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

Minimum Variance Distortionless Response based Distributed Beamforming Technique for C-Band Weather Radar 3

Minimum Variance Distortionless Response based Distributed B...

引用

3rd IEEE India Geoscience and Remote Sensing Symposium, InGARSS 2023

作者： Athira, S. Sahoo, Swaroop Benny, Steffy Chandrasekar, V. IIT Palakkad Department of Electrical Engineering Palakkad India Colorado State University Department of Electrical and Computer Engineering Fort Collins United States

ISBN: (纸本)9798350325591

Distributed Beamforming (DB) technique in phased array radars is a technique that offers significant advantages over mechanically steered narrow-beam weather radars, in terms of scan rate or optimized polarimetric measurement variance. In this study, a simulation-based investigation has been conducted to analyze the variance reduction (in azimuth angle scan) of radar-estimated reflectivity and differential reflectivity using the DB technique. This DB technique uses the minimum variance distortion-less response (MVDR) method for individual beamforming. The In-phase/Quadrature (I/Q) signals used in the beamforming have been simulated from the reflectivity and differential reflectivity observed by CSU-CHIVO C-band radar deployed and operated during the RELAMPAGO field experiment. The main challenge of the study is to simulate a spoiled transmit beam that is $12^{o}$ wide in real-time and then use digital beamforming to generate multiple simultaneous receive beams that are $4^{o}$ wide because of the application of the DB technique the estimated reflectivity standard deviation reduced by 5 dB while the differential reflectivity reduced by 0.5 dB. The results of the simulation-based study showed that using the distributed beamforming technique with MVDR led to a significant improvement in the variance of reflectivity and differential reflectivity measurements. © 2023 IEEE.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Physical-layer security solutions for IoT devices using Radio Frequency Fingerprints 1

Physical-layer security solutions for IoT devices using Radi...

引用

1st International Conference on Computing, Internet of Things and Microwave Systems, ICCIMS 2024

作者： Traynor, Zachary A. Curtin, Ian M. Henggeler, Calvin T. Sulyman, Ahmed Iyanda Electrical and Software Engineering Embry-Riddle Aeronautical University Department of Computer Prescott United States

ISBN: (纸本)9798350351736

Security concerns have been one of the main hinderance for large-scale industrial internet-of-things (IoT) deployments. IoT is actively deployed in industrial sectors such as mining, power generation and transmissions, manufacturing, and transportation. Security breaches in any of these sectors would result in large-scale compromised infrastructure with potential losses far outweighing the benefits of cost-reduction enjoyed in IoT deployments. For these reasons, many levels of security checks must be included in IoT systems deployed in these sectors. Physical layer security solutions are amenable to delay-intolerant applications and are easier to implement than MAC-layer solutions. In this paper, we review promising approaches for Physical layer security solutions in IoT systems using radio frequency (RF) fingerprints from IoT devices. © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Model Explainable AI Method for Fault Detection in Inverter-Based Distribution Systems

Model Explainable AI Method for Fault Detection in Inverter-...

引用

2024 IEEE Texas Power and Energy Conference, TPEC 2024

作者： Reyes, Alejandro Montano Chengu, Ambe Gatsis, Nikolaos Ahmed, Sara Alamaniotis, Miltiadis The University of Texas at San Antonio Department of Electrical and Computer Engineering San Antonio United States

ISBN: (纸本)9798350331202

This paper proposes a model-based explainable artificial intelligence (XAI) architecture for the detection of short circuit faults in inverter-based distribution systems. The architecture consists of two artificial neural networks - one for fault type and the other for fault location classification, which work in tandem for the overall fault detection. These neural networks are trained on synthetic fault data produced in simulation using a test distribution network with inverter-based resource generation. Once a high training accuracy is achieved for each model, Shapley values are employed to provide explanations of the mechanism into how each black-box model - i.e., the neural network- on average, uses each input feature leading to the output response. © 2024 IEEE.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Requirements Elicitation for Machine Learning Applications: A Research Preview

Requirements Elicitation for Machine Learning Applications: ...

引用

2024 IEEE International Conferences of AI, Science, engineering, and Technology, AIxSET 2024

作者： Elvira, Timothy Procko, Tyler Thomas Ochoa, Omar Embry-Riddle Aeronautical University Department of Electrical Engineering and Computer Science Florida United States

ISBN: (纸本)9798350390995

The development of software systems is preceded by an important first phase, requirements elicitation, wherein developers establish the intended functionality of a system to be developed in a series of interviews with a customer. These requirements can often be raw, requiring refinement in an iterative process. Traditional software requirements are of the form 'The system shall... ', where each requirement is written to be clear, concise, consistent, complete, testable and traceable through development. Because Machine Learning (ML) is stochastic, or uncertain, in the face of unseen data, ML behavior cannot be precisely defined. As such, it is posited that software requirements specific to ML must delineate a window of acceptable behavior, e.g., a plus/minus value for evaluated model metrics. The provision of such is essential for the quality of future ML software systems, as the current trend of large-scale generative ML has brought about a paradigm of fine-tuning, e.g., of Large Language Models, in which pre-trained large models are taken 'off the shelf' and made fit for very specific purposes. These specific purposes vary with different use cases, but they are effectively undeclared requirements. The present paper discusses requirements elicitation in the context of ML by considering the four-software engineering requirement elicitation techniques: conversational, observational, analytic and synthetic, providing future researchers with insight for eliciting quality ML requirements. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

FairWire: Fair Graph Generation 38

FairWire: Fair Graph Generation

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Deniz Kose, O. Shen, Yanning Department of Electrical Engineering and Computer Science University of California Irvine IrvineCA United States

Machine learning over graphs has recently attracted growing attention due to its ability to analyze and learn complex relations within critical interconnected systems. However, the disparate impact that is amplified by the use of biased graph structures in these algorithms has raised significant concerns for their deployment in real-world decision systems. In addition, while synthetic graph generation has become pivotal for privacy and scalability considerations, the impact of generative learning algorithms on structural bias has not yet been investigated. Motivated by this, this work focuses on the analysis and mitigation of structural bias for both real and synthetic graphs. Specifically, we first theoretically analyze the sources of structural bias that result in disparity for the predictions of dyadic relations. To alleviate the identified bias factors, we design a novel fairness regularizer that offers a versatile use. Faced with the bias amplification in graph generation models brought to light in this work, we further propose a fair graph generation framework, FairWire, by leveraging our fair regularizer design in a generative model. Experimental results on real-world networks validate that the proposed tools herein deliver effective structural bias mitigation for both real and synthetic graphs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Forward-Bias Microring Phase Shifters in 45nm Electronic-Photonic Foundry CMOS

Efficient Forward-Bias Microring Phase Shifters in 45nm Elec...

引用

2024 Frontiers in Optics, FiO 2024

作者： Day-Friedland, Elam Kramnik, Danielius Stojanović, Vladimir Department of Electrical Engineering and Computer Sciences UC Berkeley BerkeleyCA94720 United States

O-band optical phase shifters based on carrier injection into adiabatic microring resonators are fabricated and characterized in 45nm CMOS. We present a design methodology for optimizing their insertion loss given tun... 详细信息

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

High Performance Hybrid mmWave Massive MIMO Mobile Transceiver using 2-Bit Precoder and DPC 13

High Performance Hybrid mmWave Massive MIMO Mobile Transceiv...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Chen, Kai-Lun Lu, Hsiao-Feng National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu Taiwan

ISBN: (纸本)9798350355079

A near-optimal design of hybrid transceivers for mmWave massive MIMO downlink communications is presented in this paper. The design utilizes low-cost finite-resolution analog precoders and high-performance dirty paper coding for baseband signaling. It achieves within one bit of capacity upper bound using an analog precoder with only 2-bit phase resolution and greatly reduces the cost of commercial hybrid massive MIMO systems. It also improves the transmission rate of a recent hybrid WMMSE-based design that requires continuous phase shifters by more than 360%, making it highly appealing for consumer applications. © 2024 IEEE.

关键词： Radio transceivers

来源：评论

学校读者我要写书评

暂无评论

Understanding Stress in the Aging Community with Technology 6

Understanding Stress in the Aging Community with Technology

引用

6th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Vergara, Kristine Khalil, Mohammad George, Kiran California State University Fullerton Electrical and Computer Engineering Department FullertonCA United States

ISBN: (纸本)9798350396133

Addressing stress in the aging community calls for heightened attention in patient care and mental health services. To refine our comprehension of stress, this study employed electroencephalography (EEG) bio-signal data gathered from individuals aged 65 and older engaged in various skill-based games. The *** Research headset facilitated the acquisition of EEG data. This study's participant group included those without major health conditions;in future work, this data will be compared to others who are confronting significant health issues. Subsequent MATLAB processing enabled comparisons between EEG stress signals of participants without major health conditions. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Error Correction Codes for Robust Classification with Neural Networks Under Sparse Noise 58

Error Correction Codes for Robust Classification with Neural...

引用

58th Asilomar Conference on Signals, Systems and computers, ACSSC 2024

作者： Riherd, Eva Mudumbai, Raghu Xu, Weiyu University of Iowa Department of Electrical and Computer Engineering Iowa CityIA52240 United States

ISBN: (纸本)9798350354058

We consider the problem of designing neural network classifiers that are robust when their inputs are corrupted by sparse noise. We report on a series of experiments on the MNIST image dataset where we test the performance of neural network classifiers on images with a small number of corrupted pixels. We find that neural network classifiers are highly vulnerable to sparsely corrupted inputs, and this vulnerability remains even when substantial amounts of redundancy is added to the inputs. We show that this vulnerability can be effectively fixed by designing a real-numbered error correction code and using 1 minimization procedure to clean up the corrupted inputs. © 2024 IEEE.

关键词： classification error correction code neural network semantic communication sparse error correction

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：