Search results for: feature representation

Authors: Chien-Hung Chen, Yan-Chun Hsing, Yung-Chun Chang

Abstract:

The Internet has grown into a powerful medium for information dispersion and social interaction that leads to a rapid growth of social media which allows users to easily post their emotions and perspectives regarding certain topics online. Our research aims at using natural language processing and text mining techniques to explore the public emotions expressed on Twitter by analyzing the sentiment behind tweets. In this paper, we propose a composite kernel method that integrates tree kernel with the linear kernel to simultaneously exploit both the tree representation and the distributed emotion keyword representation to analyze the syntactic and content information in tweets. The experiment results demonstrate that our method can effectively detect public emotion of tweets while outperforming the other compared methods.

Keywords: Public emotion recognition, natural language processing, composite kernel, sentiment analysis, text mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 773

Authors: Mohammed Benbrahim, Adil Daoudi, Khalid Benjelloun, Aomar Ibenbrahim

Abstract:

The automatic discrimination of seismic signals is an important practical goal for earth-science observatories due to the large amount of information that they receive continuously. An essential discrimination task is to allocate the incoming signal to a group associated with the kind of physical phenomena producing it. In this paper, two classes of seismic signals recorded routinely in geophysical laboratory of the National Center for Scientific and Technical Research in Morocco are considered. They correspond to signals associated to local earthquakes and chemical explosions. The approach adopted for the development of an automatic discrimination system is a modular system composed by three blocs: 1) Representation, 2) Dimensionality reduction and 3) Classification. The originality of our work consists in the use of a new wavelet called "modified Mexican hat wavelet" in the representation stage. For the dimensionality reduction, we propose a new algorithm based on the random projection and the principal component analysis.

Keywords: Seismic signals, Wavelets, Dimensionality reduction, Artificial neural networks, Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1634

Authors: Roman V. Yampolskiy, Venu Govindaraju

Abstract:

Functioning of a biometric system in large part depends on the performance of the similarity measure function. Frequently a generalized similarity distance measure function such as Euclidian distance or Mahalanobis distance is applied to the task of matching biometric feature vectors. However, often accuracy of a biometric system can be greatly improved by designing a customized matching algorithm optimized for a particular biometric application. In this paper we propose a tailored similarity measure function for behavioral biometric systems based on the expert knowledge of the feature level data in the domain. We compare performance of a proposed matching algorithm to that of other well known similarity distance functions and demonstrate its superiority with respect to the chosen domain.

Keywords: Behavioral Biometrics, Euclidian Distance, Matching, Similarity Measure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1652

Authors: Zeitoun D. G., Thierry Dana-Picard

Abstract:

The study of a real function of two real variables can be supported by visualization using a Computer Algebra System (CAS). One type of constraints of the system is due to the algorithms implemented, yielding continuous approximations of the given function by interpolation. This often masks discontinuities of the function and can provide strange plots, not compatible with the mathematics. In recent years, point based geometry has gained increasing attention as an alternative surface representation, both for efficient rendering and for flexible geometry processing of complex surfaces. In this paper we present different artifacts created by mesh surfaces near discontinuities and propose a point based method that controls and reduces these artifacts. A least squares penalty method for an automatic generation of the mesh that controls the behavior of the chosen function is presented. The special feature of this method is the ability to improve the accuracy of the surface visualization near a set of interior points where the function may be discontinuous. The present method is formulated as a minimax problem and the non uniform mesh is generated using an iterative algorithm. Results show that for large poorly conditioned matrices, the new algorithm gives more accurate results than the classical preconditioned conjugate algorithm.

Keywords: Function singularities, mesh generation, point allocation, visualization, collocation least squares method, Augmented Lagrangian method, Uzawa's Algorithm, Preconditioned Conjugate Gradien

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1708

Authors: Bernd Kiefer, Abraham Gebru Tesfay, Dietrich Klakow

Abstract:

The motivation of our work is to detect different terrain types traversed by a robot based on acoustic data from the robot-terrain interaction. Different acoustic features and classifiers were investigated, such as Mel-frequency cepstral coefficient and Gamma-tone frequency cepstral coefficient for the feature extraction, and Gaussian mixture model and Feed forward neural network for the classification. We analyze the system’s performance by comparing our proposed techniques with some other features surveyed from distinct related works. We achieve precision and recall values between 87% and 100% per class, and an average accuracy at 95.2%. We also study the effect of varying audio chunk size in the application phase of the models and find only a mild impact on performance.

Keywords: Terrain classification, acoustic features, autonomous robots, feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1134

Authors: Mousa Mojarrad, Mashallah Abbasi Dezfouli, Amir Masoud Rahmani

Abstract:

Detection and recognition of the Human Body Composition and extraction their measures (width and length of human body) in images are a major issue in detecting objects and the important field in Image, Signal and Vision Computing in recent years. Finding people and extraction their features in Images are particularly important problem of object recognition, because people can have high variability in the appearance. This variability may be due to the configuration of a person (e.g., standing vs. sitting vs. jogging), the pose (e.g. frontal vs. lateral view), clothing, and variations in illumination. In this study, first, Human Body is being recognized in image then the measures of Human Body extract from the image.

Keywords: Analysis of image processing, canny edge detection, classification, feature extraction, human body recognition, segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2771

Authors: O. Z. Jasim

Abstract:

An accuracy digital map must satisfy the users for two main requirements, first, map must be visually readable and second, all the map elements must be in a good representation. These two requirements hold especially true for map generalization which aims at simplifying the representation of cartographic data. Different scales of maps are very important for any decision in any maps with different scales such as master plan and all the infrastructures maps in civil engineering. Cartographer cannot project the data onto a piece of paper, but he has to worry about its readability. The map layout of any geodatabase is very important, this layout is help to read, analyze or extract information from the map. There are many principles and guidelines of generalization that can be find in the cartographic literature. A manual reduction method for generalization depends on experience of map maker and therefore produces incompatible results. Digital generalization, rooted from conventional cartography, has become an increasing concern in both Geographic Information System (GIS) and mapping fields. This project is intended to review the state of the art of the new technology and help to understand the needs and plans for the implementation of digital generalization capability as well as increase the knowledge of production topographic maps.

Keywords: Cartography, digital generalization, mapping, GIS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1289

Authors: Ricardo Mestre

Abstract:

The soundscape stands out as an agglomeration of sounds available in the world, associated with different contexts and origins, being a theme studied by various areas of knowledge, seeking to guide their benefits and their consequences, contributing to the welfare of society and other ecosystems. With the objective for a greater recognition of sound reality, through the selection and differentiation of sounds, the soundscape studies focus on the contribution for a better tuning of the world and to the balance and well-being of humanity. Sound environment, produced and created in various ways, can provide various sources of information, contributing to the orientation of the human being, alerting and manipulating him during his daily journey, like small notifications received on a cell phone or other device with these features. In this way, it becomes possible to give sound its due importance in relation to the processes of individual representation, in manners of social, professional and emotional life. Ensuring an individual representation means providing the human being with new tools for the long process of reflection by recognizing his environment, the sounds that represent him, and his perspective on his respective function in it. In order to provide more information about the importance of the sound environment inherent to the individual reality, one introduces the term sound instance, in order to refer to the whole sound field existing in the individual's life, which is divided into four distinct subfields, but essential to the process of individual representation, called sound matrix, sound cycles, sound traces and sound interference. Alongside volunteers we were able to create six representations of sound instances, based on the individual perception of his/her life, focusing on the present, past and future. With this investigation it was possible to determine that sound instance has a tool for self-recognition, considering the statements of opinion about the experience from the volunteers, reflecting about the three time lines, based on memories, thoughts and wishes.

Keywords: Sound instance, soundscape, sound art, self-recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 579

Authors: P. Gnanasekar, A. Nagappan, S. Sharavanan, O. Saravanan, D. Vinodkumar, T. Elayabharathi, G. Karthik

Abstract:

In this paper we present the deep study about the Bio- Medical Images and tag it with some basic extracting features (e.g. color, pixel value etc). The classification is done by using a nearest neighbor classifier with various distance measures as well as the automatic combination of classifier results. This process selects a subset of relevant features from a group of features of the image. It also helps to acquire better understanding about the image by describing which the important features are. The accuracy can be improved by increasing the number of features selected. Various types of classifications were evolved for the medical images like Support Vector Machine (SVM) which is used for classifying the Bacterial types. Ant Colony Optimization method is used for optimal results. It has high approximation capability and much faster convergence, Texture feature extraction method based on Gabor wavelets etc..

Keywords: ACO Ant Colony Optimization, Correlogram, CCM Co-Occurrence Matrix, RTS Rough-Set theory

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3013

Authors: A. Sopharak, B. Uyyanonvara, S. Barman

Abstract:

Microaneurysm is a key indicator of diabetic retinopathy that can potentially cause damage to retina. Early detection and automatic quantification are the keys to prevent further damage. In this paper, which focuses on automatic microaneurysm detection in images acquired through non-dilated pupils, we present a series of experiments on feature selection and automatic microaneurysm pixel classification. We found that the best feature set is a combination of 10 features: the pixel-s intensity of shade corrected image, the pixel hue, the standard deviation of shade corrected image, DoG4, the area of the candidate MA, the perimeter of the candidate MA, the eccentricity of the candidate MA, the circularity of the candidate MA, the mean intensity of the candidate MA on shade corrected image and the ratio of the major axis length and minor length of the candidate MA. The overall sensitivity, specificity, precision, and accuracy are 84.82%, 99.99%, 89.01%, and 99.99%, respectively.

Keywords: Diabetic retinopathy, microaneurysm, naive Bayes classifier

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2190

Authors: Sokkhey Phauk, Takeo Okazaki

Abstract:

The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.

Keywords: Academic performance prediction system, prediction model, educational data mining, dominant factors, feature selection methods, student performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 979

Authors: B. Leela Devi, A. Sankar

Abstract:

The web’s increased popularity has included a huge amount of information, due to which automated web page classification systems are essential to improve search engines’ performance. Web pages have many features like HTML or XML tags, hyperlinks, URLs and text contents which can be considered during an automated classification process. It is known that Webpage classification is enhanced by hyperlinks as it reflects Web page linkages. The aim of this study is to reduce the number of features to be used to improve the accuracy of the classification of web pages. In this paper, a novel feature selection method using an improved Particle Swarm Optimization (PSO) using principle of evolution is proposed. The extracted features were tested on the WebKB dataset using a parallel Neural Network to reduce the computational cost.

Keywords: Web page classification, WebKB Dataset, Term Frequency-Inverse Document Frequency (TF-IDF), Particle Swarm Optimization (PSO).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3260

Authors: Zeinab Ghasemi, S. Amirhassan Monadjemi, Abbas Vafaei

Abstract:

This paper presents a comparative analysis of a new unsupervised PCA-based technique for steel plates texture segmentation towards defect detection. The proposed scheme called Variance Based Component Analysis or VBCA employs PCA for feature extraction, applies a feature reduction algorithm based on variance of eigenpictures and classifies the pixels as defective and normal. While the classic PCA uses a clusterer like Kmeans for pixel clustering, VBCA employs thresholding and some post processing operations to label pixels as defective and normal. The experimental results show that proposed algorithm called VBCA is 12.46% more accurate and 78.85% faster than the classic PCA.

Keywords: Principal Component Analysis; Variance Based Component Analysis; Defect Detection; Texture Segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1973

Authors: Marzuki Khalid, RubiyahYusof, AnisSalwaMohdKhairuddin

Abstract:

An automated wood recognition system is designed to classify tropical wood species.The wood features are extracted based on two feature extractors: Basic Grey Level Aura Matrix (BGLAM) technique and statistical properties of pores distribution (SPPD) technique. Due to the nonlinearity of the tropical wood species separation boundaries, a pre classification stage is proposed which consists ofKmeans clusteringand kernel discriminant analysis (KDA). Finally, Linear Discriminant Analysis (LDA) classifier and KNearest Neighbour (KNN) are implemented for comparison purposes. The study involves comparison of the system with and without pre classification using KNN classifier and LDA classifier.The results show that the inclusion of the pre classification stage has improved the accuracy of both the LDA and KNN classifiers by more than 12%.

Keywords: Tropical wood species, nonlinear data, featureextractors, classification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2000

Authors: Youngjae Jin, Daeshik Kim

Abstract:

This paper describes a cycle accurate simulation results of weight values learned by an auto-encoder behavior model in terms of pre-route simulation. Given the results we visualized the first layer representations with natural images. Many common deep learning threads have focused on learning high-level abstraction of unlabeled raw data by unsupervised feature learning. However, in the process of handling such a huge amount of data, the learning method’s computation complexity and time limited advanced research. These limitations came from the fact these algorithms were computed by using only single core CPUs. For this reason, parallel-based hardware, FPGAs, was seen as a possible solution to overcome these limitations. We adopted and simulated the ready-made auto-encoder to design a behavior model in VerilogHDL before designing hardware. With the auto-encoder behavior model pre-route simulation, we obtained the cycle accurate results of the parameter of each hidden layer by using MODELSIM. The cycle accurate results are very important factor in designing a parallel-based digital hardware. Finally this paper shows an appropriate operation of behavior model based pre-route simulation. Moreover, we visualized learning latent representations of the first hidden layer with Kyoto natural image dataset.

Keywords: Auto-encoder, Behavior model simulation, Digital hardware design, Pre-route simulation, Unsupervised feature learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2690

Authors: Peerapong Uthansakul, Monthippa Uthansakul

Abstract:

The rapid growth of e-Commerce services is significantly observed in the past decade. However, the method to verify the authenticated users still widely depends on numeric approaches. A new search on other verification methods suitable for online e-Commerce is an interesting issue. In this paper, a new online signature-verification method using angular transformation is presented. Delay shifts existing in online signatures are estimated by the estimation method relying on angle representation. In the proposed signature-verification algorithm, all components of input signature are extracted by considering the discontinuous break points on the stream of angular values. Then the estimated delay shift is captured by comparing with the selected reference signature and the error matching can be computed as a main feature used for verifying process. The threshold offsets are calculated by two types of error characteristics of the signature verification problem, False Rejection Rate (FRR) and False Acceptance Rate (FAR). The level of these two error rates depends on the decision threshold chosen whose value is such as to realize the Equal Error Rate (EER; FAR = FRR). The experimental results show that through the simple programming, employed on Internet for demonstrating e-Commerce services, the proposed method can provide 95.39% correct verifications and 7% better than DP matching based signature-verification method. In addition, the signature verification with extracting components provides more reliable results than using a whole decision making.

Keywords: Online signature verification, e-Commerce services, Angular transformation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1582

Authors: Nuawi M. Z., Lamin F., Ismail A. R., Abdullah S., Wahid Z.

Abstract:

A filter is used to remove undesirable frequency information from a dynamic signal. This paper shows that the Znotch filter filtering technique can be applied to remove the noise nuisance from a machining signal. In machining, the noise components were identified from the sound produced by the operation of machine components itself such as hydraulic system, motor, machine environment and etc. By correlating the noise components with the measured machining signal, the interested components of the measured machining signal which was less interfered by the noise, can be extracted. Thus, the filtered signal is more reliable to be analysed in terms of noise content compared to the unfiltered signal. Significantly, the I-kaz method i.e. comprises of three dimensional graphical representation and I-kaz coefficient, Z∞ could differentiate between the filtered and the unfiltered signal. The bigger space of scattering and the higher value of Z∞ demonstrated that the signal was highly interrupted by noise. This method can be utilised as a proactive tool in evaluating the noise content in a signal. The evaluation of noise content is very important as well as the elimination especially for machining operation fault diagnosis purpose. The Z-notch filtering technique was reliable in extracting noise component from the measured machining signal with high efficiency. Even though the measured signal was exposed to high noise disruption, the signal generated from the interaction between cutting tool and work piece still can be acquired. Therefore, the interruption of noise that could change the original signal feature and consequently can deteriorate the useful sensory information can be eliminated.

Keywords: Digital signal filtering, I-kaz method, Machiningmonitoring, Noise Cancelling, Sound

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1884

Authors: Tin Hninn Hninn Maung

Abstract:

This paper introduces a hand gesture recognition system to recognize real time gesture in unstrained environments. Efforts should be made to adapt computers to our natural means of communication: Speech and body language. A simple and fast algorithm using orientation histograms will be developed. It will recognize a subset of MAL static hand gestures. A pattern recognition system will be using a transforrn that converts an image into a feature vector, which will be compared with the feature vectors of a training set of gestures. The final system will be Perceptron implementation in MATLAB. This paper includes experiments of 33 hand postures and discusses the results. Experiments shows that the system can achieve a 90% recognition average rate and is suitable for real time applications.

Keywords: Hand gesture recognition, Orientation Histogram, Myanmar Alphabet Language, Perceptronnetwork, MATLAB.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4698

Authors: Deeman Yousif Mahmood, Mohammed Abdullah Hussein

Abstract:

The goal of a network-based intrusion detection system is to classify activities of network traffics into two major categories: normal and attack (intrusive) activities. Nowadays, data mining and machine learning plays an important role in many sciences; including intrusion detection system (IDS) using both supervised and unsupervised techniques. However, one of the essential steps of data mining is feature selection that helps in improving the efficiency, performance and prediction rate of proposed approach. This paper applies unsupervised K-means clustering algorithm with information gain (IG) for feature selection and reduction to build a network intrusion detection system. For our experimental analysis, we have used the new NSL-KDD dataset, which is a modified dataset for KDDCup 1999 intrusion detection benchmark dataset. With a split of 60.0% for the training set and the remainder for the testing set, a 2 class classifications have been implemented (Normal, Attack). Weka framework which is a java based open source software consists of a collection of machine learning algorithms for data mining tasks has been used in the testing process. The experimental results show that the proposed approach is very accurate with low false positive rate and high true positive rate and it takes less learning time in comparison with using the full features of the dataset with the same algorithm.

Keywords: Information Gain (IG), Intrusion Detection System (IDS), K-means Clustering, Weka.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2776

Authors: A. Kojah, A. Nacaroğlu

Abstract:

Single phase transmission lines are used to transfer data or energy between two users. Transient conditions such as switching operations and short circuit faults cause the generation of the fluctuation on the waveform to be transmitted. Spatial voltage distribution on the single phase transmission line may change owing to the position and duration of the short circuit fault in the system. In this paper, the state space representation of the single phase transmission line for short circuit fault and for various types of terminations is given. Since the transmission line is modeled in time domain using distributed parametric elements, the mathematical representation of the event is given in state space (time domain) differential equation form. It also makes easy to solve the problem because of the time and space dependent characteristics of the voltage variations on the distributed parametrically modeled transmission line.

Keywords: Energy transmission, transient effects, transmission line, transient voltage, RLC short circuit, single phase.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1168

Authors: M.Ghazvini, S. A. Monadjemi, N. Movahhedinia, K. Jamshidi

Abstract:

In this article, a method has been offered to classify normal and defective tiles using wavelet transform and artificial neural networks. The proposed algorithm calculates max and min medians as well as the standard deviation and average of detail images obtained from wavelet filters, then comes by feature vectors and attempts to classify the given tile using a Perceptron neural network with a single hidden layer. In this study along with the proposal of using median of optimum points as the basic feature and its comparison with the rest of the statistical features in the wavelet field, the relational advantages of Haar wavelet is investigated. This method has been experimented on a number of various tile designs and in average, it has been valid for over 90% of the cases. Amongst the other advantages, high speed and low calculating load are prominent.

Keywords: Defect detection, tile and ceramic quality inspection, wavelet transform, classification, neural networks, statistical features.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2377

Authors: Sing-Wu Liou, Yin-Fu Huang

Abstract:

For identifying the discriminative sequence features between exons and introns, a new paradigm, rescaled-range frameshift analysis (RRFA), was proposed. By RRFA, two new sequence features, the frameshift sensitivity (FS) and the accumulative penta-mer complexity (APC), were discovered which were further integrated into a new feature of larger scale, the persistency in anti-mutation (PAM). The feature-validation experiments were performed on six model organisms to test the power of discrimination. All the experimental results highly support that FS, APC and PAM were all distinguishing features between exons and introns. These identified new sequence features provide new insights into the sequence composition of genes and they have great potentials of forming a new basis for recognizing the exonintron boundaries in gene sequences.

Keywords: Exon-Intron Discrimination, Rescaled-Range Frameshift Analysis, Frameshift Sensitivity, Accumulative Sequence Complexity

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1174

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 1454

Authors: Seda Sahin, Emin Akata

Abstract:

Obturator Foramen is a specific structure in Pelvic bone images and recognition of it is a new concept in medical image processing. Moreover, segmentation of bone structures such as Obturator Foramen plays an essential role for clinical research in orthopedics. In this paper, we present a novel method to analyze the similarity between the substructures of the imaged region and a hand drawn template as a preprocessing step for computation of Pelvic bone rotation on hip radiographs. This method consists of integrated usage of Marker-controlled Watershed segmentation and Zernike moment feature descriptor and it is used to detect Obturator Foramen accurately. Marker-controlled Watershed segmentation is applied to separate Obturator Foramen from the background effectively. Then, Zernike moment feature descriptor is used to provide matching between binary template image and the segmented binary image for final extraction of Obturator Foramens. Finally, Pelvic bone rotation rate calculation for each hip radiograph is performed automatically to select and eliminate hip radiographs for further studies which depend on Pelvic bone angle measurements. The proposed method is tested on randomly selected 100 hip radiographs. The experimental results demonstrated that the proposed method is able to segment Obturator Foramen with 96% accuracy.

Keywords: Medical image analysis, marker-controlled watershed segmentation, segmentation of bone structures on hip radiographs, pelvic bone rotation rate, zernike moment feature descriptor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1993

Authors: Mohamed Abdel Fattah, Fuji Ren

Abstract:

This work proposes an approach to address automatic text summarization. This approach is a trainable summarizer, which takes into account several features, including sentence position, positive keyword, negative keyword, sentence centrality, sentence resemblance to the title, sentence inclusion of name entity, sentence inclusion of numerical data, sentence relative length, Bushy path of the sentence and aggregated similarity for each sentence to generate summaries. First we investigate the effect of each sentence feature on the summarization task. Then we use all features score function to train genetic algorithm (GA) and mathematical regression (MR) models to obtain a suitable combination of feature weights. The proposed approach performance is measured at several compression rates on a data corpus composed of 100 English religious articles. The results of the proposed approach are promising.

Keywords: Automatic Summarization, Genetic Algorithm, Mathematical Regression, Text Features.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2336

Authors: Paulo Fernando Silva Filho, Elcio Hideiti Shiguemori

Abstract:

The selection of specific landmarks for an Unmanned Aerial Vehicles’ Visual Navigation systems based on Automatic Landmark Recognition has significant influence on the precision of the system’s estimated position. At the same time, manual selection of the landmarks does not guarantee a high recognition rate, which would also result on a poor precision. This work aims to develop an automatic landmark selection that will take the image of the flight area and identify the best landmarks to be recognized by the Visual Navigation Landmark Recognition System. The criterion to select a landmark is based on features detected by ORB or AKAZE and edges information on each possible landmark. Results have shown that disposition of possible landmarks is quite different from the human perception.

Keywords: Clustering, edges, feature points, landmark selection, X-Means.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 819

Authors: Essam Al Daoud

Abstract:

Intrusion detection is a mechanism used to protect a system and analyse and predict the behaviours of system users. An ideal intrusion detection system is hard to achieve due to nonlinearity, and irrelevant or redundant features. This study introduces a new anomaly-based intrusion detection model. The suggested model is based on particle swarm optimisation and nonlinear, multi-class and multi-kernel support vector machines. Particle swarm optimisation is used for feature selection by applying a new formula to update the position and the velocity of a particle; the support vector machine is used as a classifier. The proposed model is tested and compared with the other methods using the KDD CUP 1999 dataset. The results indicate that this new method achieves better accuracy rates than previous methods.

Keywords: Feature selection, Intrusion detection, Support vector machine, Particle swarm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1990

Authors: Mona F. M. Mursi, Ghazy M.R. Assassa, Hatim A. Aboalsamh, Khaled Alghathbar

Abstract:

The challenge in the case of image authentication is that in many cases images need to be subjected to non malicious operations like compression, so the authentication techniques need to be compression tolerant. In this paper we propose an image authentication system that is tolerant to JPEG lossy compression operations. A scheme for JPEG grey scale images is proposed based on a data embedding method that is based on a secret key and a secret mapping vector in the frequency domain. An encrypted feature vector extracted from the image DCT coefficients, is embedded redundantly, and invisibly in the marked image. On the receiver side, the feature vector from the received image is derived again and compared against the extracted watermark to verify the image authenticity. The proposed scheme is robust against JPEG compression up to a maximum compression of approximately 80%,, but sensitive to malicious attacks such as cutting and pasting.

Keywords: Authentication, DCT, JPEG, Watermarking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Farshideh Einsele, Hassan Foroosh

Abstract:

In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation, style, illumination, and can suffer from perspective distortion. Pre-processing is performed to make the characters scale and rotation invariant. Since text degradations can not be appropriately defined using well-known geometric transformations such as translation, rotation, affine transformation and shearing, we use the whole character black pixels as our feature vector. Classification is performed with minimum distance classifier using the maximum likelihood criterion, which delivers very promising Character Recognition Rate (CRR) of 89%. We achieve considerably higher Word Recognition Rate (WRR) of 99% when using lower level linguistic knowledge about product words during the recognition process.

Keywords: Camera-based OCR, Feature extraction, Document and image processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2470

Authors: Nishant Rodrigues, Nicole Spanedda, Chilukuri K. Mohan, Arindam Chakraborty

Abstract:

A crucial objective in quantum chemistry is the computation of the energy levels of chemical systems. This task requires electron-repulsion integrals as inputs and the steep computational cost of evaluating these integrals poses a major numerical challenge in efficient implementation of quantum chemical software. This work presents a moment-based machine learning approach for the efficient evaluation of electron-repulsion integrals. These integrals were approximated using linear combinations of a small number of moments. Machine learning algorithms were applied to estimate the coefficients in the linear combination. A random forest approach was used to identify promising features using a recursive feature elimination approach, which performed best for learning the sign of each coefficient, but not the magnitude. A neural network with two hidden layers was then used to learn the coefficient magnitudes, along with an iterative feature masking approach to perform input vector compression, identifying a small subset of orbitals whose coefficients are sufficient for the quantum state energy computation. Finally, a small ensemble of neural networks (with a median rule for decision fusion) was shown to improve results when compared to a single network.

Keywords: Quantum energy calculations, atomic orbitals, electron-repulsion integrals, ensemble machine learning, random forests, neural networks, feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 188