检索结果-内蒙古大学图书馆

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： Ramiz Salama Sinem Al-Turjman Chadi Altrjman Fadi Al-Turjman Richa Gupta Satya Prakash Yadav Satvik Vats Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia TURKIYE Artificial Intelligence Engineering Dept AI and Robotics Institute Near East University Nicosia Turkey Department of Chemical Engineering Waterloo University ON Canada Department of Electronics & Communication Engineering Raj Kumar Goel Institute of technology Department of Computer Science and Engineering G.L. Bajaj Institute of Technology and Management(GLBITM) Greater Noida India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

Artificial intelligence and blockchain are quickly integrating in daily life and business applications. When numerous information systems must access and analyze data in real-time in centralized systems and applications, such as healthcare, a bottleneck develops. This issue would be resolved by blockchain's decentralized database architecture, safe data storage, data exchange, and authentication. Additionally, AI can be present at the very top of the blockchain and produce insights from the shared data that is created and applied to forecasts. Blockchain is a cutting-edge Cybersecurity technology that creates chains by mutual consent between nodes that chronologically link new blocks to those previously stored in nodes. A number of industries, including banking, insurance, cybersecurity, forecasting, healthcare, and cryptocurrencies, among others, are growing more quickly as a result of technology convergence. The likelihood of these systems being hacked increases as more digital technologies are used and these businesses provide services. Blockchain technology and artificial intelligence can work together to create a strong defense against these dangers and security problems. We'll examine how blockchain and AI are merged in cybersecurity in this chapter. We'll go into more detail about how they help secure cyber-physical systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic 3D Teeth Semantic Segmentation with Mesh Augmentation Network 3

Automatic 3D Teeth Semantic Segmentation with Mesh Augmentat...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zhao, Qijun Wu, Xiao Zhu, Feiyu Liu, Jun Wei, Mingying Peng, Jiahan Lu, Yin Sichuan University College of Computer Science Chengdu China Sichuan University National Key Laboratory of Fundamental Science on Synthetic Vision Chengdu China Sichuan University State Key Laboratory of Oral Diseases National Clinical Research Center for Oral Diseases Department of Orthodontics West China Hospital of Stomatology Chengdu China The People's Hospital of Neijiang Department of Stomatology Neijiang China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

In this paper, we propose an approach that improves segmentation networks with automatic augmentation networks for dental mesh data. Since conventional data augmentation is to augment all samples uniformly with predefined parameters, it ignores the unique characteristics of a single tooth sample and cannot make good use of the data set. And the traditional method separates data augmentation and segmentation network training, so the augmented data cannot be well adapted to the network to make it play a good role. We adopt a joint optimization strategy to integrate the augmentation network and the segmentation network, so that the augmented tooth data is the most suitable for the segmentation network. In addition, we design new improved loss functions suitable for augmentation and segmentation networks. Experiments have shown that the automatic augmentation network in our proposed method, named MeshAugNet, can effectively improve the segmentation accuracy after it is used for tooth segmentation. In general, this work achieves a combination of 3D dental data auto- augmentation network and segmentation network, which improves the accuracy of tooth segmentation, and can be used to solve the problem of too few samples in tooth datasets. © 2022 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Intrusive Neural Interfaces: Vascular Stent-Based Neural Electrodes

Revolutionizing Intrusive Neural Interfaces: Vascular Stent-...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Liang Shen Bo Wen Zihua Chen Minjie Wang Linlin Han Bo Shen Kai Cao Lihua Zhang Jianjun Wu Xiaoyang Kang Shanghai Engineering Research Center of AI & Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI & Robotics Ministry of Education Institute of AI & Robotics Institute of Meta-Medical Academy for Engineering & Technology Fudan University Shanghai China Department of Neurology and National Research Center for Aging and Medicine & National Center for Neurological Disorders State Key Laboratory of Medical Neurobiology Huashan Hospital Fudan University Shanghai China Yiwu Research Institute of Fudan University Chengbei Road Yiwu City Zhejiang China

This review delves into the emerging field of endovascular stent electrodes in the realm of brain-computer interfaces, highlighting advancements in their fabrication methods, signal acquisition performance, electrical stimulation effects, and research progress in electrochemical characteristics, mechanical stability, and biocompatibility. In comparison to traditional invasive procedures, endovascular stent electrodes, implanted through minimally invasive means, mitigate the risks associated with extensive trauma and tissue inflammation, demonstrating commendable signal acquisition capabilities. While exhibiting a slight deficiency in visual evoked potentials, they showcase accuracy in the acquisition and decoding of motor perception signals, rivaling or surpassing traditional surgical methods. Additionally, the technology shows potential therapeutic efficacy in electrical stimulation applications. Nevertheless, challenges such as electrical stimulation thresholds and visibility issues warrant further research and refinement. In summary, endovascular stent electrodes, as an emerging avenue in brain-computer interfaces, hold promise for significant breakthroughs in future research, opening up new possibilities in the field of neuroscience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Learning Assisted Approach for Electronic and Optical Characterization of Tin-Doped Titanium Oxide 2

A Learning Assisted Approach for Electronic and Optical Char...

引用

2nd IEEE International Conference on Artificial Intelligence in Everything, AIE 2022

作者： Vubangsi, Mercel Nforna, Edwin Akongnwi Kamsu, Brigitte Fotso Tchoffo, M. Al-Turjman, Fadi Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin Nicosia10 Turkey Htttc Bambili University of Bamenda Nwr Computational Materials Science Lab Department of Computer Science Cameroon Htttc Bambili University of Bamenda Materials Science Research Unit Department of Fundamental Sciences Cameroon Faculty of Science University of Dschang Condensed Matter Electronics and Signal Processing Research Unit Department of Physics Cameroon University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Mersin Kyrenia10 Cyprus

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

In this work, we evaluate the effect of variation of mole fraction of Tin in doped titanium oxide on band gap. To achieve this, we resort to Matminer's "dielectric_constant"dataset and apply an algorithm to featurize the chemical formulae of the compounds in the dataset. Using k-fold cross-validation of random forest, we obtain a Machine learning model with R2 value of 0.81 MAE=0.45. Applying our model to predict the band gap of doped Titanium oxide over a range of 6 compositions, we find that the 50% doping level has a remarkably lower band gap than all other compositions which makes it a more suitable candidate for optical applications such as in solar cells. © 2022 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Machine Learning In Sustainable Development–An Overview

Machine Learning In Sustainable Development–An Overview

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Chadi Altrjman Richa Gupta Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Turkey Faculty of Engineering University of Kyrenia Kyrenia Turkey Waterloo University Canada Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

I have studied how artificial intelligence (AI) or machine learning (ML) is applied in a sustainable system called "Eugenie" for my work, project, and thesis. In this project, I get to discuss Eugenie’s role in ensuring the sustainability of large environmental business organizations. I also get to discuss how it aids operation managers in making predictions about when their machines will break down days, weeks, and months in advance, allowing them to schedule maintenance cycles more effectively. In other words, Eugenie provides plant operators with data so they can prioritize repairs. Eugenie executes this process by utilizing real-time data from numerous sensors attached to large machinery and equipment in the process industry, metals and mining, oil and gas, and smart cities industries. Two products make up this program; the first is named RAY-FINN and the second is called PAPILLON. Eugenie assists businesses in a variety of ways, including:•Aids in the attainment of operational excellence by process organizations•Always raise overall profitability.•Contributes to a greener and safer future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Autoencoder's Weakness to Generate Pseudo Anomalies

arXiv

引用

arXiv 2024年

作者： Astrid, Marcella Zaheer, Muhammad Zaigham Aouada, Djamila Lee, Seung-Ik Department of Artificial Intelligence University of Science and Technology Daejeon34113 Korea Republic of Field Robotics Research Section Electronics and Telecommunications Research Institute Daejeon34129 Korea Republic of Interdisciplinary Centre for Security Reliability and Trust University of Luxembourg Luxembourg1855 Luxembourg Department of Computer Vision Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the trained AE is expected to well reconstruct normal but to poorly reconstruct anomalous data. However, contrary to the expectation, anomalous data is often well reconstructed as well. In order to further separate the reconstruction quality between normal and anomalous data, we propose creating pseudo anomalies from learned adaptive noise by exploiting the aforementioned weakness of AE, i.e., reconstructing anomalies too well. The generated noise is added to the normal data to create pseudo anomalies. Extensive experiments on Ped2, Avenue, ShanghaiTech, CIFAR-10, and KDDCUP datasets demonstrate the effectiveness and generic applicability of our approach in improving the discriminative capability of AEs for anomaly detection. © 2024, CC BY-NC-SA.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

arXiv

引用

arXiv 2023年

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha410082 China College of Engineering and Design Hunan Normal University Changsha410082 China

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Wireless Sensor Networks and Green Networking for 6G communication- An Overview

Wireless Sensor Networks and Green Networking for 6G communi...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Ramiz Salama Fadi Al-Turjman Dibyahash Bordoloi Satya Prakash Yadav Department of Computer Engineering AI and Robotics Institute Research Center for AI and IoT Near East University Nicosia Turkey Artificial Intelligence Engineering Dept. AI and Robotics Institute Near East University Nicosia Turkey Faculty of Engineering Research Center for AI and IoT University of Kyrenia Kyrenia Turkey Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun RS CSE Graphic Era University Dehradun Department of Computer Science and Engineering G.L. Bajaj Institute of technology and Management (GLBITM) Greater Noida India

Wireless sensor networks and green networking have been major research areas in the field of communication technology for the past few decades. In particular, the development of 6G communication systems has brought renewed focus on these areas, as the demands for higher data rates, more diverse applications, and lower energy consumption continue to increase. The use of wireless sensor networks in 6G communication systems has been widely explored in the literature, and has shown great potential for a wide range of applications, including environmental monitoring, industrial process control, and healthcare. However, a key challenge in the deployment of these networks is ensuring their energy efficiency, as the demands on the network will be much higher than in previous generations. To address this challenge, researchers have proposed various green networking techniques, such as energy harvesting and low-power communication protocols, which have been shown to significantly reduce the energy consumption of the sensors. In addition to improving the energy efficiency of wireless sensor networks, researchers have also studied their reliability, scalability, and adaptability. These properties are important in 6G communication systems, as the demands on the network are expected to be much higher than in previous generations. researchers have proposed various methods to improve the reliability, scalability, and adaptability of wireless sensor networks, including the use of error-correction codes, redundant communication channels, and machine learning algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDA: An Accelerated Collision Free Motion Planner for Autonomous Navigation in Cluttered Environments

arXiv

引用

arXiv 2022年

作者： Han, Ruihua Wang, Shuai Wang, Shuaijun Zhang, Zeqing Zhang, Qianru Eldar, Yonina C. Hao, Qi Pan, Jia The Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China The Department of Computer Science The University of Hong Kong Hong Kong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Department of Computer Science and Engineering Harbin Institute of Technology Guangdong Shenzhen China The Weizmann Institute of Science Rehovot Israel The Department of Computer Science and Engineering The Shenzhen Key Laboratory of Robotics and Computer Vision The Sifakis Research Institute for Trustworthy Autonomous Systems Southern University of Science and Technology Guangdong Shenzhen China

Autonomous motion planning is challenging in multi-obstacle environments due to nonconvex collision avoidance constraints. Directly applying numerical solvers to these nonconvex formulations fails to exploit the constraint structures, resulting in excessive computation time. In this paper, we present an accelerated collision-free motion planner, namely regularized dual alternating direction method of multipliers (RDADMM or RDA for short), for the model predictive control (MPC) based motion planning problem. The proposed RDA addresses nonconvex motion planning via solving a smooth biconvex reformulation via duality and allows the collision avoidance constraints to be computed in parallel for each obstacle to reduce computation time significantly. We validate the performance of the RDA planner through path-tracking experiments with car-like robots in both simulation and real-world settings. Experimental results show that the proposed method generates smooth collision-free trajectories with less computation time compared with other benchmarks and performs robustly in cluttered environments. The source code is available at https://***/hanruihua/ RDA_planner. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Multimodal segmentation of medical images with heavily missing data

Multimodal segmentation of medical images with heavily missi...

引用

2021 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2021

作者： Akbar, Muhammad Usman Murino, Vittorio Sona, Diego Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova Italy Department of Electrical Electronics and Telecommunication Engineering degli Studi di Genova Genova Italy Huawei Technologies Ltd. Ireland Research Center Dublin Ireland Department of Computer Science Università di Verona Verona Italy Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Genova Italy Data Science for Health Center for Digital Health & Wellbeing Fondazione Bruno Kessler Trento Italy

ISBN: (纸本)9781665403580

An important aim of research in medical imaging is the development of computer aided diagnosis (CAD) systems. A fundamental step in these systems is the image segmentation and convolutional neural networks (CNNs) are becoming the most commonly used approach to solve this task. However, despite their great power, in this domain CNNs are limited in their potential performance by the usually small amount of data [1]. Computed tomography (CT) and magnetic resonance imaging (MRI) scans are often used to examine the internal structure of human body and have their own unique properties and limitations. As a common practice, the investigations are usually done on a single modality, nonetheless, the simultaneous analysis of multiple modalities can significantly boost the segmentation accuracy. However, obtaining multiple imaging modalities for the same subject is very unlikely. In this paper we investigate the possibility of generating a multimodal CT-MRI representation for a segmentation task starting from a single modality, either CT or MRI. We considered this as a missing data problem, hence, we designed a pipeline where a CycleGAN was used to generate the missing modality. The synthetic modality was then paired with the real one to perform the required segmentation taking advantage of the multimodal representation and the augmented training dataset. To test the system we used two unrelated labeled datasets, one with CT data and the other one with MRI data. Results show that data enrichment with synthetic modalities improves the segmentation performance. © 2021 IEEE

关键词： Magnetic resonance imaging

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：