检索结果-内蒙古大学图书馆

Novel nonlinear fractional order Parkinson's disease model for brain electrical activity rhythms: Intelligent adaptive Bayesian networks

引用

Chaos, Solitons and Fractals 2024年 180卷

作者： Mukhtar, Roshana Chang, Chuan-Yu Raja, Muhammad Asif Zahoor Chaudhary, Naveed Ishtiaq Shu, Chi-Min Graduate School of Engineering Science and Technology National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Safety Health and Environmental Engineering National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

In this study, a novel investigation in developing intelligent adaptive Bayesian networks (IABN) is carried out to solve the fractional order Parkinson's disease model (FOPDM) represented with a system of three fractional differential equations reflecting the brain's electrical activity rhythms at different cerebral cortex positions. The IABN are developed by using the competency of the multi-layer architecture of neural networks with backpropagation through Bayesian regularization optimization scheme. The reference dataset for IABN is created through Grunwald-Letnikov fractional derivative-based numerical solver for FOPDM in case of varying sensor locations on the cerebral cortex, as well as, considering different fractional orders in FOPDM. The proposed IABN is applied to the created datasets arbitrarily partitioned into training and testing sets by optimizing the fitness criterion based on mean square error (MSE) metric. The detailed analyses of the proposed IABN through extensive simulations and comparison with the reference numerical solutions of FOPDM in terms of MSE training/testing plots, absolute error, training/testing regression plots, and error histogram results, endorse the worth of the proposed intelligent scheme for different fractional orders. © 2024 Elsevier Ltd

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Electronic Health Record with Consortium Blockchain

Privacy Preserving Electronic Health Record with Consortium ...

引用

International Conference on information Technology, information Systems and Electrical engineering (ICITISEE)

作者： Adri Gautama Adian Fatchur Rochim Luhur Bayuaji Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia Department of Computer Engineering Diponegoro University Semarang Indonesia Computer Science Budi Luhur University Jakarta Indonesia

Every patient has health record, it was written as statement of patient's conditions, treatments, and medications, and nowadays it is become digitalized, it can be copied and shared easily, but the nature of EHR is private, not for public, private between patients and healthcare provider. Privacy preserving can be done by implementing Blockchain network for storing EHR, only authorized users or nodes can access and write data to the network. New block in blockchain created as per consensus among nodes, every node can join a blockchain network if it is public, to meet a consensus required resources intensive cryptographic challenge, in private blockchain, only selected can join and involved in the network or specific transaction. In healthcare, data privacy is the main concerned, need a secure, scalable, and efficient blockchain hence implementing consortium blockchain is perfect match for EHR where multiple healthcare provider can operate in a single platform to conduct transaction or sharing EHR among members. This study analyzes 15 articles derived from IEEE Explore, science Direct and Scopus by implementing screening with keyword Consortium Blockchain and EHR and proposing new blockchain model accommodating solution for challenges on access, storage, sharing, privacy, and performance.

关键词： Electrical engineering Data privacy Privacy Analytical models Monte Carlo methods Medical services Blockchains

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with Greedy Layer-Wise Compound Scaling for Temperature and Humidity Prediction in Solar Dryer Dome

SSRN

引用

SSRN 2022年

作者： Cenggoro, Tjeng Wawan Elwirehardja, Gregorius Natanael Dominic, Nicholas Setiawan, Karli Eka Rahutomo, Reza Djuana, Endang Gunawan, Fergyanto E. Budiman, Arief S. Romeli, Sugiarto Pardamean, Bens Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Electrical Engineering Department Faculty of Industrial Technology Universitas Trisakti Jakarta11440 Indonesia Industrial Engineering Department BINUS Graduate Program Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia Department of Manufacturing and Mechanical Engineering and Technology Oregon Institute of Technology Klamath FallsOR97601 United States PT. Impack Pratama Industri Jakarta Indonesia

Drying has been an eco-friendly and cost-efficient method to reduce post-harvest losses of agricultural crops. In various countries, the technique has been widely utilized in the form of Solar Dryer Dome (SDD) buildings. Accurate indoor microclimate forecasting is very important to implement smart control systems in SDDs that can maintain the ideal conditions, as the availability of solar energy is limited only at daytimes and the temperature may drop significantly during nighttimes in remote areas. The microclimate variables that play an important role in maintaining ideal environmental conditions include temperature and relative humidity. © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Reducing Effective System Dimensionality with Long-Range Collective Dipole-Dipole Interactions

引用

Physical Review Letters 2024年第17期132卷 173803-173803页

作者： Ashwin K. Boddeti Yi Wang Xitlali G. Juarez Alexandra Boltasseva Teri W. Odom Vladimir Shalaev Hadiseh Alaeian Zubin Jacob Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette Indiana 47907 USA Birck Nanotechnology Center Purdue University West Lafayette Indiana 47907 USA Graduate Program in Applied Physics Northwestern University Evanston Illinois 60208 USA Department of Materials Science and Engineering Northwestern University Evanston Illinois 60208 USA Department of Chemistry Northwestern University Evanston Illinois 60208 USA School of Physics and Astronomy Purdue University West Lafayette Indiana 47907 USA

Dimensionality plays a crucial role in long-range dipole-dipole interactions (DDIs). We demonstrate that a resonant nanophotonic structure modifies the apparent dimensionality in an interacting ensemble of emitters, as revealed by population decay dynamics. Our measurements on a dense ensemble of interacting quantum emitters in a resonant nanophotonic structure with long-range DDIs reveal an effective dimensionality reduction to d¯=2.20(12), despite the emitters being distributed in 3D. This contrasts with the homogeneous environment, where the apparent dimension is d¯=3.00. Our work presents a promising avenue to manipulate dimensionality in an ensemble of interacting emitters.

关键词： Light-matter interaction Long-range interactions Metamaterials Optics & lasers Photonics Plasmonics Quantum optics

来源：评论

学校读者我要写书评

暂无评论

Sufficient Algorithm for Inclusion of Pattern Caterpillar in Text Tree

Sufficient Algorithm for Inclusion of Pattern Caterpillar in...

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Daisuke Abe Tomoya Miyazaki Kouichi Hirata Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Kawazu 680-4 Iizuka Japan Mitsubishi Electric Information Systems Corporation Department of Artificial Intelligence Kyushu Institute of Technology Kawazu 680-4 Iizuka Japan

In this paper, as the restriction of a rooted labeled unordered tree (tree, for short), we introduce a rooted labeled k-caterpillar(k-caterpillar, for short) that is a tree T whose number of the leaves in the tree obtained by deleting all of the leaves in T is at most k. Then, we design the sufficient algorithm to return “yes” implying that a pattern caterpillar P is included in a text tree T as a $k -$caterpillar. It runs in $O(k(h+H)\sigma)$ time, where h is the height of $P, H$ is the height of T, and $\sigma$ is the number of labels occurring in P and T. Finally, we give experimental results for the algorithm by using real data for caterpillars and trees as k - caterpillars.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning

Out-of-Distributed Semantic Pruning for Robust Semi-Supervis...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yu Wang Pengchong Qiao Chang Liu Guoli Song Xiawu Zheng Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science(AI4S)-Preferred Program Peking University Shenzhen Graduate School China Peng Cheng Laboratory Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China

Recent advances in robust semi-supervised learning (SSL) typically filter out-of-distribution (OOD) information at the sample level. We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field. In this paper, we take an initial step to explore and propose a unified framework termed OOD Semantic Pruning (OSP), which aims at pruning OOD semantics out from in-distribution (ID) features. Specifically, (i) we propose an aliasing OOD matching module to pair each ID sample with an OOD sample with semantic overlap. (ii) We design a soft orthogonality regularization, which first transforms each ID feature by suppressing its semantic component that is collinear with paired OOD sample. It then forces the predictions before and after soft orthogonality decomposition to be consistent. Being practically simple, our method shows a strong performance in OOD detection and ID classification on challenging benchmarks. In particular, OSP surpasses the previous state-of-the-art by 13.7% on accuracy for ID classification and 5.9% on AUROC for OOD detection on TinyImageNet dataset. The source codes are publicly available at https://***/rain305f/OSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational Approach for Determining the Base Frequency for The F0 Contour Generation Model

SSRN

引用

SSRN 2023年

作者： Arimoto, Yoshiko Horiuchi, Yasuo Ohno, Sumio Faculty of Information and Computer Science Chiba Institute of Technology 2-17-1 Tsudanuma Chiba Narashino275-0016 Japan Graduate School of Engineering Chiba University 1-33 Yayoi Inage Chiba Chiba263-8522 Japan School of Computer Science Tokyo University of Technology 1404-1 Katakura Hachioji Tokyo192-0982 Japan

A reliable method of determining the base frequency (Fb) for utterances of various speaking styles is critical to enabling stable command labeling in the Fujisaki model. To achieve stable command labeling for various speaking styles, a linear fitted model was developed using the ten percentile F0 value of each utterance from three corpora of various speaking style (read, acted, and spontaneous) as the independent variable to estimate a consistent Fb for each utterance. To assess the robustness of the model for unknown utterances, the model was applied to test data which includes both open and corpus-open data not used for the model development, and the difference between the estimated Fb and the trained labelers’ annotated Fb was calculated. As a result, the obtained estimation model was well-fitted to the manually labelled Fbs by exhibiting a small root mean squared error (RMSE) at 0.096 and a high coefficient of determination (R2 ) at 0.89 for the closed dataset. Moreover, the model also exhibited a small RMSE at 0.091 and a high R2 at 0.92 for the corpus-open dataset. The results revealed that the proposed model can reliably estimate the Fb of utterances with various speaking style. © 2023, The Authors. All rights reserved.

关键词： Open Data

来源：评论

学校读者我要写书评

暂无评论

Zero-Trust Empowered Decentralized Security Defense against Poisoning Attacks in SL-IoT: Joint Distance-Accuracy Detection Approach

Zero-Trust Empowered Decentralized Security Defense against ...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Rongxuan Song Jun Wu Qianqian Pan Muhammad Imran Niddal Naser Rebet Jones Christos Verikoukis Graduate School of Information Production and Systems Waseda University Japan Department of Computing and Mathematics Manchester Metropolitan University UK Institute of Innovation Science and Sustainsbility Federation University Australia College of Engineering Alfaisal University Riyadh Saudi Arabia Department of Computer Science Capitol Technology University USA University of Patras and Iquadrat Information Greece

Swarm learning (SL) exploits the blockchain to realize a federated and decentralized learning, which is very suitable for internet of things (IoT). Different from FL using central server to update global parameter, SL using edge node (header) to do that. However, poisoning attack is also an unresolved problem to SL. Because if header is malicious, it can pollute global parameter more easily than edge nodes. Moreover, there are following important limitations in existing defense schemes for FL, which cannot be used in SL directly. First, existing defense schemes focus on building a whitelist, which obstructs the decentralization because it can just provide decentralization in honest nodes instead of all of nodes. Second, existing schemes just consider poisoning attacks from edge nodes, they cannot defend attacks from header. Third, most existing schemes will let server execute the defense algorithm, but in SL, malicious header can return wrong defense results to deceive managers. To address above challenges, in this paper, we propose a protection system that leverages the concept of zero-trust architecture for SL, which achieves continuous risk calculation, analysis of learning behavior and abnormal parameter detection based on Manhattan distance and accuracy difference of parameters. We also evaluate the performance in the presence of random and customized malicious edge nodes. Experimental results demonstrate that our scheme can achieve higher accuracy than the other existing schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Propagable Backdoors over Blockchain-based Federated Learning via Sample-Specific Eclipse

Propagable Backdoors over Blockchain-based Federated Learnin...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Zheng Yang Gaolei Li Jun Wu Wu Yang School of Electronic Information and Electrical Engineeering Shanghai Jiao Tong University Shanghai China Graduate School of Information Production and Systems Waseda University Fukuoka Japan College of Computer Science and Technology Harbin Engineering University Harbin China

ISBN: (纸本)9781665435413

Blockchain-based federated learning, also being named as swarm learning, is perceived to have great potential to support decentralized and privacy-enhancing big data processing. However, numerous serious vulnerabilities found on blockchain and federated learning enforce us to concern about the security of swarm learning. Some seemingly-unrelated combinations of known vulnerabilities may derive highly-converted and unknown threats to swarm learning. In this paper, we first investigate the security threats of the swarm learning framework. And then, leveraging backdoor attacks and eclipse attacks, a novel hybrid vulnerability that can furtively propagate backdoors among swarm learning nodes is identified. To speed up the backdoor propagation and reduce attack costs, a sample-specific eclipse (SSE) strategy that can select the swarm network node with a high data contribution rate as the attack object is also proposed. Finally, by adjusting the trigger size, the data distribution rate, and the poisoning ratio, we conduct various comparison experiments to validate the feasibility of the proposed methods. To the best of our knowledge, this is the first article to study the epidemicity of backdoors in swarm learning.

关键词： Toxicology Costs Federated learning Big Data Blockchains Security Global communication

来源：评论

学校读者我要写书评

暂无评论

Multiplexed Implantable 'Barcode' Platform for Continuous Oxygen and Glucose Monitoring

引用

IEEE Sensors Journal 2024年

作者： Chen, Zheyuan Falohun, Tokunbo Kameoka, Jun Mcshane, Michael J. Texas A&M University Department of Biomedical Engineering College StationTX77843 United States Texas A&M University Department of Electrical and Computer Engineering College StationTX77843 United States Waseda University Graduate School of Information Production and Systems Fukuoka808-0135 Japan Texas A&M University Department of Biomedical Engineering Department of Materials Science and Engineering College StationTX77843 United States

Multianalyte biosensors have been of interest in various applications, especially in healthcare areas that target a broad range of biomarkers related to various pathological diseases. However, successful examples of such sensors generally utilize electrochemical transducers, a fact which limits their use as implants due to the presence of interferents in vivo, the difficulty of transdermal signal transduction, and the difficulty of miniaturizing the electronics into an integrated biocompatible form factor suitable for implantation. In this study, we demonstrate an attractive alternative for multiplexed sensing platform based on oxidoreductase enzymes coupled with optically distinct oxygen-sensitive metalloporphyrin phosphors which are immobilized within nanofilm-coated alginate microparticles;these are embedded in discrete compartments of a single miniature biocompatible hydrogel to achieve a 'barcode' sensor device. Continuous multiplex oxygen and glucose monitoring were demonstrated through the measurement of phosphorescence lifetime changes of the metalloporphyrin phosphors when exposed to different environmental conditions. The phosphorescence lifetime exhibited a negative correlation with increases in oxygen concentration for all compartments. In contrast, the oxygen-responsive assays maintained a constant phosphorescence lifetime and the glucose-responsive assays showed increased phosphorescence lifetime when the glucose concentration increased from 0 to 400 mg/dL. This observation confirmed the desired behavior without any apparent crosstalk between the adjacent oxygen- and glucose-responsive compartments. Furthermore, the sensors demonstrated high stability during repeated glucose challenges over 10 cycles. These findings suggest that the hydrogel barcode optical sensing platform has potential for use in various situations requiring multiplexed chemical analysis such as in continuous medical monitoring. © 2001-2012 IEEE.

关键词： Phosphorescence

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：