Search results for: graph convolutional network

Authors: Jing Zhao, Dayong Liu, Shihao Wang, Xinghua Zhu, Delong Li

Abstract:

Uhumanned Underwater Vehicles generally operate in the deep sea, which has its own unique working conditions. Lithium-ion power batteries should have the necessary stability and endurance for use as an underwater vehicle’s power source. Therefore, it is essential to accurately forecast how long lithium-ion batteries will last in order to maintain the system’s reliability and safety. In order to model and forecast lithium battery Remaining Useful Life (RUL), this research suggests a model based on Complete Ensemble Empirical Mode Decomposition with Adaptive noise-Temporal Convolutional Net (CEEMDAN-TCN). In this study, two datasets, NASA and CALCE, which have a specific gap in capacity data fluctuation, are used to verify the model and examine the experimental results in order to demonstrate the generalizability of the concept. The experiments demonstrate the network structure’s strong universality and ability to achieve good fitting outcomes on the test set for various battery dataset types. The evaluation metrics reveal that the CEEMDAN-TCN prediction performance of TCN is 25% to 35% better than that of a single neural network, proving that feature expansion and modal decomposition can both enhance the model’s generalizability and be extremely useful in industrial settings.

Keywords: lithium-ion battery, remaining useful life, complete EEMD with adaptive noise, temporal convolutional net

Procedia PDF Downloads 114

Authors: Puttaswamy, Anwar Alwardi, Nayaka S. R.

Abstract:

One of the algebraic representation of a graph is the graph polynomial. In this article, we introduce the paired-domination polynomial of a graph G. The paired-domination polynomial of a graph G of order n is the polynomial Dp(G, x) with the coefficients dp(G, i) where dp(G, i) denotes the number of paired dominating sets of G of cardinality i and γpd(G) denotes the paired-domination number of G. We obtain some properties of Dp(G, x) and its coefficients. Further, we compute this polynomial for some families of standard graphs. Further, we obtain some characterization for some specific graphs.

Keywords: domination polynomial, paired dominating set, paired domination number, paired domination polynomial

Procedia PDF Downloads 201

Authors: A. Kulandai Therese

Abstract:

The eccentric connectivity index based on degree and eccentricity of the vertices of a graph is a widely used graph invariant in mathematics.In this paper, we present the explicit eccentric connectivity index, first and second Zagreb indices for a Corona graph and sub division-related corona graphs.

Keywords: corona graph, degree, eccentricity, eccentric connectivity index, first zagreb index, second zagreb index, subdivision graphs

Procedia PDF Downloads 311

Authors: T. Pathinathan, M. Peter

Abstract:

Fuzzy graphs incorporate concepts from graph theory with fuzzy principles. In this paper, we make a study on the properties of fuzzy graphs which are non-cyclic and are of two-dimensional in structure. In particular, this paper presents 2D structure or the structure of double layer for a non-cyclic fuzzy graph whose underlying crisp graph is non-cyclic. In any graph structure, introducing 2D structure may lead to an inherent cycle. We propose relevant conditions for 2D structured non-cyclic fuzzy graphs. These conditions are extended even to fuzzy graphs of the 3D structure. General theoretical properties that are studied for any fuzzy graph are verified to 2D structured or double layered fuzzy graphs. Concepts like Order, Degree, Strong and Size for a fuzzy graph are studied for 2D structured or double layered non-cyclic fuzzy graphs. Using different types of fuzzy graphs, the proposed concepts relating to 2D structured fuzzy graphs are verified.

Keywords: double layered fuzzy graph, double layered non–cyclic fuzzy graph, order, degree and size

Procedia PDF Downloads 369

Authors: Mehwish Asghar

Abstract:

Breast Cancer (BC) is a common type of cancer among women. Its screening is usually performed using different imaging modalities such as magnetic resonance imaging, mammogram, X-ray, CT, etc. Among these modalities’ mammogram is considered a powerful tool for diagnosis and screening of breast cancer. Sophisticated machine learning approaches have shown promising results in complementing human diagnosis. Generally, machine learning methods can be divided into two major classes: one is Radiomics analysis (RA), where image features are extracted manually; and the other one is the concept of convolutional neural networks (CNN), in which the computer learns to recognize image features on its own. This research aims to improve the incidence of early detection, thus reducing the mortality rate caused by breast cancer through the latest advancements in computer science, in general, and machine learning, in particular. It has also been aimed to ease the burden of doctors by improving and automating the process of breast cancer detection. This research is related to a relative analysis of different techniques for the implementation of different models for detecting and classifying breast cancer. The main goal of this research is to provide a detailed view of results and performances between different techniques. The purpose of this paper is to explore the potential of a convolutional neural network (CNN) w.r.t feature extractor and as a classifier. Also, in this research, it has been aimed to add the module of Radiomics for comparison of its results with deep learning techniques.

Keywords: breast cancer (BC), machine learning (ML), convolutional neural network (CNN), radionics, magnetic resonance imaging, artificial intelligence

Procedia PDF Downloads 195

Authors: Pengchao Wei, Xiangzhong Fang

Abstract:

Noise is ubiquitous in this world. Denoising is an essential technology, especially in image semantic segmentation, where noises are generally categorized into two main types i.e. feature noise and label noise. The main focus of this paper is aiming at modeling label noise, investigating the behaviors of different types of label noise on image semantic segmentation tasks using K-Nearest-Neighbor and Convolutional Neural Network classifier. The performance without label noise and with is evaluated and illustrated in this paper. In addition to that, the influence of feature noise on the image semantic segmentation task is researched as well and a feature noise reduction method is applied to mitigate its influence in the learning procedure.

Keywords: convolutional neural network, denoising, feature noise, image semantic segmentation, k-nearest-neighbor, label noise

Procedia PDF Downloads 192

Authors: Parisa Mansour

Abstract:

Cystic fibrosis (CF) is one of the most common autosomal recessive diseases among whites. It mostly affects the lungs, causing infections and inflammation that account for 90% of deaths in CF patients. Because of this high variability in clinical presentation and organ involvement, investigating treatment responses and evaluating lung changes over time is critical to preventing CF progression. High-resolution computed tomography (HRCT) greatly facilitates the assessment of lung disease progression in CF patients. Recently, artificial intelligence was used to analyze chest CT scans of CF patients. In this paper, we propose a convolutional neural network (CNN) approach to classify CF lung patterns in HRCT images. The proposed network consists of two convolutional layers with 3 × 3 kernels and maximally connected in each layer, followed by two dense layers with 1024 and 10 neurons, respectively. The softmax layer prepares a predicted output probability distribution between classes. This layer has three exits corresponding to the categories of normal (healthy), bronchitis and inflammation. To train and evaluate the network, we constructed a patch-based dataset extracted from more than 1100 lung HRCT slices obtained from 45 CF patients. Comparative evaluation showed the effectiveness of the proposed CNN compared to its close peers. Classification accuracy, average sensitivity and specificity of 93.64%, 93.47% and 96.61% were achieved, indicating the potential of CNNs in analyzing lung CF patterns and monitoring lung health. In addition, the visual features extracted by our proposed method can be useful for automatic measurement and finally evaluation of the severity of CF patterns in lung HRCT images.

Keywords: HRCT, CF, cystic fibrosis, chest CT, artificial intelligence

Procedia PDF Downloads 39

Authors: Ezgi Kaya, A. Dilek Maden

Abstract:

A topological index is a number related to graph which is invariant under graph isomorphism. In theoretical chemistry, molecular structure descriptors (also called topological indices) are used for modeling physicochemical, pharmacologic, toxicologic, biological and other properties of chemical compounds. Let G be a graph with n vertices and m edges. For a given edge uv, the quantity nu(e) denotes the number of vertices closer to u than v, the quantity nv(e) is defined analogously. The vertex PI index defined as the sum of the nu(e) and nv(e). Here the sum is taken over all edges of G. The energy of a graph is defined as the sum of the eigenvalues of adjacency matrix of G and the Laplacian energy of a graph is defined as the sum of the absolute value of difference of laplacian eigenvalues and average degree of G. In theoretical chemistry, the π-electron energy of a conjugated carbon molecule, computed using the Hückel theory, coincides with the energy. Hence results on graph energy assume special significance. The Laplacian matrix of a graph G weighted by the vertex PI weighting is the Laplacian vertex PI matrix and the Laplacian vertex PI eigenvalues of a connected graph G are the eigenvalues of its Laplacian vertex PI matrix. In this study, Laplacian vertex PI energy of a graph is defined of G. We also give some bounds for the Laplacian vertex PI energy of graphs in terms of vertex PI index, the sum of the squares of entries in the Laplacian vertex PI matrix and the absolute value of the determinant of the Laplacian vertex PI matrix.

Keywords: energy, Laplacian energy, laplacian vertex PI eigenvalues, Laplacian vertex PI energy, vertex PI index

Procedia PDF Downloads 210

Authors: Muhammad Arif Khan, Haroon Idrees, Imran Aziz, Sidra Mushtaq

Abstract:

Social platforms like online discussion and mailing groups are well aligned with academic as well as professional learning spaces. Professional communities are increasingly moving to online forums for sharing and capturing the intellectual abilities. This study investigated dynamics of social connectivity of yahoo mailing groups of Pakistani Library and Information Science (LIS) professionals using Graph Theory technique. Design/Methodology: Social Network Analysis is the increasingly concerned domain for scientists in identifying whether people grow together through online social interaction or, whether they just reflect connectivity. We have conducted a longitudinal study using Network Graph Theory technique to analyze the large data-set of email communication. The data was collected from three yahoo mailing groups using network analysis software over a period of six months i.e. January to June 2016. Findings of the network analysis were reviewed through focus group discussion with LIS experts and selected respondents of the study. Data were analyzed in Microsoft Excel and network diagrams were visualized using NodeXL and ORA-Net Scene package. Findings: Findings demonstrate that professionals and students exhibit intellectual growth the more they get tied within a network by interacting and participating in communication through online forums. The study reports on dynamics of the large network by visualizing the email correspondence among group members in a network consisting vertices (members) and edges (randomized correspondence). The model pair wise relationship between group members was illustrated to show characteristics, reasons, and strength of ties. Connectivity of nodes illustrated the frequency of communication among group members through examining node coupling, diffusion of networks, and node clustering has been demonstrated in-depth. Network analysis was found to be a useful technique in investigating the dynamics of the large network.

Keywords: emailing networks, network graph theory, online social platforms, yahoo mailing groups

Procedia PDF Downloads 212

Authors: Stefan Wagenpfeil, Felix Engel, Paul McKevitt, Matthias Hemmje

Abstract:

Multimedia Indexing and Retrieval is generally designed and implemented by employing feature graphs. These graphs typically contain a significant number of nodes and edges to reflect the level of detail in feature detection. A higher level of detail increases the effectiveness of the results but also leads to more complex graph structures. However, graph-traversal-based algorithms for similarity are quite inefficient and computation intensive, especially for large data structures. To deliver fast and effective retrieval, an efficient similarity algorithm, particularly for large graphs, is mandatory. Hence, in this paper, we define a graph-projection into a 2D space (Graph Code) as well as the corresponding algorithms for indexing and retrieval. We show that calculations in this space can be performed more efficiently than graph-traversals due to a simpler processing model and a high level of parallelization. In consequence, we prove that the effectiveness of retrieval also increases substantially, as Graph Codes facilitate more levels of detail in feature fusion. Thus, Graph Codes provide a significant increase in efficiency and effectiveness (especially for Multimedia indexing and retrieval) and can be applied to images, videos, audio, and text information.

Keywords: indexing, retrieval, multimedia, graph algorithm, graph code

Procedia PDF Downloads 133

Authors: Xianwei Zheng, Yuan Yan Tang

Abstract:

Classical window Fourier transform has been widely used in signal processing, image processing, machine learning and pattern recognition. The related Gabor transform is powerful enough to capture the texture information of any given dataset. Recently, in the emerging field of graph signal processing, researchers devoting themselves to develop a graph signal processing theory to handle the so-called graph signals. Among the new developing theory, windowed graph Fourier transform has been constructed to establish a time-frequency analysis framework of graph signals. The windowed graph Fourier transform is defined by using the translation and modulation operators of graph signals, following the similar calculations in classical windowed Fourier transform. Specifically, the translation and modulation operators of graph signals are defined by using the Laplacian eigenvectors as follows. For a given graph signal, its translation is defined by a similar manner as its definition in classical signal processing. Specifically, the translation operator can be defined by using the Fourier atoms; the graph signal translation is defined similarly by using the Laplacian eigenvectors. The modulation of the graph can also be established by using the Laplacian eigenvectors. The windowed graph Fourier transform based on these two operators has been applied to obtain time-frequency representations of graph signals. Fundamentally, the modulation operator is defined similarly to the classical modulation by multiplying a graph signal with the entries in each Fourier atom. However, a single Laplacian eigenvector entry cannot play a similar role as the Fourier atom. This definition ignored the relationship between the translation and modulation operators. In this paper, a new definition of the modulation operator is proposed and thus another time-frequency framework for graph signal is constructed. Specifically, the relationship between the translation and modulation operations can be established by the Fourier transform. Specifically, for any signal, the Fourier transform of its translation is the modulation of its Fourier transform. Thus, the modulation of any signal can be defined as the inverse Fourier transform of the translation of its Fourier transform. Therefore, similarly, the graph modulation of any graph signal can be defined as the inverse graph Fourier transform of the translation of its graph Fourier. The novel definition of the graph modulation operator established a relationship of the translation and modulation operations. The new modulation operation and the original translation operation are applied to construct a new framework of graph signal time-frequency analysis. Furthermore, a windowed graph Fourier frame theory is developed. Necessary and sufficient conditions for constructing windowed graph Fourier frames, tight frames and dual frames are presented in this paper. The novel graph signal time-frequency analysis framework is applied to signals defined on well-known graphs, e.g. Minnesota road graph and random graphs. Experimental results show that the novel framework captures new features of graph signals.

Keywords: graph signals, windowed graph Fourier transform, windowed graph Fourier frames, vertex frequency analysis

Procedia PDF Downloads 315

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 89

Authors: Zainab Yasir Abed Al-Rekaby, Abdul Jalil M. Khalaf

Abstract:

Let the vertices of a graph such that every two adjacent vertices have different color is a very common problem in the graph theory. This is known as proper coloring of graphs. The possible number of different proper colorings on a graph with a given number of colors can be represented by a function called the chromatic polynomial. Two graphs G and H are said to be chromatically equivalent, if they share the same chromatic polynomial. A Graph G is chromatically unique, if G is isomorphic to H for any graph H such that G is chromatically equivalent to H. The study of chromatically equivalent and chromatically unique problems is called chromaticity. This paper shows that a wheel W12 is chromatically unique.

Keywords: chromatic polynomial, chromatically equivalent, chromatically unique, wheel

Procedia PDF Downloads 402

Authors: Po-Fang Hsu, Chiching Wei

Abstract:

In this paper, we present a novel neural graph matching approach applied to document comparison. Document comparison is a common task in the legal and financial industries. In some cases, the most important differences may be the addition or omission of words, sentences, clauses, or paragraphs. However, it is a challenging task without recording or tracing the whole edited process. Under many temporal uncertainties, we explore the potentiality of our approach to proximate the accurate comparison to make sure which element blocks have a relation of edition with others. In the beginning, we apply a document layout analysis that combines traditional and modern technics to segment layouts in blocks of various types appropriately. Then we transform this issue into a problem of layout graph matching with textual awareness. Regarding graph matching, it is a long-studied problem with a broad range of applications. However, different from previous works focusing on visual images or structural layout, we also bring textual features into our model for adapting this domain. Specifically, based on the electronic document, we introduce an encoder to deal with the visual presentation decoding from PDF. Additionally, because the modifications can cause the inconsistency of document layout analysis between modified documents and the blocks can be merged and split, Sinkhorn divergence is adopted in our neural graph approach, which tries to overcome both these issues with many-to-many block matching. We demonstrate this on two categories of layouts, as follows., legal agreement and scientific articles, collected from our real-case datasets.

Keywords: document comparison, graph matching, graph neural network, modification similarity, multi-modal

Procedia PDF Downloads 153

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 133

Authors: Montaceur Zaghdoud, Mohamed Moussaoui, Jalel Akaichi

Abstract:

Frequent subgraph mining refers usually to graph matching and it is widely used in when analyzing big data with large graphs. A lot of research works dealt with structural exact or inexact graph matching but a little attention is paid to semantic matching when graph vertices and/or edges are attributed and typed. Therefore, it seems very interesting to integrate background knowledge into the analysis and that extracted frequent subgraphs should become more pruned by applying a new semantic filter instead of using only structural similarity in graph matching process. Consequently, this paper focuses on developing a new hybrid approximate structuralsemantic graph matching to discover a set of frequent subgraphs. It uses simultaneously an approximate structural similarity function based on graph edit distance function and a possibilistic vertices similarity function based on affinity function. Both structural and semantic filters contribute together to prune extracted frequent set. Indeed, new hybrid structural-semantic frequent subgraph mining approach searches will be suitable to be applied to several application such as community detection in social networks.

Keywords: approximate graph matching, hybrid frequent subgraph mining, graph mining, possibility theory

Procedia PDF Downloads 372

Authors: Zainab Yasir Al-Rekaby, Abdul Jalil M. Khalaf

Abstract:

Coloring the vertices of a graph such that every two adjacent vertices have different color is a very common problem in the graph theory. This is known as proper coloring of graphs. The possible number of different proper colorings on a graph with a given number of colors can be represented by a function called the chromatic polynomial. Two graphs G and H are said to be chromatically equivalent, if they share the same chromatic polynomial. A Graph G is chromatically unique, if G is isomorphic to H for any graph H such that G is chromatically equivalent to H. The study of chromatically equivalent and chromatically unique problems is called chromaticity. This paper shows that a wheel W14 is chromatically unique.

Keywords: chromatic polynomial, chromatically Equivalent, chromatically unique, wheel

Procedia PDF Downloads 388

Authors: Chirawat Wattanapanich, Hong Wei

Abstract:

This study presents new gait representations for improving gait recognition accuracy on cross gait appearances, such as normal walking, wearing a coat and carrying a bag. Based on the Gait Energy Image (GEI), two ideas are implemented to generate new gait representations. One is to append lower knee regions to the original GEI, and the other is to apply convolutional operations to the GEI and its variants. A set of new gait representations are created and used for training multi-class Support Vector Machines (SVMs). Tests are conducted on the CASIA dataset B. Various combinations of the gait representations with different convolutional kernel size and different numbers of kernels used in the convolutional processes are examined. Both the entire images as features and reduced dimensional features by Principal Component Analysis (PCA) are tested in gait recognition. Interestingly, both new techniques, appending the lower knee regions to the original GEI and convolutional GEI, can significantly contribute to the performance improvement in the gait recognition. The experimental results have shown that the average recognition rate can be improved from 75.65% to 87.50%.

Keywords: convolutional image, lower knee, gait

Procedia PDF Downloads 179

Authors: Almagul Assainova , Dariya Abykenova, Liudmila Goncharenko, Sergey Sybachin, Saule Rakhimova, Abay Aman

Abstract:

The recognition of a handwritten Kazakh text is a relevant objective today for the digitization of materials. The study presents a model of a hybrid neural network for handwriting recognition, which includes a convolutional neural network and a multi-layer perceptron. Each network includes 1024 input neurons and 42 output neurons. The model is implemented in the program, written in the Python programming language using the EMNIST database, NumPy, Keras, and Tensorflow modules. The neural network training of such specific letters of the Kazakh alphabet as ә, ғ, қ, ң, ө, ұ, ү, h, і was conducted. The neural network model and the program created on its basis can be used in electronic document management systems to digitize the Kazakh text.

Keywords: handwriting recognition system, image recognition, Kazakh font, machine learning, neural networks

Procedia PDF Downloads 229

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: deep learning, field programmable gate array, FPGA, hardware accelerator, convolutional neural networks, CNN

Procedia PDF Downloads 98

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 41

Authors: Chia-Feng Lu, Yuh-Jen Wang, Shin Teng, Yu-Te Wu, Sui-Hing Yan

Abstract:

Brain functional networks based on resting-state EEG data were compared between patients with mild Alzheimer’s disease (mAD) and matched patients with amnestic subtype of mild cognitive impairment (aMCI). We integrated the time–frequency cross mutual information (TFCMI) method to estimate the EEG functional connectivity between cortical regions and the network analysis based on graph theory to further investigate the alterations of functional networks in mAD compared with aMCI group. We aimed at investigating the changes of network integrity, local clustering, information processing efficiency, and fault tolerance in mAD brain networks for different frequency bands based on several topological properties, including degree, strength, clustering coefficient, shortest path length, and efficiency. Results showed that the disruptions of network integrity and reductions of network efficiency in mAD characterized by lower degree, decreased clustering coefficient, higher shortest path length, and reduced global and local efficiencies in the delta, theta, beta2, and gamma bands were evident. The significant changes in network organization can be used in assisting discrimination of mAD from aMCI in clinical.

Keywords: EEG, functional connectivity, graph theory, TFCMI

Procedia PDF Downloads 402

Authors: Tian Lan, Yixiang Wang, Wenxin Tai, Yilan Lyu, Zufeng Wu

Abstract:

The monaural speech enhancement task in the time-frequencydomain has a myriad of approaches, with the stacked con-volutional neural network (CNN) demonstrating superiorability in feature extraction and selection. However, usingstacked single convolutions method limits feature represen-tation capability and generalization ability. In order to solvethe aforementioned problem, we propose an attention-basedadaptive convolutional network that integrates the multi-scale convolutional operations into a operation-specific blockvia input dependent attention to adapt to complex auditoryscenes. In addition, we introduce a two-stage progressivelearning method to enlarge the receptive field without a dra-matic increase in computation burden. We conduct a series ofexperiments based on the TIMIT corpus, and the experimen-tal results prove that our proposed model is better than thestate-of-art models on all metrics.

Keywords: speech enhancement, adaptive convolu-tion, progressive learning, time-frequency domain

Procedia PDF Downloads 92

Authors: Svitov David, Alyamkin Sergey

Abstract:

The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.

Keywords: ArcFace, distillation, face recognition, margin-based softmax

Procedia PDF Downloads 118

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

Abstract:

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

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

Procedia PDF Downloads 110

Authors: Mahdi Bazarganigilani

Abstract:

Aortic enlargement, also known as an aortic aneurysm, can occur when the walls of the aorta become weak. This disease can become deadly if overlooked and undiagnosed. In this paper, a computer-aided diagnosis (CAD) system was introduced to accurately diagnose aortic enlargement from chest x-ray images. An enhanced convolutional neural network (CNN) was employed and then trained by transfer learning by using three different main areas from the original images. The areas included the left lung, heart, and right lung. The accuracy of the system was then evaluated on 1001 samples by using 4-fold cross-validation. A promising accuracy of 90% was achieved in terms of the F-measure indicator. The results showed using different areas from the original image in the training phase of CNN could increase the accuracy of predictions. This encouraged the author to evaluate this method on a larger dataset and even on different CAD systems for further enhancement of this methodology.

Keywords: computer-aided diagnosis systems, aortic enlargement, chest X-ray, image processing, convolutional neural networks

Procedia PDF Downloads 131

Authors: Nan Deng, Zhenqiu Liu

Abstract:

Thousands of patients with metastatic tumors were diagnosed with cancers of unknown primary sites each year. The inability to identify the primary cancer site may lead to inappropriate treatment and unexpected prognosis. Nowadays, a large amount of genomics and transcriptomics cancer data has been generated by next-generation sequencing (NGS) technologies, and The Cancer Genome Atlas (TCGA) database has accrued thousands of human cancer tumors and healthy controls, which provides an abundance of resource to differentiate cancer types. Meanwhile, deep convolutional neural networks (CNNs) have shown high accuracy on classification among a large number of image object categories. Here, we utilize 25 cancer primary tumors and 3 normal tissues from TCGA and convert their RNA-Seq gene expression profiling to color images; train, validate and test a CNN classifier directly from these images. The performance result shows that our CNN classifier can archive >80% test accuracy on most of the tumors and normal tissues. Since the gene expression pattern of distant metastases is similar to their primary tumors, the CNN classifier may provide a potential computational strategy on identifying the unknown primary origin of metastatic cancer in order to plan appropriate treatment for patients.

Keywords: bioinformatics, cancer, convolutional neural network, deep leaning, gene expression pattern

Procedia PDF Downloads 269

Authors: Junjie Zhong, Kai Hong, Lei Wang

Abstract:

Passage Retrieval (PR) plays an important role in many Natural Language Processing (NLP) tasks. Traditional efficient retrieval models relying on exact term-matching, such as TF-IDF or BM25, have nowadays been exceeded by pre-trained language models which match by semantics. Though they gain effectiveness, deep language models often require large memory as well as time cost. To tackle the trade-off between efficiency and effectiveness in PR, this paper proposes Graph Passage Retriever (GraphPR), a graph-based model inspired by the development of graph learning techniques. Different from existing works, GraphPR is end-to-end and integrates both term-matching information and semantics. GraphPR constructs a passage-level graph from BM25 retrieval results and trains a GCN-like model on the graph with graph-based objectives. Passages were regarded as nodes in the constructed graph and were embedded in dense vectors. PR can then be implemented using embeddings and a fast vector-similarity search. Experiments on a variety of real-world retrieval datasets show that the proposed model outperforms related models in several evaluation metrics (e.g., mean reciprocal rank, accuracy, F1-scores) while maintaining a relatively low query latency and memory usage.

Keywords: efficiency, effectiveness, graph learning, language model, passage retrieval, term-matching model

Procedia PDF Downloads 98

Authors: Qin Long, Li Xiaoge

Abstract:

The Knowledge Graphs have now become a new form of knowledge representation. However, there is no consensus in regard to a plausible and definition of entities and relationships in the domain-specific knowledge graph. Further, in conjunction with several limitations and deficiencies, various domain-specific entities and relationships recognition approaches are far from perfect. Specifically, named entity recognition in Chinese domain is a critical task for the natural language process applications. However, a bottleneck problem with Chinese named entity recognition in new domains is the lack of annotated data. To address this challenge, a domain distant supervised named entity recognition framework is proposed. The framework is divided into two stages: first, the distant supervised corpus is generated based on the entity linking model of graph attention neural network; secondly, the generated corpus is trained as the input of the distant supervised named entity recognition model to train to obtain named entities. The link model is verified in the ccks2019 entity link corpus, and the F1 value is 2% higher than that of the benchmark method. The re-pre-trained BERT language model is added to the benchmark method, and the results show that it is more suitable for distant supervised named entity recognition tasks. Finally, it is applied in the computer field, and the results show that this framework can obtain domain named entities.

Keywords: distant named entity recognition, entity linking, knowledge graph, graph attention neural network

Procedia PDF Downloads 71

Authors: P. Karthick, K. Mahesh

Abstract:

Video has become an increasingly significant component of our digital everyday contact. With the advancement of greater contents and shows of the resolution, its significant volume poses serious obstacles to the objective of receiving, distributing, compressing, and revealing video content of high quality. In this paper, we propose the primary beginning to complete a deep video compression model that jointly upgrades all video compression components. The video compression method involves splitting the video into frames, comparing the images using convolutional neural networks (CNN) to remove duplicates, repeating the single image instead of the duplicate images by recognizing and detecting minute changes using generative adversarial network (GAN) and recorded with long short-term memory (LSTM). Instead of the complete image, the small changes generated using GAN are substituted, which helps in frame level compression. Pixel wise comparison is performed using K-nearest neighbours (KNN) over the frame, clustered with K-means, and singular value decomposition (SVD) is applied for each and every frame in the video for all three color channels [Red, Green, Blue] to decrease the dimension of the utility matrix [R, G, B] by extracting its latent factors. Video frames are packed with parameters with the aid of a codec and converted to video format, and the results are compared with the original video. Repeated experiments on several videos with different sizes, duration, frames per second (FPS), and quality results demonstrate a significant resampling rate. On average, the result produced had approximately a 10% deviation in quality and more than 50% in size when compared with the original video.

Keywords: video compression, K-means clustering, convolutional neural network, generative adversarial network, singular value decomposition, pixel visualization, stochastic gradient descent, frame per second extraction, RGB channel extraction, self-detection and deciding system

Procedia PDF Downloads 163