检索结果-内蒙古大学图书馆

Disruptive Technologies (ICDT), International Conference on

作者： Geetha Ponnaian Jayanthi. N R. Sarasu Sajitha. L.P R. Ramalakshmi Manimegalai L Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Thandalam Chennai India School of Management Studies Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and business system R. M. K Engineering College Kavaraipettai Tamilnadu India Department of Electronics and Communication Engineering Ramco Institute of Technology Rajapalayam Department of Electronics and Communication Engineering R.M.K. College of Engineering and Technology Chennai India

This research focuses on enhancing the spectral efficiency of 5G networks through the utilization of nonlinear stochastic precoding techniques. The proposed approach aims to mitigate the detrimental effects of channel impairments and noise by employing advanced precoding schemes that exploit the statistical properties of the wireless channel. By incorporating nonlinear precoding algorithms and stochastic optimization methods, the system can dynamically adapt to varying channel conditions, resulting in improved data transmission rates and overall spectral efficiency. Through extensive simulations and analysis, the effectiveness of the proposed method is demonstrated, showcasing its potential to significantly enhance the performance of 5G networks in real-world scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DDPS: Dynamic Differential Pricing-Based Edge Offloading system With Energy Harvesting Devices

引用

IEEE Transactions on Network science and engineering 2025年

作者： Xue, Hai Xia, Yun Xiong, Neal N. Zhang, Di Pei, Songwen University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Sul Ross State University Department of Computer Science and Mathematics AlpineTX79830 United States Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China Zhengzhou University Henan International Joint Laboratory of Intelligent Health Information System Zhengzhou450001 China Zhengzhou University National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China

Mobile edge computing (MEC) mitigates the energy and computation burdens on mobile users (MUs) by offloading tasks to the network edge. To optimize MEC server utilization through effective resource allocation, a well-designed pricing strategy is indispensable. In this paper, we propose a dynamic differential pricing scheme (DDPS) for an edge offloading scenario with energy harvesting devices, which determines prices based on computing resource usage to enhance edge server (ES) utilization. First, an offloading decision algorithm is proposed to balance harvested and consumed energy, determining whether and how much data to offload. Second, a Stackelberg game-based differential pricing algorithm is proposed to optimize computing resource allocation for MUs and reallocate surplus resources to delay-sensitive devices. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme. Specifically, in comparison to the existing best-performing pricing scheme, for different task arrival rates, DDPS can achieve a 5.3% decrease in average execution delay, a 1.7% increase in ES utility (Userver, which represents the payment from MUs minus penalties for discarded tasks), and a 2.1% increase in the average ratio of service for MUs. In addition, DDPS also improves 2.8% Userver on average with different ES computation capacities. © 2025 IEEE. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Identifying Trustworthiness Challenges in Deep Learning Models for Continental-Scale Water Quality Prediction

arXiv

引用

arXiv 2025年

作者： Xia, Xiaobo Liu, Xiaofeng Liu, Jiale Fang, Kuai Lu, Lu Oymak, Samet Currie, William S. Liu, Tongliang School of Computer Science University of Sydney Australia Department of Statistics and Data Science Yale University United States Michigan Institute for Data and AI in Society University of Michigan United States School for Environment and Sustainability University of Michigan United States College of Information Science and Technology Penn State University United States Department of Earth System Science Stanford University United States Department of Electrical Engineering and Computer Science University of Michigan United States

Water quality is foundational to environmental sustainability, ecosystem resilience, and public health. Deep learning models, particularly Long Short-Term Memory (LSTM) networks, offer trans-formative potential for large-scale water quality prediction and scientific insights generation. However, their widespread adoption in high-stakes decision-making, such as pollution mitigation and equitable resource allocation, is prevented by unresolved trustworthiness challenges including fairness, uncertainty, interpretability, robustness, generalizability, and reproducibility. In this work, we present the first comprehensive evaluation of trustworthiness in a continental-scale multi-task LSTM model predicting 20 water quality variables (encompassing physical/chemical processes, geochemical weathering, and nutrient cycling) across 482 U.S. basins. Our investigation uncovers systematic patterns of model performance disparities linked to basin characteristics, the inherent complexity of biogeochemical processes, and variable predictability, emphasizing critical performance fairness concerns. We further propose methodological frameworks for quantitatively evaluating critical aspects of trustworthiness, including uncertainty, interpretability, and robustness, identifying key limitations that could challenge reliable real-world deployment. This work serves as a timely call to action for advancing trustworthy data-driven methods for water resources management and provides a pathway to offering critical insights for researchers, decision-makers, and practitioners seeking to leverage artificial intelligence (AI) responsibly in environmental management. Copyright © 2025, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence for Antenna Sensor Modeling

Explainable Artificial Intelligence for Antenna Sensor Model...

引用

Communications and Networking (MeditCom), IEEE International Mediterranean Conference on

作者： Wenkai Tan Jayaprakash B. Shivakumar Rishikesh Srinivasaraghavan Govindarajan Nicholas Reed Daewon Kim Eduardo Rojas Yongxin Liu Houbing Song Department of Information System University of Maryland Baltimore County Maryland USA Department of Electrical Engineering & Computer Science Embry-Riddle Aeronautical University Florida USA Department of Aerospace Engineering Embry-Riddle Aeronautical University Florida USA Department of Mathematics Embry Riddle Aeronautical University Florida USA

ISBN: (数字)9798350309485

ISBN: (纸本)9798350309492

The extensive application of Artificial Intelligence and Machine Learning is notable in additive manufacturing realms such as manufacturing supervision and error identification. Nonetheless, the escalating employment of AI in vital processes during production necessitates its decision-making and prediction abilities to display interpretability. Consequently, the need for explainable Artificial Intelligence (xAI) in such manufacturing procedures becomes *** this paper, we develop an explainable AI framework for antenna sensor modeling during additive manufacturing. An explainable machine learning method is used in this framework for modeling based on the frequency response data from the antenna sensor. In this approach, the explainable dimension reduction method can interpret the chosen components using projection matrix. The decision tree regressor exhibits proficiency in efficiently handling small datasets and retaining commendable *** demonstrate that the S-parameter prediction generated by our method are more accurate and reliable. This method can be generalized to a new *** work could provide a useful tool for antenna sensor modeling and signal processing fields during additive manufacturing.

关键词： Production Learning (artificial intelligence) Signal processing Three-dimensional printing Frequency response Manufacturing Scattering parameters

来源：评论

学校读者我要写书评

暂无评论

Automatic LPI Radar Waveform Recognition Using Vision Transformer

Automatic LPI Radar Waveform Recognition Using Vision Transf...

引用

IEEE International Conference on Radar

作者： Junseob Kim Sunghwan Cho Sunil Hwang Yeongyoon Choi Department of Electrical Engineering Korea Military Academy Republic of Korea Maneuver System Coordination and Contract Team Defense Acquisition Program Administration Republic of Korea Department of Electrical Engineering and Computer Science GIST Republic of Korea

This paper investigates the classification of low probability of intercept (LPI) radar signals by exploiting the intrinsic advantages of the Vision Transformer (ViT). Due to the characteristics of LPI radar signals, such as intrapulse modulation, wide frequency bands, and low transmission power, these signals are challenging to be detected and classified using traditional analytic methods. This has led to the adoption of various deep learning techniques to overcome these limitations. On the one hand, the ViT, originally developed for natural language processing, has demonstrated outstanding performance in computer vision by replacing the structure of the convolutional neural network (CNN) with the transformer, specifically leveraging self-attention. Therefore, this paper explores a method based on the ViT technique for classifying LPI signal images. The simulation results show that the proposed ViT method outperforms the traditional CNN method by 12.8% at −10dB SNR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Green and Blue Hydrogen Production Potential in Saudi Arabia

SSRN

引用

SSRN 2024年

作者： Al-Khelaiwi, Muhannad S. Al-Masaabi, Talal A. Farag, Hany Rehman, Shafiqur Chemical Engineering Department King Fahd University of Pertolium & Minerals Dhahran Saudi Arabia Interdsiciplinary Research Center for Renewable and Power System King Fahd University of Pertolium & Minerals Dhahran Saudi Arabia Electrical Engineering and Computer Science Department York University ON Canada

The Saudi kingdom has rich renewable energy resources, specifically for wind and solar in addition to massive natural gas reserves. This paper investigates the potential of both green and blue hydrogen production for five selected cities in Saudi Arabia. To that end, a techno-economic model is formulated to conduct the study. Four renewable energy scenarios are evaluated for a total of 1.9 GW to reveal the best scenario of Green Hydrogen Production (GHP) in each city. Also, Blue Hydrogen Production (BHP) is investigated for three cases of Steam Methane Reforming (SMR) with different percentages of carbon capture. The economic analysis for both GHP and BHP is performed by calculating the Levelized Cost of Hydrogen (LCOH) and cash flow. The LCOH for GHP range for all cities ($3.27/kgH2 -$12.17/kgH2) with the lowest LCOH is for NEOM city (50%PV-50%wind) ($3.27/kgH2). BHP LCOH are $0.534/kgH2, $0.647/kgH2, and $0.897/kgH2 for SMR wo CCS/U, SMR 55% CCS/U, and SMR 90% CCS/U respectively. © 2024, The Authors. All rights reserved.

关键词： Cost benefit analysis

来源：评论

学校读者我要写书评

暂无评论

Based on Internet of Things Tracking of Hand Hygiene and Practices 2nd

Based on Internet of Things Tracking of Hand Hygiene and Pra...

引用

2nd International Conference on Mechanical and Energy Technologies , ICMET 2021

作者： Jayadeva, Sujay Mugaloremutt Singh, Krishanveer Karnan, Lokanayaki Franklin Telfer, L. Bharti, Anupama Dhiman, Viney Department of Health System Management Studies JSS Academy of Higher Education and Research Karnataka Mysuru India GLA University Mathura India Department of Computer Science St. Francis de Sales College Bengaluru India Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai India Department of Sociology and Social Work Himachal Pradesh University Himachal Pradesh Shimla India Department of Cardiology PGIMER Chandigarh India

ISBN: (纸本)9789811901072

The study explores the tracking and practices essentiality in hospitals and health facilities, because related infections, such as higher risks and acceleration of illness, can have significant effects on health care. Human observers tracking and Practices have problems of their own, such as loss of observation concentration, accumulation of human mistake and expert deformation. In this investigation, the results of two internet-based techniques for controlling the hand hygiene of medical personnel during patient visits were carried out and evaluated. As base stations and smart phones, we employed ESP modules as mobile nodes and calculated the range to be located in the patient's room using Bluetooth RSSI values. We analyzed the RSSI in the proximity solution from a sensor host measured on different ESP nodes/module and used the premise that the sensor host is nearest to the ESP node which offers the maximum RSSI values. We utilized the RSSI value to measure the location between mobile nodes and every ESP node in the trilateration method and we applied the trilateration technique to identify the mobile node inside the room. Our tests have shown that 20% of the solution based on proximity was erroneous, whilst the 8% of the solution based on trilateration was erroneous. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Massive Fabrication of Carbon Nanotube Transistors by Surface Tension-Driven Inkjet-Printing Method

Massive Fabrication of Carbon Nanotube Transistors by Surfac...

引用

IEEE International Conference on Flexible and Printable Sensors and systems (FLEPS)

作者： Soohyun Park Minhye Shin Hongki Kang Yoonhee Lee Division of Electronics and Information System Daegu Gyeongbuk Institute of Science and Technology (DGIST) Daegu South Korea Department of Electrical Engineering and Computer Science Daegu Gyeongbuk Institute of Science and Technology (DGIST) Daegu South Korea

Carbon nanotube field-effect transistors (CNTFETs) have been ideal nanoelectronics in semiconductor technologies with exceptional electrical properties. Scaling the CNT -FET fabrication enables the expansion of the application fields. However, placing nanotubes with uniform alignment and controlled density to the electrode contacts has been the maj or challenge in massive manufacturing. Here, we introduce the in-place inkjet-printing method for fabricating CNTFETs with controlled numbers of connected CNTs at a single CNT level. A picoliter (pL) drop of CNT ink is printed to the pre-patterned electrode arrays in parallel over a four-inch silicon wafer, allowing adaptive manufacturing without additional lithographic processes. Drops form thin films on the metal electrode patterns driven by the surface tension flow, diluting the surface density of CNT on the one-micrometer channel gap and avoiding bundled coffee ring edges. Finally, single CNTs are correctly bridged to the electrodes with high statistical yield. This process enables reproducible and high-throughput single CNT deposition, integrating into the FET manufacturing process, and can be used for versatile nanoelectronics applications, such as biosensors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor Dynamic Fusion Based Modality-Imbalanced Multimodal Federated Learning in Mobile Edge Computing for Consumer Applications

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Nie, Xin Yi, Lingzhi Yang, Laurence T. Deng, Xianjun Fan, Fulan Zhang, Hongtao Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei EngineeringResearch Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Zhongnan University of Economics and Law School of Information and Safety Engineering Wuhan430074 China Huazhong University of Science and Technology School of Computer Science and Technology Wuhan China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou China St. Francis Xavier University Department of Computer Science Antigonish Canada South-Central Minzu University School of Education Wuhan430074 China

Mobile edge computing extends the capabilities of computation and storage from the cloud to the edge, enabling local data storage and processing. This computing paradigm complements federated learning (FL), as it satisfies the need for privacy protection while providing efficiency and quick response. In consumer applications, multimodal data is experiencing explosive growth. Therefore, multimodal FL has emerged as a crucial research area. However, applying traditional FL methods directly to multimodal data poses certain challenges. Additionally, issues like sensor failures result in modality-imbalanced data among clients, i.e., the number and type of data modalities between client devices vary. Hence, it is imperative to design specialized FL frameworks and models specifically tailored for analyzing multimodal data. To address these challenges, we propose a tensor fusion-based multimodal federated learning (TenMFL). First, a tensor dynamic fusion network is designed for addressing the challenge of multimodal data fusion. This approach separates the parameter forward computation and the modal fusion computation, effectively resolving issues related to client-side modality imbalance. Second, we introduce a hybrid fusion method that combines feature fusion and decision fusion to further exploit the complementarity of multimodal data. We evaluate TenMFL on three multimodal datasets, experimental results demonstrate our superior performances. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition of Humans using modern technology of AI: A Survey

Emotion Recognition of Humans using modern technology of AI:...

引用

Innovative Approaches in Smart Technologies (ISAS), International Symposium on

作者： Ahmed Adil Mohammed Alheeti Mustafa Muhanad M. Salih Alaa Hamid Mohammed Mostafa A. Hamood Nemer Radhwan Khudhair Ahmed Thair Shakir Department of Computer Engineering Karabuk University Turkey Department of Computer Science and information system AL Mansour University College Iraq-Baghdad Department of Medical Instruments Techniques Engineering Al-Maarif University College Department Of Chemical Engineering College Of Engineering University Of Baghdad Baghdad Iraq Department of Biophysics College of Applied Sciences University of Anbar Ramadi Iraq

This comprehensive investigation and evaluation of the subject matter of emotion recognition is presented, focusing on the broader implications for society at large. The study utilizes a thorough analysis of scholarly literature and practical observations to establish a theoretical framework that facilitates comprehension of the topic under investigation. The findings have considerable implications for future investigations and pragmatic applications. Emotion recognition holds immense importance in diverse domains such as human-computer interaction and healthcare. The analysis of techniques used for emotional recognition includes facial expression assessment, speech patterns analysis, physiological signal interpretation, music perception, and written expression evaluation. The study presents a comprehensive overview of research methodologies commonly used in emotion recognition, discussing datasets, feature extraction techniques, and classification algorithms. The analysis of challenges and limitations pertaining to emotion recognition systems, including privacy concerns, is also discussed. Performance evaluation is analyzed through various methods, including machine assessment and self-report. The significance of continued investigation within the domains encompassing data integration across diverse modalities, the creation of robust classification algorithms, and the exploration of the intricate connection between the brain and affective states is underscored.

关键词：

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：