检索结果-内蒙古大学图书馆

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Abedal-Kareem Al-Banna Mohammad Arafah Mohammad Al-habahbeh Mohammed Abu-Arqoub Mohammad AlShaikh-Hasan Department of AI and Data Science University of Petra Department of Security University of Petra Department of IT General Budget Jordan Department of Computer Science University of Petra Department of Computer Science Brunel University London

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

This paper introduces ClearFlow, an AI-driven text generation tool designed specifically for People Who Stutter (PWS) leveraging Retrieval Augmented Generation (RAG) technology to enhance communication fluency. The tool combines pre-trained models to generate real-time stutter-friendly text alternatives based on a private knowledge base. ClearFlow's architecture integrates ada-2 for text embedding and GPT-4 as the Large Language Model (LLM), employing a refined retrieval mechanism that uses cosine similarity to identify and suggest alternative document chunks that minimize stuttering events. The tool was evaluated using the Stuttering Severity Instrument 4 (SSI-4), a standardized assessment tool for mea-suring stuttering severity. The framework's effectiveness was tested through a comprehensive study involving six subjects, comparing their speech text fluency before and after using ClearFlow. Our implementation, built on Django 5.1 and utilizing the LangChain framework, demonstrates significant potential in reducing stuttering events while maintaining the semantic integrity of the intended communication. Results indicate that ClearFlow successfully assists PWS in generating alternative speech patterns that reduce core stuttering behaviors, such as blocks, repetitions, and prolongations, while preserving the intended message's meaning.

关键词： Large language models Instruments Retrieval augmented generation Semantics Knowledge based systems Medical treatment Machine learning Assistive technologies Vectors Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Towards Fine-grained Renal Vasculature Segmentation: Full-Scale Hierarchical Learning with FH-Seg

Towards Fine-grained Renal Vasculature Segmentation: Full-Sc...

引用

Medical Imaging 2025: Digital and Computational Pathology

作者： Long, Yitian Wu, Zhongze Su, Xiu Yu, Lining Deng, Ruining Yang, Haichun Huo, Yuankai Data Science Institute Vanderbilt University NashvilleTN United States Big Data Institute Central South University Hunan Changsha China Department of Computer Science Vanderbilt University NashvilleTN United States Department of Pathology Microbiology and Immunology Vanderbilt University Medical Center NashvilleTN United States

ISBN: (纸本)9781510686045

Accurate fine-grained segmentation of the renal vasculature is critical for nephrological analysis, yet it faces challenges due to diverse and insufficiently annotated images. Existing methods struggle to accurately segment intricate regions of the renal vasculature, such as the inner and outer walls, arteries and lesions. In this paper, we introduce FH-Seg, a Full-scale Hierarchical Learning Framework designed for comprehensive segmentation of the renal vasculature. Specifically, FH-Seg employs full-scale skip connections that merge detailed anatomical information with contextual semantics across scales, effectively bridging the gap between structural and pathological contexts. Additionally, we implement a learnable hierarchical soft attention gates to adaptively reduce interference from non-core information, enhancing the focus on critical vascular features. To advance research on renal pathology segmentation, we also developed a Large Renal Vasculature (LRV) dataset, which contains 16,212 fine-grained annotated images of 5,600 renal arteries. Extensive experiments on the LRV dataset demonstrate FH-Seg's superior accuracies (71.23% Dice, 73.06% F1), outperforming Omni-Seg by 2.67 and 2.13 percentage points respectively. Code is available at: https://***/hrlblab/FH-seg. © 2025 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Self SOC Estimation for Second-Life Lithium-Ion Batteries

引用

IEEE Access 2025年 13卷 75033-75042页

作者： Gotz, Joelton Deonei Viana, Emilson Ribeiro Galvão, José Rodolfo Corrêa, Fernanda Cristina Borsato, Milton Badin, Alceu André Paraná Curitiba81280-340 Brazil Department of Computer Science Paraná Curitiba80215-901 Brazil Department of Physics Paraná Curitiba81280-340 Brazil Paraná Ponta Grossa80230-901 Brazil Postgraduate Program in Mechanical and Materials Engineering Paraná Curitiba81280-340 Brazil

Lithium-ion batteries (LIB) are the mainstream technology for energy storage in several industrial segments, such as mobility and stationary systems for solar, wind, or other alternative energy source. This technology has a long lifetime, low self-discharge, high capacity and density, and can store energy longer. Despite that, LIB is suitable to supply power for electric mobility if its state of health (SOH) is higher than 80%. Then, an alternative for batteries with SOH below that is recycling or second-life batteries (SLB). The first is expensive and complex;only some companies retain the technology. Still, the SLB can be an excellent solution to maintaining LIBs in operation for slow vehicles or stationary systems. However, SLB requires intelligent battery management systems (BMS) because the packs are composed of cells with different characteristics, which makes the operation more difficult. This work presents a system consisting of two Machine Learning (ML) layers to automatically estimate the state of charge (SOC) of SLB independent of the battery’s capacity or age. In the first phase, a Random Forest (RF) model was built and trained to discover the curve capacity of different SLB characteristics and capacities. After the capacity curve selection, in the second phase, a new RF model was built and trained for each capacity curve to make SOC inferences of the batteries. The discharge data curve of one hundred batteries was used for the development, whereas eighteen were used for the training and eighty-two for tests. The results indicated a root square mean error (RSME) below 45 mAh for the capacity estimation (phase 1), and an RSME below 0.87% was found in the second phase for the SOC estimation. Finally, the capacity and SOC models have been inserted in a Raspberry system to measure the main parameters of SLB (voltage and current) and make inferences in real time independent of the cell’s age. The results showed an RSME below 100 mAh for the first layer and be

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Air Pollutant Prediction Using Shallow Architecture Machine Learning Algorithms 8th

Air Pollutant Prediction Using Shallow Architecture Machine ...

引用

8th World Conference on Smart Trends in Systems Security and Sustainability, WorldS4 2024

作者： Olaifa, Moses Malele, Vusumuzi Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria South Africa Unit of Data Science and Computing Vaal Campus North-West University Vanderbijlpark South Africa

ISBN: (纸本)9789819786947

Over the past few decades, mortality rates associated with air quality pollution have risen in numerous countries around the globe. This pollution stems from different factors such as meteorological conditions, human activities from urban industrialization, vehicular emission, and so on. Air pollution constituents such as NO2, CO, SO, and coarse and fine particulate matter for different locations have been analyzed to learn both correlation and inter-dependency for long and short terms. However, many of these studies overlook datasets collected using low-cost tools and equipment. Most of the time, datasets of this nature are marred with inconsistencies and gaps at irregular intervals. This may render the air pollutant data unsuitable. In order to test the suitability of machine learning algorithms on such dataset, this study conducts a time-series forecast analysis using the prophet algorithm. Two additional models including linear regressor and random forest regressor are trained and tested on the same dataset and a comparative analysis of the three models is performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Review on the Role of Blockchain Technology for Decentralized Identity Management: A Future Without Passwords 4

A Review on the Role of Blockchain Technology for Decentrali...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Raut, Rohini Gourshettiwar, Palash Thakre, Gayatri Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Data Science Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Advanced identity mechanisms are essential for secure client-identifiable proof in the unambiguously computerized world. Because the board frameworks rely on aggregated databases, fraud, data breaches, and unauthorized access are significant security risks. By providing a decentralized, immutable structure, blockchain technology advances security and protection. Through Self-Sovereign Identity, blockchain gives people authority over their own data. While also improving confirmation and check mechanisms. The potential of blockchain-based Identity, this article examines the board frameworks, focusing on five essential components: authentication, privacy, trust, integrity, and simplicity. It examines how interoperability, flexibility, and collaboration with outdated frameworks prevent decentralized IDMS being more widely used. The study also covers customer satisfaction, legal concerns, and potential future developments, such as Web 3.0, security enhancements, and integration with decentralized money. By addressing these problems and looking into new possibilities, blockchain-based IDMS may be able to reform advanced identity across the entire board. © 2025 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Improving learning material repositories using student profiles

引用

Soft Computing 2025年第5期29卷 2417-2431页

作者： Silva Bravo, Natalie Ferraz Martins, André Ferreira de Souza Fonseca Rodrigues, Thales Brito Machado, Marcelo Bernardino, Heder Soares Vieira, Alex Borges Barbosa, Hélio José Corrêa de Souza, Jairo Francisco LApIC Research Group Federal University of Juiz de Fora Minas Gerais Juiz de Fora36036-900 Brazil Postgraduate Program in Computer Science Federal University of Juiz de Fora Minas Gerais Juiz de Fora36036-900 Brazil Postgraduate Program in Informatics Federal University of the State of Rio de Janeiro Rio de Janeiro22290-255 Brazil Department of Computer Science Federal University of Juiz de Fora Minas Gerais Juiz de Fora36036-900 Brazil

aaaa The adaptive learning community seeks to provide solutions to customize and enhance students’ learning experiences when accessing web-based learning systems. The adaptation usually occurs from the use of learning materials and user information data, which turns the adaptation process highly dependent on the quality of the repositories. Then, the best adaptation a system may offer might still not satisfy the users’ needs. In this work, we propose an approach to assist teachers and stakeholders in understanding repositories’ characteristics and their gaps according to students’ needs. Our approach, first, selects the best sequence of learning materials for each student, which is a well-known problem called Adaptive Curriculum Sequencing. Then, based on the selected sequences, we use optimization approaches, such as GRASP and Simulated Annealing, to generate new learning materials possibilities that can improve ACS recommendations. This way, our new approach assists teachers in assembling their learning materials. We have evaluated our approach by comparing it to a traditional approach using a real dataset, and the results are promising. In fact, it is possible to design customized materials using a combination of GRASP and brute force algorithms on the characteristics of the learning materials. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Instruction-based Learning with Bidirectional LSTM for Autonomous Vehicle Pedestrian Detection

Integrating Instruction-based Learning with Bidirectional LS...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Shoba, B. Raghunathan, T. Peter, S.Sam Karthick, K. Akshya, J. Sundarrajan, M. Choudhry, Mani Deepak Psn College of Engineering and Technology Department of Electronics and Communication Engineering Tirunelveli India Dr.NG.p.Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Sri Krishna College of Technology Department of Computer Science and Engineering Coimbatore India Sona College of Technology Department of Information Technology Salem India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Networking and Communications Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

Pedestrian detection is a crucial aspect of autonomous vehicle (A V) safety, as it enables accurate identification and tracking of individuals in an A V environment. Effective pedestrian detection supports essential A V functions like braking, steering, and speed control to prevent accidents in urban settings. Traditional computer vision methods, such as Support Vector Machines and Random Forests, rely on pre-designed features like the Histogram of Oriented Gradients. While the existing techniques offer some performance, it face significant challenges in dynamic environments, especially under varying lighting conditions, occlusions, and diverse pedestrian poses. Traditional models also require extensive manual feature engineering and tuning, which limits scalability and adaptability. Recent advances in deep learning, particularly with Convolutional Neural Networks (CNNs), have allowed for automatic feature learning, yielding practical improvements over classical methods. However, CNNs can struggle in low light and when facing adversarial attacks, as they mainly capture spatial features. To address these limitations, this research proposes a new methodology combining CNNs for spatial feature extraction with Bidirectional Long Short-Term Memory (BiLSTM) networks to capture temporal dependencies. This hybrid approach enhances detection capabilities by learning both static and dynamic patterns. Our proposed CNN-BiLSTM model achieves a 92 % detection accuracy and an F1 score of 88.5% across diverse conditions, outperforming existing models by up to 15%. By integrating temporal features, the model reduces missed detections and false positives by up to 20%, providing a more reliable and adaptable solution for pedestrian detection in autonomous vehicles. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed Channel Estimation and Optimization for 6D Movable Antenna: Unveiling Directional Sparsity

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 349-365页

作者： Shao, Xiaodan Zhang, Rui Jiang, Qijun Park, Jihong Quek, Tony Q. S. Schober, Robert Friedrich-Alexander-University Erlangen-Nurnberg Institute for Digital Communications Erlangen91054 Germany Shenzhen Research Institute of Big Data The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore The Chinese University of HongKong School of Science and Engineering Shenzhen518172 China Singapore University of Technology and Design 487372 Singapore

Six-dimensional movable antenna (6DMA) is an innovative and transformative technology to improve wireless network capacity by adjusting the 3D positions and rotations of antennas/antenna surfaces based on the channel spatial distribution. To achieve optimal antenna positions and rotations, acquiring statistical channel state information (CSI) is essential for 6DMA systems. However, existing works assume that a central processing unit (CPU) jointly processes the signals of all 6DMA surfaces. This incurs prohibitively high processing cost and latency for channel estimation due to the vast numbers of 6DMA candidate positions/rotations and antenna elements. Therefore, we propose a distributed 6DMA processing architecture to reduce the processing complexity of the CPU by equipping each 6DMA surface with a local processing unit (LPU). Furthermore, we unveil for the first time the directional sparsity property of the 6DMA channels with respect to distributed users, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs. Based on this property, we propose a practical three-stage protocol for the 6DMA system and corresponding algorithms to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization based on statistical CSI, and instantaneous CSI estimation for user data transmission with optimized 6DMA positions/rotations. Simulation results show that the proposed channel estimation algorithms achieve higher accuracy than benchmark schemes, while requiring lower pilot overhead. Moreover, the proposed 6DMA system with statistical CSI-based position/rotation optimization achieves a higher ergodic sum rate than fixed-position and fluid antenna systems, even if the latter have perfect instantaneous CSI. © 2025 IEEE.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Techniques for Lung Sound Classification: Binary, Multi-Class, and Ensemble Approach

Advanced Deep Learning Techniques for Lung Sound Classificat...

引用

Software Engineering and computer science (CSECS), International Conference on

作者： Gayan Perera Heshan Chandeepa Pathmakumara Department of Computer and Data Science NSBM Green University Homagama Sri Lanka

ISBN: (数字)9798331522216

ISBN: (纸本)9798331522223

Detecting respiratory diseases, particularly lung disorders is crucial due to their global prevalence. Auscultation by experts has been the standard method for detecting lung diseases. However, the efficiency of diagnosis can be greatly increased by automating this procedure. Using Convolutional Neural Networks (CNN) for binary classification and a CNN, CNN-LSTM hybrid model for multi class classification, this study uses deep learning approaches to automate lung sound classification. To increase classification accuracy, the study extracts important elements from lung sounds such as chromograms, Mel spectrograms and Mel Frequency Cepstral Coefficients (MFCCs). Ensemble learning which combines CNN and CNN-LSTM for multi-class classification, substantially improves the model. With an accuracy of 86.11% the suggested ensemble model surpasses current models in the field. The accuracy of binary classification is 88.38%. This study demonstrates the advantages of combining multiple architectures to improve classification performance and shows how deep learning models can be used to effectively classify lung sounds. The results have significant implications for the early detection of lung diseases.

关键词： Deep learning Accuracy Lungs Pulmonary diseases Stacking Convolutional neural networks Ensemble learning Mel frequency cepstral coefficient Spectrogram Standards

来源：评论

学校读者我要写书评

暂无评论

Assessing the Alignment of FOL Closeness Metrics with Human Judgement

arXiv

引用

arXiv 2025年

作者： Thatikonda, Ramya Keerthy Buntine, Wray Shareghi, Ehsan Department of Data Science & AI Monash University Australia College of Engineering and Computer Science VinUniversity Viet Nam

The recent successful paradigm of solving logical reasoning problems with tool-augmented large language models (LLMs) leverages translation of natural language statements into First-Order Logic (FOL) and external theorem provers. However, the correctness of FOL statements, comprising operators and text predicates, often goes unverified due to the lack of a reliable evaluation metric for comparing generated and ground-truth FOLs. In this paper, we present a comprehensive study of sensitivity of existing metrics and their alignment with human judgement on FOL evaluation. Using ground-truth FOLs, we carefully designed various perturbations on the ground-truth to assess metric sensitivity. We sample FOL translation candidates for natural language statements and measure the ranking alignment between automatic metrics and human annotators. Our empirical findings highlight oversensitivity in the n-gram metric BLEU for text perturbations, the semantic graph metric Smatch++ for structural perturbations, and FOL metric for operator perturbation. We also observe a closer alignment between BertScore and human judgement. Additionally, we show that combining metrics enhances both alignment and sensitivity compared to using individual metrics. © 2025, CC BY.

关键词： Semantics

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：