检索结果-南通市图书馆

FSCIL-EACA: Few-Shot Class-Incremental Learning network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

引用

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education department information network Engineering Research center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Age of information Based User Scheduling and Data Assignment in Multi-User Mobile Edge Computing networks:An Online Algorithm

引用

China Communications 2024年第5期21卷 153-165页

作者： Ge Yiyang Xiong Ke Dong Rui Lu Yang Fan Pingyi Qu Gang School of Computer and information Technology Beijing Jiaotong UniversityBeijing 100044China Engineering Research center of network management Technology for High Speed Railway of Ministry of Education Beijing 100044China Beijing Engineering Research center of High-speed Railway Broadband Mobile Communications Beijing 100044China department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National Research center for information Science and Technology Tsinghua UniversityBeijing 100084China department of Electrical and Computer Engineering College ParkMarylandUSA

This paper investigates the age of information(AoI)-based multi-user mobile edge computing(MEC)network with partial offloading mode.The weighted sum AoI(WSA)is first analyzed and derived,and then a WSA minimization problem is formulated by jointly optimizing the user scheduling and data assignment.Due to the non-analytic expression of the WSA w.***.t.the optimization variables and the unknowability of future network information,the problem cannot be solved with known solution methods.Therefore,an online Joint Partial Offloading and User Scheduling Optimization(JPOUSO)algorithm is proposed by transforming the original problem into a single-slot data assignment subproblem and a single-slot user scheduling sub-problem and solving the two sub-problems separately.We analyze the computational complexity of the presented JPO-USO algorithm,which is of O(N),with N being the number of users.Simulation results show that the proposed JPO-USO algorithm is able to achieve better AoI performance compared with various baseline methods.It is shown that both the user’s data assignment and the user’s AoI should be jointly taken into account to decrease the system WSA when scheduling users.

关键词： age of information(aoi) mobile edge computing(mec) user scheduling

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Protein Arginine Methyltransferase 1 Ablation in Motor Neurons Causes Mitochondrial Dysfunction Leading to Age-related Motor Neuron Degeneration with Muscle Loss

引用

Research 2024年第1期2023卷 637-649页

作者： Hyun-Kyung So Hyebeen Kim Jinwoo Lee Chang-Lim You Chae-Eun Yun Hyeon-Ju Jeong Eun-Ju Jin Yunju Jo Dongryeol Ryu Gyu-Un Bae Jong-Sun Kang department of Molecular Cell Biology Sungkyunkwan University School of MedicineSuwonKorea Single Cell network Research center Sungkyunkwan University School of MedicineSuwonKorea Research Institute of Aging-Related Diseases AniMusCureInc.SuwonKorea Drug information Research Institute Muscle Physiome Research CenterCollege of PharmacySookmyung Women’s UniversitySeoulKorea

Neuromuscular dysfunction is tightly associated with muscle wasting that occurs with age or due to degenerative diseases.However,the molecular mechanisms underlying neuromuscular dysfunction are currently unclear.Recent studies have proposed important roles of Protein arginine methyltransferase 1(Prmt1)in muscle stem cell function and muscle maintenance.In the current study,we set out to determine the role of Prmt1 in neuromuscular function by generating mice with motor neuron-specific ablation of Prmt1(mnKO)using Hb9-Cre.mnKO exhibited age-related motor neuron degeneration and neuromuscular dysfunction leading to premature muscle loss and lethality.Prmt1 deficiency also impaired motor function recovery and muscle reinnervation after sciatic nerve injury.The transcriptome analysis of aged mnKO lumbar spinal cords revealed alterations in genes related to inflammation,cell death,oxidative stress,and mitochondria.Consistently,mnKO lumbar spinal cords of sciatic nerve injury model or aged mice exhibited elevated cellular stress response in motor neurons.Furthermore,Prmt1 inhibition in motor neurons elicited mitochondrial dysfunction.Our findings demonstrate that Prmt1 ablation in motor neurons causes agerelated motor neuron degeneration attributing to muscle loss.Thus,Prmt1 is a potential target for the prevention or intervention of sarcopenia and neuromuscular dysfunction related to aging.

关键词： degeneration impaired prevention

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Community-Level Practice Checklists for Health Protection During Cold Spells in China

引用

China CDC weekly 2024年第5期6卷 83-87页

作者： Jing Shang Mengzhen Zhao Zhao Liu Xiya Zhang Shiguang Miao Ishaq D.Sulaymon Wenjia Cai Institute of Urban Meteorology CMABeijingChina School of management and Economics Beijing Institute of TechnologyBeijingChina School of Airport Economics and management Beijing Institute of Economics and ManagementBeijingChina department of Earth System Science Tsinghua UniversityBeijingChina Sand and Dust Storm Warning Regional center National Center for MeteorologyJeddahSaudi Arabia Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment TechnologySchool of Environmental Science and EngineeringNanjing University of Information Science and TechnologyNanjing CityJiangsu ProvinceChina

Communities play a crucial role in protecting the health of vulnerable populations such as the elderly,low-income groups,and high-risk individuals during cold spells.However,current strategies for responding to cold spells primarily consist of programmatic policies that lack practicality,specificity,and detailed implementation guidelines for community workers.Therefore,this study aims to identify and analyze the challenges faced by communities in responding to cold spells,review international experiences,and develop a set of practical checklists for community-level health protection.These checklists will assist community workers and volunteers in effectively preparing for,responding to,and recovering from cold spells.

关键词： preparing income primarily

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine

引用

Chinese Journal of Integrative Medicine 2024年第3期30卷 267-276页

作者： WANG Xin-yu YANG Tao GAO Xiao-yuan HU Kong-fa School of Artificial Intelligence and information Technology Nanjing University of Chinese MedicineNanjing210023China School of information management Nanjing UniversityNanjing210023China Jiangsu Collaborative Innovation center of Traditional Chinese Medicine in Prevention and Treatment of Tumor Nanjing210023China Jiangsu Province Engineering Research center of TCM Intelligence Health Service Nanjing210023China

Chinese medicine(CM)diagnosis intellectualization is one of the hotspots in the research of CM modernization.The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues,however,it is difficult to solve the problems such as excessive or similar categories.With the development of natural language processing techniques,text generation technique has become increasingly mature.In this study,we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues.The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory(BILSTM)with Transformer as the backbone network.Meanwhile,the CM diagnosis generation model Knowledge Graph Enhanced Transformer(KGET)was established by introducing the knowledge in medical field to enhance the inferential capability.The KGET model was established based on 566 CM case texts,and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence(LSTM-seq2seq),Bidirectional and Auto-Regression Transformer(BART),and Chinese Pre-trained Unbalanced Transformer(CPT),so as to analyze the model manifestations.Finally,the ablation experiments were performed to explore the influence of the optimized part on the KGET model.The results of Bilingual Evaluation Understudy(BLEU),Recall-Oriented Understudy for Gisting Evaluation 1(ROUGE1),ROUGE2 and Edit distance of KGET model were 45.85,73.93,54.59 and 7.12,respectively in this study.Compared with LSTM-seq2seq,BART and CPT models,the KGET model was higher in BLEU,ROUGE1 and ROUGE2 by 6.00–17.09,1.65–9.39 and 0.51–17.62,respectively,and lower in Edit distance by 0.47–3.21.The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance.Additionally,the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the p

关键词： Chinese medicine diagnosis knowledge graph enhanced transformer text generation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Pregnancy and the disease recurrence of patients previously treated for differentiated thyroid cancer:A systematic review and meta analysis

引用

Chinese Medical Journal 2024年第5期137卷 547-555页

作者： Rui Shan Xin Li Ming Tao Wucai Xiao Jing Chen Fang Mei Shibing Song Bangkai Sun Chunhui Yuan Zheng Liu department of Maternal and Child Health School of Public HealthPeking UniversityBeijing 100191China department of General Surgery Peking University Third HospitalBeijing 100191China department of Pathology Peking University Third HospitalSchool of Basic Medical SciencesPeking University Health Science CenterBeijing 100191China information management and Big Data center Peking University Third HospitalBeijing 100191China

Background:Differentiated thyroid cancer(DTC)is commonly diagnosed in women of child-bearing age,but whether pregnancy influences the prognosis of DTC remains controversial.This study aimed to summarize existing evidence regarding the association of pregnancy with recurrence risk in patients previously treated for DTC.Methods:We searched PubMed,Embase,Web of Science,Cochrane,and Scopus based on the prespecified protocol registered at PROSPERO(CRD42022367896).After study selection,two researchers independently extracted data from the included studies.For quantitative data synthesis,we used random-effects meta-analysis models to pool the proportion of recurrence(for pregnant women only)and odds ratio(OR;comparing the risk of recurrence between the pregnancy group and the nonpregnancy group),respectively.Then we conducted subgroup analyses to explore whether risk of recurrence differed by response to therapy status or duration of follow-up time.We also assessed quality of the included studies.Results:A total of ten studies were included.The sample size ranged from 8 to 235,with participants’age at pregnancy or delivery ranging from 28 to 35 years.The follow-up time varied from 0.1 to 36.0 years.The pooled proportion of recurrence in all pregnant patients was 0.13(95%confidence intervals[CI]:0.06-0.25;I^(2):0.58).Among six included studies reporting response to therapy status before pregnancy,we observed a trend for increasingly higher risk of recurrence from excellent,indeterminate,and biochemically incomplete to structurally incomplete response to therapy(P trend0.05)or the OR of recurrence in studies with a comparison group(P>0.05).Two included studies that focused on patients with distant metastasis

关键词： Thyroid cancer Pregnancy Recurrence Women Systematic review Meta-analysis

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Resource Allocation for Channel Estimation in Reconfigurable Intelligent Surface-Aided Multi-Cell networks

引用

Journal of Communications and information networks 2024年第1期9卷 64-79页

作者： Yining Xu Sheng Zhou department of Electronic Engineering Beijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China

Reconfigurable intelligent surface(RIS)is a promising solution to deal with the blockage-sensitivity of millimeter wave band and reduce the high energy consumption caused by network densification. However, deploying large scale RISs may not bring expected performance gain due to significant channel estimation overhead and non-negligible reflected interference.In this paper,we derive the analytical expressions of the coverage probability, area spectrum efficiency(ASE)and energy efficiency (EE)of a downlink RIS-aided multi-cell network.In order to optimize the network performance, we investigate the conditions for the optimal number of training symbols of each antenna-to-antenna and antenna-to-element path (referred to as the optimal unit training overhead) in channel estimation.Our study shows that:1)RIS deployment is not“the more, the better”, only when blockage objects are dense should one deploy more RISs;2) the coverage probability is maximized when the unit training overhead is designed as large as possible;3)however,the ASE-and-EE-optimal unit training overhead exists. It is a monotonically increasing function of the frame length and a monotonically decreasing function of the average signal-to-noise-ratio (in the high signal-to-noise-ratio region). Additionally,the optimal unit training overhead is smaller when communication nodes deploy particularly few or many antennas.

关键词： reconfigurable intelligent surface multi-cell network directional transmissions channel estimation resource allocation stochastic geometry

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in neuromorphic computing:Expanding horizons for AI development through novel artificial neurons and in-sensor computing

引用

Chinese Physics B 2024年第3期33卷 1-23页

作者：杨玉波赵吉哲刘胤洁华夏扬王天睿郑纪元郝智彪熊兵孙长征韩彦军王健李洪涛汪莱罗毅 department of Electronic Engineering Tsinghua UniversityBeijing 100084China Beijing National Research center for information Science and Technology Tsinghua UniversityBeijing 100084China

AI development has brought great success to upgrading the information age.At the same time,the large-scale artificial neural network for building AI systems is thirsty for computing power,which is barely satisfied by the conventional computing hardware.In the post-Moore era,the increase in computing power brought about by the size reduction of CMOS in very large-scale integrated circuits(VLSIC)is challenging to meet the growing demand for AI computing power.To address the issue,technical approaches like neuromorphic computing attract great attention because of their feature of breaking Von-Neumann architecture,and dealing with AI algorithms much more parallelly and energy efficiently.Inspired by the human neural network architecture,neuromorphic computing hardware is brought to life based on novel artificial neurons constructed by new materials or devices.Although it is relatively difficult to deploy a training process in the neuromorphic architecture like spiking neural network(SNN),the development in this field has incubated promising technologies like in-sensor computing,which brings new opportunities for multidisciplinary research,including the field of optoelectronic materials and devices,artificial neural networks,and microelectronics integration technology.The vision chips based on the architectures could reduce unnecessary data transfer and realize fast and energy-efficient visual cognitive processing.This paper reviews firstly the architectures and algorithms of SNN,and artificial neuron devices supporting neuromorphic computing,then the recent progress of in-sensor computing vision chips,which all will promote the development of AI.

关键词： neuromorphic computing spiking neural network(SNN) in-sensor computing artificial intelligence

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

High-Level Security Dimension Evaluation of Blockchain BaaS System and Key Technology

引用

China Communications 2024年第6期21卷 176-191页

作者： Chen Wanfa Zheng Qing’an Chen Shuzhen Fu Hongyi Chen Liang Fujian Police College Fuzhou 350007China Computer Science and information Security management department Fujian Police CollegeFuzhou 350007China Fujian Province Key Laboratory for Digital network Crime Supervision and Prevention Fuzhou 350007China Beijing University of Posts and Telecommunications Beijing 100876China Fujian Provincial Prison Administration Fuzhou 350002China

In recent years,blockchain technology integration and application has gradually become an important driving force for new technological innovation and industrial transformation.While blockchain technology and applications are developing rapidly,the emerging security risks and obstacles have gradually become prominent.Attackers can still find security issues in blockchain systems and conduct attacks,causing increasing losses from network attacks every year.In response to the current demand for blockchain application security detection and assessment in all industries,and the insufficient coverage of existing detection technologies such as smart contract detectiontechnology,this paper proposes a blockchain core technology security assessment system model,and studies the relevant detection and assessment key technologies and systems.A security assessment scheme based on a smart contract and consensus mechanism detection scheme is designed.And the underlying blockchain architecture supports the traceability of detection results using super blockchains.Finally,the functionality and performance of the system were tested,and the test results show that the model and solutions proposed in this paper have good feasibility.

关键词： blockchain security consensus mechanis smart contract

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Burden of routine orthopedic implant removal a single center retrospective study

引用

World Journal of Orthopedics 2024年第2期15卷 139-146页

作者： Ammar K AlOmran Nader Alosaimi Ahmed A Alshaikhi Omar M Bakhurji Khalid J Alzahrani Basil Ziyad Salloot Tamim Omar Alabduladhem Ahmed I AlMulhim Arwa Alumran department of Orthopedic College of MedicineImam Abdulrahman Bin Faisal UniversityDammam 31441Saudi Arabia Health information management and Technology department Imam Abdulrahman Bin Faisal UniversityDammam 31441Saudi Arabia

BACKGROUND Open reduction and internal fixation represent prevalent orthopedic procedures,sparking ongoing discourse over whether to retain or remove asymptomatic implants.Achieving consensus on this matter is paramount for orthopedic surgeons.This study aims to quantify the impact of routine implant removal on patients and healthcare facilities.A retrospective analysis of implant removal cases from 2016 to 2022 at King Fahad Hospital of the University(KFHU)was conducted and subjected to statistical scrutiny.Among these cases,44%necessitated hospitalization exceeding one day,while 56%required only a single day.Adults exhibited a 55%need for extended hospital stays,contrasting with 22.8%among the pediatric cohort.The complication rate was 6%,with all patients experiencing at least one complication.Notably,34.1%required sick leave and 4.8%exceeded 14 d.General anesthesia was predominant(88%).Routine implant removal introduces unwarranted complications,particularly in adults,potentially prolonging hospitalization.This procedure strains hospital resources,tying up the operating room that could otherwise accommodate critical surgeries.Clearly defined institutional guidelines are imperative to regulate this practice.AIM To measure the burden of routine implant removal on the patients and hospital.METHODS This is a retrospective analysis study of 167 routine implant removal cases treated at KFHU,a tertiary hospital in Saudi Arabia.Data were collected in the orthopedic department at KFHU from February 2016 to August 2022,which includes routine asymptomatic implant removal cases across all age categories.Nonroutine indications such as infection,pain,implant failure,malunion,nonunion,restricted range of motion,and prominent hardware were excluded.Patients who had external fixators removed or joints replaced were also excluded.RESULTS Between February 2016 and August 2022,360 implants were retrieved;however,only 167 of those who met the inclusion criteria were included in this study.The remaining implants were rejected due

关键词： Implant removal Healed fracture Orthopedic implant Complications Healthcare system

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：