检索结果-内蒙古大学图书馆

Geo-Structures 2024: Innovation and Experience with Earth Retaining Structures

作者： Mukta, Banu M. Aftabur, Rahman M. Dept. of Civil Engineering Chittagong Univ. of Engineering and Technology Chattogram Bangladesh

ISBN: (数字)9780784485842

Since Bangladesh is a low-lying country, the upper layer soil is very soft and weak to withstand structural load. For this reason, deep pile foundation is required for medium-to-low weight structure which is an economic and environmental concern. Ground improvement with geopolymer-based deep mixing method, an alternative to conventional cement stabilization, is carried out in the laboratory in the present study. Class F Fly Ash, a byproduct of Coal Power Plant and has a high potential of Fly Ash waste in Bangladesh in years ahead, is used as a binder at 10%, 15%, 20%, and 25% of soft soil weight to evaluate the strength development. Chemical additives (NaOH:Na2SO3 = 1:2) of 50% of Fly Ash weight are used to provide adhesiveness. The soil has a water content equal to its Liquid Limit while sampling. Unconfined Compressive Strength (UCS) is tested for 14, 28, and 56 days curing period. Strength is found to be increasing with the increase in binder content and curing period. Total water-to-binder ratio has an inverse effect on strength. The maximum rise of strength is observed 33.6 times compared to the parent soil when treated with 25% binder content at 56 days curing age. Strengths at 14 days and 28 days curing period of the same soil-geopolymer mix are 18.5 and 28.7 times greater, respectively. This increase in strength due to geopolymer-based deep mixing could be an effective solution for foundation on poor ground. © ASCE.

关键词： Fly ash

来源：评论

学校读者我要写书评

暂无评论

CochleaTion: Speech Emotion Recognition Through Cochleagram with CNN-GRU and Attention Mechanism 6

CochleaTion: Speech Emotion Recognition Through Cochleagram ...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Namey, Atkia Akter, Khadija Chittagong University of Engineering and Technology Dept. of Electronics and Telecommunication Engineering Chattogram Bangladesh

ISBN: (纸本)9798350385779

Speech Emotion Recognition (SER) system classifies the human emotional state based on speaker's utterances in different categories. This study proposes a novel SER system using cochleagram which is an acoustic feature associated with human auditory perception of emotions. The proposed model integrates a hybrid architecture comprising Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) network, augmented with self-attention mechanism. Evaluation of the model is conducted on the BanglaSER and RAVDESS dataset, where BanglaSER provides a notable accuracy of 91.17% in categorizing five distinct emotions: angry, calm, happy, neutral, and sad. Furthermore,on the RAVDESS dataset, the model exhibited a solid accuracy of 78.35% in classifying eight diverse emotions. The incorporation of cochleagram and the hybrid neural network design showcases the efficacy of the proposed SER system, offering a promising approach for precise and efficient emotion categorization in speech signals © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Fusion Based Brain Tumor Classification From Imbalance MRI Dataset Using Weighted Loss Functions 2

Deep Feature Fusion Based Brain Tumor Classification From Im...

引用

2nd International Conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Tasnim, Taieba Parvin, Farjana Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi Bangladesh

ISBN: (纸本)9798331517984

Deep learning using MRI images to classify brain tumours presents a significant challenge due to imbalanced training datasets, where one tumor type may have far more samples than others. The overrepresented class may perform worse in classifiers as a result of this imbalance. In order to tackle this issue, the paper examines how feature learning in CNNs is affected by weighted loss functions to manage data imbalance. The article propose deep feature fusion, where particular CNN model features that were trained using three distinct loss functions are fused and classified using softmax classifier. This approach lead to notable improvements in brain tumor classification compared to a CNN trained with standard cross-entropy loss. Notably, the proposed methods substantially reduce classification errors between uneven class samples. The proposed model achieved an impressive 94.5% classification accuracy, accompanied by an average Fl-score of 94.6%, average precision of 94.6 %, and average recall of 95%. These findings underscore the effectiveness of our methodology in improving brain tumor classification accuracy, offering a promising avenue for more reliable diagnosis and treatment planning in clinical settings, © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bi-Directional Power Flow Control for Three Phase Grid Tied Converters in Ev Charging Applications

Bi-Directional Power Flow Control for Three Phase Grid Tied ...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Prabhakar, B. Kishore, D. Ravi Venkata Srinu, P.Veera Sivaramakrishna, P.M.V. Saiprasad, T. Godavari Institute of Engineering and Technology Dept. Electrical and Electronics Engineering Rajahmundry India

ISBN: (纸本)9798350309140

The expenses associated with conventional energy have increased dramatically in recent times due to factors such as climate change, environmental degradation, and the depletion of fossil resources. Thus, there is an urgent global need to use clean, innovative energy. Worldwide, there is widespread usage of electric cars (EVs) with smart grid technologies. More and more attention has been directed into the Vehicle-to-Grid (V2G) system. The Bi-directional grid-connected AC/DC converter, which enables bilateral power transfer while satisfying grid power quality criteria, is an essential component of the V2G hybrid system. A Bi-directional Power flow control for three phase grid tied converter is presented in this study. It can offer bidirectional power transfer between EVs and the grid in addition to correcting reactive power and lowering power grid volatility. Introducing the V2G system setup and creating the mathematical model for the AC/DC converter are the first tasks. The next step is to propose an analysis of the PI control method and build a controller. D-Q-0 theory finds use in efficiently synchronising the grid and controlling ripple current in the grid current. The basis for the system simulation model is MATLAB/Simulink. © 2024 IEEE.

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

Vivaldi Antenna with Reconfigurable Rectangular Slots 3

Vivaldi Antenna with Reconfigurable Rectangular Slots

引用

3rd IEEE International Conference of Electron Devices Society Kolkata Chapter, EDKCON 2024

作者： Sharma, Harish Gupta, Neeraj Prakash, Ved Dey, Sukomal Amity School of Engineering & Technology Amity University Dept. of E & C engineering Gurgaon India Indian Institute of Technology Palakkad Dept. of Electrical Engineering Palakkad India

ISBN: (纸本)9798350374643

Antenna re-configurability is achieved through the integration of electronic switches, such as RF-MEMS, PIN diodes, and photoconductive switches, onto the antenna structure. This study introduces a Tapered Slot Antenna (TSA) that has the ability to change its frequency band. The TSA incorporates two switchable rectangular slots, allowing for dynamic adjustments to its characteristics. By utilizing diodes, a notch band is created, enabling precise tuning of the antenna's frequency response. They are a wide bandwidth mode that works with frequencies from 3.2 GHz to 9.5 GHz and a narrow band mode that works with frequencies from 8.4 GHz to 8.7 GHz. There is a requirement for the use of PIN diodes in order to alter both the impedance match plus the pattern of radiation. The simulation results clearly illustrate the outstanding performance of the proposed solutions. © 2024 IEEE.

关键词： Photoconductive switches

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Road Safety for Advanced Vehicular Accident Prediction 2

Revolutionizing Road Safety for Advanced Vehicular Accident ...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Deepika, T. Yuvaraj, N. Sri Preethaa, K.R. KPR Institute of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350327533

The detection and tracking of vehicle speed are crucial for ensuring the safety of civilians and preventing accidents. Speed tracking plays a pivotal role in traffic surveillance, where effective management and the well-being of citizens take precedence. The approach leverages computer vision-based models, specifically Multi-scale Detector for object detection, and a fusion of the DeepSORT and Centroid Sort algorithms for vehicle tracking from streaming video. To cater to the requirements of these algorithms, a custom dataset was developed within a controlled setting. Dataset augmentation was employed to prevent overfitting, thereby enhancing the dataset's diversity and the model's ability to generalize. The method demonstrates the capacity to accurately detect and track vehicles, maintaining performance even in high-traffic conditions. Cross-validation at every epoch during the training phase was implemented to increase the model's accuracy. In addition to the technical aspects, an LED display board was integrated to provide real-time data to oncoming vehicles at road curves. This display showcases information such as vehicle types, passage time, and the number of vehicles within the curvy road. The proposed Multi-Scale Detector model, a customized version of the You Only Look Once (YOLO) architecture, achieved a mean average precision (mAP) of 0.954 at a confidence interval of 0.5. This overall research provides an effective and accurate solution for optimizing vehicle tracking, enhancing transportation safety, and enabling a variety of practical applications in traffic management and monitoring. © 2024 IEEE.

关键词： DeepSORT Euclidean Distance and Vehicle Intelligence Multi-scale Detector Object Detection Speed Tacking

来源：评论

学校读者我要写书评

暂无评论

A Fuzzy Logic Approach for Predicting Gestational Diabetes Mellitus Using Risk Factors 6

A Fuzzy Logic Approach for Predicting Gestational Diabetes M...

引用

6th International Conference on Electrical engineering and Information and Communication technology, ICEEICT 2024

作者： Hasan, Nowshad Islam, Md. Saiful Hayat, Md. Tanvir Chittagong University of Engineering and Technology Dept. of Electronics and Telecommunication Engineering Chittagong Bangladesh

ISBN: (纸本)9798350385779

Gestational Diabetes Mellitus (GDM) is a health condition distinguished by heightened glucose levels experienced during pregnancy. Early detection of GDM is key to managing the condition and protecting both the mother and fetus. The aim of this study is to introduce a fuzzy expert system that is designed to assist both medical professionals and non-specialists in the evaluation of patients with GDM using risk factors. The approach employed five risk indicators such as age, body mass index, family diabetes history, previous GDM history and poor obstetric outcome as inputs. Triangular and trapezoidal fuzzy numbers are applied in this process. The Mamdani Fuzzy Inference system is used, with specific rules established for GDM prediction. The results indicated three levels of gestational diabetes: low, medium, and high. The resultant fuzzy expert system demonstrated promising potential for supporting medical professionals during the decision-making process pertaining to GDM. In conclusion, while the developed fuzzy expert system for GDM prediction cannot replace the invaluable work of specialist doctors, it can serve as a supportive tool in healthcare settings. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A study on proposal of the floating disaster prevention house against flood disasters (part 1) : Consideration of floating performance of the floating unit by water tank experiment

引用

Journal of Environmental engineering (Japan) 2023年第812期88卷 808-817页

作者： Mitsuhiro MASUDA Dept. of Maritime Systems Engineering Division of Marine Technology Tokyo University of Marine Science and Technology

The floating disaster prevention house (FDPH) was proposed, and conclusions about its disaster prevention performance were obtained as follows from this study. ,,1. The floating unit can perform the floating performance regardless of the slit position and the slit area of the flood wall, flow velocity and elevating speed of the water level.,, 2. The floating behavior of the floating unit can be reduced at the start of floating by setting up the clearance between the bottom of the flood wall and the floating unit. ,,3. FDPH is expected to be less susceptible to fluid pressure and drifting objects. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： Disaster prevention

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement of Distributed Generation for Minimization of Power Loss, Carbon Emission and Voltage Deviation Considering Demand Uncertainty

Optimal Placement of Distributed Generation for Minimization...

引用

2024 International Conference on Computer, Electrical and Communication engineering, ICCECE 2024

作者： Jana, Chandan Pradhan, Debolina Banerjee, Sannistha Bala, Mousumi Jana Hooghly Engineering and Technology College Dept. of Electrical Engineering West Bengal Hooghly India Meghnad Saha Institue of Technology Dept. of Electrical Engineering Uchhepota Kolkata India

ISBN: (纸本)9798350386479

Optimal position of Distributed Generation has been obtained in an unbalanced radial distribution system with lateral branches where loads are probabilistically varying in nature. Here four single objective indices like expected value of mean voltage, efficiency of distribution network, profitability index (PI) and Certified Emission Reduction (CER) and one multi-objective function giving priority to first two indices are set as decision making factor on yearly basis. Results obtained for different indices have been compared for IEEE 34 node test feeder. © 2024 IEEE.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Kinematic Features of Handwriting Data to Detect Parkinson's Disease 2

Analysis of Kinematic Features of Handwriting Data to Detect...

引用

2nd International Conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Shely, Shakila Khatun Hossain, Md. Foisal Khulna University of Engineering & Technology Dept. of Electronics and Communication Engineering Khulna Bangladesh

ISBN: (纸本)9798331517984

Across various neurodegenerative diseases, the second most common disease is Parkinson's disease. It affects the brain cells, which are accountable for releasing dopamine. When there is less release of dopamine, the muscles of the body can't work properly, which creates a problem for a person. In recent years, it caught the eyes of researchers that handwriting analysis can be a good solution to identify Parkinson's disease. Various attempts have already been made since the discovery of this idea. In this work, we have tried to use kinematic features of handwriting to detect Parkinson's disease. As there was less data variational autoencoder was used to generate synthetic data to train the model and the obtained accuracy of this proposed model is 89% © 2024 IEEE.

关键词： Neurodegenerative diseases

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：