检索结果-内蒙古大学图书馆

A large field‑of‑view,single‑cell‑resolution two‑and three‑photon microscope for deep and wide imaging

eLight 2024年第1期4卷 26-39页

作者： Aaron T.Mok Tianyu Wang Shitong Zhao Kristine E.Kolkman Danni Wu Dimitre G.Ouzounov Changwoo Seo Chunyan Wu Joseph R.Fetcho Chris Xu School of Applied and Engineering Physics Cornell UniversityIthacaNYUSA Meining School of Biomedical Engineering Cornell UniversityIthacaNYUSA Department of Electrical and Computer Engineering Boston UniversityBostonMAUSA Department of Neurobiology and Behavior Cornell UniversityIthacaNYUSA Harvard T.H.Chan School of Public Health Harvard UniversityCambridgeMAUSA Department of Molecular&Cellular Biology Harvard UniversityCambridgeMAUSA McGovern Institute for Brain Research at MIT CambridgeMAUSA

In vivo imaging of large-scale neuronal activity plays a pivotal role in unraveling the function of the brain’s *** microscopy,a powerful tool for deep-tissue imaging,has received sustained interest in advancing its speed,field of view and imaging ***,to avoid thermal damage in scattering biological tissue,field of view decreases exponentially as imaging depth *** present a suite of innovations to optimize three-photon microscopy for large field-of-view imaging at depths unreachable by two-photon *** techniques enable us to image neuronal activities of transgenic animals expressing protein calcium sensors in a~3.5-mm diameter field-of-view with single-cell resolution in the deepest cortical layer of mouse *** further demonstrate simultaneous large field-of-view two-photon and three-photon imaging,subcortical imaging in the mouse brain,and whole-brain imaging in adult *** demonstrated techniques can be integrated into typical multiphoton microscopes to enlarge field of view for system-level neural circuit research.

关键词： Three-photon microscopy Two-photon microscopy Large field of view Brain imaging DEEPscope

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization for a Grid-Connected Hydrogen Integrated Energy Community

Multi-Objective Optimization for a Grid-Connected Hydrogen I...

引用

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Li, Na Maselli, Riccardo Ziar, Hesan Van Der Weijden, Joep Okur, Özge Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Netherlands Afry Netherlands Delft University of Technology The Green Village Netherlands Delft University of Technology Faculty of Technology Policy and Management Netherlands

ISBN: (纸本)9789531842976

Hydrogen is increasingly recognized for its role in enhancing the electrification of the built environment, particularly as a seasonal storage medium to balance the intermittent nature of renewable generation. Despite its potential, the high investment costs of hydrogen technologies make their integration challenging in current energy systems. This study addresses the gap in research concerning the impacts of hydrogen integration within energy communities, focusing on system performance and grid operations through different grid connection scenarios. We explore three grid connection capacities - unlimited, 24 kW, and 16 kW - using a case study from The Green Village. Our findings indicate that an unlimited grid connection poses a risk of grid congestion, whereas a restricted connection could result in unmet load demands. Our results suggest that aligning the grid connection capacity with the peak demand of the energy community effectively balances the need to reduce grid congestion while meeting energy requirements. This research highlights the need for strategic planning in the integration of hydrogen technologies within energy communities, advocating for a balance that supports both energy independence and grid stability. © 2024 IEEE.

关键词： Hydrogen storage

来源：评论

学校读者我要写书评

暂无评论

Guided Malware Sample Analysis Based on Graph Neural Networks

引用

IEEE Transactions on Information Forensics and Security 2023年 18卷 4128-4143页

作者： Chen, Yi-Hsien Lin, Si-Chen Huang, Szu-Chun Lei, Chin-Laung Huang, Chun-Ying National Taiwan University Department of Electrical Engineering Taipei106319 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300093 Taiwan Delft University of Technology Faculty of Technology Policy and Management Delft2628 BX Netherlands

Malicious binaries have caused data and monetary loss to people, and these binaries keep evolving rapidly nowadays. With tons of new unknown attack binaries, one essential daily task for security analysts and researchers is to analyze and effectively identify malicious parts and report the critical behaviors within the binaries. While manual analysis is slow and ineffective, automated malware report generation is a long-term goal for malware analysts and researchers. This study moves one step toward the goal by identifying essential functions in malicious binaries to accelerate and even automate the analyzing process. We design and implement an expert system based on our proposed graph neural network called MalwareExpert. The system pinpoints the essential functions of an analyzed sample and visualizes the relationships between involved parts. We evaluate our proposed approach using executable binaries in the Windows operating system. The evaluation results show that our approach has a competitive detection performance (97.3% accuracy and 96.5% recall rate) compared to existing malware detection models. Moreover, it gives an intuitive and easy-to-understand explanation of the model predictions by visualizing and correlating essential functions. We compare the identified essential functions reported by our system against several expert-made malware analysis reports from multiple sources. Our qualitative and quantitative analyses show that the pinpointed functions indicate accurate directions. In the best case, the top 2% of functions reported from the system can cover all expert-annotated functions in three steps. We believe that the MalwareExpert system has shed light on automated program behavior analysis. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

The Neural Networks Based Needle Detection for Medical Retinal Surgery

The Neural Networks Based Needle Detection for Medical Retin...

引用

2022 International Conference on computer Graphics, Artificial Intelligence, and Data Processing, ICCAID 2022

作者： Xu, Jidong Yu, Jinglun Yao, Jianing Zhang, Rendong Department of Electrical and Computer Engineering Johns Hopkins University Baltimore United States Department of Biostatistics Johns Hopkins Bloomberg School of Public Health Baltimore United States

ISBN: (纸本)9781510663350

In recent years, deep learning technology has developed rapidly, and the application of deep neural networks in the medical image processing field has become the focus of the spotlight. This paper aims to achieve needle position detection in medical retinal surgery by adopting the target detection algorithm based on YOLOv5 as the basic deep neural network model. The state-of-the-art needle detection approaches for medical surgery mainly focus on needle structure segmentation. Instead of the needle segmentation, the proposed method in this paper contains the angle examination during the needle detection process. This approach also adopts a novel classification method based on the different positions of the needle to improve the model. The experiments demonstrate that the proposed network can accurately detect the needle position and measure the needle angle. The performance test of the proposed method achieves 4.80 for the average Euclidean distance between the detected tip position and the actual tip position. It also obtains an average error of 0.85 degrees for the tip angle across all test sets. © 2023 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managing Road Safety Hazards 24

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managin...

引用

24th IEEE International Conference on Mobile Data Management, MDM 2023

作者： Christou, Georgios Georgiou, Andreas Laoudias, Christos Savva, Aristotelis Panayiotou, Christos G. University of Cyprus Kios Center of Excellence Cyprus Ministry of Transport Communications and Works Public Works Department Cyprus University of Cyprus Department of Electrical and Computer Engineering Cyprus

ISBN: (纸本)9798350341010

In this demonstration paper, we present FixCyprus, which is a cost-effective crowdsourcing service for road transportation authorities in Cyprus to gather information and manage defects and incidents on the road network and surrounding infrastructure (e.g., pavements, lighting, drinking water pipes, etc.). The production service, which includes a lightweight and user-friendly mobile application for sharing image-annotated incident reports, is already operating nationwide for six months providing significant budget savings by reducing field inspections and the use of expensive equipment. We will demonstrate FixCyprus using two modes: i) Interactive mode, where attendees will be able to create and submit their own dummy incident reports and see the end-to-end processing flow in a test environment and ii) Trace-driven mode, where attendees will be able to visualize a large number of synthetic reports, see the workload for manually managing them, and explore enhancements that are underway for automating some of the underlying tasks using machine learning. © 2023 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

From Lab to Field: Real-World Evaluation of an Ai-Driven Smart Video Solution to Enhance Community Safety

SSRN

引用

SSRN 2024年

作者： Yao, Shanle Ardabili, Babak Rahimi Pazho, Armin Danesh Noghre, Ghazal Alinezhad Neff, Christopher Bourque, Lauren Tabkhi, Hamed University of North Carolina at Charlotte Department of Electrical and Computer Engineering United States University of North Carolina at Charlotte Department of Public Policy United States

This article adopts and evaluates an AI-enabled Smart Video Solution (SVS) designed to enhance safety in the real world. The system integrates with existing infrastructure camera networks, leveraging recent advancements in AI for easy adoption. Prioritizing privacy and ethical standards, pose based data is used for downstream AI tasks such as anomaly detection. Cloud-based infrastructure and mobile app are deployed, enabling real-time alerts within communities. The SVS employs innovative data representation and visualization techniques, such as the Occupancy Indicator, Statistical Anomaly Detection, Bird's Eye View, and Heatmaps, to understand pedestrian behaviors and enhance public safety. Evaluation of the SVS demonstrates its capacity to convert complex computer vision outputs into actionable insights for stakeholders, community partners, law enforcement, urban planners, and social scientists. This article presents a comprehensive real-world deployment and evaluation of the SVS, implemented in a community college environment across 16 cameras. The system integrates AI-driven visual processing, supported by statistical analysis, database management, cloud communication, and user notifications. Additionally, the article evaluates the end-to-end latency from the moment an AI algorithm detects anomalous behavior in real-time at the camera level to the time stakeholders receive a notification. The results demonstrate the system's robustness, effectively managing 16 CCTV cameras with a consistent throughput of 16.5 frames per second (FPS) over a 21-hour period and an average end-to-end latency of 26.76 seconds between anomaly detection and alert issuance. © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark

arXiv

引用

arXiv 2024年

作者： Pazho, Armin Danesh Yao, Shanle Noghre, Ghazal Alinezhad Ardabili, Babak Rahimi Katariya, Vinit Tabkhi, Hamed Department of Electrical and Computer Engineering University of North Carolina Charlotte United States Public Policy Program University of North Carolina Charlotte United States

Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal. At its core, human-centric VAD faces substantial challenges, such as the complexity of diverse human behaviors, the rarity of anomalies, and ethical constraints. These challenges limit access to high-quality datasets and highlight the need for a dataset and framework supporting continual learning. Moving towards adaptive human-centric VAD, we introduce the HuVAD (Human-centric privacy-enhanced Video Anomaly Detection) dataset and a novel Unsupervised Continual Anomaly Learning (UCAL) framework. UCAL enables incremental learning, allowing models to adapt over time, bridging traditional training and real-world deployment. HuVAD prioritizes privacy by providing de-identified annotations and includes seven indoor/outdoor scenes, offering over 5× more pose-annotated frames than previous datasets. Our standard and continual benchmarks, utilize a comprehensive set of metrics, demonstrating that UCAL-enhanced models achieve superior performance in 82.14% of cases, setting a new state-of-the-art (SOTA). The dataset can be accessed at https://***/TeCSAR-UNCC/HuVAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Object Detection for Vehicles with Yolo 22

Object Detection for Vehicles with Yolo

引用

2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics, SAMI 2024

作者： Maleki, Pouria Ramazani, Abbas Khotanlou, Hassan Ojaghi, Sina Mousavi, Milad Kalinin, Alexey Mosavi, Amir Bu-Ali Sina University Department of Electrical Engineering Hamedan Iran Bu-Ali Sina University Department of Computer Engineering Hamedan Iran University of Tehran School of Computer and Electrical Engineering Tehran Iran K. N. Toosi University of Technology Tehran Iran Abylkas Saginov Karaganda Technical University Kazakhstan Obuda University John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

ISBN: (纸本)9798350317206

The rapid urban population growth has intensified the challenges associated with urban and suburban traffic, necessitating effective traffic control and management. The efficient movement of emergency vehicles, particularly ambulances and fire trucks, has emerged as a critical concern. This article presents the Vehicle Dataset, a comprehensive benchmark for object detection, encompassing seven vehicle classes, including cars, motorcycles, buses, trucks, vans, ambulances, and fire trucks. The dataset, includes 29,759 meticulously labeled images obtained from freely available online sources, enables the identification of traffic patterns through deep neural networks. Notably, the dataset emphasizes the facilitation of emergency vehicle movement. The Vehicle Dataset in this study is divided into three subsets, with 25,369 images assigned for training, 2,896 for validation, and 1,494 for testing. Through the utilization of the dataset, object detection algorithms based on YOLO versions 5, 6, and 7 have been trained. Remarkably, YOLO version 7 has yielded outstanding results, achieving a final precision of 85% and a mAP of 85% at an IoU threshold of 0.5. Moreover, at IoU thresholds ranging from 0.5 to 0.9, a mAP of 64% has been attained. The Vehicle Dataset represents significant resource for researchers and practitioners in the transportation and traffic management field. Its inclusion of emergency vehicles such as ambulances and fire trucks contribute to its unique value. This article presents a detailed exploration of the dataset, underscoring its significance in advancing object detection methodologies. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

On the periodic motions of a one-degree-of-freedom oscillator

引用

SeMA Journal 2024年第3期81卷 479-494页

作者： Kooij, Robert Zegeling, André Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Unit ICT Strategy and Policy TNO (Netherlands Organisation for Applied Scientific Research) The Hague Netherlands College of Mathematics and Statistics Guangxi Normal University Guilin China

We present a mechanical model for an oscillator with one degree of freedom under the influence of a flowing medium. Under fairly general conditions we show that the ensuing differential equation has at most two limit cycles and we give examples where exactly two limit cycles will occur. The implications of this result are that it is possible for a system of this kind to exhibit galloping even when the so-called Den Hartog criterion of local instability is not satisfied. © 2023, The Author(s).

关键词： 34C15 34C25 34C29 73K70 Galloping Limit cycles Liénard system Wind-induced vibrations

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Motion Intention Detection for Robotic Rehabilitation: Evaluating Classification and Regression Algorithms

引用

SN computer Science 2024年第8期5卷 1057页

作者： Khan, Abdul Manan Khan, Fatima Dwivedi, Anshu Kumar Semwal, Vijay Bhaskar Martha, Sheshikala Bijalwan, Vishwanath Department of Aerospace Engineering University of Bristol Bristol United Kingdom Graduate School of Cancer Science and Policy National Cancer Center Ilsan South Korea School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of CSE Maulana Azad National Institute of Technology Bhopal India School of Computer Science & amp Artificial Intelligence SR University Warangal Warangal India Department of Electrical and Electronics Engineering University of West London London United Kingdom

Rehabilitation robots have shown significant efficacy in restoring lost motor functions in stroke survivors by providing compliant assistance during rehabilitation tasks. However, accurately understanding the desired motion intention (DMI) of the subjects is a significant challenge in providing effective robotic assistance. This work aims to determine the desired motion intention (DMI) for compliant robotic assistance through the analysis of upper limb motions using electroencephalography (EEG) signals. A group of fifteen individuals who were in good health carried out six distinct exercises. These movements were categorized using decision trees, random forest, and deep learning algorithms. Using deep learning, we achieved the highest accuracy rates, reaching 82% for movement-to-movement classification and 90% for movement-to-rest classification. The random forest method achieved superior performance compared to the other algorithms in regression tests, with an accuracy rate of 83%. The results demonstrate the effectiveness of our proposed EEG-based classification and regression techniques in detecting DMI for robotic help in *** study was conducted with a small sample size, exclusively involving healthy subjects, which is a critical factor to consider. This may limit the generalizability of the results, particularly when populations with motor impairments are taken into account. However, the study offers valuable insights into the potential of the EEG-based models for real-time rehabilitation applications despite this limitation. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： C-RNN Deep learning Desired motion intention EEG signals Machine learning Rehabilitation

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：