检索结果-内蒙古大学图书馆

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Liu, Ganjun Hou, Xiaohui Ge, Meng Zhang, Tao Li, Haizhou School of Electrical and Information Engineering Tianjin University Tianjin China School of Date Science Chinese University of HongKong Shenzhen China Saw Swee Hock School of Public Health National University of Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (纸本)9798400701726

AI-driven severity assessment techniques for dysarthric disorders show promise in aiding speech-language pathologists with diagnostics and therapeutic follow-ups for patients. Existing solutions generally focus on the average intelligibility and hoarseness of the individual speaker’s speech (i.e., speaker-level classification). This potentially ignores the slight variations in pronunciation attributed to the speaker’s dysarthric disorders, e.g., /t/ and /d/. To address this issue, we rethink the inherent differences in the dysarthria speech, and propose a non-intrusive severity assessment approach called DysarNet. Specifically, we first design a prosodic emphasis module based on frame-level speech features to highlight the fine-grained temporal changes including pronunciation content, rhythm, and timing. Second, we design a multi-scale aggregation strategy to collect statistical cues on articulatory information at different scales, i.e., frame-level and utterance-level. By doing so, multi-scale prosody and articulatory cues are directly assist the prediction network for assessing dysarthria severity from multiple views, and naturally achieve speaker-independent generalization ability. Experimental results on VCC 2018 and TORGO datasets show that our DysarNet excels in assessing dysarthria severity. © 2024 Copyright held by the owner/author(s). publication rights licensed to ACM.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Machine Learning Classification of Snowflakes to Enhance Microphysical and Scattering Characterization of Snow

Machine Learning Classification of Snowflakes to Enhance Mic...

引用

2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2023

作者： Thant, Hein Zhizhin, Mikhail Notaros, Branislav M. Colorado State University Electrical & Computer Engineering Dept. Fort CollinsCO United States Colorado School of Mines Payne Institute for Public Policy GoldenCO United States

ISBN: (纸本)9781665442282

No two snowflakes are alike. However, they can be classified into over a hundred different categories based on their geometry. Recent developments in machine learning algorithms have led to the possibility of automatically classifying more classes of snowflakes more accurately and efficiently. We present supervised and unsupervised learning approaches to snowflake classification coupled with dimensional reduction techniques. Proper automatic and detailed classification of ice and snow hydrometeors enables advanced characterization of geometrical, microphysical, and scattering properties of particles, which, in turn, is essential for development of radar-based quantitative precipitation estimation of snow. © 2023 IEEE.

关键词： Snow

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

Miniaturization of High Voltage Power Supply for Portable Electrostatic Filtration 50

Miniaturization of High Voltage Power Supply for Portable El...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Wang, Jia Hao Yu, Cynthia Urquhart, Cameron Hernke, Zane Espelien, Jan Leuca Simpson, Christopher Novosselov, Igor Mamishev, Alexander SpectTree LLC SeattleWA United States Department of Electrical and Computer Engineering University of Washington SeattleWA United States School of Public Health University of Washington SeattleWA United States Dept. of Electrical Engineering Columbia University New YorkNY United States Department of Mechanical Engineering University of Washington SeattleWA United States

ISBN: (纸本)9781665464543

Electrostatic Precipitation (ESP) is an effective method of removing particulates from the air. It is currently used in many large-scale industrial applications but sees limited use in smaller-scale cases due to the difficulty of generating high voltage in small packages. Additionally, safety concerns prevent the widespread use of this effective technique. This paper presents the motivation, design, and evaluation of a miniature high-voltage DC (HVDC) power supply for applications in small-scale ESP systems. The power supply's potential for portable ESP application is tested on a personal protective device, the so-called Smart, Individualized, Noncontact, Extended-Wear (SINEW) mask. The results show that the power supply operates with acceptable efficiency and generates high voltages and power necessary to drive ESP setups in practical applications. © 2024 IEEE.

关键词： Electrostatic precipitators

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

Carbon-neutral pathway to mitigating transport-power grid cross-sector effects

引用

The Innovation 2024年第3期5卷 27-29页

作者： Jing Ma Huiwen Kong Jianxiao Wang Haiwang Zhong Bo Li Jie Song Daniel M.Kammen State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Electrical and Electronic EngineeringNorth China Electric Power UniversityBeijing 102206China National Engineering Laboratory for Big Data Analysis and Applications Peking UniversityBeijing 100871China Peking University Ordos Research Institute of Energy Ordos 017000China State Key Laboratory of Power Systems and Generation Equipment Department of Electrical EngineeringTsinghua UniversityBeijing 100084China School of Electrical Engineering Guangxi UniversityNanning 530004China Department of Industrial Engineering and Management College of EngineeringPeking UniversityBeijing 100871China Energy and Resources Group and Goldman School of Public PolicyUniversity of CaliforniaBerkeleyBerkeleyCA 94720USA

Dear Editor,The growing demand for transportation energy has brought increasing challenges to reducing greenhouse gas ***,many countries or regions have proposed solutions to achieve carbon-neutral transportation such as the rapid expansion of the global electric vehicle(EV)***,these benefits are not *** the goal of decarbonization in electricity is achieved,the“pseudo net zero emissions”effect of the transportation sector will inevitably be accompanied by a quiet shifting of carbon responsibility.1 This shift is undoubtedly fatal for both net zero emissions at the national level and carbon responsibility at the industry level;however,the corresponding effects have not yet been clarified.

关键词： neutral doubt shifting

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Deep Learning Algorithms in Twitter Bot Detection 5

Performance Comparison of Deep Learning Algorithms in Twitte...

引用

5th College of Science International Conference on Recent Trends in Information Technology, CSCTIT 2022

作者： Al-Ibadi, Samer Emad Neama Cevik, Mesut Altinbas University Department of Electrical and Computer Engineering Istanbul Turkey Information and Telecom Public Company Ministry of Communications Baghdad Iraq Altinbas University Istanbul Turkey Electrical and Computer Engineering Department Istanbul Turkey

ISBN: (纸本)9798350334920

Difficulty in detecting social media bots - software-controlled accounts that seem as human - has serious consequences. Bots have been used to affect the financial market, political elections, and spreading conspiracy theories. Most approaches detect bots at the account level by studying social media posts and using network structure, system dynamics, content analytics, etc. In this study, we compare the performance of the recurrent neural network (RNN), convolutional neural network (CNN), and feed forward neural network (FNN) in detecting Twitter bots by evaluating the textual content of 10,416,240 tweets from humans and bots. Deep learning models utilize sample data to gauge performance. The CNN model identified recent social bot samples most accurately (97.67 %). In comparison, the RNN model achieved great accuracy (97.04 %) with a longer training time. RNN and CNN algorithms perform well when compared to other deep learning classifiers. © 2022 IEEE.

关键词： Recurrent neural networks

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：