Search results for: Fast Convolution

Authors: T. Alghamdi, G. Alaghband

Abstract:

In this paper we develop a model that couples Two Concurrent Convolution Neural Network with different filters (TC*CNN) for face recognition and compare its performance to an existing sequential CNN (base model). We also test and compare the quality and performance of the models on three datasets with various levels of complexity (easy, moderate, and difficult) and show that for the most complex datasets, edges will produce the most accurate and efficient results. We further show that in such cases while Support Vector Machine (SVM) models are fast, they do not produce accurate results.

Keywords: Convolution neural network, edges, face recognition, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 728

Authors: Ephraim Gower, Thato Tsalaile, Monageng Kgwadi, Malcolm Hawksford.

Abstract:

In this paper, the statistical properties of filtered or convolved signals are considered by deriving the resulting density functions as well as the exact mean and variance expressions given a prior knowledge about the statistics of the individual signals in the filtering or convolution process. It is shown that the density function after linear convolution is a mixture density, where the number of density components is equal to the number of observations of the shortest signal. For circular convolution, the observed samples are characterized by a single density function, which is a sum of products.

Keywords: Circular Convolution, linear Convolution, mixture density function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1516

Authors: Ghulam Murtaza, Kalsoom Farzana

Abstract:

The aim of this article is to narrate the utility of novel simulation approach i.e. convolution method to predict blood concentration of drug utilizing dissolution data of salbutamol sulphate microparticulate formulations with different release patterns (1:1, 1:2 and 1:3, drug:polymer). Dissolution apparatus II USP 2007 and 900 ml double distilled water stirrd at 50 rpm was employed for dissolution analysis. From dissolution data, blood drug concentration was determined, and in return predicted blood drug concentration data was used to calculate the pharmacokinetic parameters i.e. Cmax, Tmax, and AUC. Convolution is a good biwaiver technique; however its better utility needs it application in the conditions where biorelevant dissolution media are used.

Keywords: Convolution, Dissolution, Pharmacokinetics, Salbutamol sulphate

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2593

Authors: Mountassar Maamoun, Mehdi Neggazi, Abdelhamid Meraghni, Daoud Berkani

Abstract:

This paper presents a VLSI design approach of a highspeed and real-time 2-D Discrete Wavelet Transform computing. The proposed architecture, based on new and fast convolution approach, reduces the hardware complexity in addition to reduce the critical path to the multiplier delay. Furthermore, an advanced twodimensional (2-D) discrete wavelet transform (DWT) implementation, with an efficient memory area, is designed to produce one output in every clock cycle. As a result, a very highspeed is attained. The system is verified, using JPEG2000 coefficients filters, on Xilinx Virtex-II Field Programmable Gate Array (FPGA) device without accessing any external memory. The resulting computing rate is up to 270 M samples/s and the (9,7) 2-D wavelet filter uses only 18 kb of memory (16 kb of first-in-first-out memory) with 256×256 image size. In this way, the developed design requests reduced memory and provide very high-speed processing as well as high PSNR quality.

Keywords: Discrete Wavelet Transform (DWT), Fast Convolution, FPGA, VLSI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1965

Authors: Towfeeq Fairooz, Salim Istyaq

Abstract:

The passive electrical properties of a tissue depends on the intrinsic constituents and its structure, therefore by measuring the complex electrical impedance of the tissue it might be possible to obtain indicators of the tissue state or physiological activity [1]. Complete bio-impedance information relative to physiology and pathology of a human body and functional states of the body tissue or organs can be extracted by using a technique containing a fourelectrode measurement setup. This work presents the estimation measurement setup based on the four-electrode technique. First, the complex impedance is estimated by three different estimation techniques: Fourier, Sine Correlation and Digital De-convolution and then estimation errors for the magnitude, phase, reactance and resistance are calculated and analyzed for different levels of disturbances in the observations. The absolute values of relative errors are plotted and the graphical performance of each technique is compared.

Keywords: Electrical Impedance, Fast Fourier Transform, Additive White Gaussian Noise, Total Least Square, Digital De-Convolution, Sine-Correlation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2732

Authors: I Gede Puja Astawa, Yoedy Moegiharto, Ahmad Zainudin, Imam Dui Agus Salim, Nur Annisa Anggraeni

Abstract:

Performance of Orthogonal Frequency Division Multiplexing (OFDM) system can be improved by adding channel coding (error correction code) to detect and correct errors that occur during data transmission. One can use the convolution code. This paper present performance of OFDM using Space Time Block Codes (STBC) diversity technique use QAM modulation with code rate ½. The evaluation is done by analyzing the value of Bit Error Rate (BER) vs. Energy per Bit to Noise Power Spectral Density Ratio (Eb/No). This scheme is conducted 256 subcarrier transmits Rayleigh multipath channel in OFDM system. To achieve a BER of 10^-3 is required 10dB SNR in SISO-OFDM scheme. For 2x2 MIMO-OFDM scheme requires 10 dB to achieve a BER of 10^-3. For 4x4 MIMO-OFDM scheme requires 5 dB while adding convolution in a 4x4 MIMO-OFDM can improve performance up to 0 dB to achieve the same BER. This proves the existence of saving power by 3 dB of 4x4 MIMO-OFDM system without coding, power saving 7dB of 2x2 MIMO-OFDM and significant power savings from SISO-OFDM system

Keywords: Convolution code, OFDM, MIMO, QAM, BER.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3386

Authors: Marque Adrien, Delahaye Daniel, Marechal Pierre, Berry Isabelle

Abstract:

Wind direction and uncertainty are crucial in aircraft or unmanned aerial vehicle trajectories. By computing wind covariance matrices on each spatial grid point, these spatial grids can be defined as images with symmetric positive definite matrix elements. A data pre-processing step, a specific convolution, a specific max-pooling, and specific flatten layers are implemented to process such images. Then, the neural network is applied to spatial grids, whose elements are wind covariance matrices, to solve classification problems related to the feasibility of unmanned aerial vehicles based on wind direction and wind uncertainty.

Keywords: Wind direction, uncertainty level, Unmanned Aerial Vehicle, convolution neural network, SPD matrices.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 28

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In this paper, an approach to reduce the computation steps required by fast neural networksfor the searching process is presented. The principle ofdivide and conquer strategy is applied through imagedecomposition. Each image is divided into small in sizesub-images and then each one is tested separately usinga fast neural network. The operation of fast neuralnetworks based on applying cross correlation in thefrequency domain between the input image and theweights of the hidden neurons. Compared toconventional and fast neural networks, experimentalresults show that a speed up ratio is achieved whenapplying this technique to locate human facesautomatically in cluttered scenes. Furthermore, fasterface detection is obtained by using parallel processingtechniques to test the resulting sub-images at the sametime using the same number of fast neural networks. Incontrast to using only fast neural networks, the speed upratio is increased with the size of the input image whenusing fast neural networks and image decomposition.

Keywords: Fast Neural Networks, 2D-FFT, CrossCorrelation, Image decomposition, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2178

Authors: Gesine Hellwig

Abstract:

Functional imaging procedures for the non-invasive assessment of tissue microcirculation are highly requested, but require a mathematical approach describing the trans- and intercapillary passage of tracer particles. Up to now, two theoretical, for the moment different concepts have been established for tracer kinetic modeling of contrast agent transport in tissues: pharmacokinetic compartment models, which are usually written as coupled differential equations, and the indicator dilution theory, which can be generalized in accordance with the theory of lineartime- invariant (LTI) systems by using a convolution approach. Based on mathematical considerations, it can be shown that also in the case of an open two-compartment model well-known from functional imaging, the concentration-time course in tissue is given by a convolution, which allows a separation of the arterial input function from a system function being the impulse response function, summarizing the available information on tissue microcirculation. Due to this reason, it is possible to integrate the open two-compartment model into the system-theoretic concept of indicator dilution theory (IDT) and thus results known from IDT remain valid for the compartment approach. According to the long number of applications of compartmental analysis, even for a more general context similar solutions of the so-called forward problem can already be found in the extensively available appropriate literature of the seventies and early eighties. Nevertheless, to this day, within the field of biomedical imaging – not from the mathematical point of view – there seems to be a trench between both approaches, which the author would like to get over by exemplary analysis of the well-known model.

Keywords: Functional imaging, Tracer kinetic modeling, LTIsystem, Indicator dilution theory / convolution approach, Two-Compartment model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1417

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 2346

Authors: Phang Chang, Phang Piau

Abstract:

Wavelet transform or wavelet analysis is a recently developed mathematical tool in applied mathematics. In numerical analysis, wavelets also serve as a Galerkin basis to solve partial differential equations. Haar transform or Haar wavelet transform has been used as a simplest and earliest example for orthonormal wavelet transform. Since its popularity in wavelet analysis, there are several definitions and various generalizations or algorithms for calculating Haar transform. Fast Haar transform, FHT, is one of the algorithms which can reduce the tedious calculation works in Haar transform. In this paper, we present a modified fast and exact algorithm for FHT, namely Modified Fast Haar Transform, MFHT. The algorithm or procedure proposed allows certain calculation in the process decomposition be ignored without affecting the results.

Keywords: Fast Haar Transform, Haar transform, Wavelet analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3138

Authors: Salem Belhaj, Moncef Tagina

Abstract:

This paper is aimed at describing a delay-based endto- end (e2e) congestion control algorithm, called Very FAST TCP (VFAST), which is an enhanced version of FAST TCP. The main idea behind this enhancement is to smoothly estimate the Round-Trip Time (RTT) based on a nonlinear filter, which eliminates throughput and queue oscillation when RTT fluctuates. In this context, an evaluation of the suggested scheme through simulation is introduced, by comparing our VFAST prototype with FAST in terms of throughput, queue behavior, fairness, stability, RTT and adaptivity to changes in network. The achieved simulation results indicate that the suggested protocol offer better performance than FAST TCP in terms of RTT estimation and throughput.

Keywords: Fast tcp, RTT, delay estimation, delay-based congestion control, high speed TCP, large bandwidth delay product.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1731

Authors: Lenka Krulikovská, Jaroslav Polec, Tomáš Hirner

Abstract:

In this paper we present a novel method, which reduces the computational complexity of abrupt cut detection. We have proposed fast algorithm, where the similarity of frames within defined step is evaluated instead of comparing successive frames. Based on the results of simulation on large video collection, the proposed fast algorithm is able to achieve 80% reduction of needed frames comparisons compared to actually used methods without the shot cut detection accuracy degradation.

Keywords: Abrupt cut, fast algorithm, shot cut detection, Pearson correlation coefficient.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1746

Authors: Ijeoma Chinyere Ukonu

Abstract:

This research seeks to investigate how the globalisation of fast food has affected students’ food choice. A mixed method approach was used in this research; basically involving quantitative and qualitative methods. The quantitative method uses a self-completion questionnaire to randomly sample one hundred and four students; while the qualitative method uses a semi structured interview technique to survey four students on their knowledge and choice to consume fast food. A cross tabulation of variables and the Kruskal Wallis nonparametric test were used to analyse the quantitative data; while the qualitative data was analysed through deduction of themes, and trends from the interview transcribe. The findings revealed that globalisation has amplified the evolution of fast food, popularising it among students. Its global presence has affected students’ food choice and preference. Price, convenience, taste, and peer influence are some of the major factors affecting students’ choice of fast food. Though, students are familiar with the health effect of fast food and the significance of using food information labels for healthy choice making, their preference of fast food is more than homemade food.

Keywords: Fast food, food choice, globalisation, students.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9184

Authors: G. Hernandez-Maskivker, G. Ryan, M. Blazey, M. Pàmies

Abstract:

Waiting times and queues are a daily problem for theme parks. Fast lines or priority queues appear as a solution for a specific segment of customers, that is, tourists who are willing to pay to avoid waiting. This paper analyzes the fast line system and explores the factors that affect the decision to purchase a fast line pass. A greater understanding of these factors may help companies to design appropriate products and services. This conceptual paper was based on a literature review in marketing and consumer behavior. Additional research was identified in related disciplines such as leisure studies, psychology, and sociology. A conceptual framework of the factors influencing the decision to purchase a fast line pass is presented.

Keywords: Tourist behavior, fast lines, theme park, willing to pay.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4478

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, fast neural networks for object/face detection were presented in [1-3]. The speed up factor of these networks relies on performing cross correlation in the frequency domain between the input image and the weights of the hidden layer. But, these equations given in [1-3] for conventional and fast neural networks are not valid for many reasons presented here. In this paper, correct equations for cross correlation in the spatial and frequency domains are presented. Furthermore, correct formulas for the number of computation steps required by conventional and fast neural networks given in [1-3] are introduced. A new formula for the speed up ratio is established. Also, corrections for the equations of fast multi scale object/face detection are given. Moreover, commutative cross correlation is achieved. Simulation results show that sub-image detection based on cross correlation in the frequency domain is faster than classical neural networks.

Keywords: Conventional Neural Networks, Fast Neural Networks, Cross Correlation in the Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2478

Authors: Ahmad R. Naghsh-Nilchi, Latifeh Pourmohammadbagher

Abstract:

Both image steganography and image encryption have advantages and disadvantages. Steganograhy allows us to hide a desired image containing confidential information in a covered or host image while image encryption is decomposing the desired image to a non-readable, non-comprehended manner. The encryption methods are usually much more robust than the steganographic ones. However, they have a high visibility and would provoke the attackers easily since it usually is obvious from an encrypted image that something is hidden! The combination of steganography and encryption will cover both of their weaknesses and therefore, it increases the security. In this paper an image encryption method based on sinc-convolution along with using an encryption key of 128 bit length is introduced. Then, the encrypted image is covered by a host image using a modified version of JSteg steganography algorithm. This method could be applied to almost all image formats including TIF, BMP, GIF and JPEG. The experiment results show that our method is able to hide a desired image with high security and low visibility.

Keywords: Sinc Approximation, Image Encryption, Sincconvolution, Image Steganography, JSTEG.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1827

Authors: Christian Mayr, Holger Eisenreich, Stephan Henker, René Schüffny

Abstract:

Image convolution similar to the receptive fields found in mammalian visual pathways has long been used in conventional image processing in the form of Gabor masks. However, no VLSI implementation of parallel, multi-layered pulsed processing has been brought forward which would emulate this property. We present a technical realization of such a pulsed image processing scheme. The discussed IC also serves as a general testbed for VLSI-based pulsed information processing, which is of interest especially with regard to the robustness of representing an analog signal in the phase or duration of a pulsed, quasi-digital signal, as well as the possibility of direct digital manipulation of such an analog signal. The network connectivity and processing properties are reconfigurable so as to allow adaptation to various processing tasks.

Keywords: Neural image processing, pulse computation application, pulsed Gabor convolution, VLSI pulse routing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1390

Authors: A. Nachour, L. Ouzizi, Y. Aoura

Abstract:

Recent developments on multi-agent system have brought a new research field on image processing. Several algorithms are used simultaneously and improved in deferent applications while new methods are investigated. This paper presents a new automatic method for edge detection using several agents and many different actions. The proposed multi-agent system is based on parallel agents that locally perceive their environment, that is to say, pixels and additional environmental information. This environment is built using Vector Field Convolution that attract free agent to the edges. Problems of partial, hidden or edges linking are solved with the cooperation between agents. The presented method was implemented and evaluated using several examples on different synthetic and medical images. The obtained experimental results suggest that this approach confirm the efficiency and accuracy of detected edge.

Keywords: Edge detection, medical MR images, multi-agent systems, vector field convolution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1902

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

In recent years, fast neural networks for object/face detection have been introduced based on cross correlation in the frequency domain between the input matrix and the hidden weights of neural networks. In our previous papers [3,4], fast neural networks for certain code detection was introduced. It was proved in [10] that for fast neural networks to give the same correct results as conventional neural networks, both the weights of neural networks and the input matrix must be symmetric. This condition made those fast neural networks slower than conventional neural networks. Another symmetric form for the input matrix was introduced in [1-9] to speed up the operation of these fast neural networks. Here, corrections for the cross correlation equations (given in [13,15,16]) to compensate for the symmetry condition are presented. After these corrections, it is proved mathematically that the number of computation steps required for fast neural networks is less than that needed by classical neural networks. Furthermore, there is no need for converting the input data into symmetric form. Moreover, such new idea is applied to increase the speed of neural networks in case of processing complex values. Simulation results after these corrections using MATLAB confirm the theoretical computations.

Keywords: Fast Code/Data Detection, Neural Networks, Cross Correlation, real/complex values.

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

Authors: Fituri H Belgassem, Abdulbasit Nigrat, Seddeeq Ghrari

Abstract:

In this paper, the construction of fast algorithms for the computation of Periodic Walsh Piecewise-Linear PWL transform and the Periodic Haar Piecewise-Linear PHL transform will be presented. Algorithms for the computation of the inverse transforms are also proposed. The matrix equation of the PWL and PHL transforms are introduced. Comparison of the computational requirements for the periodic piecewise-linear transforms and other orthogonal transforms shows that the periodic piecewise-linear transforms require less number of operations than some orthogonal transforms such as the Fourier, Walsh and the Discrete Cosine transforms.

Keywords: Piece wise linear transforms, Fast transforms, Fast algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1660

Authors: Israa Al-Neami, Ali J. Al-Askery, Martin Johnston, Charalampos Tsimenidis

Abstract:

In this paper, we focus on the design of a multi-line copper wire (MLCW) communication system. First, we construct our proposed MLCW channel and verify its characteristics based on the Kolmogorov-Smirnov test. In addition, we apply Middleton class A impulsive noise (IN) to the copper channel for further investigation. Second, the MIMO G.fast system is adopted utilizing the proposed MLCW channel model and is compared to a single line G-fast system. Second, the performance of the coded system is obtained utilizing concatenated interleaved Reed-Solomon (RS) code with four-dimensional trellis-coded modulation (4D TCM), and compared to the single line G-fast system. Simulations are obtained for high quadrature amplitude modulation (QAM) constellations that are commonly used with G-fast communications, the results demonstrate that the bit error rate (BER) performance of the coded MLCW system shows an improvement compared to the single line G-fast systems.

Keywords: G.fast, Middleton Class A impulsive noise, mitigation techniques, copper channel Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 702

Authors: Vincent King Soon Wong, Hong Seng Ng, Florinna Sim

Abstract:

Negative Bias Temperature Instability (NBTI) is one of the critical degradation mechanisms in semiconductor device reliability that causes shift in the threshold voltage (Vth). However, thorough understanding of this reliability failure mechanism is still unachievable due to a recovery characteristic known as NBTI recovery. This paper will demonstrate the severity of NBTI recovery as well as one of the effective methods used to mitigate, which is the minimization of measurement system delays. Comparison was done in between two measurement systems that have significant differences in measurement delays to show how NBTI recovery causes result deviations and how fast measurement systems can mitigate NBTI recovery. Another method to minimize NBTI recovery without the influence of measurement system known as Fast Wafer Level Reliability (FWLR) NBTI was also done to be used as reference.

Keywords: Fast vs slow BTI, Fast wafer level reliability, Negative bias temperature instability, NBTI measurement system, metal-oxide-semiconductor field-effect transistor, MOSFET, NBTI recovery, reliability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1663

Authors: Nur Syarafina Binti Othman, Tsubasa Jindo, Makato Yamada, Miho Tsuyama, Hitoshi Nakano

Abstract:

A novel method to produce a fast high voltage solid states switch using Insulated Gate Bipolar Transistors (IGBTs) is presented for discharge-pumped gas lasers. The IGBTs are connected in series to achieve a high voltage rating. An avalanche transistor is used as the gate driver. The fast pulse generated by the avalanche transistor quickly charges the large input capacitance of the IGBT, resulting in a switch out of a fast high-voltage pulse. The switching characteristic of fast-high voltage solid state switch has been estimated in the multi-stage series-connected IGBT with the applied voltage of several tens of kV. Electrical circuit diagram and the mythology of fast-high voltage solid state switch as well as experimental results obtained are presented.

Keywords: High voltage, IGBT, Solid states switch.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5912

Authors: Shruti Taksali

Abstract:

This paper focuses on the analysis of Nanoptenna for extreme fast communication. The Nanoptenna is basically a nano antenna designed for communication at optical range of frequencies. Since, this range of frequencies includes the visible spectrum of the light, so there is a high possibility of the data transfer at high rates and extreme fast communication (XFC). The shape chosen for the analysis is a bow tie structure due to its various characteristics of electric field enhancement.

Keywords: Nanoptenna, communication, optical range, XFC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1355

Authors: Hazem M. El-Bakry, Qiangfu Zhao

Abstract:

Recently, neural networks have shown good results for detection of a certain pattern in a given image. In our previous papers [1-5], a fast algorithm for pattern detection using neural networks was presented. Such algorithm was designed based on cross correlation in the frequency domain between the input image and the weights of neural networks. Image conversion into symmetric shape was established so that fast neural networks can give the same results as conventional neural networks. Another configuration of symmetry was suggested in [3,4] to improve the speed up ratio. In this paper, our previous algorithm for fast neural networks is developed. The frequency domain cross correlation is modified in order to compensate for the symmetric condition which is required by the input image. Two new ideas are introduced to modify the cross correlation algorithm. Both methods accelerate the speed of the fast neural networks as there is no need for converting the input image into symmetric one as previous. Theoretical and practical results show that both approaches provide faster speed up ratio than the previous algorithm.

Keywords: Fast Pattern Detection, Neural Networks, Modified Cross Correlation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1744

Authors: Hazem M. El-Bakry

Abstract:

Principal Component Analysis (PCA) has many different important applications especially in pattern detection such as face detection / recognition. Therefore, for real time applications, the response time is required to be as small as possible. In this paper, new implementation of PCA for fast face detection is presented. Such new implementation is designed based on cross correlation in the frequency domain between the input image and eigenvectors (weights). Simulation results show that the proposed implementation of PCA is faster than conventional one.

Keywords: Fast Face Detection, PCA, Cross Correlation, Frequency Domain

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1796

Authors: Boontee Kruatrachue, Narongchai Moongfangklang, Kritawan Siriboon

Abstract:

This paper describes fast and efficient method for page segmentation of document containing nonrectangular block. The segmentation is based on edge following algorithm using small window of 16 by 32 pixels. This segmentation is very fast since only border pixels of paragraph are used without scanning the whole page. Still, the segmentation may contain error if the space between them is smaller than the window used in edge following. Consequently, this paper reduce this error by first identify the missed segmentation point using direction information in edge following then, using X-Y cut at the missed segmentation point to separate the connected columns. The advantage of the proposed method is the fast identification of missed segmentation point. This methodology is faster with fewer overheads than other algorithms that need to access much more pixel of a document.

Keywords: Contour Direction Technique, Missed SegmentationPoints, Page Segmentation, Recursive X-Y Cut Technique

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2782

Authors: Yeon-Jea Cho, Sang-Uk Park, Won-Chul Choi, Dong-Jo Park

Abstract:

This paper proposes a smart design strategy for a sequential detector to reliably detect the primary user-s signal, especially in fast fading environments. We study the computation of the log-likelihood ratio for coping with a fast changing received signal and noise sample variances, which are considered random variables. First, we analyze the detectability of the conventional generalized log-likelihood ratio (GLLR) scheme when considering fast changing statistics of unknown parameters caused by fast fading effects. Secondly, we propose an efficient sensing algorithm for performing the sequential probability ratio test in a robust and efficient manner when the channel statistics are unknown. Finally, the proposed scheme is compared to the conventional method with simulation results with respect to the average number of samples required to reach a detection decision.

Keywords: Cognitive radio, fast fading, sequential detection, spectrum sensing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1743

Authors: Jiajun Wang, Xiaoge Li

Abstract:

The purpose of the aspect-level sentiment analysis task is to identify the sentiment polarity of aspects in a sentence. Currently, most methods mainly focus on using neural networks and attention mechanisms to model the relationship between aspects and context, but they ignore the dependence of words in different ranges in the sentence, resulting in deviation when assigning relationship weight to other words other than aspect words. To solve these problems, we propose an aspect-level sentiment analysis model that combines a multi-channel convolutional network and graph convolutional network (GCN). Firstly, the context and the degree of association between words are characterized by Long Short-Term Memory (LSTM) and self-attention mechanism. Besides, a multi-channel convolutional network is used to extract the features of words in different ranges. Finally, a convolutional graph network is used to associate the node information of the dependency tree structure. We conduct experiments on four benchmark datasets. The experimental results are compared with those of other models, which shows that our model is better and more effective.

Keywords: Aspect-level sentiment analysis, attention, multi-channel convolution network, graph convolution network, dependency tree.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 505