scholarly journals A mixed-scale dense convolutional neural network for image analysis

2017 ◽  
Vol 115 (2) ◽  
pp. 254-259 ◽  
Author(s):  
Daniël M. Pelt ◽  
James A. Sethian
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Network Architecture ◽  
Training Data ◽  
Network Architectures ◽  
Feature Maps ◽  
Deep Convolutional Neural Networks ◽  
Single Set ◽  
Reduced Risk

Deep convolutional neural networks have been successfully applied to many image-processing problems in recent works. Popular network architectures often add additional operations and connections to the standard architecture to enable training deeper networks. To achieve accurate results in practice, a large number of trainable parameters are often required. Here, we introduce a network architecture based on using dilated convolutions to capture features at different image scales and densely connecting all feature maps with each other. The resulting architecture is able to achieve accurate results with relatively few parameters and consists of a single set of operations, making it easier to implement, train, and apply in practice, and automatically adapts to different problems. We compare results of the proposed network architecture with popular existing architectures for several segmentation problems, showing that the proposed architecture is able to achieve accurate results with fewer parameters, with a reduced risk of overfitting the training data.

Product Identification Using Image Processing and Radial Basis Function Neural Networks

2015 ◽  
Vol 761 ◽  
pp. 120-124
Author(s):  
K.A.A. Aziz ◽  
Abdul Kadir ◽  
Rostam Affendi Hamzah ◽  
Amat Amir Basari
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Radial Basis Function ◽  
Basis Function ◽  
Network Architecture ◽  
Rbf Neural Networks ◽  
Specific Product ◽  
Product Identification ◽  
Radial Basis

This paper presents a product identification using image processing and radial basis function neural networks. The system identified a specific product based on the shape of the product. An image processing had been applied to the acquired image and the product was recognized using the Radial Basis Function Neural Network (RBFNN). The RBF Neural Networks offer several advantages compared to other neural network architecture such as they can be trained using a fast two-stage training algorithm and the network possesses the property of best approximation. The output of the network can be optimized by setting suitable values of the center and the spread of RBF. In this paper, fixed spread value was used for every cluster. The system can detect all the four products with 100% successful rate using ±0.2 tolerance.

Application of convolutional neural networks for monitoring of marine objects

2020 ◽  
pp. 53-61
Author(s):  
Н.А. Полковникова ◽  
Е.В. Тузинкевич ◽  
А.Н. Попов
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Research Process ◽  
Probability Of Detection ◽  
Neural Network Architecture ◽  
Deep Convolutional Neural Networks

В статье рассмотрены технологии компьютерного зрения на основе глубоких свёрточных нейронных сетей. Применение нейронных сетей особенно эффективно для решения трудно формализуемых задач. Разработана архитектура свёрточной нейронной сети применительно к задаче распознавания и классификации морских объектов на изображениях. В ходе исследования выполнен ретроспективный анализ технологий компьютерного зрения и выявлен ряд проблем, связанных с применением нейронных сетей: «исчезающий» градиент, переобучение и вычислительная сложность. При разработке архитектуры нейросети предложено использовать функцию активации RELU, обучение некоторых случайно выбранных нейронов и нормализацию с целью упрощения архитектуры нейросети. Сравнение используемых в нейросети функций активации ReLU, LeakyReLU, Exponential ReLU и SOFTMAX выполнено в среде Matlab R2020a. На основе свёрточной нейронной сети разработана программа на языке программирования Visual C# в среде MS Visual Studio для распознавания морских объектов. Программапредназначена для автоматизированной идентификации морских объектов, производит детектирование (нахождение объектов на изображении) и распознавание объектов с высокой вероятностью обнаружения. The article considers computer vision technologies based on deep convolutional neural networks. Application of neural networks is particularly effective for solving difficult formalized problems. As a result convolutional neural network architecture to the problem of recognition and classification of marine objects on images is implemented. In the research process a retrospective analysis of computer vision technologies was performed and a number of problems associated with the use of neural networks were identified: vanishing gradient, overfitting and computational complexity. To solve these problems in neural network architecture development, it was proposed to use RELU activation function, training some randomly selected neurons and normalization for simplification of neural network architecture. Comparison of ReLU, LeakyReLU, Exponential ReLU, and SOFTMAX activation functions used in the neural network implemented in Matlab R2020a.The computer program based on convolutional neural network for marine objects recognition implemented in Visual C# programming language in MS Visual Studio integrated development environment. The program is designed for automated identification of marine objects, produces detection (i.e., presence of objects on image), and objects recognition with high probability of detection.

scholarly journals Classification of Partial Discharge Images Using Deep Convolutional Neural Networks

Energies ◽  
2020 ◽  
Vol 13 (20) ◽  
pp. 5496 ◽  
Author(s):  
Marek Florkowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Electric Fields ◽  
High Voltage ◽  
Network Architecture ◽  
Partial Discharge ◽  
Electrical Insulation ◽  
Deep Convolutional Neural Networks ◽  
Insulation Systems

Artificial intelligence-based solutions and applications have great potential in various fields of electrical power engineering. The problem of the electrical reliability of power equipment directly refers to the immunity of high-voltage (HV) insulation systems to operating stresses, overvoltages and other stresses—in particular, those involving strong electric fields. Therefore, tracing material degradation processes in insulation systems requires dedicated diagnostics; one of the most reliable quality indicators of high-voltage insulation systems is partial discharge (PD) measurement. In this paper, an example of the application of a neural network to partial discharge images is presented, which is based on the convolutional neural network (CNN) architecture, and used to recognize the stages of the aging of high-voltage electrical insulation based on PD images. Partial discharge images refer to phase-resolved patterns revealing various discharge stages and forms. The test specimens were aged under high electric stress, and the measurement results were saved continuously within a predefined time period. The four distinguishable classes of the electrical insulation degradation process were defined, mimicking the changes that occurred within the electrical insulation in the specimens (i.e., start, middle, end and noise/disturbance), with the goal of properly recognizing these stages in the untrained image samples. The results reflect the exemplary performance of the CNN and its resilience to manipulations of the network architecture and values of the hyperparameters. Convolutional neural networks seem to be a promising component of future autonomous PD expert systems.

scholarly journals Rumor Detection Based on SAGNN: Simplified Aggregation Graph Neural Networks

2021 ◽  
Vol 3 (1) ◽  
pp. 84-94
Author(s):  
Liang Zhang ◽  
Jingqun Li ◽  
Bin Zhou ◽  
Yan Jia
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Network Architectures ◽  
Neural Network Architecture ◽  
Convolutional Networks ◽  
Effective Manner ◽  
Deep Learning Network ◽  
Graph Neural Networks ◽  
Rumor Detection

Identifying fake news on media has been an important issue. This is especially true considering the wide spread of rumors on popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

scholarly journals APLIKASI PENGENALAN PLAT NOMOR KENDARAAN DI UNIVERSITAS RIAU

2019 ◽  
Vol 9 (3) ◽  
pp. 47-52
Author(s):  
Noprizal ◽  
Feri Candra
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Artificial Neural Network ◽  
Digital Image Processing ◽  
Digital Image ◽  
Training Data ◽  
License Plate ◽  
Backpropagation Method ◽  
Artificial Neural

Abstract Vehicle license plate recognition application has been found in shopping centers, university, and other agency buildings with various methods of recognition. Some examples of methods used such as digital image processing techniques, neural networks and so forth. This study makes an application for the introduction of license plates, especially for student vehicle license plates in the university area. This application is developed with Digital Image Processing Methods and Artificial Neural Networks. In this study, 900 training data are used, taken from 200 photo vehicle number plates, to train 36 characters that contain 26 alphabets and 10 decimal numbers. The training data is used to test 30 photos of vehicle license plates. Plate photos used as training and testing data are the Indonesian standard with black and white plates. Artificial Neural Network used to recognize vehicle license plate by using the Backpropagation method with parameters Epoch 1000, Hidden layer1 with node 60, Hidden layer2 with node 55, Goal 0.001. The final conclusion of this Study shows that the use of Artificial Neural Network Backpropagation method is very good, with the best testing accuracy obtained, namely 98% and 1.25 error. Keywords : digital image processing, artificial neural networks, vehicle license plate Abstrak Aplikasi pengenalan plat nomor kendaraan sudah banyak ditemukan di pusat perbelanjaan, universitas, dan gedung instansi dengan berbagai metode pengenalan. Beberapa contoh metode yang digunakan seperti teknik pengolahan citra digital, jaringan syaraf tiruan dan lain sebagainya. Disini penulis membuat sebuah aplikasi pengenalan plat nomor kendaraan khususnya untuk plat nomor kendaraan mahasiswa yang ada dilikungan Universitas Riau. Aplikasi ini dikembangkan dengan metode pengolahan citra digital dan jaringan syaraf tiruan. Pada penelitian ini, digunakan 700 data pelatihan yang diambil dari 200 foto plat nomor, untuk melatih 36 karakter. Data pelatihan tersebut kemudian digunakan untuk menguji 30 foto plat nomor kendaraan. Foto plat yang dijadikan untuk data pelatihan dan pengujian yaitu plat standar indonesia yang berwarna hitam dan putih. Jaringan syaraf tiruan yang digunakan untuk melakukan pengenalan yaitu dengan Metode Backpropagation dengan parameter Epoch 1000, Hidden layer1 dengan jumlah node 60, Hidden layer2 dengan jumlah node 55, Goal  0,001. Kesimpulan akhir dari penelitian ini yaitu menunjukan bahwa penggunaan Metode Backpropagation jaringan syaraf tiruan ini sangat bagus, dengan akurasi pengujian terbaik yang didapat yaitu 98% dengan eror 1,25. Kata kunci: pengolahan citra digital, jaringan syaraf tiruan, Backpropagation, plat nomor  

scholarly journals CommNets: Communicating Neural Network Architectures for Resource Constrained Systems

2019 ◽  
Vol 33 ◽  
pp. 9909-9910
Author(s):  
Prince M Abudu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Network Architecture ◽  
Resource Constraints ◽  
Constrained Systems ◽  
Detection Accuracy ◽  
Network Architectures ◽  
Operating Environments ◽  
Hidden States

Applications that require heterogeneous sensor deployments continue to face practical challenges owing to resource constraints within their operating environments (i.e. energy efficiency, computational power and reliability). This has motivated the need for effective ways of selecting a sensing strategy that maximizes detection accuracy for events of interest using available resources and data-driven approaches. Inspired by those limitations, we ask a fundamental question: whether state-of-the-art Recurrent Neural Networks can observe different series of data and communicate their hidden states to collectively solve an objective in a distributed fashion. We realize our answer by conducting a series of systematic analyses of a Communicating Recurrent Neural Network architecture on varying time-steps, objective functions and number of nodes. The experimental setup we employ models tasks synonymous with those in Wireless Sensor Networks. Our contributions show that Recurrent Neural Networks can communicate through their hidden states and we achieve promising results.

scholarly journals Optimizing Artificial Neural Networks For The Evaluation Of Asphalt Pavement Structural Performance

2019 ◽  
Vol 14 (1) ◽  
pp. 58-79 ◽  
Author(s):  
Gaetano Bosurgi ◽  
Orazio Pellegrino ◽  
Giuseppe Sollazzo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Performance Evaluation ◽  
Network Architecture ◽  
Training Data ◽  
Structural Performance ◽  
Reliable Technique ◽  
Artificial Neural

Artificial Neural Networks represent useful tools for several engineering issues. Although they were adopted in several pavement-engineering problems for performance evaluation, their application on pavement structural performance evaluation appears to be remarkable. It is conceivable that defining a proper Artificial Neural Network for estimating structural performance in asphalt pavements from measurements performed through quick and economic surveys produces significant savings for road agencies and improves maintenance planning. However, the architecture of such an Artificial Neural Network must be optimised, to improve the final accuracy and provide a reliable technique for enriching decision-making tools. In this paper, the influence on the final quality of different features conditioning the network architecture has been examined, for maximising the resulting quality and, consequently, the final benefits of the methodology. In particular, input factor quality (structural, traffic, climatic), “homogeneity” of training data records and the actual net topology have been investigated. Finally, these results further prove the approach efficiency, for improving Pavement Management Systems and reducing deflection survey frequency, with remarkable savings for road agencies.

scholarly journals Novel convolutional neural networks for efficient classification of rotated and scaled images

2021 ◽  
Author(s):  
Paweł Tarasiuk ◽  
Piotr S. Szczepaniak
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Network Models ◽  
Input Image ◽  
Feature Maps ◽  
Neural Network Models ◽  
Geometric Transformations

AbstractThis paper presents a novel method for improving the invariance of convolutional neural networks (CNNs) to selected geometric transformations in order to obtain more efficient image classifiers. A common strategy employed to achieve this aim is to train the network using data augmentation. Such a method alone, however, increases the complexity of the neural network model, as any change in the rotation or size of the input image results in the activation of different CNN feature maps. This problem can be resolved by the proposed novel convolutional neural network models with geometric transformations embedded into the network architecture. The evaluation of the proposed CNN model is performed on the image classification task with the use of diverse representative data sets. The CNN models with embedded geometric transformations are compared to those without the transformations, using different data augmentation setups. As the compared approaches use the same amount of memory to store the parameters, the improved classification score means that the proposed architecture is more optimal.

scholarly journals Overview of Tool Wear Monitoring Methods Based on Convolutional Neural Network

2021 ◽  
Vol 11 (24) ◽  
pp. 12041
Author(s):  
Qun Wang ◽  
Hengsheng Wang ◽  
Liwei Hou ◽  
Shouhua Yi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Tool Wear ◽  
Network Architecture ◽  
Manufacturing Systems ◽  
Convolution Neural Network ◽  
Tool Wear Monitoring ◽  
Monitoring Methods ◽  
Deep Convolutional Neural Networks ◽  
Wear Monitoring

Tool wear monitoring is of great significance for the development of manufacturing systems and intelligent manufacturing. Online tool condition monitoring is a crucial technology for cost reduction, quality improvement, and manufacturing intelligence in modern manufacturing. However, it remains a difficult problem to monitor the status of tools online, in real-time and accurately in the industry. In the research status of mainstream technology, the convolution neural network may be a good solution to this problem, based on the appropriate sensor system and correct signal processing methods. Therefore, this paper outlines the state-of-the-art systems encountered in the open access literature, focusing on information collection, feature selection–extraction technologies based on deep convolutional neural networks, and monitoring network architecture and modeling methods. Based on typical cases, this paper focuses on the application of the convolution neural network in tool wear monitoring. From the application results, it is feasible and reliable to apply convolution neural networks in tool wear monitoring. Additionally, it can improve the prediction accuracy, which is of great significance for the future development of technology. This paper can be a guide for the researchers and manufacturers in the area of tool wear monitoring for explaining the latest trends and requirements.

Sign in / Sign up

Export Citation Format

Share Document