检索结果-内蒙古大学图书馆

conference on Signal Processing, sensor/Information fusion, and Target Recognition XXVIII

作者： Blasch, Erik Air Force Res Lab Arlington VA 22203 USA

ISBN: (纸本)9781510627024

Complex systems are composed from various networks such as physical, computer, cyber, communication, cognitive, and social systems. Information fusion can support complex systems uncertainty analysis for various infrastructures applications such as electrical power grids, human-machine coordination, and urban systems. In addition, advances in artificial intelligence (AI), machine learning (ML), and data mining;along with information fusion provide a big data approach for multidomain complex systems analysis. The presentation position focuses on the Dynamic Data Driven applications Systems (DDDAS) paradigm that brings together high-dimensional network models, real-time data measurement processing, and uncertainty quantification to support infrastructure network analysis. The challenges of applying information fusion to infrastructure system include multi-dimensional models, asynchronous measurement updates, human-machine architectures, communication protocols, and user awareness support.

关键词： Information fusion big data complex systems Dynamic Data Driven applications Systems

来源：评论

学校读者我要写书评

暂无评论

Intelligent fault diagnosis of surface level defects in stainless steel plates through fused sensor data

引用

AIP conference Proceedings 2024年第1期3217卷

作者： Savita Sindhu Anisha Nagpal Ajay Kumar Namrata Dogra Sangita Rani Parveen Kumar Rupayali Swaroop Manav Rachna International Institute of Research and Studies Faridabad Haryana India Department of Mechanical Engineering School of Engineering & Technology JECRC University Jaipur - 303 905 India Department of Orthodontics Faculty of Dental Sciences SGT University Gurugram Haryana India 122505 Department of Computer Science &amp Engineering World college of Technology and Management Gurugram Haryana India Department of Mechanical Engineering Rawal Institute of Engineering and Technology Faridabad Haryana India Department of Computer Science and Engineering School of Engineering & Technology JECRC University Jaipur - 303 905 India

IoT based condition monitoring has acclaimed a remarkable place in the predictive maintenance of industrial applications. Most of the methods, use data driven strategies like Machine Learning and Deep Learning to learn the patterns in the past data to predict the faults from their early warning signs. The industrial applications demand the deployment of heterogeneous sensors at various locations, making its interpretability a difficult process. Also, most of the ML algorithms explore the data space in a more normalized fashion, thus treating every feature in same way. The proposed work uses a sensor fusion technique based on coefficient of weighted variance to assign higher weights to sensors that shows significant deviation. This method is used to predict the surface level faults of steel plates by examining 27 sensor values. A comparative analysis of some of the important intelligent ML algorithms that operates on the fused data is done. The results delineates that a profound betterment in classification metrics can be seen in classifying the fault class of the steel plates.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LogTrans: Providing Efficient Local-Global fusion with Transformer and CNN Parallel Network for Biomedical Image Segmentation

LogTrans: Providing Efficient Local-Global Fusion with Trans...

引用

IEEE International conference on High Performance Computing and Communications (HPCC)

作者： Xingqing Nie Xiaogen Zhou Zhiqiang Li Luoyan Wang Xingtao Lin Tong Tong College of Physics and Information Engineering Fuzhou University Fuzhou China Fujian Key Lab of Medical Instrumentation and Pharmaceutical Technology Fuzhou University Fuzhou China Imperial Vision Technology Fuzhou China

Accurate biomedical image segmentation is a prerequisite for excellent computer-aided diagnosis (CAD) systems. A series of researches have shown that convolutional neural networks (CNNs) have made impressive progress in segmentation tasks. Nevertheless, owing to the finite receptive field of CNN-based algorithms, such networks are focused too much on local area features rather than global context. While the Transformer architecture can encode global dependencies information through the self-attention mechanism, this mechanism typically ignores the local pixel-level structural information within each divided patch. Therefore, a better solution is still needed for how to integrate CNN architecture with Transformer architecture efficiently. In this essay, we propose an originative parallel segmentation algorithm called LogTrans. First, in the encoder path, the local details and global contour dependencies on the entire image are captured by the CNN branch and the Transformer branch, respectively. Then these two branches complement each other by a novel separate-combiner (SeCo) module, leading to better fused features. Moreover, we attempt to further enhance the segmentation properties by using a residual stackable dilated (ReS $D$ ) block, which applies residual shortcut connections to resolve dimension alterations in the target region and stacks dilated convolutions to capture more spatial information. The proposed LogTrans framework was evaluated on two biomedical datasets, including ISIC-2017 and UITNS-2022 datasets. Collectively, multiple results have indicated that our LogTrans performs superior with other state-of-the-art architectures in both visual comparison and quantitative appraisal.

关键词： Image segmentation Visualization Fuses Transformers Decoding Image restoration Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

In-Class Vehicle Categorization Using Standard Convolutional Neural Networks Via Fiber Bragg Grating sensor Array

In-Class Vehicle Categorization Using Standard Convolutional...

引用

International conference on Emerging eLearning Technologies and applications (ICETA)

作者： Patrik Kamencay Daniel Benedikovic Jozef Dubovan Miroslav Markovic Milan Dado Faculty of Electrical Engineering and Information Technology University of Žilina Žilina Slovakia

ISBN: (纸本)9781665421034

Internet of Things is a key innovation that will shape future systems, especially in future data-hungry applications. this mostly includes sensing, communication, biomedicine as well as smart buildings, military or automotive 4.0 industry, among other surging application areas. Internet of Things leverages the fact that inherently different physical systems are combined together, alongside with modern machine learning algorithms. To date, the IoT technology is ubiquitous for automotive domain due to its profound impact on vehicle classification, instant on-road control, or smart traffic management. In this work, we evaluate a fiber Bragg grating based dataset by using established open-access convolutional neural networks (AlexNet, GoogLeNet, and ResNet-50), enabling an effective vehicle categorization. In particular, we show that individual fiber Bragg grating technological platform can offer good detection accuracies for passing vehicles using standard convolutional neural networks. In this case, we obtained classification precisions between 34% - 62% for AlexNet, 51% - 77% for GoogleNet and 57% - 78% for ResNet-50 architectures. Those detection accuracy levels are sufficiently high to pave a promising way for effective car categorization using passive fiber Bragg grating technology coupled with standard and open-access neural networks.

关键词： Bragg gratings Technological innovation Smart buildings Shape sensors Internet of Things Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

6th Latin American High Performance Computing conference, CARLA 2019

6th Latin American High Performance Computing Conference, CA...

引用

6th Latin American High Performance Computing conference, CARLA 2019

ISBN: (纸本)9783030410049

The proceedings contain 32 papers. The special focus in this conference is on High Performance Computing conference. The topics include: Assessing Kokkos Performance on Selected architectures;Improving the Simulation of Biologically Accurate Neural Networks Using Data Flow HLS Transformations on Heterogeneous SoC-FPGA Platforms;Delivering Scalable Deep Learning to Research with Bridges-AI;towards a Platform to Evaluate the Impact of Resource Information Distribution in IoT Environments;GPU Support for Automatic Generation of Finite-Differences Stencil Kernels;adding Probabilistic Certainty to Improve Performance of Convolutional Neural Networks;assessing the Impact of a Preprocessing Stage on Deep Learning architectures for Breast Tumor Multi-class Classification with Histopathological Images;assessing the Robustness of Recurrent Neural Networks to Enhance the Spectrum of Reverberated Speech;collaborative Development and Use of Scientific applications in Orlando Tools: Integration, Delivery, and Deployment;a Performance Evaluation of Several Artificial Neural Networks for Mapping Speech Spectrum Parameters;using Cluster Analysis to Assess the Impact of Dataset Heterogeneity on Deep Convolutional Network Accuracy: A First Glance;evolutionary Approach for Bus Synchronization;autonomous Flight of Unmanned Aerial Vehicles Using Evolutionary algorithms;an Experimental Study on Fundamental Frequency Detection in Reverberated Speech with Pre-trained Recurrent Neural Networks;measuring the Effect of Reverberation on Statistical Parametric Speech Synthesis;enhancing Speech Recorded from a Wearable sensor Using a Collection of Autoencoders;Insight GT: A Public, Fast, Web Image Ground Truth Authoring Tool;comparison of Four Automatic Classifiers for Cancer Cell Phenotypes Using M-Phase Features Extracted from Brightfield Microscopy Images;Matching of EM Map Segments to Structurally-Relevant Bio-molecular Regions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

64X48 PIXEL BACKSIDE ILLUMINATED SPAD DETECTOR ARRAY FOR LIDAR applications 17

64X48 PIXEL BACKSIDE ILLUMINATED SPAD DETECTOR ARRAY FOR LID...

引用

conference on Quantum Sensing and Nano Electronics and Photonics XVII part of SPIE OPTO conference

作者： Ruskowski, Jennifer Thattil, Charles Drewes, Jan H. Brockherde, Werner Fraunhofer Inst Microelect Circuits & Syst Fraunh Finkenstr 61 D-47057 Duisburg Germany

ISBN: (纸本)9781510633407;9781510633391

LiDAR sensors in applications like autonomous driving, human-robot-collaboration, or logistics have to be robust, low-cost, and reliable. While several LiDAR architectures and methods are currently tested in the field, the improvement of individual system components, including photon detectors and laser sources, are part of ongoing scientific work. The detector presented here is a CMOS integrated SPAD (single photon avalanche diodes) array device employing a new groundbreaking technology. Backside illuminated SPADs are fabricated and bonded wafer-to-wafer onto a smart ROIC (read-out IC), combining state-of-the-art circuitry and algorithms in a single device. With 64x48 pixels the novel detector test vehicle paves the way for near-future LiDAR devices. The detector comprises a state-of-the-art time-to-digital converter (TDC) architecture for accurate time-of-flight (ToF) measurements with one TDC shared among 4 pixels. The TDC provides a time resolution of 312.5 ps and has a measurement range up to 192 m. Furthermore, the sensor supports switching of the acquisition modes between timing, counting, and time gating modes. The integrated background-light rejection algorithm, presented earlier in a previous device, allows about 66% higher maximum measurement ranges in environments with a high level of ambient light. The large pixel pitch of 125 mu m is actually limited by the ROIC manufactured in a 350 nm CMOS process. Thus, with smaller CMOS feature sizes for the ROIC, the pixel count can be scaled up drastically in future devices without changing the detection principle or the architecture of the SPAD detector array.

关键词： SPAD LiDAR time-of-flight 3D Integration Backside-illuminated SPADs Time-to-Digital Converter

来源：评论

学校读者我要写书评

暂无评论

A comprehensive review of wireless sensor networks: applications, challenges, radio technologies, and protocols

引用

AIP conference Proceedings 2023年第1期2834卷

作者： Fadhil Mohammad Salman Software Department College of Information Technology University of Babylon Babylon Iraq

Recently, significant advances in digital sensing technology and wireless communications have led to the production of small-scale smart sensors that have the ability to sense physical changes in different environments and convert them into digital signals that are collected in one central location. These networks are called wireless sensor networks (WSNs) because they have the ability to wirelessly communicate with each other for the purpose of passing data between them and deliver it to the central station. Wireless sensor networks have great importance in human environments, as they are used to monitor and record physical changes in environments that are not accessible to humans, such as environments with very high temperatures, or in cases of chemical environmental pollution, in forests and seas as well as in deep layers of earth to monitor seismic and volcanic activity. In view of the great importance of wireless sensor networks and their obvious impact on human life, and for the purpose of providing researchers with brief and complete information about these networks, we have presented this paper that briefly reviews what sensor networks are, their specifications, applications and the challenges they face. This paper also included most of the radio communication techniques used in sensor architectures. As well as touching on the most important routing algorithms in "WSNs" and their classifications with a comparison of their performance. Finally, this paper provided an overview of research trends that could lead to significant technological development and beneficial growth to overcome the challenges of wireless sensor networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SACoD: sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powe...

引用

International conference on Computer Vision (ICCV)

作者： Yonggan Fu Yang Zhang Yue Wang Zhihan Lu Vivek Boominathan Ashok Veeraraghavan Yingyan Lin Rice University MIT-IBM Watson AI Lab

ISBN: (纸本)9781665428132

There has been a booming demand for integrating Convolutional Neural Networks (CNNs) powered functionalities into Internet-of-Thing (IoT) devices to enable ubiquitous intelligent "IoT cameras". However, more extensive applications of such IoT systems are still limited by two challenges. First, some applications, especially medicine-and wearable-related ones, impose stringent requirements on the camera form factor. Second, powerful CNNs often require considerable storage and energy cost, whereas IoT devices often suffer from limited resources. PhlatCam, with its form factor potentially reduced by orders of magnitude, has emerged as a promising solution to the first aforementioned challenge, while the second one remains a bottleneck. Existing compression techniques, which can potentially tackle the second challenge, are far from realizing the full potential in storage and energy reduction, because they mostly focus on the CNN algorithm itself. To this end, this work proposes SACoD, a sensor Algorithm Co-Design framework to develop more efficient CNN-powered PhlatCam. In particular, the mask coded in the Phlat-Cam sensor and the backend CNN model are jointly optimized in terms of both model parameters and architectures via differential neural architecture search. Extensive experiments including both simulation and physical measurement on manufactured masks show that the proposed SACoD framework achieves aggressive model compression and energy savings while maintaining or even boosting the task accuracy, when benchmarking over two state-of-the-art (SOTA) designs with six datasets across four different vision tasks including classification, segmentation, image translation, and face recognition. Our codes are available at: https://***/RICE-EIC/SACoD.

关键词： Image segmentation Computer architecture Cameras Particle measurements Classification algorithms Convolutional neural networks Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Using Time-of-Flight sensors for People Counting applications 13

Using Time-of-Flight Sensors for People Counting Application...

引用

conference on Design and architectures for Signal and Image Processing (DASIP)

作者： Stec, Michal Herrmann, Viktor Stabernack, Benno HHI Fraunhofer Heinrich Hertz Inst Embedded Syst Grp Berlin Germany Univ Potsdam Embedded Syst Architectures Signal Proc Potsdam Germany

ISBN: (纸本)9781728140742

Precisely detecting and counting people who are using public transportation is one of the key methods for predicting and planning an efficient use of buses, trams and trains. Providing an effective, well-planned public transportation service is not only important for economic reasons. It also helps to tackle a variety of environmental problems and contributes to a reduction of traffic congestion in urban areas. A couple of such systems had been developed in the past. Those were not sufficiently precise, however. In most cases, these systems rely on data processing generated by one particular type of a 2D image sensor. In this paper we present a robust people counting application, which runs on embedded systems with reasonable requirements as far as computational power is concerned and relies on the processing of 3D data generated by a Time-of-Flight (ToF) sensor. Processing of time-of-flight data requires a couple of preprocessing steps, which is crucial for the subsequent people detection, tracking and counting algorithms. The influence of these preprocessing steps and the effect on the developed detection algorithm are presented. Methods of avoiding misinterpretations by the detection algorithms are discussed. A detailed description of the core algorithms which were developed to process 3D data is provided. An overview will be given on how this method could be further enhanced for the purpose of detecting and differentiating vital and non-vital objects.

关键词： Time-of-Flight 3D Vision People Detection People Counting Public Transportation

来源：评论

学校读者我要写书评

暂无评论

Localization of sound sources with dual acoustic vector sensor 23

Localization of sound sources with dual acoustic vector sens...

引用

23rd IEEE conference on Signal Processing algorithms, architectures, Arrangements, and applications (SPA)

作者： Kotus, Jozef Szwoch, Grzegorz Gdansk Univ Technol Fac Elect Telecommun & Informat Dept Multimedia Syst Narutowicza 11-12 PL-80233 Gdansk Poland

ISBN: (纸本)9788362065363

The aim of the work is to estimate the position of sound sources. The proposed method uses a setup of two acoustic vector sensors (AVS). The intersection of azimuth rays from each AVS should indicate the position of a source. In practice, the result of position estimation using this method is an area rather than a point. This is a result of inaccuracy of the individual sensors, but more importantly, of the influence of a source size. The proposed method was validated in experiments performed in an anechoic room, using a custom-made setup of two sensors built from digital MEMS microphones, for sound source placed at varying distance and angle from the sensors. The paper discusses the observed variations in the measured angle and distance to the source. The obtained results indicate that the proposed method allows for estimation of the source position with satisfactory accuracy. Errors in the position estimation depend on the source size, the distance to the source and the source angle relative to the sensors. Possible application of the proposed method is estimation of the position of moving sound sources, such as road vehicles.

关键词： acoustic vector sensor sound source localization sound intensity acoustics

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：