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

Enabling Ultralow-Latency Services With Ubiquitous Mobility by Means of a Compact Network Architecture

引用

IEEE Transactions on Mobile Computing 2025年第6期24卷 4858-4873页

作者： Cai, Guiliang Wu, Qiang Wang, Ran Zhi, Lianyi Fu, Xiaoming Zhang, Hongke Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Faculty of Mathematics and Computer Science University of Göettingen Göttingen37073 Germany Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China

With the rapid development of emerging services such as cellular vehicle-to-everything and immersive video service, network connections have further evolved from tangible physical connections to intangible virtual connections such as content, services, and computing resources, and the application scenarios have become more abundant. The mobile ultra-service, which is characterized by ultra-low latency, ultra-high reliability, and ubiquitous mobility, is becoming one of the most representative traffic types. However, the existing mobile network architecture has not evolved sufficiently to meet the specific requirements of these mobile ultra-services, the mobility anchors introduce unnecessary node and link latency, leaving space for further optimization. A compact network architecture (ComArch) is proposed in this paper for ultralow-latency services with ubiquitous mobility. ComArch is designed with a mapping control plane and a generalized forwarding plane to collaboratively implement packet forwarding in mobile scenarios. The generalized forwarding plane handles packet forwarding, while the mapping control plane manages terminals’ identifier and locator mapping entries. The node latency introduced by mobility anchors is eliminated, and an efficient routing scheme is proposed to find the optimal mandatory nodes in the forwarding path, thereby reducing unnecessary link latency. Experimental results show that ComArch can effectively reduce end-to-end delay while saving resources. © 2002-2012 IEEE.

关键词： Vehicle to Everything

来源：评论

学校读者我要写书评

暂无评论

Advancing Healthcare Through Internet of Things: A Comprehensive Review of Smart Healthcare Systems and Their Applications 2

Advancing Healthcare Through Internet of Things: A Comprehen...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Raushan, Rahul Chaudhri, Shiv Nath Suman, Saurabh Kumar, Dhiraj Kumar, Gulshan Kumar, Abhishek Faculty of Engineering and - Technology Department of Computer Science & Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

The Internet of Things (IoT) has turned the healthcare domain in a better direction due to more interconnected and smarter systems that enhance care delivery. Certainly, the IoT-accessible applications in these fields are only possible if devices, sensors, and real-time data are interconnected. Among today's marvels are remote patient monitoring, wearable health trackers, telemedicine, and smart hospital management. Medicine gets more personal, effective, and accessible due to these improvements. However, its development remains unmatched being faced with complexities such as security of personalized data, safety risks resolution, and seamless device-to-system integration. This paper examines the influential role of IoT in advanced healthcare systems, with its virtues, major applications, and implementation obstacles as the subject. The Internet of Things as a mode of health and technology bridging can entirely change how medicines are being practiced and even lead to the improvement of the lives of patients by introducing adaptive and efficient hospital systems. Thus, IoT can be a technology that balances tech and medicine for the betterment of patient treatment outcomes and make the system adaptive and efficient. © 2025 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising

引用

IEEE Access 2025年 13卷 71880-71907页

作者： El-Nabi, Samy Abd Ibrahim, Ahmed F. El-Rabaie, El-Sayed M. Hassan, Osama F. Soliman, Naglaa F. Ramadan, Khalil F. El-Shafai, Walid Faculty of Computer Science and Engineering Department of Artificial Intelligence Engineering South Sinai 46511 Egypt Menoufia University Faculty of Electronic Engineering Department of Electronics and Electrical Communications Engineering Menouf32952 Egypt Suez Canal University Faculty of Computers and Informatics Information Systems Department Ismailia41522 Egypt Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Computer Science Department Riyadh11586 Saudi Arabia

With the rapid development of intelligent transportation systems and growing emphasis on driver safety, real-time detection of driver drowsiness has become a critical area of research. This study presents a robust and scalable driver drowsiness detection framework that integrates a Swin Transformer-based deep learning model with a diffusion model for image denoising. While conventional convolutional neural networks (CNNs) are effective in standard vision tasks, they often suffer performance degradation in real-world driving scenarios due to noise, poor lighting, motion blur, and adversarial attacks. To address these challenges, the proposed model focuses on eye-state detection, specifically, prolonged eye closure, as a primary indicator of driver disengagement and fatigue. Our system introduces a novel preprocessing stage using a denoising diffusion model built on a U-Net encoder-decoder architecture, effectively mitigating the impact of Gaussian noise and adversarial perturbations. Additionally, we incorporate adversarial training with Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) attacks, demonstrating significant improvements in classification accuracy and resilience. Evaluations are conducted on two benchmark datasets, Eye-Blink and Closed Eyes in the Wild (CEW), under both clean and noisy conditions. Comparative experiments show that the proposed system outperforms several state-of-the-art models, including ViT, ResNet50V2, InceptionV3, MobileNet, DenseNet169, and VGG19, in terms of accuracy (up to 99.82%), PSNR (up to 41.61 dB), and SSIM (up to 0.984), while maintaining competitive inference times suitable for practical deployment. Moreover, a detailed sensitivity analysis of data augmentation strategies reveals that techniques such as rotation and horizontal flip substantially enhance the model’s generalization across variable visual inputs. The system also demonstrates improved robustness under real-world black-box scenarios and adver

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Topology-adaptive Bayesian optimization for deep ring echo state networks in speech emotion recognition

引用

Neural Computing and Applications 2025年第1期37卷 399-416页

作者： Soltani, Rebh Benmohamed, Emna Ltifi, Hela University of Sfax BP 1173 Sfax3038 Tunisia Department of computer science Onaizah college of Engineering and Information Technology Oniazah colleges Saudi Arabia Computer Science and Mathematics Department Faculty of Sciences and Techniques of Sidi Bouzid University of Kairouan Kairouan Tunisia

Speech emotion recognition is a difficult task that is gaining attention in a variety of domains, including psychology, human–computer interaction, and speech processing. To recognize speech emotions, machine learning techniques such as convolutional neural networks and long short-term memory networks have been successfully used. However, these models often fail to capture the long-term temporal dynamics of emotional speech. In this work, data augmentation was performed on all datasets. The generated result was used to extract the discriminant features. Then we apply a deep echo state network with a ring topology. The Bayesian optimization (BO) algorithm was applied to the spectral radius of the reservoir matrix. Our approach reveals term-weighted and unweighted accuracies of (75.45%, 74.79%), (86.89%, 86.14%), (98.99%, 97.62%), and (62%, 61.24%) on EMO-DB, SAVEE, RAVDESS, and TESS datasets. The findings demonstrate that by using BO, we are able to determine an optimal spectral radius. Therefore, this approach balances the minimal complexity of reservoir design and high emotion recognition accuracy. Notably, we demonstrate that a simple, deterministically constructed cycle reservoir within DRESN is comparable to other methodologies. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Centripetal Intensive Deep Hashing for Remote Sensing Image Retrieval

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12439-12453页

作者： Wang, Weigang Guo, Zhongwen Cui, Ziyuan Zhao, Hailei Xian, Lintao The Faculty of Electrical Engineering and Computer Science Ocean University of China Qingdao266499 China The Department of Intelligent Medical Engineering Shandong Second Medical University Weifang261053 China

With the breakthrough of convolutional neural networks, deep hashing methods have demonstrated remarkable performance in large-scale image retrieval tasks. However, existing deep supervised hashing methods, which rely on pairwise or triplet labels, typically learn the hash function via random or hardest sample mining within training batches. This strategy primarily captures local sample similarities, causing a distribution shift and limiting retrieval performance. Furthermore, most methods emphasize global features while overlooking structural information, which is essential for understanding spatial relationships in images. To solve these limitations, we propose a Centripetal Intensive Deep Hashing (CIDH) method for remote sensing image retrieval. Initially, we design a Hybrid-Attention Guided Multiscale Refinement Network (HGMRN) that integrates channel and spatial attention to capture multiscale visual features and highlight salient regions at different scales. Subsequently, we introduce a central similarity loss via class-centered labels to optimize the spatial distribution of global samples, which can encourage hash codes with similar semantics to cluster around centroids and reduce distribution shift. Meanwhile, we incorporate a central intensive loss into the Hamming space to shorten intra-class Hamming distances, generating more compact and discriminative hash codes. Extensive experiments demonstrate the superiority of our CIDH method compared with current state-of-the-art deep hashing methods. © 2008-2012 IEEE.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Auto-3D-house Design from Structured User Requirements

引用

Machine Intelligence Research 2025年第2期22卷 368-385页

作者： Minkui Tan Qi Chen Zixiong Huang Qi Wu Yuanqing Li Jiaqiu Zhou School of Software Engineering South China University of TechnologyGuangzhou 510006China Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide SA 5005Australia School of Automation Science and Engineering South China University of TechnologyGuangzhou 510006China

We study the task of automated house design,which aims to automatically generate 3D houses from user ***,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user *** address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,*** the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of *** addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary ***,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline ***,we render 3D houses according to the given style requirements in a rule-based *** on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.

关键词： Automated house design user requirements understanding outline processing layout generation graph feature generation.

来源：评论

学校读者我要写书评

暂无评论

Development of Technologies for Prevention of Wild-Animal Related Losses to Agricultural Fields

引用

Journal of The Institution of Engineers (India): Series B 2025年第2期106卷 635-646页

作者： Doss, Srinath Kumar, Rajiv Paranthaman, Jothi Faculty of Engineering and Technology Botho University Gaborone Botswana School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India Faculty of Engineering Gaborone University College of Law and Professional studies Gaborone Botswana

Over the past decades, integration of wireless sensor networks (WSNs) and computer vision (CV) technology has shown promising results in mitigating crop losses caused by wild animal attacks. Studies have demonstrated the effectiveness of these technologies in providing real-time monitoring and early detection of animal intrusions into agricultural fields. By deploying WSNs equipped with motion sensors and cameras, farmers can receive instant alerts when wild animals enter their fields, allowing for timely intervention to prevent crop damage. Furthermore, advancements in CV algorithms possess made possible to automatically detect and classify the animal species, facilitating targeted response strategies. For example, sophisticated image processing techniques can differentiate between harmless birds and destructive mammals, allowing farmers to focus their efforts on deterring the most damaging species. Field trials and pilot projects implementing WSN-CV systems have reported significant reductions in crop losses attributed to wild animal raids. By leveraging data collected through sensor networks and analyzed using computer vision algorithms, farmers can make informed decisions regarding pest and insect management strategies. This data-driven approach has led to more efficient utilization of resources, such as targeted application of insecticides and pesticides, resulting in both economic and environmental benefits. Moreover, the integration of WSN-CV technology has enabled the development of innovative deterrent systems that leverage artificial intelligence and automation. These systems can deploy non-lethal methods, such as sound or light-based repellents, to deter wild animals without causing harm to the environment or wildlife populations. Overall, the combination of wireless sensor networks and computer vision technology provides the promising resolution to the long-standing issue of wild animal-related losses in agriculture. By harnessing the power of data and a

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Theoretical analysis and design of a dual-wavelength and selectable all-optical broadband QDs semiconductor optical amplifier (QDs-SOA) with inhomogeneous broadening

引用

Optical and Quantum Electronics 2025年第2期57卷 1-26页

作者： Eyvazi, Mahdiyeh Yadipour, Reza Rostami, Ali Rostami, Parisa Mirtagioglu, Hamid Faculty of Electrical and Computer Engineering University of Tabriz Tabriz*** Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz*** Iran SP-EPT Lab ASEPE Company Industrial Park of Advanced Technologies Tabriz Iran Faculty of Medicine Tabriz University of Medical Science Tabriz Iran Department of Statistics Faculty of Science and Literature University of Bitlis Eren Bitlis Turkey

This study delves into the significant role played by Quantum Dot Semiconductor Optical Amplifiers (QD-SOAs) in meeting the ever-growing bandwidth demands. QD-SOAs offer a unique blend of cost-effectiveness, integration capabilities, wide bandwidth, rapid responsiveness, robust power output, stability, and spectral adaptability, driving notable advancements in optical communication systems. In this work, we introduce a novel two-wavelength amplifier structure based on Quantum Dot Semiconductor Optical Amplifiers (QD-SOAs) that utilizes quantum dots of different sizes to achieve efficient amplification at specific mid-infrared wavelengths. This innovative approach, which incorporates quantum dots with varying sizes, enables enhanced performance by optimizing the amplification process for each specific wavelength. Furthermore, this work demonstrates the use of tailored optical pumping mechanisms that enhance the carrier recovery process and reduce carrier relaxation times in the active region. This novel optical pumping technique leads to a significant increase in the efficiency and speed of the amplifier, distinguishing this study from others in the field. Simulation results provide detailed insights into the complex interplay between carrier interactions and gain spectra, offering a comprehensive understanding of QD-SOA operational dynamics. The proposed Quantum Dot Semiconductor Optical Amplifier (QD-SOA) achieves significant advancements in optical communication, offering maximum amplification rates of 26.9 and 19.9 times for QD1 and QD2, respectively, and bandwidths of 12 THz and 15 THz. The study highlights the role of quantum dot size, homogeneous and inhomogeneous broadening, and optical pumping in enhancing gain and performance, demonstrating the potential of QD-SOAs for high-gain, wide-bandwidth applications in photonic systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Semiconductor quantum dots

来源：评论

学校读者我要写书评

暂无评论

PuzMaty: Supporting Puzzle Mats Design Creation

PuzMaty: Supporting Puzzle Mats Design Creation

引用

2025 IEEE/SICE International Symposium on System Integration, SII 2025

作者： Yamamoto, Sarii Wang, Jiajun Chan, Liwei Sugiura, Yuta Keio University Faculty of Information and Computer Science Kanagawa Japan National Yang Ming Chiao Tung University Department of Computer Science and Engineering Hsinchu Taiwan

ISBN: (纸本)9798331531614

Puzzle mats made of cushioned material are widely used in environments like homes and playrooms to prevent injuries from infants and toddlers falling. The mats feature puzzle-like edges, allowing users to freely adjust their size and shape to fit the space where the mat is placed. This study proposes "PuzMaty,"a design interface for drawing patterns of animals, numbers, letters, etc. using puzzle mats of different colors. This interface is expected to make the puzzle mat function not only as a safety measure but also as an interior decoration. It is also likely to reduce the burden of childcare when placing mats because it makes the number of mats required for a particular space more intuitive. © 2025 IEEE.

关键词：

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：