检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ma, Chengzhi Wang, Jintao Yang, Xi Yang, Guanghua Zhang, Wei Ma, Shaodan State Key Laboratory of Internet of Things for Smart City the Department of Electrical and Computer Engineering University of Macau China Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China School of Intelligent Systems Science and Engineering and GBA B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China School of Electrical Engineering & Telecommunications University of New South Wales Sydney Australia

In this paper, we investigate a novel reconfigurable distributed antennas and reflecting surface (RDARS) aided multi-user massive multiple-input multiple-output (MIMO) system with imperfect channel state information (CSI) and propose a practical two-timescale (TTS) transceiver design to reduce the communication overhead and computational complexity of the system. In the RDARS-aided system, not only distribution gain but also reflection gain can be obtained by a flexible combination of the distributed antennas and reflecting surface, which differentiates the system from the others and also makes the TTS design challenging. To enable the optimal TTS transceiver design, the achievable rate of the system is first derived in closed-form. The rate expression is general and covers that of the distributed antenna systems (DAS) and reconfigurable intelligent surface (RIS) aided systems as special cases. Then the TTS design aiming at the weighted sum rate maximization is considered. To solve the challenging non-convex optimization problem with high order design variables, i.e., the transmit powers and the phase shifts at the RDARS, a block coordinate descent based method is proposed to find the optimal solutions in semi-closed forms iteratively. Specifically, two efficient algorithms are proposed with provable convergence for the optimal phase shift design, i.e., Riemannian Gradient Ascent based algorithm by exploiting the unit-modulus constraints, and Two-Tier Majorization-Minimization based algorithm with closed-form optimal solutions in each iteration. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the superiority of deploying RDARS in massive MIMO systems to provide substantial rate improvement with a significantly reduced total number of active antennas/RF chains and lower transmit power when compared to the DAS and RIS-aided systems. Copyright © 2023, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

IF: Iterative Fractional Optimization 29

IF: Iterative Fractional Optimization

引用

29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021

作者： Chatterjee, Sarthak Das, Subhro Pequito, Sérgio Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY United States MIT-IBM Watson AI Lab IBM Research CambridgeMA United States Delft Center for Systems and Control Delft University of Technology Netherlands

ISBN: (纸本)9782875870827

Most optimization problems lack closed-form solutions of the argument that minimizes a given function, and even if these were available it might be prohibitive to compute it. As such, we rely on iterative numerical algorithms to find an approximate solution. In this paper, we propose to leverage fractional calculus in the context of time series analysis methods to devise a new iterative algorithm. Specifically, we propose to leverage autoregressive fractional-order integrative moving average time series, whose coefficients encode a proxy for local spatial information. We provide evidence that our algorithm is efficient and particularly suitable for cases where the Hessian is ill-conditioned. © 2021 ESANN Intelligence and Machine Learning. All rights reserved.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Speech Separation for Low-Resource Languages

Speech Separation for Low-Resource Languages

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Marvin Borsdorf Zexu Pan Pascal Himmelmann Haizhou Li Tanja Schultz Machine Listening Lab University of Bremen Bremen Germany Alibaba Group Singapore Department of Mathematics and Computer Science FernUniversität in Hagen Hagen Germany School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Cognitive Systems Lab University of Bremen Bremen Germany

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speech separation aims to equip machines with the human ability of selective listening, i.e. to focus attention on specific information in spoken communication. Studies have shown that the language spoken in a cocktail party scenario matters. While the development of speech separation models can leverage extensive databases, for the majority of languages only very limited data is available. This work presents the very first study on speech separation for low-resource languages. We choose blind source separation as the task to be studied and analyze three strategies to overcome the data scarcity of two low-resource languages from the GlobalPhoneMS2 database. We show that data from other languages can be used to develop models that work for low-resource languages. Finetuning additionally boosts the performance, and training on multiple languages increases both performance and robustness. We show that dynamic mixing in the development helps to find a trade-off between performance and development time.

关键词： Training Measurement Databases Signal processing Data models Blind source separation Robustness Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

On frequency response modeling of interconnected microgrids: Two different perspectives

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2022年 2卷

作者： Rehimi, Sharara Bevrani, Hassan Mirzaei, Rahmatollah Shafiee, Qobad Naderi, Mobin Kato, Takeyoshi Institute of Materials and Systems for Sustainability Nagoya University Nagoya Japan Smart/Micro Grids Research Center (SMGRC) Computer and Electrical Engineering Department University of Kurdistan Sanandaj Iran

This paper deals with the frequency response modeling of interconnected microgrids. The frequency response model is used for frequency and tie-line power control analysis and synthesis. The proposed frequency response model is obtained using two different perspectives: (1) based on frequency sensitivity analysis, (2) based on the inertia concept. Besides, the dynamic of back-to-back converters and controllable active power sources are also included to obtain a generalized frequency response model with desirable performance. Indeed, it can be observed that in the first method, some circuit parameters can be neglected in the frequency response model. This finding is effective in providing a more simplified model. In the second method, the frequency response model has been presented as an innovative approach. In a way, we have selected the nature of distributed generations as an indicator of source classification in the model. This model is also enhanced by considering the inertia dynamics and controllable power source and has a better performance to show the network status. Since the microgrid frequency response model only covers the low-frequency dynamics, the fast dynamics of inner control loops as well as the modulation units and sensors are not considered. The proposed frequency response model can be used for frequency stability analysis studies as well as frequency and tie-line power control analysis and synthesis. Comprehensive simulation studies are carried out using the MATlab simulation environment to compare and evaluate the developed models. Further, the proposed models are verified via PSCAD/EMTDC, considering two microgrids interconnected through back-to-back converters. The results showed that the proposed models are suitable and efficient for frequency response studies. © 2022 The Author(s)

关键词： Back-to-back converters Controllable power source Frequency response model Interconnected microgrids Virtual inertia

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Distributed Antennas and Reflecting Surface: A New Architecture for Wireless Communications

arXiv

引用

arXiv 2023年

作者： Ma, Chengzhi Yang, Xi Wang, Jintao Yang, Guanghua Zhang, Wei Ma, Shaodan The State Key Laboratory of Internet of Things for Smart City The Department of Electrical and Computer Engineering University of Macau China The Shanghai Key Laboratory of Multidimensional Information Processing School of Communication and Electronic Engineering East China Normal University Shanghai200241 China The School of Intelligent Systems Science and Engineering GBA and B&R International Joint Research Center for Smart Logistics Jinan University Zhuhai519070 China The School of Electrical Engineering & Telecommunications University of New South Wales Sydney Australia

Distributed Antenna systems (DASs) employ multiple antenna arrays in remote radio units to achieve highly directional transmission and provide great coverage performance for future-generation networks. However, the utilization of fully digital or hybrid active antenna arrays results in a significant increase in hardware costs and power consumption for DAS. To address these issues, integrating DAS with Reconfigurable Intelligent Surfaces (RIS) offers a viable approach to ensure coverage and transmission performance while maintaining low hardware costs and power consumption. To incorporate the merits of RIS into the DAS from practical consideration, a novel architecture of "Reconfigurable Distributed Antennas and Reflecting Surfaces (RDARS)" is proposed in this paper. Specifically, based on the design of the additional direct-through state together with the existing high-quality fronthaul link, any element of the RDARS can be dynamically programmed to connect with the base station (BS) via fibers and perform the connected mode as remote distributed antennas of the BS to receive or transmit signals. Additionally, RDARS also inherits the low-cost and low-energy-consumption benefits of fully passive RISs by default configuring the elements as passive to perform the reflection mode. As a result, RDARS encompasses both DAS and RIS as special cases, offering flexible control over the trade-off between distribution gain and reflection gain to enhance performance. To unveil the potential of such architecture, the ergodic achievable rate under the RDARS architecture is analyzed and closed-form expression with meaningful insights is derived. The theoretical analysis proves that the RDARS can achieve a higher achievable rate than both DAS and fully passive RIS with the passive beamforming gain provided by elements acting reflection mode while combating the "multiplicative fading" suffered by RISs through the connected mode performed at the RDARS. Simulation results also demonstr

关键词： Reconfigurable architectures

来源：评论

学校读者我要写书评

暂无评论

Explore the Future Earth with Wander 2.0: AI Chatbot Driven By Knowledge-base Story Generation and Text-to-image Model

Explore the Future Earth with Wander 2.0: AI Chatbot Driven ...

引用

Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing systems, CHI EA 2023

作者： Sun, Yuqian Xu, Ying Cheng, Chenhang Li, Yihua Lee, Chang Hee Asadipour, Ali Computer Science Research Centre Royal College of Art London United Kingdom Department of Industrial Design School of Art and Design Wuhan University of Technology Wuhan China Shanghai China Department of Product Design College of Fashion and Design Donghua University Shanghai China Affective Systems and Cognition Lab Industrial Design Department College of Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of

ISBN: (纸本)9781450394222

People always envision the future of earth through science fiction (Sci-fi), so can we create a unique experience of "visiting the future earth"through the lens of artificial intelligence (AI)? We introduce Wander 2.0, an AI chatbot that co-creates sci-fi stories through knowledge-based story generation on daily communication platforms like WeChat and Discord. Using location information from Google Maps, Wander generates narrative travelogues about specific locations (e.g. Paris) through a large-scale language model (LLM). Additionally, using the large-scale text-to-image model (LTGM) Stable Diffusion, Wander transfers future scenes that match both the text description and location photo, facilitating future imagination. The project also includes a real-time visualization of the human-AI collaborations on a future map. Through journeys with visitors from all over the world, Wander demonstrates how AI can serve as a subjective interface linking fiction and reality. Our research shows that multi-modal AI systems have the potential to extend the artistic experience and creative world-building through adaptive and unique content generation for different people. Wander 2.0 is available at http://***/ © 2023 Owner/Author.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

From Pre-Training to Fine-Tuning: An In-Depth Analysis of Large Language Models in the Biomedical Domain

SSRN

引用

SSRN 2024年

作者： Bonfigli, Agnese Bacco, Luca Merone, Mario Dell’Orletta, Felice ItaliaNLP Lab Institute of Computational Linguistics "Antonio Zampolli" National Research Council Via Giuseppe Moruzzi 1 Pisa56124 Italy Research Unit of Computer Systems and Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Via Alvaro del Portillo 21 Rome00128 Italy

In this study, we delve into the adaptation and effectiveness of Transformer-based, pre-trained Large Language Models (LLMs) within the biomedical domain, a field that poses unique challenges due to its complexity and the specialized nature of its data. Building on the foundation laid by the transformative architecture of Transformers, we investigate the nuanced dynamics of LLMs through a multifaceted lens, focusing on two domain-specific tasks, i.e., Natural Language Inference (NLI) and Named Entity Recognition (NER).Our objective is to bridge the knowledge gap regarding how these models’ downstream performances correlate with their capacity to encapsulate task-relevant *** achieve this goal, we probed and analyzed the inner encoding and attention mechanisms in LLMs, both encoder- and decoder-based, tailored for either general or biomedical-specific applications. This examination occurs before and after the models are fine-tuned across various data volumes. Our findings reveal that the models' downstream effectiveness is intricately linked to specific patterns within their internal mechanisms, shedding light on the nuanced ways in which LLMs process and apply knowledge in the biomedical context. The source code for this paper is available at https://***/agnesebonfigli99/LLMs-in-the-Biomedical-Domain. © 2024, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Design of Energy Management System using Non-Intrusive Load Monitoring Strategy

Machine Learning based Design of Energy Management System us...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Kamal Shahid Muhammad Majid Gulzar Muhammad Ali Raza Salman Habib Hasnain Ahmad Institute of Electrical Electronics and Computer Engineering University of the Punjab Lahore Pakistan Department of Control & Instrumentation Engineering King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Interdisciplinary Research Center for Sustainability Energy Systems (IRC-SES) King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Interdisciplinary Research Center for Smart Mobility and Logistics (IRC-SML) King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Department of Electrical Engineering Pakistan Institute of Engineering and Applied Sciences (PIEAS) Islamabad Pakistan

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

In this work, a Non-Intrusive Load Monitoring (NILM) system is designed for smart homes based on smart energy meters. The proposed solution simplifies the monitoring process by using a single set of sensors, in contrast to conventional systems that call for several sensors. From different appliances and their combinations, crucial electrical information, such as voltage, current, active power, reactive power, apparent power, power factor, and frequency was gathered. Proposed intelligent data analysis employing machine learning methods, particularly Artificial Neural Networks (ANN) and Deep Neural Networks (DNN), is the key innovation. These methods accurately categorize various appliance kinds, with DNN performing best in real-time circumstances. Additionally, there is a built-in email alert system that activates whenever there are odd electrical surges. The streamlined user interface, offers accurate identification of individual appliances and combinations in real-time forecasts based on past data. Future developments include a larger appliance data-set, improved categorization methods, load forecasting, and the creation of a smartphone app for real-time energy consumption data and automatic control, among other things. In a net-shell, this study offers an effective, single-sensorbased solution for load monitoring in smart homes, representing a substantial development in NILM technology. This technology claims to improve resource utilization and energy management in both domestic and commercial settings.

关键词： Meters Load monitoring Reactive power Artificial neural networks smart homes Machine learning User interfaces

来源：评论

学校读者我要写书评

暂无评论

From Rule-Based Models to Deep Learning Transformers Architectures for Natural Language Processing and Sign Language Translation systems: Survey, Taxonomy and Performance Evaluation

arXiv

引用

arXiv 2024年

作者： Shahin, Nada Ismail, Leila Intelligent Distributed Computing and Systems Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Emirates Center for Mobility Research United Arab Emirates University Abu Dhabi United Arab Emirates

With the growing Deaf and Hard of Hearing population worldwide and the persistent shortage of certified sign language interpreters, there is a pressing need for an efficient, signs-driven, integrated end-to-end translation system, from sign to gloss to text and vice-versa. There has been a wealth of research on machine translations and related reviews. However, there are few works on sign language machine translation considering the particularity of the language being continuous and dynamic. This paper aims to address this void, providing a retrospective analysis of the temporal evolution of sign language machine translation algorithms and a taxonomy of the Transformers architectures, the most used approach in language translation. We also present the requirements of a real-time Quality-of-Service sign language machine translation system underpinned by accurate deep learning algorithms. We propose future research directions for sign language translation *** Codes I.2, I.2.7, I.4, I.4.9 © 2024, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Cross-links matter for link prediction: rethinking the debiased GNN from a data perspective 23

Cross-links matter for link prediction: rethinking the debia...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Zihan Luo Hong Huang Jianxun Lian Xiran Song Xing Xie Hai Jin National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China

Recently, the bias-related issues in GNN-based link prediction have raised widely spread concerns. In this paper, we emphasize the bias on links across different node clusters, which we call cross-links, after considering its significance in both easing information cocoons and preserving graph connectivity. Instead of following the objective-oriented mechanism in prior works with compromised utility, we empirically find that existing GNN models face severe data bias between internal-links (links within the same cluster) and cross-links, and this inspires us to rethink the bias issue on cross-links from a data perspective. Specifically, we design a simple yet effective twin-structure framework, which can be easily applied to most GNNs to mitigate the bias as well as boost their utility in an end-to-end manner. The basic idea is to generate debiased node embeddings as demonstrations and fuse them into the embeddings of original GNNs. In particular, we learn debiased node embeddings with the help of augmented supervision signals, and a novel dynamic training strategy is designed to effectively fuse debiased node embeddings with the original node embeddings. Experiments on three datasets with six common GNNs show that our framework can not only alleviate the bias between internal-links and cross-links but also boost the overall accuracy. Comparisons with other state-of-the-art methods also verify the superiority of our method.

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：