检索结果-内蒙古大学图书馆

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Sharma, Nupur Sharma, Deeplata Ezhilarasan, G. Arka Jain University Department of Computer Science & It Jharkhand Jamshedpur India Vivekananda Global University Department of Chemistry Jaipur India School of Engineering and Technology Department of Electrical and Electronics Engineering Karnataka Bangalore India

ISBN: (纸本)9798350370249

Net of factors (IoT)-primarily based cloud networks are composed of more than one distributed computing gadget consisting of sensors, gateways, and edge servers that accumulate, examine, and save massive volumes of information. It is important to make certain that facts are accumulated comfortably and stored in an at-ease manner. This paper discusses diverse protection mechanisms that may be used to secure information collection and control within IoT-primarily-based cloud networks. Firstly, cozy identity management strategies along with identity authentication, token-primarily based authentication, and digital certificates are mentioned to ensure the relaxed acquisition and transmission of records. Secondly, encryption techniques such as secure encryption algorithms, key control strategies, and comfortable channel protocols are mentioned to enable storage and switching of the facts in a comfy way. Eventually, safety rules and great practices, together with identification and getting the right of entry to manipulate, data anonymization, and device logging, are supplied to ensure relaxed facts control in cloud networks. Its miles understood that comfortable facts control within IoT-based totally cloud networks is essential to guarantee confidentiality, integrity, and availability of information. As such, the security techniques discussed in this paper can assist in offering comfortable surroundings for the collection and management of facts in IoT-based totally cloud networks. © 2024 IEEE.

关键词： Collection Iot-Based Management Networks Protocols Strategies Techniques

来源：评论

学校读者我要写书评

暂无评论

Wavelength-multiplexed orbital angular momentum meta-holography

引用

PhotoniX 2024年第1期5卷 276-289页

作者： Jaehyuck Jang Seong-Won Moon Joohoon Kim Jungho Mun Stefan A.Maier Haoran Ren Junsuk Rho Department of Chemical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea Department of Materials Science and Engineering Stanford UniversityStanfordCA 94305USA Department of Mechanical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea School of Electrical and Computer Engineering Purdue UniversityWest LafayetteIN 47907USA School of Physics and Astronomy Monash UniversityMelbourneVIC 3800Australia Department of Physics Imperial College LondonLondon SW72AZUK Department of Electrical Engineering Pohang University of Science and Technology(POSTECH)Pohang 37673Republic of Korea POSCO-POSTECH-RIST Convergence Research Center for Flat Optics and Metaphotonics Pohang 37673Republic of Korea National Institute of Nanomaterials Technology(NINT) Pohang 37673Republic of Korea

The field of high-bandwidth holography has been extensively studied over the past *** angular momentum(OAM)holography,which utilizes vortex beams with theoretically unbounded OAM modes as information carriers,showcases the large capacitance of hologram ***,OAM holography has been limited to a single wavelength,restricting its potential for full-color holography and *** this study,we propose wavelength and OAM multiplexed holography that utilizes the multiple dimensions of light—wavelength and OAM—to provide a multi-color platform that expands the information capacity of holographic storage *** proposed wavelength-OAM multiplexed holography is physically realized by a metasurface,the state-of-the-art optical element consisting of an array of artificially engineered *** silicon meta-atoms,the constituents of the metasurface,are engineered to possess wavelength selectivity by tailoring the dispersion of polarization *** meta-atoms are used to encode the calculated OAM-preserved phase maps based on our *** sampling grid of the phase map is rotated by 45°,which effectively suppress higher-order diffraction,providing a great strategy for achieving large field-of-view(FOV)*** successfully demonstrate six holographic images that are selectively reconstructed under the illumination of light with specific wavelengths(λ=450,635 nm)and topological charges(l=-2,0,2),without high-order *** work suggests that ultrathin meta-holograms can potentially realize ultrahigh-bandwidth full-color holography and holographic video displays with large FOV.

关键词： Metasurface Meta-holography Wavelength-multiplexed holography OAM holography

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation and Pseudo-sequence of fNIRS for Depression Recognition

Data Augmentation and Pseudo-sequence of fNIRS for Depressio...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Shao, Kai Hao, Yixue Hu, Long Zong, Xiaofen Chen, Min Huazhong University of Science and Technology School of Computer Science and Technology Wuhan China Wuhan University Renmin Hospital Department of Psychiatry Wuhan China South China University of Technology Pazhou Laboratory School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Depression is a mental disorder caused by factors such as genetics, life events and social influences, and has become a major public health problem worldwide. Previous studies have demonstrated the potential of functional near-infrared spectroscopy (fNIRS) in the diagnosis of depression. However, in the real medical scene, fNIRS data are difficult to obtain, limited in number and suffer from class imbalance. To overcome these problems, in this paper, we propose a novel model for depression identification based on data augmentation and pseudo-sequence of fNIRS. Specifically, the data augmentation using the time masking and warping method generates richer data. Then, a stimulation task-driven data pseudo-sequence method is designed to map the sequence data into pseudo-sequence activation images. Finally, a depression recognition model is established based on the class imbalance loss function. Experiments show that the precision of our depression recognition model reaches 0.94. This scheme transforms fNIRS data into image sequences, which provides a new solution idea for subsequent research. © 2023 IEEE.

关键词： Data Augmentation Depression Recognition fNIRS Pseudo-sequence

来源：评论

学校读者我要写书评

暂无评论

THE EFFECT OF INTRINSIC DATASET PROPERTIES ON GENERALIZATION: UNRAVELING LEARNING DIFFERENCES BETWEEN NATURAL AND MEDICAL IMAGES 12

THE EFFECT OF INTRINSIC DATASET PROPERTIES ON GENERALIZATION...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Konz, Nicholas Mazurowski, Maciej A. Department of Electrical and Computer Engineering Duke University NC United States Department of Radiology Duke University NC United States Department of Computer Science Duke University NC United States Department of Biostatistics & Bioinformatics Duke University NC United States

This paper investigates discrepancies in how neural networks learn from different imaging domains, which are commonly overlooked when adopting computer vision techniques from the domain of natural images to other specialized domains such as medical images. Recent works have found that the generalization error of a trained network typically increases with the intrinsic dimension (ddata) of its training set. Yet, the steepness of this relationship varies significantly between medical (radiological) and natural imaging domains, with no existing theoretical explanation. We address this gap in knowledge by establishing and empirically validating a generalization scaling law with respect to ddata, and propose that the substantial scaling discrepancy between the two considered domains may be at least partially attributed to the higher intrinsic "label sharpness" (KF) of medical imaging datasets, a metric which we propose. Next, we demonstrate an additional benefit of measuring the label sharpness of a training set: it is negatively correlated with the trained model's adversarial robustness, which notably leads to models for medical images having a substantially higher vulnerability to adversarial attack. Finally, we extend our ddata formalism to the related metric of learned representation intrinsic dimension (drepr), derive a generalization scaling law with respect to drepr, and show that ddata serves as an upper bound for drepr. Our theoretical results are supported by thorough experiments with six models and eleven natural and medical imaging datasets over a range of training set sizes. Our findings offer insights into the influence of intrinsic dataset properties on generalization, representation learning, and robustness in deep neural networks. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

SyREC: A Symbolic-Regression-Based Ensemble Combiner 36

SyREC: A Symbolic-Regression-Based Ensemble Combiner

引用

36th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2024

作者： Fong, Kei Sen Motani, Mehul Department of Electrical and Computer Engineering Singapore College of Design and Engineering Singapore Institute of Data Science Singapore N.1 Institute for Health Singapore National University of Singapore Singapore

ISBN: (纸本)9798331527235

Symbolic Regression (SR) is the task of finding a concise white-box mathematical expression that fulfills a given machine learning (ML) objective. In this work, we introduce the first-of-its-kind SR-based ensemble combiner (SyREC) for ML which utilizes the quasi-arithmetic mean (parameterized by a function f) as an ensemble combiner and discovers f via SR. Our Sy REC demonstrates advantages over existing ensemble combiners, i.e., averaging methods and meta-learners. Compared to averaging methods, Sy REC allows for increased combiner complexity via exploring a large function class and provides a learning process to tune the ensemble combiner to the specific dataset. Compared to meta-learners, SyREC preserves important ensemble properties, like idempotency, monotonicity and boundedness, which produce predictions more consistent with the base models. We note SyREC produces a white-box ensemble combiner that lies in the intersection of both categories of existing combiners, addressing the weaknesses while capturing the strengths of each category. To evaluate Sy REC, we present experiments on 16 open-source PMLB datasets and commonly used base models, including a large variety of experiments and analyses across different settings: (i) regression and classification tasks, (ii) equally weighted combiners and custom-weighted combiners, (iii) homogeneous and heterogeneous ensembles, (iv) sequential and parallel ensembles. We find that in all these settings, SyREC shows consistent improvement over existing ensembling approaches. This indicates that SyREC is a robust ensemble combiner, which produces explainable and consistent ensemble predictions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DUAL-STEP OPTIMIZATION FOR BINARY SEQUENCES WITH HIGH MERIT FACTORS

arXiv

引用

arXiv 2024年

作者： Pšeničnik, Blaž Mlinarič, Rene Brest, Janez Bošković, Borko Computer Architecture and Languages Laboratory Faculty of Electrical Engineering and Computer Science University of Maribor Slovenia

MSC Codes 68T20The problem of finding aperiodic low auto-correlation binary sequences (LABS) presents a significant computational challenge, particularly as the sequence length increases. Such sequences have important applications in communication engineering, physics, chemistry, and cryptography. This paper introduces a novel dual-step algorithm for long binary sequences with high merit factors. The first step employs a parallel algorithm utilizing skew-symmetry and restriction classes to generate sequence candidates with merit factors above a predefined threshold. The second step uses a priority queue algorithm to refine these candidates further, searching the entire search space unrestrictedly. By combining GPU-based parallel computing and dual-step optimization, our approach has successfully identified new best-known binary sequences for all lengths ranging from 450 to 527, with the exception of length 518, where the previous best-known value was matched with a different sequence. This hybrid method significantly outperforms traditional exhaustive and stochastic search methods, offering an efficient solution for finding long sequences with good merit factors. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Carrier Transfer From C-Plane to Semipolar-Plane Regions in a Red-Emitting InGaN/GaN Heterostructure

Carrier Transfer From C-Plane to Semipolar-Plane Regions in ...

引用

CLEO: science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Malhotra, Yakshita Shen, Yifan Wu, Yuanpeng Hanish, Josey Guo, Yifu Xiao, Yixin Sun, Kai Norris, Theodore Mi, Zetian Department of Electrical Engineering and Computer Science University of Michigan 1301 Beal Avenue Ann ArborMI48109 United States Department of Material Science and Engineering University of Michigan 2300 Hayward Street Ann ArborMI48109 United States

Temperature and power dependent time-resolved photoluminescence measurements are performed on a novel ultra-stable red-emitting InGaN/GaN heterostructure. PL dynamics at two distinct wavelengths indicate a lateral car... 详细信息

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Automatic Skull Shape Completion of Defective Skulls Using Transformers for Cranial Implant Design

引用

Procedia computer science 2024年 235卷 3305-3314页

作者： Resmi S RimjhimPadam Singh Kannappan Palaniappan Department. of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita VishwaVidyapeetham India Dept. of Electrical Engineering and Computer Science University of Missouri Missouri USA

Cranioplasty is a surgical method that restores the aesthetic and protecting function of a damaged skull by implanting material into the damaged *** and accurate design of patient specific cranial implants is very much required in the process of *** time consumption for designing and manufacturing of patient specific cranial implant has become an obstruction for cranioplasty procedures. Hence, a fully automatic and fast design of cranial implant becomes very important. The cranial implant design processmainly comprises of two steps. The former step concentrates on the automatic skull shape completion of defective skulls to fill the gaps and the cracks created in the skull. While the second step computes the difference between defective input and the completed skull for generating the implant. Currently computer aided design is used for the skull shape completion task which is a time consuming process. The application of deep learning techniques may result to faster and accurate skull shape completionwhich can be used for the design of patient specific cranial implants. This work proposes a novel approach combining 3D U-Net with Transformers for the automatic skull shape completion *** are using a vision transformer in the encoder section of the 3D U-Net architecture to consider the volumetric skull reconstruction as sequence- to-sequence prediction problem and to efficaciously grasp the global contextual information. The work also compares its performance with the famous variants of 3D U-Net deep network model namely, 3D U-Net and 3D U-Net with attention. From the values resulted for the dice coefficient metric it is clear that the proposed 3D U-Net with transformer approach performs better than the other two models on test images.

关键词： Cranioplasty 3DU-Net 3DU-Net with Attention 3DU-Net with Transformer Dice coefficient

来源：评论

学校读者我要写书评

暂无评论

Building Intelligent Automated Real-Time Data Analysis Systems Through Machine Learning 2

Building Intelligent Automated Real-Time Data Analysis Syste...

引用

2nd IEEE International Conference on Futuristic Technologies, INCOFT 2023

作者： Rathee, Sahil Vigenesh, M. Priydarshini, Kala Vijaykumar, R. Singh, Shweta Seth, Jyoti Department of Computer Science and Information Technology Karnataka Bangalore India Karpagam Academy of Higher Education Department of Computer Science Engineering Coimbatore641021 India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9798350308846

This paper explores the capacity of using gadget-get-to-know-based facts evaluation structures to build intelligent, automated real-time statistics analysis systems. It examines the demanding situations present points evaluation systems pose and proposes a unique remedy. The proposed method leverages supervised and unsupervised devices and learning strategies to enable deep information on complex datasets. It then makes use of predictive skills to make clever selections with the aid of comparing input facts about databases. ultimately, the paper describes a case to demonstrate the effectiveness of this proposed machine and outlines implications for comparable implementations in the enterprise. This work is precious for information scientists and commercial enterprise decision-makers, as it outlines an ability to deploy reliable and accurate records analysis structures. © 2023 IEEE.

关键词： Accurate Deploying Enterprise Structures

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection in 5G Cellular Network Using Machine Learning

引用

computer Systems science & engineering 2023年第11期47卷 2439-2453页

作者： Ishtiaque Mahmood Tahir Alyas Sagheer Abbas Tariq Shahzad Qaiser Abbas Khmaies Ouahada Knowledge Unit of Systems and Technology UMT Sialkot CampusSialkot51040Pakistan Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan Faculty of Computer Science National College of Business Administration and EconomicsLahore54660Pakistan Department of Electrical and Computer Engineering COMSATS University IslamabadSahiwal CampusSahiwal57000Pakistan Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351Saudi Arabia Department of Computer Science&IT University of SargodhaSargodha40100Pakistan Department of Electrical and Electronic Engineering Science University of JohannesburgP.O Box 524Auckland ParkJohannesburg2006South Africa

Attacks on fully integrated servers,apps,and communication networks via the Internet of Things(IoT)are growing *** devices’effectiveness harms end users,increases cyber threats and identity theft,raises costs,and negatively impacts income as problems brought on by the Internet of Things network go unnoticed for extended *** on Internet of Things interfaces must be closely monitored in real time for effective safety and *** the 1,2,3,and 4G cellular networks,the 5th generation wireless 5G network is indeed the great invasion of mankind and is known as the global advancement of cellular *** to this day,experts are working on the evolution’s sixth generation(6G).It offers amazing capabilities for connecting everything,including gadgets and machines,with wavelengths ranging from 1 to 10 mm and frequencies ranging from 300 MHz to 3 *** gives you the most recent *** countries have already established this technology within their *** is the most crucial aspect of using a 5G *** of the absence of study and network deployment,new technology first introduces new gaps for attackers and *** Protocol(IP)attacks and intrusion will become more prevalent in this *** efficient approach to detect intrusion in the 5G network using a Machine Learning algorithm will be provided in this *** research will highlight the high accuracy rate by validating it for unidentified and suspicious circumstances in the 5G network,such as intruder hackers/*** applying different machine learning algorithms,obtained the best result on Linear Regression Algorithm’s implementation on the dataset results in 92.12%on test data and 92.13%on train data with 92%precision.

关键词： Intrusion detection system machine learning confidentiality integrity availability

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：