检索结果-内蒙古大学图书馆

IEEE International Conference on Consumer Electronics (ICCE)

作者： Linh Nguyen Cheol-Hong Min Hanho Lee Tuy Tan Nguyen School of Informatics Computing and Cyber Systems Northern Arizona University USA Department of Electrical. and Computer Engineering University of St. Thomas USA Department of Electrical and Computer Engineering Inha University Republic of Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Channel coding in sixth-generation (6G) networks must attain exceptionally low bit error rate (BER), typically in the range of 10– 6 to 10– 9 , to ensure the requisite level of reliability. While fifth-generation (5G) New Radio (NR) coding techniques have made substantial progress, the inherent limitations of the low error floor impede the attainment of such stringent BER targets. Compared to the low-density parity check (LDPC) codes employed in 5G communications, generalized low-density parity check (GLDPC) codes offer a more advantageous tradeoff between computational complexity and error correction performance in 6G networks. GLDPC codes enhance traditional LDPC structures by incorporating more complex local decoding units within their check nodes. When coupled with cryptographic techniques, GLDPC codes can establish a robust information security framework. In this paper, we propose a new security-based GLDPC that uses a number of BCH matrices for the GLDPC decoding process combined with the Kyber algorithm (BCH-based KyGLDPC) before transmitting data to increase reli-ability and solve the security problem against quantum computer attacks. The system's performance is assessed using both image data and data encrypted prior to transmission in a white additive Gaussian noise environment. The results indicate that the system provides strong error correction and data security.

关键词： 6G mobile communication Quantum computing computer network reliability System performance Bit error rate Parity check codes Error correction codes Decoding Reliability Channel coding

来源：评论

学校读者我要写书评

暂无评论

Development of Programmed Autonomous Electric Heavy Vehicle: An Application of IoT 2

Development of Programmed Autonomous Electric Heavy Vehicle:...

引用

2nd International Conference on Electronics and Renewable systems, ICEARS 2023

作者： Reddy, P. Nagasekhar Umaeswari, P. Natrayan, L. Choudhary, Ankur Mahatma Gandhi Institute of Technology Department of Electrical and Electronics Engineering Hyderabad500075 India R.M.K Engineering College Department of Computer Science and Business Systems Kavaraipettai601206 India Saveetha School of Engineering Department of Mechanical Engineering Simats India Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun248002 India

ISBN: (纸本)9798350346640

The influence of automation in the agriculture and construction industry plays a vital role in the development of the economic backbone of any country. The factors such as power, torque and speed are efficiently controlled by automation devices using Internet of things (IoT). The heavy vehicles are the multi-faced application carrier which is been used in construction, agriculture, mining and other heavy-duty fields. This research focuses on developing a IoT integrated sensor-based obstacle detection system for programmed autonomous heavy vehicles which will improve safety in both on-road and off-road construction. The automation process consists of two main categories: Observing the environment and recognizing the activities. The environment in our case is both highways and rural roads. An intelligent- camera is utilised to capture the activities from the captured video and process the data. A LiDAR sensor performs the obstacle detection process using laser reflection technology and an ultrasonic sensor is used to process the vibration and sound produced by the obstacle or upcoming vehicles. These three sensors are integrated with a controller-based device to be powered by the power distribution system in the programmed autonomous heavy vehicle. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Optical sorting:past,present and future

引用

光：科学与应用（英文版） 2025年第5期14卷 1188-1234页

作者： Meng Yang Yuzhi Shi Qinghua Song Zeyong Wei Xiong Dun Zhiming Wang Zhanshan Wang Cheng-Wei Qiu Hui Zhang Xinbin Cheng Institute of Precision Optical Engineering School of Physics Science and EngineeringTongji UniversityShanghai 200092China MOE Key Laboratory of Advanced Micro-Structured Materials Shanghai 200092China Shanghai Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China Shanghai Frontiers Science Center of Digital Optics Shanghai 200092China Tsinghua Shenzhen International Graduate School Tsinghua UniversityShenzhen 518055China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 610054China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore

Optical sorting combines optical tweezers with diverse techniques,including optical spectrum,artificial intelligence(AI)and immunoassay,to endow unprecedented capabilities in particle *** comparison to other methods such as microfluidics,acoustics and electrophoresis,optical sorting offers appreciable advantages in nanoscale precision,high resolution,non-invasiveness,and is becoming increasingly indispensable in fields of biophysics,chemistry,and materials *** review aims to offer a comprehensive overview of the history,development,and perspectives of various optical sorting techniques,categorised as passive and active sorting *** begin,we elucidate the fundamental physics and attributes of both conventional and exotic optical *** then explore sorting capabilities of active optical sorting,which fuses optical tweezers with a diversity of techniques,including Raman spectroscopy and machine ***,we reveal the essential roles played by deterministic light fields,configured with lens systems or metasurfaces,in the passive sorting of particles based on their varying sizes and shapes,sorting resolutions and *** conclude with our vision of the most promising and futuristic directions,including Al-facilitated ultrafast and bio-morphology-selective *** can be envisioned that optical sorting will inevitably become a revolutionary tool in scientific research and practical biomedical applications.

关键词： present future past optical sorting

来源：评论

学校读者我要写书评

暂无评论

Multimodal Detection of Bots on X (Twitter) using Transformers

arXiv

引用

arXiv 2023年

作者： Ilias, Loukas Kazelidis, Ioannis Michail Askounis, Dimitris The Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Athens15780 Greece

Although not all bots are malicious, the vast majority of them are responsible for spreading misinformation and manipulating the public opinion about several issues, i.e., elections and many more. Therefore, the early detection of bots is crucial. Although there have been proposed methods for detecting bots in social media, there are still substantial limitations. For instance, existing research initiatives still extract a large number of features and train traditional machine learning algorithms or use GloVe embeddings and train LSTMs. However, feature extraction is a tedious procedure demanding domain expertise. Also, language models based on transformers have been proved to be better than LSTMs. Other approaches create large graphs and train graph neural networks requiring in this way many hours for training and access to computational resources. To tackle these limitations, this is the first study employing only the user description field and images of three channels denoting the type and content of tweets posted by the users. Firstly, we create digital DNA sequences, transform them to 3d images, and apply pretrained models of the vision domain, including EfficientNet, AlexNet, VGG16, etc. Next, we propose a multimodal approach, where we use TwHIN-BERT for getting the textual representation of the user description field and employ VGG16 for acquiring the visual representation for the image modality. We propose three different fusion methods, namely concatenation, gated multimodal unit, and crossmodal attention, for fusing the different modalities and compare their performances. Finally, we present a qualitative analysis of the behavior of our best performing model. Extensive experiments conducted on the Cresci’17 and TwiBot-20 datasets demonstrate valuable advantages of our introduced approaches over state-of-the-art ones. © 2023, CC BY-NC-ND.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Optimal Method Combining Blockchain and Multi-Agent System to Ensure Data Integrity and Deduplication in the Cloud Environment

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第10期18卷 90-105页

作者： El Ghazouani, Mohamed Ikidid, Abdelouafi Zaouiat, Charafeddine Ait Aziz, Layla Ichahane, Moulay Youssef Er-Rajy, Latifa ESIM Polydisciplinary Faculty of Sidi Bennour Chouaîb Doukkali University El Jadida Morocco Laboratory of System Analysis Information Processing and Industrial Management EST Salé Mohammed V University Salé Morocco Information Technology Laboratory National School of Applied Sciences Chouaîb Doukkali University El Jadida Morocco Computer Science Department Laboratory of Information Systems Engineering Cadi Ayyad University Marrakesh Morocco

Cloud computing (CC) refers to the transmission, storage, and processing of any type of information at a location that is not owned or controlled by the information owner. This information can be stored and accessed anytime, from anywhere, and using any device. However, several challenges threaten the deployment of cloud computing technology within organizations, including user privacy, data integrity, and managing the retention of the vast amount of data that will be stored and analyzed in this environment. In recent years, various data integrity checking systems and data storage mechanisms have been proposed to address these diverse challenges. Nevertheless, some protocols do not guarantee data confidentiality against auditors during the auditing process, while others do not provide batch auditing. Additionally, the majority of these protocols do not support the deduplication technique. Therefore, in this research work, the security features of blockchain technology and those of multi-agent systems (MAS) have prompted us to propose models that enable both data deduplication, saving storage space, and data integrity auditing, efficiently verifying the accuracy of data outsourced to CC environments. Implementation findings indicate that the suggested system is highly feasible and applicable in real-world scenarios. © 2024 by the authors of this article.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Disease Prediction

Hybrid Deep Learning Algorithm For MRI Brain Alzheimer's Dis...

引用

2023 International Conference on Energy, Materials and Communication engineering, ICEMCE 2023

作者： Karthikeyan, D. Nivasini, R. Raja, Kiruba Thangam Madhivadhani, D. Sivakumar, B. Krishna Priya, A.T.R. Srm Institute of Science and Technology Department of Electrical and Electronics Engineering Kattankulathur Chennai India Iitm Research Park Guvi Geek Networks Tamilnadu Chennai India Vit University School of Computer Science Engineering and Information Systems Department of Software and Systems Engineering Vellore India Kings Engineering College Department of Electronics and Communication Engineering Sriperumbudur Chennai India Rohini College of Engineering and Technology Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350393378

Magnetic resonance imaging (MRI) has been used to study the structural makeup of the brain and analyse several neurological disorders and diseased areas. For the adoption of preventative measures, early recognition of Alzheimer's disease (AD) patients is essential. Here, a thorough inspection of the tissue arrangements obtained by MRI images of Outcome and Assessment Information (OASIS) dataset enables an exact characterization of certain brain diseases. There have been a number of division techniques for diagnosing AD that range in complexity. Compassion has been tested by deep learning techniques used to segment the structure of the brain and classify AD because they have the potential to uncover important information from vast amounts of data. In this paper the deep learning technique of Hybrid Dragonfly based GWO convolutional Neural Network (CNN) is achieved promising result for the diagnosis of AD. At image preprocessing wiener filter is used for removing the additive noises and the Gray Level Co-Occurrence Matrix (GLCM) extraction is implemented for texture analyzing. As a result, hybrid deep learning methods of CNN has the accuracy as 90% and the result of the image prediction are presented in this paper. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Dos and Don'ts in Blockchain Research and Development 22

Dos and Don'ts in Blockchain Research and Development

引用

4th International Conference on Blockchain Technology, ICBCT 2022

作者： Zhao, Wenbing Yang, Shunkun Luo, Xiong Zhou, Jiong Department of Electrical Engineering and Computer Science Cleveland State University United States School of Reliability and Systems Engineering Beihang University China School of Computer and Communication Engineering University of Science and Technology Beijing China School of Humanities Economics and Law Northwestern Polytechnical University China

ISBN: (纸本)9781450395762

The goal of this paper is to clarify common misconceptions regarding the blockchain technology, and pointing out some worrisome practices in the field of blockchain technology. We first provide a brief introduction of the blockchain technology, highlighting its design principle, nuts and bolts, and the most fundamental innovation of the technology. Next, we elaborate on a key concept regarding data immutability. In particular, it is a mistake to equate blockchain to data immutability. Data immutability can only be achieved in large-scale public blockchains where the cost becomes an insurmountable barrier for any attempt to change the data recorded in the blockchain. The third topic we discuss is the differences between public, private, and consortium blockchains. We caution the use of private and consortium blockchains. The last topic we argue is regarding blockchain consensus. Because the proof of work (PoW) consensus algorithm has obvious drawbacks on energy consumption, many alternative algorithms have been proposed. We single out two most egregious wrong practices: (1) selecting a small set of validators for reaching consensus, and (2) adopting traditional distributed consensus. © 2022 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR Data

arXiv

引用

arXiv 2025年

作者： Zhu, Haoran Dong, Zhenyuan Topollai, Kristi Choromanska, Anna Learning Systems Laboratory Department of Electrical and Computer Engineering New York University 370 Jay Street NY United States

As opposed to human drivers, current autonomous driving systems still require vast amounts of labeled data to train. Recently, world models have been proposed to simultaneously enhance autonomous driving capabilities by improving the way these systems understand complex real-world environments and reduce their data demands via self-supervised pre-training. In this paper, we present AD-L-JEPA (aka Autonomous Driving with LiDAR data via a Joint Embedding Predictive Architecture), a novel self-supervised pre-training framework for autonomous driving with LiDAR data that, as opposed to existing methods, is neither generative nor contrastive. Our method learns spatial world models with a joint embedding predictive architecture. Instead of explicitly generating masked unknown regions, our self-supervised world models predict Bird’s Eye View (BEV) embeddings to represent the diverse nature of autonomous driving scenes. Our approach furthermore eliminates the need to manually create positive and negative pairs, as is the case in contrastive learning. AD-L-JEPA leads to simpler implementation and enhanced learned representations. We qualitatively and quantitatively demonstrate high-quality of embeddings learned with AD-L-JEPA. We furthermore evaluate the accuracy and label efficiency of AD-L-JEPA on popular downstream tasks such as LiDAR 3D object detection and associated transfer learning. Notably, our method achieves up to a 5× speed-up in pre-training time compared with the state-of-the-art (SOTA) approaches and consistently delivers better performance when fine-tuned on different amounts of labeled data compared to SOTA. More impressively, the experiments show that even when the first layers of the encoders of ADL-JEPA are randomly initialized while the remaining layers are initialized as pre-trained, our method still yields positive transfers, whereas the competitor method suffer from the negative transfers in this case. Systematic experimental results demonstrate that

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

SANS: Spatial-Aware Neural Solver for Plane Geometry Problem 27th

SANS: Spatial-Aware Neural Solver for Plane Geometry Proble...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Lin, Zi-Hao Xiao, Shun-Xin Chen, Zi-Rong Li, Jian-Min Wang, Da-Han Zhang, Xu-Yao School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031781186

Geometry problem solving (GPS) is an important research direction in artificial intelligence. Previous studies have demonstrated the effectiveness of neural solvers in GPS. However, they are deficiencies in accurately representing spatial relationships of geometric primitives within visually rich geometric diagrams. This paper presents a novel neural solver termed spatial-aware neural solver (SANS) that can perceive spatial relationships between geometric primitives. SANS includes two new modules: multimodal dual-branch spatial awareness pre-trained language module and point-primitive spatial-aware attention module. The pre-training module employs a dual-branch visual-textual point-matching strategy to align visual and textual points, and utilizes semantic structure pre-training to model global relationships. Additionally, the point-primitive spatial awareness attention module enhances the model’s ability to perceive spatial relationships between geometric primitives by accounting for the relative positions of points. Experiments show that SANS achieves 81.5 and 74.1 of accuracy on the Geometry3K and PGPS9K datasets. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Applications of Reinforcement Learning in Radar Spectrum Sharing with Reactive Emitters

Applications of Reinforcement Learning in Radar Spectrum Sha...

引用

IEEE International Conference on Radar

作者： Brooke E. Hayden William L. Melvin Douglas B. Williams School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta USA Systems and Technology Research LLC Atlanta USA

ISBN: (数字)9798331539566

ISBN: (纸本)9798331539573

In the last 20 years, radars have been required to share spectrum with other radio frequency (RF) systems. The substantial body of research on radar spectrum sharing has focused on collaborative approaches and non-collaborative approaches with simple interfering emitter behaviors. Modern radar systems have many degrees of freedom (DoFs) which present an opportunity to develop algorithmic techniques to harness the DoFs for effective spectrum sharing with complex interfering emitters. This paper investigates the applicability of reinforcement learning for radar spectrum sharing. To this end, we present results using Q-Learning with $\varepsilon$ -greedy action selection to inform radar waveform selection in environments containing interfering emitters with complex behaviors such as reactivity and time-varying adaptation to the changing spectrum environment. Additionally, we conduct a parametric study of the exploration rate used for $\varepsilon$ -greedy action selection and assess exploration strategies for spectrum sharing problems that include emitters exhibiting both reactive and dynamic changes in behavior.

关键词： Radio frequency Q-learning Parametric study Collaboration Radar Bandwidth Radar applications Tuning

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：