Search results for: Latent values/vectors

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

We present probabilistic multinomial Dirichlet classification model for multidimensional data and Gaussian process priors. Here, we have considered efficient computational method that can be used to obtain the approximate posteriors for latent variables and parameters needed to define the multiclass Gaussian process classification model. We first investigated the process of inducing a posterior distribution for various parameters and latent function by using the variational Bayesian approximations and important sampling method, and next we derived a predictive distribution of latent function needed to classify new samples. The proposed model is applied to classify the synthetic multivariate dataset in order to verify the performance of our model. Experiment result shows that our model is more accurate than the other approximation methods.

Keywords: Multinomial dirichlet classification model, Gaussian process priors, variational Bayesian approximation, Importance sampling, approximate posterior distribution, Marginal likelihood evidence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1614

Authors: Bagher Rahimpour Cami, Hamid Hassanpour, Hoda Mashayekhi

Abstract:

Nowadays websites provide a vast number of resources for users. Recommender systems have been developed as an essential element of these websites to provide a personalized environment for users. They help users to retrieve interested resources from large sets of available resources. Due to the dynamic feature of user preference, constructing an appropriate model to estimate the user preference is the major task of recommender systems. Profile matching and latent factors are two main approaches to identify user preference. In this paper, we employed the latent factor and profile matching to cluster the user profile and identify user preference, respectively. The method uses the Distance Dependent Chines Restaurant Process as a Bayesian nonparametric framework to extract the latent factors from the user profile. These latent factors are mapped to user interests and a weighted distribution is used to identify user preferences. We evaluate the proposed method using a real-world data-set that contains news tweets of a news agency (BBC). The experimental results and comparisons show the superior recommendation accuracy of the proposed approach related to existing methods, and its ability to effectively evolve over time.

Keywords: Content-based recommender systems, dynamic user modeling, extracting user interests, predicting user preference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 815

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we propose the variational EM inference algorithm for the multi-class Gaussian process classification model that can be used in the field of human behavior recognition. This algorithm can drive simultaneously both a posterior distribution of a latent function and estimators of hyper-parameters in a Gaussian process classification model with multiclass. Our algorithm is based on the Laplace approximation (LA) technique and variational EM framework. This is performed in two steps: called expectation and maximization steps. First, in the expectation step, using the Bayesian formula and LA technique, we derive approximately the posterior distribution of the latent function indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. Second, in the maximization step, using a derived posterior distribution of latent function, we compute the maximum likelihood estimator for hyper-parameters of a covariance matrix necessary to define prior distribution for latent function. These two steps iteratively repeat until a convergence condition satisfies. Moreover, we apply the proposed algorithm with human action classification problem using a public database, namely, the KTH human action data set. Experimental results reveal that the proposed algorithm shows good performance on this data set.

Keywords: Bayesian rule, Gaussian process classification model with multiclass, Gaussian process prior, human action classification, laplace approximation, variational EM algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: Hamed Alqahtani, Manolya Kavakli-Thorne

Abstract:

The large pose discrepancy is one of the critical challenges in face recognition during video surveillance. Due to the entanglement of pose attributes with identity information, the conventional approaches for pose-independent representation lack in providing quality results in recognizing largely posed faces. In this paper, we propose a practical approach to disentangle the pose attribute from the identity information followed by synthesis of a face using a classifier network in latent space. The proposed approach employs a modified generative adversarial network framework consisting of an encoder-decoder structure embedded with a classifier in manifold space for carrying out factorization on the latent encoding. It can be further generalized to other face and non-face attributes for real-life video frames containing faces with significant attribute variations. Experimental results and comparison with state of the art in the field prove that the learned representation of the proposed approach synthesizes more compelling perceptual images through a combination of adversarial and classification losses.

Keywords: Video surveillance, disentanglement, face detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 607

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: Natural Language Inference, explanation generation, variational auto-encoder, generative model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 694

Authors: M. Faraji, F. Berroug

Abstract:

A one-dimensional mathematical model was developed in order to analyze and optimize the latent heat storage wall. The governing equations for energy transport were developed by using the enthalpy method and discretized with volume control scheme. The resulting algebraic equations were next solved iteratively by using TDMA algorithm. A series of numerical investigations were conducted in order to examine the effects of the thickness of the PCM layer on the thermal behavior of the proposed heating system. Results are obtained for thermal gain and temperature fluctuation. The charging discharging process was also presented and analyzed.

Keywords: Phase change material, Building, Concrete, Latent heat, Thermal control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2145

Authors: Manal Mhada, BrahimEzzahiri, Ouafae Benlhabib

Abstract:

Seventy-nine accessions, including two local wild species (Chenopodium album and C. murale) and several cultivated quinoa lines developed through recurrent selection in Morocco were screened for their resistance against Peronospora farinose, the causal agent of downy mildew disease. The method of artificial inoculation on detached healthy leaves taken from the middle stage of the plant was used. Screened accessions showed different levels of quantitative resistance to downy mildew as they were scored through the calculation of their area under disease progress curve and their two resistance components, the incubation period and the latent period. Significant differences were found between accessions regarding the three criteria (Incubation Period, Latent Period and Area Under Diseases Progress Curve). Accessions M2a and S938/1 were ranked resistant as they showed the longest Incubation Period (7 days) and Latent Period (12 days) and the lowest area under diseases progress curve (4). Therefore, M24 is the most susceptible accession as it has presented the highest area under diseases progress curve (34.5) and the shortest Incubation Period (1 day) and Latent Period (3 days). In parallel to this evaluation approach, the accession resistance was confirmed under the field conditions through natural infection by using the tree-leaf method. The high correlation found between detached leaf inoculation method and field screening under natural infection allows us to use this laboratory technique with sureness in further selection works.

Keywords: Detached leaf inoculation, Downy mildew, Field screening, Quinoa.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2510

Authors: Sunee Pongpinigpinyo, Wanchai Rivepiboon

Abstract:

Word sense disambiguation is one of the most important open problems in natural language processing applications such as information retrieval and machine translation. Many approach strategies can be employed to resolve word ambiguity with a reasonable degree of accuracy. These strategies are: knowledgebased, corpus-based, and hybrid-based. This paper pays attention to the corpus-based strategy that employs an unsupervised learning method for disambiguation. We report our investigation of Latent Semantic Indexing (LSI), an information retrieval technique and unsupervised learning, to the task of Thai noun and verbal word sense disambiguation. The Latent Semantic Indexing has been shown to be efficient and effective for Information Retrieval. For the purposes of this research, we report experiments on two Thai polysemous words, namely  /hua4/ and /kep1/ that are used as a representative of Thai nouns and verbs respectively. The results of these experiments demonstrate the effectiveness and indicate the potential of applying vector-based distributional information measures to semantic disambiguation.

Keywords: Distributional semantics, Latent Semantic Indexing, natural language processing, Polysemous words, unsupervisedlearning, Word Sense Disambiguation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1814

Authors: W. Fethallah, L. Chraibi, N. Sefiani

Abstract:

The present paper is concerned with a statistical approach involving latent and manifest variables applied in order to assess the organization's social responsibility performance. The main idea is to develop an assessment tool and a measurement of the Social Responsibility Performance, enabling the company to characterize her performance regarding to the ISO 26000 standard's seven core subjects. For this, we conceptualize a structural equation modeling (SEM) which describes various causal connections between the Social Responsibility’s components. The SEM’s resolution is based on the Partial Least squares (PLS) method and the implementation is running in the XLSTAT software.

Keywords: Corporate social responsibility, latent and manifest variable, partial least squares, structural equation model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1224

Authors: M.Radmehr, S.M.Anisheh, I.Yousefian

Abstract:

In this work a new offline signature recognition system based on Radon Transform, Fractal Dimension (FD) and Support Vector Machine (SVM) is presented. In the first step, projections of original signatures along four specified directions have been performed using radon transform. Then, FDs of four obtained vectors are calculated to construct a feature vector for each signature. These vectors are then fed into SVM classifier for recognition of signatures. In order to evaluate the effectiveness of the system several experiments are carried out. Offline signature database from signature verification competition (SVC) 2004 is used during all of the tests. Experimental result indicates that the proposed method achieved high accuracy rate in signature recognition.

Keywords: Fractal Dimension, Offline Signature Recognition, Radon Transform, Support Vector Machine

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2601

Authors: Qiang Niu, Linzhang Lu

Abstract:

Restarted GMRES methods augmented with approximate eigenvectors are widely used for solving large sparse linear systems. Recently a new scheme of augmenting with error approximations is proposed. The main aim of this paper is to develop a restarted GMRES method augmented with the combination of harmonic Ritz vectors and error approximations. We demonstrate that the resulted combination method can gain the advantages of two approaches: (i) effectively deflate the small eigenvalues in magnitude that may hamper the convergence of the method and (ii) partially recover the global optimality lost due to restarting. The effectiveness and efficiency of the new method are demonstrated through various numerical examples.

Keywords: Arnoldi process, GMRES, Krylov subspace, systems of linear equations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1938

Authors: Subramaniam Chandran

Abstract:

The significance of psychology in studying politics is embedded in philosophical issues as well as behavioural pursuits. For the former is often associated with Sigmund Freud and his followers. The latter is inspired by the writings of Harold Lasswell. Political psychology or psychopolitics has its own impression on political thought ever since it deciphers the concept of human nature and political propaganda. More importantly, psychoanalysis views political thought as a textual content which needs to explore the latent from the manifest content. In other words, it reads the text symptomatically and interprets the hidden truth. This paper explains the paradigm of dream interpretation applied by Freud. The dream work is a process which has four successive activities: condensation, displacement, representation and secondary revision. The texts dealing with political though can also be interpreted on these principles. Freud's method of dream interpretation draws its source after the hermeneutic model of philological research. It provides theoretical perspective and technical rules for the interpretation of symbolic structures. The task of interpretation remains a discovery of equivalence of symbols and actions through perpetual analogies. Psychoanalysis can help in studying political thought in two ways: to study the text distortion, Freud's dream interpretation is used as a paradigm exploring the latent text from its manifest text; and to apply Freud's psychoanalytic concepts and theories ranging from individual mind to civilization, religion, war and politics.

Keywords: Psychoanalysis, political thought, dreaminterpretation, latent content, manifest content

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1562

Authors: Tudor Barbu

Abstract:

An automatic moment-based texture segmentation approach is proposed in this paper. First, we describe the related work in this computer vision domain. Our texture feature extraction, the first part of the texture recognition process, produces a set of moment-based feature vectors. For each image pixel, a texture feature vector is computed as a sequence of area moments. Then, an automatic pixel classification approach is proposed. The feature vectors are clustered using an unsupervised classification algorithm, the optimal number of clusters being determined using a measure based on validation indexes. From the resulted pixel classes one determines easily the desired texture regions of the image.

Keywords: Image segmentation, moment-based texture analysis, automatic classification, validity indexes.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2379

Authors: Min Kook Choi, Hyun Gyu Lee, Ryan You, Byeong-Seok Shin, Sang-Chul Lee

Abstract:

Wireless capsule Endoscopy (WCE) has rapidly shown its wide applications in medical domain last ten years thanks to its noninvasiveness for patients and support for thorough inspection through a patient-s entire digestive system including small intestine. However, one of the main barriers to efficient clinical inspection procedure is that it requires large amount of effort for clinicians to inspect huge data collected during the examination, i.e., over 55,000 frames in video. In this paper, we propose a method to compute meaningful motion changes of WCE by analyzing the obtained video frames based on regional optical flow estimations. The computed motion vectors are used to remove duplicate video frames caused by WCE-s imaging nature, such as repetitive forward-backward motions from peristaltic movements. The motion vectors are derived by calculating directional component vectors in four local regions. Our experiments are performed on small intestine area, which is of main interest to clinical experts when using WCEs, and our experimental results show significant frame reductions comparing with a simple frame-to-frame similarity-based image reduction method.

Keywords: Wireless capsule endoscopy, optical flow, duplicated image, duplicated frame.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1693

Authors: Eric Jiang

Abstract:

As a popular rank-reduced vector space approach, Latent Semantic Indexing (LSI) has been used in information retrieval and other applications. In this paper, an LSI-based content vector model for text classification is presented, which constructs multiple augmented category LSI spaces and classifies text by their content. The model integrates the class discriminative information from the training data and is equipped with several pertinent feature selection and text classification algorithms. The proposed classifier has been applied to email classification and its experiments on a benchmark spam testing corpus (PU1) have shown that the approach represents a competitive alternative to other email classifiers based on the well-known SVM and naïve Bayes algorithms.

Keywords: Feature Selection, Latent Semantic Indexing, Text Classification, Vector Space Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1885

Authors: J. Davoodi, F. Katouzi

Abstract:

The aim of this research was to calculate the thermal properties of Au3Ni Nanowire. The molecular dynamics (MD) simulation technique was used to obtain the effect of radius size on the energy, the melting temperature and the latent heat of fusion at the isobaric-isothermal (NPT) ensemble. The Quantum Sutton-Chen (Q-SC) many body interatomic potentials energy have been used for Gold (Au) and Nickel (Ni) elements and a mixing rule has been devised to obtain the parameters of these potentials for nanowire stats. Our MD simulation results show the melting temperature and latent heat of fusion increase upon increasing diameter of nanowire. Moreover, the cohesive energy decreased with increasing diameter of nanowire.

Keywords: Au3Ni Nanowire, Thermal properties, Molecular dynamics simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2008

Authors: Nasrul Amri Mohd Amin, Martin Belusko, Frank Bruno

Abstract:

PCMs have always been viewed as a suitable candidate for off peak thermal storage, particularly for refrigeration systems, due to the high latent energy densities of these materials. However, due to the need to have them encapsulated within a container this density is reduced. Furthermore, PCMs have a low thermal conductivity which reduces the useful amount of energy which can be stored. To consider these factors, the true energy storage density of a PCM system was proposed and optimised for PCMs encapsulated in slabs. Using a validated numerical model of the system, a parametric study was undertaken to investigate the impact of the slab thickness, gap between slabs and the mass flow rate. The study showed that, when optimised, a PCM system can deliver a true energy storage density between 53% and 83% of the latent energy density of the PCM.

Keywords: Phase change material, refrigeration, sustainability, thermal energy storage.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2299

Authors: Hossein Nezamabadi-pour, Saeid Saryazdi

Abstract:

In this paper, we present a new and effective image indexing technique that extracts features directly from DCT domain. Our proposed approach is an object-based image indexing. For each block of size 8*8 in DCT domain a feature vector is extracted. Then, feature vectors of all blocks of image using a k-means algorithm is clustered into groups. Each cluster represents a special object of the image. Then we select some clusters that have largest members after clustering. The centroids of the selected clusters are taken as image feature vectors and indexed into the database. Also, we propose an approach for using of proposed image indexing method in automatic image classification. Experimental results on a database of 800 images from 8 semantic groups in automatic image classification are reported.

Keywords: Object-based image retrieval, DCT domain, Image indexing, Image classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2025

Authors: Shin-Hyung Cho, Dong-Kyu Kim, Seung-Young Kho

Abstract:

Truck-involved crashes have higher crash severity than non-truck-involved crashes. There have been many studies about the frequency of crashes and the development of severity models, but those studies only analyzed the relationship between observed variables. To identify why more people are injured or killed when trucks are involved in the crash, we must examine to quantify the complex causal relationship between severity of the crash and risk factors by adopting the latent factors of crashes. The aim of this study was to develop a structural equation or model based on truck-involved and non-truck-involved crashes, including five latent variables, i.e. a crash factor, environmental factor, road factor, driver’s factor, and severity factor. To clarify the unique characteristics of truck-involved crashes compared to non-truck-involved crashes, a confirmatory analysis method was used. To develop the model, we extracted crash data from 10,083 crashes on Korean freeways from 2008 through 2014. The results showed that the most significant variable affecting the severity of a crash is the crash factor, which can be expressed by the location, cause, and type of the crash. For non-truck-involved crashes, the crash and environment factors increase severity of the crash; conversely, the road and driver factors tend to reduce severity of the crash. For truck-involved crashes, the driver factor has a significant effect on severity of the crash although its effect is slightly less than the crash factor. The multiple group analysis employed to analyze the differences between the heterogeneous groups of drivers.

Keywords: Crash severity, structural equation modeling, truck-involved crashes, multiple group analysis, crash on freeway.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1340

Authors: Mayank Shakya, Soundra Pandian. K. K

Abstract:

A linear feedback shift register (LFSR) is proposed which targets to reduce the power consumption from within. It reduces the power consumption during testing of a Circuit Under Test (CUT) at two stages. At first stage, Control Logic (CL) makes the clocks of the switching units of the register inactive for a time period when output from them is going to be same as previous one and thus reducing unnecessary switching of the flip-flops. And at second stage, the LFSR reorders the test vectors by interchanging the bit with its next and closest neighbor bit. It keeps fault coverage capacity of the vectors unchanged but reduces the Total Hamming Distance (THD) so that there is reduction in power while shifting operation.

Keywords: Linear Feedback Shift Register, Total Hamming Distance, Fault Coverage, Control Logic

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2026

Authors: M. Analoui, M. Fadavi Amiri

Abstract:

The design of a pattern classifier includes an attempt to select, among a set of possible features, a minimum subset of weakly correlated features that better discriminate the pattern classes. This is usually a difficult task in practice, normally requiring the application of heuristic knowledge about the specific problem domain. The selection and quality of the features representing each pattern have a considerable bearing on the success of subsequent pattern classification. Feature extraction is the process of deriving new features from the original features in order to reduce the cost of feature measurement, increase classifier efficiency, and allow higher classification accuracy. Many current feature extraction techniques involve linear transformations of the original pattern vectors to new vectors of lower dimensionality. While this is useful for data visualization and increasing classification efficiency, it does not necessarily reduce the number of features that must be measured since each new feature may be a linear combination of all of the features in the original pattern vector. In this paper a new approach is presented to feature extraction in which feature selection, feature extraction, and classifier training are performed simultaneously using a genetic algorithm. In this approach each feature value is first normalized by a linear equation, then scaled by the associated weight prior to training, testing, and classification. A knn classifier is used to evaluate each set of feature weights. The genetic algorithm optimizes a vector of feature weights, which are used to scale the individual features in the original pattern vectors in either a linear or a nonlinear fashion. By this approach, the number of features used in classifying can be finely reduced.

Keywords: Feature reduction, genetic algorithm, pattern classification, nearest neighbor rule classifiers (k-NNR).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1768

Authors: Lakshmi Pujitha Dachuri, Nalini Uppala

Abstract:

In many applications retransmissions of lost packets are not permitted. OFDM is a multi-carrier modulation scheme having excellent performance which allows overlapping in frequency domain. With OFDM there is a simple way of dealing with multipath relatively simple DSP algorithms.

 In this paper, an image frame is compressed using DWT, and the compressed data is arranged in data vectors, each with equal number of coefficients. These vectors are quantized and binary coded to get the bit steams, which are then packetized and intelligently mapped to the OFDM system. Based on one-bit channel state information at the transmitter, the descriptions in order of descending priority are assigned to the currently good channels such that poorer sub-channels can only affect the lesser important data vectors. We consider only one-bit channel state information available at the transmitter, informing only about the sub-channels to be good or bad. For a good sub-channel, instantaneous received power should be greater than a threshold P_th. Otherwise, the sub-channel is in fading state and considered bad for that batch of coefficients. In order to reduce the system power consumption, the mapped descriptions onto the bad sub channels are dropped at the transmitter. The binary channel state information gives an opportunity to map the bit streams intelligently and to save a reasonable amount of power. By using MAT LAB simulation we can analysis the performance of our proposed scheme, in terms of system energy saving without compromising the received quality in terms of peak signal-noise ratio.

Keywords: Binary channel state, Channel state feedback, DWT-OFDM system, Energy saving, Fading broadcast channel.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2810

Authors: T. Kusuma, K. Ashwini

Abstract:

This paper presents a real time video surveillance system which is capable of tracking multiple real time objects using Polar Vector Median (PVM) and Block Coding Modes (BCM) with Global Motion Compensation (GMC). This strategy works in the packed area and furthermore utilizes the movement vectors and BCM from the compressed bit stream to perform real time object tracking. We propose to do this in view of the neighboring Motion Vectors (MVs) using a method called PVM. Since GM adds to the object’s native motion, for accurate tracking, it is important to remove GM from the MV field prior to further processing. The proposed method is tested on a number of standard sequences and the results show its advantages over some of the current modern methods.

Keywords: Block coding mode, global motion compensation, object tracking, polar vector median, video surveillance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 748

Authors: M. Jändel

Abstract:

A new conceptual architecture for low-level neural pattern recognition is presented. The key ideas are that the brain implements support vector machines and that support vectors are represented as memory patterns in competitive queuing memories. A binary classifier is built from two competitive queuing memories holding positive and negative valence training examples respectively. The support vector machine classification function is calculated in synchronized evaluation cycles. The kernel is computed by bisymmetric feed-forward networks feed by sensory input and by competitive queuing memories traversing the complete sequence of support vectors. Temporary summation generates the output classification. It is speculated that perception apparatus in the brain reuses structures that have evolved for enabling fluent execution of prepared action sequences so that pattern recognition is built on internalized motor programmes.

Keywords: Competitive queuing model, Olfactory system, Pattern recognition, Support vector machine, Thalamus

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1369

Authors: Muhammad Kamil Abdullah, Khazaimatol S Subari, Justin Leo Cheang Loong, Nurul Nadia Ahmad

Abstract:

This paper discusses the effectiveness of the EEG signal for human identification using four or less of channels of two different types of EEG recordings. Studies have shown that the EEG signal has biometric potential because signal varies from person to person and impossible to replicate and steal. Data were collected from 10 male subjects while resting with eyes open and eyes closed in 5 separate sessions conducted over a course of two weeks. Features were extracted using the wavelet packet decomposition and analyzed to obtain the feature vectors. Subsequently, the neural networks algorithm was used to classify the feature vectors. Results show that, whether or not the subjects- eyes were open are insignificant for a 4– channel biometrics system with a classification rate of 81%. However, for a 2–channel system, the P4 channel should not be included if data is acquired with the subjects- eyes open. It was observed that for 2– channel system using only the C3 and C4 channels, a classification rate of 71% was achieved.

Keywords: Biometric, EEG, Wavelet Packet Decomposition, NeuralNetworks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3028

Authors: Daniel Morariu, Lucian N. Vintan, Volker Tresp

Abstract:

Text categorization is the problem of classifying text documents into a set of predefined classes. After a preprocessing step the documents are typically represented as large sparse vectors. When training classifiers on large collections of documents, both the time and memory restrictions can be quite prohibitive. This justifies the application of features selection methods to reduce the dimensionality of the document-representation vector. Four feature selection methods are evaluated: Random Selection, Information Gain (IG), Support Vector Machine (called SVM_FS) and Genetic Algorithm with SVM (GA_FS). We showed that the best results were obtained with SVM_FS and GA_FS methods for a relatively small dimension of the features vector comparative with the IG method that involves longer vectors, for quite similar classification accuracies. Also we present a novel method to better correlate SVM kernel-s parameters (Polynomial or Gaussian kernel).

Keywords: Features selection, learning with kernels, support vector machine, genetic algorithms and classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1539

Authors: Amna Javed, Hisashi Masuda, Youji Kohda

Abstract:

This study examines the value analysis in Islamic and conventional banking services in Pakistan. Many scholars have focused on co-creation of values in services but mainly economic values not non-economic. As Islamic banking is based on Islamic principles that are more concerned with non-economic values (well-being, partnership, fairness, trust worthy, and justice) than economic values as money in terms of interest.  This study is important to know the providers point of view about the co-created values, because, it may be more sustainable and appropriate for today’s unpredictable socio-economic environment. Data were collected from 4 banks (2 Islamic and 2 conventional banks). Text mining technique is applied for data analysis, and values with 100% occurrences in Islamic banking are chosen. The results reflect that Islamic banking is more centric towards non-economic values than economic values and it promotes team work and partnership concept by applying Islamic spirit and trust worthiness concept.

Keywords: Economic values, Islamic banking, Non-economic values, Value system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3257

Authors: M. M. Abutaleb, A. Hamdy, M. E. Abuelwafa, E. M. Saad

Abstract:

Optical flow is a research topic of interest for many years. It has, until recently, been largely inapplicable to real-time applications due to its computationally expensive nature. This paper presents a new reliable flow technique which is combined with a motion detection algorithm, from stationary camera image streams, to allow flow-based analyses of moving entities, such as rigidity, in real-time. The combination of the optical flow analysis with motion detection technique greatly reduces the expensive computation of flow vectors as compared with standard approaches, rendering the method to be applicable in real-time implementation. This paper describes also the hardware implementation of a proposed pipelined system to estimate the flow vectors from image sequences in real time. This design can process 768 x 576 images at a very high frame rate that reaches to 156 fps in a single low cost FPGA chip, which is adequate for most real-time vision applications.

Keywords: Optical flow, motion detection, real-time systems, FPGA.

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

Authors: Lv Meibo, Naqvi Najam Abbas, Hina Arshad, Li YanJun

Abstract:

This research contribution is drafted to present the orbit design, orbit propagator and geomagnetic field estimator for the nanosatellites specifically for the upcoming CUBESAT, ICUBE-1 of the Institute of Space Technology (IST), Islamabad, Pakistan. The ICUBE mission is designed for the low earth orbit at the approximate height of 700KM. The presented research endeavor designs the Keplarian elements for ICUBE-1 orbit while incorporating the mission requirements and propagates the orbit using J2 perturbations, The attitude determination system of the ICUBE-1 consists of attitude determination sensors like magnetometer and sun sensor. The Geomagnetic field estimator is developed according to the model of International Geomagnetic Reference Field (IGRF) for comparing the magnetic field measurements by the magnetometer for attitude determination. The output of the propagator namely the Keplarians position and velocity vectors and the magnetic field vectors are compared and verified with the same scenario generated in the  Satellite Tool Kit (STK).

Keywords: CUBESAT, Geomagnetic Field, ICUBE-1, Orbit Propagator, Satellite.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3611

Authors: Sidi Yang, Haiyi Zhang

Abstract:

Twitter is a microblogging platform, where millions of users daily share their attitudes, views, and opinions. Using a probabilistic Latent Dirichlet Allocation (LDA) topic model to discern the most popular topics in the Twitter data is an effective way to analyze a large set of tweets to find a set of topics in a computationally efficient manner. Sentiment analysis provides an effective method to show the emotions and sentiments found in each tweet and an efficient way to summarize the results in a manner that is clearly understood. The primary goal of this paper is to explore text mining, extract and analyze useful information from unstructured text using two approaches: LDA topic modelling and sentiment analysis by examining Twitter plain text data in English. These two methods allow people to dig data more effectively and efficiently. LDA topic model and sentiment analysis can also be applied to provide insight views in business and scientific fields.

Keywords: Text mining, Twitter, topic model, sentiment analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1808