检索结果-内蒙古大学图书馆

16th ACM Multimedia Systems Conference, MMSys 2025

作者： Chaudhary, Shubham Mishra, Navneet Gambhir, Keshav Rajore, Tanmay Bhattacharya, Arani Maity, Mukulika Dept. of Computer Science & Engineering IIIT Delhi Delhi New Delhi India

ISBN: (纸本)9798400714672

The growing popularity of live online classes, even in remote areas, stresses the need for a good and seamless quality of experience to enhance learning. However, these bandwidth-hungry applications challenge the current cellular networks to maintain consistent bandwidth and latency. In this work, we, therefore, propose using the collaboration of multiple devices with their individual cellular networks to support such live video streaming. We design a content-aware system Compact that splits video into foreground and background using video tiles (independently encoded spatial blocks) and streams them over different paths. Compact depends on its scheduler, which exhaustively searches for the best quality based on the network estimates. We extensively evaluate our system using network traces while walking and traveling on the bus or car. Compared to the single path, Compact manages to reduce the median stall and E2E lag by 70.6% and 28.57%, and the tail stall and lag by 83.9% and ≈ 80% on a bus trace. Furthermore, we performed a live experiment to test Compact on the actual cellular network. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Activity Prediction for Localizing the Events in Imagined Speech EEG Signals 13

Activity Prediction for Localizing the Events in Imagined Sp...

引用

13th International Winter Conference on Brain-computer Interface, BCI 2025

作者： Balasubramanian, Arun Pandey, Kartik Veer, Gautam Samanta, Debasis Dept. of Computer Science and Enginnering Indian Institute of Technology Kharagpur India

ISBN: (纸本)9798331521929

Imagined speech electroencephalogram (EEG) signals are often collected for longer durations than necessary, leading to a difficulty in understanding the generation of EEG during the task as it is likely that most of the data collected is that of resting state. Developing a filter to identify the segments of the trials with actual information and remove those that contain the EEG from resting states could significantly advance our understanding of EEG signals in neuroscience and biomedical engineering. This work uses derivatives-based features to form the feature vectors used to train the classifiers. Based on feature importance analysis, it has been found that the derivative-based features contributed more to the classification than the traditionally preferred feature, band power in the alpha frequency band. Using the proposed features, the classification performance experienced a significant enhancement, surpassing the results reported in previous studies. The greater accuracy of the classifiers with the proposed features implies that they are effective at filtering out the resting state segments from imagined speech EEG signals. © 2025 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Energy Recovery and Power Management in EVs Using Supercapacitors and Regenerative Braking 2

Energy Recovery and Power Management in EVs Using Supercapac...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Shib, Sowrov Komar Dipto, Durjoy Roy Rahman, Md Tanvir Islam, Md Ashikul Islam, Md Mahafuzul Shufian, Abu American International University-Bangladesh Dept. of Electrical and Electronics Engineering Dhaka Bangladesh Dhaka Bangladesh Lamar University Dept. of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798331506995

Regenerative braking (RB) is crucial in enhancing the efficiency and sustainability of electric vehicles (EVs) by converting kinetic energy into usable electric energy during braking. However, current systems face challenges in maximizing energy recovery and managing power effectively. This research presents an optimized regenerative braking system that combines the benefits of supercapacitors and Brushless DC (BLDC) motors to improve energy recovery efficiency. The study introduces advanced control algorithms for BLDC motors to ensure precise and reliable operation across various driving conditions. Furthermore, refined power management strategies are developed to optimize energy storage between supercapacitors and batteries, enhancing overall system efficiency. The proposed model employs modern control techniques and power management solutions, allowing for real-time energy optimization during braking. With an overall energy recovery efficiency of 92.5%, the system shows significant promise in minimizing energy losses and supporting the sustainability goals of electric vehicles. © 2025 IEEE.

关键词： Battery management systems

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based Monitoring System for Detecting Slope Movement

An IoT-Based Monitoring System for Detecting Slope Movement

引用

Geotechnical Frontiers 2025: Geotechnics of Natural Hazards

作者： Alam, Md. Jobair Bin Manzano, Luis Salgado Debnath, Rahul Ahmed, Ahmed Abdelmoamen Williams, Synia Hartsfield, Markus Dept. of Civil and Environmental Engineering Prairie View A&M Univ. TX United States Dept. of Computer Science TX United States Dept. of Civil and Environmental Engineering TX United States

ISBN: (数字)9780784485996

Shallow landslides pose significant hazards to communities, infrastructure, and natural ecosystems, particularly in regions with steep slopes and vulnerable soil conditions. The slope movement naturally occurs slower depending on environmental conditions and man-made activities and is often triggered by climatic conditions such as precipitation and temperature fluctuations. The initial movement of the slope remains unsighted as the overall earthen slopes’ performance seems satisfactory. However, the initial movement of the slope eventually causes major failure. Therefore, it is crucial to monitor and detect slope movements in real-time, particularly for slopes prone to failure or steep, and timely actions should be taken for the durability and resilience of the earthen slopes. However, monitoring each slope in real-time is a challenging task. This study aimed to develop a distributed sensing system, including slope movement and hydrologic responses executing on the Internet of Things (IoT) at a prototype slope. The proposed system uses various IoT sensors, including tilt sensors and hydrologic sensors, such as moisture sensors and tensiometers, to build a laboratory prototype embankment (0.55 m length, 0.31 m width, and 0.31 m height). The embankment prototype was constructed with Fat Clay (CH). An IoT-integrated data processing and computational system was developed. The experimental results showed that our system could detect negligible movement rotation (0.03°) of slopes. The study’s outcome indicated that our IoT-based slope monitoring system can be cheap and implementable for failure-prone slopes in the field for an effective monitoring system. © ASCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Brain Tumor Identification through Convolutional Neural Networks and Transformer Models 15

Enhancing Brain Tumor Identification through Convolutional N...

引用

15th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2025

作者： Dudam, Nerajdattu Chato, Lina Motupalli, Nagamani Kashyap, Kristipati Thoyajaksha Sane, Madhusree Bollina, Mounika University of South Dakota Dept. Computer Science Vermillion United States

ISBN: (纸本)9798331507695

An automatic diagnosis of brain tumors based on Deep Learning (DL) is a promising research field to enhance the diagnosis and prognosis of brain tumors. This paper presents an exploration into the use of Convolutional Neural Networks (CNNs) and Vision Transformers (ViT) for brain tumor classification, specifically identifying glioma, meningioma, pituitary tumors, and no tumor from brain Magnetic Reasons Imaging (MRI) scans. We implemented different approaches, such as 1) developing a custom CNN model from scratch, 2) leveraging pre-trained models based on Transfer Learning (TL) (including VGG16 and ResNet50), 3) developing a custom ViT model from scratch, and 4) leveraging pre-trained model in vision transformers, such as ViT B16. A publicly available labeled dataset is used to develop and test our proposed classification Deep Learning models. Our findings reveal that both custom-trained and pre-trained CNN and ViT models achieve high accuracy. The model ViT B16 based on transferred learning achieves the best accuracy of 97.6%, which is slightly better than the CNN models. To enhance the accuracy of the prediction model and reduce the misclassifications, ensemble model based on the combination of ViT B16 and CNN model;this approach increases the accuracy to 98%. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

QaSAL: QoS-aware State-Augmented Learnable Algorithms for Coexistence of 5G NR-U/Wi-Fi 59

QaSAL: QoS-aware State-Augmented Learnable Algorithms for Co...

引用

59th Annual Conference on Information sciences and Systems, CISS 2025

作者： Fasihi, Mohammad Reza Mark, Brian L. George Mason University Dept. of Electrical and Computer Engineering and Wireless Cyber Center FairfaxVA United States

ISBN: (纸本)9798331513269

With the increasing demand for wireless connectivity, ensuring the efficient coexistence of multiple radio access technologies in shared unlicensed spectrum has become an important issue. This paper focuses on optimizing Medium Access Control (MAC) parameters to enhance the coexistence of 5G New Radio in Unlicensed Spectrum (NR-U) and Wi-Fi networks operating in unlicensed spectrum with multiple priority classes of traffic that may have varying quality-of-service (QoS) requirements. In this context, we tackle the coexistence parameter management problem by introducing a QoS-aware State-Augmented Learnable (QaSAL) framework, designed to improve network performance under various traffic conditions. Our approach augments the state representation with constraint information, enabling dynamic policy adjustments to enforce QoS requirements effectively. Simulation results validate the effectiveness of QaSAL in managing NR-U and Wi-Fi coexistence, demonstrating improved channel access fairness while satisfying a latency constraint for high-priority traffic. © 2025 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Integrated Word2Vec-based Speech Annotations for Enhanced EEG Decoding of Speech Intentions 13

Integrated Word2Vec-based Speech Annotations for Enhanced EE...

引用

13th International Winter Conference on Brain-computer Interface, BCI 2025

作者： Jang, Se-Na Park, Hyeong-Yeong Kim, Seong-Wook Yu, Seong-Hyun Lee, Minji Jeong, Ji-Hoon Dept. Computer Science Chungbuk National University Cheongju Korea Republic of Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon Korea Republic of

ISBN: (纸本)9798331521929

Brain-computer interface (BCI) technology has promising applications as an intuitive communication tool and in fields such as language rehabilitation. This study aims to decode human speech intentions by analyzing EEG signals recorded during actual and imagined speech. EEG data were collected using a 64 channels system, with preprocessing to remove artifacts. Automatic speech recognition (ASR) was used to extract precise speech onset times, generating time-specific speech annotations corresponding with EEG data. Pretrained Word2Vec embeddings were integrated to provide semantic context, combining neural signals with high-level linguistic features. Support vector machine (SVM), linear discriminant analysis (LDA) were employed for decoding. The results demonstrate that integrating speech annotations improves decoding accuracy, even for imagined speech, highlighting the potential of BCI technology for advanced applications in communication and rehabilitation. © 2025 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A New Method for One-Pedal Driving With Fuzzy-Based Efficiency-Optimization Algorithm

A New Method for One-Pedal Driving With Fuzzy-Based Efficien...

引用

2025 IEEE International Conference on Mechatronics, ICM 2025

作者： Heydrich, Marius Hammer, Tim Mitsching, Thomas Ivanov, Valentin Technische Universitä t Ilmenau Dept. of Computer Science and Automation Ilmenau Germany Technische Universitä t Ilmenau Dept. of Mechanical Engineering Ilmenau Germany

ISBN: (纸本)9798331533892

This paper presents a case study on adaptive one pedal driving for a battery electric sport utility vehicle with in wheel based rear-wheel drive that is able to adjust the drive pedal curve automatically. In addition, a fuzzy logic observes the state of the electric machines to adapt the motor torque to the most efficient region. The control method was tested in a co-simulation using a validated vehicle model and a driver-in-the-loop strategy. Within the experiments, an improvement in energy recovery of up to 4.8 % was achieved compared to the classic brake blending. In addition, the total number of brake pedal applications is ten times lower, which translates into less driving stress and greater driving comfort, especially on long distance trips, proving the effectiveness of the controller. © 2025 IEEE.

关键词： Vehicle wheels

来源：评论

学校读者我要写书评

暂无评论

Smith Predictor Based Fractional LFC Strategy for Storage Supported Thermal Power System Amid Communication Dead Time and Cyber Threats

引用

IEEE Transactions on Industry Applications 2025年第3期61卷 4515-4529页

作者： Kumar, Deepak Raja, G. Lloyds Alkhatib, Mohamed Deep, Akash Kumar Muduli, Utkal Ranjan United Arab Emirates University Department of Electrical and Communication Engineering Abu Dhabi Al Ain15551 United Arab Emirates National Institute of Technology Department of Electrical Engineering Patna800005 India Khalifa University APEC Dept. of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates

Communication dead time (CDT) amid integration of renewable energy sources (RESs) and energy storage systems (ESSs) into modern power system networks can result in instabilities, phase lags and sluggish corrective action when dealing with frequency and tie-line power deviations. To compensate CDT, a Smith predictor based Fractional Order Proportional-Integral-Derivative with Integrator (FPIDI) controller is analytically designed for a dual-area thermal power system (TPS) with integrated RES, battery ESS, flywheel ESS and Ultra-capacitors. The FPIDI controller is designed using a modified internal model control (IMC) theory that is based on the frequency-relocated fractional-order model of the TPS. This modified IMC method eliminates the need of phase-lag inducing IMC filter. The performance-robustness tradeoff is enhanced by appropriate selection of the single tuning parameter (frequency-relocation factor (ψ)) by minimizing the integral of time-weighted absolute value of area control errors. The proposed controller is validated both by simulation and hardware-in-loop implementation to show its practical feasibility. © 1972-2012 IEEE.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Self-Aware Financial Inclusion System for Digital Society 3

An Intelligent Self-Aware Financial Inclusion System for Dig...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Rawat, Ruchira Goyal, Himanshu Rai Sharma, Sachin Kotiyal, Bina Graphic Era Deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798331542375

The continuous advancement in technology has restructured industries, due to innovations in Artificial Intelligence (AI) the financial sector endorsing astonishing transformations. This research recognizes the potential of AI in fintech for digital society while focusing on the transition toward Industry 5.0, which is based on human-AI collaboration. AI technologies, such as Artificial Generative Intelligence (AGI) and Artificial Narrow Intelligence (ANI), are limited in handling intricate, vigorous financial environments. ANI has improved efficiency via credit risk assessment, customer service automation, and fraud detection, whereas AGI aims for more comprehensive decision-making capabilities. ANI and AGI are creating a gap in accomplishing a truly responsive, customer-centric system as it cannot fully adapt to subtle decision-making or erratic market shifts. This paper suggests a Super Artificial Intelligence (SAl) as a promising solution to overcome limitations, standing SAI-based design for a unified nifty digital financial system. Its forward-thinking decision-making proficiencies, self-learning, and flexibility are expected to transmute financial aligned with Industry 5.0's human-centered principles by providing adaptive services, enhancing financial inclusion and personalized. The study identifies key challenges in current AI applications, through a comprehensive review of literature and case studies, such as algorithmic errors and customer facility, and highlights how SAI could offer a more autonomous and ethical approach to financial decision-making. The paper concludes by underscoring the importance of continuous AI validation, ethical considerations, and human oversight to ensure sustainable, secure, and customer-focused financial systems. © 2025 IEEE.

关键词： Fintech

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：