检索结果-内蒙古大学图书馆

PACLIC 23 - Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation 2009年 2卷 811-818页

作者： Singh, Thoudam Doren Nongmeikapam, Kishorjit Ekbal, Asif Bandyopadhyay, Sivaji Center for Development of Advanced Computing Gulmohar Cross Road No 9 Juhu Mumbai-400049 India Computer Science and Engineering Department Jadavpur University Kolkata-700032 India Department of Computational Linguistics University of Heidelberg Im Neuenheimer Feld 325 69120 Heidelberg Germany

ISBN: (纸本)9789624423198

This paper reports about the development of a Manipuri NER system, a less computerized Indian language. Two different models, one using an active learning technique based on the context patterns generated from an unlabeled news corpus and the other based on the well known Support Vector Machine (SVM), have been developed. The active learning technique has been considered as the baseline system. The Manipuri news corpus has been manually annotated with the major NE tags, namely Person name, Location name, Organization name and Miscellaneous name to apply SVM. The SVM based system makes use of the different contextual information of the words along with the variety of orthographic word-level features which are helpful in predicting the NE classes. In addition, lexical context patterns generated using the active learning technique have been used as the features of SVM in order to improve performance. The system has been trained and tested with 28,629 and 4,763 wordforms, respectively. Experimental results show the effectiveness of the proposed approach with the overall average Recall, Precision and F-Score values of 93.91%, 95.32% and 94.59% respectively. © 2009 by Thoudam Doren Singh, Kishorjit Nongmeikapam, Asif Ekbal, and Sivaji Bandyopadhyay.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Effects of Date Seeds Size and Loading on Properties of Linear Low-Density Polyethylene/Date Seeds Powder Composites 1

Effects of Date Seeds Size and Loading on Properties of Line...

引用

1st International Conference on Green and Sustainable computing (ICoGeS)

作者： Alnaid, Abduati Noriman, N. Z. Dahham, Omar S. Hamzah, R. Al-Samarrai, Marwa N. Idrus, S. Z. Syed Shayfull, Z. Center of Excellence Geopolymer and Green Technology (CEGeoGTech) Faculty of Engineering Technology (FETech) Universiti Malaysia Perlis (UniMAP) UniCITI Alam Campus Sungai Chucuh Padang Besar Perlis 02100 Malaysia School of Human Development and Techno-communication (IKOM) Green Advanced Computing and Technology (GREAT) Research Group-CEGeoGTech Universiti Malaysia Perlis (UniMAP) Malaysia School of Manufacturing Engineering Universiti Malaysia Perlis Arau 02600 Malaysia Green Design and Manufacture Research Group Center of Excellence Geopolymer and Green Technology (CEGeoGTech) Universiti Malaysia Perlis Kangar 0100 Malaysia

In this work, the influences of different date seeds (DS) size, fine size (125- 250 wn), medium size (250- 500 wn) and coarse size (500, 1000 wn) and different DS content (5, 10, 15, 20 wt%) on the tensile properties of linear low density polyethylene / date seeds (LLDPE/DS) composites were evaluated. The extrusion and injection molding process were used respectively to form LLDPE/DS composites. Results show that the addition of DS up to 10 wt%, particularly DS fine size has increased the tensile strength (TS) of LLDPE/DS composites. However, high DS content, particularly DS coarse size decreased the TS of the composites. The percentage of elongation at break (Eb) decreased while the modulus increased gradually as DS content increased in LLDPE/DS composites, which made the composite stiffer and less flexible. The SEM shows clearly the good distribution of DS fine size and the agglomeration of DS coarse size.

关键词： Tensile strength

来源：评论

学校读者我要写书评

暂无评论

Short-term electricity demand forecasting via variational autoencoders and batch training-based bidirectional long short-term memory

引用

SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS 2022年第PartC期52卷

作者： Moradzadeh, Arash Moayyed, Hamed Zare, Kazem Mohammadi-Ivatloo, Behnam [a]Faculty of Electrical and Computer Engineering University of Tabriz *** Tabriz Iran [b]GECAD-Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development Polytechnic of Porto (P. PORTO) P-4200-072 Porto Portugal [c]Information Technologies Application and Research Center İstanbul Ticaret University Istanbul Turkey

Electricity load forecasting is a key aspect for power producers to maximize their economic efficiency in deregulated markets. So far, many solutions have been employed to forecast the consumption load in power grids. However, most of these methods have suffered in modeling the time-series state of data and removing noise from real-world data. Thus, the forecasting results in most cases did not have acceptable accuracy due to the mentioned problems. In this paper, in order to short-term electricity load forecast in Tabriz, Iran, a hybrid technique based on deep learning applications called Variational Autoencoder Bidirectional Long Short-Term Memory (VAEBiLSTM) is presented. Pre-processing, noise cancellation, and time-series state modeling of the data are prominent features of the developed load forecasting model. In addition, in order to prevent overfitting problems in the process of training large amounts of data, the training process is developed in the form of batch training. Load forecasting is done using meteorological and environmental data of Tabriz city as well as historical information and days of the week as input variables. In the hybrid method structure, the Variational Autoencoders are applied to the data for data preprocessing and reconstruction. Then, the normalized, noise-free data is utilized as a dataset for training the Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed training method for BiLSTM is based on batch training. To present the effectiveness of the proposed technique in a comparative approach, the conventional LSTM and Support Vector Regression (SVR) algorithms are also applied to the data. Each network is trained with input data related to the years of 2017 and 2018 to predict the electricity load of the Tabriz city separately for each of the four seasons of the 2019 year. The forecasting results obtained from each method are evaluated by different statistical performance indicators. It can be seen that the proposed

关键词： Electricity demand Load forecasting Deep learning Variational Autoencoders (VAE) Bidirectional long short-term memory (BiLSTM)

来源：评论

学校读者我要写书评

暂无评论

SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning

arXiv

引用

arXiv 2023年

作者： Ren, Ziyao Kang, Yan Fan, Lixin Yang, Linghua Tong, Yongxin Yang, Qiang State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing School of Computer Science Beihang University China Webank China Hong Kong University of Science and Technology Hong Kong

SecureBoost is a tree-boosting algorithm leveraging homomorphic encryption to protect data privacy in vertical federated learning setting. It is widely used in fields such as finance and healthcare due to its interpretability, effectiveness, and privacy-preserving capability. However, SecureBoost suffers from high computational complexity and risk of label leakage. To harness the full potential of SecureBoost, hyperparameters of SecureBoost should be carefully chosen to strike an optimal balance between utility, efficiency, and privacy. Existing methods either set hyperparameters empirically or heuristically, which are far from optimal. To fill this gap, we propose a Constrained Multi-Objective SecureBoost (CMOSB) algorithm to find Pareto optimal solutions that each solution is a set of hyperparameters achieving optimal tradeoff between utility loss, training cost, and privacy leakage. We design measurements of the three objectives. In particular, the privacy leakage is measured using our proposed instance clustering attack. Experimental results demonstrate that the CMOSB yields not only hyperparameters superior to the baseline but also optimal sets of hyperparameters that can support the flexible requirements of FL participants. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Signal approximation with Pascal’s triangle and sampling

Signal approximation with Pascal’s triangle and sampling

引用

Chinese Control and Decision Conference, CCDC

作者： Lei Chen Xinghuo Yu Jinhu Lü School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Engineering RMIT University Melbourne VIC Australia

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

This brief explores the approximation properties of a unique basis expansion based on Pascal's triangle, which realizes a sampled-data driven approach between a continuous-time signal and its discrete-time representation. The roles of certain parameters, such as sampling time interval or model order, and signal characteristics, i.e., its curvature, on the approximation are investigated. Approximate errors in one and multiple-step predictions are analyzed. Furthermore, time-variant approximations under the thresholds of signal curvature are employed to narrow errors and provide flexibilities.

关键词： Shape Electronic mail Analytical models Mathematical analysis Data models Upper bound

来源：评论

学校读者我要写书评

暂无评论

Generating disentangled arguments with prompts: A simple event extraction framework that works

arXiv

引用

arXiv 2021年

作者： Si, Jinghui Peng, Xutan Li, Chen Xu, Haotian Li, Jianxin Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China State Key Laboratory of Software Development Environment Beihang University China Alibaba Group China Department of Computer Science The University of Sheffield United Kingdom

Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding constraints. In this paper, for the first time we introduce the prompt-based learning strategy to the domain of Event Extraction, which empowers the automatic exploitation of label semantics on both input and output sides. To validate the effectiveness of the proposed generative method, we conduct extensive experiments with 11 diverse baselines. Empirical results show that, in terms of F1 score on Argument Extraction, our simple architecture is stronger than any other generative counterpart and even competitive with algorithms that require template engineering. Regarding the measure of recall, it sets new overall records for both Argument and Trigger Extractions. We hereby recommend this framework to the community, with the code publicly available at https://***/GDAP. Copyright © 2021, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A parallel algorithm for logic simulation on transputer networks

A parallel algorithm for logic simulation on transputer netw...

引用

Great Lakes Symposium on VLSI

作者： S. Srinivas A. Basu A. Paulraj L.M. Patnaik Department of Electrical and Computer Engineering Concordia University Montreal QUE Canada Centre for Development of Advanced Computing Bangalore India Microprocessor Applications Laboratory Supercomputing Education and Research Center Department of Computer Science and Automation Indian Institute of Science Bangalore India

The authors present a parallel algorithm for logic simulation of VLSI circuits. It is implemented on a network of transputers connected in a ring topology. The approach is based on partitioning a functionality matrix representation of the circuit among the transputers and adopting a data flow technique for the solution. A significant aspect of the algorithm is that it overlaps computation with communication, thereby reducing the communication overhead. It also attempts even distribution of load in order to reduce processor idle time. The algorithm possesses the advantages of ease of implementation and ease of extension to incorporate additional parameters for simulation. Performance results of the algorithm are given.< >

关键词： Parallel algorithms Circuit simulation Computational modeling Concurrent computing Application software Logic circuits Very large scale integration Algorithm design and analysis Logic design Design automation

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Automated Smart Irrigation System Incorporating Sensor Parameters 5th

IoT-Enabled Automated Smart Irrigation System Incorporating ...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Singh, Jagendra Neeraj Srinivas Reddy, P. Hasan, Dler Salih Alsahlanee, Abbas Thajeel Rhaif Shaik, Nazeer Alliance School of Advanced Computing Alliance University Bangalore India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Mechanical Engineering CVR College of Engineering Hyderabad India Department of Computer Science and Information Technology University of Salahaddin-Erbil Erbil Iraq Development and Continuous Education Center University of Thi-Qar Thi-Qar Iraq Department of Computer Science and Engineering Srinivasa Ramanujan Institute of Technology—Autonomous Anantapur India

ISBN: (纸本)9789819763177

This article presents the experimental findings of a smart irrigation system evaluated in two separate agricultural settings—small-scale farming and large-scale agriculture. The system combines sensors, microcontrollers, and actuators to precisely monitor and regulate the irrigation process in order to optimum water use and crop output. Water savings range from 20 to 45% when using smart irrigation technology in small-scale agriculture. By only turning on the irrigation pump when necessary, the technology optimizes water use and fosters sustainable farming methods. Furthermore, by sustaining perfect growing conditions, the approach boosts crop output, with yield benefits ranging from 10 to 22%. These improvements assist small-scale farmers in becoming more profitable and raising their level of living. In large-scale agriculture, smart irrigation systems allow excellent water management and resource optimization across huge agricultural fields. The technology consistently saves a large quantity of water, often between 25 and 50%, addressing water scarcity issues. Additionally, this method has led to a 12–25% increase in aggregate crop yields, thereby raising farm income and increasing agricultural firm profitability. Experiments shows that this smart irrigation system could bring cost-effective, sustainable techniques to extensive and intensive agriculture alike. Intelligence-guided decision-making technology is applied here, and cutting-edge technologies are brought to bear on the water use problem. The system conserves precious resources and increases agricultural output at the same time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

On the Outage Performance of Drones-Aided Cooperative D2D communications systems

On the Outage Performance of Drones-Aided Cooperative D2D co...

引用

Computer Communications and Intelligent Systems (I3CIS), International Conference on

作者： Widad Belaoura Khalida Ghanem Mohummed Zeeshan Shakir Department Engineering of Electrical Systems Université M'Hamed Bougara Boumerdes Boumerdes Algeria System Architecture Laboratory Center of development of advanced techniques (CDTA) Algiers Algeria School of Computing Engineering and Physical Sciences University of the West of Scotland Paisley UK

The advanced Device-to-Device (D2D) system is recognized as one of the key emerging technologies to support the increasing wireless data traffic of fifth generation (5G) systems and beyond. In this paper, we aim to study a novel cooperative D2D communications concept to improve the communication between the D2D users. In this model, multiple drones are included in the network and operate as half duplex amplify-and-forward (AF) relays scheme and the Maximal Ratio Combining (MRC) method is employed at the receiver side to combine the relayed signals. The effect of various parameters on the outage probability is investigated, including drone altitude placement, number of drones, and transmission power. Simulation results indicate that the outage probability of the cooperative D2D solution is greatly improved whenever an additional drone is added to the cooperative system.

关键词： Wireless communication Simulation System performance Cooperative systems Receivers Probability Device-to-device communication

来源：评论

学校读者我要写书评

暂无评论

Fast Tunable Coupling Scheme of Kerr Parametric Oscillators Based on Shortcuts to Adiabaticity

引用

Physical Review Applied 2022年第3期18卷 034076-034076页

作者： S. Masuda T. Kanao H. Goto Y. Matsuzaki T. Ishikawa S. Kawabata Research Center for Emerging Computing Technologies (RCECT) National Institute of Advanced Industrial Science and Technology (AIST) 1-1-1 Umezono Tsukuba Ibaraki 305-8568 Japan NEC-AIST Quantum Technology Cooperative Research Laboratory National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba Ibaraki 305-8568 Japan Frontier Research Laboratory Corporate Research & Development Center Toshiba Corporation 1 Komukai-Toshiba-cho Saiwai-ku Kawasaki 212-8582 Japan

Kerr parametric oscillators (KPOs), which can be implemented with superconducting parametrons possessing large Kerr nonlinearity, have been attracting much attention in terms of their applications to quantum annealing, universal quantum computation, and studies of quantum many-body systems. It is of practical importance for these studies to realize fast and accurate tunable coupling between KPOs in a simple manner. We develop a simple scheme of fast tunable coupling of KPOs with high tunability in speed and amplitude using the fast transitionless rotation of a KPO in the phase space based on the shortcuts to adiabaticity. Our scheme enables rapid switching of the effective coupling between KPOs, and can be implemented with always-on linear coupling between KPOs, by controlling the phase of the pump field and the resonance frequency of the KPO without controlling the amplitude of the pump field nor using additional drive fields and couplers. We apply the coupling scheme to a two-qubit gate, and show that our scheme realizes high gate fidelity compared with a purely adiabatic one, by mitigating undesired nonadiabatic transitions.

关键词： Circuit quantum electrodynamics Optoelectronics Quantum control Quantum gates Quantum information with solid state qubits Optical parametric oscillators & amplifiers Superconducting qubits Kerr effect

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：