检索结果-内蒙古大学图书馆

5th International Conference on Information and Communication technology for Development for Africa, ICT4DA 2023

作者： Erdaw, Helawe Behailu Taye, Yesuneh Getachew Lemma, Dereje Teferi Bahir Dar Institute of Technology Bahir Dar University Faculty of Computing Bahir Dar Ethiopia Bahir Dar Institute of Technology Bahir Dar University Faculty of Electrical and Computer Engineering Bahir Dar Ethiopia Addis Ababa University Department of Information Science Addis Ababa Ethiopia

ISBN: (纸本)9798350328486

computer vision is one of the state-of-The-Art technologies for object detection problems. Accurate detection of obstacles could assist blind and visually impaired people to n avigate safely while they walk. However, object detection and t racking are some of the challenging tasks in computer vision. I n video analysis, there are basic steps to be done: detection of target objects in consecutive frames, and analysis of objects to understand their behavior. Recently, several methods of object detection based convolutional neural networks have improved performance undue different conditions like speed and accurac y. However, most of these methods have slow recognition speed that limits their use in real-Time situations. Recently, a unified object detection model You Only Look Once (YOLO) was prop osed, which could directly regress from input image to object cl ass scores and positions. In this paper, we applied YOLOv2 to our prepared datasets of three different classes namely pothole, garbage bin, and pole and we proposed a technique called Short-Term Memory, which considers information between every f rame, to reinforce the detection capability of YOLO in video st reaming by including obj ect location and size estimation tasks. Through this, we achieved a mean average precision of 60.17% accuracy with an average detection speed of 34.6 fps. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Performance of Clinical data using Machine learning Approach- An Ensemble Model 2

Evaluating the Performance of Clinical data using Machine le...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Abdullah, A. Sheik Vinod, A Aashish Pranav, A G Vishal Govindarajan, Yeshwanth Selvakumar, Subramanian Vellore Institute of Technology School of Computer Science and Engineering Chennai India Bahir Dar University Faculty of Electrical and Computer Engineering Ethiopia

ISBN: (纸本)9798350372892

In the rapidly evolving field of healthcare, accurate clinical predictions are paramount for effective disease management and treatment planning. This paper introduces a novel ensemble machine learning model that utilizes the combined strengths of decision trees, neural networks, random forests, and support vector machines, integrated through a sophisticated linear regression meta-learner. This advanced integration strategy enhances predictive accuracy by optimally weighting the contributions of each base model based on their predictive reliability and effectiveness. The ensemble model amalgamates diverse algorithms with a meta-learning approach to harness a broader spectrum of data insights, thereby overcoming the limitations of traditional single-model approaches. Comparative analysis reveals that the ensemble model significantly outperforms existing methods, achieving superior accuracy in clinical predictions. These results underscore the potential of ensemble approaches in revolutionizing predictive analytics in healthcare, offering a promising tool for improving diagnostic precision and patient outcomes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Medicinal Plant Identification and Therapeutic Use Prediction

Deep Learning Approach for Medicinal Plant Identification an...

引用

2024 International Conference on Information and Communication technology for Development for Africa, ICT4DA 2024

作者： Azmeraw, Emiyamrew Tesfahun, Abebe Kinfu, Tsegazewold Fikirie, Tenagne Tigabu, Kindu University of Gondar Institute of Technology Gondar Ethiopia Debre Markos University Debre Markos Ethiopia Hawassa University Institute of Technology Hawassa Ethiopia Bahir Dar University Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar Ethiopia

ISBN: (纸本)9798331527792

The therapeutic nature of medicinal plants and their ability to heal many diseases raises the need for their automatic identification. However, the preservation and transmission of traditional medicinal knowledge encounter substantial problems due to factors such as professional secrecy, wrong cultural beliefs and lack of experts on the field. Consequently, there is a pressing risk of traditional medicinal knowledge fading away, resulting in a decline in expertise and an increased likelihood of errors in a field that demands serious attention and care. This work explores deep learning and proposes a deep learning approach for medicinal plant identification and to predict therapeutic use of medicinal plants from their leaf image. The transfer learning approach along with the pre-trained neural networks such as VGG16, InceptionV3 and Xception architectures were employed to extract features from the input leaf images. The Softmax and support vector machine(SVM) were used to classify the features generated by the three feature extractor model. The InceptionV3 architecture outperformed the state-of-the-art pre-trained models by achieving 99.17% average validation accuracy of Support Vector Machine (SVM) and softMax classifier) and the maximum validation accuracy of 99.34 is obtained using SVM. The average validation accuracy of the two classifier on each feature extractor model is used to select the better feature extractor model. To improve performance the SVM classifier was tuned using the Bayesian optimization technique and the proposed model InceptionV3 was validated with our custom datasets and achieved 99.34% prediction accuracy. The finding of this work showcases transfer learning-based InceptionV3 feature with support vector machine classifier(SVM), can effectively predict the therapeutic use of medicinal plants from leaf images with high accuracy and offers a promising solution to the fading traditional medicinal knowledge. © 2024 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Secured Smart Mirror Control Systems with Enhanced Vehicle and Signboard Detection 11th

Artificial Intelligence-Based Secured Smart Mirror Control S...

引用

11th EAI International Conference on Advancement of Science and technology, ICAST 2023

作者： Sanjay, S. Nithish Soorya, S.S. Vengatesh, R. Prakasam, P. Annamalai, Pushparaghavan School of Electronics Engineering Vellore Institute of Technology Vellore India Faculty of Electrical and Computer Engineering Bahirdar University Bahir Dar Ethiopia

ISBN: (纸本)9783031641503

Vehicle accidents have a significant impact on society, and they have a number of detrimental repercussions on individuals, families, and communities. Vehicles are an essential part of everyone’s daily lives in the modern world;therefore, it is very important to drive them in a cautious manner to prevent accidents. A side mirror is very important equipment in a vehicle as it helps drivers with a view of the area behind and to the sides of the vehicle. The proposed work focuses on the enhancement of artificial intelligence (AI)-based automatic side mirror folding systems in addition with vehicle and signboard detection as driver alert measures. The system proposed inspects authorized persons with the help of face detection and fingerprint verification applications provided via individual phones. The signboard detection helps the driver to notice signboards to make necessary adjustments in very crowded traffic areas, and vehicle detection helps the driver to drive in a cautious manner, specifically when taking turns in highly congested areas with the help of Internet of Things (IOT) applications. The system checks for the presence of signboards, monitors the surroundings, and supervises the security of the vehicle using face detection and android app-based fingerprint verification. The proposed AI-based method achieved the 95.5% testing accuracy for unregistered persons with the help of face detection and fingerprint verification. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mirrors

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Compact Slotted Rectangular Microstrip Patch Antenna for 5G Communication Systems Operating at 28 GHz 7

Design and Analysis of Compact Slotted Rectangular Microstri...

引用

7th IEEE International conference for Convergence in technology, I2CT 2022

作者： Ayalew, Lijaddis Getnet Asmare, Fanuel Melak Bahir Dar Institute of Technology Bahir Dar University Faculty of Electrical & Computer Engineering Bahir Dar Ethiopia

ISBN: (纸本)9781665421683

This paper presents two compact-sized rectangular microstrip patch antenna(RMSPA) models with multiple slots for 5G mobile communication applications which require high bandwidth. The radiating elements of the proposed antennas are modified by varying slot arrangements. The resonating frequency of 28GHz, one of the candidates for 5G applications, is considered at which a low atmospheric absorption rate of electromagnetic waves has resulted. The size of the proposed antennas is 7 × 7 × 0.8 mm3 with a substrate of FR4 material, a relative permittivity of 4.3, and a loss tangent of 0.025. The proposed antennas are simulated using computer Simulation technology (CST) Microwave Studio electromagnetic simulator software. For a better bandwidth improvement over the existing designs, multiple slots are inserted and optimized. Additionally, compared to published results the performance of the proposed antennas show improvements in return loss, voltage standing wave ratio(VSWR), and gain. © 2022 IEEE.

关键词： Internet of things

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 6

Quantum Generative Adversarial Network for Autonomous Drone ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Swarnalatha, Anumula Archana, Nalluri Mukkapati, Naveen Selvakumar, Subramanian Tamir, Eneyachew Manikandaprabu, P. Department of Aeronautical and Aerospace Engineering KCG College of Technology Tamil Nadu Chennai600097 India Department of Computer Science and Engineering Vignan's Foundation for Science Technology and Research Andhra Pradesh 522213 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh 522502 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 Tamil Nadu Salem636005 India

ISBN: (纸本)9798331522667

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. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Transient stability enhancement of Beles to bahir dar transmission line using adaptive neuro-fuzzy-based unified power flow controller

引用

Journal of electrical Systems and Information technology 2024年第1期11卷 1-18页

作者： Alemu, Yechale Amogne Yetayew, Tefera Terefe Mossie, Molla Addisu Faculty of Electrical and Computer Engineering Woldia Institute of Technology (WiT) Woldia University Woldia Ethiopia Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology (BiT) Bahir Dar University Bahir Dar Ethiopia

A power system is a complex, nonlinear, and dynamic system, with operating parameters that change over time. Because of the complexity of big load lines and faults, high-voltage transmission power systems are usually vulnerable to transient instability concerns, resulting in power losses and increased voltage variation. This issue has the potential to cause catastrophic events such as cascade failure or widespread blackouts. This problem affects Ethiopia's high-voltage transmission power grid in the northwest area. Because of the increased demand for electrical energy, transmission lines' maximum carrying capacity should be enhanced to maintain a secure and uninterrupted power supply to consumers. To address the problem, ANFIS-based UPFC is used for high-voltage transmission lines. This device was chosen as the ideal alternative due to its capacity to rapidly correct reactive power on high-voltage transmission networks. The PSO algorithm was used to determine the best location for the UPFC. The ANFIS controller receives voltage error and rate of change of voltage error as inputs. Seventy percentage of the retrieved data are used for ANFIS training and 30% for ANFIS testing. To show the performance of the proposed controller, three-phase ground faults are used from a severity perspective. When a three-phase ground fault occurs at the midpoint of the Beles to bahir dar transmission line, for instance, the settling time of rotor angle deviation, rotor speed, rotor speed deviation, and output active power of synchronous generators using ANFIS-based UPFC is reduced by 70.58%, 37.75%, 37.75%, and 43.75%, respectively, compared to a system without UPFC. At peak load, PI-based UPFC and ANFIS-based UPFC reduce active power loss by 51.25% and 71.50%, respectively, compared to a system without UPFC on the Beles to bahir dar transmission line. In terms of percentage overshoot and settling time, ANFIS-based UPFC outperforms PI-based UPFC for transient stability enhancement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Communication Reliability: Designing Microwave Links for bahir dar-Woretta Connectivity

引用

Advances in Materials Science and engineering 2024年第1期2024卷 6535616-6535616页

作者： Mihretu Adega, Gashaw Faculty of Electrical and Computer Engineering Bahir Dar Institute of Technology Bahir Dar University POB 26 Bahir Dar Ethiopia

This paper explores the need for establishing a microwave link between bahir dar and Woretta as an alternative communication solution to the existing optical fiber infrastructure. Microwave links offer an effective way to overcome challenges posed by rugged terrains and unfavorable environmental conditions that hinder the deployment of fiber optics. As Woretta emerges as a key economic and investment hub within the Amhara Region, demand for reliable and efficient communication is expected to grow significantly. The study encompasses various aspects of planning and designing the microwave link, including site surveys, consideration of fade margins, frequency planning, link budget calculations, and assessing the feasibility and reliability of the proposed link. The paper employs LINKPlanner 5.4.1 software to simulate and validate the results. Due to terrain constraints, a direct link between bahir dar and Woretta is not feasible. Instead, a two-hop link is proposed, involving transmission from bahir dar to Zege, and then from Zege to Woretta. This alternative configuration ensures optimal connectivity while addressing the terrain limitations. By presenting a comprehensive analysis and simulation of the microwave link, this paper provides valuable insights into the planning and implementation of a robust communication infrastructure. The proposed microwave link will offer a reliable and efficient alternative to the existing optical fiber network, ensuring uninterrupted connectivity to support the region's growth and development. © 2024 Gashaw Mihretu Adega.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Feasibility Study and Energy Management of a Hybrid Microgrid for Ethiopian Rural Community

Feasibility Study and Energy Management of a Hybrid Microgri...

引用

2022 IEEE International Conference on electrical, computer, and Energy Technologies, ICECET 2022

作者： Ashetehe, Ahunim Abebe Shewarega, Fekadu Bantyirga, Belachew Bahir Dar Institute of Technology-Bahir Dar University Faculty of Electrical and Computer Engineering Bahir Dar Ethiopia University Duisburg-Essen Electrical and Computer Engineering Duisburg Germany

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

This paper presents the feasibility study of a hybrid microgrid and its energy management for the Ethiopian rural community conducted on Dek island. Daily electric energy consumption of residential, public institutions, small industries (mills), commercial, and deferrable loads of the Island are considered and its average daily energy consumption is 3,596 kWh/day with 405 kW peak power demand. The proposed microgrid configuration is evaluated and collated based on the least net present cost and Levelized cost of energy. Using the Hybrid optimization Model for Electric Renewable software, the study presents the optimal microgrid configuration that meets the energy demand of the study site. The simulation result indicates that the Photovoltaic/Diesel generator/Battery hybrid microgrid configuration is feasible regarding technical, economical, and environmental issues with the net present cost of 4.13M at 0.149 cost of energy. For the optimal operation of the feasible hybrid microgrid, Multi-Agent System with a Fuzzy Logic Controller based energy management system is proposed. © 2022 IEEE.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

Mitigation of High Pv Penetration Effects in electrical Grid Systems Using a Hybrid Particle Swarm and Grey Wolf Optimization Approach

SSRN

引用

SSRN 2024年

作者： Yenealem, Mezigebu Getinet Electrical and Computer Engineering Faculty Bahir Dar Technology Institute Bahir Dar University Bahir Dar Ethiopia

The rising integration of photovoltaic systems into electrical grids has introduced significant challenges allied with voltage stability, power quality, and grid reliability, particularly beneath high PV penetration scenarios. This work presents a hybrid optimization approach combining Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) to mitigate these challenges effectively. The hybrid PSO-GWO method is not only applied to optimize the position and sizing of PV systems, but also the configuration of grid-supportive devices like STATCOMs, in IEEE14- test bus system. Simulation results demonstrate that the hybrid approach significantly improves voltage profiles, reduces power losses, and enhances overall grid stability, outperforming standalone PSO and GWO methods. The findings suggest that the hybrid PSO-GWO optimization technique is a promising tool for managing the complexities of high PV penetration in modern electrical grids, ensuring proficient and reliable grid operation. © 2024, The Authors. All rights reserved.

关键词： Particle swarm optimization (PSO)

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：