Search results for: graph convolutional network
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 5019

Search results for: graph convolutional network

4719 Exploring the Role of Humorous Dialogues in Advertisements of Pakistani Network Companies: Analysis of Discourses through Multi-Modal Critical Approach

Authors: Jane E. Alam Solangi

Abstract:

The contribution of the study is to explore the important part of humorous dialogues in cellular network advertisements. This promotes the message of valuable construction and promotion of network companies in Pakistan that employ different and broad techniques to give promotion to selling products. It merely instigates the consumers to buy it. The results of the study after analysis of its collected data gives a vision that advertisers of network advertisements use humorous dialogues as a significant device to the greater level. The source of entertainment in the advertisement is accompanied by the texts and humorous discourses to influence buying decisions of the consumers. Therefore, it tends to neutralize personal and social based values. The earlier contribution of scholars presented that the technical employment of humorous devices leads to the successful market of the relevant products. In order to analyze the humorous discourse devices, the approach of multi-modality of Fairclough (1989) is used. It is accompanied by the framework of Kress and van Leeuwen’s (1996). It analyzes the visual graph of the grammar. The overall findings in the study verified the role of humorous devices in the captivation of consumers’ decision to buy the product that interests them. Therefore, the role of humor acts as a breaker of the monotonous rhythm of advertisements.

Keywords: advertisements, devices, humorous, multi-modality, networks, Pakistan

Procedia PDF Downloads 80
4718 Development of Graph-Theoretic Model for Ranking Top of Rail Lubricants

Authors: Subhash Chandra Sharma, Mohammad Soleimani

Abstract:

Selection of the correct lubricant for the top of rail application is a complex process. In this paper, the selection of the proper lubricant for a Top-Of-Rail (TOR) lubrication system based on graph theory and matrix approach has been developed. Attributes influencing the selection process and their influence on each other has been represented through a digraph and an equivalent matrix. A matrix function which is called the Permanent Function is derived. By substituting the level of inherent contribution of the influencing parameters and their influence on each other qualitatively, a criterion called Suitability Index is derived. Based on these indices, lubricants can be ranked for their suitability. The proposed model can be useful for maintenance engineers in selecting the best lubricant for a TOR application. The proposed methodology is illustrated step–by-step through an example.

Keywords: lubricant selection, top of rail lubrication, graph-theory, Ranking of lubricants

Procedia PDF Downloads 272
4717 Monitoring a Membrane Structure Using Non-Destructive Testing

Authors: Gokhan Kilic, Pelin Celik

Abstract:

Structural health monitoring (SHM) is widely used in evaluating the state and health of membrane structures. In the past, in order to collect data and send it to a data collection unit on membrane structures, wire sensors had to be put as part of the SHM process. However, this study recommends using wireless sensors instead of traditional wire ones to construct an economical, useful, and easy-to-install membrane structure health monitoring system. Every wireless sensor uses a software translation program that is connected to the monitoring server. Operational neural networks (ONNs) have recently been developed to solve the shortcomings of convolutional neural networks (CNNs), such as the network's resemblance to the linear neuron model. The results of using ONNs for monitoring to evaluate the structural health of a membrane are presented in this work.

Keywords: wireless sensor network, non-destructive testing, operational neural networks, membrane structures, dynamic monitoring

Procedia PDF Downloads 61
4716 AS-Geo: Arbitrary-Sized Image Geolocalization with Learnable Geometric Enhancement Resizer

Authors: Huayuan Lu, Chunfang Yang, Ma Zhu, Baojun Qi, Yaqiong Qiao, Jiangqian Xu

Abstract:

Image geolocalization has great application prospects in fields such as autonomous driving and virtual/augmented reality. In practical application scenarios, the size of the image to be located is not fixed; it is impractical to train different networks for all possible sizes. When its size does not match the size of the input of the descriptor extraction model, existing image geolocalization methods usually directly scale or crop the image in some common ways. This will result in the loss of some information important to the geolocalization task, thus affecting the performance of the image geolocalization method. For example, excessive down-sampling can lead to blurred building contour, and inappropriate cropping can lead to the loss of key semantic elements, resulting in incorrect geolocation results. To address this problem, this paper designs a learnable image resizer and proposes an arbitrary-sized image geolocation method. (1) The designed learnable image resizer employs the self-attention mechanism to enhance the geometric features of the resized image. Firstly, it applies bilinear interpolation to the input image and its feature maps to obtain the initial resized image and the resized feature maps. Then, SKNet (selective kernel net) is used to approximate the best receptive field, thus keeping the geometric shapes as the original image. And SENet (squeeze and extraction net) is used to automatically select the feature maps with strong contour information, enhancing the geometric features. Finally, the enhanced geometric features are fused with the initial resized image, to obtain the final resized images. (2) The proposed image geolocalization method embeds the above image resizer as a fronting layer of the descriptor extraction network. It not only enables the network to be compatible with arbitrary-sized input images but also enhances the geometric features that are crucial to the image geolocalization task. Moreover, the triplet attention mechanism is added after the first convolutional layer of the backbone network to optimize the utilization of geometric elements extracted by the first convolutional layer. Finally, the local features extracted by the backbone network are aggregated to form image descriptors for image geolocalization. The proposed method was evaluated on several mainstream datasets, such as Pittsburgh30K, Tokyo24/7, and Places365. The results show that the proposed method has excellent size compatibility and compares favorably to recently mainstream geolocalization methods.

Keywords: image geolocalization, self-attention mechanism, image resizer, geometric feature

Procedia PDF Downloads 190
4715 Deciding Graph Non-Hamiltonicity via a Closure Algorithm

Authors: E. R. Swart, S. J. Gismondi, N. R. Swart, C. E. Bell

Abstract:

We present an heuristic algorithm that decides graph non-Hamiltonicity. All graphs are directed, each undirected edge regarded as a pair of counter directed arcs. Each of the n! Hamilton cycles in a complete graph on n+1 vertices is mapped to an n-permutation matrix P where p(u,i)=1 if and only if the ith arc in a cycle enters vertex u, starting and ending at vertex n+1. We first create exclusion set E by noting all arcs (u, v) not in G, sufficient to code precisely all cycles excluded from G i.e. cycles not in G use at least one arc not in G. Members are pairs of components of P, {p(u,i),p(v,i+1)}, i=1, n-1. A doubly stochastic-like relaxed LP formulation of the Hamilton cycle decision problem is constructed. Each {p(u,i),p(v,i+1)} in E is coded as variable q(u,i,v,i+1)=0 i.e. shrinks the feasible region. We then implement the Weak Closure Algorithm (WCA) that tests necessary conditions of a matching, together with Boolean closure to decide 0/1 variable assignments. Each {p(u,i),p(v,j)} not in E is tested for membership in E, and if possible, added to E (q(u,i,v,j)=0) to iteratively maximize |E|. If the WCA constructs E to be maximal, the set of all {p(u,i),p(v,j)}, then G is decided non-Hamiltonian. Only non-Hamiltonian G share this maximal property. Ten non-Hamiltonian graphs (10 through 104 vertices) and 2000 randomized 31 vertex non-Hamiltonian graphs are tested and correctly decided non-Hamiltonian. For Hamiltonian G, the complement of E covers a matching, perhaps useful in searching for cycles. We also present an example where the WCA fails.

Keywords: Hamilton cycle decision problem, computational complexity theory, graph theory, theoretical computer science

Procedia PDF Downloads 348
4714 Some New Bounds for a Real Power of the Normalized Laplacian Eigenvalues

Authors: Ayşe Dilek Maden

Abstract:

For a given a simple connected graph, we present some new bounds via a new approach for a special topological index given by the sum of the real number power of the non-zero normalized Laplacian eigenvalues. To use this approach presents an advantage not only to derive old and new bounds on this topic but also gives an idea how some previous results in similar area can be developed.

Keywords: degree Kirchhoff index, normalized Laplacian eigenvalue, spanning tree, simple connected graph

Procedia PDF Downloads 346
4713 Speech Emotion Recognition with Bi-GRU and Self-Attention based Feature Representation

Authors: Bubai Maji, Monorama Swain

Abstract:

Speech is considered an essential and most natural medium for the interaction between machines and humans. However, extracting effective features for speech emotion recognition (SER) is remains challenging. The present studies show that the temporal information captured but high-level temporal-feature learning is yet to be investigated. In this paper, we present an efficient novel method using the Self-attention (SA) mechanism in a combination of Convolutional Neural Network (CNN) and Bi-directional Gated Recurrent Unit (Bi-GRU) network to learn high-level temporal-feature. In order to further enhance the representation of the high-level temporal-feature, we integrate a Bi-GRU output with learnable weights features by SA, and improve the performance. We evaluate our proposed method on our created SITB-OSED and IEMOCAP databases. We report that the experimental results of our proposed method achieve state-of-the-art performance on both databases.

Keywords: Bi-GRU, 1D-CNNs, self-attention, speech emotion recognition

Procedia PDF Downloads 98
4712 Deep Convolutional Neural Network for Detection of Microaneurysms in Retinal Fundus Images at Early Stage

Authors: Goutam Kumar Ghorai, Sandip Sadhukhan, Arpita Sarkar, Debprasad Sinha, G. Sarkar, Ashis K. Dhara

Abstract:

Diabetes mellitus is one of the most common chronic diseases in all countries and continues to increase in numbers significantly. Diabetic retinopathy (DR) is damage to the retina that occurs with long-term diabetes. DR is a major cause of blindness in the Indian population. Therefore, its early diagnosis is of utmost importance towards preventing progression towards imminent irreversible loss of vision, particularly in the huge population across rural India. The barriers to eye examination of all diabetic patients are socioeconomic factors, lack of referrals, poor access to the healthcare system, lack of knowledge, insufficient number of ophthalmologists, and lack of networking between physicians, diabetologists and ophthalmologists. A few diabetic patients often visit a healthcare facility for their general checkup, but their eye condition remains largely undetected until the patient is symptomatic. This work aims to focus on the design and development of a fully automated intelligent decision system for screening retinal fundus images towards detection of the pathophysiology caused by microaneurysm in the early stage of the diseases. Automated detection of microaneurysm is a challenging problem due to the variation in color and the variation introduced by the field of view, inhomogeneous illumination, and pathological abnormalities. We have developed aconvolutional neural network for efficient detection of microaneurysm. A loss function is also developed to handle severe class imbalance due to very small size of microaneurysms compared to background. The network is able to locate the salient region containing microaneurysms in case of noisy images captured by non-mydriatic cameras. The ground truth of microaneurysms is created by expert ophthalmologists for MESSIDOR database as well as private database, collected from Indian patients. The network is trained from scratch using the fundus images of MESSIDOR database. The proposed method is evaluated on DIARETDB1 and the private database. The method is successful in detection of microaneurysms for dilated and non-dilated types of fundus images acquired from different medical centres. The proposed algorithm could be used for development of AI based affordable and accessible system, to provide service at grass root-level primary healthcare units spread across the country to cater to the need of the rural people unaware of the severe impact of DR.

Keywords: retinal fundus image, deep convolutional neural network, early detection of microaneurysms, screening of diabetic retinopathy

Procedia PDF Downloads 121
4711 A Hybrid Based Algorithm to Solve the Multi-objective Minimum Spanning Tree Problem

Authors: Boumesbah Asma, Chergui Mohamed El-amine

Abstract:

Since it has been shown that the multi-objective minimum spanning tree problem (MOST) is NP-hard even with two criteria, we propose in this study a hybrid NSGA-II algorithm with an exact mutation operator, which is only used with low probability, to find an approximation to the Pareto front of the problem. In a connected graph G, a spanning tree T of G being a connected and cycle-free graph, if k edges of G\T are added to T, we obtain a partial graph H of G inducing a reduced size multi-objective spanning tree problem compared to the initial one. With a weak probability for the mutation operator, an exact method for solving the reduced MOST problem considering the graph H is then used to give birth to several mutated solutions from a spanning tree T. Then, the selection operator of NSGA-II is activated to obtain the Pareto front approximation. Finally, an adaptation of the VNS metaheuristic is called for further improvements on this front. It allows finding good individuals to counterbalance the diversification and the intensification during the optimization search process. Experimental comparison studies with an exact method show promising results and indicate that the proposed algorithm is efficient.

Keywords: minimum spanning tree, multiple objective linear optimization, combinatorial optimization, non-sorting genetic algorithm, variable neighborhood search

Procedia PDF Downloads 69
4710 First-Year Undergraduate Students' Dilemma with Kinematics Graphs

Authors: Itumeleng Phage

Abstract:

Students’ comprehension of graphs may be affected by the characteristics of the discipline in which the graph is used, the type of the task as well as the background of the students who are the readers or interpreters of the graph. This research study investigated these aspects of the graph comprehension of 152 first-year undergraduate physics students by comparing their responses to corresponding tasks in the mathematics and physics disciplines. The discipline characteristics were analysed for four task-related constructs namely coordinates, representations, area and slope. Students’ responses to corresponding visual decoding and judgement tasks set in mathematics and kinematics contexts were statistically compared. The effects of the participants’ gender, year of school completion and study course were determined as reader characteristics. The results of the empirical study indicated that participants generally transferred their mathematics knowledge on coordinates and representation of straight line graphs to the physics contexts, but not in the cases of parabolic and hyperbolic functions or area under graphs. Insufficient understanding of the slope concept contributed to weak performances on this construct in both mathematics and physics contexts. Discipline characteristics seem to play a vital role in students’ understanding, while reader characteristics had insignificant to medium effects on their responses.

Keywords: kinematics graph, discipline characteristics, constructs, coordinates, representations, area and slope

Procedia PDF Downloads 237
4709 Application of Deep Neural Networks to Assess Corporate Credit Rating

Authors: Parisa Golbayani, Dan Wang, Ionut¸ Florescu

Abstract:

In this work we implement machine learning techniques to financial statement reports in order to asses company’s credit rating. Specifically, the work analyzes the performance of four neural network architectures (MLP, CNN, CNN2D, LSTM) in predicting corporate credit rating as issued by Standard and Poor’s. The paper focuses on companies from the energy, financial, and healthcare sectors in the US. The goal of this analysis is to improve application of machine learning algorithms to credit assessment. To accomplish this, the study investigates three questions. First, we investigate if the algorithms perform better when using a selected subset of important features or whether better performance is obtained by allowing the algorithms to select features themselves. Second, we address the temporal aspect inherent in financial data and study whether it is important for the results obtained by a machine learning algorithm. Third, we aim to answer if one of the four particular neural network architectures considered consistently outperforms the others, and if so under which conditions. This work frames the problem as several case studies to answer these questions and analyze the results using ANOVA and multiple comparison testing procedures.

Keywords: convolutional neural network, long short term memory, multilayer perceptron, credit rating

Procedia PDF Downloads 212
4708 Coupling Large Language Models with Disaster Knowledge Graphs for Intelligent Construction

Authors: Zhengrong Wu, Haibo Yang

Abstract:

In the context of escalating global climate change and environmental degradation, the complexity and frequency of natural disasters are continually increasing. Confronted with an abundance of information regarding natural disasters, traditional knowledge graph construction methods, which heavily rely on grammatical rules and prior knowledge, demonstrate suboptimal performance in processing complex, multi-source disaster information. This study, drawing upon past natural disaster reports, disaster-related literature in both English and Chinese, and data from various disaster monitoring stations, constructs question-answer templates based on large language models. Utilizing the P-Tune method, the ChatGLM2-6B model is fine-tuned, leading to the development of a disaster knowledge graph based on large language models. This serves as a knowledge database support for disaster emergency response.

Keywords: large language model, knowledge graph, disaster, deep learning

Procedia PDF Downloads 31
4707 Survivable IP over WDM Network Design Based on 1 ⊕ 1 Network Coding

Authors: Nihed Bahria El Asghar, Imen Jouili, Mounir Frikha

Abstract:

Inter-datacenter transport network is very bandwidth and delay demanding. The data transferred over such a network is also highly QoS-exigent mostly because a huge volume of data should be transported transparently with regard to the application user. To avoid the data transfer failure, a backup path should be reserved. No re-routing delay should be observed. A dedicated 1+1 protection is however not applicable in inter-datacenter transport network because of the huge spare capacity. In this context, we propose a survivable virtual network with minimal backup based on network coding (1 ⊕ 1) and solve it using a modified Dijkstra-based heuristic.

Keywords: network coding, dedicated protection, spare capacity, inter-datacenters transport network

Procedia PDF Downloads 425
4706 An Integrated Visualization Tool for Heat Map and Gene Ontology Graph

Authors: Somyung Oh, Jeonghyeon Ha, Kyungwon Lee, Sejong Oh

Abstract:

Microarray is a general scheme to find differentially expressed genes for target concept. The output is expressed by heat map, and biologists analyze related terms of gene ontology to find some characteristics of differentially expressed genes. In this paper, we propose integrated visualization tool for heat map and gene ontology graph. Previous two methods are used by static manner and separated way. Proposed visualization tool integrates them and users can interactively manage it. Users may easily find and confirm related terms of gene ontology for given differentially expressed genes. Proposed tool also visualize connections between genes on heat map and gene ontology graph. We expect biologists to find new meaningful topics by proposed tool.

Keywords: heat map, gene ontology, microarray, differentially expressed gene

Procedia PDF Downloads 292
4705 Leveraging the Power of Dual Spatial-Temporal Data Scheme for Traffic Prediction

Authors: Yang Zhou, Heli Sun, Jianbin Huang, Jizhong Zhao, Shaojie Qiao

Abstract:

Traffic prediction is a fundamental problem in urban environment, facilitating the smart management of various businesses, such as taxi dispatching, bike relocation, and stampede alert. Most earlier methods rely on identifying the intrinsic spatial-temporal correlation to forecast. However, the complex nature of this problem entails a more sophisticated solution that can simultaneously capture the mutual influence of both adjacent and far-flung areas, with the information of time-dimension also incorporated seamlessly. To tackle this difficulty, we propose a new multi-phase architecture, DSTDS (Dual Spatial-Temporal Data Scheme for traffic prediction), that aims to reveal the underlying relationship that determines future traffic trend. First, a graph-based neural network with an attention mechanism is devised to obtain the static features of the road network. Then, a multi-granularity recurrent neural network is built in conjunction with the knowledge from a grid-based model. Subsequently, the preceding output is fed into a spatial-temporal super-resolution module. With this 3-phase structure, we carry out extensive experiments on several real-world datasets to demonstrate the effectiveness of our approach, which surpasses several state-of-the-art methods.

Keywords: traffic prediction, spatial-temporal, recurrent neural network, dual data scheme

Procedia PDF Downloads 92
4704 Development of Partial Discharge Defect Recognition and Status Diagnosis System with Adaptive Deep Learning

Authors: Chien-kuo Chang, Bo-wei Wu, Yi-yun Tang, Min-chiu Wu

Abstract:

This paper proposes a power equipment diagnosis system based on partial discharge (PD), which is characterized by increasing the readability of experimental data and the convenience of operation. This system integrates a variety of analysis programs of different data formats and different programming languages and then establishes a set of interfaces that can follow and expand the structure, which is also helpful for subsequent maintenance and innovation. This study shows a case of using the developed Convolutional Neural Networks (CNN) to integrate with this system, using the designed model architecture to simplify the complex training process. It is expected that the simplified training process can be used to establish an adaptive deep learning experimental structure. By selecting different test data for repeated training, the accuracy of the identification system can be enhanced. On this platform, the measurement status and partial discharge pattern of each equipment can be checked in real time, and the function of real-time identification can be set, and various training models can be used to carry out real-time partial discharge insulation defect identification and insulation state diagnosis. When the electric power equipment entering the dangerous period, replace equipment early to avoid unexpected electrical accidents.

Keywords: partial discharge, convolutional neural network, partial discharge analysis platform, adaptive deep learning

Procedia PDF Downloads 56
4703 Normal and Peaberry Coffee Beans Classification from Green Coffee Bean Images Using Convolutional Neural Networks and Support Vector Machine

Authors: Hira Lal Gope, Hidekazu Fukai

Abstract:

The aim of this study is to develop a system which can identify and sort peaberries automatically at low cost for coffee producers in developing countries. In this paper, the focus is on the classification of peaberries and normal coffee beans using image processing and machine learning techniques. The peaberry is not bad and not a normal bean. The peaberry is born in an only single seed, relatively round seed from a coffee cherry instead of the usual flat-sided pair of beans. It has another value and flavor. To make the taste of the coffee better, it is necessary to separate the peaberry and normal bean before green coffee beans roasting. Otherwise, the taste of total beans will be mixed, and it will be bad. In roaster procedure time, all the beans shape, size, and weight must be unique; otherwise, the larger bean will take more time for roasting inside. The peaberry has a different size and different shape even though they have the same weight as normal beans. The peaberry roasts slower than other normal beans. Therefore, neither technique provides a good option to select the peaberries. Defect beans, e.g., sour, broken, black, and fade bean, are easy to check and pick up manually by hand. On the other hand, the peaberry pick up is very difficult even for trained specialists because the shape and color of the peaberry are similar to normal beans. In this study, we use image processing and machine learning techniques to discriminate the normal and peaberry bean as a part of the sorting system. As the first step, we applied Deep Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) as machine learning techniques to discriminate the peaberry and normal bean. As a result, better performance was obtained with CNN than with SVM for the discrimination of the peaberry. The trained artificial neural network with high performance CPU and GPU in this work will be simply installed into the inexpensive and low in calculation Raspberry Pi system. We assume that this system will be used in under developed countries. The study evaluates and compares the feasibility of the methods in terms of accuracy of classification and processing speed.

Keywords: convolutional neural networks, coffee bean, peaberry, sorting, support vector machine

Procedia PDF Downloads 125
4702 End-to-End Spanish-English Sequence Learning Translation Model

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation

Procedia PDF Downloads 155
4701 A Neural Network Classifier for Identifying Duplicate Image Entries in Real-Estate Databases

Authors: Sergey Ermolin, Olga Ermolin

Abstract:

A Deep Convolution Neural Network with Triplet Loss is used to identify duplicate images in real-estate advertisements in the presence of image artifacts such as watermarking, cropping, hue/brightness adjustment, and others. The effects of batch normalization, spatial dropout, and various convergence methodologies on the resulting detection accuracy are discussed. For comparative Return-on-Investment study (per industry request), end-2-end performance is benchmarked on both Nvidia Titan GPUs and Intel’s Xeon CPUs. A new real-estate dataset from San Francisco Bay Area is used for this work. Sufficient duplicate detection accuracy is achieved to supplement other database-grounded methods of duplicate removal. The implemented method is used in a Proof-of-Concept project in the real-estate industry.

Keywords: visual recognition, convolutional neural networks, triplet loss, spatial batch normalization with dropout, duplicate removal, advertisement technologies, performance benchmarking

Procedia PDF Downloads 316
4700 Software Component Identification from Its Object-Oriented Code: Graph Metrics Based Approach

Authors: Manel Brichni, Abdelhak-Djamel Seriai

Abstract:

Systems are increasingly complex. To reduce their complexity, an abstract view of the system can simplify its development. To overcome this problem, we propose a method to decompose systems into subsystems while reducing their coupling. These subsystems represent components. Consisting of an existing object-oriented systems, the main idea of our approach is based on modelling as graphs all entities of an oriented object source code. Such modelling is easy to handle, so we can apply restructuring algorithms based on graph metrics. The particularity of our approach consists in integrating in addition to standard metrics, such as coupling and cohesion, some graph metrics giving more precision during the components identi cation. To treat this problem, we relied on the ROMANTIC approach that proposed a component-based software architecture recovery from an object oriented system.

Keywords: software reengineering, software component and interfaces, metrics, graphs

Procedia PDF Downloads 481
4699 An Accurate Brain Tumor Segmentation for High Graded Glioma Using Deep Learning

Authors: Sajeeha Ansar, Asad Ali Safi, Sheikh Ziauddin, Ahmad R. Shahid, Faraz Ahsan

Abstract:

Gliomas are most challenging and aggressive type of tumors which appear in different sizes, locations, and scattered boundaries. CNN is most efficient deep learning approach with outstanding capability of solving image analysis problems. A fully automatic deep learning based 2D-CNN model for brain tumor segmentation is presented in this paper. We used small convolution filters (3 x 3) to make architecture deeper. We increased convolutional layers for efficient learning of complex features from large dataset. We achieved better results by pushing convolutional layers up to 16 layers for HGG model. We achieved reliable and accurate results through fine-tuning among dataset and hyper-parameters. Pre-processing of this model includes generation of brain pipeline, intensity normalization, bias correction and data augmentation. We used the BRATS-2015, and Dice Similarity Coefficient (DSC) is used as performance measure for the evaluation of the proposed method. Our method achieved DSC score of 0.81 for complete, 0.79 for core, 0.80 for enhanced tumor regions. However, these results are comparable with methods already implemented 2D CNN architecture.

Keywords: brain tumor segmentation, convolutional neural networks, deep learning, HGG

Procedia PDF Downloads 227
4698 Study on Energy Performance Comparison of Information Centric Network Based on Difference of Network Architecture

Authors: Takumi Shindo, Koji Okamura

Abstract:

The first generation of the wide area network was circuit centric network. How the optimal circuit can be signed was the most important issue to get the best performance. This architecture had succeeded for line based telephone system. The second generation was host centric network and Internet based on this architecture has very succeeded world widely. And Internet became as new social infrastructure. Currently the architecture of the network is based on the location of the information. This future network is called Information centric network (ICN). The information-centric network (ICN) has being researched by many projects and different architectures for implementation of ICN have been proposed. The goal of this study is to compare performances of those ICN architectures. In this paper, the authors propose general ICN model which can represent two typical ICN architectures and compare communication performances using request routing. Finally, simulation results are shown. Also, we assume that this network architecture should be adapt to energy on-demand routing.

Keywords: ICN, information centric network, CCN, energy

Procedia PDF Downloads 314
4697 Pairwise Relative Primality of Integers and Independent Sets of Graphs

Authors: Jerry Hu

Abstract:

Let G = (V, E) with V = {1, 2, ..., k} be a graph, the k positive integers a₁, a₂, ..., ak are G-wise relatively prime if (aᵢ, aⱼ ) = 1 for {i, j} ∈ E. We use an inductive approach to give an asymptotic formula for the number of k-tuples of integers that are G-wise relatively prime. An exact formula is obtained for the probability that k positive integers are G-wise relatively prime. As a corollary, we also provide an exact formula for the probability that k positive integers have exactly r relatively prime pairs.

Keywords: graph, independent set, G-wise relatively prime, probability

Procedia PDF Downloads 71
4696 Graph Neural Networks and Rotary Position Embedding for Voice Activity Detection

Authors: YingWei Tan, XueFeng Ding

Abstract:

Attention-based voice activity detection models have gained significant attention in recent years due to their fast training speed and ability to capture a wide contextual range. The inclusion of multi-head style and position embedding in the attention architecture are crucial. Having multiple attention heads allows for differential focus on different parts of the sequence, while position embedding provides guidance for modeling dependencies between elements at various positions in the input sequence. In this work, we propose an approach by considering each head as a node, enabling the application of graph neural networks (GNN) to identify correlations among the different nodes. In addition, we adopt an implementation named rotary position embedding (RoPE), which encodes absolute positional information into the input sequence by a rotation matrix, and naturally incorporates explicit relative position information into a self-attention module. We evaluate the effectiveness of our method on a synthetic dataset, and the results demonstrate its superiority over the baseline CRNN in scenarios with low signal-to-noise ratio and noise, while also exhibiting robustness across different noise types. In summary, our proposed framework effectively combines the strengths of CNN and RNN (LSTM), and further enhances detection performance through the integration of graph neural networks and rotary position embedding.

Keywords: voice activity detection, CRNN, graph neural networks, rotary position embedding

Procedia PDF Downloads 41
4695 Neural Network Based Compressor Flow Estimator in an Aircraft Vapor Cycle System

Authors: Justin Reverdi, Sixin Zhang, Serge Gratton, Said Aoues, Thomas Pellegrini

Abstract:

In Vapor Cycle Systems, the flow sensor plays a key role in different monitoring and control purposes. However, physical sensors can be expensive, inaccurate, heavy, cumbersome, or highly sensitive to vibrations, which is especially problematic when embedded into an aircraft. The conception of a virtual sensor based on other standard sensors is a good alternative. In this paper, a data-driven model using a Convolutional Neural Network is proposed to estimate the flow of the compressor. To fit the model to our dataset, we tested different loss functions. We show in our application that a Dynamic Time Warping based loss function called DILATE leads to better dynamical performance than the vanilla mean squared error (MSE) loss function. DILATE allows choosing a trade-off between static and dynamic performance.

Keywords: deep learning, dynamic time warping, vapor cycle system, virtual sensor

Procedia PDF Downloads 125
4694 Problem Solving in Chilean Higher Education: Figurations Prior in Interpretations of Cartesian Graphs

Authors: Verónica Díaz

Abstract:

A Cartesian graph, as a mathematical object, becomes a tool for configuration of change. Its best comprehension is done through everyday life problem-solving associated with its representation. Despite this, the current educational framework favors general graphs, without consideration of their argumentation. Students are required to find the mathematical function without associating it to the development of graphical language. This research describes the use made by students of configurations made prior to Cartesian graphs with regards to an everyday life problem related to a time and distance variation phenomenon. The theoretical framework describes the function conditions of study and their modeling. This is a qualitative, descriptive study involving six undergraduate case studies that were carried out during the first term in 2016 at University of Los Lagos. The research problem concerned the graphic modeling of a real person’s movement phenomenon, and two levels of analysis were identified. The first level aims to identify local and global graph interpretations; a second level describes the iconicity and referentiality degree of an image. According to the results, students were able to draw no figures before the Cartesian graph, highlighting the need for students to represent the context and the movement of which causes the phenomenon change. From this, they managed Cartesian graphs representing changes in position, therefore, achieved an overall view of the graph. However, the local view only indicates specific events in the problem situation, using graphic and verbal expressions to represent movement. This view does not enable us to identify what happens on the graph when the movement characteristics change based on possible paths in the person’s walking speed.

Keywords: cartesian graphs, higher education, movement modeling, problem solving

Procedia PDF Downloads 197
4693 Glaucoma Detection in Retinal Tomography Using the Vision Transformer

Authors: Sushish Baral, Pratibha Joshi, Yaman Maharjan

Abstract:

Glaucoma is a chronic eye condition that causes vision loss that is irreversible. Early detection and treatment are critical to prevent vision loss because it can be asymptomatic. For the identification of glaucoma, multiple deep learning algorithms are used. Transformer-based architectures, which use the self-attention mechanism to encode long-range dependencies and acquire extremely expressive representations, have recently become popular. Convolutional architectures, on the other hand, lack knowledge of long-range dependencies in the image due to their intrinsic inductive biases. The aforementioned statements inspire this thesis to look at transformer-based solutions and investigate the viability of adopting transformer-based network designs for glaucoma detection. Using retinal fundus images of the optic nerve head to develop a viable algorithm to assess the severity of glaucoma necessitates a large number of well-curated images. Initially, data is generated by augmenting ocular pictures. After that, the ocular images are pre-processed to make them ready for further processing. The system is trained using pre-processed images, and it classifies the input images as normal or glaucoma based on the features retrieved during training. The Vision Transformer (ViT) architecture is well suited to this situation, as it allows the self-attention mechanism to utilise structural modeling. Extensive experiments are run on the common dataset, and the results are thoroughly validated and visualized.

Keywords: glaucoma, vision transformer, convolutional architectures, retinal fundus images, self-attention, deep learning

Procedia PDF Downloads 170
4692 Implementation in Python of a Method to Transform One-Dimensional Signals in Graphs

Authors: Luis Andrey Fajardo Fajardo

Abstract:

We are immersed in complex systems. The human brain, the galaxies, the snowflakes are examples of complex systems. An area of interest in Complex systems is the chaos theory. This revolutionary field of science presents different ways of study than determinism and reductionism. Here is where in junction with the Nonlinear DSP, chaos theory offer valuable techniques that establish a link between time series and complex theory in terms of complex networks, so that, the study of signals can be explored from the graph theory. Recently, some people had purposed a method to transform time series in graphs, but no one had developed a suitable implementation in Python with signals extracted from Chaotic Systems or Complex systems. That’s why the implementation in Python of an existing method to transform one dimensional chaotic signals from time domain to graph domain and some measures that may reveal information not extracted in the time domain is proposed.

Keywords: Python, complex systems, graph theory, dynamical systems

Procedia PDF Downloads 492
4691 Land Cover Remote Sensing Classification Advanced Neural Networks Supervised Learning

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 344
4690 Secure Content Centric Network

Authors: Syed Umair Aziz, Muhammad Faheem, Sameer Hussain, Faraz Idris

Abstract:

Content centric network is the network based on the mechanism of sending and receiving the data based on the interest and data request to the specified node (which has cached data). In this network, the security is bind with the content not with the host hence making it host independent and secure. In this network security is applied by taking content’s MAC (message authentication code) and encrypting it with the public key of the receiver. On the receiver end, the message is first verified and after verification message is saved and decrypted using the receiver's private key.

Keywords: content centric network, client-server, host security threats, message authentication code, named data network, network caching, peer-to-peer

Procedia PDF Downloads 620