检索结果-内蒙古大学图书馆

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Lai, Yi-Shan Chen, Yi Fu, Li-Chen Hsiao, Pei-Yung Wang, Yu-Chieh National Taiwan University Department of Computer Science and Information Engineering Taiwan National University of Kaohsiung Department of Electrical Engineering Taiwan Automotive Research and Testing Center Taiwan Taiwan

ISBN: (纸本)9798350382204

In recent years, with the development of autonomous driving technology, designing a driver monitoring system that can run on vehicles has become increasingly important. The driving system analyzes various factors such as head pose, gaze direction, and eye state to determine the driver's attentiveness and aid the system in evaluating the driver's capability to control the vehicle. In this paper, we present a lightweight multi-task deep learning model that utilizes full-face images to detect head pose, gaze direction, and eye state simultaneously. We propose a task-based cross-dimensional attention module (TCAM) that selectively filters and enhances relevant features for each specific task. Additionally, to tackle the lack of diverse head pose angles in the eye state dataset, we introduce a data augmentation technique to generate eye state data under different head poses, enhancing the model's robustness in detecting eye states under varying head poses. We demonstrate the results of our work on the 300WLP, AFLW2000, BIWI, Gaze360, and MRL datasets. Extensive experiments show that our method can obtain competitive results with lower parameter costs. Furthermore, we establish a baseline for eye state detection using full-face images as the input on the CEW datasets. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal distribution in chemical composition of wet atmospheric deposition in Bandung Indonesia

引用

Environmental Science and Pollution research 2024年第55期31卷 64295-64313页

作者： Indrawati, Asri Tanti, Dyah Aries Ambarsari, Novita Ma’ruf, Ilma Fauziah Sumaryati Setyawati, Wiwiek Pusfitasari, Eka Dian Nugroho, Ginaldi Ari Cholianawati, Nani Sinatra, Tiin Halimurrahman Triani, Listi Restu Nafiisyanti, Aisya Putra, Sany Indra Nurlatifah, Amalia Huo, Mingqun Awaludin, Asif Research Center for Climate and Atmosphere National Research and Innovation Agency Jl. Sangkuriang Dago Bandung40135 Indonesia 1182 Sowa Nishi-Ku Niigata-Shi950-2144 Japan Computer Engineering Department School of Electrical Engineering Telkom University Jl. Telekomunikasi. 1 Dayeuhkolot Kab Bandung 40257 Indonesia

Bandung, Indonesia, represents the complex interactions between climate variability, basin topography, and deposition processes. This study conducted a long-term spatiotemporal analysis, including pH distribution and pollutant accumulation monitoring, to observe the chemical composition of wet deposition in Bandung as part of the Acid Deposition Monitoring Network in East Asia (EANET). The results revealed that NH4+ and NO3- were the predominant ions, followed by SO42-, with their distribution varying across different sites due to local emissions and atmospheric processes. The interactions between these ions, particularly the formation of secondary inorganic aerosols such as ammonium sulfate and ammonium nitrate, were closely linked to the basin’s localized sources and topographical features. Areas experiencing high traffic congestion were classified as acidic regions due to their low pH levels. In contrast, a rural site exhibited a basic pH due to the high concentration of ion NH4+. Variations in pH and conductivity, along with the impacts of climatic events such as El Niño and La Niña, emphasized the role of weather patterns in shaping wet deposition dynamics. Seasonal trends indicated elevated total ion concentrations during the dry season, driven by sea salt contributions, as supported by strong correlations between Na+ and Cl- and between Na+ and Mg2+. Additionally, geological materials and atmospheric reactions contributed to the strong correlations observed between soil-derived cations and acidic species. The increasing trend in nss-SO42- and the contrasting decrease in NO3- concentrations in rural areas suggest evolving emission sources and environmental conditions. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： pH

来源：评论

学校读者我要写书评

暂无评论

Integration of metasurface and PCSEL in real-time depth-sensing micro-system for facial recognition

Integration of metasurface and PCSEL in real-time depth-sens...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Hsu, Wen-Cheng Chang, Chia-Hsun Hong, Yu-Heng Kuo, Hao-Chung Huang, Yao-Wei Department of Photonics College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Semiconductor Research Center Hon Hai Research Institute Taipei11492 Taiwan

We demonstrate a novel dot projector architecture for depth-sensing perception facial recognition applying metasurfaces and photonic crystal surface-emitting lasers (PCSELs), which has area 55 times smaller and power-... 详细信息

ISBN: (纸本)9781957171395

关键词： Optical projectors

来源：评论

学校读者我要写书评

暂无评论

Smart tailoring of molecular catalysts:Mounting approach to oxygen reduction reaction

引用

Journal of Materials Science & Technology 2024年第1期168卷 169-184页

作者： Anuj Kumar Mohd Ubaidullah Guoxin Zhang Jasvinder Kaur Saira Ajmal Mudassir Hasan Krishna Kumar Yadav Hafiz M.Adeel Sharif Ram K.Gupta Ghulam Yasin Nano-Technology Research Laboratory Department of ChemistryGLA UniversityMathuraUttar Pradesh 281406India Department of Chemistry College of ScienceKing Saud UniversityRiyadh 11451Saudi Arabia Department of Electrical Engineering and Automation Shandong University of Science and TechnologyQingdaoShandong 266590China Institute for Advanced Study Shenzhen UniversityShenzhenGuangdong 518060China Department of Chemistry Kansas Polymer Research CenterPittsburg State UniversityPittsburgKS 66762United States Faculty of Science and Technology Madhyanchal Professional UniversityRatibadBhopal 462044India Environmental and Atmospheric Sciences Research Group Scientific Research CenterAl-Ayen UniversityThi-QarNasiriyah 64001Iraq Department of Chemical Engineering King Khalid University Saudi Arabia Department of Chemistry School of SciencesIFTM UniversityMoradabadUttar Pradesh 244102India Research Center for Eco-Environmental Engineering Dongguan University of TechnologyDongguan 523808China School of Environment and Civil Engineering Dongguan University of TechnologyDongguanGuangdong 523808China

Efficient electrocatalytic rupture of energy-rich molecules(H_(2)and O_(2))is a green approach for gener-ating clean energy for modern *** this context,porphyry-type molecular electrocatalysts act intelligently toward oxygen reduction reaction(ORR),a fundamental process in fuel cells,due to their redox-rich chemistry,which involves core metal ions and macrocyclic *** concerned scientific community has tried many times to correlate the ORR intermediates with their formation kinetics and simplify the associated multi H+/e-stages during the ORR process,constructing several volcano plots be-tween catalytic Tafel data,turnover frequencies,and overpotentials for many *** the fact that many review articles on molecular electrocatalysts for ORR have been published,understanding the strategic implications and molecular catalyst intelligence towards homogenous ORR has been poorly *** review examined the relationships between volcano plots of current *** parameters and the Sabatier principle in order to explain the intelligence of molecular electrocatalysts and approaches for their creation,as well as the difficulties and potential prospects of molecular *** facts distinguish this review from previously published articles and will pique the scien-tific community’s interest in avoiding trial-and-error procedures for catalyst creation while also allowing for more exact evaluations of the molecular catalyst’s performance.

关键词： Electrocatalysis Molecular catalysts Oxygen reduction reaction Sabatier principle

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Intelligent Energy Management for EV Charging Stations

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2024年第11期51卷 1853-1861页

作者： Dasi, Swathi Bondalapati, Swarupa Rani Subbaraju, Mummidi P. Nimma, Divya Jangir, Pradeep Reddy, R. Vijaya Kumar Zareena, N. Electronics and Communication Engineering Department Prasad V. Potluri Siddhartha Institute of Technology Andhra Pradesh Vijayawada India Electrical and Electronics Engineering Department Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh Vijayawada India Electrical and Electronics Engineering Department Aditya University Andhra Pradesh Surampalem India University of Southern Mississippi United States Biosciences Department Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India associated with Applied Science Research Center Applied Science Private University Amman Jordan. Computer Science and Engineering Department Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Computer Science and Engineering Department R.V.R. & J. C. College of Engineering Guntur India

The electronics panels and controllers used in electric vehicle (EV) charging stations need to function securely and optimally in countries such as India, where the external temperature remains high for a significant part of the year. This study is the first to use a solar-battery storage integrated switchable glazing architecture to supply HVAC (heating, ventilation, and air conditioning) in the control rooms of electric vehicle charging stations throughout the day. The EV charging station has been equipped with a rooftop-mounted solar PV source as part of an initiative to promote renewable energy and sustainable forms of mobility. The utilization of a vanadium redox flow battery (VRFB) by the system ensures energy security through the provision of a durable solution for storing energy over an extended period of time. A smart scheduling system utilizing IoT technology was demonstrated to effectively meet the glazing load need of buildings in real-time, taking into account dynamic climatic conditions. This system incorporates solar PV, VRFB storage, and the neighborhood power grid. The efficiency of the suggested method was validated using four separate transitory scenarios: sunny, intermittently cloudy, prolongedly cloudy, and low solar radiation with frequent grid outages. Due to its versatility to be applied in various situations, the suggested method has the potential to greatly enhance capacity. © (2024), (International Association of Engineers). All rights reserved.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

IDSDeep-CCD: intelligent decision support system based on deep learning for concrete cracks detection

引用

Multimedia Tools and Applications 2025年第12期84卷 10013-10026页

作者： Abualigah, Sayel M. Al-Naimi, Ahmad F. Sachdeva, Gagan AlAmri, Omran Abualigah, Laith Department of Computer Information Systems Jordan University of Science and Technology Irbid Jordan Gagan Sachdeva Dubai United Arab Emirates Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Computer Science Department Al al-Bayt University Mafraq25113 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Applied Science Research Center Applied Science Private University Amman11931 Jordan College of Engineering Yuan Ze University Taoyuan32003 Taiwan

In an era where Intelligent Decision Support Systems (IDSS) are integral to managing the vast data from Internet of Everything (IoE) systems, this study introduces IDSDeep-CCD, a novel IDSS approach for detecting concrete cracks, a critical issue in civil infrastructure maintenance. Traditional visual inspection methods for crack detection are time-consuming and error-prone. To address this, IDSDeep-CCD employs deep learning, utilizing an open-source dataset of concrete crack images for enhanced accuracy. The system's two-stage approach, featuring feature extraction via pre-trained models and a fully connected network for classification, significantly outperforms existing methods. Our results demonstrate a remarkable 99.9% accuracy rate in crack detection without data augmentation, marking a notable advancement in automatic detection technology. This breakthrough offers practical benefits for the industry by enabling more precise and efficient identification of concrete cracks, paving the way for timely and accurate remedial actions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Transfer Multi-task Learning Approach for Scene Classification 27th

Hierarchical Transfer Multi-task Learning Approach for Scen...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Khoshkangini, Reza Tajgardan, Mohsen Jamali, Mahtab Ljungqvist, Martin Georg Mihailescu, Radu-Casian Davidsson, Paul Internet of Things and People Research Center Department of Computer Science and Media Technology Malmö University Malmö Sweden Faculty of Electrical and Computer Engineering Qom University of Technology Qom Iran Axis Communications AB Lund Sweden

ISBN: (纸本)9783031781063

This paper presents a novel Hierarchical Transfer and Multi-task Learning (HTMTL) approach designed to substantially improve the performance of scene classification networks by leveraging the collective influence of diverse scene types. HTMTL is distinguished by its ability to capture the interaction between various scene types, recognizing how context information from one scene category can enhance the classification performance of another. Our method, when applied to the Places365 dataset, demonstrates a significant improvement in the network’s ability to accurately identify scene types. By exploiting these inter-scene interactions, HTMTL significantly enhances scene classification performance, making it a potent tool for advancing scene understanding and classification. Additionally, this study explores the contribution of individual tasks and task groupings on the performance of other tasks. To further validate the generality of HTMTL, we applied it to the Cityscapes dataset, where the results also show promise. This indicates the broad applicability and effectiveness of our approach across different datasets and scene types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Alternating Minimization for the Downlink of Wideband IRS-Aided mmWave MIMO Systems 26

Alternating Minimization for the Downlink of Wideband IRS-Ai...

引用

26th International ITG Workshop on Smart Antennas, WSA 2023 and 13th Conference on Systems, Communications, and Coding, SCC 2023

作者： Pérez-Adán, Darian Joham, Michael Fresnedo, Óscar González-Coma, José P. Utschick, Wolfgang Castedo, Luis Department of Computer Engineering CITIC Research Center University of A Coruña Spain Defense University Center at the Spanish Naval Academy University of Vigo Marín 36920 Spain Department of Electrical and Computer Engineering Technical University of Munich Munich Germany

ISBN: (纸本)9783800760510

We consider an orthogonal frequency division multiplexing (OFDM) intelligent reflecting surface (IRS)- aided millimeter-wave (mmWave) multiple-input multipleoutput (MIMO) broadcast (BC) system. The IRS phase-shift matrix, the filters, and the precoders are jointly designed to minimize the mean square error (MSE) of the estimated user symbols. This is challenging because the IRS phase-shift matrix is frequency-flat and common to all the users. The optimization problem is solved via the BC-multiple access channel (MAC) duality and following an alternating minimization approach. The results show that the proposed approach leads to large gains with respect to baseline strategies that do not account for the inter-user interference. © VDE VERLAG GMBH · Berlin · Offenbach.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Low crosstalk and high extinction ratio all-optical 4 × 2 encoder based on metal–insulator–metal plasmonic waveguides

引用

Optical and Quantum Electronics 2025年第4期57卷 1-14页

作者： Qiaoling, Tang Afshari-Bavil, Mehdi Rezaei, Mir Hamid School of Physics and Electronic Information Engineering Neijiang Normal University Sichuan Province Neijiang641112 China Photonics Research Center Neijiang Normal University Sichuan Province Neijiang641112 China Department of Communications and Electronics School of Electrical and Computer Engineering Shiraz University Shiraz Iran

This paper presents an all-optical 4 × 2 encoder based on metal–insulator–metal (MIM) waveguides, designed for operation across a wide wavelength range of 1–2 μm. The MIM waveguides consist of SiO2 dielectric strips sandwiched between layers of silver metal. The encoder incorporates a straight waveguide to detect the state of the In0 input. Additionally, it includes one splitter and two combiners with outputs Out0 and Out1 for detecting the states of the In1, In2, and In3 inputs. A key innovation in this work is the distance created between the splitter and combiners, which allows for tuning and improving the encoder output characteristics. The proposed encoder was simulated using the finite-difference time-domain method. It demonstrates a minimum extinction ratio of 11.65 dB and a crosstalk level of − 15.65 dB at a wavelength of 1550 nm. The total footprint of the encoder is less than 8 μm2. Our research indicates that a 4 × 2 encoder utilizing MIM waveguides has not been previously reported. Given its straightforward fabrication process, high extinction ratio, and low crosstalk, the suggested encoder is a promising candidate for a wide range of plasmonic communication and signal-processing applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Crosstalk

来源：评论

学校读者我要写书评

暂无评论

Information Presentation Strategies to Promote Pedestrian Behavior Change in Mixed Spaces with Automated Vehicle

Information Presentation Strategies to Promote Pedestrian Be...

引用

2024 IEEE/SICE International Symposium on System Integration, SII 2024

作者： Nishiura, Yuki Yamada, Hiroyuki Kurazume, Ryo Graduate School of Information Science and Electrical Engineering Kyushu University Japan Center for Sustainability - Connective Automation Hitachi Ltd. Research and Development Group Autonomous Control Research Department Ibaraki312-0034 Japan Kyushu University Faculty of Information Science and Electrical Engineering Fukuoka819-0395 Japan

ISBN: (纸本)9798350312072

This paper introduces an information presentation strategy for pedestrians, aiming to enhance traffic efficiency in a mixed pedestrian-automated vehicle environment, such as a public road. While automated driving technology has made remarkable progress, interactions with pedestrians on regular roads have mostly been studied in virtual environments using virtual reality goggles. According to these studies, potential traffic efficiency and safety issues arise from pedestrians' limited understanding of automated vehicle behavior. To address this, we propose a human-machine interface employing a head-mounted display (HMD) to mitigate traffic efficiency degradation caused by pedestrians. The proposed system draws upon behavioral economics principles to encourage pedestrians to modify their behavior and develop better interactions with automated vehicles. Simulations were conducted to identify an information presentation strategy that strongly supports learning, and its effectiveness was further validated through experiments involving a real vehicle. Notably, the experimental results confirmed that the information presentation strategies proven effective in simulations also facilitated pedestrian learning during real-world interactions. © 2024 IEEE.

关键词： Virtual reality

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：