检索结果-内蒙古大学图书馆

Intelligent wearable vision systems for the visually impaired in Saudi Arabia

Neural Computing and Applications 2025年第14期37卷 8571-8591页

作者： Talaat, Fatma M. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Abd Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Navigating the world with visual impairments presents unique challenges, often limiting independence and safety. This research introduces SafeStride, a novel algorithm designed to empower visually impaired individuals through real-time obstacle detection and navigation assistance. SafeStride functions through five interconnected phases: sensor data acquisition, data preprocessing, obstacle detection, path planning, and feedback and guidance. A combination of ultrasonic sensors, cameras, and inertial measurement units (IMUs) feed comprehensive environmental data into the system, enabling accurate obstacle detection and safe path planning. Evaluating SafeStride's performance involved the MNIST dataset for image recognition and a dedicated indoor object detection dataset. Additionally, comparisons were made against three deep learning models—convolutional neural network (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU). The results showcased SafeStride's high accuracy and effectiveness in both obstacle detection and classification. Beyond its impressive performance, SafeStride represents a significant leap forward in navigation aids for the visually impaired. By offering a comprehensive solution that enhances safety and independence in diverse environments, it holds immense potential to improve the lives of countless individuals. Future efforts will focus on further optimizing the algorithm and testing its real-world capabilities, paving the way for a future where safe and independent navigation becomes a reality for all. All three deep learning models (CNN, LSTM, GRU) excelled in the experiment, achieving high accuracy above 0.98, strong recall and F1-scores near 0.99, and exceptional AUC-ROC scores exceeding 0.9998. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Tunicate Swarm Naked Mole-Rat Algorithm for Image Segmentation and Numerical Optimization

引用

computers, Materials & Continua 2022年第5期71卷 3445-3462页

作者： Supreet Singh Nitin Mittal Urvinder Singh Rohit Salgotra Atef Zaguia Dilbag Singh Department of Electronics&Communication Engineering Chandigarh UniversityMohali140413India Department of Electronics&Communication Engineering TIETPatiala147004India Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia School of Electrical Engineering and Computer Science Gwangju Institute of Science and TechnologyGwangju61005Korea

This paper provides a new optimization algorithm named as tunicate swarm naked mole-rat algorithm(TSNMRA)which uses hybridization concept of tunicate swarm algorithm(TSA)and naked mole-rat algorithm(NMRA).This newly developed algorithm uses the characteristics of both algorithms(TSA and NMRA)and enhance the exploration abilities of *** from the hybridization concept,important parameter of NMRA such as mating factor is made to be self-adaptive with the help of simulated annealing(sa)mutation operator and there is no need to define its value *** evaluating the working capabilities of proposed TSNMRA,it is tested for 100-digit challenge(CEC 2019)test problems and real multi-level image segmentation *** the results obtained for CEC 2019 test problems,it can be seen that proposed TSNMRA performs well as compared to original TSA and *** case of image segmentation problem,comparison of TSNMRA is performed with multi-threshold electro magnetism-like optimization(MTEMO),particle swarm optimization(PSO),genetic algorithm(GA),bacterial foraging(BF)and found superior results for TSNMRA.

关键词： Optimization NMRA TSA image segmentation thresholding

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation and Analysis of Deep Learning Autoencoder-Based Wireless Communication System 3

Performance Evaluation and Analysis of Deep Learning Autoenc...

引用

3rd IEEE International Conference on Electronic engineering, ICEEM 2023

作者： Ismail, Eman Ali, Abdelhay Aly, Omar A. M. Abo-Zahhad, Mohammed Assuit University Faculty of Engineering Department of Electrical Engineering Assuit Egypt Egypt-Japan University of Science and Technology Faculty of Electronics Communications and Computer Engineering Department of Electronics and Communications Engineering Alexandra Egypt

ISBN: (纸本)9798350323511

Recent advancements in deep learning have led to the emergence of autoencoder-based (AE) wireless communication systems, presenting a promising approach to tackle the challenges posed by conventional mathematical models. In this research, a thorough evaluation and analysis of the performance of deep learning AE-based wireless communication systems is conducted. Specifically, our investigation focuses on employing the additive white Gaussian noise (AWGN) channel and explores the impact of varying signal-to-noise ratio (SNR) conditions during the AE training process on system performance. The results show that training the autoencoder under diverse SNR conditions, particularly with an extended number of epochs, surpasses the performance of a fixed-trained autoencoder regarding block error rate (BLER). Additionally, a comparison of BLER between multiple AE models and traditional mathematical representations used in communication systems is conducted. The obtained findings indicate that deep learning AE-based wireless communication systems exhibit promising performance compared to conventional models, underscoring their potential as an effective solution for wireless communication systems. © 2023 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Predicting Landslides and Floods with Deep Learning 4

Predicting Landslides and Floods with Deep Learning

引用

4th International Conference on electronics and Sustainable Communication Systems, ICESC 2023

作者： Chaganti, Pavan Chandra Vishal Vasireddy, Kuladeep Reddy, Endurthy Rishik Dondeti, Revant Reddy Syama, S. Amrita Vishwa Vidyapeetham Department of Electrical and Electronics Engineering Bengaluru India Amrita Vishwa Vidyapeetham Department of Computer Science Engineering Bengaluru India

ISBN: (纸本)9798350300093

Landslides are destructive natural disasters that have a strong destructive potential. The field of landslide disaster prevention is built around landslide detection mapping. Land slide detection is one of the fundamental studies in this subject since the goal of landslide analysis is to reduce the likelihood of landslide occurrence by physical intervention. This study summarizes pioneering studies in the area of landslide analysis and presents how to gather and use landslide data for deciliter and cubic centimeter techniques. The most popular analytical indexes for object detection and image segmentation are listed next. This work even suggests a system of algorithms for identifying the presence of floodwater (water hazard) in images taken using cell phones or other optical cameras. Of the several approaches tested, the pretrained VGG-16 network using a logistic regression classifier achieved the best results. Landslide and flood prediction research is conducted by interpreting aerial photographs and conducting field verification. Remote sensing technologies have enabled researchers to use pictures provided by high-resolution laser to identify landslides and flood brought on by significant events. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Robotic Arm Vehicle using Voice Recognition for Physically Challenged People 2

A Robotic Arm Vehicle using Voice Recognition for Physically...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Nannda, Jia Dora, Lokareddy Venkanna Gupta, Tanvi Chouhan, Aryan Verma, Anmol Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies India Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Faridabad India Department of electrical and electronics engineering Manav Rachna International Institute of Research and Studies India

ISBN: (纸本)9798331541217

In Today's world, all the work is automated by robots. The Robots have become a significant part of today's world, improving many people's lives, especially those who are physically challenged. This research paper presents a unique method for helping people with physical disabilities: A robotic arm vehicle using voice recognition for physically challenged people. Two remarkable features of the robot are its design and its adaptability in handling objects accurately. The comparative research demonstrates improved performance, such as faster job completion and increased grasping efficiency, when compared to older methods. Additionally, by integrating AI, the robotic arm gains the flexibility needed to operate in real-world environments. This finding might lead to more autonomous and effective assistive technology for personal support and healthcare applications. © 2024 IEEE.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

Novel Power-Aware Optimization Methodology and Efficient Task Scheduling Algorithm

引用

computer Systems science & engineering 2022年第4期41卷 209-224页

作者： K.Sathis Kumar K.Paramasivam Department of Computer Science and Engineering Bannari Amman Institute of TechnologySathyamangalam638401TamilnaduIndia Department of Electrical and Electronics Engineering Kumaraguru College of TechnologyCoimbatore641049TamilnaduIndia

The performance of central processing units(CPUs)can be enhanced by integrating multiple cores into a single *** performance can be improved by allocating the tasks using intelligent *** Small tasks wait for long time or executes for long time,then CPU consumes more ***,the amount of power consumed by CPUs can be reduced without increasing the *** are used to connect cores,which are organized together to form a network called network on chips(NOCs).NOCs are mainly used in the design of ***,its performance can still be enhanced by reducing power *** main problem lies with task scheduling,which fully utilizes the ***,we propose a novel randomﬁt algorithm for NOCs based on power-aware *** this algorithm,tasks that are under the same application are mapped to the neighborhoods of the same application,whereas tasks belonging to different applications are mapped to the processor cores on the basis of a series of *** scheduling process is performed during the run *** results show that the proposed randomﬁt algorithm reduces the amount of power consumed and increases system performance based on effective scheduling.

关键词： Randomﬁt algorithm network on chips processor cores power-aware optimization

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Smart Solar Photovoltaic Uninterruptible Power Supply System 1

Design and Development of a Smart Solar Photovoltaic Uninter...

引用

1st International Conference on Circuits, Power, and Intelligent Systems, CCPIS 2023

作者： Maswabi, Thabang Samikannu, Ravi Karpagam, R. Priya, N. Elavarasi, R. Yahya, Abid Botswana International University of Science and Technology Department of Electrical Computer and Telecommunications Engineering Palapye Botswana Easwari Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Amet Deemed to Be University Department of Electrical and Electronics Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350315769

This project focuses on the research, development, and implementation of a solar Photo Voltaic (PV) Uninterruptible Power Supply (UPS) as a backup source of energy from the commonly used hydrocarbon or coal-fired in Botswana. These are the UPS system that will serve as a power backup for a connected load. The design consists of;a solar PV panel, solar charge controller, inverter circuit, and a 2-channel relay 'for switching between the solar and main supplies.' For the UPS system, a solar PV panel converts solar energy to electrical energy. The solar PV panel feeds a Direct Current (DC) output that charges a 12V battery which then connects an inverted circuit where the DC is converted to Alternating Current (AC). A step-up transformer is then used to increase the voltage from 12V to 230V. A relay is programmed to automatically switch between the solar supply and the AC main supply in case of failure of one of the sources and use the stored charge from the battery to supply the load when both sources fail. © 2023 IEEE.

关键词： Uninterruptible power systems

来源：评论

学校读者我要写书评

暂无评论

Deep learning approach for smart home security using 5G technology

Deep learning approach for smart home security using 5G tech...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Amanullah, M. Chaudhary, Sumit Yalini, R. Balaji, M. Vijaya Sudha, M. Dhanraj, Joshuva Arockia Department of Computer Science and Engineering Saveetha School of Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Indrashil University Gujarat Rajpur India Department of Electrical and Electronics Engineering Jayam College of Engineering and Technology Tamil Nadu Nallanur Dharmapuri India Department of Electronics and Communication Engineering Mohan Babu University Andhra Pradesh Tirupati India Department of Computer Science and Engineering Ramachandra College of Engineering Andhra Pradesh Eluru India Department of Mechatronics Engineering Hindustan Institute of Technology and Science Tamil Nadu Padur Chennai India

ISBN: (纸本)9781032669663

With the advent of 5G technology, the entire world will soon be permanently connected, which will connect everything from the biggest megacities to the smallest internet of things. Such a connected hierarchy must integrate the internet of things, smart homes, and smart cities into a single, comprehensive infrastructure. In this research, a fourlayer design is proposed that employs technologies including 5G, the internet of things and deep learning that connect and interface various elements. The research that existing deep learning methods for IoT in smart homes. Deep learning has been used in numerous domains and provides outcomes that are superior to those of human specialists. Deep learning can be typically regarded as an essential move toward genuine AI. Numerous data flows are produced in the detecting areas as a result of such IoT’s development using the 5G standards and uploaded to the cloud for further analysis. Better IoT aid may even be achieved by integrating big data extraction and deep learning in efficient ways. High dependability standards, extremely low latencies, additional capacity, increased security, and high-speed user interaction required for the upcoming 5G network. Also consider future trends, unresolved problems, and insights related to employing deep learning techniques to improve IoT security. As a result, the adoption of deep learning algorithms in the 5G networks has the prospect of enhancing people’s way of life through automating and competence. © 2024 The Author(s).

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

TSDSI Standards Driven Implementation of Smart Radio Environment 17

TSDSI Standards Driven Implementation of Smart Radio Environ...

引用

17th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2023

作者： Shrivastava, Amit K. Kumar, Satish Sahu, Khushboo Sonwani, Bhavesh Sharma, Dixit Srivastava, Dipti S. Garg, Navneet Kherani, Arzad Alam Bhatia, Vimal Mukherjee, Soumava Mukhopadhyay, Samrat Das, Priyanka Mahapatra, Rajarshi Das, Debanjan Lall, Brejesh Iit Department of Electrical Engineering and Computer Science Bhilai India Iiit Department of Electronics and Communication Engineering Bangalore India Iiit Department of Electronics and Communication Engineering Naya Raipur India Department of Electronics Engineering Dhanbad India Iit Department of Electrical Engineering Indore India Iit Department of Electrical Engineering Jodhpur India Iit Department of Electrical Engineering Delhi India

ISBN: (纸本)9798350307672

This paper presents a prototype implementation of a smart radio environment (SRE) based communication system. A reflecting plate, reconfigurable intelligent surface (RIS) is placed between the transmitter and receiver to build the SRE. The RIS can rotate to reflect the incident wave to a particular direction. The experimental model consists of a channel estimator (CE), a generic RIS controller (GRC), and a RIS-specific controller (RSC). The channel estimator is equipped with two universal software radio peripheral's (USRP's) that act as transmitter and receiver. Further, based on the desired throughput requirements, the CE sends commands to the GRC, which in turn sends commands to the RSC that controls the RIS. Since a RIS can be designed and fabricated in many ways, a Telecommunications Standards Development Society, India (TSDSI) standard is in place to list the interface/messages between the wireless system and the RIS. These standardized commands are used to exchange messages between the GRC and RSC. With this setup, the received power improvement of around 20 dBm has been achieved if RIS is deployed. Also, an algorithm at GRC finds the beamforming angle where the received power is maximized. © 2023 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A Method for Image De-Hazing for Vision Based Applications

A Method for Image De-Hazing for Vision Based Applications

引用

2024 International Conference on Computational Intelligence for Green and Sustainable Technologies, ICCIGST 2024

作者： Santhosh Krishna, B.V. Senthil Anandhi, A. Sharmila, G. Ramya, D. Balaji, L. Pasupulati, Baburao New Horizon College of Engineering Computer Science and Engineering Karnataka Bangalore India Karpagam College of Engineering Anna University Computer Science and Engineering Tamilnadu Coimbatore India Sri Eshwar College of Engineering Computer Science and Business Systems Tamilnadu Coimbatore India Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Electronics and Communication Engineering Tamilnadu Chennai India Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Electrical & Electronics Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350381887

The acquired images deteriorate in hazy or foggy circumstances, reducing the fidelity of the color, contrast, and visibility records. The atmospheric particles attenuate, scatter the source radiations are to be blame for this picture degradation. The corruption force relies upon assorted situations having a variable density of environmental particles, their frequency and distance from obtaining gadget. Existing picture dehazing strategies for apparent band pictures are either founded on earlier suspicion to reproduce the transmission map or utilized a learning system to straightforwardly gauge the dehazed picture. As of late, execution examination of existing well known picture dehazing techniques utilizing ghostly dim pictures are acted in which chose frequency groups from various for thickness levels are to be utilized for correlations. The correlation results are shown execution debasement of existing strategies with frequency groups determination and haze thickness levels. In this review, we plan a compelling ghastly and earlier based picture dehazing and upgrade network showing better execution when contrasted with existing strategies while utilizing phantom. Dim pictures from variable frequency groups and haze thickness levels. Our SPIDE-NET comprises of two organizations: 1) otherworldly Picture De-hazing Organization, which is prepared on multi-ghastly murky pictures between 450 nm and 720 nm, and exploits fluctuating constrictions in various frequency groups. 2) Multiscale Earlier based picture De-hazing Organization utilizes multi-scale dull channel and variety lessening priors on picture trios chose from a multiotherworldly foggy picture data set. The suggested approach is a CNN network in the encoder-decoder manner that combines data from both SID-Net and MPDNet by sharing a typical decoder stage. The SHIA dataset was used to create the suggested network, which was then assessed at various haze thickness levels. In comparison to well-known prior learning

关键词： Demulsification

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：