检索结果-内蒙古大学图书馆

Wearable Assistive Device for Enhanced Navigation in Visually Impaired Individuals Using YOLO-Based Object Detection 5

Wearable Assistive Device for Enhanced Navigation in Visuall...

引用

5th IEEE International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Rao, Abhishek S. Poojary, Ramaprasad Karthik Pai, B.H. Rohan Arya, A.R. Utkarsh Kumar, Harsh Darshan, S. Shenoy, H. Nagesh Nmam Institute of Technology Department of Information Science and Engineering India School of Engineering and It Manipal Academy of Higher Education Dubai Campus PO Box no 345050 Dubai United Arab Emirates Canara Engineering College Department of Computer Science and Engineering Benjanapadavu India

ISBN: (纸本)9798350356236

The proposed study addresses the pressing challenge of enabling visually impaired individuals to navigate their surroundings with enhanced safety and autonomy. To this end, we propose a wearable assistive device designed to improve spatial awareness and facilitate environmental interaction. The primary objectives include developing an accurate object detection system, integrating real-time distance measurement capabilities, and incorporating situational awareness through weather data integration. The study methodology employs cutting-edge computer vision and machine learning techniques, with a YOLO-based object detection model at its core. This model ensures robust identification of objects, achieving an impressive 97% precision and recall. To support safe navigation, real-time distance measurement functionality was implemented. Additionally, the device incorporates real-time weather data via the Open Weather API, delivering comprehensive updates on temperature, precipitation, and wind conditions to assist in user decision-making. Design considerations focused on user-centric aspects such as battery life, portability, and cost-effectiveness to ensure practicality and accessibility. Evaluation results demonstrated an average mAP of 98.34% at IoU 0.5 across all object classes, with some reaching up to 99.50%. User testing validated the system's efficacy, achieving a 95% success rate in object identification and spatial guidance. These findings underscore the device's potential to enhance independence, safety, and quality of life for visually impaired users, promoting inclusivity through advanced assistive technology. © 2025 IEEE.

关键词： Distance measurement

来源：评论

学校读者我要写书评

暂无评论

Bayesian hypergame approach to equilibrium stability and robustness in moving target defense 63

Bayesian hypergame approach to equilibrium stability and rob...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Zhang, Hanzheng Cheng, Zhaoyang Chen, Guanpu Johansson, Karl Henrik Shanghai Research Institute for Autonomous Intelligent Systems Tongji University Shanghai China University of Chinese Academy of Science Academy of Mathematics and System Science Chinese Academy of Science Beijing China Kth Royal Institute of Technology and the Digital Futures Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm Sweden

ISBN: (纸本)9798350316339

We investigate the equilibrium stability and robustness in a class of moving target defense problems, in which players have both incomplete information and asymmetric cognition. We first establish a Bayesian Stackelberg game model for incomplete information and then employ a hypergame reformulation to address asymmetric cognition. With the core concept of the hyper Bayesian Nash equilibrium (HBNE), a condition for achieving both the strategic and cognitive stability in equilibria can be realized by solving linear equations. Moreover, to deal with players' underlying perturbed knowledge, we study the equilibrium robustness by presenting a condition of robust HBNE under the given configuration. Experiments evaluate our theoretical results. © 2024 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Secure Vehicular Networks Based on IoT and Cloud Computing

引用

SN computer science 2022年第3期3卷 1-8页

作者： El Zouka, Hesham A. Computer Engineering Department College of Engineering and Technology Arab Academy for Science Technology and Maritime Transport Alexandria Egypt

Undeniably, the increasing number of vehicles on the roads has automatically led to the unbelievable number of accidents occurring every day and the need for a safe communication system among the vehicles has become quite urgent. Using such systems, vehicles can communicate via wireless communication technologies and protocols like ZigBee, WiMax, Bluetooth, GSM, and RF. This paper introduces a communication system that works on preventing accidents by making all the surrounding vehicles communicate using RF, IoT, and LCD technologies to show all the warnings and the indications sent from other vehicles and a VLC that is connected to every vehicle to detect and send all needed information of occurring accidents on the road to all connected vehicles and to identify the hit or damaged ones. Moreover, the framework proposed in this paper attempts to perform mutual authentication procedures between vehicles and road-side units based on radio frequency identification devices and cloud computing. According to this framework, a low-cost device has been implemented using an LED lamp and an electrical circuit to control the LED luminous flux, and the modulated carrier signal has also been modified to effectively suppress the low-frequency noise. It should be noted that the experiments have shown that vehicular networks must be resilient and self-adapted to failures and potential threats to support coordinated transportation systems. Finally, the security analysis has also shown that the proposed framework is efficient, easily deployed and capable of finding the best routing paths between communicating vehicles. © 2022, The Author(s).

关键词： Anonymity Cloud computing Conditional privacy Identity-based cryptography Internet of things Mutual authentication Vehicular network security

来源：评论

学校读者我要写书评

暂无评论

Applying Deep Learning for the Examination of Voice Disorders in the Identification of Parkinson's Disease 1

Applying Deep Learning for the Examination of Voice Disorder...

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Gupta, Kushagra Jain, Vedant Andrew, J. Manipal Institute of Technology Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9798350330915

Parkinson's disease is a degenerative neurological condition marked by difficulties with coordination, tremors, and rigidity in the muscles. Positively, speech recordings show potential as a precocious biomarker for Parkinson's disease, able to identify minute alterations prior to the manifestation of other symptoms. The main objective of this research is to create a machine learning model that can analyse speech recordings and reliably determine whether Parkinson's disease is present. Key questions that the model aims to answer include how well it detects early signs of Parkinson's disease, how well it distinguishes between voice samples from healthy individuals and those from early stages of Parkinson's disease, and whether or not accuracy will vary depending on variables like the length or calibre of voice recordings. The primary goal is to use deep learning methods to analyse voice data to detect Parkinson's disease early on. © 2023 IEEE.

关键词： Deep Learning Extreme Gradient Boosting K-Nearest Neighbour Parkinson's disease Standard Scalar Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Automated Brain Abnormality Segmentation using Modified JAYA algorithm based Fuzzy C-Means Clustering 1

Automated Brain Abnormality Segmentation using Modified JAYA...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Jeenath Shafana, N. Priya Lakshmi, S. Vijayalakshmi Ramani, U. Ramaraj, Kottaimalai Thilagaraj, M. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Cmr Institute of Technology Department of Computer Science and Engineering Bengaluru India K Ramakrishnan College of Engineering Department of Electrical and Electronics Engineering Tiruchirappalli India Kalasalingam Academy of Research and Education Department of Electronics and Communication Engineering Krishnankoil India Mvj College of Engineering Department of Industrial Internet of Things Bengaluru India

ISBN: (纸本)9798350352931

The main risk factors in humans, irrespective of gender or location, are anomalies of the brain, such as tumors and strokes. In healthcare facilities, the degree of disability and underlying cause of brain lesions are typically evaluated by means of regular methods created by trained clinicians. During this procedure, signals and images of the brain are collected in a controlled setting. Selecting an appropriate separation method is essential to getting the desired results. The novel JAYA algorithm, which relies on meta-heuristics, aids in the reclustering of the FCM segmentation results in our suggested techniques, yielding more productive delineation results with clear borders with 86% of Dice Score. However, the exploitation and exploration techniques for searching become more flexible and help identify the optimal solution faster by adjusting the desired function with respect to the accommodating cluster location and population size. Regarding the processing speed, optimal exploitation, and exploratory abilities, the suggested strategy outperforms the other available metaheuristic optimization techniques. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Considering Multiple Stakeholders Perspectives for interval-based Goal Oriented Requirements Prioritization in agile development 6

Considering Multiple Stakeholders Perspectives for interval-...

引用

6th International Conference on computer, Software and Modeling, ICCSM 2022

作者： Fadel, Shaimaa Abdelmoez, Walid Saad, Amani A. Arab Academy for Science and Technology Computer Engineering Department Alexandria Egypt Arab Academy for Science and Technology Software Engineering Department Alexandria Egypt

ISBN: (数字)9781665454865

ISBN: (纸本)9781665454865

Addressing the importance of the requirements prioritization, recent research introduced 'A value-based approach for reasoning with goal models', which allows stakeholders to set an importance estimate for each element in a goal model, that relates the requirements with the business objectives. These estimates are then propagated by means of their relationships (dependencies, contributions and decompositions) to get a prioritized list of all requirements. In this paper, a methodology that extends the aforementioned technique is presented. It uses Goal Oriented Requirements Language (GRL) to prioritize requirements in an agile environment, taking into consideration the opinion of many Stakeholders. As the static value of the estimate is never accurate and does not give the stakeholders enough flexibility, the proposed methodology enables each stakeholder to provide for each requirement its importance as an estimated interval instead of a static value. Then, for each requirement the mean value of the estimation interval is calculated, the information asymmetry and confidence level per requirement are demonstrated, so that a prioritized list can then be generated. The analyst can choose to use the prioritized list based on one of these criteria. This methodology is demonstrated on a case study. © 2022 IEEE.

关键词： Computational modeling Estimation Software Cognition Stakeholders Business

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks for Automated Detection and Classification of Plasmodium Species in Thin Blood Smear Images 1

Convolutional Neural Networks for Automated Detection and Cl...

引用

1st International Conference on Software, Systems and Information technology, SSITCON 2024

作者： Mahesh Kumar, A.S. Maindola, Meenakshi Salis, Vimuktha E Mitra, Abhijit Janumala, Tabitha Vijayan, Alpha Maharaja Institute of Technology Department of Electronics and Communication Engineering Belawadi India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India Global Academy of Technology Department of Information Science and Engineering Bengaluru India Pune India R v College of Engineering Department of Electronics and Instrumentation Engineering Bengaluru India Christ University Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350352931

There has been a continued transmission of malaria throughout the world due to protozoan parasites from the Plasmodium species. As for treatment and control, it is very important to make correct and more efficient diagnostic. In order to observe the efficiency of the proposed approach, This Research built a Convolutional Neural Network (CNN) model for Automated detection and classification on thin blood smear images of Plasmodium species. This model was built on a corpus of 27558 images, included five Plasmodium species. Our CNN model got an overall accuracy of 96% for the cheating detection with an F 1score of 0.94. In the detection of the presence of malaria parasites the test accuracy conducted was as follows: 8%. Species-specific classification accuracies were: P. falciparum (95.7%), P. vivax (94.9%), P. ovale (93.2%), P. malaria (92.8%) and P. Knowles (91, 5%). As for the model SL was found to have sensitivity of 97.3% And the specificity in this case is 9 6. 1 %. The proposed CNN-based approach provides a sound and fully automated solution for malarial parasite detection and species determination, which could lead to better diagnostic performances in day-to-day practices. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Attention Mechanism for Domain-invariant Spoken Language Identification via Inter-domain Alignment and Intra-domain Language Discrimination

Hierarchical Attention Mechanism for Domain-invariant Spoken...

引用

2024 IEEE Conference on engineering Informatics, ICEI 2024

作者： Goswami, Urvashi Muralikrishna, H. Kumar, Sujeet Dileep, A.D. Thenkanidiyoor, Veena Indian Institute of Technology Mandi School of Computing and Electrical Engineering Mandi India Manipal Institute of Technology Manipal Academy of Higher Education Department of Electronics and Communication Engineering Manipal576104 India Indian Institute of Technology Dharwad Department of Computer Science and Engineering Dharwad India National Institute of Technology Goa Department of Computer Science and Engineering Goa India

ISBN: (纸本)9798331505776

Modern methods for spoken language identification (LID) have demonstrated promising results when trained on large datasets. However, their effectiveness is considerably impacted by the discrepancies between the training and testing distributions. Unsupervised domain adaptation (UDA) addresses the domain discrepancies by aligning feature distributions across source and target domains without using labeled target data, thereby ensuring the model performs consistently across both domains. This alignment, however, may come at the cost of reduced model discriminability. To enhance performance under domainmismatched conditions, a LID system should learn domaininvariant representations of speech while maintaining language discriminability at every level, from initial segment-level representations to final utterance-level representations. To address this issue, in this paper, we propose a hierarchical attention network that simultaneously enhances model domain invariance through inter-domain alignment and improves model's language discriminability using intra-domain contrastive discrimination. The performance on the target domain shows that the proposed method exceeds the effectiveness of the top-performing existing approaches. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Implicit Scene Context-Aware Interactive Trajectory Prediction for Autonomous Driving

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 5461-5477页

作者： Lan, Wenxing Li, Dachuan Hao, Qi Zhao, Dezong Tian, Bin Southern University of Science and Technology Research Institute of Trustworthy Autonomous Systems Shenzhen518055 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China

The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context information (e.g., traffic rules) within complex scenarios is still challenging. In this work, we propose an implicit scene context-aware trajectory prediction framework (the PRISC-Net, Prediction with Implicit Scene Context) for accurate and interactive behavior forecasting. The novelty of the proposed approach includes: 1) development of a behavior prediction framework that takes advantage of both model- and learning-based approaches to fully encode scene context information while modeling complex interactions;2) development of a candidate path target predictor that utilizes explicit and implicit scene context information for candidate path target prediction, along with a motion planning-based generator that generates kinematic feasible candidate trajectories;3) integration of the proposed target predictor and trajectory generator with a learning-based evaluator to capture complex agent-agent and agent-scene interactions and output accurate predictions. Experiment results based on vehicle behavior datasets and real-world road tests show that the proposed approaches outperform state-of-the-art methods in terms of prediction accuracy and scene context compliance. © 2016 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Multilevel Product Classification Using Machine Learning Algorithms Sowjanya 3

Multilevel Product Classification Using Machine Learning Alg...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Sowjanya Arjunan, R. Vijaya Babu, D. Vijendra Manipal Institute of Technology Manipal Academy of Higher Education Computer Science and Engineering Karnataka Manipal India Vellore Institute of Technology School of Electronics Engineering Tamil Nadu Vellore India

ISBN: (纸本)9798350372120

Platforms for e-commerce commonly employ a preestablished, organized structure of product classifications. Traditional product categorization methods have primarily relied on text-based data, which can occasionally fall short of providing a comprehensive understanding of a product's characteristics. However, employing image data in classification models has several advantages. The pictures offer a wealth of visual knowledge by capturing details such as color, shape, texture, and size that text explanations may miss. By incorporating text and image data, the classifier gains greater knowledge of each product, resulting in higher categorization reliability. Furthermore, the inclusion of image data enables the machine learning model to discover aesthetic patterns and features that are tricky to convey through text alone, expanding its ability to precisely assign items to their corresponding categories. The current study validates a new classifier for predicting categories using both textual and image data. This suggested approach is being attempted to enhance the accuracy and fullness of product classification. © 2024 IEEE.

关键词： Image classification

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：