Search results for: Wavelet encoder

Authors: Raquel Ramos López, Anissa El-Khattabi, Ana Lucila Sandoval Orozco, Luis Javier García Villalba

Abstract:

An increasing number of mobile devices with integrated cameras has meant that most digital video comes from these devices. These digital videos can be made anytime, anywhere and for different purposes. They can also be shared on the Internet in a short period of time and may sometimes contain recordings of illegal acts. The need to reliably trace the origin becomes evident when these videos are used for forensic purposes. This work proposes an algorithm to identify the brand and model of mobile device which generated the video. Its procedure is as follows: after obtaining the relevant video information, a classification algorithm based on sensor noise and Wavelet Transform performs the aforementioned identification process. We also present experimental results that support the validity of the techniques used and show promising results.

Keywords: Digital video, forensics analysis, key frame, mobile device, PRNU, sensor noise, source identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1199

Authors: S. Anbumozhi, P. S. Manoharan

Abstract:

Medical Image fusion plays a vital role in medical field to diagnose the brain tumors which can be classified as benign or malignant. It is the process of integrating multiple images of the same scene into a single fused image to reduce uncertainty and minimizing redundancy while extracting all the useful information from the source images. Fuzzy logic is used to fuse two brain MRI images with different vision. The fused image will be more informative than the source images. The texture and wavelet features are extracted from the fused image. The multilevel Adaptive Neuro Fuzzy Classifier classifies the brain tumors based on trained and tested features. The proposed method achieved 80.48% sensitivity, 99.9% specificity and 99.69% accuracy. Experimental results obtained from fusion process prove that the use of the proposed image fusion approach shows better performance while compared with conventional fusion methodologies.

Keywords: Image fusion, Fuzzy rules, Neuro-fuzzy classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3060

Authors: Soroosh Rezazadeh, Mehran Yazdi

Abstract:

In this paper, a robust digital image watermarking scheme for copyright protection applications using the singular value decomposition (SVD) is proposed. In this scheme, an entropy masking model has been applied on the host image for the texture segmentation. Moreover, the local luminance and textures of the host image are considered for watermark embedding procedure to increase the robustness of the watermarking scheme. In contrast to all existing SVD-based watermarking systems that have been designed to embed visual watermarks, our system uses a pseudo-random sequence as a watermark. We have tested the performance of our method using a wide variety of image processing attacks on different test images. A comparison is made between the results of our proposed algorithm with those of a wavelet-based method to demonstrate the superior performance of our algorithm.

Keywords: Watermarking, copyright protection, singular value decomposition, entropy masking, texture segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1767

Authors: I. Hosni, L. Bennaceur Farah, N. Saber, R Bennaceur

Abstract:

Soil moisture content is a key variable in many environmental sciences. Even though it represents a small proportion of the liquid freshwater on Earth, it modulates interactions between the land surface and the atmosphere, thereby influencing climate and weather. Accurate modeling of the above processes depends on the ability to provide a proper spatial characterization of soil moisture. The measurement of soil moisture content allows assessment of soil water resources in the field of hydrology and agronomy. The second parameter in interaction with the radar signal is the geometric structure of the soil. Most traditional electromagnetic models consider natural surfaces as single scale zero mean stationary Gaussian random processes. Roughness behavior is characterized by statistical parameters like the Root Mean Square (RMS) height and the correlation length. Then, the main problem is that the agreement between experimental measurements and theoretical values is usually poor due to the large variability of the correlation function, and as a consequence, backscattering models have often failed to predict correctly backscattering. In this study, surfaces are considered as band-limited fractal random processes corresponding to a superposition of a finite number of one-dimensional Gaussian process each one having a spatial scale. Multiscale roughness is characterized by two parameters, the first one is proportional to the RMS height, and the other one is related to the fractal dimension. Soil moisture is related to the complex dielectric constant. This multiscale description has been adapted to two-dimensional profiles using the bi-dimensional wavelet transform and the Mallat algorithm to describe more correctly natural surfaces. We characterize the soil surfaces and sub-surfaces by a three layers geo-electrical model. The upper layer is described by its dielectric constant, thickness, a multiscale bi-dimensional surface roughness model by using the wavelet transform and the Mallat algorithm, and volume scattering parameters. The lower layer is divided into three fictive layers separated by an assumed plane interface. These three layers were modeled by an effective medium characterized by an apparent effective dielectric constant taking into account the presence of air pockets in the soil. We have adopted the 2D multiscale three layers small perturbations model including, firstly air pockets in the soil sub-structure, and then a vegetable canopy in the soil surface structure, that is to simulate the radar backscattering. A sensitivity analysis of backscattering coefficient dependence on multiscale roughness and new soil moisture has been performed. Later, we proposed to change the dielectric constant of the multilayer medium because it takes into account the different moisture values of each layer in the soil. A sensitivity analysis of the backscattering coefficient, including the air pockets in the volume structure with respect to the multiscale roughness parameters and the apparent dielectric constant, was carried out. Finally, we proposed to study the behavior of the backscattering coefficient of the radar on a soil having a vegetable layer in its surface structure.

Keywords: Multiscale, bi-dimensional, wavelets, SPM, backscattering, multilayer, air pockets, vegetable.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 609

Authors: Rosalyn R. Porle, Ali Chekima, Farrah Wong, G. Sainarayanan

Abstract:

Arms detection is one of the fundamental problems in human motion analysis application. The arms are considered as the most challenging body part to be detected since its pose and speed varies in image sequences. Moreover, the arms are usually occluded with other body parts such as the head and torso. In this paper, histogram-based skin colour segmentation is proposed to detect the arms in image sequences. Six different colour spaces namely RGB, rgb, HSI, TSL, SCT and CIELAB are evaluated to determine the best colour space for this segmentation procedure. The evaluation is divided into three categories, which are single colour component, colour without luminance and colour with luminance. The performance is measured using True Positive (TP) and True Negative (TN) on 250 images with manual ground truth. The best colour is selected based on the highest TN value followed by the highest TP value.

Keywords: image colour analysis, image motion analysis, skin, wavelet transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1567

Authors: Jun Wan, Zehua Chen, Yingwu Chen, Zhidong Bai

Abstract:

Classification is an interesting problem in functional data analysis (FDA), because many science and application problems end up with classification problems, such as recognition, prediction, control, decision making, management, etc. As the high dimension and high correlation in functional data (FD), it is a key problem to extract features from FD whereas keeping its global characters, which relates to the classification efficiency and precision to heavens. In this paper, a novel automatic method which combined Genetic Algorithm (GA) and classification algorithm to extract classification features is proposed. In this method, the optimal features and classification model are approached via evolutional study step by step. It is proved by theory analysis and experiment test that this method has advantages in improving classification efficiency, precision and robustness whereas using less features and the dimension of extracted classification features can be controlled.

Keywords: Classification, functional data, feature extraction, genetic algorithm, wavelet.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1557

Authors: J. Kavitha, S. Sowmyayani, P. Arockia Jansi Rani

Abstract:

In this paper, a shot boundary detection method is presented using octagon square search pattern. The color, edge, motion and texture features of each frame are extracted and used in shot boundary detection. The motion feature is extracted using octagon square search pattern. Then, the transition detection method is capable of detecting the shot or non-shot boundaries in the video using the feature weight values. Experimental results are evaluated in TRECVID video test set containing various types of shot transition with lighting effects, object and camera movement within the shots. Further, this paper compares the experimental results of the proposed method with existing methods. It shows that the proposed method outperforms the state-of-art methods for shot boundary detection.

Keywords: Content-based indexing and retrieval, cut transition detection, discrete wavelet transform, shot boundary detection, video source.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1001

Authors: K.Mala, V.Sadasivam, S.Alagappan

Abstract:

Advances in clinical medical imaging have brought about the routine production of vast numbers of medical images that need to be analyzed. As a result an enormous amount of computer vision research effort has been targeted at achieving automated medical image analysis. Computed Tomography (CT) is highly accurate for diagnosing liver tumors. This study aimed to evaluate the potential role of the wavelet and the neural network in the differential diagnosis of liver tumors in CT images. The tumors considered in this study are hepatocellular carcinoma, cholangio carcinoma, hemangeoma and hepatoadenoma. Each suspicious tumor region was automatically extracted from the CT abdominal images and the textural information obtained was used to train the Probabilistic Neural Network (PNN) to classify the tumors. Results obtained were evaluated with the help of radiologists. The system differentiates the tumor with relatively high accuracy and is therefore clinically useful.

Keywords: Fuzzy c means clustering, texture analysis, probabilistic neural network, LVQ neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2991

Authors: Yang Zhang, Jian He

Abstract:

Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper presents sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for CHD prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.

Keywords: Bi-LSTM, CHD, coronary heart disease, ECG, electrocardiogram, ResNet, sliding window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 341

Authors: K. L. Mak, P. Peng

Abstract:

This paper investigates the problem of automated defect detection for textile fabrics and proposes a new optimal filter design method to solve this problem. Gabor Wavelet Network (GWN) is chosen as the major technique to extract the texture features from textile fabrics. Based on the features extracted, an optimal Gabor filter can be designed. In view of this optimal filter, a new semi-supervised defect detection scheme is proposed, which consists of one real-valued Gabor filter and one smoothing filter. The performance of the scheme is evaluated by using an offline test database with 78 homogeneous textile images. The test results exhibit accurate defect detection with low false alarm, thus showing the effectiveness and robustness of the proposed scheme. To evaluate the detection scheme comprehensively, a prototyped detection system is developed to conduct a real time test. The experiment results obtained confirm the efficiency and effectiveness of the proposed detection scheme.

Keywords: Defect detection, Filtering, Gabor function, Gaborwavelet networks, Textile fabrics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2362

Authors: Ali Pour Yazdanpanah, Farideh Foroozandeh Shahraki, Emma Regentova

Abstract:

The reconstruction from sparse-view projections is one of important problems in computed tomography (CT) limited by the availability or feasibility of obtaining of a large number of projections. Traditionally, convex regularizers have been exploited to improve the reconstruction quality in sparse-view CT, and the convex constraint in those problems leads to an easy optimization process. However, convex regularizers often result in a biased approximation and inaccurate reconstruction in CT problems. Here, we present a nonconvex, Lipschitz continuous and non-smooth regularization model. The CT reconstruction is formulated as a nonconvex constrained L1 − L2 minimization problem and solved through a difference of convex algorithm and alternating direction of multiplier method which generates a better result than L0 or L1 regularizers in the CT reconstruction. We compare our method with previously reported high performance methods which use convex regularizers such as TV, wavelet, curvelet, and curvelet+TV (CTV) on the test phantom images. The results show that there are benefits in using the nonconvex regularizer in the sparse-view CT reconstruction.

Keywords: Computed tomography, sparse-view reconstruction, L1 −L2 minimization, non-convex, difference of convex functions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2035

Authors: Monika Garg, Lillie Dewan

Abstract:

Three novel and significant contributions are made in this paper Firstly, non-recursive formulation of Haar connection coefficients, pioneered by the present authors is presented, which can be computed very efficiently and avoid stack and memory overflows. Secondly, the generalized approach for state analysis of singular bilinear time-invariant (TI) and time-varying (TV) systems is presented; vis-˜a-vis diversified and complex works reported by different authors. Thirdly, a generalized approach for parameter estimation of bilinear TI and TV systems is also proposed. The unified framework of the proposed method is very significant in that the digital hardware once-designed can be used to perform the complex tasks of state analysis and parameter estimation of different types of bilinear systems single-handedly. The simplicity, effectiveness and generalized nature of the proposed method is established by applying it to different types of bilinear systems for the two tasks.

Keywords: Bilinear Systems, Haar Wavelet, Haar ConnectionCoefficients, Parameter Estimation, Singular Bilinear Systems, StateAnalysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1579

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: Convolutional neural network, discrete wavelet transform, deep learning, heart sound classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1149

Authors: S. Shefali, S. M. Deshpande, S. G. Tamhankar

Abstract:

Now a days, a significant part of commercial and governmental organisations like museums, cultural organizations, libraries, commercial enterprises, etc. invest intensively in new technologies for image digitization, digital libraries, image archiving and retrieval. Hence image authorization, authentication and security has become prime need. In this paper, we present a semi-fragile watermarking scheme for color images. The method converts the host image into YIQ color space followed by application of orthogonal dual domains of DCT and DWT transforms. The DCT helps to separate relevant from irrelevant image content to generate silent image features. DWT has excellent spatial localisation to help aid in spatial tamper characterisation. Thus image adaptive watermark is generated based of image features which allows the sharp detection of microscopic changes to locate modifications in the image. Further, the scheme utilises the multipurpose watermark consisting of soft authenticator watermark and chrominance watermark. Which has been proved fragile to some predefined processing like intentinal fabrication of the image or forgery and robust to other incidental attacks caused in the communication channel.

Keywords: Cryptography, Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT), Watermarking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2043

Authors: Sudhakar.R, Jayaraman.S

Abstract:

Large volumes of fingerprints are collected and stored every day in a wide range of applications, including forensics, access control etc. It is evident from the database of Federal Bureau of Investigation (FBI) which contains more than 70 million finger prints. Compression of this database is very important because of this high Volume. The performance of existing image coding standards generally degrades at low bit-rates because of the underlying block based Discrete Cosine Transform (DCT) scheme. Over the past decade, the success of wavelets in solving many different problems has contributed to its unprecedented popularity. Due to implementation constraints scalar wavelets do not posses all the properties which are needed for better performance in compression. New class of wavelets called 'Multiwavelets' which posses more than one scaling filters overcomes this problem. The objective of this paper is to develop an efficient compression scheme and to obtain better quality and higher compression ratio through multiwavelet transform and embedded coding of multiwavelet coefficients through Set Partitioning In Hierarchical Trees algorithm (SPIHT) algorithm. A comparison of the best known multiwavelets is made to the best known scalar wavelets. Both quantitative and qualitative measures of performance are examined for Fingerprints.

Keywords: Mutiwavelet, Modified SPIHT Algorithm, SPIHT, Wavelet.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1613

Authors: Chia-Hung Lin, Mei-Sung Kang, Cong-Hui Huang, Chao-Lin Kuo

Abstract:

This paper proposes fractal patterns for power quality (PQ) detection using color relational analysis (CRA) based classifier. Iterated function system (IFS) uses the non-linear interpolation in the map and uses similarity maps to construct various fractal patterns of power quality disturbances, including harmonics, voltage sag, voltage swell, voltage sag involving harmonics, voltage swell involving harmonics, and voltage interruption. The non-linear interpolation functions (NIFs) with fractal dimension (FD) make fractal patterns more distinguishing between normal and abnormal voltage signals. The classifier based on CRA discriminates the disturbance events in a power system. Compared with the wavelet neural networks, the test results will show accurate discrimination, good robustness, and faster processing time for detecting disturbing events.

Keywords: Power Quality (PQ), Color Relational Analysis(CRA), Iterated Function System (IFS), Non-linear InterpolationFunction (NIF), Fractal Dimension (FD).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1649

Authors: Liyakathunisa, V. K. Ananthashayana

Abstract:

Crucial information barely visible to the human eye is often embedded in a series of low resolution images taken of the same scene. Super resolution reconstruction is the process of combining several low resolution images into a single higher resolution image. The ideal algorithm should be fast, and should add sharpness and details, both at edges and in regions without adding artifacts. In this paper we propose a super resolution blind reconstruction technique for linearly degraded images. In our proposed technique the algorithm is divided into three parts an image registration, wavelets based fusion and an image restoration. In this paper three low resolution images are considered which may sub pixels shifted, rotated, blurred or noisy, the sub pixel shifted images are registered using affine transformation model; A wavelet based fusion is performed and the noise is removed using soft thresolding. Our proposed technique reduces blocking artifacts and also smoothens the edges and it is also able to restore high frequency details in an image. Our technique is efficient and computationally fast having clear perspective of real time implementation.

Keywords: Affine Transforms, Denoiseing, DWT, Fusion, Image registration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2671

Authors: Mak Kaboudan

Abstract:

A multi-agent system is developed here to predict monthly details of the upcoming peak of the 24th solar magnetic cycle. While studies typically predict the timing and magnitude of cycle peaks using annual data, this one utilizes the unsmoothed monthly sunspot number instead. Monthly numbers display more pronounced fluctuations during periods of strong solar magnetic activity than the annual sunspot numbers. Because strong magnetic activities may cause significant economic damages, predicting monthly variations should provide different and perhaps helpful information for decision-making purposes. The multi-agent system developed here operates in two stages. In the first, it produces twelve predictions of the monthly numbers. In the second, it uses those predictions to deliver a final forecast. Acting as expert agents, genetic programming and neural networks produce the twelve fits and forecasts as well as the final forecast. According to the results obtained, the next peak is predicted to be 156 and is expected to occur in October 2011- with an average of 136 for that year.

Keywords: Computational techniques, discrete wavelet transformations, solar cycle prediction, sunspot numbers.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1330

Authors: Esmeralda Hysenbelliu

Abstract:

The aim of this paper is to present the QoE (Quality of Experience) IPTV SDN-based media streaming server enhanced architecture for configuring, controlling, management and provisioning the improved delivery of IPTV service application with low cost, low bandwidth, and high security. Furthermore, it is given a virtual QoE IPTV SDN-based topology to provide an improved IPTV service based on QoE Control and Management of multimedia services functionalities. Inside OpenFlow SDN Controller there are enabled in high flexibility and efficiency Service Load-Balancing Systems; based on the Loading-Balance module and based on GeoIP Service. This two Load-balancing system improve IPTV end-users Quality of Experience (QoE) with optimal management of resources greatly. Through the key functionalities of OpenFlow SDN controller, this approach produced several important features, opportunities for overcoming the critical QoE metrics for IPTV Service like achieving incredible Fast Zapping time (Channel Switching time) < 0.1 seconds. This approach enabled Easy and Powerful Transcoding system via FFMPEG encoder. It has the ability to customize streaming dimensions bitrates, latency management and maximum transfer rates ensuring delivering of IPTV streaming services (Audio and Video) in high flexibility, low bandwidth and required performance. This QoE IPTV SDN-based media streaming architecture unlike other architectures provides the possibility of Channel Exchanging between several IPTV service providers all over the word. This new functionality brings many benefits as increasing the number of TV channels received by end –users with low cost, decreasing stream failure time (Channel Failure time < 0.1 seconds) and improving the quality of streaming services.

Keywords: Improved QoE, OpenFlow SDN controller, IPTV service application, softwarization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1030

Authors: Mohammed M. Siddeq, Mohammed H. Rasheed, Omar M. Salih, Marcos A. Rodrigues

Abstract:

This research proposes a data encoding and decoding method based on the Matrix Minimization algorithm. This algorithm is applied to high-frequency coefficients for compression/encoding. The algorithm starts by converting every three coefficients to a single value; this is accomplished based on three different keys. The decoding/decompression uses a search method called QSS (Quick Sequential Search) Decoding Algorithm presented in this research based on the sequential search to recover the exact coefficients. In the next step, the decoded data are saved in an auxiliary array. The basic idea behind the auxiliary array is to save all possible decoded coefficients; this is because another algorithm, such as conventional sequential search, could retrieve encoded/compressed data independently from the proposed algorithm. The experimental results showed that our proposed decoding algorithm retrieves original data faster than conventional sequential search algorithms.

Keywords: Matrix Minimization Algorithm, Decoding Sequential Search Algorithm, image compression, Discrete Cosine Transform, Discrete Wavelet Transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 249

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are increasingly important in automated customer service. These models, adept at recognizing complex relationships between input and output sequences, are essential for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the model’s focus during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the context of chatbots utilizing the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Using the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k = 3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k = 3). These findings emphasize the crucial influence of selecting an appropriate attention-scoring function to enhance the performance of seq2seq models for chatbots, particularly highlighting the model integrating tanh activation as a promising approach to improving chatbot quality in customer support contexts.

Keywords: Attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 95

Authors: Mahdieh Khalilinezhad, Silvana Dellepiane, Gianni Vernazza

Abstract:

The aim of this work is to build a model based on tissue characterization that is able to discriminate pathological and non-pathological regions from three-phasic CT images. With our research and based on a feature selection in different phases, we are trying to design a neural network system with an optimal neuron number in a hidden layer. Our approach consists of three steps: feature selection, feature reduction, and classification. For each region of interest (ROI), 6 distinct sets of texture features are extracted such as: first order histogram parameters, absolute gradient, run-length matrix, co-occurrence matrix, autoregressive model, and wavelet, for a total of 270 texture features. When analyzing more phases, we show that the injection of liquid cause changes to the high relevant features in each region. Our results demonstrate that for detecting HCC tumor phase 3 is the best one in most of the features that we apply to the classification algorithm. The percentage of detection between pathology and healthy classes, according to our method, relates to first order histogram parameters with accuracy of 85% in phase 1, 95% in phase 2, and 95% in phase 3.

Keywords: Feature selection, Multi-phasic liver images, Neural network, Texture analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2536

Authors: Raghad Jawad Ahmed

Abstract:

Segmentation of a color image composed of different kinds of regions can be a hard problem, namely to compute for an exact texture fields. The decision of the optimum number of segmentation areas in an image when it contains similar and/or un stationary texture fields. A novel neighborhood-based segmentation approach is proposed. A genetic algorithm is used in the proposed segment-pass optimization process. In this pass, an energy function, which is defined based on Markov Random Fields, is minimized. In this paper we use an adaptive threshold estimation method for image thresholding in the wavelet domain based on the generalized Gaussian distribution (GGD) modeling of sub band coefficients. This method called Normal Shrink is computationally more efficient and adaptive because the parameters required for estimating the threshold depend on sub band data energy that used in the pre-stage of segmentation. A quad tree is employed to implement the multi resolution framework, which enables the use of different strategies at different resolution levels, and hence, the computation can be accelerated. The experimental results using the proposed segmentation approach are very encouraging.

Keywords: Color image segmentation, Genetic algorithm, Markov random field, Scale space filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1579

Authors: Ehab F. Badran, Guoxiang Gu

Abstract:

We consider optimal channel equalization for MIMO (multi-input/multi-output) time-varying channels in the sense of MMSE (minimum mean-squared-error), where the observation noise can be non-stationary. We show that all ZF (zero-forcing) receivers can be parameterized in an affine form which eliminates completely the ISI (inter-symbol-interference), and optimal channel equalizers can be designed through minimization of the MSE (mean-squarederror) between the detected signals and the transmitted signals, among all ZF receivers. We demonstrate that the optimal channel equalizer is a modified Kalman filter, and show that under the AWGN (additive white Gaussian noise) assumption, the proposed optimal channel equalizer minimizes the BER (bit error rate) among all possible ZF receivers. Our results are applicable to optimal channel equalization for DWMT (discrete wavelet multitone), multirate transmultiplexers, OFDM (orthogonal frequency division multiplexing), and DS (direct sequence) CDMA (code division multiple access) wireless data communication systems. A design algorithm for optimal channel equalization is developed, and several simulation examples are worked out to illustrate the proposed design algorithm.

Keywords: Channel equalization, Kalman filtering, Time-varying systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1836

Authors: Michael Zimba, Darlison Nyirenda

Abstract:

A novel copy-move image forgery, CMIF, detection method is proposed. The proposed method presents a new approach which relies on electrostatic field theory, EFT. Solely for the purpose of reducing the dimension of a suspicious image, the proposed algorithm firstly performs discrete wavelet transform, DWT, of the suspicious image and extracts only the approximation subband. The extracted subband is then bijectively mapped onto a virtual electrostatic field where concepts of EFT are utilized to extract robust features. The extracted features are invariant to additive noise, JPEG compression, and affine transformation. Finally, same affine transformation selection, SATS, a duplication verification method, is applied to detect duplicated regions. SATS is a better option than the common shift vector method because SATS is insensitive to affine transformation. Consequently, the proposed CMIF algorithm is not only fast but also more robust to attacks compared to the existing related CMIF algorithms. The experimental results show high detection rates, as high as 100% in some cases.

Keywords: Affine transformation, Radix sort, SATS, Virtual electrostatic field.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1816

Authors: Tirtha S. Das, Ayan K. Sau, Subir K. Sarkar

Abstract:

Digital watermarking is a way to provide the facility of secure multimedia data communication besides its copyright protection approach. The Spread Spectrum modulation principle is widely used in digital watermarking to satisfy the robustness of multimedia signals against various signal-processing operations. Several SS watermarking algorithms have been proposed for multimedia signals but very few works have discussed on the issues responsible for secure data communication and its robustness improvement. The current paper has critically analyzed few such factors namely properties of spreading codes, proper signal decomposition suitable for data embedding, security provided by the key, successive bit cancellation method applied at decoder which have greater impact on the detection reliability, secure communication of significant signal under camouflage of insignificant signals etc. Based on the analysis, robust SS watermarking scheme for secure data communication is proposed in wavelet domain and improvement in secure communication and robustness performance is reported through experimental results. The reported result also shows improvement in visual and statistical invisibility of the hidden data.

Keywords: Spread spectrum modulation, spreading code, signaldecomposition, security, successive bit cancellation

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

Authors: R. Sarathi, G. Koperundevi

Abstract:

Design of Converter transformer insulation is a major challenge. The insulation of these transformers is stressed by both AC and DC voltages. Particle contamination is one of the major problems in insulation structures, as they generate partial discharges leading it to major failure of insulation. Similarly corona discharges occur in transformer insulation. This partial discharge due to particle movement / corona formation in insulation structure under different voltage wave shapes, are different. In the present study, UHF technique is adopted to understand the discharge activity and could be realized that the characteristics of UHF signal generated under low and high fields are different. In the case of corona generated signal, the frequency content of the UHF sensor output lies in the range 0.3-1.2 GHz and is not much varied except for its increase in magnitude of discharge with the increase in applied voltage. It is realized that the current signal injected due to partial discharges/corona is about 4ns duration measured for first one half cycle. Wavelet technique is adopted in the present study. It allows one to identify the frequency content present in the signal at different instant of time. The STD-MRA analysis helps one to identify the frequency band in which the energy content of the UHF signal is maximum.

Keywords: Contamination, Insulation, Partial Discharges, Transformer oil, UHF sensors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3842

Authors: Sajjad Farashi

Abstract:

Neurons in the nervous system communicate with each other by producing electrical signals called spikes. To investigate the physiological function of nervous system it is essential to study the activity of neurons by detecting and sorting spikes in the recorded signal. In this paper a method is proposed for considering the spike sorting problem which is based on the nonlinear modeling of spikes using exponential autoregressive model. The genetic algorithm is utilized for model parameter estimation. In this regard some selected model coefficients are used as features for sorting purposes. For optimal selection of model coefficients, self-organizing feature map is used. The results show that modeling of spikes with nonlinear autoregressive model outperforms its linear counterpart. Also the extracted features based on the coefficients of exponential autoregressive model are better than wavelet based extracted features and get more compact and well-separated clusters. In the case of spikes different in small-scale structures where principal component analysis fails to get separated clouds in the feature space, the proposed method can obtain well-separated cluster which removes the necessity of applying complex classifiers.

Keywords: Exponential autoregressive model, Neural data, spike sorting, time series modeling.

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

Authors: Somnath Dey, Debasis Samanta

Abstract:

Iris-based biometric authentication is gaining importance in recent times. Iris biometric processing however, is a complex process and computationally very expensive. In the overall processing of iris biometric in an iris-based biometric authentication system, feature processing is an important task. In feature processing, we extract iris features, which are ultimately used in matching. Since there is a large number of iris features and computational time increases as the number of features increases, it is therefore a challenge to develop an iris processing system with as few as possible number of features and at the same time without compromising the correctness. In this paper, we address this issue and present an approach to feature extraction and feature matching process. We apply Daubechies D4 wavelet with 4 levels to extract features from iris images. These features are encoded with 2 bits by quantizing into 4 quantization levels. With our proposed approach it is possible to represent an iris template with only 304 bits, whereas existing approaches require as many as 1024 bits. In addition, we assign different weights to different iris region to compare two iris templates which significantly increases the accuracy. Further, we match the iris template based on a weighted similarity measure. Experimental results on several iris databases substantiate the efficacy of our approach.

Keywords: Iris recognition, biometric, feature processing, patternrecognition, pattern matching.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2141

Authors: Vishal Raj, Noorhan Abbas

Abstract:

Ambiguity in NLP (Natural Language Processing) refers to the ability of a word, phrase, sentence, or text to have multiple meanings. This results in various kinds of ambiguities such as lexical, syntactic, semantic, anaphoric and referential. This study is focused mainly on solving the issue of Lexical ambiguity. Word Sense Disambiguation (WSD) is an NLP technique that aims to resolve lexical ambiguity by determining the correct meaning of a word within a given context. Most WSD solutions rely on words for training and testing, but we have used lemma and Part of Speech (POS) tokens of words for training and testing. Lemma adds generality and POS adds properties of word into token. We have designed a method to create an affinity matrix to calculate the affinity between any pair of lemma_POS (a token where lemma and POS of word are joined by underscore) of given training set. Additionally, we have devised an algorithm to create the sense clusters of tokens using affinity matrix under hierarchy of POS of lemma. Furthermore, three different mechanisms to predict the sense of target word using the affinity/similarity value are devised. Each contextual token contributes to the sense of target word with some value and whichever sense gets higher value becomes the sense of target word. So, contextual tokens play a key role in creating sense clusters and predicting the sense of target word, hence, the model is named Contextual SenSe Model (CSM). CSM exhibits a noteworthy simplicity and explication lucidity in contrast to contemporary deep learning models characterized by intricacy, time-intensive processes, and challenging explication. CSM is trained on SemCor training data and evaluated on SemEval test dataset. The results indicate that despite the naivety of the method, it achieves promising results when compared to the Most Frequent Sense (MFS) model.

Keywords: Word Sense Disambiguation, WSD, Contextual SenSe Model, Most Frequent Sense, part of speech, POS, Natural Language Processing, NLP, OOV, out of vocabulary, ELMo, Embeddings from Language Model, BERT, Bidirectional Encoder Representations from Transformers, Word2Vec, lemma_POS, Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 404