全部
期刊
图书
会议
学位论文
当前检索条件:
关键词: TensorFlow>
已选文献 0 清除 导出文献
主题排序 时间排序
497 结果
  • 17
每页显示  
Book Chapter
摘要: Advances in Surveillance Vehicles have opened forums for applications, one of which is military supervision. Its adaptability and monitoring of a highly secret area allow it to swiftly identify targets and any safety issues. Identifying targets or in simple words detecting them with their 3-dimensional characteristics, gives us a much-evolved vehicle. The goal of this research is to recognize items in rural regions that are highly complicated, as well as to evaluate precision and computational c关键词: Surveillance vehicle;Object detection;Classification;TensorFlow GPU;Faster-RCNN;3-dimensional;MeshLab;COLMAP
收藏原文链接
Book Chapter
摘要: Existing ROS packages for object detection are based on traditional template matching techniques. They are used to identify only a few classes and cannot be adjusted to detect new classes. These methods also fail with changes in parameters like lighting, shape, size and orientation. Deep learning-based object detection can overcome these drawbacks and are also more accurate compared to traditional methods. Therefore, few shot object detection is attempted with the help of TensorFlow object detec关键词: Mobile robots;Robot Operating System (ROS);Gazebo;Raspberry Pi;Arduino;Transfer learning;Few shot object detection;TensorFlow object detection API
收藏原文链接
Journal
摘要: The effects of the global pandemic are wide spreading. Many sectors like tourism and recreation have been temporarily suspended, but sectors like construction, development and maintenance have not been halted due to their importance to society. Such projects involve people working together in close proximity, thus leaving them susceptible to infection. It is recommended that people maintain social distance and wear a face mask to reduce the spread of COVID-19. To this effect, we propose COVID Vi关键词: Computer vision convolutional neural networks Haar cascade classifier;Keras;Machine learning TensorFlow
收藏原文链接
Book Chapter
摘要: Wind turbine blade failure will reduce power generation efficiency and increase operating costs. Serious faults will lead to production accidents. In this paper, a method of blade fault diagnosis based on deep learning algorithm is proposed. Mask-rcnn model is used to identify the defects in blade images, and the method is verified by the pictures of unmanned aerial vehicle (UAV) patrolling blades. Good recognition results are obtained. Most of the blade defects can be identified and the phenome关键词: Wind turbines blade;Fault diagnosis;Deep learning;Mask-rcnn;Tensorflow
收藏原文链接
Book Chapter
Sapra Vernika;Gupta Rohan;Sharma Parikshit;Grover Rashika;Sapra Urvashi;
摘要: The universal dissemination of Covid-19 due to the SARS-COV-2 virus has increased the inclination of the world in the backward direction, where it is dallying from its substantial growth approximately by 5 years and is worsening day-by-day. People are suffering from this disease and are trying to fight against it, by taking enormous precautions for themselves like cleansing their hands at regular intervals, wearing single or double-layered masks, eating healthy and home-cooked food, and working 关键词: Pandemic;Wireless communication;Keras;TensorFlow;OpenCV
收藏原文链接
Book Chapter
摘要: Farming system can improve more by using innovative technologies that will help us to improve the quality and quantity of agricultural production. Nowadays, plant leaf diseases are the major drawbacks for the crop yields, and it is reducing the production and its quality because of that we are facing major threats on food security. The proposed system will be very helpful to reduce the diseases on frond to get more effective crop by using this technique. So this system will be helpful to the far关键词: Disease detection;Deep learning;AlexNet;LeNet;TensorFlow
收藏原文链接
Book Chapter
摘要: In this chapter we will provide an introductory knowledge of Neural Network and Deep Learning and we will use those two words interchangeably meaning the same. Neural network has evolved from a concept of simulating human brain recognition of images through communication involving neurons. We will analyze how handwritten digits can be recognized effectively using neural network techniques. Neural network as a part of statistical learning methods evolved more than 50 years and it got new energy b关键词: Neural network;Artificial neural network;Convolutional neural network;TensorFlow
收藏原文链接
Book Chapter
摘要: According to a recent study, almost 70% of smartphone users experience random app pop-ups that interrupt what they are doing on their phone and they are hard to close out (Samadiani et al., Sensors 19(8):1863 (2019) []). Most of the time it is an ad for a game and other times it is an ad for insurance. Some pop-ups make noise and some do not. It is irritating for a person when he/she is listening to music on YouTube and it totally stops the song altogether and after that, the ad just stays on an关键词: Keras;CNN;CVV;Tensorflow;Image classification;Algorithms
收藏原文链接
Journal
摘要: A computational fluid dynamics (CFD) simulation framework for fluid-flow prediction is developed on the Tensor Processing Unit (TPU) platform. The TPU architecture is featured with accelerated dense matrix multiplication, large high bandwidth memory, and a fast inter-chip interconnect, making it attractive for high-performance scientific computing. The CFD framework solves the variable-density Navier-Stokes equation using a low-Mach approximation, and the governing equations are discretized by a关键词: Tensor processing unit;TensorFlow;Computational fluid dynamics;High performance computing
收藏原文链接
Journal
摘要: Since the outbreak of COVID-19 pandemic, enormous development has been done in computer vision systems in face masks and temperature detection. To enforce the mandate for wearing the mask in public places, the authors have suggested a solution using transfer learning (MobileNetV2) architecture as a foundation for image classification. The proposed solution is embedded devices with Raspberry Pi4 and python packages viz TensorFlow, OpenCV, and Keras. In this Work, a combination of transfer learnin关键词: Keywords;Transfer learning;MobileNetV2;Raspberry Pi4;Sensors;Face mask;Temperature Detection;Thinkspeak;Cloud;TensorFlow;and LCD
收藏原文链接
Book Chapter
摘要: Nowadays, with the rapid development of science and technology, many methods of object recognition have appeared. The most well-known of them are used to obtain more accurate information about the recognized object. Drones are usually used to obtain information in the locality. Modern drones can be used to collect information about the objects that surround us. Neural networks can process this information much more effectively than humans can. In this article is discussed a method to recognize o关键词: Machine learning;Neural network;UGV;Tensorflow
收藏原文链接
Journal
摘要: The important, while mostly underestimated, step in the process of short-term load forecasting–STLF is the selection of similar days. Similar days are identified based on numerous factors, such as weather, time, electricity prices, geographical conditions and consumers’ types. However, those factors influence the load differently within different circumstances and conditions. To investigate and optimise the similar days selection process, a new forecasting method, named Genetic algorithm-based–s关键词: artificial neural networks;effectiveness;hybrid method;STLF;genetic algorithm;tensorflow
收藏原文链接
Journal
摘要: Timely information on land use, vegetation coverage, and air and water quality, are crucial for monitoring and managing territories, especially for areas in which there is dynamic urban expansion. However, getting accessible, accurate, and reliable information is not an easy task, since the significant increase in remote sensing data volume poses challenges for the timely processing and analysis of the resulting massive data volume. From this perspective, classical methods for urban monitoring p关键词: urban sprawl;data fusion;Sentinel-2;Copernicus;synthetic aperture radar;deep learning;Google Earth Engine;TensorFlow;COVID-19;decision support system
收藏原文链接
Book Chapter
Osman Anas;Abid Usman;Gemma Luca;Perotto Matteo;Brunelli Davide;
摘要: Recent advances in state-of-the-art ultra-low power embedded devices for machine learning (ML) have permitted a new class of products whose key features enable ML capabilities on microcontrollers with less than 1 mW power consumption (TinyML). TinyML provides a unique solution by aggregating and analyzing data at the edge on low-power embedded devices. However, we have only recently been able to run ML on microcontrollers, and the field is still in its infancy, which means that hardware, softwar关键词: TinyML;Microcontrollers;Tensorflow Lite Micro;CUBE AI;IoT
收藏原文链接
Journal
摘要: Deep learning-based object detection technology can efficiently infer results by utilizing graphics processing units (GPU). However, when using general deep learning frameworks in embedded systems and mobile devices, processing functionality is limited. This allows deep learning frameworks such as TensorFlow-Lite (TF-Lite) and TensorRT (TRT) to be optimized for different hardware. Therefore, this paper introduces a performance inference method that fuses the Jetson monitoring tool with TensorFlo关键词: deep learning;embedded system;Nvidia Jetson platform;TensorFlow;TensorRT;YOLO
收藏原文链接
Journal
KhoKhar Fahad Ahmed;Shah Jamal Hussain;Khan Muhammad Attique;Sharif Muhammad;Tariq Usman;Kadry Seifedine;
Computers and Electrical EngineeringVolume 99, Issue , 2022, PP
摘要: Nowadays, data privacy is an important consideration in machine learning. This paper provides an overview of how Federated Learning can be used to improve data security and privacy. Federated Learning is made up of three distinct architectures that ensure that privacy is never jeopardised. Federated learning is a type of collective learning in which individual edge devices are trained and then aggregated on the server without sharing edge device data. On the other hand, federated learning provid关键词: Ederated learning;Data privacy;Edge computing;Secure communication;Tensorflow federated
收藏原文链接
Journal
摘要: Yellow journalism has increased the spread of hyperpartisan news on the internet. It is very difficult for online news article readers to distinguish hyperpartisan news articles from mainstream news articles. There is a need for an automated model that can detect hyperpartisan news on the internet and tag them as hyperpartisan so that it is very easy for readers to avoid that news. A hyperpartisan news detection article was developed by using three different natural language processing technique关键词: BERT;Transformers;Word embedding's;ELMo;NLP;Word2vec;Tensorflow;Bidirectional
收藏原文链接
Journal
摘要: With the increase in the usage of mobile devices such as smartphones, laptops, smartwatches, etc., access to information and communication has been effortless and convenient. Thus, making Raspberry Pi, an Android device, has been made. LineageOS is used specifically as an operating system that Konstakang developed. With CNN's MobileNet architecture and transfer learning, the classification for papaya leaf disease was a success. MobileNet Architecture was retrained using the images of the followi关键词: convolutional neural networks;transfer learning;MobileNet;plant disease identification;TensorFlow;lineage OS
收藏原文链接
Book Chapter
摘要: Healthcare industry is increasingly adopting artificial intelligence in analyzing laboratory and radiology outputs to provide optimal treatments for patients. Medical imaging has been playing an important role in understanding several underlying conditions of patients. With rise in incidents of cardiac diseases world-wide, usage of computer vision and deep learning methods are proving to be very useful in detecting anomalies that are conventionally done using human perception. This paper aims at关键词: Artificial intelligence;Healthcare;Deep learning;Neural networks;Automated segmentation of heart;Convolutional neural network;U-Net;Ejection fraction;TensorFlow
收藏原文链接
Book Chapter
摘要: Road accidents are without a doubt the most incessant and lethal happenings across the nation. Every year, a huge number of individuals lose their lives, and the same number or more face extreme wounds. Expanded monetary advancement has brought an expansion in the vehicle division in the nation. This led to a huge increase in street traffic and ‘speed’, which is one of the fundamental reasons for vehicle accidents. Drivers with different records of street petty criminal offenses, for example, sp关键词: Accident detection;Intelligent transportation systems;Neural networks;TensorFlow object detection
收藏原文链接
Book Chapter
Kipli Kuryati;Hui Lee Yee;Tajudin Nurul Mirza Afiqah;Sapawi Rohana;Sahari Siti Kudnie;Mat Dayang Azra Awang;Jalil M. A.;Ray Kanad;Shamim Kaiser M.;Mahmud Mufti;
摘要: The key to preventing blindness caused by diabetic retinopathy (DR) is regular screening and early recognition during its early stages. Currently, DR grading is done manually by ophthalmologists and trained graders where the process is time-consuming. Therefore, this paper aims to develop a mobile app that can provide DR detection and grading without a professional or doctor. The patients will be referred to ophthalmologists if further evaluations are required. This research builds an image clas关键词: Diabetic retinopathy;Image classification;Mobile application;Google TensorFlow;Google cloud platform;Cloud AutoML
收藏原文链接
Journal
摘要: This study is aimed to analyze the characteristics of different kinds of time-of-flight diffraction (TOFD) images for welding seam defects. Combined with the image recognition technology of artificial intelligence, a deep learning neural network program based on TensorFlow was developed and applied to the training and recognition of welding seam defects in ultrasonic TOFD images. The results showed that, after training, the program could identify typical welding seam defects such as stoma, crack关键词: image recognition;TensorFlow;TOFD images;welding seam defect
收藏原文链接
Book Chapter
摘要: The internet of Things (IoT) technology is present in all aspects of our modern lives, and its standard usage is increasing remarkably. But their inherent limitations in size, storage memory, and power consumption limit its specific functionality in the secure transmission of sensitive information, where the development of lightweight ciphers responds adequately to these limitations. However, the conventional cryptanalysis of these modern ciphers can be impractical or demonstrate apparent limita关键词: Tensorflow;Deep learning;Neural networks;Cryptanalysis;Lightweight cipher;Attack;Internet of Things
收藏原文链接
Journal
摘要: It is no longer a fresh thing to use convolutional neural networks to classify images. The most common experiment is to use CNN for handwritten digit recognition. However, the pictures used for training in the recognition just have two colors of black and white while which mostly are colored in the real world. As a result, more complex models need to be designed for training and classification. This article mainly does the following work: Study the principle of CNN and its application on graph c关键词: TensorFlow; Convolutional neural network; Graph classification.
收藏原文链接
Journal
摘要: Several factors are motivating the development of preventive, personalized, connected, virtual, and ubiquitous healthcare services. These factors include declining public health, increase in chronic diseases, an ageing population, rising healthcare costs, the need to bring intelligence near the user for privacy, security, performance, and costs reasons, as well as COVID-19. Motivated by these drivers, this paper proposes, implements, and evaluates a reference architecture called Imtidad that pro关键词: tiny AI;tiny ML;distributed AI as a service (DAIaaS);fog computing;edge computing;cloud computing;skin disease diagnosis;healthcare;smart societies;smart cities;smart healthcare;reference architecture;TensorFlow
收藏原文链接
Journal
Bucinsky Lukas;Bortňák Dušan;Gall Marián;Matúška Ján;Milata Viktor;Pitoňák Michal;Štekláč Marek;Végh Daniel;Zajaček Dávid;
Computational Biology and ChemistryVolume 98, Issue prepublish, 2022, PP 107656-
摘要: Molecular docking results of two training sets containing 866 and 8,696 compounds were used to train three different machine learning (ML) approaches. Neural network approaches according to the Keras and TensorFlow libraries and the gradient boosted decision trees approach of XGBoost were used with DScribe’s Smooth Overlap of Atomic Positions molecular descriptors. In addition, neural networks using the SchNetPack library and descriptors were used. The ML performance was tested on three differen关键词: AutoDock molecular docking;3CLpro Mpro 6WQF;machine learning;TensorFlow XGBoost SchNetPack;COVID19;SARS-CoV-2
收藏原文链接
Book Chapter
摘要: The paper proposes a universal architecture of a convolutional neural network designed to recognize road signs and traffic lights on a video frame. The main aim was to simultaneously recognize objects of different classes, such as road signs and traffic lights of different types, by one neural network at the same processing step simultaneously. The neural network implementation was based on Keras and TensorFlow for classification and OpenCV to highlight the contours of possible road signs and tr关键词: Object recognition;Video processing;CNN;Keras;OpenCV;TensorFlow
收藏原文链接
Book Chapter
摘要: Our world is going through a lot of misery due to the outbreak of coronavirus disease (COVID-19) from the end of 2019 affecting many people’s livelihood and causing deaths. Wearing a face mask has become very normal today as the whole world is trying to recover back to normalcy and continue their activities. Therefore, it has become crucial to implement this policy especially in public areas, offices, etc. Constant monitoring cannot be done on every individual. Hence, technology plays a prominen关键词: Convolutional neural network (CNN);Cascaded classifier (Haar cascade classifier);TensorFlow;Keras;OpenCV;Accuracy;Loss score
收藏原文链接
Book Chapter
摘要: Social distancing is the term that has surprised the entire world and is affected our lives in ways we never imagined. With the ease of lockdown rules, it is expected that working population would hit the roads and population density would increase at public places. Hence, maintaining social distancing has become an important issue. So, our idea to develop an AI model that recognizes whether an individual is following social distancing and simultaneously are wearing masks. The whole device is pl关键词: Social distancing;Mask detection;Image processing;Obstacle avoiding;OpenCV;TensorFlow
收藏原文链接
Journal
Merkelbach Kilian;Schweidtmann Artur M.;Müller Younes;Schwoebel Patrick;Mhamdi Adel;Mitsos Alexander;Schuppert Andreas;Mrziglod Thomas;Schneckener Sebastian;
Computers & Chemical EngineeringVolume , Issue prepublish, 2022, PP 107736-
摘要: Hybrid modelling, i.e., the combination of data-driven modelling with mechanistic model components, reduces the data demand and enables extrapolation of data-driven models. However, building, training and evaluation of hybrid models is cumbersome with current frameworks. We developed HybridML, an open-source modeling platform, in which hybrid models can be trained, i.e., combinations of artificial neural networks, arithmetic expressions, and differential equations. We employ TensorFlow for artif关键词: Hybrid modeling;Machine Learning;Modeling tools;Tensorflow;Python;pharmacokinetics
收藏原文链接
回到顶部