检索结果-内蒙古大学图书馆

Edit and Alphabet-Ordering Sensitivity of Lex-parse

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Nakashima, Yuto Köppl, Dominik Funakoshi, Mitsuru Inenaga, Shunsuke Bannai, Hideo Department of Informatics Kyushu University Japan Department of Computer Science and Engineering University of Yamanashi Japan NTT Communication Science Laboratories M&D Data Science Center Tokyo Medical and Dental University Japan

We investigate the compression sensitivity [Akagi et al., 2023] of lex-parse [Navarro et al., 2021] for two operations: (1) single character edit and (2) modification of the alphabet ordering, and give tight upper and lower bounds for both operations. For both lower bounds, we use the family of Fibonacci words. For the bounds on edit operations, our analysis makes heavy use of properties of the Lyndon factorization of Fibonacci words to characterize the structure of lex-parse. © 2024, CC BY.

关键词：

Asynchronous Deep Reinforcement Learning for Collaborative Task Computing and On-Demand Resource Allocation in Vehicular Edge Computing

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Transportation Systems 2023年第12期24卷 15513-15526页

作者： Liu, Lei Feng, Jie Mu, Xuanyu Pei, Qingqi Lan, Dapeng Xiao, Ming Xidian University Guangzhou Institute of Technology Guangzhou510555 China Ministry of Education Shanghai201804 China Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunication Engineering Shaanxi Xi'an710071 China Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Information Communication Network and Security Shaanxi Xi'an710121 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China University of Oslo Department of Informatics Oslo0373 Norway Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm10044 Sweden

Vehicular Edge Computing (VEC) is enjoying a surge in research interest due to the remarkable potential to reduce response delay and alleviate bandwidth pressure. Facing the ever-growing service applications in VEC, how to effectively aggregate and flexibly schedule ubiquitous network resources for implementing diverse tasks and meeting differentiated demands from numerous vehicular users remains haunting. Toward this end, we investigate collaborative task computing and on-demand resource allocation. The collaborative computing framework in VEC is provided to support deep collaboration and intelligent management of heterogeneous resources widely distributed in vehicles, edge servers and cloud. Based on this framework, the joint optimization problem of distributed task offloading and multi-resource management is formulated with the aim to maximize the system utility by making the optimal task and resource scheduling policy, the novelty of which lies in the exploration of available vehicle resources and the consideration of service migration. In view of the dynamics, randomness and time-variant of vehicular networks, the asynchronous deep reinforcement algorithm is leveraged to find the optimal solution. Extensive simulation experiments are implemented to demonstrate the superiority of our proposed algorithm in terms of response latency compared with full offloading and random offloading. © 2000-2011 IEEE.

关键词： Reinforcement learning

Aspect-Based Subjectivity Analysis Using a BERT-based Approach

学校读者我要写书评

暂无评论

Aspect-Based Subjectivity Analysis Using a BERT-based Approa...

International Conference on computer Applications and Industrial Electronics (ICCAIE)

作者： Hu Ng Wing Kin Chong Yu Zhang Chia Timothy Tzen Vun Yap Vik Tor Goh Lai Kuan Wong Ian Kim Teck Tan Dong Theng Cher Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia School of Mathematical & Computer Sciences Heriot-Watt University Putrajaya Malaysia Faculty of Engineering Multimedia University Cyberjaya Malaysia SIRIM Berhad Shah Alam Malaysia

ISBN: (数字)9798350348798

ISBN: (纸本)9798350348804

Aspect-based subjectivity analysis stands as an important task in natural language processing, seeking to identify the subjectivity of various aspects or features within a text. A new method for aspect-based subjectivity analysis using BERT is introduced in this paper. BERT has demonstrated impressive performance across various NLP tasks, and its capabilities are utilized to accurately ascertain the subjectivity of specific aspects within a given text. The approach involves fine-tuning BERT on a sizable dataset annotated with aspect-level subjectivity labels, enabling the model to grasp the subtleties of aspect-based subjectivity analysis. Extensive experiments on benchmark datasets are conducted to showcase the effectiveness of this approach and compare it with existing methods. The results reveal that this proposed approach surpasses state-of-the-art techniques in aspect-based subjectivity analysis, underscoring the potential of leveraging BERT for such purposes.

关键词： Industrial electronics Analytical models Sentiment analysis Predictive models Benchmark testing Robustness Task analysis

Thermal and RGB Images Work Better Together in Wind Turbine Damage Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Svystun, Serhii Melnychenko, Oleksandr Radiuk, Pavlo Savenko, Oleg Sachenko, Anatoliy Lysyi, Andrii Department of Computer Engineering and Information Systems Khmelnytskyi National University Khmelnytskyi29016 Ukraine Department of Computer Science Khmelnytskyi National University Khmelnytskyi29016 Ukraine Research Institute for Intelligent Computer Systems West Ukrainian National University Ternopil46020 Ukraine Department of Informatics Kazimierz Pulaski University of Technology and Humanities in Radom Radom26600 Poland

The inspection of wind turbine blades (WTBs) is crucial for ensuring their structural integrity and operational efficiency. Traditional inspection methods can be dangerous and inefficient, prompting the use of unmanned aerial vehicles (UAVs) that access hard-to-reach areas and capture high-resolution imagery. In this study, we address the challenge of enhancing defect detection on WTBs by integrating thermal and RGB images obtained from UAVs. We propose a multispectral image composition method that combines thermal and RGB imagery through spatial coordinate transformation, key point detection, binary descriptor creation, and weighted image overlay. Using a benchmark dataset of WTB images annotated for defects, we evaluated several state-of-the-art object detection models. Our results show that composite images significantly improve defect detection efficiency. Specifically, the YOLOv8 model’s accuracy increased from 91% to 95%, precision from 89% to 94%, recall from 85% to 92%, and F1-score from 87% to 93%. The number of false positives decreased from 6 to 3, and missed defects reduced from 5 to 2. These findings demonstrate that integrating thermal and RGB imagery enhances defect detection on WTBs, contributing to improved maintenance and reliability. © 2024, CC BY.

关键词： Unmanned aerial vehicles (UAV)

Predicting and Analyzing Pedestrian Crossing Behavior at Unsignalized Crossings

学校读者我要写书评

暂无评论

Predicting and Analyzing Pedestrian Crossing Behavior at Uns...

IEEE Symposium on Intelligent Vehicle

作者： Chi Zhang Janis Sprenger Zhongjun Ni Christian Berger Department of Computer Science and Engineering University of Gothenburg Sweden German Research Center for Artificial Intelligence (DFKI) Saarland Informatics Campus Germany Department of Science and Technology Linköping University Campus Norrköping Sweden

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Understanding and predicting pedestrian crossing behavior is essential for enhancing automated driving and improving driving safety. Predicting gap selection behavior and the use of zebra crossing enables driving systems to proactively respond and prevent potential conflicts. This task is particularly challenging at unsignalized crossings due to the ambiguous right of way, requiring pedestrians to constantly interact with vehicles and other pedestrians. This study addresses these challenges by utilizing simulator data to investigate scenarios involving multiple vehicles and pedestrians. We propose and evaluate machine learning models to predict gap selection in non-zebra scenarios and zebra crossing usage in zebra scenarios. We investigate and discuss how pedestrians’ behaviors are influenced by various factors, including pedestrian waiting time, walking speed, the number of unused gaps, the largest missed gap, and the influence of other pedestrians. This research contributes to the evolution of intelligent vehicles by providing predictive models and valuable insights into pedestrian crossing behavior.

关键词： Legged locomotion Pedestrians Intelligent vehicles Neural networks Machine learning Predictive models Safety

LMGAN: A Progressive End-to-End Chinese Landscape Painting Generation Model

学校读者我要写书评

暂无评论

LMGAN: A Progressive End-to-End Chinese Landscape Painting G...

International Joint Conference on Neural Networks (IJCNN)

作者： Yingqian Zhang Shaomin Xie Xiangrong Liu Nian Zhang School of Information Science and Technology Xiamen University Tan Kah Kee College Zhangzhou China School of Informatics Xiamen University Xiamen China College of Computer and Information Engineering Xiamen University of Technology Xiamen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

AI Generated Content (AIGC) has caught the attention of researchers around the world. Very good results have been achieved in the generation of Western art painting, but little research has been done on the generation of Chinese Landscape Painting (CLP). In addition, the quality of CLP generated by existing studies is still not high enough, they only imitate the color and often lack of details in their scenes. To overcome those weaknesses, we propose a progressive end-to-end Long Memory Adversarial Generation Network (LMGAN) to generate CLP. First, we create a new high-quality CLP dataset. Then we design a memory module and a mapping module to capture more low-dimensional features, as well as a layer extraction module to improve the layers of the generated results. Experiments show that LMGAN can generate richer and more detailed CLP compared to former methods.

关键词： Art Image color analysis Generative AI Neural networks Memory modules Feature extraction Painting

ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shivashankara, Kshama Kodthalu Deepanshi Shervedani, Afagh Mehri Clifford, Gari D. Reyna, Matthew A. Sameni, Reza The School of Electrical and Computer Engineering Georgia Institute of Technology AtlantaGA United States The Electrical and Computer Engineering Department University of Illinois Chicago ChicagoIL United States The Department of Biomedical Informatics Emory University AtlantaGA United States The Department of Biomedical Engineering Georgia Institute of Technology GA United States

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, and the electrocardiogram (ECG) plays a crucial role in diagnosing CVDs. For decades, ECGs have been recorded in printed formats, and their digitization offers significant potential for training machine learning (ML) models in algorithmic ECG diagnosis. However, the valuable information in physical ECG archives risks deterioration, leading to a considerable loss in CVD research, particularly in low and low-middle-income countries where paper-based ECGs are common. Furthermore, merely scanning printed ECGs is inadequate, as most ML models require ECG time-series data. Therefore, digitizing and converting paper ECG archives into time-series data is essential. In this context, deep learning models for image processing are promising. Nonetheless, the scarcity of clinical ECG archives with reference time-series data presents a challenge. To overcome this, data augmentation techniques using digital twins offer a potential solution. We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic ECG images with realistic artifacts from time-series data, and showcase its application in developing algorithms for ECG image digitization. Synthetic data is generated by producing distortionless ECG images on a standard ECG paper background. Subsequently, various distortions, including handwritten text artifacts, wrinkles, creases, and perspective transformations, are applied to these ECG images. The artifacts and text are synthetically generated, excluding personally identifiable information. The toolbox is used for data augmentation in the 2024 PhysioNet Challenge on Digitization and Classification of ECG Images. As a case study, we employed ECG-Image-Kit to create an ECG image dataset of 21,801 records from the PhysioNet QT database [1, 2]. A denoising convolutional neural network (DnCNN)-based model was developed and trained on this synthetic dataset and used to convert the synthetically ge

关键词： Electrocardiograms

3D Direction of Arrival Estimation: An Innovative Deep Neural Network Approach

学校读者我要写书评

暂无评论

3D Direction of Arrival Estimation: An Innovative Deep Neura...

International Conference on Modern Circuits and Systems Technologies (MOCAST)

作者： Constantinos M. Mylonakis Pantelis Velanas Pavlos I. Lazaridis Panagiotis Sarigiannidis Sotirios K. Goudos Zaharias D. Zaharis Electrical & Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Acceligence Ltd Nicosia Cyprus School of Computing and Engineering University of Huddersfield Huddersfield U.K Informatics & Telecommunications Engineering University of Western Macedonia Kozani Greece ELEDIA@AUTH School of Physics Aristotle University of Thessaloniki Thessaloniki Greece

ISBN: (数字)9798350385427

ISBN: (纸本)9798350385434

The recent integration of neural networks into the domain of direction of arrival estimation marks a promising fron-tier in the landscape of next-generation wireless communications. Our paper meticulously delves into the architecture of the proposed deep convolutional neural network (DCNN), presenting a novel framework designed to streamline the classification process within the output layer. Operating on correlation matrices created by signals received by a 4 × 4 planar antenna array, our DCNN predicts angles of arrival in 3D space. We assess the model's performance in scenarios involving the simultaneous reception of signals, employing the mean absolute error as a metric to gauge prediction errors in the angle domain. The simulation results affirm the superior performance of the proposed deep learning-based scheme. The model's robustness is rigorously examined across various validation cases, providing conclusive evidence of its potential in real-world applications.

关键词： Wireless communication Solid modeling Direction-of-arrival estimation Three-dimensional displays Transmission line matrix methods Array signal processing Simulation

Advanced Clustering Techniques for Speech Signal Enhancement: A Review and Metanalysis of Fuzzy C-Means, K-Means, and Kernel Fuzzy C-Means Methods

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Abdullah, Abdulhady Abas Ahmed, Aram Mahmood Rashid, Tarik Veisi, Hadi Rassul, Yassin Hussein Hassan, Bryar Fattah, Polla Ali, Sabat Abdulhameed Shamsaldin, Ahmed S. Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq School of Intelligent Systems College of Interdisciplinary Science and Technologies University of Tehran Iran Computer Science and Engineering Department University of Kurdistan Hewler KR Erbil Iraq Software and Informatics Engineering College of Engineering Salahaddin University-Erbil Iraq

Speech signal processing is a cornerstone of modern communication technologies, tasked with improving the clarity and comprehensibility of audio data in noisy environments. The primary challenge in this field is the effective separation and recognition of speech from background noise, crucial for applications ranging from voice-activated assistants to automated transcription services. The quality of speech recognition directly impacts user experience and accessibility in technology-driven communication. This review paper explores advanced clustering techniques, particularly focusing on the Kernel Fuzzy C-Means (KFCM) method, to address these challenges. Our findings indicate that KFCM, compared to traditional methods like K-Means (KM) and Fuzzy C-Means (FCM), provides superior performance in handling nonlinear and non-stationary noise conditions in speech signals. The most notable outcome of this review is the adaptability of KFCM to various noisy environments, making it a robust choice for speech enhancement applications. Additionally, the paper identifies gaps in current methodologies, such as the need for more dynamic clustering algorithms that can adapt in real time to changing noise conditions without compromising speech recognition quality. Key contributions include a detailed comparative analysis of current clustering algorithms and suggestions for further integrating hybrid models that combine KFCM with neural networks to enhance speech recognition accuracy. Through this review, we advocate for a shift towards more sophisticated, adaptive clustering techniques that can significantly improve speech enhancement and pave the way for more resilient speech processing systems. © 2024, CC BY.

关键词： Noise abatement