检索结果-内蒙古大学图书馆

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Balaji, V. Anand, Taruna Abid, Tahera Ramya, D. Chauhan, Amit Hazela, Bramah Aditya Engineering College Department of Eee Andhra Pradesh Surampalem India Graphic Era Deemed to Be University Department of Humanities and Social Sciences Dehradun India Nawab Shah Alam Khan College of Engineering and Technology Department of It Telangana Hyderabad India Sri Eshwar College of Engineering Department of Computer Science and Business Systems Coimbatore India School of Sciences Department of Life Sciences Karnataka Bengaluru India Amity University Amity School of Engineering and Technology Lucknow Uttar Pradesh India

ISBN: (纸本)9798350313987

Demand forecasting is crucial in the business sector. Despite the inherent uncertainty of the future, it is essential for any firm to be able to accurately predict the market for both short- and long-term planning in order to place itself in a profitable position. The proposed approach focus on the passenger transport sector because it is particularly vulnerable to fluctuations in consumer demand for perishable commodities. At every stage of the planning process from initial network designs to final pricing of inventory for each vehicle in a route-an accurate prediction of demand is essential. Forecasting passenger demand is crucial since passenger transportation is responsible for a substantial chunk of global commerce. The suggested method relies on three distinct techniques: data preparation, feature selection, and model training. Data modification, cleansing, and reduction are the three sub-processes that make up preprocessing. When it comes to feature selection, partition-based clustering algorithms like k-means are the norm. Let's go on to training the models with stacked BiLSTM. The proposed method is demonstrably superior to both LSTM and BiLSTM, the two most common competing approaches. The proposed method had a success rate of 98.45 percent. © 2023 IEEE.

关键词： Demand Forecasting Electronic Ticketing Machines (ETMs) Long Short-Term Memory (LSTM)

来源：评论

学校读者我要写书评

暂无评论

The KIND Dataset: A Social Collaboration Approach for Nuanced Dialect Data Collection 18

The KIND Dataset: A Social Collaboration Approach for Nuance...

引用

18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Student Research Workshop, SRW 2024

作者： Yamani, Asma Z. Alziyady, Raghad AlYami, Reem Albelali, Salma A. Abouhagar, Leina Almulhim, Jawharah Alsulami, Amjad Alfarraj, Motaz Al-Zaidy, Rabeah Department of Information and Computer Science King Fahd University of Petroleum & Minerals Saudi Arabia Center for Integrative Petroleum Research CIPR King Fahd University of Petroleum & Minerals Saudi Arabia Department of Electrical Engineering King Fahd University of Petroleum & Minerals Saudi Arabia SDAIA-KFUPM Joint Research Center for AI King Fahd University of Petroleum & Minerals Saudi Arabia Preparatory Year Program King Fahd University of Petroleum & Minerals Saudi Arabia Department of Computer Science Imam Abdulrahman Bin Faisal University Saudi Arabia Saudi Data & AI Authority Saudi Arabia

ISBN: (纸本)9798891760905

Nuanced dialects are a linguistic variant that pose several challenges for NLP models and techniques. One of the main challenges is the limited amount of datasets to enable extensive research and experimentation. We propose an approach for efficiently collecting nuanced dialectal datasets that are not only of high quality, but are versatile enough to be multipurpose as well. To test our approach we collect the KIND corpus, which is a collection of fine-grained Arabic dialect data. The data is short texts, and unlike many nuanced dialectal datasets, it is curated manually through social collaboration efforts as opposed to being crawled from social media. The collaborative approach is incentivized through educational gamification and competitions for which the community itself benefits from the open source dataset. Our approach aims to achieve: (1) coverage of dialects from under-represented groups and fine-grained dialectal varieties, (2) provide aligned parallel corpora for translation between Modern Standard Arabic (MSA) and multiple dialects to enable translation and comparison studies, (3) promote innovative approaches for nuanced dialect data collection. We explain the steps for the competition as well as the resulting datasets and the competing data collection systems. The KIND dataset is shared with the research community. © 2024 Association for Computational Linguistics.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Demonstration of a CAFQA-bootstrapped Variational Quantum Eigensolver on a trapped-ion quantum computer

arXiv

引用

arXiv 2024年

作者： Wang, Qingfeng Zhukas, Liudmila Miao, Qiang Dalvi, Aniket S. Love, Peter J. Monroe, Christopher Chong, Frederic T. Ravi, Gokul Subramanian Duke Quantum Center Departments of Electrical and Computer Engineering and Physics Duke University Durham United States Chemical Physics Program Institute for Physical Science and Technology University of Maryland College ParkMD United States Duke Quantum Center Duke University Durham United States Department of Electrical and Computer Engineering Duke University Durham United States Department of Physics and Astronomy Tufts University Medford United States Department of Computer Science University of Chicago Chicago United States Department of Computer Science and Engineering University of Michigan Ann Arbor United States

To enhance the variational quantum eigensolver (VQE), the CAFQA method can utilize classical computational capabilities to identify a better initial state than the Hartree-Fock method. Previous research has demonstrated that the initial state provided by CAFQA recovers more correlation energy than that of the Hartree-Fock method and results in faster convergence. In the present study, we advance the investigation of CAFQA by demonstrating its advantages on a high-fidelity trapped-ion quantum computer located at the Duke Quantum Center—this is the first experimental demonstration of CAFQA-bootstrapped VQE on a TI device and on any academic quantum device. In our VQE experiment, we use LiH and BeH2 as test cases to show that CAFQA achieves faster convergence and obtains lower energy values within the specified computational budget limits. To ensure the seamless execution of VQE on this academic device, we develop a novel hardware-software interface framework that supports independent software environments for both the circuit and hardware end. This mechanism facilitates the automation of VQE-type job executions as well as mitigates the impact of random hardware interruptions. This framework is versatile and can be applied to a variety of academic quantum devices beyond the trapped-ion quantum computer platform, with support for integration with customized packages. © 2024, CC BY.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

CCT5: A Code-Change-Oriented Pre-Trained Model

arXiv

引用

arXiv 2023年

作者： Lin, Bo Liu, Yepang Wang, Shangwen Xia, Xin Liu, Zhongxin Mao, Xiaoguang College of Computer Science National University of Defense Technology Changsha China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Zhejiang University Hangzhou China Key Laboratory of Software Engineering for Complex Systems China Research Institute of Trustworthy Autonoumous Systems United Kingdom

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that the cost of dealing with these tasks can account for a large proportion (typically around 70 percent) of the total development expenditure, automating such processes will significantly lighten the burdens of developers. To achieve such a target, existing approaches mainly rely on training deep learning models from scratch or fine-tuning existing pre-trained models on such tasks, both of which have weaknesses. Specifically, the former uses comparatively small-scale labelled data for training, making it difficult to learn and exploit the domain knowledge of programming language hidden in the large-amount unlabelled code in the wild;the latter is hard to fully leverage the learned knowledge of the pre-trained model, as existing pre-trained models are designed to encode a single code snippet rather than a code change (i.e., the difference between two code snippets). We propose to pre-train a model specially designed for code changes to better support developers in software maintenance. To this end, we first collect a large-scale dataset containing 1.5M+ pairwise data of code changes and commit messages. Based on these data, we curate five different tasks for pre-training, which equip the model with diverse domain knowledge about code changes. We fine-tune the pre-trained model, CCT5, on three widely-studied tasks incurred by code changes and two tasks specific to the code review process. Results show that CCT5 outperforms both conventional deep learning approaches and existing pre-trained models on these tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Gradient Descent with Low-Rank Objective Functions

Gradient Descent with Low-Rank Objective Functions

引用

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

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

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

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

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：