检索结果-内蒙古大学图书馆

A microstrip-based sensor for glucose monitoring: towards non-invasive blood glucose detection

学校读者我要写书评

暂无评论

Measurement 2025年 256卷

作者： Guodao Zhang Qiwen Zhang Chaochao Wang Xiaojun Ji Zhengqiu Weng Abdulilah Mohammad Mayet Xinjun Miao Institute of Intelligent Media Computing Hangzhou Dianzi University Hangzhou 310018 China Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing University Jiaxing 314000 China Shangyu Institute of Science and Engineering Co.Ltd. Hangzhou Dianzi University Shaoxing 312300 China Department of Cardiology Wenzhou Central Hospital Wenzhou 325000 China School of Data Science and Artificial Intelligence Wenzhou University of Technology Wenzhou 325000 China Electrical Engineering Department College of Engineering King Khalid University Abha Kingdom of Saudi Arabia Department of Emergency Wenzhou Central Hospital Wenzhou 325000 China

In this study, a microstrip sensor with U-shaped resonators was designed and developed for non-invasive blood glucose measurement. The sensor comprises five U-shaped resonators forming a microstrip circuit, transmitting in the frequency ranges of 2–2.3 GHz and 3.9–4.2 GHz. Glucose solutions with concentrations from 50 mg/dL to 500 mg/dL were prepared and placed in a 3D-printed PLA container for testing. Samples were positioned non-contact on the sensor, and frequency response changes up to 6 GHz were recorded. The sensor exhibited high sensitivity, measuring 1.50 MHz per mg/dL. Due to environmental susceptibilities and the relatively low repeatability of microstrip sensors, each sample was tested five times, yielding a total of 50 measurements. These recorded responses were processed using a multilayer perceptron (MLP) neural network, which predicted glucose concentrations with a mean relative error (MRE%) of less than 2.48 %. This research highlights the development of a highly sensitive, non-invasive glucose sensor integrated with a neural network, offering precise and rapid blood glucose measurements. This system holds promise as a valuable tool for managing diabetes and other blood glucose-related conditions.

关键词：

Predicting the risk of ischemic stroke in patients with atrial fibrillation using heterogeneous drug-protein-disease network-based deep learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lyu, Zhiheng Yang, Jiannan Xu, Zhongzhi Wang, Weilan Cheng, Weibin Tsui, Kwok-Leung Tse, Gary Zhang, Qingpeng School of Data Science City University of Hong Kong Hong Kong Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong School of Public Health Sun Yat-sen University Guangzhou China Centre for Healthy Longevity Yong Loo Lin School of Medicine National University of Singapore Singapore Institute for Healthcare Artificial Intelligence Guangdong Second Provincial General Hospital Guangzhou China Grado Department of Industrial and Systems Engineering Virginia Polytechnic Institute State University United States Tianjin Key Laboratory of Ionic-Molecular Function of Cardiovascular Disease Department of Cardiology Tianjin Institute of Cardiology Second Hospital of Tianjin Medical University Tianjin China Cardiac Electrophysiology Unit Cardiovascular Analytics Group Kowloon Hong Kong School of Nursing and Health Studies Hong Kongetropolitan University Homantin Hong Kong Department of Pharmacology and Pharmacy LKS Faculty of Medicine The University of Hong Kong Hong Kong

Existing risk assessment models for predicting ischemic stroke (IS) in atrial fibrillation (AF) patients overlook the impacts of medications and the intricacy of drug-protein-disease interplays. We aim to develop an interpretable deep learning model, namely the AF-Biological-IS-Path (ABioSPATH), to predict the one-year IS risk in AF patients, and elucidate the underlying molecular mechanisms by integrating drug-protein-disease pathways and real-world clinical data of AF patients. A heterogeneous multilayer drug-protein-disease network was constructed to identify the mechanism of drug action and disease comorbidity propagation pathways. By integrating mechanism pathways and patient characteristics, ABioSPATH generated the IS risk and potential pathways for each patient. The Electronic Health Record (EHR) data of 7859 patients diagnosed with AF between 01/2008-12/2009 from 43 hospitals in Hong Kong were included. ABioSPATH outperformed all baselines across all metrics (AUROC=0.7815;95% CI: 0.7346-0.8283, PPV=0.430, NPV=0.870, sensitivity=0.500, specificity=0.885, average precision=0.409, Brier score=0.195). In the cohort-level analysis, key proteins in the ten most common pathways, including CRP, REN, and PTGS2, were identified. A subsequent individual level analysis revealed the PIK3/Akt and cytokine and chemokine-induced signaling pathways among the top twenty important ones. Potential IS risks tied to less-studied drugs like prochlorperazine maleate were also highlighted. ABioSPATH demonstrated superior predictive performance in estimating IS risk with valuable molecular-level insights for clinical use. The advantage is that only routinely collected data are required, without requiring expensive biomarkers to be tested. Its applications extend beyond IS, indicating potential for risk screening in other diseases, enhancing patient care, and offering insights for drug development. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

Analysis of 5G academic Network based on graph representation learning method

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Xiaoming Xu, Guangquan Yu, Wei Jiao, Pengfei Song, Xiangyu Zhejiang Yuexiu University of Foreign Languages School of International Business Shaoxing China Shaoxing Key Laboratory of Intelligent Monitoring and Prevention of Smart City Shaoxing China School of Big Data School of Big Data Qingdao Huanghai University Qingdao China College of Intelligence and Computing Tianjin University Tianjin China School of IT Faculty of Science Engineering and Built Environment Deakin University GeelongVIC3220 Australia

With the rapid development of 5th Generation Mobile Communication Technology (5G), the diverse forms of collaboration and extensive data in academic social networks constructed by 5G papers make the management and analysis of academic social networks increasingly challenging. Despite the particular success achieved by representation learning in analyzing academic and social networks, most present presentation learning models focus on maintaining the first-order and second-order similarity of nodes. They rarely possess similar structural characteristics of spatial independence in the network. This paper proposes a Low-order Network representation Learning Model (LNLM) based on Non-negative Matrix Factorization (NMF) to solve these problems. The model uses the random walk method to extract low-order features of nodes and map multiple components to a low-dimensional space, effectively maintaining the internal correlation between members. This paper verifies the performance of this model, conducts comparative experiments on four test datasets and four real network datasets through downstream tasks such as multi-label classification, clustering, and link prediction. Comparing eight mainstream network representation learning models shows that the proposed model can significantly improve the detection efficiency and learning methods and effectively extract local and low-order features of the network. © 2021, CC BY.

关键词： Non-negative matrix factorization

Two-DOF Speed Control of Permanent Magnet Synchronous Machine with a novel Parameter Identification Method

学校读者我要写书评

暂无评论

Two-DOF Speed Control of Permanent Magnet Synchronous Machin...

第三十九届中国控制会议

作者： Mingjin Hu Wei Hua Xudong Wu Chengdong Wu Dazhi Wang Zhentao Liu Xiaofang Yuan Wennong Zhang School of Electrical Engineering Southeast University Faculty of Robot Science and Engineering Northeastern University College of Information Science and Engineering Northeastern University Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Electrical and Information Engineering Hunan University

In this paper, a two-degree-of-freedom（2-DOF） speed control scheme for permanent magnet synchronous machines is developed. Both the reference-tracking and disturbance rejection performance are taken into account and only a single parameter related to expected bandwidth determines the dynamics. To improve the performance of speed control, a novel identification method for mechanical parameters is also proposed. The effectiveness of the proposed method is verified by simulations.

关键词： Speed Control two-degree-of-freedom permanent magnet synchronous machine parameter identification

Natidroid: Cross-language android permission specification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Chaoran Chen, Xiao Sun, Ruoxi Xue, Jason Wen, Sheng Ahmed, Muhammad Ejaz Camtepe, Seyit Xiang, Yang School of Software and Electrical Engineering Swinburne University of Technology HawthornVIC3122 Australia Department of Software Systems and Cybersecurity Faculty of IT Monash University ClaytonVIC3800 Australia School of Computer Science University of Adelaide North TerraceSA5005 Australia CSIRO Data61 Australia

The Android system manages access to sensitive APIs by permission enforcement. An application (app) must declare proper permissions before invoking specific Android APIs. However, there is no official documentation providing the complete list of permission-protected APIs and the corresponding permissions to date. Researchers have spent significant efforts extracting such API protection mapping from the Android API framework, which leverages static code analysis to determine if specific permissions are required before accessing an API. Nevertheless, none of them has attempted to analyze the protection mapping in the native library (i.e., code written in C and C++), an essential component of the Android framework that handles communication with the lower-level hardware, such as cameras and sensors. While the protection mapping can be utilized to detect various security vulnerabilities in Android apps, such as permission over-privilege and component hijacking, imprecise mapping will lead to false results in detecting such security vulnerabilities. To fill this gap, we thereby propose to construct the protection mapping involved in the native libraries of the Android framework to present a complete and accurate specification of Android API protection. We develop a prototype system, named NATIDROID, to facilitate the cross-language static analysis to benchmark against two state-of-the-art tools, termed AXPLORER [1] and ARCADE [2]. We evaluate NATIDROID on more than 11,000 Android apps, including system apps from custom Android ROMs and third-party apps from the Google Play. Our NATIDROID can identify up to 464 new API-permission mappings, in contrast to the worst-case results derived from both AXPLORER and ARCADE, where approximately 71% apps have at least one false positive in permission over-privilege and up to 3.6% apps have at least one false negative in component hijacking. Additionally, we identify that 24 components with at least one Native-triggered component hij

关键词： Mobile security

Learning with Group Noise

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Qizhou Yao, Jiangchao Gong, Chen Liu, Tongliang Gong, Mingming Yang, Hongxia Han, Bo Department of Computer Science Hong Kong Baptist University Hong Kong Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of MoE School of Computer Science and Engineering Nanjing University of Science and Technology China Data Analytics and Intelligence Lab Alibaba Group China Department of Computing Hong Kong Polytechnic University Hong Kong Trustworthy Machine Learning Lab School of Computer Science University of Sydney Australia School of Mathematics and Statistics University of Melbourne Australia

Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object (cf. Figure 1) w.r.t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on a range of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Lecture Notes in Networks and Systems

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Networks and systems 2024年 1117 LNNS卷 xiii-xiv页

作者： Roy, Satyabrata Sinwar, Deepak Dey, Nilanjan Perumal, Thinagaran Tavares, João Manuel R. S. Department of Computer Science and Engineering Manipal University Jaipur Rajasthan Jaipur India Department of IoT and Intelligent Systems Manipal University Jaipur Rajasthan Jaipur India Department of Computer Science and Engineering Techno International New Town West Bengal Rajarhat India Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Selangor Serdang Malaysia Departamento de Engenharia Mecânica Faculdade de Engenharia Universidade do Porto Porto Portugal

Utility maximization for multihop wireless networks employing BATS codes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dong, Yanyan Jin, Sheng Chen, Yanzuo Yang, Shenghao Yin, Hoover H.F. The School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Carnegie Mellon University The N-hop Technologies Limited Hong Kong The Institute of Network Coding The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of IoT Intelligent Systems and Wireless Network Technology Shenzhen Research Institute of Big Data Shenzhen China

BATS (BATched Sparse) codes are a class of efficient random linear network coding variation that has been studied for multihop wireless networks mostly in scenarios of a single communication flow. Towards sophisticated multi-flow network communications, we formulate a network utility maximization (NUM) problem that jointly optimizes the BATS code parameters of all the flows and network scheduling. The NUM problem adopts a batch-wise packet loss model that can be obtained from the network local statistics without any constraints on packet loss patterns. Moreover, the NUM problem allows a different number of recoded packets to be transmitted for different batches in a flow, which is called adaptive recoding. Due to both the probably nonconcave objective and the BATS code-related variables, the algorithms developed for the existing flow optimization problems cannot be applied directly to solve our NUM problem. We introduce a two-step algorithm to solve our NUM problem, where the first step solves the problem with nonadaptive recoding schemes, and the second step optimizes adaptive recoding hop-by-hop from upstream to downstream in each flow. We perform various numerical evaluations and simulations to verify the effectiveness and efficiency of the algorithm. © 2021, CC BY-NC-ND.

关键词： Packet loss

Status of the operations of CALET for 7.5 years on the International Space Station 38

学校读者我要写书评

暂无评论

Status of the operations of CALET for 7.5 years on the Inter...

38th International Cosmic Ray Conference, ICRC 2023

作者： Tamura, T. Akaike, Y. Kobayashi, K. Adriani, O. Asano, K. Asaoka, Y. Berti, E. Bigongiari, G. Binns, W.R. Bongi, M. Brogi, P. Bruno, A. Cannady, N. Castellini, G. Checchia, C. Cherry, M.L. Collazuol, G. de Nolfo, G.A. Ebisawa, K. Ficklin, A.W. Fuke, H. Gonzi, S. Guzik, T.G. Hams, T. Hibino, K. Ichimura, M. Ioka, K. Ishizaki, W. Israel, M.H. Kasahara, K. Kataoka, J. Kataoka, R. Katayose, Y. Kato, C. Kawanaka, N. Kawakubo, Y. Kohri, K. Krawczynski, H.S. Krizmanic, J.F. Maestro, P. Marrocchesi, P.S. Messineo, A.M. Mitchell, J.W. Miyake, S. Moiseev, A.A. Mori, M. Mori, N. Motz, H.M. Munakata, K. Nakahira, S. Nishimura, J. Okuno, S. Ormes, J.F. Ozawa, S. Pacini, L. Papini, P. Rauch, B.F. Ricciarini, S.B. Sakai, K. Sakamoto, T. Sasaki, M. Shimizu, Y. Shiomi, A. Spillantini, P. Stolzi, F. Sugita, S. Sulaj, A. Takita, M. Tamura, T. Terasawa, T. Torii, S. Tsunesada, Y. Uchihori, Y. Vannuccini, E. Wefel, J.P. Yamaoka, K. Yanagita, S. Yoshida, A. Yoshida, K. Zober, W.V. Kanagawa University Faculty of Engineering Department of Applied Physics 3-27-1 Rokkakubashi Kanagawa-ku Yokohama Japan Department of Physics University of Florence Via Sansone 1 Sesto Fiorentino50019 Italy INFN Sezione di Firenze Via Sansone 1 Sesto Fiorentino50019 Italy Waseda Research Institute for Science and Engineering Waseda University 17 Kikuicho Shinjuku Tokyo162-0044 Japan JEM Utilization Center Human Spaceflight Technology Directorate Japan Aerospace Exploration Agency 2-1-1 Sengen Ibaraki Tsukuba305-8505 Japan Institute for Cosmic Ray Research The University of Tokyo 5-1-5 Kashiwa-no-Ha Kashiwa Chiba277-8582 Japan Via Madonna del Piano 10 Sesto Fiorentino50019 Italy Department of Physical Sciences Earth and Environment University of Siena via Roma 56 Siena53100 Italy INFN Sezione di Pisa Polo Fibonacci Largo B. Pontecorvo 3 Pisa56127 Italy Department of Physics McDonnell Center for the Space Sciences Washington University One Brookings Drive St. LouisMO63130-4899 United States Heliospheric Physics Laboratory NASA GSFC GreenbeltMD20771 United States Center for Space Sciences and Technology University of Maryland Baltimore County 1000 Hilltop Circle BaltimoreMD21250 United States Astroparticle Physics Laboratory NASA GSFC GreenbeltMD20771 United States Center for Research and Exploration in Space Sciences and Technology NASA GSFC GreenbeltMD20771 United States Department of Physics and Astronomy Louisiana State University 202 Nicholson Hall Baton RougeLA70803 United States Department of Physics and Astronomy University of Padova Via Marzolo 8 Padova35131 Italy INFN Sezione di Padova Via Marzolo 8 Padova35131 Italy Institute of Space and Astronautical Science Japan Aerospace Exploration Agency 3-1-1 Yoshinodai Chuo Kanagawa Sagamihara252-5210 Japan Kanagawa University 3-27-1 Rokkakubashi Kanagawa Kanagawa Yokohama221-8686 Japan Faculty of Science and Technology Graduate School of Science a

The CALorimetric Electron Telescope (CALET) has successfully been carrying out cosmic-ray observations on the International Space Station since October, 2015. CALET directly measures the cosmic-ray electron spectrum in the energy range of 1 GeV to 20 TeV with a 2 % energy resolution above 30 GeV. In addition, the instrument can measure the spectrum of gamma rays well into the TeV range, and the spectra of protons and nuclei up to a PeV. The scientific operations are implemented by taking into account orbital variations of geomagnetic rigidity cutoff. Scheduled command sequences are used to control the CALET observation modes on orbit. The high-energy (>10 GeV) trigger mode is always active for maintaining maximum exposure to high-energy electrons and other high-energy shower events. Also, around the ISS orbit, calibration data acquisition by, for example, recording pedestal and penetrating particle events, a low-energy electron trigger mode operating at high geomagnetic latitude, a low-energy gamma-ray trigger mode operating at low geomagnetic latitude, and an ultra-heavy trigger mode, are scheduled. As of June 30, 2023, the total observation time is 2818 days with a live time fraction of the total time around 86 %. Nearly 1.86 billion events are collected with the high-energy trigger. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmology