检索结果-内蒙古大学图书馆

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Aritra Chowdhury Sourav Dey Sohrab Hossain Mehdi Hasan Sunzida Chowdhury Department of Computer Science and Engineering East Delta University Chittagong Bangladesh Department of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh School of Science Engineering & Technology East Delta University Chittagong Bangladesh Graduate School of Computer Science and Engineering Yeshiva University New York USA Department of Information Science University of Cumberlands New York USA

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

Heart failure is one of the global health issues that is needed for precise prognostic instruments. In order to predict survival and time-to-event outcomes in patients with heart failure, this study assesses machine learning techniques. Most effective prediction models are determined for heart failure prognosis by combining clinical information and evaluating model performance. According to the results, the LightGBM classifier had the lowest accuracy at 77%, while the SVM classifier had the highest accuracy at 88%. These findings suggest that machine learning can greatly improve clinical judgement in cardiovascular medicine and advance patient-focused treatment.

关键词： Support vector machines Heart Accuracy Explainable AI Instruments Predictive models Cardiovascular diseases Clinical diagnosis Prognostics and health management

来源：评论

学校读者我要写书评

暂无评论

Light-assisted hierarchical fabrication of two-dimensional surfaces using DNA-functionalized semiconductor nanocrystal quantum dots

arXiv

引用

arXiv 2023年

作者： Senel, Zeynep Phul, Ruby Yazıcı, Ahmet Faruk Akrema Taze, Emirhan Erdem, Talha Department of Electrical and Computer Engineering Graduate School of Engineering and Natural Sciences Abdullah Gül University Kayseri Turkey Department of Electrical-Electronics Engineering Abdullah Gül University Kayseri38080 Turkey Department of Nanotechnology Engineering Abdullah Gül University Kayseri38080 Turkey

The development of novel strategies for self-assembly in the field of nanotechnology has witnessed remarkable progress in recent years. Here, we present a DNA-driven programmable self-assembly to fabricate the targeted nanophotonic structures. The exploitation of the programmable properties of DNA and the unique optical properties of QDs unfolds the ability to engineer complex nanostructures with laser irradiation. The main advantages of this method are the precise interaction of colloidal quantum dots (QDs)/nanoparticles (NPs) with the substrate and its reversibility in tuning the temperature of the medium. Two-dimensional (2D) hierarchical patterns of QD-ssDNA (ss-single stranded) conjugates were formed over the amine-ssDNA (NH-ssDNA complementary to the ssDNA conjugated with QDs) coated glass substrates using the laser (green laser light) radiation for3 or4 h. The localised heating effect of laser created a dark spot on the substrate where the laser was irradiated. The optical microscopy images confirmed the effect of laser irradiation on the coating behaviour of QD-ssDNA conjugates on the substrate. Further, green-emitting QD-ssDNA were coated onto the hole created by laser radiation over the red-emitting QD-ssDNA-coated substrate. The optical properties of DNA-functionalized QDs can be actively controlled on the complementary DNA-functionalized glass surface by an external optical excitation. The results of this study demonstrate the potential of light-driven self-assembly as a powerful tool for fabricating desired nanostructures of DNA-QD conjugates. This technique holds promise for various applications, including the development of advanced optical devices, nanophotonic circuits, and bioengineering systems. © 2023, CC BY-NC-SA.

关键词： Semiconductor quantum dots

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tong Liu Dongyang Xu Tiantian Zhang Shilong Zhang Jinhua Chen Keping Yu Victor C. M. Leung Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The accelerated development of the Industrial Internet of Things (IoT) has significantly enhanced the computational efficiency and processing capabilities of Wireless Consumer Application Networks (WCAN). Despite these advancements, the performance of WCAN remains constrained by the inherent limitations in computational capacity and energy resources of wireless devices. To address these issues, this paper proposes a wireless powered-mobile edge computing system with Reconfigurable Intelligent Surface (RIS) assistance for WCAN, where wireless consumer devices can not only harvest energy from access point, but also offload computing tasks to edge server with the help of RIS. Aiming to maximize the system computation rate, a non-convex problem is developed and a block optimization with deep reinforcement learning (BO-DRL) scheme is proposed. First, the RIS phase shifts in the Wireless Power Transfer (WPT) stage and offloading stage are optimized using closed-form solutions and the gradient ascent algorithm, respectively. Subsequently, the offloading strategies are optimized using deep reinforcement learning, and a convex optimization algorithm is employed to obtain the time allocation for the WPT and offloading stages. Numerical results illustrate that the BO-DRL algorithm greatly enhances computation rate by 20% compared to without RIS.

关键词： Wireless communication Training Performance evaluation Wireless power transfer Reconfigurable intelligent surfaces Deep reinforcement learning Convex functions Resource management Servers Uplink

来源：评论

学校读者我要写书评

暂无评论

A Study of Parameters Required for a Thermogram Dataset in Obesity Detection: A Systematic Review

A Study of Parameters Required for a Thermogram Dataset in O...

引用

2021 International Conference on computer System, Information Technology, and electrical engineering, COSITE 2021

作者： Leo, Hendrik Saddami, Khairun Roslidar, Roslidar Oktiana, Maulisa Arnia, Fitri Munadi, Khairul Universitas Syiah Kuala Post Graduate Programme in Engineering Banda Aceh Indonesia Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh Indonesia

ISBN: (纸本)9781665425094

Developing an early detection system of obesity is very important to prevent the increase rate of obesity. Infrared thermography (IRT) can be a potential approach to an early detection of obesity. Deep learning (DL) models can interpret thermogram acquired from IRT. However, studies related to DL based on IRT are still few, and access to thermograms datasets is limited. In this article, we aim to: (1) summarize studies on thermal image datasets of obesity and (2) discuss parameters that need to be considered in acquiring and building a thermal image dataset of obesity. A comprehensive online search was performed in different databases, and the inclusion criteria fitted 12 studies. The collected studies are summarized, and the parameters that need to be considered are discussed. The parameters such as participant quantity, participant condition, image quantity, and body region need to be readjusted with the study's objectives. The other parameters, such as participant selection and control parameters, room protocol, and thermal camera settings need to be configured to reduce BAT activation factors during image acquisition. © 2021 IEEE.

关键词： Thermography (temperature measurement)

来源：评论

学校读者我要写书评

暂无评论

Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Shen, Xuemin Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The Department of Electrical and Computer Engineering University of Waterloo Canada The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Artificial Intelligence-Generated Content (AIGC) refers to the use of AI to automate the information creation process while fulfilling the personalized requirements of users. However, due to the instability of AIGC models, e.g., the stochastic nature of diffusion models, the quality and accuracy of the generated content can vary significantly. In wireless edge networks, the transmission of incorrectly generated content may unnecessarily consume network resources. Thus, a dynamic AIGC service provider (ASP) selection scheme is required to enable users to connect to the most suited ASP, improving the users’ satisfaction and quality of generated content. In this article, we first review the AIGC techniques and their applications in wireless networks. We then present the AIGC-as-a-service (AaaS) concept and discuss the challenges in deploying AaaS at the edge networks. Yet, it is essential to have performance metrics to evaluate the accuracy of AIGC services. Thus, we introduce several image-based perceived quality evaluation metrics. Then, we propose a general and effective model to illustrate the relationship between computational resources and user-perceived quality evaluation metrics. To achieve efficient AaaS and maximize the quality of generated content in wireless edge networks, we propose a deep reinforcement learning-enabled algorithm for the optimal ASP selection. Simulation results show that the proposed algorithm can provide a higher quality of generated content to users and achieve fewer crashed tasks by comparing with four benchmarks, i.e., overloading-avoidance, random, round-robin policies, and the upper-bound schemes. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Liu, Tong Xu, Dongyang Zhang, Tiantian Zhang, Shilong Chen, Jinhua Yu, Keping Leung, Victor C.M. Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (纸本)9798331521165

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysis and Fully Memristor-based Reservoir Computing for Temporal Data Classification

arXiv

引用

arXiv 2024年

作者： Singh, Ankur Choi, Sanghyeon Wang, Gunuk Daimari, Maryaradhiya Lee, Byung-Geun School of Electrical Engineering and Computer Science Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States KU-KIST Graduate School of Converging Science and Technology Department of Integrative Energy Engineering Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of

Reservoir computing (RC) offers a neuromorphic framework that is particularly effective for processing spatiotemporal signals. Known for its temporal processing prowess, RC significantly lowers training costs compared to conventional recurrent neural networks. A key component in its hardware deployment is the ability to generate dynamic reservoir states. Our research introduces a novel dual-memory RC system, integrating a short-term memory via a WOx-based memristor, capable of achieving 16 distinct states encoded over 4 bits, and a long-term memory component using a TiOx-based memristor within the readout layer. We thoroughly examine both memristor types and leverage the RC system to process temporal data sets. The performance of the proposed RC system is validated through two benchmark tasks: isolated spoken digit recognition and with only a fraction of complete samples forecasting the Mackey-Glass (MG) time series prediction. The system delivered an impressive 98.84% accuracy in speech digit recognition and sustained a low normalized root mean square error (NRMSE) of 0.036 in the time series prediction task, underscoring its capability. This study illuminates the adeptness of memristor-based RC systems in managing intricate temporal challenges, laying the groundwork for further innovations in neuromorphic computing. © 2024, CC BY-NC-ND.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Global distortions from local rewards: neural coding strategies in path-integrating neural systems 24

Global distortions from local rewards: neural coding strateg...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Francisco Acosta Fatih Dinc William T. Redman Manu Madhav David Klindt Nina Miolane Department of Physics UC Santa Barbara CNC Program Stanford University Applied Physics Laboratory Johns Hopkins University Biomedical Engineering University of British Columbia NeuroAI CSHL Electrical & Computer Engineering UC Santa Barbara

ISBN: (纸本)9798331314385

Grid cells in the mammalian brain are fundamental to spatial navigation, and therefore crucial to how animals perceive and interact with their environment. Traditionally, grid cells are thought support path integration through highly symmetric hexagonal lattice firing patterns. However, recent findings show that their firing patterns become distorted in the presence of significant spatial landmarks such as rewarded locations. This introduces a novel perspective of dynamic, subjective, and action-relevant interactions between spatial representations and environmental cues. Here, we propose a practical and theoretical framework to quantify and explain these interactions. To this end, we train path-integrating recurrent neural networks (piRNNs) on a spatial navigation task, whose goal is to predict the agent's position with a special focus on rewarded locations. Grid-like neurons naturally emerge from the training of piRNNs, which allows us to investigate how the two aspects of the task, space and reward, are integrated in their firing patterns. We find that geometry, but not topology, of the grid cell population code becomes distorted. Surprisingly, these distortions are global in the firing patterns of the grid cells despite local changes in the reward. Our results indicate that after training with location-specific reward information, the preserved representational topology supports successful path integration, whereas the emergent heterogeneity in individual responses due to global distortions may encode dynamically changing environmental cues. By bridging the gap between computational models and the biological reality of spatial navigation under reward information, we offer new insights into how neural systems prioritize environmental landmarks in their spatial navigation code.

关键词：

来源：评论

学校读者我要写书评

暂无评论

50 Gb/s 850 nm Few-Mode VCSELs for Pre-Emphasis NRZ-OOK over 100-m GI-SMF Transmission 26

50 Gb/s 850 nm Few-Mode VCSELs for Pre-Emphasis NRZ-OOK over...

引用

26th Microoptics Conference, MOC 2021

作者： Yeh, Yen-Wei Lee, Po-Tsung Kuo, Hao-Chung College Of Electrical And Computer Engineering National Yang Ming Chiao Tung University Department Of Photonics Graduate Institute Of Electro-Optical Engineering Hsinchu30010 Taiwan

A few-mode VCSEL has an oxide-confined aperture of 6 μm and a heavily Zn-diffusion aperture of 4 μm, which is demonstrated a -3-dB E-O bandwidth (26.5 GHz), and passed 50 Gb/s pre-emphasis NRZ-OOK transmission over ... 详细信息

ISBN: (纸本)9784863487758

关键词： Amplitude shift keying

来源：评论

学校读者我要写书评

暂无评论

Growing Our PEARLS and ASSETS Through a Support Ecosystem for Low-Income Academically Talented Students 54

Growing Our PEARLS and ASSETS Through a Support Ecosystem fo...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Lopez Del Puerto, Carla Jimenez, Manuel Alfaro, Monica Bellido, Carmen Cafaro, Matias J. Univ. of Puerto Rico Mayaguez Civil Engineering Department Mayaguez00681-9000 Puerto Rico Univ. of Puerto Rico Mayaguez Electrical & Computer Eng. Department Mayaguez00681-9000 Puerto Rico Univ. of Puerto Rico Mayaguez Biology Department Mayaguez00681-9000 Puerto Rico Teacher Preparation Program Univ. of Puerto Rico Mayaguez Mayaguez00681-9000 Puerto Rico

ISBN: (纸本)9798350351507

This research to practice paper describes two NSF-funded projects: The 'program for engineering Access, Retention, and LIATS Success' (PEARLS) and the 'Academic and Socioemotional Support Ecosystem for Talented low-income STEM Students' (ASSETS). These initiatives aim to support low-income, academically talented students pursuing STEM degrees, offering academic, socio-emotional, and financial assistance. Both projects provide mentoring, workshops, mental health services, and scholarships. Outcomes have shown increased engagement, retention, and graduation rates among participants compared to non-participants. Retention and persistence rates among PEARLS participants reached 97% and 96.3% respectively, showcasing the model effectiveness in keeping students focused on their studies. Graduation rates saw remarkable improvements, with on-time graduation rates soaring to 4.17 times that of non-participating students. The paper presents a robust framework for an integrated support ecosystem, emphasizing scalability and replicability across diverse institutions. By addressing the challenges faced by underprivileged students during environmental crises, this framework aims to foster equity and inclusion in higher education, ensuring all students have the support they need to succeed. © 2024 IEEE.

关键词： Students

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：