检索结果-内蒙古大学图书馆

2006 IEEE computer Society Conference on computer Vision and Pattern Recognition, CVPR 2006

作者： Navalpakkam, Vidhya Itti, Laurent Dept. of Computer Science Neuroscience Graduate Program University of Southern California

ISBN: (纸本)0769525970

Integration of goal-driven, top-down attention and image-driven, bottom-up attention is crucial for visual search. Yet, previous research has mostly focused on models that are purely top-down or bottom-up. Here, we propose a new model that combines both. The bottom-up component computes the visual salience of scene locations in different feature maps extracted at multiple spatial scales. The top-down component uses accumulated statistical knowledge of the visual features of the desired search target and background clutter, to optimally tune the bottom-up maps such that target detection speed is maximized. Testing on 750 artificial and natural scenes shows that the model's predictions are consistent with a large body of available literature on human psychophysics of visual search. These results suggest that our model may provide good approximation of how humans combine bottom-up and top-down cues such as to optimize target detection speed. © 2006 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Benchmarking for 3D Image-to-Image Fusion Problem

Super-Resolution Benchmarking for 3D Image-to-Image Fusion P...

引用

IEEE International Symposium on Biomedical Imaging

作者： Daniel Franco-Barranco Aitor González-Marfil Albert Cardona Arrate Muñoz-Barrutia Ignacio Arganda-Carreras MRC Laboratory of Molecular Biology University of Cambridge Cambridge UK Department of Physiology Development and Neuroscience University of Cambridge Cambridge UK Donostia International Physics Center (DIPC) San Sebastian Spain Dept. of Computer Science and Artificial Intelligence University of the Basque Country (UPV/EHU) San Sebastian Spain Dept. de Bioingenieria Universidad Carlos III de Madrid Madrid Spain Area de Bioingenieria Instituto de Investigatión Sanitaria Gregorio Marañón Madrid Spain IKERBASQUE Basque Foundation for Science Bilbao Spain Biofisika Institute (CSIC-UPV/EHU) Leioa Spain

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Fluorescence microscopy faces challenges in resolution, phototoxicity, and anisotropic artifacts. The Fuse My Cells challenge, organized by France-BioImaging, aims to develop deep learning models that predict fused 3D volumes from single-view acquisitions, reducing phototoxic exposure while enhancing resolution. In this work, we benchmark state-of-the-art super-resolution models, including DFCAN, RCAN-3D, UNETR, and a 3D-adapted RCAN-it, evaluating their performance on the Fuse My Cells challenge dataset, which encompasses 802 3D light-sheet microscopy images. A novel training strategy prioritizing high-discrepancy regions optimizes efficiency and improves reconstruction accuracy. Our findings suggest that super-resolution models can not fully reconstruct the information on those image areas with minimum signal information. Code and documentation can be found at https://***/danifranco/BiaPy.

关键词： Training Measurement Deep learning Solid modeling Three-dimensional displays Fuses Microscopy Superresolution Biomembranes Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional quantitative phase imaging evaluating glioblastoma targeting CAR T-cell efficacy 11

Three-dimensional quantitative phase imaging evaluating glio...

引用

Quantitative Phase Imaging XI 2025

作者： Serafini, Caroline E. Davarzani, Amin Cappabianca, Dan Collazos, Daniela Baez Li, Zhenmin Mamaghani, Deniz Tommasi, Anna Sarko, Lauren La Vonne Denne, Nina Mao, Leidong Saha, Krishanu Karumbaiah, Lohitash Robles, Francisco E. George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology AtlantaGA United States Wallace H. Coulter Dept. of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA United States School of Electrical and Computer Engineering College of Engineering University of Georgia AthensGA United States Regenerative Bioscience Center University of Georgia AthensGA United States Department of Biomedical Engineering University of Wisconsin-Madison MadisonWI United States Wisconsin Institute for Discovery University of Wisconsin-Madison MadisonWI United States School of Electrical and Computer Engineering Georgia Institute of Technology 266 Ferst Drive AtlantaGA United States Department of Cellular Biology University of Georgia AthensGA United States Division of Neuroscience Biomedical and Translational Sciences Institute University of Georgia AthensGA United States Edgar L. Rhodes Center for Animal and Dairy Science College of Agriculture and Environmental Science University of Georgia AthensGA United States

ISBN: (纸本)9781510684065

Glioblastoma (GBM) is a highly aggressive brain tumor with limited treatment options and poor patient outcomes. While patient-derived spheroids offer a platform for studying GBM treatment, existing imaging modalities are often destructive or limited to endpoint analyses. Here, we present quantitative Oblique Back- illumination Microscopy (qOBM) as a novel, label-free imaging technique for real-time, non-invasive monitoring of GBM spheroids treated with tumor targeting chimeric antigen receptor T-cells (CAR T-cells). qOBM overcomes existing imaging limitations by providing high-resolution, 3D quantitative phase imaging through epi-illumination, enabling longitudinal visualization of cellular and subcellular processes within thick spheroids. Here, we apply qOBM to monitor the responses of GBM spheroids derived from three unique patient cell lines to targeted CAR T-cell immunotherapy and non-targeted controls. With this, we capture changes in the spheroids over 72 hours of treatment, allowing for visualization of processes such as CAR T-cell infiltration, mitosis, and apoptosis. Further, using images from GBM/CAR T cell cocultures, we develop a machine learning model for predicting spheroid cytotoxicity rates. Our findings establish qOBM as a powerful, non-destructive tool for longitudinal GBM spheroid toxicity monitoring and demonstrate its potential to advance personalized cancer therapy by providing real-time insight into treatment efficacy. © 2025 SPIE.

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

Enhancing Software Quality Through Defect Prediction 3

Enhancing Software Quality Through Defect Prediction

引用

3rd International Conference on Creative Communication and Innovative Technology, ICCIT 2024

作者： Gita Gayatri, Nyoman Ayu Soeparno, Haryono Gaol, Ford Lumban Arifin, Yulyani Bina Nusantara University Binus Graduate Program Computer Science Dept. of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350367492

Prediction of software defects is an important aspect of software quality assurance, aiming to identify defective modules to improve reliability and reduce costs in the maintenance process. A systematic literature review (SLR) on software defect prediction is presented in this study, focusing on identifying commonly used datasets, methods, and frameworks in this domain between 2014 and 2023. The review follows established SLR guidelines to synthesize data from primary studies, providing insight into research trends as well as methodological advances. The results show a significant reliance on public datasets such as the NASA Metrics Data program (MDP) and the PROMISE repository. Various machine-learning techniques have been used, with Neural networks, support vector machines, and random forests becoming the most popular techniques. This review aims to guide future research by highlighting key trends and gaps in the existing literature. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Coordination and learning in multirobot systems

引用

IEEE Intelligent Systems and Their Applications 1998年第2期13卷 6-8页

作者： Matarić, Maja J. University of Southern California Computer Science Department Neuroscience Program University of Southern California USC Robotics Research Lab. MIT AAAI ISAB Computer Science Dept. MC 0781 Univ. of Southern California Los Angeles CA 90089-0781 United States

Finding methods for generating coherent, robust, useful and adaptive behavior in groups of autonomous robots is an increasingly active area of research. The incremental approach to robotics-first studying control and learning in a single robot-is not sufficient or even relevant (for some problems) to the multi-robot coordination and learning problem. Instead, the problem requires a general approach-which is fundamentally different from most of today's robot control and learning methods-to make the necessary strides in this challenging domain. Based on our research of situated, embodied systems, we suggest that control and learning in multi-robot systems must be addressed as a separate, novel and unified problem-not an additional "module" in a single-robot approach. We propose a bottom-up methodology to produce the desired system behavior.

关键词： Multirobot systems Robot kinematics Robot sensing systems Mobile robots Robot control Delay Tactile sensors Infrared sensors Robustness Multiagent systems

来源：评论

学校读者我要写书评

暂无评论

Deep Gaussian processes 16

Deep Gaussian processes

引用

16th International Conference on Artificial Intelligence and Statistics, AISTATS 2013

作者： Damianou, Andreas C. Lawrence, Neil D. Dept. of Computer Science Sheffield Institute for Translational Neuroscience University of Sheffield Sheffield United Kingdom

In this paper we introduce deep Gaussian process (GP) models. Deep GPS are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inputs to that Gaussian process are then governed by another GP. A single layer model is equivalent to a standard GP or the GP latent variable model (GP-LVM). We perform inference in the model by approximate variational marginalization. This results in a strict lower bound on the marginal likelihood of the model which we use for model selection (number of layers and nodes per layer). Deep belief networks are typically applied to relatively large data sets using stochastic gradient descent for optimization. Our fully Bayesian treatment allows for the application of deep models even when data is scarce. Model selection by our variational bound shows that a five layer hierarchy is justified even when modelling a digit data set containing only 150 examples. Copyright 2013 by the authors.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Detecting "Smart" Spammers on Social Network: A Topic Model Approach

Detecting "Smart" Spammers on Social Network: A Topic Model ...

引用

2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Student Research Workshop, SRW 2016

作者： Liu, Linqing Lu, Yao Luo, Ye Zhang, Renxian Itti, Laurent Lu, Jianwei iLab Tongji School of Software Engineering Tongji University China Dept. of Computer Science and Technology Tongji University China Dept. of Computer Science and Neuroscience Program University of Southern California United States Institute of Translational Medicine Tongji University China

ISBN: (纸本)9781941643815

Spammer detection on social network is a challenging problem. The rigid anti-spam rules have resulted in emergence of "smart" spammers. They resemble legitimate users who are difficult to identify. In this paper, we present a novel spammer classification approach based on Latent Dirichlet Allocation (LDA), a topic model. Our approach extracts both the local and the global information of topic distribution patterns, which capture the essence of spamming. Tested on one benchmark dataset and one self-collected dataset, our proposed method outperforms other state-of-the-art methods in terms of averaged F1-score. © 2016 Association for Computational Linguistics.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Adaptive entity-identifier generation for IMD emergency access 14

Adaptive entity-identifier generation for IMD emergency acce...

引用

1st Workshop on Cryptography and Security in Computing Systems, CS2 2014

作者： Seepers, Robert M. Strydis, Christos Sourdis, Ioannis De Zeeuw, Chris I. Dept. of Neuroscience Erasmus Medical Center Rotterdam Netherlands Dept. of Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (纸本)9781450324847

Recent work on wireless Implantable Medical Devices (IMDs) has revealed the need for secure communication in order to prevent data theft and implant abuse by malicious attackers. However, security should not be provided at the cost of patient safety and an IMD should, thus, remain accessible during an emergency regardless of device security. In this paper, we present a novel method of providing IMD emergency access, based on generating Entity Identifiers (EI) using the Inter-Pulse Intervals (IPIs) of heartbeats. We evaluate the current state-of-the-art in EI-generation in terms of security and accessibility for healthy subjects with a wide range of heart rates. Subsequently, we present an adaptive EI-generation algorithm which takes the heart rate into account, maintaining an acceptable emergency-mode activation time (between 5-55.4 s) while improving security by up to 3.4x for high heart rates. Finally, we show that activating emergency mode may consume as little as 0.24μJ from the IMD battery. Copyright © 2014 ACM.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Decoding Asymmetric Neural Dynamics in Visual Processing via TMS-induced Cortical Effective Connectivity 46

Decoding Asymmetric Neural Dynamics in Visual Processing via...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Paolini, Edoardo Siviero, Ilaria Bonfanti, Davide Menegaz, Gloria Savazzi, Silvia Mazzi, Chiara Storti, Silvia F. University of Verona Dept. of Computer Science Verona Italy University of Verona Dept. of Neuroscience Biomedicine and Movement Science Verona Italy University of Verona Dept. of Engineering for Innovation Medicine Verona Italy

ISBN: (纸本)9798350371499

Exploring brain connectivity is made possible through the combination of transcranial magnetic stimulation and electroencephalography (TMS-EEG) signals. While previous research has investigated hemispheric asymmetries in signal propagation at the electrode space following occipital TMS, this work extends this exploration at the source level. The sources of the neural activity were reconstructed using EEG data and mapped into regions of interest. The TMS evoked potential (TEP) was estimated using a Bayesian approach, which provides better results when the number of trials is limited. Subsequently, time-varying effective connectivity was calculated for uncovering hemispheric asymmetries in the dynamics of signal propagation. A distinct contralateral influence emerged following stimulation of the left occipital lobe, especially toward the parietal and frontal lobes, aligning with the observations on the scalp. In conclusion, our study advances the understanding of brain connectivity dynamics, particularly in hemispheric interactions, and paves the way for further insights into the implications of TMS on neural networks. © 2024 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

An integrated software management tool for adopting software product lines

An integrated software management tool for adopting software...

引用

2012 IEEE/ACIS 11th International Conference on computer and Information science, ICIS 2012

作者： Park, Kibum Ryu, Duksan Baik, Jongmoon Dept. of Software Engineering Program KAIST Daejeon Korea Republic of Dept. of Computer Science KAIST Daejeon Korea Republic of

ISBN: (纸本)9780769546940

Software product line engineering has become widely known that it provides software organization with tremendous profits through systematical reuse to a number of organizations that require producing various and similar kinds of software products. However, when adopting software product lines, it has been reported that there are several challenges, e.g., the shortage of procedural support for application engineering, and original reasons of complexity and implicit properties for variability management. In order to address these major problems, an integrated tool support is required to guide software product line engineering process. The integrated software management tool for adopting software product lines, called "ISMT4SPL" can offer beneficial traceability among the artifacts created from domain engineering and application engineering. Furthermore, all the artifacts could consistently be managed by explicit representation of the relationship between artifacts generated at each software development phase by ISMTSPL. ISMT4SPL would contribute to adopting and guiding software product lines into the organizations that demand the seamless introduction of systematic reuse since the ISMT4SPL is helpful to manage variability by delivering the method that can generate a flexible and automatic variability model, which reduces complexity for managing a number of variation points and variants. In addition, consistency between all the artifacts would reduce confusion and quality problems by removing mismatches among them. © 2012 IEEE.

关键词： Software design

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：