检索结果-内蒙古大学图书馆

9th IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2023

作者： Nuha, Nishat Sultana Mahmud, Tanjim Rezaoana, Noortaz Hossain, Mohammad Shahadat Andersson, Karl University of Chittagong Department of Computer Science and Engineering Chittagong4331 Bangladesh Rangamati Science and Technology University Department of Computer Science and Engineering Rangamati4500 Bangladesh Luleå University of Technology Pervasive and Mobile Computing Laboratory Sweden

ISBN: (纸本)9798350319651

Student engagement refers to the level of involve-ment, interest, attention, and active participation that students demonstrate during their learning experiences. As the engage-ment rate increases the learning rate, teachers always try to mea-sure the engagement rate in the classroom in various ways. This paper introduces a multimodal approach for detecting student engagement, a vital aspect of effective learning. Leveraging Convolutional Neural Networks (CNNs), video and audio data are integrated to capture comprehensive insights into engagement levels. The objective is to classify student engagement into three categories: highly engaged, engaged, and not engaged. Separate unimodal models are employed for speech and video data., achieving notable accuracies of 92.87 % and 94.77 %, respectively, in recognizing engagement levels. The combined model, achieved through feature-level fusion, yields a competitive accuracy of 69.36%, benefiting from the strengths of both modalities. Al-though the combined model exhibits slightly lower test accuracy compared to the individual speech and video models, its enhanced interpretability and comprehensive insights make it a promising avenue for future research. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-rank Decomposition 24

Decoupling General and Personalized Knowledge in Federated L...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wu, Xinghao Liu, Xuefeng Niu, Jianwei Wang, Haolin Tang, Shaojie Zhu, Guogang Su, Hao State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China Department of Management Science and Systems University at Buffalo BuffaloNY United States School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9798400706868

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://***/XinghaoWu/FedDecomp © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Topological magnonic properties of an antiferromagnetic chain

引用

Physical Review B 2024年第14期110卷 144448页

作者： Topojit Debnath Shri Hari Soundararaj Sohee Kwon Alexander A. Balandin Roger K. Lake Laboratory for Terahertz & Terascale Electronics (LATTE) Department of Electrical and Computer Engineering Materials Science and Engineering Department of Materials Science and Engineering

The magnonic excitations of a dimerized, one-dimensional, antiferromagnetic chain can be trivial or topological depending on the signs and magnitudes of the alternating exchange couplings and the anisotropy. The topological phase that occurs when the signs of the two different exchange couplings alternate is qualitatively different from that of the Su-Schrieffer-Heeger model. A material that may exhibit these properties is the quasi-one-dimensional material MoI3 that consists of dimerized chains weakly coupled to adjacent chains. The magnetic ground state and its excitations are analyzed both analytically and numerically using exchange and anisotropy parameters extracted from density functional theory calculations.

关键词： First-principles calculations Magnetic anisotropy Magnetic coupling Magnetic interactions Magnetic order Magnetic phase transitions Magnetic texture Magnetism Magnons Topological phase transition 1-dimensional spin chains Antiferromagnets Classical spin chains Density functional calculations Heisenberg model Holstein-Primakoff method Linear spin wave theory Quantum spin chains

来源：评论

学校读者我要写书评

暂无评论

Optimizing Lender Portfolios: A P2P Lending Recommendation Approach 4

Optimizing Lender Portfolios: A P2P Lending Recommendation A...

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Sannapareddy, Varshini Rifah, Umais Anusha Hegde, H. Bhowmik, Biswajit National Institute of Technology Karnataka Ishwarchandra Vidyasagar Ait Lab Brics Laboratory Department of Computer Science and Engineering Surathkal Mangalore575025 India

ISBN: (纸本)9798350354218

The proliferation of peer-to-peer (P2P) lending platforms has ushered in a new era of financial accessibility, but it has also brought to the forefront the growing concern of loan defaults. This paper explores the increasing significance of P2P lending platforms and addresses the critical issue of loan default prediction. The study focuses on the application of machine learning techniques, specifically employing the Random Forest algorithm and logistic regression, to train a predictive model for assessing the likelihood of default within a loan portfolio. The primary objective is to enhance the decision-making process for lenders by recommending optimal loan portfolios based on the predictive insights generated by the model. By leveraging the capabilities of this robust algorithm, the research aims to contribute to the advancement of risk assessment methodologies in P2P lending, ultimately fostering more informed and secure lending practices on these platforms. We trained and compared logistic Reression and random forest models and derived resultant optimal portfolio by considering both the models which is intended to give better results than a single model. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Leveraging AI to Improve STEM Engagement for Black and Latine Youth

Leveraging AI to Improve STEM Engagement for Black and Latin...

引用

Black Issues in Computing Education (BICE)

作者： Aisha Cora Vicente Arroyos Liban Hussein Vikram Iyer R. Benjamin Shapiro Kyle Johnson Department of Electrical and Computer Engineering University of Washington USA AVELA - A Vision for Engineering Literacy & Access USA Department of Computer Science and Engineering University of Washington USA

ISBN: (数字)9798350372915

ISBN: (纸本)9798350372922

Recent studies have shown that pedagogical approaches like hands-on lessons, representative and near-peer mentoring, as well as culturally responsive teaching increase Science Technology engineering and Math (STEM) engagement in classrooms, specifically those with underrepresented minority (URM) students. URM students interested in pursuing STEM show increased engagement and confidence from more holistic outreach programs, however there is a dearth of instructors who represent URM student identities who also have the necessary technical know-how. However, new AI tools based on Large Language Models (LLMs), like GPT-3.5, have been shown to increase the productivity of software developers, with the largest productivity gains being for non-experts. Therefore, we propose a study on the usability of LLMs as an educational tool for supporting instructors of various skill levels in both facilitating and scaling programming classes for URM students. We aim to evaluate the capacity for these AI tools to help reduce the digital divide by exploring the limitations, effectiveness, and potential hesitations URM communities may have with integrating LLMs into their classrooms. If LLMs can support, and/or help scale the number of, culturally responsive mentors capable of instructing programming courses, URM students in the US may be poised as one of the major beneficiaries of these new AI tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The ϵ-Effective Capacity for Statistical Delay and Error-Rate Bounded QoS Provisioning Over 6G CF M-MIMO Wireless Networks Using HARQ-IR 57

The ϵ-Effective Capacity for Statistical Delay and Error-Ra...

引用

57th Annual Conference on Information Sciences and Systems, CISS 2023

作者： Zhang, Xi Wang, Jingqing Poor, H. Vincent Texas AandM University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States Princeton University Department of Electrical and Computer Engineering PrincetonNJ08544 United States

ISBN: (纸本)9781665451819

Significant effort has been devoted to the problem of guaranteeing stringent ultra-reliable and low-latency communications (URLLC) while introducing new requirements for better quality-of-services (QoS) over next generation wireless networks. One of the major design issues raised by URLLC is how to support explosively growing demands for delay-sensitive multimedia applications while guaranteeing ultra-reliability. Towards this end, there have been a wide spectrum of promising techniques, including statistical delay and error rate-bounded QoS provisioning, cell-free (CF) massive multiple-input-multiple-output (m-MIMO), finite blocklength coding (FBC), hybrid automatic repeat request with incremental redundancy (HARQ-IR) protocol, etc. However, when being integrated with FBC, how to rigorously and efficiently characterize the dynamics of mobile wireless networks in terms of statistical delay and error-rate bounded QoS provisioning for CF m-MIMO has imposed many new challenges not encountered before. To overcome these challenges, in this paper we develop statistical delay and error-rate bounded QoS analytical modeling schemes to characterize the FBC-based ϵ-effective capacity over 6G CF m-MIMO wireless networks using HARQ-IR. In particular, first we establish CF m-MIMO based system architecture models. Second, we apply a HARQ-IR protocol for deriving the channel coding rate, outage probability, and FBC based ϵ-effective capacity function using the Mellin transform. Finally, we conduct a set of simulations to validate and evaluate our proposed schemes. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Statistical QoS Provisioning for Scalable Software-Defined 6G Mobile Networks 57

Heterogeneous Statistical QoS Provisioning for Scalable Soft...

引用

57th Annual Conference on Information Sciences and Systems, CISS 2023

作者： Zhang, Xi Zhu, Qixuan Poor, H. Vincent Texas AandM University Networking and Information Systems Laboratory Department of Electrical and Computer Engineering College StationTX77843 United States Princeton University Department of Electrical and Computer Engineering PrincetonNJ08544 United States

ISBN: (纸本)9781665451819

Due to the explosively increasing number of mobile users and the new types of data demands in the fifth generation (5G) mobile wireless network, research in wireless networks has shifted toward the development of the sixth-generation (6G) wireless network. Although the research for software-defined network (SDN) architectures in 5G mainly focuses on the dynamic programming for the internet backbone, these software programming techniques can be also applied at the network edge to support the exponentially increasing demands from mobile users under constrained wireless resources. In order to study the interference problem resulted by massive mobile users, the scaling law is a powerful tool to show how fast the levels of network imperfections can be tolerated as the number of mobile users increases. In this paper, we investigate the scaling behavior of software-defined architectures over 6G wireless networks. We consider the wireless channel in three scenarios: single-input-single-output (SISO), multiple-input-single-output (MISO), and multiple-input-multiple-output (MIMO), where we derive the corresponding scaling law for each scenario, respectively. Our derived scaling law shows how the network performance scales with the number of mobile users in a wireless network. Then, we propose a software-defined network slicing scheme to select the optimal mobile users and derive their optimal resource allocations, according to our derived scaling law, under SISO, MISO, and MIMO wireless channel, respectively. Finally, we validate and evaluate the derived scaling behavior of the software-defined architecture over 6G wireless networks through numerical analyses. © 2023 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

A Comparison of LEACH-Like Protocols to Improve Power Consumption Efficiency in Wireless Sensor Networks 8th

A Comparison of LEACH-Like Protocols to Improve Power Consum...

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Benhadji, Mohammed Kaddi, Mohammed Omari, Mohammed Lagouch, Aakila LEESI Laboratory Material Sciences Department Ahmed Draïa University Adrar Adrar Algeria LDDI Laboratory Mathematics and Computer Science Department Ahmed Draïa University Adrar Adrar Algeria Computer Science and Engineering Department American University of Ras Al Khaimah Ras Al Khaimah United Arab Emirates

ISBN: (纸本)9789819748945

Many clustering-based routing techniques are widely used in wireless sensor networks due to their low power consumption and longer network life. One of the most well-known protocols is LEACH, which assisting in the decrease of sensor energy usage during the data aggregation and transmission phase to the base station. However, the cluster head selection process is regarded as a drawback that reduces the protocol’s efficiency. Recently, researchers have attempted to develop approaches relying on several optimization methods. In this article, we attempt to present the LEACH methodology, highlighting its flaws, then discussing some of the protocol enhancements that has improved the efficiency of the protocol. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Clustering Energy consumption LEACH Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Revolutionary self-powered transducing mechanism for long-lasting and stable glucose monitoring:achieving selective and sensitive bacterial endospore germination in microengineered paper-based platforms

引用

Microsystems & Nanoengineering 2024年第6期10卷 375-389页

作者： Yang Gao Anwar Elhadad Seokheun Choi Department of Electrical&Computer Engineering Bioelectronics&Microsystems LaboratoryState University of New York at BinghamtonBinghamtonNY 13902USA Center for Research in Advanced Sensing Technologies&Environmental Sustainability State University of New York at BinghamtonBinghamtonNY 13902USA

We introduce a groundbreaking proof-of-concept for a novel glucose monitoring transducing mechanism,marking the first demonstration of a spore-forming microbial whole-cell sensing *** approach uses selective and sensitive germination of Bacillus subtilis spores in response to glucose in potassium-rich bodily fluids such as *** the rate of germination and the number of metabolically active germinating cells are directly proportional to glucose concentration,the electrogenic activity of these cells—manifested as electricity—serves as a self-powered transducing signal for glucose *** a microengineered,paper-based microbial fuel cell(MFC),these electrical power outputs are measurable and can be visually displayed through a compact interface,providing real-time *** dormant spores extend shelf-life,and the self-replicating bacteria ensure *** MFC demonstrated a remarkable sensitivity of 2.246µW·(log mM)^(-1)·cm^(-2) to glucose concentrations ranging from 0.2 to 10 mM,with a notably lower limit of detection at~0.07 *** sensor exhibited exceptional selectivity,accurately detecting glucose even in the presence of various *** analyses revealed that,unlike conventional enzymatic biosensors whose performance degrades significantly through time even when inactive,the spore-based MFC is stable for extended periods and promptly regains functionality when *** preliminary investigation indicates that the spore-forming microbial whole-cell sensing strategy holds considerable promise for efficient diabetes management and can be extended toward noninvasive wearable monitoring,overcoming critical challenges of current technologies and paving the way for advanced biosensing applications.

关键词： prompt mechanism holds

来源：评论

学校读者我要写书评

暂无评论

Cross-project Defect Prediction with An Enhanced Transfer Boosting Algorithm 12

Cross-project Defect Prediction with An Enhanced Transfer Bo...

引用

12th International Conference on computer and Knowledge engineering, ICCKE 2022

作者： Nikravesh, Nazgol Keyvanpour, Mohammad Reza Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Department of Computer Engineering Faculty of Engineering Tehran Iran

ISBN: (数字)9781665476133

ISBN: (纸本)9781665476133

A growing number of software projects makes it increasingly crucial to predict software defects. If adequate historical data are accessible, within-project defect prediction models can be reliable. However, during the early phases of software development, sufficient data are not available to train an effective predictor. Cross-project defect prediction (CPDP) utilizes information from previous mature projects (source data) for predicting whether new software modules (target data) will be defective. CPDP models must take into account the fact that data distributions between source and target projects are different. Cross-project defect prediction often reduces distribution differences by either selecting training data or using transfer learning methods. Using transfer learning effectively reduces distribution differences in recent CPDP models, yet none of them have taken into account the possibility that negative transfer may occur as a result of the imbalanced nature of defect data. In this paper, a four-step model is proposed, of which three steps are dedicated to the preparation of training data and their initial weights for use in the fourth step, which involves an enhanced version of the transfer boosting algorithm. In this algorithm, the imbalance nature of data is considered and the weighting of the source data is updated to enhance the prediction performance. Therefore, aside from reducing distribution discrepancy between source and target data, this model also addresses the issues related to defect data class imbalance. As compared to four state-of-the-art CPDP models, this model provided consistent and accurate predictions for fifteen projects from PROMISE, AEEEM, and SOFTLAB. Our proposed model provided the best average results for both AUC and F-measure and in some datasets, the improvements were more than 5%. © 2022 IEEE.

关键词： Defects

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：