检索结果-内蒙古大学图书馆

10th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2024

作者： Mu, Zeyu Tu, Guancheng Shi, Austin Yang, Kun Sun, Yixin Shen, Cong Park, B. Brian Department of Systems & Information Engineering University of Virginia CharlottesvilleVA United States Department of Computer Science University of Virginia CharlottesvilleVA United States Department of Electrical & Computer Engineering University of Virginia CharlottesvilleVA United States Departments of Computer Science and Electrical & Computer Engineering University of Virginia CharlottesvilleVA United States Departments of Civil & Environmental Engineering and Systems & Information Engineering University of Virginia CharlottesvilleVA United States

ISBN: (纸本)9789897587030

Preceding vehicle identification is crucial for establishing cooperative platooning. This paper presents the development of a prototype preceding vehicle identification system (PVIS) and its field evaluation for the assessment of commercial viability. We designed and assembled a prototype consisting of a processing unit (Jetson Nano board), a communication device (Wi-Fi dongle), a GPS unit, and a distance measurement sensor (Terabee sensor). The Jetson Nano integrates the SparkFun GPS-RTK-SMA unit, the Terabee time-of-flight sensor, and the Wi-Fi dongle. The PVIS prototype in the ego vehicle measures the distance to its preceding vehicle and receives the GPS data from potential preceding vehicles with the PVIS prototypes. With these, the PVIS in the ego vehicle determines the connectivity of the preceding vehicle. The field evaluation results showed that the prototype PVIS works as designed, and each successful identification takes about 5.3 seconds. However, it was found that the Terabee (time of flight) sensor, at times, did not properly measure distances, likely due to an angle issue caused by the roadway surface and vibration of the vehicle. We discussed how to overcome the challenges identified and enhance the prototype for successful commercialization. Copyright © 2024 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Vehicle to vehicle communications

来源：评论

学校读者我要写书评

暂无评论

PairingNet: A Multi-Frame Based Vehicle Trajectory Prediction Deep Learning Network

引用

IEEE Access 2023年 11卷 29566-29575页

作者： Chen, Guan-Wen Sun, Min-Te Ik, Tsi-Ui National Yang Ming Chiao Tung University College of Computer Science Department of Computer Science Hsinchu30010 Taiwan National Central University Department of Computer Science and Information Engineering Taoyuan320317 Taiwan

The traffic infrastructure of a city requires evaluation and improvement through a large amount of data analysis. The construction and laborious work of traditional methods make computer vision flourish in traffic analysis. Among different computer vision technologies for intelligent transportation system, one of the most important algorithms is multiple object tracking (MOT). At present, MOT used in traffic analysis has several shortcomings, such as lack of the output of vehicle speed and movement direction, and the consideration of single factor in trajectory tracking. These limitations have affected the results of traffic analysis. This research proposes an end-to-end deep learning network, called PairingNet. In addition to retaining the function and accuracy of the original detection network, PairingNet integrates the calculation of vehicle trajectory into the network through the feature fusion of consecutive images, which is introduced to predict the movement direction and speed of the vehicle. These additional features can be used to better track the trajectories of vehicles. In addition, a pipeline is designed to reduce the loading latency incurred by using the consecutive frames as the input for PairingNet. The experiment results indicate that the vehicle identification of PairingNet reaches 96% accuracy, surpassing the original YOLOv3 as the backbone structure, and reaches a near 100% accuracy rate in the predicted vehicle position. Moreover, with the pipeline process, the inference speed of PairingNet is very close to the original YOLOv3. In MOT results, the MOTA of PairingNet also has a high performance of 91%. © 2013 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

SE-DO: Navigating the 6G Frontier with Scalable and Efficient DevOps for Intelligent Agents Optimization 14

SE-DO: Navigating the 6G Frontier with Scalable and Efficien...

引用

2024 IEEE 14th Annual Computing and Communication Workshop and Conference, CCWC 2024

作者： Tshakwanda, Petro M. Kumar, Harsh Arzo, Sisay T. Devetsikiotis, Michael University of New Mexico Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350360134

In the imminent era of 6G dominance and the expanding realm of interconnected IoT devices, ensuring seamless connectivity is vital. This paper introduces the Scalable and Efficient DevOps (SE-DO) methodology - a scalable multi-agent system designed for next-gen networks. SE-DO's avant-garde architecture dynamically integrates new agents, mirroring evolving IoT ecosystems. Two sets of agents manage vast IoT data in urban matrices: extraction agents collect, and preprocessing agents refine for computational tasks. Anticipating 6G's prowess, training agents optimize machine learning models for real-time traffic analytics. Augmented by predictor agents, SE-DO prioritizes accuracy, efficiency, and security, validated empirically. SE-DO's adaptability ensures scalable proficiency amid IoT integrations, facilitating a smooth transition to the 6G era. Addressing IoT challenges, SE-DO, rooted in a robust multi-agent system, optimizes agent performance in resource-constrained environments. Real-world experiments highlight SE-DO's high accuracy and efficiency, making it pivotal for future network optimization. Access SE-DO's future on GitHub - where innovation meets accessibility. As next-gen networks demand reliable solutions, SE-DO emerges as an indispensable tool for navigating emergent network paradigms. © 2024 IEEE.

关键词： Intelligent agents

来源：评论

学校读者我要写书评

暂无评论

Food ingredient recognition model via image and textual feature extraction and hybrid classification strategy

引用

International Journal of Reasoning-based Intelligent Systems 2024年第1期16卷 74-90页

作者： Madival, Sharanabasappa A. Jawaligi, Shivkumar S. Department of Computer Science and Engineering Faculty of Engineering and Technology Sharnbasva University India Department of Electronic and Communication Engineering Faculty of Engineering and Technology Sharnbasva University Karanataka Kalburgi India

This research work focuses on food recognition, especially, the identification of the ingredients from food images. Here, the developed model includes two stages namely: 1) feature extraction;2) classification. Initially, the image features and textual features will be extracted, where image features like SIFT and improved CNN-based deep features, textural features are extracted. Then, the hybrid classifier is used for the identification of food ingredients that combines the models like neural network (NN) as well as long short-term memory (LSTM). In order to make the accurate results, the weights of NN and LSTM are fine-tuned via the Chebyshev map evaluated teamwork optimisation (CME-TWO) algorithm. At the final stage, the primacy of the offered scheme is proven concerning varied metrics. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Programable Architecture for LWC NIST FIPS Standard ASCON 12

Efficient Programable Architecture for LWC NIST FIPS Standar...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Elsadek, Islam Tawfik, Eslam Yahya The Ohio State University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350330366

NIST finalized the LWC standardization process initiated in 2018 by selecting ASCON as the new standard. ASCON is an AEAD cryptography algorithm featuring three variants 'ASCON-128, ASCON-128a, ASCON-80pq' vary in terms of input block size and the number of rounds, etc. In this work an efficient programable hardware design that supports all the three AEAD variants is proposed and implemented over GF22nm, SKY130nm ASIC technologies and Spartan-7 FPGA. The programable design is compared to the HW of each individual variant showing the savings in utilizing the programable design which eliminates the need for three separate standalone designs. Results are shown in terms of area, throughput and Energy efficiency. Results show that the programable ASCON saves 61% of total silicon area. The programable HW has an average energy efficiency overhead of 4% compared to dedicated HW design for each variant. In addition to assessing the programmable design, comprehensive study and comparison of the hardware for the individual variants is conducted. ASCON-128a variant is the most energy efficient '2981 Gbits/J' variant with highest throughput '12.16 Mbits/clk'. However, ASCON-128 has the smallest silicon area '2206 μm2' on GF22nm. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

PAC-MC: An Efficient Password-Based Access Control Framework for Time Sequence Aware Media Cloud

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 5632-5648页

作者： Wang, Haiyan Liu, Penghui Zhong, Xiaoxiong Luo, Fucai Xiao, Bin Yang, Yuanyuan Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Zhejiang Gongshang University School of Computer Science and Technology Hangzhou China Hong Kong Polytechnic University Department of Computing Hong Kong Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States

Cloud storage makes it easier for users to access and share data remotely, but it often requires integration with cryptographic technologies to address consumer-oriented applications, such as fine-grained data access, secure data sharing and retrieval. This paper focuses on the fine-grained access problem of media applications based on time sequence, that is, certain critical media applications based on time sequences should ideally be accessible only to authorized clients. The traditional keyword-based searchable encryption (SE) allows effective search and access over encrypted data while preserving data privacy, but most existing solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users within a specified time range). In this paper, we propose PAC-MC, an efficient password-based access control framework for media cloud relying on content control with the time sequence attribute. PAC-MC not only supports multi-keyword search using any monotonic boolean formulas but also allows media owners to control content-encryption keys for different time periods with an updatable password. Furthermore, it supports the self-retrieval of content-encryption keys. In addition, PAC-MC is provably secure under the standard model. Finally, the detailed performance evaluation results and experimental comparisons indicate that PAC-MC is very efficient and outperforms the previous solutions in terms of computation, communication, and storage costs. © 2025 IEEE.

关键词： Media Encryption Access control Cloud computing Servers Passwords Keyword search Copyright protection Streaming media Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning with Quasi-Hyperbolic Discounting 63

Reinforcement Learning with Quasi-Hyperbolic Discounting

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Eshwar, S.R. Motwani, Mayank Roy, Nibedita Thoppe, Gugan Indian Institute of Science Department of Computer Science and Automation Bengaluru India Indian Institute of Technology Department of Computer Science and Engineering Bombay India

ISBN: (纸本)9798350316339

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which has a bias towards immediate gratification. Quasi-Hyperbolic (Q H) discounting is a simple alternative for modeling this bias. Unlike in traditional discounting, though, the optimal QH-policy, starting from some time t1, can be different to the one starting from t2. Hence, the future self of an agent, if it is naive or impatient, can deviate from the policy that is optimal at the start, leading to sub-optimal overall returns. To prevent this behavior, an alternative is to work with a policy anchored in a Markov Perfect Equilibrium (MPE). In this work, we propose the first model-free algorithm for finding an MPE. Using a two-timescale analysis, we show that, if our algorithm converges, then the limit must be an MPE. We also validate this claim numerically for the standard inventory system with stochastic demands. Our work significantly advances the practical application of reinforcement learning. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Property Price Prediction 3

Property Price Prediction

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Robin, Aleena Anna Prasad, Gouri Jiji, Jyothsna Raajesh, Sanjay Sheena, K.V. Muthoot Institute of Technology and Science Department of Computer Science and Engineering India

ISBN: (纸本)9798350354171

This data analytics project is designed for the real estate industry, with the primary aim of predicting property prices, including lands, buildings, and houses linear regression model and also by carefully analyzing and interpreting current market trends. Although numerous existing systems share the common objective of property price prediction, our proposed system brings distinct advantages. One of them is its ability to explore rental options for rooms and buildings. What truly sets our system apart is its comprehensive approach to property valuation. It achieves this by incorporating a user-specific data analysis component, which considers critical factors like user loan availability. Essentially, it bridges the gap between the realm of property investment and the realm of financial planning, equipping users with essential insights to make sound financial decisions in the context of real estate. This project has been meticulously designed with the unique needs of the real estate industry in mind, offering a transformative tool that assists individuals in making smarter choices concerning property investments, rentals, and loans. By providing a comprehensive, user-focused approach, it paves the way for more informed decision-making in the ever-evolving landscape of the real estate market, ultimately promoting financial prudence and responsible financial planning. © 2024 IEEE.

关键词： Data analytics project Linear regression Market trends analysis Predicting property prices Real estate industry Rental options exploration

来源：评论

学校读者我要写书评

暂无评论

Soft-Touch or Hard-Touch: Quantifying Touches through A New System Focusing on A Pool Touchpad for Measuring Timing of Swimmers 23

Soft-Touch or Hard-Touch: Quantifying Touches through A New ...

引用

10th International Conference on Networking Systems and Security, NSysS 2023

作者： Quaium, Adnan Islam, Md. Ashraful Rahman, M. Sohel Islam, A. B. M. Alim Al Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Bangladesh and Department of Electrical and Electronic Engineering Ahsanullah University of Science and Technology Dhaka Bangladesh Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh

ISBN: (纸本)9798400708787

The swimming turn or finishing presents an integral part of competitive swimming, and the time it takes by a swimmer to push off the wall is a significant factor in their ratings. Therefore, it is essential to have a reliable way to measure the timing of touch, i.e., wall-contact, over the finishing or turning points. To do so, swimming pool touchpads are widely used in swimming competitions to overcome human error in measurements by enabling touch-sensing systems at the finishing or turning points. The touch-sensing devices use their sensitive touch sensors to record time with millisecond accuracy, providing athletes with the most precise measurements possible. However, these devices might need a minimal force applied from the swimmers to sense the touch, and thus, to record the timing of the touch. As such, insufficient force applied on the touchpad during swimming could cause skipping the time log. As a result, it is critical to have a trustworthy method for measuring the extent of touch or wall-contact exerted over the touch-sensing systems. This study, for the first time in the literature to the best of our knowledge, proposes such a method for measuring the extent of touch or wall-contact for swimming pool touchpads. In the process of proposing the method, we design and develop a bi-modal sensing module to distinguish the soft-touch and hard-touch exerted over a real pool touchpad used in a swimming pool organizing national and international competitions. Our experiments show that the pool touchpad under experimentation is not always accurate in registering touches. It sometimes fails to register low-force touches while generally registering touches with high force. © 2023 ACM.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Fabrication Techniques for Multilayer Printed Flexible Hybrid Sensor Systems

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2024年第5期3卷 181-189页

作者： Pravin Kachhadiya, Jeneel Tewani, Hridyesh Prabhakar, Pavana Andrews, Joesph B. University of Wisconsin-Madison Department of Electrical and Computer Engineering MadisonWI53706 United States University of Wisconsin-Madison Department of Civil and Environmental Engineering MadisonWI53706 United States University of Wisconsin-Madison Department of Civil and Environmental Engineering Department of Mechanical Engineering MadisonWI53706 United States University of Wisconsin-Madison Department of Mechanical Engineering Department of Electrical and Computer Engineering MadisonWI53706 United States

Additive manufacturing holds the potential to revolutionize circuit fabrication and enable the widespread adoption of printed electronics, particularly in flexible applications, such as wearable or conformable electronic sensing systems. However, realizing practical circuits with multilayer interconnects or vertical interconnect accesses (VIAs) using additive methods, flexible substrates pose significant challenges. In this study, we systematically evaluate four different methods for fabricating VIAs in flexible printed circuits: soldered, printed, conductive epoxy, and zero-ohm jumper VIAs. Through comprehensive testing involving various levels of bending strains, we measure changes in conductive properties and mechanical integrity to validate each method. Our results indicate that printed VIAs exhibit the most desirable properties compared to other methods, with a baseline resistance of approximately 0.9~\Omega and a change of approximately 7% when subjected to a bending radius of 12 mm. Additionally, cyclic bending tests and tensile strength test were exclusively carried out on the printed VIAs to evaluate their resilience under bending and tensile strains. Leveraging the superior performance of printed VIAs, we successfully manufacture a fully conformable impact sensing system capable of adhering to a sports ball, thereby demonstrating their effectiveness in practical applications. This study underscores the utility and potential of multilayer flexible PCB fabrication using additive printing technology, highlighting its significance in advancing the development of innovative electronic systems with enhanced flexibility and reliability. The findings presented herein offer valuable insights into the optimization of VIA fabrication methods and their implications for the design and deployment of flexible electronic devices in diverse real-world scenarios. © 2022 IEEE.

关键词： Flexible electronics

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：