检索结果-内蒙古大学图书馆

25th IEEE International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (IEEE CAMAD)

作者： Kukreja, Rishabh Rinchen, Sonam Vaidya, Binod Mouftah, Hussein T. Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON Canada

ISBN: (纸本)9781728163390

Traffic signs, which provide visual representation, play key role in autonomous navigation. Thus, detection and classification of traffic signs are one of the key requirements in autonomous vehicles (AVs). AVs heavily rely on object detection techniques to classify the traffic signs. In recent years, deep convolutional neural networks (CNNs) such as Faster R-CNN have achieved incredible success on object detection such as traffic signs. This paper focuses on the evaluation of state-of-the-art traffic signs detection techniques using deep learning algorithms and determination of the optimal one that can efficiently detect the traffic signs in real-time. Applying Faster R-CNN, the real-time traffic sign detection shall allow the autonomous vehicles to make decisions in real-time.

关键词： Traffic signs Object detection technique deep learning algorithm Autonomous vehicles Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Pedestrian tracking and counting based on YOLOv4 and deepSORT in Subway Stations 35

Pedestrian tracking and counting based on YOLOv4 and DeepSOR...

引用

35th Chinese Control and Decision Conference (CCDC)

作者： Zhang, Hui Xu, Jie Zhang, Xiaowen Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing Peoples R China

ISBN: (纸本)9798350334722

Real walking parameters of pedestrians are the basis of research on pedestrian dynamics. The detection and tracking technology provides the possibility of accurate walking parameters. To tackle the problem of lower detection accuracy of small-scale pedestrians, the YOLOv4 algorithm has been improved in two aspects. Then, the improved YOLOv4_1 model acts as the detector of deepSORT algorithm for pedestrian tracking and counting. After the improvement, the YOLOv4_I algorithm performs well in both the public and private datasets. The mAP is 90.61% in the private dataset, raising about 3.42%. Detection speeds reach 28.2 and 18.2 fps for processing images and video, respectively. Based on the YOLOv4_1-deepSORT algorithm, trajectories and walking parameters of pedestrians can he obtained. Results show the average speed of pedestrians on stairs in subway stations follows the normal distribution, the mean value is 1.27 m/s, and the standard deviation is 0.33 m(2)/s(2).

关键词： deep learning algorithm pedestrian detection pedestrian tracking trajectories walking parameters

来源：评论

学校读者我要写书评

暂无评论

Causal Effect of Small Businesses on Street Theft: Evidence from a Natural Experiment of the Beijing Cleanup Campaign

引用

JOURNAL OF QUANTITATIVE CRIMINOLOGY 2024年第4期40卷 727-760页

作者： Zhang, Yanji Cai, Liang Song, Guangwen You, Yongyi Fuzhou Univ Sch Humanities & Social Sci Dept Sociol Fuzhou 350108 Peoples R China Univ Chicago Dept Sociol Chicago IL 60637 USA Guangzhou Univ Ctr Geoinformat Publ Secur Sch Geog & Remote Sensing Guangzhou 510006 Peoples R China Fuzhou Univ Sch Architecture & Urban Rural Planning Dept Urban Rural Planning Fuzhou 350108 Peoples R China Fujian Key Lab Digital Technol Terr Space Anal & S Fuzhou 350108 Peoples R China

ObjectivesTo examine the causal impact of small businesses on street theft and the underlying *** "Cleanup Holes in the Wall" campaign in Beijing, China, provides a rare opportunity for a natural experiment. Drawing on street view images processed by deep learning algorithms and other big data sources such as court judgments and location-based service (LBS) population, we use difference-in-difference (DID) models to investigate how the disappearance of small businesses leads to changes in the occurrence of theft. We further examine the mechanisms by introducing mediators, including ambient population and social *** treatment units that experienced a mass loss of small businesses showed a significant reduction in street theft compared to the control units that were less affected by the cleanup campaign. Ambient population and social activity played a mediating role in promoting and deterring crime, respectively, with the former dominating. The results remain robust after including covariates in the models, balancing covariates using the propensity score matching method, and adopting alternative thresholds to classify the treatment *** are two competing yet coexisting mechanisms through which small businesses influence street theft. On the one hand, commercial premises provide large numbers of criminal opportunities for potential offenders;on the other hand, they are central to local social control and order. While small businesses exercise a certain amount of natural surveillance power, as a whole, they function primarily as crime generators. Implications for implementing targeted policies tailored to the nature of small businesses are discussed.

关键词： Small business Street theft Difference-in-difference model Street view image deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Analysis of Symptoms Wise Disease Inference System Using Data Mining Technique 2

Analysis of Symptoms Wise Disease Inference System Using Dat...

引用

2nd International Conference on Intelligent Computing and Control Systems (ICICCS)

作者： Burange, Tejal P. Chatur, P. N. Govt Coll Engn Dept Comp Sci & Engn Amravati India

ISBN: (纸本)9781538628423

Now a days challenges for medical community and public health issue are increases in rare diseases and this diseases were neglected for many years. Rare diseases affffect a limited number of individuals but the number of disorders that fit this definition is very large. Most rare diseases are genetic disorders, which are often severely disabling, substantially affect life expectancy, and impair physical and mental abilities. These disabilities result in reduced quality of life. In proposed system, symptoms based disease discovery system which discovers diseases on the basis of deep learning algorithm. In our base paper, sparsely deep learning is used to infer the diseases as per the specified questions/ symptoms. In sparse deep learning algorithm the author used only 3 hidden layers for processing. Our algorithm contains 5 hidden layers, therefore as compared to existing system, our system is more accurate. To implement disease inference system using deep learning algorithm. In case of any query system implement automatic question-answer system in which user will ask any question and system will process that question using data mining algorithms to find out proper answer. And also implement personalized disease prevention techniques recommendation system.

关键词： Symptoms Query Expert deep learning algorithm Rapid automatic keyword extraction(RAKE) algorithm

来源：评论

学校读者我要写书评

暂无评论

A Study on Machine learning and Artificial Intelligence Methods in Detecting the Minor Outer-Raceway Bearing Fault

A Study on Machine Learning and Artificial Intelligence Meth...

引用

IEEE International Conference on Industrial Technology (IEEE ICIT)

作者： Pandarakone, Shrinathan Esakimuthu Gunasekaran, Santhosh Asano, Keisuke Mizuno, Yukio Nakamura, Hisahide Nagoya Inst Technol Dept Elect & Mech Engn Nagoya Aichi Japan TOENEC Corp Div Res & Dev Nagoya Aichi Japan

ISBN: (纸本)9781538663769

To increase the reliability of induction motor (IM), several techniques have been proposed in condition monitoring and fault diagnosis. Bearings are the most sensitive part of IM, and fault occurring must be considered. In industry, scratch seems the most frequently occurring fault in bearing, and only few researches have encountered this issue. This paper is motivated by considering hole and scratch as faulty factor. A fast Fourier transform analysis is carried out, the features are extracted and used for training the diagnostic algorithm. Two types of diagnosis methods are proposed;machine learning algorithm and artificial intelligence method (AI). Among the various machine learning algorithms, Support Vector Machine (SVM) is selected because of its superiority over the data preprocessing. deep learning algorithm (DL) is selected in case of AI because of its intrinsic property over feature learning. A Convolutional Neural Network (CNN) architecture is originally used for fault characterization. The advantage of both the diagnosis methods and the possibility in detecting the minor bearing faults are discussed. Finally, effectiveness of the proposed methods is validated based on the experimental and diagnosis results.

关键词： Induction motor bearing fault fast fourier transform support vector machine deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

A Survey of Sentiment Analysis of Internet Textual Data and Application to Pakistani YouTube User Comments

A Survey of Sentiment Analysis of Internet Textual Data and ...

引用

IEEE International Conference on Digital Futures and Transformative Technologies (ICoDT2)

作者： Rani, Mehwish Latif, Seemab Tahir, Muhaammad Ali Mumtaz, Rafia Natl Univ Sci & Technol NUST Sch Elect Engn & Comp Sci SEECS Islamabad Pakistan

ISBN: (纸本)9781665412858

With the advent of social media, e-commerce and video sharing websites, a large amount of textual data depicting people's opinions is being generated. This text has a great impact on other web users, product sellers and content creators. Text mining and emotion detection using text analysis has prospered a lot in recent years. Sentiment Analysis is the method of mining emotions, reviews and opinions of web users. In this paper, a survey of text Sentiment Analysis techniques is presented. Sentiment Analysis is applied to comments extracted from Pakistani news videos. Different machine learning algorithms previously surveyed in this paper have been applied to this dataset. Our results have shown that transfer learning can be effectively used for Sentiment Analysis.

关键词： Sentiment Analysis deep learning algorithm Natural Language Processing LSTM GRU and Transfer learning

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

A Laboratory Set-Up for Cyber Attacks Simulation Using Protocol Analyzer and RTU Hardware Applying Semi-Supervised Detection algorithm

A Laboratory Set-Up for Cyber Attacks Simulation Using Proto...

引用

IEEE Texas Power and Energy Conference (TPEC)

作者： Parizad, Ali Hatziadoniu, Constantine Southern Illinois Univ Dept Elect & Comp Engn Carbondale IL 62901 USA

ISBN: (纸本)9781728186122

The integration of Information and Communication Technologies (ICT) into the modern power system makes it a complicated cyber-physical system (CPS). In this case, an adversary may find some loopholes, penetrate to CPS layer, compromise data, and consequently result in security and stability issues. In this paper, we proposed a laboratory set up to emulate the attacker's behavior and then detect the injected false data. To this end, RTU hardware and software are used to simulate a typical SCADA system. A protocol analyzer software is also employed to simulate a cyber-attack, inject false data, and send it to the control center. In the second stage, we developed a two-stage framework to detect FDIA. First, the LSTM, as a supervised learning algorithm, is utilized to build a predictive model. In this process, hyperparameter optimization is implemented to improve the accuracy of the developed model. In the second stage, an unsupervised scoring algorithm is applied to the real-time data to find the sequences of injected false data. Also, a penalty factor is considered during the detection procedure to prevent the algorithm from greedy search behavior. Simulation results on a real-world data set (Chicago load/weather) show the proposed method's effectiveness in the cyberattack implementation and FDIA detection problem.

关键词： Cyber Security Laboratory Set-Up RTU Hardware/Software Protocol Analyzer False Data Injection Attack (FDIA) deep learning algorithm Long Short Term Memory (LSTM) Supervised/Unsupervised learning Detection algorithm

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

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：