检索结果-内蒙古大学图书馆

IEEE International Symposium on Information Theory

作者： Galen Reeves Henry D. Pfister Departments of Electrical and Computer Engineering Duke University Statistical Science Duke University Mathematics Duke University

Recently, the authors showed that Reed–Muller (RM) codes achieve capacity on binary memoryless symmetric (BMS) channels with respect to bit error rate. This paper extends that work by showing that RM codes defined on non-binary fields, known as generalized RM codes, achieve capacity on sufficiently symmetric non-binary channels with respect to symbol error rate. The new proof also simplifies the previous approach (for BMS channels) in a variety of ways that may be of independent interest.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Striking a Balance: An Optimal Mechanism Design for Heterogenous Differentially Private Data Acquisition for Logistic Regression

arXiv

引用

arXiv 2023年

作者： Anjarlekar, Ameya Etesami, Rasoul Srikant, R. Department of Electrical and Computer Engineering Coordinated Science Lab University of Illinois Urbana-Champaign United States Departments of Industrial and Systems Engineering and Electrical and Computer Engineering The Coordinated Science Lab University of Illinois Urbana-Champaign United States

We address the challenge of solving machine learning tasks using data from privacy-sensitive sellers. Since the data is private, we design a data market that incentivizes sellers to provide their data in exchange for payments. Therefore our objective is to design a mechanism that optimizes a weighted combination of test loss, seller privacy, and payment, striking a balance between building a good privacy-preserving ML model and minimizing payments to the sellers. To achieve this, we first propose an approach to solve logistic regression with known heterogeneous differential privacy guarantees. Building on these results and leveraging standard mechanism design theory, we develop a two-step optimization framework. We further extend this approach to an online algorithm that handles the sequential arrival of sellers. © 2023, CC BY-NC-ND.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Differentiating structure of in situ and ex situ formation of laser-induced graphene hybrids

引用

Rare Metals 2022年第9期41卷 3035-3044页

作者： Li-Bei Huang Wei-Hua Guo Le Cheng Jian-Jun Su Yun Song Fei-Jun Hu Ying Lo Law Zheng Yan Jian Lin Ru-Quan Ye State Key Laboratory of Marine Pollution Department of ChemistryCity University of Hong KongHong Kong999077China Department of Mechanical and Aerospace Engineering University of MissouriColumbiaMO65211USA Department of Biomedical Biological&Chemical EngineeringUniversity of MissouriColumbiaMO65211USA Department of Electrical Engineering and Computer Science University of MissouriColumbiaMO65211USA City University of Hong Kong Shenzhen Research Institute Shenzhen518057China

Laser-induced graphene(LIG)has been exploited in various fields,such as batteries,water treatment,and flexible actuators and sensors,with the advantages of ease in patternable fabrication and graphene/metal hybrid *** in situ method which includes a single lase step and the ex situ method which uses two lase steps are both widely implemented to synthesize graphene/metal ***,the differences in the structures and properties of the resulting hybrids are not fully ***,we investigate the advantages of ex situ and in situ methods for preparing LIG hybrids using NiFe/LIG as an *** morphology,elemental composition,resistance to strong acid,and application in electrocatalysis and dye adsorption of ex situ and in situ NiFe/LIG hybrids were systematically studied and ***-dispersive X-ray spectrometry(EDS)and vibrating sample magnetometry(VSM)results confirmed the structural differences between the NiFe/LIG *** nanoparticles are mostly wrapped by carbon layers in the in situ NiFe/LIG hybrid,while the ex situ NiFe/LIG hybrid largely exposes the metal *** structural differences are significant for tailoring performance in applications,such as wastewater treatment and *** work provides insights into the synthesis and properties of LIGs and has important implications for future applications.

关键词： Ex situ In situ Laser-induced graphene Metal-containing hybrids Oxygen evolution reaction Dye adsorption

来源：评论

学校读者我要写书评

暂无评论

YOLOv5 Deep Learning Model for Mixed Seed Detection, Classification, and Counting

YOLOv5 Deep Learning Model for Mixed Seed Detection, Classif...

引用

2024 American Society of Agricultural and biological Engineers Annual International Meeting, ASABE 2024

作者： Kumari, Karishma Won, Kwanghee Nafchi, Ali M. Departments of Agronomy Horticulture & Plant Science South Dakota State University BrookingsSD57007 United States Agriculture & Biosystems Engineering South Dakota State University BrookingsSD57007 United States Electrical Eng. & Computer Science South Dakota State University BrookingsSD57007 United States

ISBN: (纸本)9798331302214

The application of deep learning to multi-seed mix detection and accurate seed counting can significantly improve efficiency and precision in fields such as agriculture, research, and seed quality control. The success of this approach relies heavily on the quality of the dataset, rigorous model selection, and model training. In different applications, including agriculture, food processing, and quality control, it can be crucial to identify the presence of several seeds in a mixture. Seed characteristics such as uniformity in size and shape, counting methods (manual or specialized equipment), and methods for seed mix detection techniques are factors to consider. Even with sophisticated machinery, counting irregularly shaped or tiny seeds can be difficult. Based on their size, shape, color, and other visual characteristics, we can count and classify seeds visually. However, manual counting is time-consuming, prone to errors, and accuracy varies with the counter's expertise and experience. In this study, a Canon LP E6N R6 5D Mark iv camera was used to capture images of various seeds including flax, hairy vetch, red clover, radish, and rye seeds. To improve the accuracy of seed mixture detection and classification, we amalgamated datasets containing these five seed types. Data annotation emerged as the main step in developing deep learning models, which was accomplished using the Robo-flow platform. This platform facilitated annotation and enabled efficient data organization and division into training, validation, and testing sets. Additionally, the application of data augmentation techniques mitigated overfitting problem, to enhance the generalization power of the model which improves the performance of the model for object detection on the testing data. Our research identified the YOLO series network effective in training mixed seed datasets, yielding the best results. Specifically, the YOLOv5 network demonstrated exceptional performance, achieving a recall 96.96 %,

关键词： Seed

来源：评论

学校读者我要写书评

暂无评论

An Artificial Intelligence Representation of Human Knowledge for Lung Nodule Classification

An Artificial Intelligence Representation of Human Knowledge...

引用

2022 IEEE Nuclear science Symposium, Medical Imaging Conference, and Room Temperature Semiconductor Detector Conference, IEEE NSS MIC RTSD 2022

作者： Gao, Yongfeng Pomeroy, Marc Cao, Weiguo Han, Fangfang Liang, Zhengrong Stony Brook University Department of Radiology Stony BrookNY11794 United States Stony Brook University Departments of Radiology Biomedical Engineering Computer Science and Electrical Engineering Stony BrookNY11794 United States

ISBN: (纸本)9781665488723

Low-dose computed tomography (LdCT), a recommended screening method for detection of early lung cancer, has high false positive (FP) rate, and lung nodule biopsy is a follow-up option to eliminate the FPs. It is challenging and meaningful to differentiate the nodule pathology by the LdCT screening data to avoid the costly interventional biopsy procedure. In this paper, we propose an artificial intelligence (AI) model to represent the human knowledge about lesion properties to differentiate the malignant nodules from benign ones. Three lesion properties in terms of heterogeneity, elasticity and growth are quantitatively represented by the proposed AI model. An augmented feature selection strategy was developed to integrate all lesion properties for the lesion classification. Experimental results show that the proposed AI model can achieve an AUC (area under the curve of receiver operating characteristics) score of 0.78 in the cases where physicians cannot determine the lesion type with AUC score around 0.5. © 2022 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL DEEP LEARNING TO DIFFERENTIATE TUMOR RECURRENCE FROM TREATMENT EFFECT IN HUMAN GLIOBLASTOMA

arXiv

引用

arXiv 2023年

作者： Hossain, Tonmoy Qureshi, Zoraiz Jayakumar, Nivetha Muttikkal, Thomas Eluvathingal Patel, Sohil Schiff, David Zhang, Miaomiao Kundu, Bijoy Departments of Computer Science University of Virginia United States Departments of Radiology and Medical Imaging University of Virginia United States Departments of Neurology University of Virginia United States Departments of Electrical and Computer Engineering University of Virginia United States Departments of Biomedical Engineering University of Virginia United States

Differentiating tumor progression (TP) from treatment-related necrosis (TN) is critical for clinical management decisions in glioblastoma (GBM). Dynamic FDG PET (dPET), an advance from traditional static FDG PET, may prove advantageous in clinical staging. dPET includes novel methods of a model-corrected blood input function that accounts for partial volume averaging to compute parametric maps that reveal kinetic information. In a preliminary study, a convolution neural network (CNN) was trained to predict classification accuracy between TP and TN for 35 brain tumors from 26 subjects in the PET-MR image space. 3D parametric PET Ki (from dPET), traditional static PET standardized uptake values (SUV), and also the brain tumor MR voxels formed the input for the CNN. The average test accuracy across all leave-one-out cross-validation iterations adjusting for class weights was 0.56 using only the MR, 0.65 using only the SUV, and 0.71 using only the Ki voxels. Combining SUV and MR voxels increased the test accuracy to 0.62. On the other hand, MR and Ki voxels increased the test accuracy to 0.74. Thus, dPET features alone or with MR features in deep learning models would enhance prediction accuracy in differentiating TP vs TN in GBM. © 2023, CC BY.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Toward Behavior-Based models of bat echolocation

Toward Behavior-Based models of bat echolocation

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Thinh H. Nguyen Dieter Vanderelst Electrical Engineering and Computer Science University of Cincinnati Cincinnati USA Electrical Engineering and Computer Science Biological Sciences University of Cincinnati Cincinnati USA

ISBN: (纸本)9781665487696

We propose a Behavior-Based Robotic (BBR) architecture to model the cognitive controller of echolocation bats. The architecture used a neural network to perform high-level control by governing two sensorimotor loops. We trained our model in a simulated environment where the echoes returned from the environment were derived from real echoes collected by a physical sonar system. We trained our BBR architecture on a foraging task and tested the trained agent in different experiments. The agent demonstrated the ability to learn the foraging task on different maze geometries by avoiding obstacles and approaching food items. The agent also demonstrated robustness against considerable noise in actuation. This prototype demonstrated the feasibility of training a BBR model of complex bat echolocation tasks using a hybrid simulated environment.

关键词： Training Computational modeling Neural networks Sonar Prototypes computer architecture Robot sensing systems

来源：评论

学校读者我要写书评

暂无评论

Exact Distribution of the Quantal Content in Synaptic Transmission

引用

Physical Review Letters 2024年第22期132卷 228401-228401页

作者： Krishna Rijal Nicolas I. C. Müller Eckhard Friauf Abhyudai Singh Ashok Prasad Dibyendu Das Department of Physics Indian Institute of Technology Bombay Powai Mumbai 400076 India Animal Physiology Group Department of Biology University of Kaiserslautern Kaiserslautern Germany Departments of Electrical and Computer Engineering Biomedical Engineering and Mathematical Sciences University of Delaware Newark Delaware 19716 USA Department of Chemical and Biological Engineering Colorado State University Fort Collins Colorado USA

During electrochemical signal transmission through synapses, triggered by an action potential (AP), a stochastic number of synaptic vesicles (SVs), called the “quantal content,” release neurotransmitters in the synaptic cleft. It is widely accepted that the quantal content probability distribution is a binomial based on the number of ready-release SVs in the presynaptic terminal. But the latter number itself fluctuates due to its stochastic replenishment, hence the actual distribution of quantal content is unknown. We show that exact distribution of quantal content can be derived for general stochastic AP inputs in the steady state. For fixed interval AP train, we prove that the distribution is a binomial, and corroborate our predictions by comparison with electrophysiological recordings from MNTB-LSO synapses of juvenile mice. For a Poisson train, we show that the distribution is nonbinomial. Moreover, we find exact moments of the quantal content in the Poisson and other general cases, which may be used to obtain the model parameters from experiments.

关键词： Fluctuations & noise Noise Nonequilibrium statistical mechanics Stochastic processes Master equation Synaptic transmission model

来源：评论

学校读者我要写书评

暂无评论

TripletGO: Integrating Transcript Expression Profiles with Protein Homology Inferences for Gene Function Prediction

引用

Genomics, Proteomics & Bioinformatics 2022年第5期20卷 1013-1027页

作者： Yi-Heng Zhu Chengxin Zhang Yan Liu Gilbert S.Omenn Peter L.Freddolino Dong-Jun Yu Yang Zhang School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Department of Computational Medicine and Bioinformatics University of MichiganAnn ArborMI 48109USA Departments of Internal Medicine and Human Genetics and School of Public HealthUniversity of MichiganAnn ArborMI 48109USA Department of Biological Chemistry University of MichiganAnn ArborMI 48109USA

Gene Ontology(GO)has been widely used to annotate functions of genes and gene ***,we proposed a new method,Triplet GO,to deduce GO terms of protein-coding and noncoding genes,through the integration of four complementary pipelines built on transcript expression profile,genetic sequence alignment,protein sequence alignment,and naīve *** GO was tested on a large set of 5754 genes from 8 species(human,mouse,Arabidopsis,rat,fly,budding yeast,fission yeast,and nematoda)and 2433 proteins with available expression data from the third Critical Assessment of Protein Function Annotation challenge(CAFA3).Experimental results show that Triplet GO achieves function annotation accuracy significantly beyond the current state-of-the-art *** analyses show that the major advantage of Triplet GO lies in the coupling of a new triplet network-based profiling method with the feature space mapping technique,which can accurately recognize function patterns from transcript expression ***,the combination of multiple complementary models,especially those from transcript expression and protein-level alignments,improves the coverage and accuracy of the final GO annotation *** standalone package and an online server of Triplet GO are freely available at https://***/Triplet GO/.

关键词： Gene function annotation Gene Ontology Transcript expression profile Triplet network Protein-level alignment

来源：评论

学校读者我要写书评

暂无评论

Plasma-Treated Polymeric Biomaterials for Improved Surface and Cell Adhesion

arXiv

引用

arXiv 2025年

作者： Rondón, Jairo Gonzalez-Lizardo, Angel Biomedical & Chemical Engineering Departments Polytechnic University of Puerto Rico Puerto Rico San Juan United States Department of Electrical and Computer Engineering and Computer Science Polytechnic University of Puerto Rico Puerto Rico San Juan United States

Surface modification of polymeric biomaterials using plasma has emerged as an effective strategy to optimize the cell-material interface without compromising the structural properties of the material. This work presents a critical review of the impact of low-temperature plasma treatment on enhancing cell adhesion, with emphasis on the physicochemical changes induced on the surface of polymers commonly used in biomedical applications. The mechanisms of interaction between reactive plasma species and the polymer surface are analyzed, along with techniques used to introduce hydrophilic functional groups that improve wettability and biocompatibility. Scientific evidence demonstrates that this type of surface modification promotes greater cell spreading, anchorage, and proliferation, making it particularly useful in the design of tissue engineering scaffolds, implantable devices, and vascular prostheses. Finally, current and future trends in the development of smart plasma-functionalized biomaterials are discussed, highlighting their role in regenerative medicine. © 2025, CC BY-NC-ND.

关键词： Medical applications

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：