检索结果-内蒙古大学图书馆

Exploring 2D representation and transfer learning techniques for indoor localization

Multimedia Tools and Applications 2025年 1-13页

作者： Kerdjidj, O. Himeur, Y. Atalla, S. Copiaco, A. Sohail, S.S. Amira, A. Fadli, F. Mansoor, W. Gawanmeh, A. Centre of Development of Advanced Techniques Algiers Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom School of Computing Science and Engineering VIT Bhopal University Kothri Kalan India Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

Indoor localization (IL) plays a critical role in various applications, including asset tracking, emergency response, and indoor navigation. Traditional methods relying on one-dimensional (1D) representations of received signal strength indicator (RSSI) data often suffer from limitations such as low accuracy, environmental sensitivity, and susceptibility to interference. To overcome these challenges, this paper proposes Scalogram-Based Transfer Learning for Indoor Localization (STL-IL), a novel framework that significantly enhances localization performance. The proposed approach transforms 1D RSSI signals into two-dimensional (2D) representations using scalogram-based time-frequency analysis, coupled with advanced transfer learning (TL) techniques. By leveraging the scalogram method to generate image representations of the data and employing diverse wavelet types. Furthermore, pre-trained deep learning models, including GoogleNet and SqueezeNet, are utilized to achieve state-of-the-art performance. Experimental results demonstrate that the STL-IL system achieves remarkable accuracy levels of 95% and 96% for SqueezeNet and GoogleNet, respectively. The proposed framework not only improves localization accuracy but also enhances robustness in dynamic and challenging environments, making it a promising solution for real-world indoor localization applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Input Voltage Range Optimization of a High Power Wireless Power Transfer System for Constant Power Output

Input Voltage Range Optimization of a High Power Wireless Po...

引用

Wireless Power Week (WPW)

作者： Lukas Elbracht Feiyang J. Lin Nejila Parspour Grant A. Covic Patrick A. J. Lawton Institute of Electrical Energy Conversion University of Stuttgart Electrical Computer and Software Engineering The University of Auckland

ISBN: (数字)9798350349139

ISBN: (纸本)9798350349146

Designing wireless power transfer systems for high power energy transfer is challenging, especially when transferring constant power under misalignment and varying battery voltage. In systems with passive rectifiers, there are not many control parameters that can be adjusted to regulate the output. In order to maintain constant power under misalignment, common approaches normally require a large input voltage range. This results in either high cost for the active frontend or higher losses in the inverter due to increased hard switching. This work shows an optimization approach to transfer constant power in all alignment conditions by achieving the best possible efficiency while minimizing the input voltage range. An existing 50 kW wireless power transfer system is taken as a starting point for an optimization. The range minimization of the input voltage is achieved by modifying the compensation parameters of the LCC resonant network on the primary side. The optimization results are then shown and suitable solutions are compared to the standard resonant design.

关键词： Wireless communication Costs Rectifiers Wireless power transfer Voltage Switches Minimization

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Efficacy of Signal Decomposition in AI-based Time Series Prediction

Revisiting the Efficacy of Signal Decomposition in AI-based ...

引用

2024 International Conference Optoelectronic Information and Optical engineering, OIOE 2024

作者： Zhang, Dan Jiang, Kexin Wu, Chuhan Peng, Yan Han, Zhaolong Chen, Yaoran Institute of Artificial Intelligence Shanghai University Shanghai200444 China Department of Computer Engineering and Science Shanghai University Shanghai200444 China Department of Electronic Engineering Tsinghua University Beijing100084 China School of Naval Architecture Ocean & Civil Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (数字)9781510688209

ISBN: (纸本)9781510688193

Time series prediction is a fundamental problem in scientific exploration and artificial intelligence (AI) technologies have substantially bolstered its efficiency and accuracy. A well-established paradigm in AI-driven time series prediction is injecting physical knowledge into neural networks through signal decomposition methods, and sustaining progress in numerous scenarios has been reported. However, we uncover non-negligible evidence that challenges the effectiveness of signal decomposition in AI-based time series prediction. We confirm that improper dataset processing with subtle future label leakage is unfortunately widely adopted, possibly yielding abnormally superior but misleading results. By processing data in a strictly causal way without any future information, the effectiveness of additional decomposed signals diminishes. Our work probably identifies an ingrained and universal error in time series modeling, and the de facto progress in relevant areas is expected to be revisited and calibrated to prevent future scientific detours and minimize practical losses. © 2025 SPIE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Concept of an Optical Distance and Speed Sensor Using Novel Offsetless Spatial Frequency Filters in the Area of Functional Safety 32

Concept of an Optical Distance and Speed Sensor Using Novel ...

引用

32nd IEEE International Symposium on Industrial Electronics, ISIE 2023

作者： Wasinski, Frank Bonath, Werner Ricklefs, Ubbo Borcsok, Josef Schwarz, Michael Hahn, Eike University of Applied Sciences THM Dept. of Electrical Engineering and Information Technology Giessen Germany Institute for Computer Architecture and System Programming University of Kassel ICAS Kassel Germany

ISBN: (纸本)9798350399714

Optical speed sensors based on the spatial frequency filter method are a proven technology that offer high measurement accuracy over a wide speed range. Newly developed variants also enable measurements at very low speeds and increase the robustness of the method [1]. This makes the sensor very suitable for use in the area of functional safety. A measurement chain up to safety integrity level 3 (SIL3) should be feasible via a combination with a safety system on a chip (SoC) for evaluating the measurement data and an extension of the sensor module to include safety-related elements [2], [3]. By integrating the sensor at IC level, a compact overall solution is to be made possible. After the first successful tests with the safety SoC, further examinations of the measuring method with regard to functional safety are now necessary. © 2023 IEEE.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Mapping Quantum Circuits to 2-Dimensional Quantum architectures

Mapping Quantum Circuits to 2-Dimensional Quantum Architectu...

引用

2022 Informatik in den Naturwissenschaften, INFORMATIK 2022 - 2022 computer Science in the Natural Sciences, INFORMATIK 2022

作者： Datta, Kamalika Kole, Abhoy Sengupta, Indranil Drechsler, Rolf Cyber Physical System Bremen Germany JIS University Department of Computer Science and Engineering Kolkata India Indian Institute of Technology Kharagpur Department of Computer Science and Engineering India University of Bremen Group of Computer Architecture Bremen Germany

ISBN: (纸本)9783885797203

We have been witnessing a rapid growth in quantum computing research over the years, with the emergence of demonstrable quantum computers of moderate size. The major issues that are faced to run a quantum algorithm reliably on these systems are: (i) lower qubit coherence period, (ii) noisy primitive gate operations, (iii) limited number of available physical qubits, and (iv) support of restricted set of 2-qubit operations. Overcoming these issues mandates physical resources that exceeds the capabilities of these noisy intermediate scale quantum (NISQ) systems. On the other hand, computation using bare qubits get further disturbed due to the inclusion of additional gates to mitigate the nearest neighbor constraints. In the present work, the 2-dimensional square, heavy-hex and fully hexagonal qubit coupling lattices are considered for mapping quantum circuits. The benefits are assessed in terms of minimal additional gates needed to satisfy the nearest neighbor (NN) constraint and the compilation complexity of mapping circuits on these architectures. From the experiments by mapping benchmark circuits on 16-qubit square and 65-qubit heavy-hex architectures from IBM as well as on a 64-qubit fully hexagonal architecture, it is observed that none of the square or heavy-hex lattice architecture provides uniform compilation advantage compared to the fully hexagonal architecture. It is expected that beyond the NISQ era, strongly connected lattices like hexagonal will become practically feasible. © 2022 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Supporting Disaster Resilience Building through Cross-Community Knowledge Sharing 13

Supporting Disaster Resilience Building through Cross-Commun...

引用

13th Annual IEEE Global Humanitarian Technology Conference, GHTC 2023

作者： Koga, Motoya Kaneko, Tetsuya Leleito, Emanuel Karashima, Kazuki Aharari, Ari Sojo University Department of Architecture Kumamoto Japan Nagoya University Graduate School of Engineering Nagoya Japan Maebashi Institute of Technology Dept.of Architecture Maebashi Japan Sojo University Department of Computer and Information Sciences Kumamoto Japan

ISBN: (纸本)9798350321326

Collaborative action in disaster mitigation efforts contributes to knowledge and experience sharing, resource sharing, improvement of response and coordination, and standardization of good practice. In this study, we propose a workshop model and develop a virtual collaboration tool to support and promote cross-community knowledge sharing and collaboration focusing on disaster mitigation efforts. The workshop model involves pre-fieldwork training, actual fieldwork, and post-fieldwork information exchange. The collaboration tool enables information collection, sharing and record keeping. The effectiveness of the workshop model and the collaboration tool is demonstrated through use in a citizen participatory disaster preparedness workshops linking two elementary schools located in the central and southern regions of Japan. © 2023 IEEE.

关键词： Disaster prevention

来源：评论

学校读者我要写书评

暂无评论

HIET:Hybrid Information Enhancement Transformer Network for Single-Photon Image Reconstruction

引用

Journal of Beijing institute of Technology 2025年第1期34卷 1-17页

作者： Yiming Liu Xuri Yao Tao Zhang Yifei Sun Ying Fu School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China Center for Quantum Technology Research and Key Laboratory of Advanced Optoelec-tronic Quantum Architecture and Measurements(MOE) School of PhysicsBeijing Institute of TechnologyBeijing 100081China School of Communication Engineering Hangzhou Dianzi UniversityHangzhou 310018China Uniview Technology Hangzhou 310056China

Single-photon sensors are novel devices with extremely high single-photon sensitivity and temporal ***,these advantages also make them highly susceptible to ***,single-photon cameras face severe quantization as low as 1 bit/*** factors make it a daunting task to recover high-quality scene information from noisy single-photon *** current image reconstruction methods for single-photon data are mathematical approaches,which limits information utilization and algorithm *** this work,we propose a hybrid information enhancement model which can significantly enhance the efficiency of information utilization by leveraging attention mechanisms from both spatial and channel ***,we introduce a structural feature enhance module for the FFN of the transformer,which explicitly improves the model's ability to extract and enhance high-frequency structural information through two symmetric convolution ***,we propose a single-photon data simulation pipeline based on RAW images to address the challenge of the lack of single-photon *** results show that the proposed method outperforms state-of-the-art methods in various noise levels and exhibits a more efficient capability for recovering high-frequency structures and extracting information.

关键词： single-photon images hybrid information enhancement structual feature enhancement data simulation pipeline

来源：评论

学校读者我要写书评

暂无评论

Multimodal Large Models are Effective Action Anticipators

引用

IEEE Transactions on Multimedia 2025年 27卷 2949-2960页

作者： Wang, Binglu Tian, Yao Wang, Shunzhou Yang, Le Xi'an University of Architecture and Technology College of Information and Control Engineering Xi'an710055 China Northwestern Polytechnical University School of Astronautics Xi'an710072 China Peking University School of Electronic and Computer Engineering Shenzhen Graduate School Shenzhen518055 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230022 China University of Science and Technology of China School of Information Science and Technology Hefei230022 China

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on recurrent units or Transformer layers to capture long-term dependencies, often fall short in addressing these challenges. Large Language Models (LLMs), with their robust sequential modeling capabilities and extensive commonsense knowledge, present new opportunities for long-term action anticipation. In this work, we introduce the ActionLLM framework, a novel approach that treats video sequences as successive tokens, leveraging LLMs to anticipate future actions. Our baseline model simplifies the LLM architecture by setting future tokens, incorporating an action tuning module, and reducing the textual decoder layer to a linear layer, enabling straightforward action prediction without the need for complex instructions or redundant descriptions. To further harness the commonsense reasoning of LLMs, we predict action categories for observed frames and use sequential textual clues to guide semantic understanding. In addition, we introduce a Cross-Modality Interaction Block, designed to explore the specificity within each modality and capture interactions between vision and textual modalities, thereby enhancing multimodal tuning. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Exploring Gate-Diversity Enabled by Reconfigurable Memristive Technology

Exploring Gate-Diversity Enabled by Reconfigurable Memristiv...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Sebastian Brandhofer Ziang Chen Li-Wei Chen Xianyue Zhao Nan Du Ilia Polian Institute of Computer Architecture and Computer Engineering University of Stuttgart Stuttgart Germany Institute for Solid State Physics Friedrich Schiller University Jena Jena Germany Department of Quantum Detection Leibniz Institute of Photonic Technology (IPHT) Jena Germany

While memristive devices are highly attractive as memory cells, they are also capable of performing computations, paving the way to futuristic in-memory computing architecture. Several memristive logic families have been proposed, and approaches to map gate-level logic circuits to such memristive implementations have been introduced. In this paper, we focus on the CRS logic family that offers several advantages compared to the more often considered IMPLY and MAGIC families. A central feature of CRS is the ability of one physical memristive device to realize varying logic gates over several clock cycles. Our method computes a schedule, i.e., an assignment which logic gate of a given circuit is executed on which memristive device during which clock cycles. Using an optimal MaxSAT model, it can minimize the resulting schedule’s duration (depth), the cost of the used memristors, or the cost of additional cache register cells, while satisfying all dependencies needed for correct computation. In addition to results of the scheduling procedure itself, we report a physical experiment that demonstrates one of the schedules and discuss the energy benefits of the CRS family.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cloud-Computing Trend Analysis of Urbanization Impacts on Land Surface Temperature and Electricity Demand in Gaborone, Botswana

引用

Remote Sensing in Earth Systems Sciences 2024年第1期8卷 283-306页

作者： Moyo, Boineelo Schröder, Dietrich Moreri, Kealeboga Institute for living conditions in rural areas Johann Heinrich von Thuenen-Institut Bundesallee 50 Lower Saxony Braunschweig 38116 Germany Department of Geomatics Computer Science and Mathematics Stuttgart University of Applied Sciences Schellingstr. 24 Baden-Wuerttemberg Stuttgart 70174 Germany Department of Civil Engineering University of Botswana Notwane Rd Gaborone Botswana

Land use land cover (LULC) changes are critical drivers of global environmental changes, profoundly impacting sustainability in rapidly urbanizing regions. In urban areas, where vegetation cover is reduced, LULC changes significantly affect the distribution and intensity of Land Surface Temperature (LST), which in turn influences electricity demand and consumption. This study explores the relationship between urbanization, vegetation loss, surface temperature and electricity demand in Gaborone, Botswana. The study utilized the Landsat data to conduct a 15-year (2005–2020) spatio-temporal analysis of LULC changes and LST dynamics, identified surface urban heat islands (SUHI) using the Getis-Ord Gi* hot-spot analysis and assessed the correlation between LST and key spectral indices adopted in the study. The analysis employed Google Earth Engine (GEE) cloud computing platform and the Random Forest (RF) machine learning algorithm, known for their accuracy and efficiency in classification and change detection studies. Findings reveal substantial LULC transformations in Gaborone with approximately 12 km² of land converted to Built-Up areas, driving a 2.36% annual urban growth rate and shrinking green and bare spaces. Consequently, surface temperatures rose by about 2.1 °C, impacting energy demand, particularly for cooling during hot summers. This demand surge, coupled with urban expansion, has fueled higher electricity prices, posing new challenges in climate adaptation and mitigation. The study provides critical insights into the interplay between urbanization, rising temperatures, and energy consumption in Gaborone. These insights highlight the urgent need for developing sustainable urban planning and energy strategies to address the impacts of climate change, land degradation, and energy poverty. © The Author(s) 2024.

关键词： Climate change Electricity demand Google earth engine Land surface temperature Land use land cover Random forest

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：