scholarly journals An End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2064 ◽  
Author(s):  
Jelena Kocić ◽  
Nenad Jovičić ◽  
Vujo Drndarević
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Learning Algorithm ◽  
Autonomous Driving ◽  
Frame Rate ◽  
Power Cost ◽  
End To End

In this paper, one solution for an end-to-end deep neural network for autonomous driving is presented. The main objective of our work was to achieve autonomous driving with a light deep neural network suitable for deployment on embedded automotive platforms. There are several end-to-end deep neural networks used for autonomous driving, where the input to the machine learning algorithm are camera images and the output is the steering angle prediction, but those convolutional neural networks are significantly more complex than the network architecture we are proposing. The network architecture, computational complexity, and performance evaluation during autonomous driving using our network are compared with two other convolutional neural networks that we re-implemented with the aim to have an objective evaluation of the proposed network. The trained model of the proposed network is four times smaller than the PilotNet model and about 250 times smaller than AlexNet model. While complexity and size of the novel network are reduced in comparison to other models, which leads to lower latency and higher frame rate during inference, our network maintained the performance, achieving successful autonomous driving with similar efficiency compared to autonomous driving using two other models. Moreover, the proposed deep neural network downsized the needs for real-time inference hardware in terms of computational power, cost, and size.

scholarly journals End-to-End Autonomous Driving Through Dueling Double Deep Q-Network

2021 ◽  
Author(s):  
Baiyu Peng ◽  
Qi Sun ◽  
Shengbo Eben Li ◽  
Dongsuk Kum ◽  
Yuming Yin ◽  
...  
Keyword(s):  
Neural Network ◽  
State Space ◽  
Learning Algorithm ◽  
Rapid Development ◽  
Autonomous Driving ◽  
Saliency Map ◽  
Hierarchical Architecture ◽  
Link Type ◽  
The Neural Network ◽  
End To End

AbstractRecent years have seen the rapid development of autonomous driving systems, which are typically designed in a hierarchical architecture or an end-to-end architecture. The hierarchical architecture is always complicated and hard to design, while the end-to-end architecture is more promising due to its simple structure. This paper puts forward an end-to-end autonomous driving method through a deep reinforcement learning algorithm Dueling Double Deep Q-Network, making it possible for the vehicle to learn end-to-end driving by itself. This paper firstly proposes an architecture for the end-to-end lane-keeping task. Unlike the traditional image-only state space, the presented state space is composed of both camera images and vehicle motion information. Then corresponding dueling neural network structure is introduced, which reduces the variance and improves sampling efficiency. Thirdly, the proposed method is applied to The Open Racing Car Simulator (TORCS) to demonstrate its great performance, where it surpasses human drivers. Finally, the saliency map of the neural network is visualized, which indicates the trained network drives by observing the lane lines. A video for the presented work is available online, https://youtu.be/76ciJmIHMD8 or https://v.youku.com/v_show/id_XNDM4ODc0MTM4NA==.html.

scholarly journals A Survey on Techniques used in Medical Imaging Processing

2021 ◽  
Vol 2089 (1) ◽  
pp. 012013
Author(s):  
Priyadarshini Chatterjee ◽  
Dutta Sushama Rani
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Analysis ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Medical Image Analysis ◽  
Artificial Neural ◽  
Automated Screening ◽  
To Come

Abstract Automated diagnosis of diseases in the recent years have gain lots of advantages and potential. Specially automated screening of cancers has helped the clinicians over the time. Sometimes it is seen that the diagnosis of the clinicians is biased but automated detection can help them to come to a proper conclusion. Automated screening is implemented using either artificial inter connected system or convolutional inter connected system. As Artificial neural network is slow in computation, so Convolutional Neural Network has achieved lots of importance in the recent years. It is also seen that Convolutional Neural Network architecture requires a smaller number of datasets. This also provides them an edge over Artificial Neural Networks. Convolutional Neural Networks is used for both segmentation and classification. Image dissection is one of the important steps in the model used for any kind of image analysis. This paper surveys various such Convolutional Neural Networks that are used for medical image analysis.

Active Noise Control Using Multi-Layered Perceptron Neural Networks

1997 ◽  
Vol 16 (2) ◽  
pp. 109-144 ◽  
Author(s):  
M.O. Tokhi ◽  
R. Wood
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Noise Control ◽  
Learning Algorithm ◽  
Free Field ◽  
Active Noise Control ◽  
Three Dimensional ◽  
Broadband Noise ◽  
Active Noise

This paper presents the development of a neuro-adaptive active noise control (ANC) system. Multi-layered perceptron neural networks with a backpropagation learning algorithm are considered in both the modelling and control contexts. The capabilities of the neural network in modelling dynamical systems are investigated. A feedforward ANC structure is considered for optimum cancellation of broadband noise in a three-dimensional propagation medium. An on-line adaptation and training mechanism allowing a neural network architecture to characterise the optimal controller within the ANC system is developed. The neuro-adaptive ANC algorithm thus developed is implemented within a free-field environment and simulation results verifying its performance are presented and discussed.

scholarly journals Image Classification: A Survey

2020 ◽  
Vol 1 (2) ◽  
pp. 1-9
Author(s):  
Ankita Singh ◽  
◽  
Pawan Singh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Learning Ability ◽  
Final Decision

The Classification of images is a paramount topic in artificial vision systems which have drawn a notable amount of interest over the past years. This field aims to classify an image, which is an input, based on its visual content. Currently, most people relied on hand-crafted features to describe an image in a particular way. Then, using classifiers that are learnable, such as random forest, and decision tree was applied to the extract features to come to a final decision. The problem arises when large numbers of photos are concerned. It becomes a too difficult problem to find features from them. This is one of the reasons that the deep neural network model has been introduced. Owing to the existence of Deep learning, it can become feasible to represent the hierarchical nature of features using a various number of layers and corresponding weight with them. The existing image classification methods have been gradually applied in real-world problems, but then there are various problems in its application processes, such as unsatisfactory effect and extremely low classification accuracy or then and weak adaptive ability. Models using deep learning concepts have robust learning ability, which combines the feature extraction and the process of classification into a whole which then completes an image classification task, which can improve the image classification accuracy effectively. Convolutional Neural Networks are a powerful deep neural network technique. These networks preserve the spatial structure of a problem and were built for object recognition tasks such as classifying an image into respective classes. Neural networks are much known because people are getting a state-of-the-art outcome on complex computer vision and natural language processing tasks. Convolutional neural networks have been extensively used.

scholarly journals Baby Cry Detection in Domestic Environment using Convolutional Neural Networks

2020 ◽  
Vol 9 (7) ◽  
pp. 793-795
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Web Application ◽  
Well Being ◽  
Emotion Detection ◽  
Neural Network Architecture ◽  
Domestic Environment ◽  
The Neural Network

In this paper we will identify a cry signals of infants and the explanation behind the screams below 0-6 months of segment age. Detection of baby cry signals is essential for the pre-processing of various applications involving crial analysis for baby caregivers, such as emotion detection. Since cry signals hold baby well-being information and can be understood to an extent by experienced parents and experts. We train and validate the neural network architecture for baby cry detection and also test the fastAI with the neural network. Trained neural networks will provide a model and this model can predict the reason behind the cry sound. Only the cry sounds are recognized, and alert the user automatically. Created a web application by responding and detecting different emotions including hunger, tired, discomfort, bellypain.

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 Design and Optimization of a Deep Neural Network Architecture for Traffic Light Detection

2020 ◽  
Vol 77 ◽  
pp. 01002
Author(s):  
Tomohide Fukuchi ◽  
Mark Ogbodo Ikechukwu ◽  
Abderazek Ben Abdallah
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Deep Neural Network ◽  
Autonomous Driving ◽  
Research Trend ◽  
Traffic Light ◽  
Light Detection ◽  
Driving System ◽  
Design And Optimization ◽  
Autonomous Driving System

Autonomous Driving has recently become a research trend and efficient autonomous driving system is difficult to achieve due to safety concerns, Applying traffic light recognition to autonomous driving system is one of the factors to prevent accidents that occur as a result of traffic light violation. To realize safe autonomous driving system, we propose in this work a design and optimization of a traffic light detection system based on deep neural network. We designed a lightweight convolution neural network with parameters less than 10000 and implemented in software. We achieved 98.3% inference accuracy with 2.5 fps response time. Also we optimized the input image pixel values with normalization and optimized convolution layer with pipeline on FPGA with 5% resource consumption.

scholarly journals Approximating the Steady-state Temperature of 3D Electronic Systems with Convolutional Neural Networks

2021 ◽  
Author(s):  
Monika Stipsitz ◽  
Hèlios Sanchis-Alepuz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Training Dataset ◽  
Electronic Systems ◽  
Long Range Correlations ◽  
Steady State Temperature ◽  
Thermal Simulations

Thermal simulations are an important part in the design of electronic systems, especially as systems with high power density become common. In simulation-based design approaches, a considerable amount of time is spent by repeated simulations. In this work, we present a proof-of-concept study of the application of convolutional neural networks to accelerate those thermal simulations. The goal is not to replace standard simulation tools but to provide a method to quickly select promising samples for more detailed investigations. Based on a training set of randomly generated circuits with corresponding Finite Element solutions, the full 3D steady-state temperature field is estimated using a fully convolutional neural network. A custom network architecture is proposed which captures the long-range correlations present in heat conduction problems. We test the network on a separate dataset and find that the mean relative error is around 2 % and the typical evaluation time is 35 ms per sample ( 2 ms for evaluation, 33 ms for data transfer). The benefit of this neural-network-based approach is that, once training is completed, the network can be applied to any system within the design space spanned by the randomised training dataset (which includes different components, material properties, different positioning of components on a PCB, etc.).

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.

Sign in / Sign up

Export Citation Format

Share Document