检索结果-内蒙古大学图书馆

International conference on advanced Materials for Innovation and Sustainability (ICAMIS)

作者： Kumar, Sudhir Kumar, Dilip Sant Longowal Inst Engn & Technol Dept Elect & Commun Engn Longowal 148106 Punjab India

In this paper a novel hollow core photonic crystal fiber (PCF) sensor is presented which provides extremely high sensitivity and low confinement loss for liquid and chemical sensing applications. We examined the efficiency of the proposed PCF structure for liquids with wide range of refractive indices i.e., 1.484-1.534. The numerical investigation of the PCF is executed by the finite element method (FEM). The structure is designed by considering circular airhole in the core instead of an elliptical airhole to decrease the fabrication complexity. The investigation is carried out for a wide wavelength range from 0.8 to1.8 mu m. In the simulation results based on FEM, we observed that the constructed PCF offers a high sensitivity of 95.64%, 96.20%, and 98% while low confinement loss of 1.13 x 10(-16) dB/m, 8.5 x 10(-17) dB/m and 5.3 x 10(-17) dB/m respectively for n = 1.484, n = 1.5 and n = 1.534 at 1.3 mu m operating wavelength. Thus, the proposed PCF can be used widely for liquid chemical detection in biosensing and commercial applications. Copyright (c) 2022 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the International conference on advanced Materials for Innovation and Sustainability.

关键词： Optical fiber PCF Hollow core FEM Liquid sensing Refractive index Materials

来源：评论

学校读者我要写书评

暂无评论

Development of Machine Intelligence for Self-Driving Vehicles Through Video Capturing

Development of Machine Intelligence for Self-Driving Vehicle...

引用

IEEE/ASME International conference on Mechtronic and Embedded systems and applications, MESA

作者： Jordon Lowe Kaya Kuru School of Engineering and Computing University of Central Lancashire Preston UK

ISBN: (数字)9798331516239

ISBN: (纸本)9798331516246

The automation of vehicles is progressing through several automation levels, with the goal of reaching full autonomy, i.e. level 5, which involves no steering wheel, brakes, pedals, or windshield. This is achieved by the vehicle taking on an increasing number of autonomous decision-making tasks under the guidance of smart control systems that are instilled with Artificial Intelligence (AI) and equipped with advanced sensor and actuator technologies. Major vehicle companies are competing to build the most talented driver, i.e. AI-agent. In this report, how the intelligence of Self-Driving Vehicles (SDVs) is being built by the automotive industry for the efficient deployment of handover wheels is analysed and applications of machine intelligence for SDVs are implemented through video capturing using Deep Learning (DL). The results show that i) the use of DL techniques as well as reinforcement learning (RL) – Deep RL approaches – can contribute to the intelligence of SDVs significantly and ii) SDVs, equipped with advanced mechatronics systems, can be fully autonomous with the level-5 automation as they are trained appropriately with proper datasets.

关键词： Industries Automation Mechatronics Embedded systems Wheels Reinforcement learning Handover Artificial intelligence Machine intelligence Vehicles

来源：评论

学校读者我要写书评

暂无评论

Research advanced in the visual SLAM methods under indoor environment 2

Research advanced in the visual SLAM methods under indoor en...

引用

2nd International conference on Computing Innovation and Applied Physics, CONF-CIAP 2023

作者： Lu, Zhengsheng Wang, Jinchang Zhang, Zelin Zhu, Conghua Virginia Polytechnic Institute and State University 24060 United States Shangqiu Normal University 476000 China Tongji University 201804 China University of Nottingham NG7 2QL United Kingdom

Simultaneous localization and mapping (SLAM) have been a hotspot study topic in the computer vision community these days, which aims to locate the agent's position and perceive the surrounding environment to build a map. In Visual SLAM, the camera is the external sensor used, creating an environment map while locating itself. Compared with radar and other rangefinders, the visual sensor is usually tiny and has low power consumption, which has been the mainstream framework in SLAM research task. This paper starts from the system overview of visual SLAM, introduces the landmark achievements and research hotspots of visual SLAM, and discusses the key issues and three research methods based on visual SLAM in indoor environment. Meanwhile, the applications of visual SLAM in dynamic scenes and large indoor environments are listed. Finally, the trend of its future development is prospected. © Published under licence by IOP Publishing Ltd.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

Stone Soup open source framework for tracking and state estimation: enhancements and applications 31

Stone Soup open source framework for tracking and state esti...

引用

conference on Signal Processing, sensor/Information Fusion, and Target Recognition xxxI

作者： Barr, Jordi Harrald, Oliver Hiscocks, Steven Perree, Nicola Pritchett, Henry Vidal, Sebastien Wright, James Carniglia, Peter Hunter, Emily Kirkland, David Raval, Divy Zheng, Siyuan Young, Anne Balaji, Bhashyam Maskell, Simon Hernandez, Marcel Vladimirov, Lyudmil Def Sci & Technol Lab London England Def Res & Dev Canada Toronto ON Canada Univ Liverpool Liverpool Merseyside England

ISBN: (数字)9781510651210

ISBN: (纸本)9781510651210;9781510651203

The tracking and state estimation community is broad, with diverse interests. These range from algorithmic research and development, applications to solve specific problems, to systems integration. Yet until recently, in contrast to similar communities, few tools for common development and testing were widespread. This was the motivation for the development of Stone Soup - the open source tracking and state estimation framework. The goal of Stone Soup is to conceive the solution of any tracking problem as a machine. This machine is built from components of varying degrees of sophistication for a particular purpose. The encapsulated nature and modularity of these components allow efficiency and reuse. Metrics give confidence in evaluation. The open nature of the code promotes collaboration. In April 2019, the Stone Soup initial beta version (v0.1b) was released, and though development continues apace, the framework is stable, versioned and subject to review. In this paper, we summarise the key features of and enhancements to Stone Soup - much advanced since the original beta release - and highlight several uses to which Stone Soup has been applied. These include a drone data fusion challenge, sensor management, target classification, and multi-object tracking in video using TensorFlow object detection. We also detail introductory and tutorial information of interest to a new user.

关键词： open source tracking state estimation drone tracking data fusion sensor management classification video tracking

来源：评论

学校读者我要写书评

暂无评论

MoDD: A Model-Driven Framework for Data Collection in Drone-Based systems

MoDD: A Model-Driven Framework for Data Collection in Drone-...

引用

Euromicro conference on Software Engineering and advanced applications (SEAA)

作者： Manele Ait Habouche Mickaël Kerboeuf Goulven Guillou Jean-Philippe Babau Université de Bretagne Occidentale Brest France

ISBN: (数字)9798350380262

ISBN: (纸本)9798350380279

Nowadays, Cyber-Physical systems (CPS), particularly drones, play a pivotal role in environmental research. Scientists depend on these platforms to monitor various sensor data and ensure comprehensive data archiving. However, despite their advantages, researchers encounter several challenges, including communication limitations and the complexity of setting up systems tailored to their needs. To address these issues, we propose MoDD, a model-driven data collection framework based on a customized publish/subscribe model. MoDD simplifies the development and configuration of data collection systems. It offers scientists a solution that meets their specific needs, allowing them to focus on high-level requirements while the framework manages the underlying complexities. We demonstrate the effectiveness of MoDD through practical evaluations on an actual Unmanned Surface Vehicle. Additionally, results show a 79% reduction in throughput (drone to base station link) compared to existing publish/subscribe systems.

关键词： Computer architecture Data collection Throughput Routing Data models Complexity theory Usability Monitoring Drones Software engineering

来源：评论

学校读者我要写书评

暂无评论

LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models 24

LazyDP: Co-Designing Algorithm-Software for Scalable Trainin...

引用

29th ACM International conference on Architectural Support for Programming Languages and Operating systems (ASPLOS)

作者： Lim, Juntaek Kwon, Youngeun Hwang, Ranggi Maeng, Kiwan Suh, G. Edward Rhu, Minsoo Korea Adv Inst Sci & Technol Daejeon South Korea Penn State Univ University Pk PA 16802 USA Cornell Univ Ithaca NY USA Meta FAIR Menlo Pk CA USA

ISBN: (纸本)9798400703850

Differential privacy (DP) is widely being employed in the industry as a practical standard for privacy protection. While private training of computer vision or natural language processing applications has been studied extensively, the computational challenges of training of recommender systems (RecSys) with DP have not been explored. In this work, we first present our detailed characterization of private RecSys training using DP-SGD, root-causing its several performance bottlenecks. Specifically, we identify DP-SGD's noise sampling and noisy gradient update stage to suffer from a severe compute and memory bandwidth limitation, respectively, causing significant performance overhead in training private RecSys. Based on these findings, we propose LazyDP, an algorithm-software co-design that addresses the compute and memory challenges of training RecSys with DP-SGD. Compared to a state-of-the-art DP-SGD training system, we demonstrate that LazyDP provides an average 119x training throughput improvement while also ensuring mathematically equivalent, differentially private RecSys models to be trained.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Context-aware assistive driving: an overview of techniques for mitigating the risks of driver in real-time driving environment

引用

INTERNATIONAL JOURNAL OF PERVASIVE COMPUTING AND COMMUNICATIONS 2023年第3期19卷 325-342页

作者： Gite, Shilpa Kotecha, Ketan Ghinea, Gheorghita Symbiosis Int Deemed Univ Symbiosis Ctr Appl AI SCAAI Symbiosis Inst Technol Comp Sci Dept Pune Maharashtra India Brunel Univ Dept Comp Sci London England

Purpose This study aims to analyze driver risks in the driving environment. A complete analysis of context aware assistive driving techniques. Context awareness in assistive driving by probabilistic modeling techniques. advanced techniques using Spatio-temporal techniques, computer vision and deep learning techniques. Design/methodology/approach Autonomous vehicles have been aimed to increase driver safety by introducing vehicle control from the driver to advanced Driver Assistance systems (ADAS). The core objective of these systems is to cut down on road accidents by helping the user in various ways. Early anticipation of a particular action would give a prior benefit to the driver to successfully handle the dangers on the road. In this paper, the advancements that have taken place in the use of multi-modal machine learning for assistive driving systems are surveyed. The aim is to help elucidate the recent progress and techniques in the field while also identifying the scope for further research and improvement. The authors take an overview of context-aware driver assistance systems that alert drivers in case of maneuvers by taking advantage of multi-modal human processing to better safety and drivability. Findings There has been a huge improvement and investment in ADAS being a key concept for road safety. In such applications, data is processed and information is extracted from multiple data sources, thus requiring training of machine learning algorithms in a multi-modal style. The domain is fast gaining traction owing to its applications across multiple disciplines with crucial gains. Research limitations/implications The research is focused on deep learning and computer vision-based techniques to generate a context for assistive driving and it would definitely adopt by the ADAS manufacturers. Social implications As context-aware assistive driving would work in real-time and it would save the lives of many drivers, pedestrians. Originality/value This paper provi

关键词： Deep learning Assistive driving Context-aware systems Driver activity anticipation Driver activity recognition Multi-sensor data fusion

来源：评论

学校读者我要写书评

暂无评论

In vivo brain tumor classification using fiber endoscopy 22

In vivo brain tumor classification using fiber endoscopy

引用

conference on advanced Biomedical and Clinical Diagnostic and Surgical Guidance systems xxII

作者： Dremel, J. Wang, T. Richter, S. Uckermann, O. Polanski, W. Eyuepoglu, I. Czarske, J. Kuschmierz, R. Tech Univ Dresden Lab Measurement & Sensor Syst Tech Dresden Germany Tech Univ Dresden BIOLAS Biomed Computat Laser Syst Dresden Germany Tech Univ Dresden EKFZ Else Kroner Fresenius Zentrum Digital Hlth Dresden Germany Tech Univ Dresden Univ Hosp Carl Gustav Carus Dept Neurosurg Dresden Germany Tech Univ Dresden Fac Med Div Med Biol Dept Psychiat Dresden Germany Tech Univ Dresden Univ Hosp Carl Gustav Carus Dresden Germany

ISBN: (纸本)9781510669222;9781510669215

The classification of brain tissue plays a key role in brain tumor diagnosis and treatment. It revolves around post-surgical histochemical staining, which is often time consuming and delays follow up treatment. Identifying tumor boarders during tumor resection is essential for an efficient therapy minimizing removed healthy tissue and maximizing removed tumor tissue. The different approaches in use are either expensive and time consuming or limited to certain tumor types. We propose a real-time in vivo label free classification approach, applicable for both demands. Based on autofluorescence properties, a label-free differentiation between tissue types is possible. Therefore, a multicore fiber (MCF) based endoscope is designed to fit into biopsy needles used during diagnosis and to be used as a handheld probe during tumor resection. It allows illuminating and imaging through the same MCF, minimizing the endoscope to a submillimeter diameter. Currently, autofluorescence images are not used in pathology. Thus, medical doctors cannot interpret them. We use a neural network for diagnosis, bridging this gap. One problem with neural networks in medical applications is data availability for training. Different techniques are investigated to maximize the classification performance with a limited training dataset. Cascaded neural networks in combination with digital twins improve the results while lowering the needed training dataset size. The preliminary data indicates that our technology might lead to a paradigm shift in brain tumor diagnosis and therapy due to the accurate result, the versatile design, and being low-cost.

关键词： tissue classification lensless endoscopy fiber bundle imaging deep learning

来源：评论

学校读者我要写书评

暂无评论

The Comparison of the Reliability Performance of Different Top Metal Materials in MEMS applications

The Comparison of the Reliability Performance of Different T...

引用

2024 Pan Pacific Strategic Electronics Symposium, Pan Pacific 2024

作者： Hein, Verena Weide-Zaage, Kirsten Clausner, Andre X-FAB Global Services GmbH Erfurt Germany Leibniz Universität Hannover Hannover Germany Fraunhofer-Institut für Keramische Technologien und Systeme IKTS Microelectronic Materials and Nanoanalysis Dresden Germany

ISBN: (纸本)9781944543204

The combination of analog/mixed-signal, high-voltage and embedded non-volatile memory options with sensor and actuator integration is still common in automotive, industrial, communication and medical applications. MEMS with or without integrated CMOS, 3D integration micro transfer printing and integrated microfluid systems are in use to realize such applications. The established top metal interconnect materials for analog/mixed-signal CMOS applications are thick Aluminum (AlCu with Titan and Titanium Nitride) and thick Copper. Integrated noble metal electrodes are necessary for MEMS applications like microfluidics. The reliability requirements of a CMOS/ MEMS process differs from a long storage shelf life at room temperature, long life time for medical (in-body) or space applications up to high operating conditions for automotive and industrial applications like oil drilling. applications, like functional surfaces, combine integrated circuits for example for next generation DNA sequencing. The noble metals for electrodes on top are thinner for such applications. An additional reliability challenge for such a lab on a chip is corrosion. Automotive applications have often mission profiles which need high currents, high temperature and a growing mechanical stability. The reliability of noble top metals is more and more under investigation because MEMS are more common in automotive products. The knowledge about reliability especially about mechanical properties is an interesting topic in addition to the results from standard tests like electro migration and stress migration tests because of the advanced mechanical stress in the applications and the danger of corrosion. The comparison of the electromigration performance and mechanical stability of AlCu, Copper, Gold and Platinum as thick and/ or top metal tracks is necessary to evaluate and assess the suitability of the materials for the different applications. The possibilities to generate test results for thick and or

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

An Introduction to Machine Learning Lifecycle Ontology and Its applications 43rd

An Introduction to Machine Learning Lifecycle Ontology and I...

引用

43rd IFIP WG 5.7 International conference on Advances in Production Management systems (APMS)

作者： Drobnjakovic, Milos Charoenwut, Perawit Nikolov, Ana Oh, Hakju Kulvatunyou, Boonserm Natl Inst Stand & Technol Engn Lab Gaithersburg MD 20899 USA

ISBN: (纸本)9783031716393;9783031716379;9783031716362

MachineLearning (ML) adoption is on the rapid rise, with a nearly40% compound annual growth rate over the next decade. In otherwords, companies will be flooded with ML models developed with different datasets and software. The ability to have information at one's fingertips about how these ML models were developed, what they were used for, what their performances and uncertainties are, what their internal structure looks like, and what datasets were used can have several benefits. These pieces of ML metadata are what we collectively call ML lifecycle information. This paper explains our current research into developing an ML Lifecycle Ontology (MLLO) to capture such information in a knowledge graph. The main objective of this paper is to describe the motivation through use cases and show that future research is warranted. To that end, basic and advanced use scenarios are described. MLLO is then introduced at a high level and validated with the basic use case to show its value. We then describe future work we are undergoing to demonstrate the hypotheses in the advanced use case in which MLLO not only serves as a standard queryable representation of ML metadata across different ML software but also as a connector to domain knowledge to assist in the ML model development and reuse.

关键词： Machine Learning Ontology Knowledge Graph Machine Learning Lifecycle Management Biomanufacturing

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：