检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data

作者： Xiaodi Li Niamat Zawad Patrick T. Brandt Javier Osorioc Vito D’Orazio Latifur Khan Computer Engineering The University of Texas at Dallas Richardson USA Computer Science The University of Texas at Dallas Richardson USA Economic Political and Policy Science The University of Texas at Dallas Richardson USA School of Government and Public Policy The University of Arizona Tucson USA Department of Political Science West Virginia University Morgantown USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The ConfliLPC framework introduces an innovative integration of Logits and Parameter Calibration (LPC) with the ConfliBERT model, tailored specifically for the nuanced analysis of political conflict and violence. This paper details the development and application of ConfliLPC, highlighting its robust capability to adapt to evolving data landscapes without succumbing to catastrophic forgetting (CF), a common challenge in machine learning models applied to dynamic domains such as political science. ConfliLPC enhances accuracy and adaptability by continually adjusting its parameters to accommodate new information while retaining valuable historical insights. The framework has been rigorously tested across various conflict scenarios, demonstrating superior performance in real-time analysis and predictive tasks. This work serves as a significant contribution to the fields of political science, conflict research, and applied machine learning, providing a powerful tool for analysts and policymakers engaged in the understanding and resolution of political conflict. The experimental results highlight the efficiency of the ConfliLPC method and its capability to minimize CF. Our code is publicly available 1

关键词： Continuing education Adaptation models Analytical models Accuracy Machine learning Data models Real-time systems Question answering (information retrieval) Calibration Streams

来源：评论

学校读者我要写书评

暂无评论

Disturbance Observer-Enhanced Adaptive CBFs for Safety-Critical Motion Control of Autonomous Vehicles

Disturbance Observer-Enhanced Adaptive CBFs for Safety-Criti...

引用

International Conference on Intelligent Transportation

作者： Yifan Cheng Yuxiang Zhang Yuyao Jiang Hongqing Chu Bingzhao Gao Hong Chen College of Electronic and Information Engineering Tongji University Shanghai China Department of Electrical and Computer Engineering National University of Singapore Singapore School of Customs and Public Administration Shanghai Customs College Shanghai China School of Automotive Studies Tongji University Shanghai China

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

The standalone adaptability in the penalty parameters of adaptive control barrier functions (ACBFs), may be insufficient to meet the high requirements for safety and robustness of autonomous vehicles (AVs) motion control, especially under system disturbances. This paper integrates the disturbance observer theory into the ACBFs, in order to improve the robustness and adaptability of the corresponding optimization framework. The enhanced performance is mainly realized in the following aspects: firstly, an auxiliary system for safety-critical control design is defined, and the constraints, related to the penalty parameters, are introduced. Secondly, the disturbance observers are introduced to estimate the unknown parts of high-order safety and stability constraints. Thirdly, the estimated error bounds are introduced into the original framework of ACBF-CLF-QPs to guarantee robustness and adaptive safety. The superior performance compared to the original ACBFs is verified in the AVs motion control under the classical scenario, and the simulation results indicate that, the proposed method has stronger robustness and adaptability to system disturbances while meeting the safety constraints.

关键词： Control design Simulation Robustness Stability analysis Disturbance observers Safety Motion control Optimization Autonomous vehicles Intelligent transportation systems

来源：评论

学校读者我要写书评

暂无评论

DataDecon: Data Cleansing Tools for Large Language Model with Efficient Decontamination Techniques

DataDecon: Data Cleansing Tools for Large Language Model wit...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Sumeth Yuenyong Norapat Buppodom Koravich Sangkaew Konthee Boonmeeprakob Prachya Boonkwan Jillaphat Jaroenkantasima Pitikorn Khlaisamniang Anuruth Lertpiya Apivadee Piyatumrong Peerawat Rojratchadakorn Thaweewat Rugsujarit Teerapol Saengsukhiran Kriangkrai Saetan Isada Sukprapa Thanachot Thavornmongkol Nucharee Thongthungwong Patteera Triamamornwooth Chanon Utupon Kobkrit Viriyayudhakorn Phoochit Witchutanon Sadit Wongprayon Thepchai Supnithi Department of Computer Engineering Faculty of Engineering Mahidol University National Electronics and Computer Technology Center Pathumthani Thailand Artificial Intelligence Asssociation of Thailand Big Data Institute (Public Organization) Bangkok Department of Electrical Engineering Faculty of Engineering Kasetsart University Looloo Technology Faculty of Engineering Kasetsart University Kasikorn Labs Kasikorn Business Technology Group Faculty of Science King Mongkut’s Institute of Technology Ladkrabang School of Information Computer and Communication Technology Sirindhorn International Institute of Technology Thammasat University Next AI Solutions Department of Biomedical Engineering Faculty of Engineering Mahidol University Department of Computer Science University of Liverpool Department of Mechanical Engineering King Mongkut’s University of Technology North Bangkok Artificial Intelligence Entrepreneur Association of Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

Large language models (LLMs) play an important role in modern NLP technology as they are versatile for a wide array of NLP tasks. However, constructing an LLM is challenging due to concealed construction pipelines, the lack of cleansed datasets, and hyperparameter settings, making it almost irreproducible. This paper presents an efficient pipeline for constructing an LLM tailored to a low-to-medium-sourced language with a high level of data contamination and tools to cleanse the dataset. Following our pipeline, we constructed OpenThaiGPT, an LLM for Thai, with only open-sourced datasets such as CC100, OSCAR, and mC4, and achieved the state-of-the-art accuracies on our downstream tasks. Here, we disclosed the data statistics and all hyperparameter settings for reproducibility.

关键词： Accuracy Large language models Decontamination Pipelines Data visualization Data models Natural language processing Reproducibility of results Arrays Contamination

来源：评论

学校读者我要写书评

暂无评论

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spectrum

Compact Millimeter-Wave Antenna Operating in 28/38 GHz Spect...

引用

2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting, AP-S/URSI 2022

作者： Rizvi, Syed Naheel Raza Sarfraz, Muhammad Alibakhshikenari, Mohammad Dalarsson, Mariana Falcone, Francisco Chungbuk National University Department of Information and Communication Engineering Cheongju Korea Republic of Virtual University of Pakistan Department of Computer Science Lahore Pakistan Universidad Carlos III de Madrid Department of Signal Theory and Communications Madrid Leganés28911 Spain KTH Royal Institute of Technology School of Electrical Engineering and Computer Science StockholmSE 100-44 Sweden Public University of Navarre Electric Electronic and Communication Engineering Department Pamplona31006 Spain Public University of Navarre Institute of Smart Cities Pamplona31006 Spain

ISBN: (数字)9781665496582

ISBN: (纸本)9781665496582

We present a compact wideband antenna operating in the 28 GHz and 38 GHz millimeter-wave spectrum. The proposed antenna is designed on the Rogers RT/duroid 5880 substrate. The proposed antenna has a simple geometry and compact dimensions of 17 mm × 12 mm × 0.79 mm. The antenna design is simulated using the ANSYS HFSS software. The features of the proposed antenna are also compared to similar designs from the literature, to demonstrate the potential of our antenna for use in the targeted frequency band. The results in the present paper indicate that our design is a good candidate for use in future wireless communication systems. © 2022 IEEE.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Cold ironing techno-economical study for a port with photovoltaic plants

引用

e-Prime - Advances in electrical engineering, Electronics and Energy 2024年 8卷

作者： Lamprinidi, Eleni P. Tsekouras, George J. Orfanos-Pepainas, Stamatios Kanellos, Fotios D. Prousalidis, John M. Vlachos, Andreas Tsirekis, Constantinos D. School of Electrical & Computer Engineering National Technical University of Athens Greece Department of Electrical and Electronics Engineering Faculty of Engineering University of West Attica Greece School of Electrical & Computer Engineering Technical University of Crete Greece School of Naval Architecture & Marine Engineering National Technical University of Athens Greece Department of Long Term Energy Planning Renewable Energy Sources & Environmental Policy Regulatory Authority of Energy Greece Strategy & System Planning Department Hellenic Independent Power Transmission Operator Greece

According to European regulation 2023/1804/EU, all member states shall ensure the availability of cold ironing (CI) in large ports for at least 90 % of the total number of port calls of seagoing ships above 5000 gross tonnes, by the end of 2029. This is a measure expected to improve air quality, especially in the vicinity of the port's urban environment. Preliminary studies show that there are financial viability issues related to CI installations, under the current electricity pricing policies and the high investment cost for CI infrastructure. In this paper, the financial viability of the penetration of photovoltaic (PV) units optimized from spatial and power produced point of view is investigated. The proposed method is applied to various ship types, indicatively for the Thessaloniki Port, taking into consideration the connection with the Medium Voltage (MV) electricity distribution grid, as well as the construction, operation, and maintenance costs, under modified economic criterion of benefit-cost ratio (BCR). © 2024 The Authors

关键词： Cold ironing Feasibility study Photovoltaic plant Shore connection

来源：评论

学校读者我要写书评

暂无评论

Low Complexity Heuristics for Multi-Objective Sensor Placement in Traffic Networks

Low Complexity Heuristics for Multi-Objective Sensor Placeme...

引用

International Conference on Intelligent Transportation

作者： Marina Sofokleous Yiolanda Englezou Aristotelis Savva Stelios Timotheou Christos G. Panayiotou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Public Works Department of the Ministry of Transport Communications & Works Nicosia Cyprus

Monitoring the traffic state of the road network is very important for a plethora of reasons, such as the prevention of traffic congestion and the development of estimation and control policies. In order to efficiently obtain high-quality information on traffic, the sensors must be installed at optimal locations in the road network under study. This problem is known as the Network Sensor Location Problem (NSLP). In this work, a multi-objective NSLP is proposed for the installation of a pre-defined number of sensors to maximise (i) the covered traffic flow volume and (ii) the minimum distance between candidate links for sensor installation, while taking into account pre-installed sensors. We reformulate the problem into a single-objective mixed-integer linear program (MILP) that yields the optimal sensor locations. In addition, we propose four low-complexity heuristics for the solution of the problem. The performance of the proposed algorithms is evaluated for the traffic network of the Republic of Cyprus under real-life conditions and traffic data. Results show that the four low-complexity approaches yield a different trade-off between execution speed and solution quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analytical inverter-based distributed generator model for power flow analysis

arXiv

引用

arXiv 2021年

作者： Turner-Bandele, Naeem Pandey, Amritanshu Pileggi, Larry Electrical and Computer Engineering Dept. Carnegie Mellon University Engineering and Public Policy Dept. Carnegie Mellon University

Quantifying the impact of inverter-based distributed generation (DG) sources on power-flow distribution system cases is arduous. Existing distribution system tools predominately model distributed generation sources as either negative PQ loads or as a PV generator and then employed a PV-PQ switching algorithm to mimic Volt/VAR support. These models neglect the unique characteristics of inverter-based distributed generation sources, have scalability and convergence issues, and are ill-suited for increasing solar penetration scenarios. This work proposes an inverter-based DG model accounting for the inverter's topology, sensing position, and control strategies. The model extends recently introduced analytical positive sequence generator models for three-phase studies. The use of circuit-simulation based heuristics help achieve robust convergence. Simulation of the PG&E prototypical feeders using a prototype solver demonstrate the model's accuracy and efficacy. © 2021, CC BY-NC-ND.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading Rate Prediction Using Deep Neural Networks

Ultrasound-Coupled Electrocoagulation Based Azo Dye Fading R...

引用

International KES Conference on Human Centred Intelligent Systems, KES HCIS 2023

作者： Akoulih, Meryem Tigani, Smail Wakrim, Asmaa Chehri, Abdellah Saadane, Rachid Ghachtouli, Sanae El IME Lab Faculty of Science Hassan 2 University Casablanca20250 Morocco AAIR Lab Digital Engineering and Artificial Intelligence Systems High Private School Casablanca20100 Morocco Electrical Engineering Department SIRC-LaGeS Hassania School of Public Labors Casablanca20250 Morocco Department of Mathematics and Computer Science Royal Military College KingstonONK7K 7B4 Canada

ISBN: (纸本)9789819934232

This research paper presents a deep learning based predictive model for predicting the azo dye fading rate during electrocoagulation coupled with ultrasound. Electrocoagulation is a commonly used method for the treatment of wastewater contaminated with azo dyes, but the efficiency of this process can be improved by incorporating ultrasound. The proposed deep learning model is trained on a dataset of electrocoagulation experiments with varying parameters such as current density, pH, and treatment time, as well as the presence or absence of ultrasound. The model is able to accurately predict the azo dye removal rate for new sets of electrocoagulation parameters, providing a valuable tool for optimizing the treatment process. The model’s performance is evaluated using standard metrics, and the results demonstrate its effectiveness in predicting azo dye removal rate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Azo dyes

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Deep Learning Algorithms in Twitter Bot Detection

Performance Comparison of Deep Learning Algorithms in Twitte...

引用

Recent Trends in Information Technology (CSCTIT), College of Science International Conference of

作者： Samer Emad Neama Al-ibadi Mesut Cevik Department of Electrical and Computer Engineering Altinbas University Istanbul Turkey Ministry of Communications Information & Telecom Public Company Baghdad Iraq Electrical and Computer Engineering Department Altinbas University Istanbul Turkey Istanbul Turkey

Difficulty in detecting social media bots - software-controlled accounts that seem as human - has serious consequences. Bots have been used to affect the financial market, political elections, and spreading conspiracy theories. Most approaches detect bots at the account level by studying social media posts and using network structure, system dynamics, content analytics, etc. In this study, we compare the performance of the recurrent neural network (RNN), convolutional neural network (CNN), and feed forward neural network (FNN) in detecting Twitter bots by evaluating the textual content of 10,416,240 tweets from humans and bots. Deep learning models utilize sample data to gauge performance. The CNN model identified recent social bot samples most accurately (97.67 %). In comparison, the RNN model achieved great accuracy (97.04 %) with a longer training time. RNN and CNN algorithms perform well when compared to other deep learning classifiers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of an EMG-based System for Monitoring and Help Request

Design and Implementation of an EMG-based System for Monitor...

引用

2022 International Conference on Smart Systems and Power Management, IC2SPM 2022

作者： Zeine, Carla Daou, Roy Abi Zeid Telawi, Samer Boercsoek, Josef Hayek, Ali Haidar, Gaby Abou University of Kassel Faculty of Electrical Engineering /Computer Science Department of Computer Architecture and System Programming Kassel Germany Lebanese German University Faculty of Public Health Jounieh Department of Computer Architecture and System Programming Biomedical Technologies Department Jounieh Lebanon Université la Sagesse Faculty of Engineering Furn El Chebbak Mechatronics Department Beirut Lebanon University of Applied Science Hamm-Lippstadt Department Lippstadt 2 Hardware Engineering Marker Allee 76-78 Hamm59063 Germany American University of Science and Technology Faculty of Engineering Zahle Lebanon

ISBN: (数字)9781665452915

ISBN: (纸本)9781665452915

Integrating electrophysiological signals in larger systems is getting wider due to the fact that such modalities facilitate the daily tasks of users. However, the high cost of monitoring systems (e.g., oscilloscopes) limits the testing and analysis of the acquired signal from such noisy systems (i. e., electrophysiological devices). The proposed system is a part of a larger proj ect that deals with the identification of sign language movements through the use of Muscle-computer Interfaces. On one hand, the user is able to display the signal acquired by the electrodes on an LCD screen. On the other hand, the system helps a mute patient to issue a special message to his surrounding environment that does not know the sign language to ask for help. The second feature is not unique, as it can be replaced by any other application based on the user's needs. The system was tested on several persons, and the results are promising. © 2022 IEEE.

关键词： Liquid crystal displays

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：