysis. The fluid part is computed by a program called PETSc-FEM a software developed at Centro de Investigaci´on de M´etodos Computacionales –CIMEC. The structural part of the coupled process is computed by the research code elementary Parallel Solver – (ELPASO) of the Technische Universit¨at Braunschweig, Institut f¨ur Konstruktionstechnik (IK).

Keywords: Computational Fluid Dynamics (CFD), Fluid Structure Interaction (FSI), Finite Element Method (FEM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1899

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: Dewi Nasien, Siti S. Yuhaniz, Habibollah Haron

Abstract:

In a handwriting recognition problem, characters can be represented using chain codes. The main problem in representing characters using chain code is optimizing the length of the chain code. This paper proposes to use randomized algorithm to minimize the length of Freeman Chain Codes (FCC) generated from isolated handwritten characters. Feedforward neural network is used in the classification stage to recognize the image characters. Our test results show that by applying the proposed model, we reached a relatively high accuracy for the problem of isolated handwritten when tested on NIST database.

Keywords: Handwriting Recognition, Freeman Chain Code andFeedforward Backpropagation Neural Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1780

Authors: R. O. Ocaya, J. J. Terblans

Abstract:

The laws of Newtonian mechanics allow ab-initio molecular dynamics to model and simulate particle trajectories in material science by defining a differentiable potential function. This paper discusses some considerations for the coding of ab-initio programs for simulation on a standalone computer and illustrates the approach by C language codes in the context of embedded metallic atoms in the face-centred cubic structure. The algorithms use velocity-time integration to determine particle parameter evolution for up to several thousands of particles in a thermodynamical ensemble. Such functions are reusable and can be placed in a redistributable header library file. While there are both commercial and free packages available, their heuristic nature prevents dissection. In addition, developing own codes has the obvious advantage of teaching techniques applicable to new problems.

Keywords: C-language, molecular dynamics, simulation, embedded atom method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1370

Authors: E. H. N. Gashti, J. Razzaghi, K. Kujala

Abstract:

In general, codes and regulations consider seismic loads only for completed structures of the bridges while, evaluation of incomplete structure of bridges, especially those constructed by free cantilever method, under these loads is also of great importance. Hence, this research tried to study the behavior of incomplete structure of common bridge type (box girder bridge), in construction phase under vertical seismic loads. Subsequently, the paper provided suitable guidelines and solutions to resist this destructive phenomenon. Research results proved that use of preventive methods can significantly reduce the stresses resulted from vertical seismic loads in box cross sections to an acceptable range recommended by design codes.

Keywords: Box girder bridges, Prestress loads, Free cantilever method, Seismic loads, Construction phase.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1770

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

Abstract:

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

Keywords: Deep neural models, natural language inference, recognizing textual entailment, sentence-to-sentence relation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1413

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, capsule network, capacity optimization, character recognition, data augmentation; semantic segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 649

Authors: N. Zhang, J. S. Kuang, S. Mogili

Abstract:

To investigate seismic performance of beam-column knee joints, four full-scale reinforced concrete beam-column knee joints, which were fabricated to simulate those in as-built RC frame buildings designed to ACI 318-14 and ACI-ASCE 352R-02, were tested under reversed cyclic loading. In the experimental programme, particular emphasis was given to the effect of horizontal reinforcement (in format of inverted U-shape bars) on the shear strength and ductility capacity of knee joints. Test results are compared with those predicted by four seismic design codes, including ACI 318-14, EC8, NZS3101 and GB50010. It is seen that the current design codes of practice cannot accurately predict the shear strength of seismically designed knee joints.

Keywords: Large-scale tests, RC beam-column knee joints, seismic performance, shear strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1147

Authors: Michal Martinovič, Jaroslav Polec, Kvetoslava Kotuliaková

Abstract:

In this paper we proposed multistage adaptive ARQ/HARQ/HARQ scheme. This method combines pure ARQ (Automatic Repeat reQuest) mode in low channel bit error rate and hybrid ARQ method using two different Reed-Solomon codes in middle and high error rate conditions. It follows, that our scheme has three stages. The main goal is to increase number of states in adaptive HARQ methods and be able to achieve maximum throughput for every channel bit error rate. We will prove the proposal by calculation and then with simulations in land mobile satellite channel environment. Optimization of scheme system parameters is described in order to maximize the throughput in the whole defined Signal-to- Noise Ratio (SNR) range in selected channel environment.

Keywords: Signal-to-noise ratio, throughput, forward error correction (FEC), pure and hybrid automatic repeat request (ARQ).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1920

Authors: Hilal A. Fadhil, Syed A. Aljunid, R. Badlishah Ahmed

Abstract:

In this paper we study the use of a new code called Random Diagonal (RD) code for Spectral Amplitude Coding (SAC) optical Code Division Multiple Access (CDMA) networks, using Fiber Bragg-Grating (FBG), FBG consists of a fiber segment whose index of reflection varies periodically along its length. RD code is constructed using code level and data level, one of the important properties of this code is that the cross correlation at data level is always zero, which means that Phase intensity Induced Phase (PIIN) is reduced. We find that the performance of the RD code will be better than Modified Frequency Hopping (MFH) and Hadamard code It has been observed through experimental and theoretical simulation that BER for RD code perform significantly better than other codes. Proof –of-principle simulations of encoding with 3 channels, and 10 Gbps data transmission have been successfully demonstrated together with FBG decoding scheme for canceling the code level from SAC-signal.

Keywords: FBG, MFH, OCDMA, PIIN, BER.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1690

Authors: Michael Moeti, Khuliso Sigama, Thapelo Samuel Matlala

Abstract:

One of the principal challenges that the world is confronted with is insecurity. The crime rate is increasing exponentially, and protecting our physical assets, especially in the motorist sector, is becoming impossible when applying our own strength. The need to develop technological solutions that detect and report theft without any human interference is inevitable. This is critical, especially for vehicle owners, to ensure theft detection and speedy identification towards recovery efforts in cases where a vehicle is missing or attempted theft is taking place. The vehicle theft detection system uses Convolutional Neural Network (CNN) to recognize the driver's face captured using an installed mobile phone device. The location identification function uses a Global Positioning System (GPS) to determine the real-time location of the vehicle. Upon identification of the location, Global System for Mobile Communications (GSM) technology is used to report or notify the vehicle owner about the whereabouts of the vehicle. The installed mobile app was implemented by making use of Python as it is undoubtedly the best choice in machine learning. It allows easy access to machine learning algorithms through its widely developed library ecosystem. The graphical user interface was developed by making use of JAVA as it is better suited for mobile development. Google's online database (Firebase) was used as a means of storage for the application. The system integration test was performed using a simple percentage analysis. 60 vehicle owners participated in this study as a sample, and questionnaires were used in order to establish the acceptability of the system developed. The result indicates the efficiency of the proposed system, and consequently, the paper proposes that the use of the system can effectively monitor the vehicle at any given place, even if it is driven outside its normal jurisdiction. More so, the system can be used as a database to detect, locate and report missing vehicles to different security agencies.

Keywords: Convolutional Neural Network, CNN, location identification, tracking, GPS, GSM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 325

Authors: Shanxiong Chen, Xu Han, Xiaolong Wang, Hui Ma

Abstract:

Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.

Keywords: Recognition, CNN, convolutional neural network, Yi character, divergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 683

Authors: Preetam Kumar, Saswat Chakrabarti

Abstract:

Overloading is a technique to accommodate more number of users than the spreading factor N. This is a bandwidth efficient scheme to increase the number users in a fixed bandwidth. One of the efficient schemes to overload a CDMA system is to use two sets of orthogonal signal waveforms (O/O). The first set is assigned to the N users and the second set is assigned to the additional M users. An iterative interference cancellation technique is used to cancel interference between the two sets of users. In this paper, the performance of an overloading scheme in which the first N users are assigned Walsh-Hadamard orthogonal codes and extra users are assigned the same WH codes but overlaid by a fixed (quasi) bent sequence [11] is evaluated. This particular scheme is called Quasi- Orthogonal Sequence (QOS) O/O scheme, which is a part of cdma2000 standard [12] to provide overloading in the downlink using single user detector. QOS scheme are balance O/O scheme, where the correlation between any set-1 and set-2 users are equalized. The allowable overload of this scheme is investigated in the uplink on an AWGN and Rayleigh fading channels, so that the uncoded performance with iterative multistage interference cancellation detector remains close to the single user bound. It is shown that this scheme provides 19% and 11% overloading with SDIC technique for N= 16 and 64 respectively, with an SNR degradation of less than 0.35 dB as compared to single user bound at a BER of 0.00001. But on a Rayleigh fading channel, the channel overloading is 45% (29 extra users) at a BER of 0.0005, with an SNR degradation of about 1 dB as compared to single user performance for N=64. This is a significant amount of channel overloading on a Rayleigh fading channel.

Keywords: DS-CDMA, Iterative Interference CancellationOrthogonal codes, Overloading.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1671

Authors: Evgeniy Burlutskiy

Abstract:

The paper presents a one-dimensional transient mathematical model of compressible thermal multi-component gas mixture flows in pipes. The set of the mass, momentum and enthalpy conservation equations for gas phase is solved. Thermo-physical properties of multi-component gas mixture are calculated by solving the Equation of State (EOS) model. The Soave-Redlich-Kwong (SRK-EOS) model is chosen. Gas mixture viscosity is calculated on the basis of the Lee-Gonzales-Eakin (LGE) correlation. Numerical analysis on rapid decompression in conventional dry gases is performed by using the proposed mathematical model. The model is validated on measured values of the decompression wave speed in dry natural gas mixtures. All predictions show excellent agreement with the experimental data at high and low pressure. The presented model predicts the decompression in dry natural gas mixtures much better than GASDECOM and OLGA codes, which are the most frequently-used codes in oil and gas pipeline transport service.

Keywords: Mathematical model, Rapid Gas Decompression

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2946

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 665

Authors: G. Sai Kiran , A. Kailasa Rao, R . Pradeep Kumar

Abstract:

In recent years, the introduction of Pre Engineered Building (PEB) concept in the design of structures has helped in optimizing design. The adoptability of PEB in the place of Conventional Steel Building (CSB) design concept resulted in many advantages, including economy and easier fabrication. In this study, an industrial structure (Ware House) is analyzed and designed according to the Indian standards, IS 800-1984, IS 800-2007 and also by referring MBMA-96 and AISC-89. In this study, a structure with length 187m,width 40m,with clear height 8m and having R-Slope 1:10,isconsidered to carry out analysis& design for 2D frames (End frame, frame without crane and frame with 3 module cranes). The economy of the structure is discussed in terms of its weight comparison, between Indian codes (IS800-1984, IS800-2007) & American code (MBMA-96), & between Indian codes (IS800-1984, IS800-2007).

Keywords: AISC, Crane Beam, MBMA, Pre-Engineered-Buildings, Staad Pro, Utilization Ratio.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6763

Authors: J. R. Wang, Y. Chiang, W. S. Hsu, H. C. Chen, S. H. Chen, J. H. Yang, S. W. Chen, C. Shih

Abstract:

In this study, the RASCAL and ALOHA codes are used to establish an analysis methodology for hydrogen fluoride (HF) evaluation. There are three main steps in this study. First, the UF₆ data were collected. Second, one postulated case was analyzed by using the RASCAL and UF₆ data. This postulated case assumes that fire occurring and UF₆ is releasing from a building. Third, the results of RASCAL for HF mass were as the input data of ALOHA. Two postulated cases of HF were analyzed by using ALOHA code and the results of RASCAL. These postulated cases assume fire occurring and HF is releasing with no raining (Case 1) or raining (Case 2) condition. According to the analysis results of ALOHA, the HF concentration of Case 2 is smaller than Case 1. The results can be a reference for the preparing of emergency plans for the release of HF.

Keywords: RASCAL, ALOHA, UF6, hydrogen fluoride.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 696

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: Convolutional neural networks, coffee bean, peaberry, sorting, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1447

Authors: K. Murali Krishna, Abhijit Mitra, C. Ardil

Abstract:

This paper presents a single correlator RAKE receiver for direct sequence code division multiple access (DS-CDMA) systems. In conventional RAKE receivers, multiple correlators are used to despread the multipath signals and then to align and combine those signals in a later stage before making a bit decision. The simplified receiver structure presented here uses a single correlator and single code sequence generator to recover the multipaths. Modified Walsh- Hadamard codes are used here for data spreading that provides better uncorrelation properties for the multipath signals. The main advantage of this receiver structure is that it requires only a single correlator and a code generator in contrary to the conventional RAKE receiver concept with multiple correlators. It is shown in results that the proposed receiver achieves better bit error rates in comparison with the conventional one for more than one multipaths.

Keywords: RAKE receiver, Code division multiple access, ModifiedWalsh-Hadamard codes, Single correlator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3595

Authors: Siddhant Rao

Abstract:

Studies estimate that there will be 266,120 new cases of invasive breast cancer and 40,920 breast cancer induced deaths in the year of 2018 alone. Despite the pervasiveness of this affliction, the current process to obtain an accurate breast cancer prognosis is tedious and time consuming. It usually requires a trained pathologist to manually examine histopathological images and identify the features that characterize various cancer severity levels. We propose MITOS-RCNN: a region based convolutional neural network (RCNN) geared for small object detection to accurately grade one of the three factors that characterize tumor belligerence described by the Nottingham Grading System: mitotic count. Other computational approaches to mitotic figure counting and detection do not demonstrate ample recall or precision to be clinically viable. Our models outperformed all previous participants in the ICPR 2012 challenge, the AMIDA 2013 challenge and the MITOS-ATYPIA-14 challenge along with recently published works. Our model achieved an F- measure score of 0.955, a 6.11% improvement in accuracy from the most accurate of the previously proposed models.

Keywords: Object detection, histopathology, breast cancer, mitotic count, deep learning, computer vision.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1326

Authors: Peyman Amini Motlagh, Ali Pak

Abstract:

Seismic retrofitting of important structures is essential in seismological active zones. The importance is doubled when it comes to some buildings like schools, hospitals, bridges etc. because they are required to continue their serviceability even after a major earthquake. Generally, seismic retrofitting codes have paid little attention to retrofitting of foundations due to its construction complexity. In this paper different methods for seismic retrofitting of tall buildings’ foundations will be discussed and evaluated. Foundations are considered in three different categories. First, foundations those are in danger of liquefaction of their underlying soil. Second, foundations located on slopes in seismological active regions. Third, foundations designed according to former design codes and may show structural defects under earthquake loads. After describing different methods used in different countries for retrofitting of the existing foundations in seismological active regions, comprehensive comparison between these methods with regard to the above mentioned categories is carried out. This paper gives some guidelines to choose the best method for seismic retrofitting of tall buildings’ foundations in retrofitting projects.

Keywords: Existing foundation, landslide, liquefaction, seismic retrofitting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4246

Authors: W. S. Hsu, Y. Chiang, Y. S. Tseng, J. R. Wang, C. Shih, S. W. Chen

Abstract:

Kuosheng nuclear power plant (NPP) is a BWR/6 plant in Taiwan. There is more concern for the safety of NPPs in Taiwan after Japan Fukushima NPP disaster occurred. Hence, in order to estimate the safety of Kuosheng NPP spent fuel pool (SFP), by using TRACE, MELCOR, and SNAP codes, the safety analysis of Kuosheng NPP SFP was performed. There were two main steps in this research. First, the Kuosheng NPP SFP models were established. Second, the transient analysis of Kuosheng SFP was done by TRACE and MELCOR under the cooling system failure condition (Fukushima-like condition). The results showed that the calculations of MELCOR and TRACE were very similar in this case, and the fuel uncover happened roughly at 4^th day after the failure of cooling system. The above results indicated that Kuosheng NPP SFP may be unsafe in the case of long-term SBO situation. In addition, future calculations were needed to be done by the other codes like FRAPTRAN for the cladding calculations.

Keywords: TRACE, MELCOR, SNAP, spent fuel pool.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1529

Authors: Antonio Carlos Marques Alvim, Fernando Carvalho da Silva, Aquilino Senra Martinez

Abstract:

For a quick and accurate calculation of spatial neutron distribution in nuclear power reactors 3D nodal codes are usually used aiming at solving the neutron diffusion equation for a given reactor core geometry and material composition. These codes use a second order polynomial to represent the transverse leakage term. In this work, a nodal method based on the well known nodal expansion method (NEM), developed at COPPE, making use of this polynomial expansion was modified to treat the transverse leakage term for the external surfaces of peripheral reflector nodes. The proposed method was implemented into a computational system which, besides solving the diffusion equation, also solves the burnup equations governing the gradual changes in material compositions of the core due to fuel depletion. Results confirm the effectiveness of this modified treatment of peripheral nodes for practical purposes in PWR reactors.

Keywords: Transverse leakage, nodal expansion method, power density, PWR reactors

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1976

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: Artificial Intelligence, machine learning, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1181