检索结果-内蒙古大学图书馆

Two-Stage Merging Network for Describing Traffic Scenes in Intelligent Vehicle Driving System

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第12期23卷 25509-25520页

作者： Song, Heng Zhu, Junwu Jiang, Yi Yangzhou Univ Inst Informat Engn Yangzhou 225127 Jiangsu Peoples R China

Intelligent vehicle driving systems aim to control the driving behavior of a vehicle in real time without human intervention by perceiving and monitoring the surrounding environment. Describing images of traffic scenes automatically, which is one of the key problems of intelligent vehicle driving technology, has drawn attention since its inception. In recent years, a variety of automatic image description technologies have been proposed, among which the attention-based encoder-decoder framework achieved good results. In this paper we will discuss the fusing of a variety of information from multiple aspects of the images of traffic scenes. First, we will introduce visual attention, text attention and image topics attention which generates the weighted visual features, the attentive text information and the global image topics information respectively. We will then propose an adaptive two-stage merging network based on an encoder-decoder framework, which can fully integrate the three kinds of information in two stages, while automatically calculating the proportions of the information at each time step. Numerous experiments conducted on COCO2014 and Flickr30K datasets have demonstrated the effectiveness and advantages of the proposed method.

关键词： Visualization Merging Adaptation models Intelligent vehicles Semantics Feature extraction Object oriented modeling Intelligent transportation traffic scenes description deep learning algorithm attention mechanism neural networks

来源：评论

学校读者我要写书评

暂无评论

Effective textile quality processing and an accurate inspection system using the advanced deep learning technique

引用

TEXTILE RESEARCH JOURNAL 2020年第9-10期90卷 971-980页

作者： Jeyaraj, Pandia Rajan Nadar, Edward Rajan Samuel Mepco Schlenk Engn Coll Dept Elect & Elect Engn Sivakasi 626005 Tamil Nadu India

This research paper focuses on the innovative detection of defects in fabric. This approach is based on the design and development of a computer-assisted system using the deep learning technique. The classification network is modeled using the ResNet512-based Convolutional Neural Network to learn the deep features in the presented fabric. Being an accurate method, this enables accurate localization of minute defects too. Our classification is based on three major steps;firstly, an image acquired by the NI Vision model and pre-processed for a standard pattern to Kullback Leibler Divergence calculation. Secondly, standard textile fabrics are presented to train the Convolutional Neural Network to classify the defective region and the defect-free region. Finally, the testing fabrics are examined by the trained deep Convolutional Neural Network algorithm. To verify the performance, multiple fabrics are presented and the classification accuracy is evaluated. For standard defects on defective fabrics, an average accuracy of 96.5% with 98.5% precision is obtained. Experimental results on the standard Textile Texture Database dataset confirmed that our method provides better results compared with similar recent classification methods, such as the Support Vector Machine and Bayesian classifier.

关键词： deep learning algorithm fabric inspection defect classification Convolution Neural Network

来源：评论

学校读者我要写书评

暂无评论

deep learning-based context aggregation network for tumor diagnosis 14

Deep learning-based context aggregation network for tumor di...

引用

14th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Zhu, Lin Qu, Xinliang Wei, Shoushui Shandong Univ Sch Control Sci & Engn Jinan 250061 Shandong Peoples R China Shandong First Med Univ Affiliated Hosp 1 Jinan 250014 Shandong Peoples R China

ISBN: (纸本)9781665400046

Craniopharyngioma is a type of benign brain tumor but has severe biological malignant behavior. Whether the craniopharyngioma invades the surrounding brain tissue has important influence on making treatment plan and the prognosis of patients, so the accurate diagnosis of craniopharyngioma is a crucial step in the treatment processing. It is important to explore some methods for judging the invasiveness of craniopharyngioma preoperatively. Therefore, we proposed a context aggregation network (CA-2D Network) based on deep learning algorithm, which can diagnose the invasiveness of craniopharyngioma by judging the characteristics of head MRI images. The proposed CA-2D Network utilizes ResNet as the backbone, and has a context modeling block and feature aggregating head to correlate features from different slices, capture context information, and aggregate features for classification. The features extracted by the CA-2D Network yield area under the curve (AUC) values of 82.59% for the test set. As demonstrated in the results, the proposed CA-2D Network is promising.

关键词： Medical image analysis deep learning algorithm Computer-aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

The Power of Positive Reporting: Examining China's Anti-Epidemic National Image in Mainstream Media

引用

JOURNAL OF PSYCHOLINGUISTIC RESEARCH 2023年第6期52卷 2047-2073页

作者： Chen, Jie Xu, Kunpei Chen, Yukun Lin, Jiaxin Guangdong Univ Finance & Econ Sch Foreign Languages Guangzhou 510655 Peoples R China Nanyang Technol Univ Sch Humanities Singapore 639798 Singapore Northwestern Polytech Univ Sch Foreign Studies Xian 710129 Peoples R China

Covid-19 out broke gave an extreme impact to the globe, imposing a challenge to health publicly and causing social interruptions. As a result, the role of mainstream media in promoting anti-epidemic measures and disseminating national images has become increasingly important. In this study, we examine the anti-epidemic reports in 2020 from three types of international news sources, identifying 566 samples for content and text analysis. Through our analysis, we found that each component of the anti-epidemic report has a clear focus, and that these reports presented China's national image of anti-epidemic in four dimensions. Notably, the European version of People's Daily exhibited a positive reporting tendency, accounting for 86% of the total, with only 8% of reports being negative. This indicates a relatively comprehensive national image construction and communication strategy amid the COVID-19 pandemic. Overall, our research reveals the important role of media in shaping a nation's image during a global crisis. The positive reporting tendency of the European version of People's Daily reflects an effective strategy for promoting a positive national image, thereby dispelling misunderstandings and prejudices towards China's anti-epidemic measures. Our findings provide inspiration for the dissemination of national images in times of crisis, highlighting the importance of comprehensive and well-coordinated communication strategies to promote a positive image.

关键词： China's international image Mainstream media psychology COVID-19 period deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence utilising corneal confocal microscopy for the diagnosis of peripheral neuropathy in diabetes mellitus and prediabetes

引用

DIABETOLOGIA 2022年第3期65卷 457-466页

作者： Preston, Frank G. Meng, Yanda Burgess, Jamie Ferdousi, Maryam Azmi, Shazli Petropoulos, Ioannis N. Kaye, Stephen Malik, Rayaz A. Zheng, Yalin Alam, Uazman Univ Liverpool Inst Life Course & Med Sci Dept Eye & Vis Sci Liverpool Merseyside England Univ Liverpool Inst Life Course & Med Sci Liverpool Merseyside England Univ Liverpool Pain Res Inst Liverpool Merseyside England Liverpool Univ Hosp NHS Fdn Trust Liverpool Merseyside England Univ Manchester Inst Cardiovasc Sci Manchester Lancs England Manchester Fdn Trust Manchester Diabet Ctr Manchester Lancs England Weill Cornell Med Qatar Doha Qatar Royal Liverpool Univ Hosp St Pauls Eye Unit Liverpool Merseyside England Univ Manchester Div Endocrinol Diabet & Gastroenterol Manchester Lancs England

Aims/hypothesis We aimed to develop an artificial intelligence (Al)-based deep learning algorithm (DLA) applying attribution methods without image segmentation to corneal confocal microscopy images and to accurately classify peripheral neuropathy (or lack of). Methods The AI-based DLA utilised convolutional neural networks with data augmentation to increase the algorithm's generalisability. The algorithm was trained using a high-end graphics processor for 300 epochs on 329 corneal nerve images and tested on 40 images (1 image/participant). Participants consisted of healthy volunteer (HV) participants (n = 90) and participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141) and prediabetes (n = 50) (defined as impaired fasting glucose, impaired glucose tolerance or a combination of both), and were classified into HV, those without neumpathy (PN-) (n = 149) and those with neuropathy (PN+) (n = 130). For the AI-based DLA, a modified residual neural network called ResNet-50 was developed and used to extract features from images and perform classification. The algorithm was tested on 40 participants (15 HV, 13 PN-, 12 PN+). Attribution methods gradient-weighted class activation mapping (Grad-CAM), Guided Grad-CAM and occlusion sensitivity displayed the areas within the image that had the greatest impact on the decision of the algorithm. Results The results were as follows: HV: recall of 1.0 (95% CI 1.0, 1.0), precision of 0.83 (95% CI 0.65, 1.0), F-1-score of 0.91 (95% CI 0.79, 1.0);PN-: recall of 0.85 (95% CI 0.62, 1.0), precision of 0.92 (95% CI 0.73, 1.0), F-1-score of 0.88 (95% CI 0.71, 1.0);PN+: recall of 0.83 (95% CI 0.58, 1.0), precision of 1.0 (95% CI 1.0, 1.0), F-1-score of 0.91 (95% CI 0.74, 1.0). The features displayed by the attribution methods demonstrated more corneal nerves in HV, a reduction in corneal nerves for PN- and an absence of corneal nerves for PN+ images. Conclusions/interpretation We demonstrate promising results in the rapid classific

关键词： Artificial intelligence Convolutional neural network Corneal confocal microscopy deep learning algorithm Diabetic neuropathy Image segmentation Ophthalmic imaging Small nerve fibres

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in glomerular diseases

引用

PEDIATRIC NEPHROLOGY 2022年第11期37卷 2533-2545页

作者： Schena, Francesco P. Magistroni, Riccardo Narducci, Fedelucio Abbrescia, Daniela, I Anelli, Vito W. Di Noia, Tommaso Univ Bari Dept Emergency & Organ Transplantat Bari Italy Univ Modena Dept Nephrol Modena Italy Polytech Bari Dept Elect & Informat Engn Bari Italy Schena Fdn Bari Italy

In this narrative review, we focus on the application of artificial intelligence in the clinical history of patients with glomerular disease, digital pathology in kidney biopsy, renal ultrasonography imaging, and prediction of chronic kidney disease (CKD). With the development of natural language processing, the clinical history of a patient can be used to identify a computable phenotype. In kidney pathology, digital imaging has adopted innovative deep learning algorithms (DLAs) that can improve the predictive capability of the examined lesions. However, at this time, these applications can only be used in research because there is no recognized validation to replace the conventional diagnostic applications. Kidney ultrasonography, used in the clinical examination of patients, provides information about the progression of kidney damage. Machine learning algorithms (MLAs) with promising results for the early detection of CKD have been proposed, but, still, they are not solid enough to be incorporated into the clinical practice. A few tools for glomerulonephritis, based on MLAs, are available in clinical practice. They can be downloaded on computers and cellular phones but can only be applied to uniracial cohorts of patients. To improve their performance, it is necessary to organize large consortia with multiracial cohorts. Finally, in many studies MLA development has been carried out using retrospective cohorts. The performance of the models might differ in retrospective cohorts compared to real-world data. Therefore, the models should be validated in prospective external large cohorts.

关键词： Glomerulonephritis Artificial Intelligence Natural Language Processing Machine learning algorithm deep learning algorithm Clinical Outcome

来源：评论

学校读者我要写书评

暂无评论

Recognizing Distraction for Assistive Driving by Tracking Body Parts Using Novel Convolutional Neural Network with LGM Classifier Over Random Forest with Improved Accuracy

Recognizing Distraction for Assistive Driving by Tracking Bo...

引用

2023 Intelligent Computing and Control for Engineering and Business Systems, ICCEBS 2023

作者： Shyam, R. Ramkumar, G. Saveetha School of Engineering Department of Ece Simats Chennai India

ISBN: (纸本)9798350394580

In the context of identifying driver distractions, the goal of this study is to investigate the degree of accuracy exhibited by the most recent iterations of deep learning algorithms. Both Convolutional Neural Networks Utilising LGM Classifier (CNNLGM) and Random Forest (RF) are compared head-to-head in the research presented here. The investigation required a total of 118 samples, which were then divided equally between two categories consisting of 58 specimens each. Group 1 utilized the CNNLGM Classifier, in contrast to Group 2's utilization of the RF technique. The RF code was implemented using software from Google Colab, and the same program was also used to import the dataset. A pre-test power of 80% and an alpha value of 0.05 were taken into consideration while determining the appropriate size of the sample for the experiment. This was accomplished with the assistance of an online tool for statistical analysis. Previous research provided the necessary information for determining the appropriate size of the sample to use. The findings of the simulation showed that the Novel CNNLGM Classifier achieved an accuracy of 96%, whereas the RF algorithm could only achieve an accuracy of 82%. There was a substantial disparity in the levels of accuracy achieved by the two approaches, as measured by a significance value of 0.001 (p © 2023 IEEE.

关键词： Automatic Recognition deep learning algorithm Driver's Distraction Machine learning Novel Convolutional Neural Network with LGM Classifier Random Forest Road Safety Road Traffic Accidents

来源：评论

学校读者我要写书评

暂无评论

deepFake Videos Detection and Classification Using Resnext and LSTM Neural Network 3

DeepFake Videos Detection and Classification Using Resnext a...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Patel, Suman Chandra, Saroj Kumar Jain, Amit O P Jindal University Computer Science and Engineering Department CG Raigarh India

ISBN: (纸本)9798350319125

deepfake videos, which are artificial intelligence-altered videos that have acquired extensive awareness recently. deep learning algorithms are utilized to create these deepfake films, which are meant to disseminate false information about anyone, including politicians and celebrities. These movies have been purposefully made viral in order to propagate propaganda and false information, to frighten people, and to destabilize society. It is exceedingly challenging for a casual viewer to recognize a deep fake video with the naked eye. Finding these manipulated films has been extremely difficult and requires careful attention. In order to recognize a deepfake movie, this paper, a novel methodology that combines ResNext, a Convolutional Neural Network (CNN) algorithm, with Long Short-Term Memory (LSTM), a Recurrent Neural Network (RNN) has been developed. It is found that as the number of epochs increased, the model's accuracy increased and its training loss reduced. © 2023 IEEE.

关键词： Artificial Intelligence Convolutional Neural Network (CNN) deep learning algorithm deepfake LSTM Recurrent Neural network (RNN) ResNext

来源：评论

学校读者我要写书评

暂无评论

Smart energy modeling in buildings with distributed energy generation by using Discrete Wavelet Transform LSTM method 9

Smart energy modeling in buildings with distributed energy g...

引用

9th International Conference on Electrical Energy Systems (ICEES)

作者： Ishwarya, S. Akash, S. Kathireshwar, R. Keerthana, B. Keerthivasan, R. M Kumarasamy Coll Engn Elect & Elect Engn Karur India

ISBN: (纸本)9798350348033

In this paper, we use solar energy resources. It is well known that electricity is usually produced by coal, which is at the extreme end in us cities take millions of years to recover from the burning of coal that has a negative effect on us Environment Today, electricity has become an important part of everyone's daily life. Sun is renewable resource are now fully available and have no harmful effects on us environment. Buildings account approximately 33% of the total energy used, and 40% of direct and indirect energy use global CO2 discharge. As energy consumption increases worldwide, managing energy use by encouraging on-site renewable energy can help meet this demand. This paper proposes a deep learning method based on the Discrete Wavelet Transform and Long Short-Term Memory (DWT-LSTM) and timescheduling method for the added need of modeling and energy management for buildings. The combination of deep learning algorithm, energy storage and energy scheduling will reduce the energy demand and sends the extra generated energy to the grid.

关键词： Maximum Power Point Tracking Discrete Wavelet Transform Long Short -Term Memory PhotoVoltaic panels deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A simple deep learning based image illumination correction method for paintings

引用

PATTERN RECOGNITION LETTERS 2020年 138卷 392-396页

作者： Goswami, Suranjan Singh, Satish Kumar IIIT Allahabad IT Allahabad 211015 Uttar Pradesh India

Image illumination correction has been a long standing topic for research in the Computer Vision problem. However, all previous literature on this topic has either been statistical in nature in the sense that a specified algorithm has been developed for approaching a particular case of illumination normalization, or involves extremely complex deep learning methods for illumination correction of either one of over illuminated or under illuminated images. We present here a very simple deep learning based image illumination correction architecture which works on color images of paintings irrespective of whether they are under or over illuminated. We have tested the results using a synthetic database as well as on real world painting images of diverse nature. (C) 2020 Elsevier B.V. All rights reserved.

关键词： deep learning algorithm Low space-time complexity Image enhancement RGB color image High range variation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：