检索结果-内蒙古大学图书馆

Mediterranean Conference on Embedded Computing (MECO)

作者： Nil Llisterri Gimé nez Felix Freitag JunKyu Lee Hans Vandierendonck Department of Computer Architecture. Technical University of Catalunya Barcelona Spain The Institute of Electronics Communications and Information Technology. Queen&#x0027 s University Belfast. UK

Machine learning applications on resource-constrained devices such as microcontroller units often use models trained externally on more powerful devices. This approach, however, limits a later adaptation of the machine learning model in the device to changing data. Differently, on-device training allows the model to be updated for new datasets, but the training process needs to take into account the resource limitations of the device. This paper compares on-device training performance for a keyword spotting task using two popular microcontroller boards, Arduino Nano 33 BLE Sense and Arduino Portenta H7, in terms of inference accuracy, training latency, and current consumption. We use feedforward neural networks having a single hidden layer for models. The inference accuracy has been significantly improved using the Portenta H7 board by employing more neurons fitted to its memory budget, compared to the Nano board. With a neural network having 25 neurons for a hidden layer, the 5.0 x inference and 4.2 x training speedups are achieved using the Arduino Portenta H7 board, compared to the Arduino Nano 33 BLE Sense. While the memory of the Arduino Nano 33 BLE Sense is capable to train a neural network for the keyword spotting task, the Arduino Portenta H7 gives new possibilities for exploring more complex models for more complex problems thanks to a larger memory budget and adapting a model to new data in lower latency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantitative Evaluation to Detect Crack Depth in Beams Based on CNN-RNN-LSTM Approach

Quantitative Evaluation to Detect Crack Depth in Beams Based...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Mohammad Asif Gandhi A. N. Swaminathen Deepak T. Patil A Ravitheja R. Kamali Akshay Rajput Department of Mechanical Engineering Anjuman-I-Islam's Kalsekar Technical Campus Panvel Maharashtra India Adi Shankara Institute of Engineering and Technology Kerala India Bharati Vidyapeeth college of Architecture Navi Mumbai Maharashtra India Department of Civil Engineering SVR Engineering College Kurnool Andhra Pradesh India Department of Computer Science And Engineering Knowledge Institute of Technology Salem Tamilnadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

In this study, the proposed approach offers a novel hybrid image-based deep learning method for autonomous concrete fracture identification. Cracks are easier to spot and false positives are reduced with hybrid images that include visual and infrared thermography data. In specifically, a Visible and infrared camera as well as a line laser make up a hybrid imaging system for spatially scanning unmanned vehicles can efficiently assess large-scale concrete-made constructions like bridges and dams. Crack detection is a commonplace task in many industrial domains, however the current method of relying on expert judgment is typically laborious, time consuming, and inaccurate. The practical benefits of automated decision-making increase as the size of the target concrete construction grows. Cracks can be automatically identified and seen using the proposed method. Preprocessing, segmentation, feature extraction, and model training are the four components of the proposed method. It performs clever edge recognition, scaling, and greyscale conversion as part of its preparation. Improved K-Means segmentation is used for the separation. It employs GLCM for feature extraction, and CNN-RNN-LSTM for model training. The new method is compared to two established approaches, CNN-RNN and CNN-LSTM, and is found to be superior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scintillation event imaging with a single photon avalanche diode camera

Communications Engineering

引用

Communications Engineering 2024年第1期3卷 135页

作者： Bocchieri, Alex Charbon, Edoardo Velten, Andreas Department of Computer Sciences University of Wisconsin - Madison Madison WI United States Advanced Quantum Architecture Laboratory (AQUA) Swiss Federal Institute of Technology Lausanne (EPFL) Neuchâtel Switzerland Department of Biostatistics and Medical Informatics University of Wisconsin - Madison Madison WI United States Department of Electrical and Computer Engineering University of Wisconsin - Madison Madison WI United States

Position and time measurements of scintillation events encode information about the radiation source. Single photon avalanche diode (SPAD) arrays offer multiple-megapixel spatial resolution and tens of picoseconds temporal resolution for detecting single photons. Current lensless designs for measuring scintillation events use sensors that are lower in spatial resolution. Camera-based designs use sensors that are lower in temporal resolution or readout rate and cannot image individual interactions. Here we propose to image scintillation events in a thick, monolithic scintillator using a high-resolution SPAD camera. We demonstrate that a commercial SPAD camera is able to gather sufficient signal to image individual scintillation events and observe 3D shifts in their spatial distribution. Simulations show that a SPAD camera can localize individual scintillation events in 3D. We report direct imaging of gamma-ray interactions in a scintillator with a SPAD camera. The proposed design may allow to measure complex signatures of individual particles interacting in the scintillator. © The Author(s) 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-Orthogonal Multiple Access Based Multi-Objective Optimization in Emergency Task Offloading

Non-Orthogonal Multiple Access Based Multi-Objective Optimiz...

引用

IEEE Conference on Wireless Communications and Networking

作者： Caijuan Chen Chaofeng Zhang Gaolei Li Yuchen Liu The Information Systems Architecture Science Research Division National Institute of Informatics Tokyo Japan Advanced Institute of Industrial Technology Tokyo Japan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Computer Science NC State University North Carolina US

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The escalating frequency of geological disasters, local conflicts, and public health crises necessitates robust emergency communication systems within Internet of Things (IoT) frameworks to ensure public safety. Employing Power-Domain NOMA (PD-NOMA) and Successive Interference Cancellation (SIC) enables effective multi-device communication that is crucial for emergency responses. However, the practical implementation of NOMA technologies in emergency scenarios is hindered by existing resource constraints and the requirement of prioritizing critical emergency information. To address these limitations, we propose a multi-objective optimization-based NOMA framework to maximize network throughput while ensuring quality of service (QoS) and energy efficiency. This framework incorporates a novel communication grouping algorithm based on queue penalty optimization and an Actor-Critic-based dynamic updating algorithm for multiple resource allocation. Our study proposes a practical approach to enhance emergency communication in disaster areas, ensuring efficient and reliable network performance under various constraints.

关键词： NOMA Interference cancellation Heuristic algorithms Disasters Quality of service Throughput Dynamic scheduling Internet of Things Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

A novel data driven approach for combating energy theft in urbanized smart grids using artificial intelligence

引用

Expert Systems with Applications 2024年 253卷

作者： Shahzadi, Nazia Javaid, Nadeem Akbar, Mariam Aldegheishem, Abdulaziz Alrajeh, Nabil Bouk, Safdar Hussain Department of Computer Science COMSATS University Islamabad Islamabad44000 Pakistan International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Yunlin64002 Taiwan Department of Urban Planning College of Architecture and Planning King Saud University Riyadh11574 Saudi Arabia Department of Biomedical Technology College of Applied Medical Sciences King Saud University Riyadh11633 Saudi Arabia Old Dominion University 5115 Hampton Blvd NorfolkVA23529 United States

Electricity Theft (ET) causes monetary losses for power utilities in the energy sector. It occurs when electricity is consumed without being billed. Several methods are available for automatically detecting ET. Most of these methods evaluate Electricity Consumption (EC) records. However, these methods either have a low Detection Rate (DR) or a high deployment cost with a high False Positive Rate (FPR). Moreover, it is difficult to identify fraudulent consumers based solely on EC records. In addition, owing to data imbalances, such methods prove to be inefficient for classification. To solve the aforementioned problems, we have proposed a combination of various techniques. The first one is the Fastfood Transform, which is used for dimensionality reduction, along with the Time Series Lag Embedded Network (TLENET) neural network, used for classification between honest and dishonest consumers. The second one is the Wavelet Transform used for dimensionality reduction with TLENET, and the third one is the Nyström method used for dimensionality reduction with TLENET. To tackle the risk of high variance that results in overfitting in Deep Learning (DL) models, a Localized Random Affine Shadowsampling (LoRAS) data balancing technique is used. We have employed various data balancing techniques to analyze the performance of our system model. A game theory based approach, SHapley Additive exPlanations (SHAP), is implemented for explaining the output of our deep model. We have used a real-world dataset, referred as the State Grid Corporation of China (SGCC), to perform the simulations. Our model has achieved 94% accuracy, 92% F1-score, 93% Area Under Curve-Receiver Operating Characteristics (AUC-ROC), and 87% Matthews Correlation Coefficient (MCC) with LoRAS, Wavelet Transform, and TLENET. With dimensionality reduction using Fastfood Transform, our model has achieved 93% accuracy, 92% F1-score, 92% AUC-ROC, and 85% MCC. When the Nyström method is employed for dimensionality redu

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Memory-facilitated Joint-space Shift Adaptation in Traffic Forecasting

Memory-facilitated Joint-space Shift Adaptation in Traffic F...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ye Wei He Haitao Gerald Schaefer Zhigang Ji Yifan Wang Hui Fang Department of Computer Science Loughborough University Loughborough UK The Alan Turing Institute London UK School of Architecture Building and Civil Engineering Loughborough University Loughborough UK National Key Laboratory of Science and Technology on Micro/Nano Fabrication Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traffic forecasting, crucial for intelligent transport systems, faces significant challenges from distribution shifts due to the dynamic nature of traffic patterns. Although normalisation approaches have been proposed to address distribution shifts in other time-series forecasting tasks such as predicting electricity consumption load prediction or influenza-like illness patient number estimation, they fall short in handling the complex spatial and temporal shifts in traffic data. In this paper, we propose a novel memory-facilitated joint-space shift adaptation framework, ST-Align, to address this problem in traffic forecasting. ST-Align comprises two key components targeting the input and latent space, respectively: a memory-based data alignment module in the input space, and an end-to-end memory network structure dedicated to alignment within the latent space. This joint-space design enables our ST-Align framework to effectively capture and adapt to dynamic distribution shifts in both spatial and temporal dimensions, thus enhancing model performance. Extensive experiments on various real-world datasets and prediction backbones convincingly demonstrate the robustness and generalisability of our method.

关键词： Adaptation models Electricity Neural networks Estimation Traffic control Robustness Forecasting

来源：评论

学校读者我要写书评

暂无评论

Trikarenos: Design and Experimental Characterization of a Fault-Tolerant 28nm RISC-V-based SoC

引用

IEEE Transactions on Nuclear Science 2025年

作者： Rogenmoser, Michael Wiese, Philip Forlin, Bruno Endres Gurkaynak, Frank K. Rech, Paolo Menicucci, Alessandra Ottavi, Marco Benini, Luca Integrated Systems Laboratory ETH Zurich Switzerland Computer Architecture for Embedded Systems University of Twente Netherlands Department of Industrial Engineering University of Trento Italy Delft University of Technology Department of Space Engineering Netherlands University of Rome Department of Electronic Engineering Tor Vergata Italy Information Engineering at the University of Bologna Department of Electrical Electronic Italy

RISC-V-based fault-tolerant system-on-chip (SoC) designs are critical for the new generation of automotive and space SoC architectures. However, reliability assessment requires characterization under controlled radiation doses to accurately quantify the fault tolerance of the fabricated designs. This work analyzes the Trikarenos design, a SoC implemented in TSMC 28nm, for single event upset (SEU) vulnerability under atmospheric neutron and 200MeV proton radiation, comparing these results to simulation-based fault injection. All faults in error correction codes (ECC) protected memory are corrected by a scrubber, showing an estimated cross-section per bit of up to 1.09 × 10−14 cm2 bit−1. Furthermore, the triple-core lockstep (TCLS) mechanism implemented in Trikarenos is validated and is shown to correct errors affecting a cross-section up to 3.23 × 10−11 cm2, with the remaining uncorrectable vulnerability below 5.36 × 10−12 cm2. When augmenting the experimental analysis of fabricated chips with gate-level fault injection in simulation, 99.10% of injections into the SoC produced correct results, while 100% of injections in the TCLS-protected cores were handled *** 12.28%of all injected faults leading to a TCLS recovery, this indicates an approximate effective flip-flop cross-section of up to 1.28 × 10−14 cm2/FF. © 1963-2012 IEEE.

关键词： Radiation damage

来源：评论

学校读者我要写书评

暂无评论

Evaluating Neighbourhood Roads Through Agent-Based Modelling: A Step Towards the Optimal Pedestrian Desire Path System

SSRN

引用

SSRN 2024年

作者： Ma, Lei Brandt, S. Anders Seipel, Stefan Ma, Ding Department of Computer and Geospatial Sciences Faculty of Engineering and Sustainable Development University of Gävle Gävle80176 Sweden Division of Visual Information and Interaction Department of Information Technology Uppsala University Uppsala75105 Sweden Research Institute for Smart Cities School of Architecture and Urban Planning Shenzhen University Shenzhen518060 China

As a part of road networks, sidewalks are critical in urban development and people’s lives. This study introduces the Road Evaluation by Desire Path Simulation System (RED-PaSS), an agent-based modelling (ABM) framework designed to assess the alignment of urban sidewalks with pedestrians' natural movement patterns. RED-PaSS simulates pedestrian movement to generate an optimal desire path system, representing the most direct and natural routes that pedestrians would choose in urban settings. The model compares existing sidewalks against these simulated desire paths using key metrics, including road patch distances, segment alignment with desire paths, and origin-destination (OD) flow efficiency. This approach enables urban planners to identify and address gaps in pedestrian infrastructure effectively. In this study, RED-PaSS was applied to evaluate and rank 708 neighbourhood-scale road networks across the United States using high-resolution population density data and open-source road datasets. The evaluation revealed that the sidewalks closely aligned with simulated desire paths offer more direct and efficient pedestrian routes, enhancing natural walking movement. In contrast, poorly aligned sidewalks often force pedestrians to take indirect routes, reducing walkability and efficiency. By identifying discrepancies between existing sidewalks and optimal pedestrian pathways, RED-PaSS provides actionable insights for designing more walkable urban environments and can potentially serve as a valuable tool for urban planners seeking to enhance urban road systems. This work contributes to urban planning by offering a method to improve pedestrian network efficiency, aligning infrastructure with actual pedestrian natural movement behaviours, and emphasizing the need for integrating organic pedestrian movements into formal road network designs to create more functional and walkable cities. © 2024, The Authors. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Artificial neural network-based prediction assessment of wire electric discharge machining parameters for smart manufacturing

引用

Paladyn 2023年第1期14卷

作者： Manoj, Itagi Vijayakumar Narendranath, SannaYellappa Mashinini, Peter Madindwa Soni, Hargovind Rab, Shanay Ahmad, Shadab Hayat, Ahatsham Department of Mechanical Engineering Nitte Meenakshi Institute of Technology Karnataka Bengaluru560064 India Department of Mechanical Engineering National Institute of Technology Karnataka Surathkal Surathkal575025 India Department of Mechanical & Industrial Engineering Technology University of Johannesburg PO Box 524 Auckland Park2006 South Africa Department of Mechanical Engineering National Institute of Technology Delhi Delhi110036 India School of Architecture Technology and Engineering University of Brighton BrightonBN2 4GJ United Kingdom School of Mechanical Engineering Shandong University of Technology Zibo255000 China Department of Electrical and Computer Engineering University of Nebraska-Lincoln LincolnNE United States

Artificial intelligence (AI), robotics, cybersecurity, the Industrial Internet of Things, and blockchain are some of the technologies and solutions that are combined to produce "smart manufacturing,"which is used to optimize manufacturing processes by creating and/or accepting data. In manufacturing, spark erosion technique such as wire electric discharge machining (WEDM) is a process that machines different hard-to-cut alloys. It is regarded as the solution for cutting intricate parts and materials that are resistant to conventional machining techniques or are required by design. In the present study, holes of different radii, i.e. 1, 3, and 5 mm, have been cut on Nickelvac-HX. Tapering in WEDM is a delicate process to avoid disadvantages such as wire break, wire bend, wire friction, guide wear, and insufficient flushing. Taper angles viz. 0°, 15°, and 30° were obtained from a unique fixture to get holes at different angles. The study also shows the influence of taper angles on the part geometry and area of the holes. Next, the artificial neural network (ANN) technique is implemented for the parametric result prediction. The findings were in good agreement with the experimental data, supporting the viability of the ANN approach for the evaluation of the manufacturing process. The findings in this research provide as a reference to the potential of AI-based assessment in smart manufacturing processes and as a design tool in many manufacturing-related fields. © 2023 the author(s), published by De Gruyter.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Enabling VR/AR and Tactile through 5G Network 4

Enabling VR/AR and Tactile through 5G Network

引用

4th International Conference on Communication, Information and Computing technology, ICCICT 2021

作者： Kusuma, Henry Mathews Shukla, Vinod Kumar Gupta, Shaurya Bachelor of Information Technology Amity University Dubai United Arab Emirates Department of Engineering and Architecture Amity University Dubai United Arab Emirates School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India

ISBN: (纸本)9781665404303

After the introduction of fifth generation network, there are several prospects and encounters for the evolving technologies like Virtual Reality (VR) and Augmented Reality (AR). This paper emphases on the possibilities of 5G network and how 5G will integrate with Virtual Reality and Augmented Reality and Tactile Internet. Tactile Internet in AR/VR is intended to generate a model alteration from the content-oriented interactions (through internet) towards remote based connections by empowering synchronized broadcast of tactile data like vibration, touch, gestures, surface texture over wireless network with the regular audio and visual data traffics which are also transferred over wireless network. Finally, this research paper intends to provide an overall opinion on the use of Tactile Internet in AR/VR, and to recognize and examine the involved drawbacks and technical problems, and to provide the possible resolutions and to suggest upcoming research guidelines. Initially, opening with the future of Tactile Internet in AR/VR and recent developments in this field, this paper presents a comprehensive outline for Tactile Internet in AR/VR in the past the 5G Era including a Tactile Internet planning, the VR/AR planning, the core technical problems, the important application studies, how it can be possibly enable ground-breaking ways to use Augmented Reality and Virtual Reality. Later, we can see a complete evaluation of the present Tactile Internet progress by generally classifying them into two main instances;specifically, haptic feedback and portable AR/VR device using 5G network. Finally, learning about both Tactile Internet and Augmented Reality/Virtual Reality, we will learn how 5G can change the way Tactile Internet integrates and works with AR/VR that can make an impact in the ever-growing IoT world. © 2021 IEEE.

关键词： 5G mobile communication systems

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：