检索结果-内蒙古大学图书馆

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Ayalew, Amogne Andualem Bitew, Gizachew Salau, Ayodeji Olalekan Tegegne, Melaku Lake Gupta, Shashi Kant Israr, Mohammad Tegegne, Tesfa Assegie, Tsehay Admassu Mizan-Tepi University School of Computing and Informatics Department of Information Technology Tepi Ethiopia Mizan Tepi University School of Computing Computer Science Department Mizan-Tepi Ethiopia Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Injibara University College of Engineering and Technology Department of Information Technology Injibara Ethiopia Eudoxia Research University Department of Computer Science and Engineering United States Maryam Abacha American University of Nigeria Hotoro Gra Kano State Nigeria Bahir Dar University Faculty of Computing Bahir Dar Institute of Technology Bahir Dara Ethiopia Injibara University College of Engineering and Technology Department of Computer Science Injibara Ethiopia

ISBN: (纸本)9798350364699

Named entity recognition has emerged as a critical step in recognizing, classifying, and extracting the most significant information from unstructured text without human intervention. It is used in information retrieval, conversation systems, machine translation, data mining, and information extraction. However, the Awngi language lacks a NER system due to inadequate datasets. This study combines feature extraction techniques with supervised machine learning algorithms, including support vector machines, Naïve Bayes, and conditional random fields with a grid search algorithm parameter optimization. These supervised machine-learning models often have various hyperparameters that must be tuned to optimize the model's performance by automatically selecting the parameter. Furthermore, the dataset used for training and testing consists of 20,193 annotated Awngi tokens, collected from Amhara Media Corporation, Awngi Telegram, and Facebook pages. The proposed SVM with grid search algorithm approach provided a promising result in ANER with an accuracy of 92% compared with Naïve Bayes, conditional random field, and decision-tree supervised machine learning models. Finally, the experiment results show that the proposed parameter tuning-based model can detect and categorize Awingi-named entities and outperforms the performance accuracy without parameter adjustment. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Braille Recognition of Geez Numbers Using an Optimal Deep Learning Algorithm 2

Braille Recognition of Geez Numbers Using an Optimal Deep Le...

引用

2nd International Conference on Advancement in Computation and computer Technologies, InCACCT 2024

作者： Abeje, Bekalu Tadele Salau, Ayodeji Olalekan Belay, Gebeyehu Chhabra, Gunjan Kaushik, Keshav Braide, Sepiribo Lucky Haramaya University Department of Information Technology Ethiopia Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Bahir Dar University Bahir Dar Institute of Technology Department of Computer Science Ethiopia Graphic Era Hill University Graphic Era Deemed to be University Department of CSE Uttarakhand Dehradun India University of Petroleum and Energy Studies School of Computer Science Uttarakhand Dehradun India Rivers State University Department of Electrical and Electronics Engineering Port Harcourt5080 Nigeria

ISBN: (纸本)9798350371314

Most of the time, people use their voices for communication and their vision to interact with the external environment. There are people who do not have the opportunity to use their vision to interact with the external environment due to different factors of disability. One of those community groups is the blind people. Blind people can communicate with other people with the help of their sounds, but they cannot communicate and exchange messages by means of writing. To overcome this challenge, the braille writing system is the prior one. Braille is the only way that they can communicate with their peers as well as other community members in the form of writing. People around the world use various languages for communication, and Geez is one of the ancient and popular languages of Ethiopians, particularly in the Ethiopian orthodox tewahedo church, where it is used for many aspects of spiritual worship. There have been numerous studies on Geez and Amharic alphabet braille recognition, but none of that research was conducted on Geez number braille recognition. This study focuses on recognizing geez braille signs into geez number digital written format by using braille image signs as input and geez numbers as the desired output. Serious steps including image acquisition, preprocessing, image segmentation, data augmentation, feature extraction, and recognition were applied. We have collected 1900 JPG images from hardcopy documents using iPhone 6 s camera and scanner, which belongs to the 19 class. Our model is trained with 100 epochs by partitioning the dataset into 0.8% of data as training and 0.2% as testing data. We have used end-to-end convolutional neural networks to recognize Geez numbers from - and base numbers up to . The proposed model achieves 96.88% training accuracy, 95.26% validation accuracy, 0.461% training loss, and 0.2844 validation loss recognition performance. The proposed model was optimal in the case of overfitting and underfitting phases as shown in

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Direct Adaptive Fuzzy PI Strategy for a Smooth MPPT of Variable Speed Wind Turbines 8th

Direct Adaptive Fuzzy PI Strategy for a Smooth MPPT of Varia...

引用

8th EAI International Conference on Advancement of Science and technology, ICAST 2020

作者： Tadesse, Abrham Ayenew, Endalew Venkata, L.N.K. Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia College of Electrical and Mechanical Engineering Addis Ababa Science and Technology University Addis Ababa Ethiopia

ISBN: (纸本)9783030806200

For this generation, life is too complex without sufficient energy. Due to the increase demand of energy from time to time, several researchers are too eager on renewable energy sources to have good enough, clean and greenhouse effect free energy. Thanks to its cost effectiveness, wind power is the primary focus of professionals on energy area and it is the fastest rising energy source. Adaptive fuzzy proportional integral (AFPI) is proposed here to keep a maximum power of a wind turbine (WT). From various methods of maximum power point tracking (MPPT), tip speed ratio (TSR) is selected here. TSR has the ability to retrieve the optimum desired speed of the generator for every wind speed value. For a WTs, a 1.5 MW permanent magnet synchronous generator (PMSG) is chosen because of its self- excitation property that enables high power factor and efficiency operation. The system efficiency is verified by MATLAB software. After all, the final result with proposed strategy display better performance than the outcome with conventional controller. © 2021, ICST institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Quantum Generative Adversarial Network for Autonomous Drone Navigation in Urban Wind Zones

Quantum Generative Adversarial Network for Autonomous Drone ...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Anumula Swarnalatha Nalluri Archana Naveen Mukkapati Subramanian Selvakumar Eneyachew Tamir Manikandaprabu P Department of Aeronautical and Aerospace Engineering KCG College of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Vignan's Foundation for Science Technology and Research Andhra Pradesh India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh India Department of Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Mechanical Engineering Sona College of Technology Salem Tamil Nadu India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Major challenges are observed when autonomous drones fly in the complex, changeable environment such as wind zones regarding accurate path planning, avoiding the object, and completing tasks. Lack of flexibility in different situations reduces the reliability of conventional models in real time. To overcome these difficulties the Savitzky-Golay Denoising CSWin Quantum Generative Adversarial Network with Emperor Penguin Optimizer known as SGDCQGANNet-EPO was developed. The RGB data and GPS-estimated wind forces in this model undergo Savitzky-Golay Denoising; this model does not rely on global data, only RGB camera data and GPS data. Recently a CSWin transformer (CSWin-T) makes feature extraction and obstacles detection as well as wind angle, wind speed and wind position identification easier. Quantum Generative Adversarial Networks (QGANet) are then used for optimized path planning, and the model is enhanced by the Emperor Penguin Optimizer (EPO) to fine tune the generator and discriminator loss functions. More accurate compared to current approaches in accuracy and efficiency, the model achieves an accuracy of 99.28%, a low RMSE of 0.38, a recall of 99.25%, and EVA of 0.95. In Confidence using this new technique, the free roaming and self-organizing drone maneuvers in complex environments achieved remarkable results.

关键词： Accuracy Navigation Wind speed Noise reduction Generative adversarial networks Transformers Path planning Data models Real-time systems Drones

来源：评论

学校读者我要写书评

暂无评论

Robust Control of Boiler Drum Water Level Via H-Infinity

SSRN

引用

SSRN 2024年

作者： Sinishaw, Getaye Yeshaneh Tekle, Mekdes Mebratu Mitaw, Abibual Abate Kassa, Abrham School of Electrical and Computer Engineering Industrial Control Woldia Institute of Technology Woldia University Woldia Ethiopia School of Electrical and Computer Engineering Electrical Power Woldia Institute of Technology Woldia University Woldia Ethiopia Faculity of Electrical Engineering Industrial Control Bahir Dar Institute of Technology Bahir Dar Ethiopia

The water level in the boiler drum is crucial for factory operations. Controlling it is challenging due to swell and shrink phenomena. If the level is below the set point, overheating of the water wall tubes may cause tube falling-out and serious accidents resulting. Damage can also be a result of several or frequently low drum level conditions. If the level goes above the limits of boiler water carryover toward the super heater or turbine may result in damage resulting in expansive maintenance costs or damage of either the turbine or boiler Various linear and nonlinear controllers have been proposed, such as fractional-order PID, LQR, fuzzy adaptive, and sliding mode controllers, but these cannot handle disturbances in steam and water flow *** paper presents a robust H-infinity-based optimal controller designed for high disturbance rejection and stability under all operating conditions. H-infinity controller can be done by selecting proper weight functions. The weights are tuned to obtain satisfactory performance margins such as rise time, percentage overshoot, settling time and steady state error. Proper weight functions are selected to shape the signal for desired performance and robustness. Weight function W1 is a low-pass filter for good disturbance rejection at low frequencies, while W3 is a high-pass filter. The coefficients of these weights are optimized using Particle Swarm Optimization (PSO).From the simulation result H infinity-based optimal controller is compared with LQR. H infinity controller shows that it has good reference tracking and performance than optimal control LQR The H-infinity controller demonstrates superior reference tracking and performance compared to the LQR. © 2024, The Authors. All rights reserved.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Faba Bean Disease Detection Using Deep Learning Techniques

Faba Bean Disease Detection Using Deep Learning Techniques

引用

2023 International Conference on Cyber Management and engineering, CyMaEn 2023

作者： Salau, Ayodeji Olalekan Abeje, Bekalu Tadele Faisal, Abeer Naser Asfaw, Tesfa Tegegne Afe Babalola University Department of Electrical/Electronics and Computer Engineering Ado-Ekiti Nigeria Haramaya University College of Computing and Informatics Department of Information Technology Ethiopia Institute of Technology Faculty of Computing Bahir Dar University Department of Computer Science Ethiopia University of Sumer College of Computer Science and Information Technology Al-Rifai Iraq

ISBN: (纸本)9781665493291

Faba bean (Vicia faba L.) is an important cash crop for animal and human consumption in many countries, especially Ethiopia due to its high protein content and high rate of production. It also improves soil fertility with the help of bacteria, which forms nodules on its roots. Ethiopia is the second largest faba bean producer;however, according to research, the yield is generally low. Among the constraints contributing to low productivity of the crop, disease is the most important. Even though there are countermeasures such as the use of chemical sprays, which is used to reduce the damage or eliminate the disease, an effective disease identification technique is still required. Chocolate spot, faba bean gal, and rust are the most common diseases of faba beans. To effectively detect the disease, in this paper, we propose an end-to-end CNN model for training before and after the dataset is preprocessed. The CNN end-to-end model is trained with raw images and achieves 92.1% training accuracy. Also, the model is trained with preprocessed data and it achieves a training accuracy of 98.14% for the end-to-end CNN classifier. The results show that the proposed approach is suitable for faba bean disease detection and can be employed to detect diseases of other crops. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis and Improvement of Distribution System Reliability by Optimization of Distributed Generation

Analysis and Improvement of Distribution System Reliability ...

引用

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Molla Addisu Mossie Sadeq Thamer Hlama Hayder Rahm Dakheel Al-Fayyadh Estifanos Abeje Sharew Ayodeji Olalekan Salau Charles Olawale Ogunnigbo School of Electrical and Computer Engineering Woldia Institute of Technology Woldia University Woldia Ethiopia College of Science University of Sumer Iraq Department of Computer Science College of Computer Science and Information Technology University of Sumer Dhi-Qar Iraq Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Electrical/ElectronicEngineering Afe Babalola University Ado-Ekiti Nigeria Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of Mechanical/Mechatronics Engineering College of Engineering Afe Babalola University Ado-Ekiti Ekiti State Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The three components of a power system are generation, transmission, and distribution. The distribution system, which provides power to meet demand, is the main part of the power system. A measurement of the consistency and reliability of the power supply to consumers is the distribution system reliability assessment. Additionally, it offers details on the system's operation and aids in determining the expenses or losses a power outage will cause the utility and the consumer. This paper uses a variety of EEU data collected to analyze reliability and improve the Woldia distribution system. System reliability indices for the cases show that the system indices (SAIFI = 103.624 in./yr, SAIDI = 891.4559 hr/yr, CAIDI = 8.603 hr/int, ASAI = 0.8982 pu, and EENS = 4904.725 MWhr/yr) of the system is unreliable. A PSO is used to optimize the appropriate location and size for 1.2 MW of DG units, and the effectiveness of the suggested methodology is evaluated on a 15 KV outgoing Woldia University feeder. Following optimal DG allocation, the radial distribution system's reliability over the previous system is increased. The suggested method outperforms the current system, as shown by the test results, which show a 46.097% reduction in EENS, a 47.377% reduction in SAIFI, and a 47.695% reduction in SAIDI. Generally speaking, the findings show that increasing the test system's reliability requires determining the exact size and placement of distributed generation.

关键词： Photovoltaic systems Renewable energy sources Power measurement Power supplies Systems operation Power system reliability Distributed power generation Reliability Indexes Resource management

来源：评论

学校读者我要写书评

暂无评论

A HybridManufacturing ProcessMonitoringMethod Using Stacked Gated Recurrent Unit and Random Forest

引用

Intelligent Automation & Soft Computing 2024年第2期39卷 233-254页

作者： Chao-Lung Yang Atinkut Atinafu Yilma Bereket Haile Woldegiorgis Hendrik Tampubolon Hendri Sutrisno Department of Industrial Management National Taiwan University of Science and TechnologyTaipeiTaiwanChina Faculty of Mechanical and Industrial Engineering Bahir Dar Institute of Technology(BiT)Bahir DarUniversityBahir Dar6000Ethiopia Department of Computer Science and Information Engineering National Taiwan University of Science and TechnologyTaipeiTaiwanChina Department of Information System Faculty of Engineering and Computer ScienceKridaWacana Christian UniversityJakartaIndonesia Department of Information Management National Dong Hwa UniversityHualienTaiwanChina

This study proposed a new real-time manufacturing process monitoring method to monitor and detect process shifts in manufacturing *** real-time production process monitoring is critical in today’s smart *** more robust the monitoring model,the more reliable a process is to be under *** the past,many researchers have developed real-time monitoring methods to detect process shifts ***,thesemethods have limitations in detecting process shifts as quickly as possible and handling various data volumes and *** this paper,a robust monitoring model combining Gated Recurrent Unit(GRU)and Random Forest(RF)with Real-Time Contrast(RTC)called GRU-RF-RTC was proposed to detect process shifts *** effectiveness of the proposed GRU-RF-RTC model is first evaluated using multivariate normal and nonnormal distribution ***,to prove the applicability of the proposed model in a realmanufacturing setting,the model was evaluated using real-world normal and non-normal *** results demonstrate that the proposed GRU-RF-RTC outperforms other methods in detecting process shifts quickly with the lowest average out-of-control run length(ARL1)in all synthesis and real-world problems under normal and non-normal *** experiment results on real-world problems highlight the significance of the proposed GRU-RF-RTC model in modern manufacturing process monitoring *** result reveals that the proposed method improves the shift detection capability by 42.14%in normal and 43.64%in gamma distribution problems.

关键词： Smart manufacturing process monitoring quality control gated recurrent unit neural network random forest

来源：评论

学校读者我要写书评

暂无评论

Optimal allocation of distributed generation for performance enhancement of distribution system using particle swarm optimization 7th

Optimal allocation of distributed generation for performance...

引用

7th EAI International Conference on Advancement of Science and technology, ICAST 2019

作者： Mandefro, Elias Bantiyrga, Belachew Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia

ISBN: (纸本)9783030436896

The rapid growth of power demand and urbanization needs a quality and reliable power supply system. On the other hand, the existing passive distribution network and high cost of power transmission from generation can’t meet the fast-growing power demand. The weak performance of the utility like high power interruption and poor voltage profile affect the living standard of individual consumers which are the most serious problems of Ethiopian power distribution system. This type of problem can be minimized by integrating optimally allocated renewable distributed generations with the existing distribution system which are environmentally friend. Optimal sizing and siting of DG done by applying PSO for multi-objective function using MATLAB software. The significant process is how to minimize the power loss, reduce power interruption and improve the voltage profile of distribution systems. The voltage profile and power loss evaluation are done using a power flow method of forward-backward for radial networks. The reliability indices of the network like SAIDI, SAIFI, and EENS are evaluated using ETAP software. The proposed method is tested at Gihon 25-bus feeder of bahir dar distribution system. The simulation result indicates appropriate sizing and placement of solar based DG improves the performance of the distribution system. © ICST institute for computer Sciences, Social Informatics and Telecommunications engineering 2020.

关键词： Distributed power generation

来源：评论

学校读者我要写书评

暂无评论

Performance enhancement of distribution power system by optimal sizing and sitting of distribution statcom 7th

Performance enhancement of distribution power system by opti...

引用

7th EAI International Conference on Advancement of Science and technology, ICAST 2019

作者： Yisaye, Nebiyu Mandefro, Elias Bantyirga, Belachew Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia

ISBN: (纸本)9783030436896

In this paper, an approach for optimal sizing and sitting of D-STATCOM in radial distribution network is proposed with multi objective functions of power loss minimization, voltage stability, and voltage profile enhancement subjected to equality and inequality constraints. Voltage stability index is used to pre-determine the candidate bus for optimal sitting of D-STATCOM. Genetic algorithm is proposed to determine the optimal size and sit of D-STATCOM. The performance of the proposed method is tested on the two IEEE 33-bus and 69-bus radial distribution feeders. The test systems are analyzed with different loading and sizing condition of D-STATCOM. The simulation result shows that optimal sitting and sizing of D-STATCOM in the proposed networks effectively upgrade the performance of the system. © ICST institute for computer Sciences, Social Informatics and Telecommunications engineering 2020.

关键词： Static synchronous compensators

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：