检索结果-内蒙古大学图书馆

OpenAI-Powered NLP for SQL Generation: Enhancing Database Access for Non-Technical Users

OpenAI-Powered NLP for SQL Generation: Enhancing Database Ac...

International ECTI Northern Section Conference on electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Yuenyong Nilsiam Piyaphiphat Khammaw Siranee Nuchitprasitchai Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Information Technology Faculty of Information Technology and Digital Innovation King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543273

ISBN: (纸本)9798331543280

Database accessibility can be challenging for users without technical expertise, particularly when generating SQL queries to retrieve information. This study addresses this gap by developing an OpenAI-powered system designed to automate SQL command generation, enabling non-expert users to interact with databases using natural language. Implemented as a web application, the system was evaluated by expert users, assessing both performance in query accuracy and user satisfaction. Results indicate high usability and satisfaction scores, with the system effectively enhancing accessibility to database functions, thus providing a user-friendly solution for database management.

关键词： Structured Query Language Accuracy Translation Databases Decision making Data structures User experience Systems support Usability Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Adaptive One Sample Ahead Preview control for Non-Sinusoidal PMSM with dq Coordinate Implementation

Adaptive One Sample Ahead Preview Control for Non-Sinusoidal...

引用

International Conference on electrical Machines and Systems (ICEMS)

作者： Guilherme V. Hollweg Lucas R. Rocha Van-Hai Bui Rodrigo P. Vieira Mengqi Wang Wencong Su Department of Electrical and Computer Engineering (ECE) University of Michigan-Dearborn Dearborn USA Power Electronics and Control Group Federal University of Santa Maria Santa Maria Brazil

ISBN: (数字)9784886864406

ISBN: (纸本)9798350379105

This paper shows a Adaptive One Sample Ahead Preview (AOSAP) control structure designed for Non-Sinusoidal Permanent Magnet Synchronous Motors (PMSMs), implemented in both $d$ and $q$ coordinates. The control strategy employs a first-order reference model and is systematically compared against conventional Proportional-Integral (PI) controllers. Experimental evaluations conducted on a Typhoon Hardware-in-the-Loop (HIL) 604 platform demonstrate the superior performance of the proposed AOSAP controller. It exhibits lower tracking errors, leading to reduced torque ripple, and demonstrates faster regulation when compared to classical PI structures. The control algorithms are practically realized on a TMS320F28335 digital signal processor (DSP), showcasing the feasibility and efficiency of the proposed approach in real applications.

关键词： Torque PI control Tropical cyclones Digital signal processors Signal processing algorithms Permanent magnet motors Harmonic analysis Regulation Torque measurement Optimization

来源：评论

学校读者我要写书评

暂无评论

Artificial neural network-based estimation for rotor-flux model reference adaptive system

引用

Transportation Research Procedia 2023年 74卷 838-845页

作者： David Bielesz Marek Kubatko Štěpán Kirschner Jan Milata Vojtěch Šotola Department of Electronics Faculty of Electrical Engineering and Computer Science VSB – Technical University of Ostrava 17. listopadu 2172/15 70800 Ostrava-Poruba Czech Republic

At the start, this paper focuses on the function of a rotor-flux model reference adaptive system (RF-MRAS) and in the following part on the realization and application of artificial neural networks (ANN) in a sensorless induction motor drive. Afterwards, a data collection and usage process for the training of ANN is described. In the final part, experimental results of ANN's ability to estimate rotor flux are presented. According to simulations, ANN estimations are accurate and its application as a part of a control scheme looks promising.

关键词： artificial neural network (ANN) neural network (NN) RF-MRAS MRAS rotor flux estimation sensorless control induction motor

来源：评论

学校读者我要写书评

暂无评论

Tackling heavy-tailed noise in distributed estimation: Asymptotic performance and tradeoffs

Tackling heavy-tailed noise in distributed estimation: Asymp...

引用

Telecommunications Forum (TELFOR)

作者： Dragana Bajovic Dusan Jakovetic Soummya Kar Manojlo Vukovic Department of Power Electronic and Communication Engineering Faculty of Technical Sciences University of Novi Sad Department of Mathematics and Informatics Faculty of Sciences University of Novi Sad Department of Electrical and Computer Engineering Carnegie Mellon University Department of Fundamental Sciences Faculty of Technical Sciences University of Novi Sad

ISBN: (数字)9798350391060

ISBN: (纸本)9798350391077

We present an algorithm for distributed estimation of an unknown vector parameter θ ∗ ∈ ℝ M in the presence of heavy-tailed observation and communication noises. Heavy-tailed noises frequently appear, e.g., in densely deployed Internet of Things (IoT) or wireless sensor network systems. The presented algorithm falls within the class of consensus+innovation estimators and combats the effect of the heavy-tailed noises by adding general nonlinearities in the consensus and innovations update parts. We present results on almost sure convergence and asymptotic normality of the estimator. In addition, we provide novel analytical studies that reveal interesting tradeoffs between the system noises and the underlying network topology.

关键词： Technological innovation Wireless sensor networks Heavily-tailed distribution Network topology Noise Estimation Vectors Telecommunications Internet of Things Convergence

来源：评论

学校读者我要写书评

暂无评论

Reinforcement of Medical Image Security Through Steganography and Encryption Techniques

Reinforcement of Medical Image Security Through Steganograph...

引用

Electronic engineering (ICEEM), International Conference on

作者： Fatma Khallaf Walid El-Shafai El-Sayed M. El-Rabaie Fathi E. Abd El-Samie Department of Electronics and Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf Egypt Department of Electrical Engineering Faculty of Engineering Ahram Canadian University Giza Egypt Department of Computer Science Security Engineering Laboratory Prince Sultan University Riyadh Saudi Arabia

Patients' data is stored in Electronic Health Records (EHRs) for confidentiality purposes. However, the insecure networks of hospitals and clinics puts patient information at risk. To address this ethical issue, secure communication is crucial. The Digital Imaging and Communications in Medicine (DICOM) standard governs the transmission of EHRs to maintain data integrity and confidentiality. This paper combines cryptography and steganography techniques to transmit medical information and images across hospital networks, securely. The introduced framework comprises encryption of patients' data using DNA-based Advanced Encryption Standard (AES), hiding the information within images using Least Significant Bit (LSB) embedding, compressing the stego images using Discrete Wavelet Transform (DWT), and reversal of the process at the receiver end. Simulation experiments demonstrate that this framework comprising both encryption and steganography outperforms existing methods in securing the medical data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of MEMS Tuning Fork Gyroscope Designs with Microlever Amplification Mechanism for Enhanced Sensitivity and Robustness

Comparative Analysis of MEMS Tuning Fork Gyroscope Designs w...

引用

International Conference on Robotics and Artificial Intelligence (ICRAI)

作者： Uzair Bashir Faraz Javaid Osama Ali Adeel Arshad Masood Ur Rehman Department of Electrical and Computer Engineering Sir Syed CASE Institute of Technology (SS-CASE-IT) Islamabad Pakistan Department of Mechatronics Engineering National University of Sciences and Technology (NUST) Islamabad Pakistan Faculty of Engineering and Technology Superior University Lahore Pakistan

ISBN: (数字)9798350355703

ISBN: (纸本)9798350355710

This paper presents a comparative analysis of two MEMS Tuning Fork Gyroscope (TFG) designs employing microlever amplification mechanisms for sensitivity amplification in the sense mode. An input frame added in microlever amplification frame to increase the robustness of MEMS gyroscope. Design A incorporates a non-anchored input frame in microlever, while Design B features an anchored input frame in microlever. Frequency response analysis and modal analysis were performed using CoventorMEMS+ to evaluate the impact of input frame of microlever on undesired mode suppression, mechanical sensitivity, and robustness. The results indicate that anchoring the microlever in Design B significantly reduces quadrature displacement arise because of environmental linear acceleration in the sense mode while maintaining comparable amplified sensitivity to Design A. Design B offers enhanced stability and robustness, making it a more suitable candidate for precision applications such as autonomous vehicle navigation systems.

关键词： Micromechanical devices Vibrations Sensitivity Navigation Modal analysis Resonant frequency Robustness Stability analysis Gyroscopes Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Unveiling Emotions and Themes in Thai Songs via Topic Modeling

Unveiling Emotions and Themes in Thai Songs via Topic Modeli...

引用

International Joint Conference on computer Science and Software engineering (JCSSE)

作者： Panupong Wanjantuk Niyom Pinitkarn Sonephanom Sengthavideth Jirat Matthayomnan Anupap Meesomboon Department of Computer Engineering Faculty of Engineering Khon Kaen University Khon Kaen Thailand Department of Electrical Engineering Faculty of Engineering Khon Kaen University Khon Kaen Thailand Scientific Research and Academic Services Office Champassak University Pakse City Western Music Department Bansomdejchaopraya Rajabhat University Bangkok Thailand

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

This paper presents a comprehensive analysis of Thai song lyrics through the application of Latent Dirichlet Allocation (LDA), exploring the thematic and emotional landscapes embedded within. By leveraging advanced computational linguistics techniques, this study uncovers the dominant themes such as love, personal growth, cultural identity, and their prevalence across a diverse corpus of lyrics. The findings illustrate how music serves as a mirror to societal values and individual experiences, revealing a nuanced tapestry of life's narratives that resonate deeply within Thai culture. Employing the Gensim library for LDA model implementation, the research meticulously fine-tunes model parameters, including topic numbers and hyperparameters, to ensure optimal thematic distinction and coherence. The analysis benefits from both quantitative metrics, like Coherence and Perplexity Scores, and qualitative expert evaluations, validating the cultural relevance and authenticity of the identified themes. Key contributions of this work include the innovative use of computational techniques in cultural analytics, enhancing our understanding of thematic and emotional dimensions in music. The study not only sheds light on the intricacies of Thai song lyrics but also demonstrates the potential of computational approaches in the arts and humanities. By providing artists and the music industry with data-driven insights and enriching cultural studies, this research underscores the symbiotic relationship between music, language, and society, paving the way for future interdisciplinary explorations.

关键词： Industries Analytical models Art Computational modeling Music Coherence Market research

来源：评论

学校读者我要写书评

暂无评论

Building Damage Detection Using Deep Learning Models

Building Damage Detection Using Deep Learning Models

引用

International Conference on Telecommunications (ICT)

作者： Kibitok Abraham Moataz Abdelwahab Mohammed Abo-Zahhad Communications & Computer Engineering School of Electronics Egypt-Japan University of Science and Technology (E-JUST) New Borg EI Arab City Alexandria Egypt Electrical Engineering Department Faculty of Engineering Assiut University Assiut Egypt

ISBN: (数字)9798350356694

ISBN: (纸本)9798350356700

Human life is significantly impacted by ongoing natural disasters. The global impact of the building damage they inflict is deeply significant. Deep learning can effectively analyze the extent of damage to buildings. However, the challenge is the availability of the dataset. An innovative, challenging dataset collected from satellites has been presented, encompassing the extent of structural harm caused by the earthquake in Morocco. The dataset is from a complex, practical, arid environment where the building colour is almost like the background. The dataset has been tested using U-Net, FCN, and ResUnet models. The ResUnet demonstrates superior performance metrics with pixel accuracy, recall, precision, Fl-score, kappa score, and IoU values of 96.2%, 86.4%, 86%, 86.2%, 75.7%, and 85.5%, respectively, which promotes it for practical application.

关键词： Measurement Deep learning Accuracy Satellites Image color analysis Green buildings Disasters

来源：评论

学校读者我要写书评

暂无评论

Topological Signal Processing and Learning: Recent Advances and Future Challenges

arXiv

引用

arXiv 2024年

作者： Isufi, Elvin Leus, Geert Beferull-Lozano, Baltasar Barbarossa, Sergio Lorenzo, Paolo Di Faculty of Electrical Engineering Mathematics and computer Science Delft University of Technology Delft Netherlands SIGIPRO Department Simula Metropolitan Center for Digital Engineering Oslo Norway Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Rome Italy

Developing methods to process irregularly structured data is crucial in applications like gene-regulatory, brain, power, and socioeconomic networks. Graphs have been the go-to algebraic tool for modeling the structure via nodes and edges capturing their interactions, leading to the establishment of the fields of graph signal processing (GSP) and graph machine learning (GML). Key graph-aware methods include Fourier transform, filtering, sampling, as well as topology identification and spatiotemporal processing. Although versatile, graphs can model only pairwise dependencies in the data. To this end, topological structures such as simplicial and cell complexes have emerged as algebraic representations for more intricate structure modeling in data-driven systems, fueling the rapid development of novel topological-based processing and learning methods. This paper first presents the core principles of topological signal processing through the Hodge theory, a framework instrumental in propelling the field forward thanks to principled connections with GSP-GML. It then outlines advances in topological signal representation, filtering, and sampling, as well as inferring topological structures from data, processing spatiotemporal topological signals, and connections with topological machine learning. The impact of topological signal processing and learning is finally highlighted in applications dealing with flow data over networks, geometric processing, statistical ranking, biology, and semantic communication. © 2024, CC BY.

关键词： Network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

Analysis Ethical and Social Implications of Artificial Intelligence (AI)

Analysis Ethical and Social Implications of Artificial Intel...

引用

Cognitive Computing in engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Faraz Khan P. K. Bharti Md Heshamuddin Muhammad Farhan Rizwan A. Farade Adeel Ahmad Khalique Ahmad Department of Computer Science & Engineering Glocal School of Science & Technology Glocal University Saharanpur Uttar Pradesh India Department of Mechanical Engineering School of Science & Technology Glocal University Saharanpur Uttar Pradesh India Department of Electrical and Electronics Engineering Faculty of Engineering Advanced Lightning Power and Energy Research (ALPER) University Putra Malaysia Serdang Malaysia Department of computer and network Engineering college engineering and computer science Jazan university Saudia Arabia

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Artificial Intelligence (AI) has progressed significantly in recent years, revolutionizing various industries and influencing numerous aspects of everyday life. This research paper aims to explore unique insights into AI, focusing on its advancements, challenges, and future implications. Through an in-depth analysis of the existing literature and cutting-edge developments, this study presents an original perspective on AI and its role in shaping the world. The increasing use of artificial intelligence (AI) tools in manipulating images, videos, and voices has led to the rise of AI-based voice scams. This research paper aims to shed light on the alarming rate at which Indian individuals are falling prey to such fraudulent activities and the lack of awareness and information that contributes to their victimization. Through a comprehensive analysis of a recent study by McAfee, this paper emphasizes the urgent need to educate and inform individuals about the risks associated with AI-generated voices and provides recommendations for prevention.

关键词： Ethics Privacy Prevention and mitigation Collaboration Psychology Machine learning Regulation Security Artificial intelligence Videos

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：