检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Romain Cosson Ali Jadbabaie Anuran Makur Amirhossein Reisizadeh Devavrat Shah Inria Paris France Laboratory for Information & Decision Systems MIT Cambridge MA USA Department of Computer Science School of Electrical & Computer Engineering Purdue University West Lafayette IN USA

Several recent empirical studies demonstrate that important machine learning tasks, e.g., training deep neural networks, exhibit low-rank structure, where the loss function varies significantly in only a few directions of the input space. In this paper, we leverage such low-rank structure to reduce the high computational cost of canonical gradient-based methods such as gradient descent (GD). Our proposed Low-Rank Gradient Descent (LRGD) algorithm finds an $\epsilon$ -minimizer of a p-dimensional function by first identifying $r\leq p$ significant directions, and then estimating the true p-dimensional gradient at every iteration by computing directional derivatives only along those $r$ directions. We establish that the “directional oracle complexity” of LRGD for strongly convex objective functions is $\mathrm{O}(r\log(1/\epsilon)+rp)$ . Therefore, when $r\ll p$ , LRGD provides significant improvement over the known complexity of $\mathcal{O}(p\log(1/\epsilon))$ of GD in the strongly convex setting. Furthermore, using real and synthetic data, we empirically find that LRGD provides significant gains over GD when the data has low-rank structure, and in the absence of such structure, LRGD does not degrade performance compared to GD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Geckler Classification from Gram Stained Smears Images for Sputum: Image Classification versus Object Detection 14

Predicting Geckler Classification from Gram Stained Smears I...

引用

14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023

作者： Sugimoto, Hitoshi Funatsu, Ryotaro Hirata, Kouichi Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Kawazu 680-4 Iizuka820-8502 Japan Kyushu Institute of Technology Department of Artificial Intelligence Kawazu 680-4 Iizuka820-8502 Japan Softmax Co. Ltd Japan

ISBN: (纸本)9798350324228

A Geckler classification is a criterion how the image is quality based on the number of buccal squamous epithelial (BSE) cells and leukocytes in the Gram stained smears images per 100 × field for sputum. The Geckler classification then determines which of images is valuable to microscope testing for the Gram stained smears images per 1, 000 × field for sputum. In this paper, we predict the Geckler classes by using two methods, image classification and object detection. For the image classification, we predict the Geckler classes from the training images for every Geckler class, without annotating BSE cells and leukocytes. On the other hand, for the object detection, we detect BSE cells and leukocytes from the training images annotated by them and determine the Geckler class by the number of them. Hence, we compare the experimental results of predicting Geckler classes obtained by the image classification with those by the object detection. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Mitigating Voltage Sag in Power systems with Proportional Integral Control using Tangent Search Algorithm and Multi-Fidelity Bayesian Neural Network 8

Mitigating Voltage Sag in Power Systems with Proportional In...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Meena, Radhey Shyam Singh, Harsimran Vasudevan, K. Ekambaram, Saranya Katiyar, Atul Kaliappan, S. Indian Institute of Technology Industry Coordinator Odl Uttar Pradesh Kanpur208016 India Guru Kashi University Department of Electrical Engineering Punjab Bathinda151302 India Parul University Department of Electrical Engineering Gujarat Vadodara391760 India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Tamil Nadu Coimbatore641202 India Mjp Rohilkhand University Bareilly Faculty of Engineering and Technology Department of Electrical Engineering Uttar Pradesh 243006 India Lovely Professional University Division of Research and Development Delhi Jalandhar144411 India

ISBN: (纸本)9798350376425

Mitigation strategies for voltage sag in power systems using dynamic voltage restorers (DVRs) involve compensating for voltage dips by injecting the required voltage to maintain stability. However, DVRs present problems such as high initial costs in installation and subsequent costs in maintenance and replacement;it only corrects voltage sag within its capability to handle severe or long periods of voltage sags. Moreover, DVRs may need complex control algorithms and most accurate tuning for optimal performance under various grid conditions. To overcome these drawbacks, this manuscript proposes a hybrid approach for voltage sag mitigation in power systems with Proportional Integral (PI) controller. The proposed method is the combined execution of both Tangent Search Algorithm (TSA) and Multi-fidelity Bayesian Neural Network (MFBNN). Hence, it is named as hybrid TSA-MFBNN approach. The major aim is to minimize the impact of voltage sags on sensitive equipment and maintain consistent power quality across the network and reduce the integral squared error (ISE) and Total Harmonic Distortion (THD) of the system. The PI controller's gain parameters are optimized by the proposed TSA, and its optimum values are predicted by the MFBNN. By then, the proposed technique is executed in MATLAB and compared with different existing approaches. The proposed method outperforms all existing approaches such as Artificial Neural Network (ANN), Salp Swarm Algorithm (SSA), and Adaptive-Network Fuzzy Inference System (ANFIS). The proposed technique demonstrates a THD of 2.38% and an ISE of 0.00410, indicating superior performance in reducing harmonic distortions and minimizing error. © 2024 IEEE.

关键词： Harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Online Learning in Blockchain-based Energy Trading systems 24

Online Learning in Blockchain-based Energy Trading Systems

引用

2024 International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing, MobiHoc 2024

作者： Liu, Yunshu Cheung, Man Hon Huang, Jianwei Pillar of Engineering Systems and Design Singapore University of Technology and Design Singapore Singapore Department of Computer Science City University of Hong Kong Hong Kong School of Science and Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network CSIJRI Joint Research Centre on Smart Energy Storage The Chinese University of HongKong Guangdong Shenzhen518172 China

ISBN: (纸本)9798400705212

In this paper, we consider a blockchain-based energy trading (BBET) system with the proof-of-stake (PoS) protocol. The system designer aims to minimize system cost by considering the prosumers’ strategic token allocation between blockchain staking and energy purchase for their applications. This is challenging as the system designer does not know prosumers’ private information of impatience levels towards different applications. To this end, we propose an online learning mechanism (OLM), which includes incentive mechanisms to guide both prosumers’ private information reporting and staking decisions in two phases. In the exploration phase, we design a randomized staking reward to encourage prosumers’ truthful reporting of their private information for the learning of impatience level distributions. Based on the threshold structure of the prosumers’ equilibrium staking strategies, in the exploitation phase, we propose a learning-error-based reward to minimize the system cost considering the finite-sample bias. By characterizing the optimal exploration duration, we prove that OLM achieves an asymptotic zero-regret against the complete information benchmark, with the regret bounded by O(3√lnT/T) when operating for T time slots. We implement the corresponding smart contract in Ethereum to demonstrate the feasibility of our approach. Experiment results show that our mechanism reduces regret by an average of 74% compared to the state-of-art mechanism. © 2024 Copyright held by the owner/author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Tight Collision Probability for UAV Motion Planning in Uncertain Environment

Tight Collision Probability for UAV Motion Planning in Uncer...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Tianyu Liu Fu Zhang Fei Gao Jia Pan Department of Mechanical Engineering The University of Hong Kong Institute of Cyber-Systems and Control Zhejiang University Department of Computer Science The University of Hong Kong

Operating unmanned aerial vehicles (UAVs) in complex environments that feature dynamic obstacles and external disturbances poses significant challenges, primarily due to the inherent uncertainty in such scenarios. Additionally, inaccurate robot localization and modeling errors further exacerbate these challenges. Recent research on UAV motion planning in static environments has been unable to cope with the rapidly changing surroundings, resulting in trajectories that may not be feasible. Moreover, previous approaches that have addressed dynamic obstacles or external disturbances in isolation are insufficient to handle the complexities of such environments. This paper proposes a reliable motion planning framework for UAVs, integrating various uncertainties into a chance constraint that characterizes the uncertainty in a probabilistic manner. The chance constraint provides a probabilistic safety certificate by calculating the collision probability between the robot's Gaussian-distributed forward reachable set and states of obstacles. To reduce the conservatism of the planned trajectory, we propose a tight upper bound of the collision probability and evaluate it both exactly and approximately. The approximated solution is used to generate motion primitives as a reference trajectory, while the exact solution is leveraged to iteratively optimize the trajectory for better results. Our method is thoroughly tested in simulation and real-world experiments, verifying its reliability and effectiveness in uncertain environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Shaping Gain of Multidimensional Constellation in Linear and Nonlinear Optical Fiber Channel

arXiv

引用

arXiv 2024年

作者： Chen, Bin Liang, Zhiwei Lei, Yi Deng, JingXin Li, Shen Liga, Gabriele School of Computer Science and Information Engineering Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province China Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden Department of Electrical and Computer Engineering Université Laval Québec Canada Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands

Utilizing the multi-dimensional (MD) space for constellation shaping has been proven to be an effective approach for achieving shaping gains. Despite there exists a variety of MD modulation formats tailored for specific optical transmission scenarios, there remains a notable absence of a dependable comparison method for efficiently and promptly re-evaluating their performance in arbitrary transmission systems. In this paper, we introduce an analytical nonlinear interference (NLI) power model-based shaping gain estimation method to enable a fast performance evaluation of various MD modulation formats in coherent dual-polarization (DP) optical transmission system. In order to extend the applicability of this method to a broader set of modulation formats, we extend the established NLI model to take the 4D joint distribution into account and thus able to analyze the complex interactions of non-iid signaling in DP systems. With the help of the NLI model, we conduct a comprehensive analysis of the state-of-the-art modulation formats and investigate their actual shaping gains in two types of optical fiber communication scenarios (multi-span and single-span). The numerical simulation shows that for arbitrary modulation formats, the NLI power and relative shaping gains in terms of signal-to-noise ratio can be more accurately estimated by capturing the statistics of MD symbols. Furthermore, the proposed method further validates the effectiveness of the reported NLI-tolerant modulation format in the literature, which reveals that the linear shaping gains and modulation-dependent NLI should be jointly considered for nonlinearity mitigation. © 2024, CC BY-NC-SA.

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Two-layer Space-oriented Partitioning for Non-point Data

arXiv

引用

arXiv 2023年

作者： Tsitsigkos, Dimitrios Bouros, Panagiotis Lampropoulos, Konstantinos Mamoulis, Nikos Terrovitis, Manolis The Department of Electrical & Computer Engineering University of Ioannina Greece The Institute of Computer Science Johannes Gutenberg University Mainz Germany The Information Systems Management Institute Research Center ‘Athena’ Greece

—Non-point spatial objects (e.g., polygons, linestrings, etc.) are ubiquitous. We study the problem of indexing non-point objects in memory for range queries and spatial intersection joins. We propose a secondary partitioning technique for space-oriented partitioning indices (e.g., grids), which improves their performance significantly, by avoiding the generation and elimination of duplicate results. Our approach is easy to implement and can be used by any space-partitioning index to significantly reduce the cost of range queries and intersection joins. In addition, the secondary partitions can be processed independently, which makes our method appropriate for distributed and parallel indexing. Experiments on real datasets confirm the advantage of our approach against alternative duplicate elimination techniques and data-oriented state-of-the-art spatial indices. We also show that our partitioning technique, paired with optimized partition-to-partition join algorithms, typically reduces the cost of spatial joins by around 50%. Copyright © 2023, The Authors. All rights reserved.

关键词： Indexing (of information)

来源：评论

学校读者我要写书评

暂无评论

Phase Analysis of N-Port Electrical Networks under Interconnections

引用

IFAC-PapersOnLine 2023年第2期56卷 4295-4300页

作者： Jianqi Chen Wei Chen Li Qiu Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong China Department of Mechanics and Engineering Science & State Key Laboratory for Turbulence and Complex Systems Peking University Beijing 100871 China

We study a class of matrix operations induced by n-port electrical network interconnections. We first introduce the frequency-dependent phases of n-port linear time-invariant electrical networks in light of the recently defined phases of complex matrices. Such phase characterization can be used to, for example, qualify the well-known notion of passivity for networks in a way. Next, the intrinsic phase properties of networks under interconnections are investigated. A scalable phase-preserving criterion is presented. The criterion involves only the phase properties of individual sub-networks, under the matrix operations featured by interconnections, whereby the phase range of the newly integrated network can be verified effectively, and more importantly maintains the scalability of analysis.

关键词： N-port network Interconnection Matrix operation Phase preservation

来源：评论

学校读者我要写书评

暂无评论

Predicting Obesity Trends Using Machine Learning from Big Data Analytics Approach

Predicting Obesity Trends Using Machine Learning from Big Da...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Vemulapalli, Gopichand Yalamati, Sreedhar Palakurti, Naga Ramesh Alam, Naved Samayamantri, Srinivas Whig, Pawan Principal Data Architect AZ United States Celer Inc. Systems Principal Solutions Architect CA United States Solution Architect United States Jamia Hamdard Department of Computer Science and Engineering New Delhi India Nu Skin International Inc SR VP- Global Engineering Chicago United States VIPS-TC Threws New Delhi India

ISBN: (纸本)9798350361537

This research paper explores the application of machine learning techniques in predicting obesity trends through big data analytics (BDA). Obesity has become a global health concern with significant socio-economic implications. Traditional methods of studying and addressing obesity trends often lack the scalability and efficiency required to handle large volumes of diverse data sources. Leveraging machine learning algorithms and big data analytics offers a promising approach to understanding and predicting obesity prevalence Our study focuses on harnessing machine learning models to analyze extensive datasets encompassing demographic, socioeconomic, environmental, and lifestyle factors. Through the integration of various data sources, including electronic health records, wearable devices, and social media, our research aims to uncover hidden patterns and correlations contributing to obesity trends. By employing predictive analytics, our model seeks to forecast future obesity rates and identify high-risk populations, facilitating targeted interventions and policy implementations. The findings of this research contribute to the advancement of data-driven approaches in public health and offer valuable insights for policymakers, healthcare professionals, and researchers striving to combat the obesity epidemic. Embracing machine learning and big data analytics presents opportunities for more proactive and personalized interventions, ultimately fostering healthier communities worldwide. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Imitating Human Reasoning to Extract 5W1H in News 25

Imitating Human Reasoning to Extract 5W1H in News

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Carlos Muñoz Marcelo Mendoza Hans Lobel Brian Keith Department of Computer Science Pontificia Universidad Católica de Chile Santiago Chile Departmento of Computing and Systems Engineering Universidad Católica del Norte Antofagasta Chile

ISBN: (纸本)9798400713316

Extracting key information from news articles is crucial for advancing search systems. Historically, the 5W1H framework, which organises information based on 'Who', 'What', 'When', 'Where', 'Why', and 'How', has been a predominant method in digital journalism empowering search tools. The rise of Large Language Models (LLMs) has sparked new research into their potential for performing such information extraction tasks effectively. Our study examines a novel approach to employing LLMs in the 5W1H extraction process, particularly focusing on their capacity to mimic human reasoning. We introduce two innovative Chain-of-Thought (COT) prompting techniques to extract 5W1H in news: extractive reasoning and question-level reasoning. The former directs the LLM to pinpoint and highlight essential details from texts, while the latter encourages the model to emulate human-like reasoning at the question-response level. Our research methodology includes experiments with leading LLMs using prompting strategies to ascertain the most effective approach. The results indicate that COT prompting significantly outperforms other methods. In addition, we show that the effectiveness of LLMs in such tasks depends greatly on the nature of the questions posed.

关键词： 5w1h

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：