检索结果-南通市图书馆

Application of LiDAR Data for Deep Learning Based Near Crash Prediction at Signalized Intersection

Journal of Transportation Technologies 2023年第2期13卷 158-172页

作者： jewel rana palit Osama A. Osman Department of Civil and Chemical Engineering University of Tennessee Chattanooga USA Center for Urban Informatics and Progress University of Tennessee Chattanooga USA

Near crash events are often regarded as an excellent surrogate measure for traffic safety research because they include abrupt changes in vehicle kinematics that can lead to deadly accident scenarios. In this paper, we introduced machine learning and deep learning algorithms for predicting near crash events using LiDAR data at a signalized intersection. To predict a near crash occurrence, we used essential vehicle kinematic variables such as lateral and longitudinal velocity, yaw, tracking status of LiDAR, etc. A deep learning hybrid model Convolutional Gated Recurrent Neural Network (CNN + GRU) was introduced, and comparative performances were evaluated with multiple machine learning classification models such as Logistic Regression, K Nearest Neighbor, Decision Tree, Random Forest, Adaptive Boost, and deep learning models like Long Short-Term Memory (LSTM). As vehicle kinematics changes occur after sudden brake, we considered average deceleration and kinematic energy drop as thresholds to identify near crashes after vehicle braking time . We looked at the next 3 seconds of this braking time as our prediction horizon. All models work best in the next 1-second prediction horizon to braking time. The results also reveal that our hybrid model gathers the greatest near crash information while working flawlessly. In comparison to existing models for near crash prediction, our hybrid Convolutional Gated Recurrent Neural Network model has 100% recall, 100% precision, and 100% F1-score: accurately capturing all near crashes. This prediction performance outperforms previous baseline models in forecasting near crash events and provides opportunities for improving traffic safety via Intelligent Transportation Systems (ITS).

关键词： Near Crash Prediction Machine Learning Kinematics Convolutional Gated Recurrent Neural Network Recall

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Travel Patterns and Street Networks: A Novel Visualization Methodology of City-Level Traffic Flows and Network Usability

引用

Journal of Transportation Technologies 2023年第1期13卷 115-137页

作者： jewel rana palit Osama A. Osman Hesham Rakha Department of Civil and Chemical Engineering University of Tennessee Chattanooga USA Center for Urban Informatics and Progress University of Tennessee Chattanooga USA Center for Sustainable Mobility Virginia Tech Transportation Institute Blacksburg USA

Street Networks, knitted in the urban fabric, facilitate spatial movement and control the flow of urbanization. The interrelation between a city’s spatial network and how the residents travel over it has always been of high interest to scholars. Over the years, multifaceted visualization methods have emerged to better express this travel trend from small to large scale. This study proposes a novel approach to 1) visualize city-wide travel patterns with respect to the street network orientation and 2) analyze the discrepancies between travel patterns and streets to evaluate network usability. The visualizations adopt histograms and rose diagrams to provide several insights into network-wide traffic flows. The visualization of four New York City (NYC) boroughs including Queens, Brooklyn, Bronx, and Staten Island was generated for the daily traffic and the average hourly flows in the morning and evening rush hours. Then the contrasts between built-in street network topology and travel orientation were drawn to show where people travel over the network, travel demand, and finally which segments experience high or light traffic, revealing the true picture of network usability. The findings of the study provide an insight into the novel and innovative approach that can help better understand the travel behavior lucidly and assist policymakers in decision making to maintain a balance between urban topology and travel demands. In addition, the study demonstrates how to further investigate city street networks and urbanization from different diverse dimensions.

关键词： Street Orientation Travel Behavior Network Usability Rose Diagrams Land Use Urban Planning Urbanization OSMnx

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Investigation on Effect of Acid Wash with Thermocol Ball on Physical Properties of Knitted Garments

引用

Journal of Textile Science and Technology 2016年第2期2卷 16-21页

作者： Elias Khalil Masud rana jewel Faria Md. Al-Amin Islam Md. Sohel rana Department of Textile Engineering World University of Bangladesh Dhaka Bangladesh

Washing is considered as the final process of garments finishing. Acid washing is one kind of finishing treatment used for making sewn garments aesthetic, fashionable, soft, comfortable and also adding value to the final garments. This paper investigates the effect of the acid washing (with thermocol balls and potassium permanganate) on different physical properties of three knitted garments (Single Jersey 100% Cotton T-shirt, Single Jersey 95% Cotton 5% Spandex T-Shirt and 1 × 1 Rib100% Cotton T-Shirt). Typical washing procedures and techniques were followed and then physical properties were analyzed under standard condition. It is observed that fabric weight, CPI, WPI, spirality and shrinkage increase while bursting strength, stitch length absorbency decrease after washing treatment. pH of all the samples is under controlled and lies between 7 to 8. There is no change in pilling, colorfastness to wash, water and dry rubbing while a little bit decrease in wet rubbing.

关键词： Acid Wash Potassium Permanganate Thermocol Ball Physical Properties Knitted Garments

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Study on Periodic MHD Flow with Temperature Dependent Viscosity and Thermal Conductivity past an Isothermal Oscillating Cylinder

引用

World Journal of Mechanics 2016年第11期6卷 419-441页

作者： Rubel Ahmed Reaz Uddin B. M. jewel rana Rafrafin Selim Sarder Firoz Ahmmed Mathematics Discipline Khulna University Khulna Bangladesh

Temperature dependent viscosity and thermal conducting heat and mass transfer flow with chemical reaction and periodic magnetic field past an isothermal oscillating cylinder have been considered. The partial dimensionless equations governing the flow have been solved numerically by applying explicit finite difference method with the help Compaq visual 6.6a. The obtained outcome of this inquisition has been discussed for different values of well-known flow parameters with different time steps and oscillation angle. The effect of chemical reaction and periodic MHD parameters on the velocity field, temperature field and concentration field, skin-friction, Nusselt number and Sherwood number have been studied and results are presented by graphically. The novelty of the present problem is to study the streamlines by taking into account periodic magnetic field.

关键词： Chemical Reaction Periodic MHD Oscillating Cylinder Variable Viscosity Thermal Conductivity

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Radiation Absorption and Variable Electrical Conductivity Effect on High Speed MHD Free Convective Flow past an Exponential Accelerated Inclined Plate

引用

World Journal of Mechanics 2017年第8期7卷 211-241页

作者： B. M. jewel rana Raju Roy Lasker Ershad Ali S. F. Ahmmed Mathematics Discipline Khulna University Khulna Bangladesh

The effects of variable electrical conductivity and radiation absorption on high-speed MHD (Magnetohydrodynamics) free convective flow past an exponential accelerated inclined plate with higher order chemical reaction have been investigated. The electrical conductivity has been considered as a function of temperature. The chemical reaction has also been considered as the higher order. The usual transformations have been used to obtain the coupled dimensionless momentum, energy and concentration equations. Then the obtained non-dimensional partial differential equations have been solved numerically by explicit finite difference method. For excellent accuracy, stability and convergence test have been carried out. A computer program Compaq Visual FORTRAN 6.6a has been used to calculate the numerical results. The obtained numerical results concerned with the fluid velocity, temperature, concentration, concerned with skin friction, Nusselt number, Sherwood number, streamlines and isotherms are imprinted graphically by Tecplot and discussed in details. It is noticed that increasing of magnetic parameter increases the temperature and decreases the velocity, skin friction and Nusselt number. It is also observed that the temperature profile is increasing with the increasing values of Dufour number. However, the order of the chemical reaction increases the concentration profile.

关键词： Radiation Absorption Thermal Radiation Variable Electrical Conductivity Variable Temperature Higher Order Chemical Reaction

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

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：