检索结果-内蒙古大学图书馆

Audio-Text Multimodal Speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

引用

computers, Materials & Continua 2024年第3期78卷 3215-3245页

作者： Shuting Ge Jin Ren Yihua Shi Yujun Zhang Shunzhi Yang Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic UniversityShenzhen518055China Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Industrial Training Centre Shenzhen Polytechnic UniversityShenzhen518055China

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling pa

关键词： Speech-text multimodal automatic speech recognition semantic alignment air traffic control communications dual-tower architecture

来源：评论

学校读者我要写书评

暂无评论

Hybrid Shunted Transformer embedding UNet for remote sensing image semantic segmentation

引用

Neural Computing and Applications 2024年第25期36卷 15705-15720页

作者： Zhou, Huacong Xiao, Xiangling Li, Huihui Liu, Xiaoyong Liang, Peng School of Computer Science Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangdong Polytechnic Normal University Guangdong Guangzhou510665 China School of Data Science and Engineering Guangdong Polytechnic Normal University Guangdong Guangzhou510630 China Academy of Heyuan Guangdong Polytechnic Normal University Guangdong Heyuan517099 China The Cyberspace Institute of Advanced Technology Guangzhou University Guangdong Guangzhou510006 China

With the development of deep learning, Remote Sensing Image (RSI) semantic segmentation has produced significant advances. However, due to the sparse distribution of the objects and the high similarity between classes, the task of semantic segmentation in RSI is still extremely challenging. In this paper, we propose a novel semantic segmentation framework for RSI called HST-UNet that can overcome the shortcomings of the existing models and extract and recover the global and local features of RSI, which is a hybrid semantic segmentation model with Shunted Transformer as encoder and Multi-Scale Convolutional Attention Network (MSCAN) as decoder. Then, to better fuse the information from the Encoder and the Decoder and alleviate the ambiguity, we design a Learnable Weighted Fusion (LWF) module to effectively connect to the decoder features. Extensive experiments demonstrate that the proposed HST-UNet outperforms the state-of-the-art methods, achieving F1 score/MIoU accuracy of 71.44%/83.00% on the ISPRS Vaihingen dataset and 77.36%/87.09% on ISPRS Potsdam dataset. The code will be available at https://***/HC-Zhou/HST-UNet. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

PFAS Incineration: Known Unknowns, Reaction Simulation, and ML to Predict Product Properties

PFAS Incineration: Known Unknowns, Reaction Simulation, and ...

引用

2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023

作者： Soiffer, Duncan Pyorre, Tuomas Kenney, David Teixeira, Andrew Worcester Polytechnic Institute Department of Computer Science and Mathematical Sciences WorcesterMA United States Worcester Polytechnic Institute Department of Robotics Engineering WorcesterMA United States Worcester Polytechnic Institute Department of Chemical Engineering WorcesterMA United States

ISBN: (纸本)9798350308600

Per- and polyfluoroalkyl substances (PFAS) are a group of chemicals used for their impressive stability, a property which has also led them to be found polluting virtually every sector of the environment-including our own bodies. Presently, our ability to destroy PFAS is limited largely to incineration, whose products and side effects are poorly understood. Research on PFAS incineration is constrained by high experimental costs and difficulty in accurately measuring reaction products. This presents an opportunity for computer simulation and machine learning to provide valuable assistance. In this study, three kinds of thermal PFAS decomposition are simulated. Further, to broaden physical understanding of PFAS incineration products, a recent in-house machine learning model for predicting the octanol-water partition coefficient (LogP) of chemicals is improved and applied to simulation results. A decrease in LogP is observed in all treatments, with the most dramatic effect (-2 average LogP) observed in oxidative pyrolysis. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Attendance Management with Deep Learning

An Efficient Attendance Management with Deep Learning

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and Communications, COSMIC 2024

作者： Shivanna Hema, H.P. Janardhana, D.R. Srinivas, P.M. Sahyadri College of Engineering and Management Department of Computer Science and Engineering Mangaluru India D S Dinakar Polytechnic College Department of Electronics and Communication Engineering Shivamogga India Nitte Meenakshi Institute of Technology Department of Computer Scince and Engineering Bengaluru India

ISBN: (纸本)9798331517892

Accurate attendance recording is critical in educational institutions to ensure students' and teachers' consistency and discipline. Traditional manual attendance systems are frequently inefficient and prone to errors, such as proxy attendance and missed entries, which may impact the accuracy of attendance records. To address these challenges, an automatic attendance system that uses camera-based facial recognition technology is proposed. The latest technology records accurate attendance by taking visuals of students as soon as the class starts and comparing them to an already-existing database. Face recognition happens through human detection. The concept used here is deep learning. For students, this automated solution streamlines attendance management by ensuring that records are accurate and up to date without the need for manual entry. The system efficiently keeps track of the presence of teachers, notifying the Head of Department (HOD) right away in the case of an excused absence, therefore preventing disruptions during scheduled lessons. This technology significantly increases the reliability and efficiency of attendance tracking by automating the process. Enhancing record accuracy and accountability leads to a more regulated and effective learning environment that benefits teachers and students alike. This technological method offers greater precision and oversight, leading to improved institutional administration and educational outcomes. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Ensemble of Handcrafted and Deep Learning Model for Histopathological Image Classification

引用

computers, Materials & Continua 2022年第11期73卷 4393-4406页

作者： Vasumathi Devi Majety N.Sharmili Chinmaya Ranjan Pattanaik ELaxmi Lydia Subhi R.M.Zeebaree Sarmad Nozad Mahmood Ali S.Abosinnee Ahmed Alkhayyat Department of Computer Science Engineering Vignan’s Nirula Institute of Technology and Science for WomenGuntur522005India Department of Computer Science Engineering Gayatri Vidya Parishad College of Engineering for WomenVisakhapatnam530048India Department of Computer Science and Engineering Ajay Binay Institute of Technology CuttackOdisha750314India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Energy Department Technical College of EngineeringDuhok Polytechnic UniversityDuhokIraq Computer Technology Engineering College of Engineering TechnologyAl-Kitab UniversityIraq Computer Technical Engineering Department College of Technical EngineeringThe Islamic UniversityNajaf54001Iraq College of Technical Engineering The Islamic UniversityNajafIraq

Histopathology is the investigation of tissues to identify the symptom of *** histopathological procedure comprises gathering samples of cells/tissues,setting them on the microscopic slides,and staining *** investigation of the histopathological image is a problematic and laborious process that necessitates the expert’s *** the same time,deep learning(DL)techniques are able to derive features,extract data,and learn advanced abstract data *** this view,this paper presents an ensemble of handcrafted with deep learning enabled histopathological image classification(EHCDL-HIC)*** proposed EHCDLHIC technique initially performs Weiner filtering based noise removal *** the images get smoothened,an ensemble of deep features and local binary pattern(LBP)features are *** the classification process,the bidirectional gated recurrent unit(BGRU)model can be *** the final stage,the bacterial foraging optimization(BFO)algorithm is utilized for optimal hyperparameter tuning process which leads to improved classification performance,shows the novelty of the *** validating the enhanced execution of the proposed EHCDL-HIC method,a set of simulations is *** experimentation outcomes highlighted the betterment of the EHCDL-HIC approach over the existing techniques with maximum accuracy of 94.78%.Therefore,the EHCDL-HIC model can be applied as an effective approach for histopathological image classification.

关键词： Histopathological image classification machine learning deep learning handcrafted features bacterial foraging optimization

来源：评论

学校读者我要写书评

暂无评论

ICON: Improving Inter-Report Consistency in Radiology Report Generation via Lesion-aware Mixup Augmentation

ICON: Improving Inter-Report Consistency in Radiology Report...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Hou, Wenjun Cheng, Yi Xu, Kaishuai Hu, Yan Li, Wenjie Liu, Jiang Department of Computing The Hong Kong Polytechnic University Hong Kong Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China

ISBN: (纸本)9798891761681

Previous research on radiology report generation has made significant progress in terms of increasing the clinical accuracy of generated *** this paper, we emphasize another crucial quality that it should possess, i.e., inter-report consistency, which refers to the capability of generating consistent reports for semantically equivalent *** quality is even of greater significance than the overall report accuracy in terms of ensuring the system's credibility, as a system prone to providing conflicting results would severely erode users' ***, existing approaches struggle to maintain inter-report consistency, exhibiting biases towards common patterns and susceptibility to lesion *** address this issue, we propose ICON, which Improves the inter-report CONsistency of radiology report *** to enhance the system's ability to capture similarities in semantically equivalent lesions, our approach first involves extracting lesions from input images and examining their ***, we introduce a lesion-aware mixup technique to ensure that the representations of the semantically equivalent lesions align with the same attributes, achieved through a linear combination during the training *** experiments on three publicly available chest X-ray datasets verify the effectiveness of our approach, both in terms of improving the consistency and accuracy of the generated reports. © 2024 Association for Computational Linguistics.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

In-memory Parallel Anisotropic Mesh Adaptation for Hypersonic Problems with Evolving Geometry

In-memory Parallel Anisotropic Mesh Adaptation for Hypersoni...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Gica, Mikiel Woodruff, Aiden Brown, Cameron S. Salazar, Giovanni Sahni, Onkar Department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute TroyNY12180 United States Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States Corvid Technologies MooresvilleNC28117 United States

ISBN: (纸本)9781624107238

In this paper, we present an automated workflow for in-memory parallel anisotropic mesh adaptation for hypersonic problems with evolving geometry. Our workflow develops and combines three simulation components to target such problems. Namely, a hypersonic flow solver;a library for geometry and mesh modification/adaptation;and an adaptation controller. Our approach is component based, in which different simulation components are combined and plugged in a flexible and modular fashion. Specifically, adaptation controller abstracts the data exchange between the geometry and mesh library and the flow solver, and defines a set of functional interfaces to carry out the necessary logic and data exchange. This paper builds on our previous studies and includes a flexible approach for evolving geometry problems to allow geometry and mesh motion to be applied in the flow solver (without any change in mesh connectivity). Updated coordinates are communicated from the flow solver to the geometry and mesh library, only when mesh modification/adaptation is triggered. A mesh size field (based on mesh metric tensors) is computed and used to drive anisotropic mesh adaptation. For demonstration of the current approach, two hypersonic flow cases with rigid body motion are considered: (i) a pitching HIFiRE-I case, and (ii) a pitching crew exploration vehicle case without and with the wake region. © 2025, American institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

STC+K: A Semi-Global Triangular and Degree Centrality Method to Identify Influential Spreaders in Complex Networks 22

STC+K: A Semi-Global Triangular and Degree Centrality Method...

引用

22nd IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2023

作者： Sadhu, Srestha Namtirtha, Amrita Malta, Mariana Curado Dutta, Animesh National Institute of Technology Durgapur Computer Science and Engineering India JIS College of Engineering Computer Science and Engineering Kalyani India Polytechnic of Porto CEOS.PP Portugal ALGORITMI Center LASI University of Minho Portugal

ISBN: (纸本)9798350309188

Influential spreaders contribute substantially to managing and optimizing any spreading process in a network. Influential spreaders are nodes that hold importance within the network. Identifying them is a challenging task. Some encysting methods for such identification include local-structure-based, global-structure-based, semi-global-structure-based, and hybrid-structure-based methods. Semi-global structure-based methods show significant potential in identifying influential nodes in different network structures. However, existing semi-global structure-based methods often identify nodes from the network's periphery, where nodes are loosely connected, and their collective influence in spreading processes is minimal. This paper presents a novel method called Semi-global triangular and degree centrality (STC+K) to overcome this limitation by considering a node's degree, the number of triangles, and the third hop of neighbourhood connectivity information. The proposed novel method outperforms the existing noteworthy indexing methods regarding ranking performance. The experimental results show better performance, as indicated by two performance metrics: recognition rate and improvement percentage. By virtue of the fact that the empirically set free parameters are absent, our method eliminates the need for time-consuming preprocessing to select optimal parameter values for ranking nodes in large networks. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

State of Health Estimation of Lithium-ion Batteries Based on Relaxation Voltage Reconstruction and AM-LSTM Method

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 7261-7273页

作者： Wei, Liangliang Xu, Hongzhang Sun, Yiwen Diao, Qi Tan, Xiaojun Fan, Yuqian Liu, Han Shenzhen Campus of Sun Yatsen University School of Intelligent Systems Engineering Shenzhen518107 China Henan Institute of Science and Technology School of Computer Science and Technology Henan Province Xinxiang453003 China Sun Yat-sen University Dongguan Institute Guangdong Province Dongguan523808 China Hong Kong Polytechnic University Department of Building and Energy Engineering Hong Kong999077 Hong Kong

It is essential to accurately estimate the state of health (SOH) for lithium-ion batteries from the perspectives of safety and reliability. However, most existing data-driven methods are based on charging or discharging data, which is relatively difficult to apply. This paper proposes a novel SOH estimation approach based on the relaxation voltage reconstruction and a long short-term memory network with an attention mechanism (AM-LSTM) method. First, based on the relaxation voltage data, a complete relaxation curve is reconstructed with a gated recurrent unit (GRU) neural network. Next, health feature (HF) extraction is carried out on the reconstructed data, and the correlation is analyzed based on Pearson correlation analysis. Then, the SOH estimation is performed based on the AM-LSTM model. Various comparative studies have been conducted to verify the effectiveness of the proposed method by comparing it with relaxation voltage reconstruction and different SOH estimation methods. The experimental results demonstrate that the proposed method can effectively reconstruct the relaxation voltage and have good accuracy in estimating the SOH with a partial relaxation voltage curve. © 2015 IEEE.

关键词： Voltage Batteries Estimation Feature extraction Long short term memory Logic gates Data models Integrated circuit modeling Data mining Transportation

来源：评论

学校读者我要写书评

暂无评论

Automated Heart Disease Diagnosis and Monitoring System Using Similarity-Navigated Graph Neural Networks with Leopard Seal Optimization in IoT Healthcare Applications 4

Automated Heart Disease Diagnosis and Monitoring System Usin...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Raja, V. Sripathi Rawat, Ruchira Pandit, Karuna Dhumpati, Raghu Vekariya, Vipul Vijitha, S. B V Raju Institute of Technology Department of Biomedical Engineering Telangana Narsapur502313 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Department of Information Science and Engineering Nitte Karkala Karnataka Udupi District India Bahrain Polytechnic Isa Town Department of Computer Science and Engineering Isa Town3339 Bahrain Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Post Limda Gujarat Waghodia391760 India Vels Institute of Science Technology and Advanced Studies Department of computer science and Engineering Pallavaram Tamil Nadu Chennai600043 India

ISBN: (纸本)9798331540364

One of the leading causes of death worldwide continues to be heart disease;therefore, early detection and precise diagnosis are essential to better patient outcomes. The conventional methods of diagnosing chemotherapy-induced nail changes involve a great deal of laboratory testing, which is more than exhaustive. In order to tackle these obstacles, this research introduces a novel methodology for the automated diagnosis and continuous tracking of heart diseases in the IoT -based health care system, integrated with deep learning algorithms. The proposed system includes several state-of-the art techniques to improve diagnostic reliability and speed. First of all, min-max normalization is used as a pre-processing technique that aims at pre-scaling the data of patients to a consistent level and, as a result, enhancing the performance of the model. The Mud Ring Algorithm is then used for feature selection, whereby the best features are chosen together with the reduction in dimensionality to decrease computational intensity, thus improving diagnostic accuracy. The core diagnostic engine is based on Similarity Navigated Graph Neural Networks (SNGNN) and has been enhanced with Leopard Seal Optimization (LSO), a new meta-method motivated by the hunting patterns of leopard seals. This combination enables the system to relate various features and give the correct prognosis for heart diseases. These techniques, applied within the IoT framework, enable real-time monitoring and diagnosis and therefore have the benefit of being a scalable solution for modern health care systems. The results show that the proposed method for providing diagnosis of heart disease is accurate, timely, and reliable and thus has the potential to revolutionize patient management in healthcare based on the IoT. © 2024 IEEE.

关键词： Chemotherapy

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：