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

Missing Data Imputation: A Comprehensive Review

引用

Journal of computer and Communications 2024年第11期12卷 53-75页

作者： Majed Alwateer El-Sayed Atlam Mahmoud Mohammed Abd El-Raouf Osama A. Ghoneim Ibrahim Gad Department of Computer Science College of Computer Science and Engineering Taibah University Yanbu Saudi Arabia Computer Science Department Faculty of Science Tanta University Tanta Egypt Basic and Applied Science Institute College of Engineering and Technology Arab Academy for Science and Technology (AAST) Alexandria Egypt Department of Computer Science Faculty of Computers and informatics Tanta University Tanta Egypt

Missing data presents a significant challenge in statistical analysis and machine learning, often resulting in biased outcomes and diminished efficiency. This comprehensive review investigates various imputation techniques, categorizing them into three primary approaches: deterministic methods, probabilistic models, and machine learning algorithms. Traditional techniques, including mean or mode imputation, regression imputation, and last observation carried forward, are evaluated alongside more contemporary methods such as multiple imputation, expectation-maximization, and deep learning strategies. The strengths and limitations of each approach are outlined. Key considerations for selecting appropriate methods, based on data characteristics and research objectives, are discussed. The importance of evaluating imputation’s impact on subsequent analyses is emphasized. This synthesis of recent advancements and best practices provides researchers with a robust framework for effectively handling missing data, thereby improving the reliability of empirical findings across diverse disciplines.

关键词： Missing Data Machine Learning Prediction Deep Learning Imputation

来源：评论

学校读者我要写书评

暂无评论

Understanding and Addressing Data Security and Privacy Concerns in Modern Cloud Computing Systems

Understanding and Addressing Data Security and Privacy Conce...

引用

2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

作者： Ateeq, Ali Alaghbari, Mohammed Abdulrazzaq Ateeq, Ranyia Ali Ahmed, Ammar Yousif College of Administrative and Financial Science Gulf University Administrative Science Department Sanad26489 Bahrain College of Administrative Sciences Applied Science University Business Administration Department Bahrain College of Information Technology University of Bahrain Bahrain College of Arts and Science Applied Science University Computer Scince Department Bahrain

ISBN: (纸本)9798350372229

This research examines the influence of the use of cloud computing on data management, with a specific emphasis on its ability to provide scalable solutions for storage and processing. The methodological approach involves doing a thorough assessment of existing literature and analyzing secondary data sources in order to provide a full overview of the topic matter. A systematic literature review was used to collect pertinent research results and data pertaining to the impact of cloud computing on data management. This approach facilitates the amalgamation of preexisting information and perspectives from many sources. The observations indicate that cloud computing has revolutionized data management by providing scalable and adaptable choices for both storage and processing. It has empowered enterprises to effectively manage substantial amounts of data and use computational resources as needed. Nevertheless, the ease and accessibility of cloud computing can give rise to difficulties in the confidentiality and protection of data. To address these difficulties, it is essential to implement encryption, and access control, and comply with data protection rules. The research concludes that cloud computing has fundamentally transformed data management, providing firms with robust tools to efficiently handle data. Nevertheless, it entails the need to employ resilient data privacy and security safeguards. Organizations should give priority to implementing measures such as encryption and access control in order to safeguard sensitive data. Adhering to legislation such as GDPR is crucial for maintaining trust and complying with legal obligations. © 2024 IEEE.

关键词： access control Cloud computing compliance data management data privacy encryption GDPR processing scalability security storage

来源：评论

学校读者我要写书评

暂无评论

DSTNet: Distinguishing Source and Target Areas for Image Copy-Move Forgery Detection 27th

DSTNet: Distinguishing Source and Target Areas for Image Cop...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhao, Kaiqi Yuan, Xiaochen Huang, Guoheng Liu, Kun School of Cyberspace Security Shandong University of Political Science and Law Jinan China Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Technology Guangdong University of Technology Guangzhou China School of Information Science and Engineering University of Jinan Jinan China

ISBN: (纸本)9783031783111

In copy-move forgery detection, most relevant studies concern locating the copy-move areas without the distinction of source and target regions. This paper proposes an end-to-end network, DSTNet, to identify the source and target based on consistency detection between the copy-move region and the non-copy-move region. The DSTNet is composed of two stages, the Pre-processing stage and the Discrimination stage. Pre-processing Stage extracts internal information of copy-move and non-copy-move areas and conducts a series of operations to meet the requirements of network input. Discrimination stage allows multiple patches for input and classifies the input patches. Specifically, the Pre-processing stage, contains the Copy-move Patches Selection (CM Patches Selection) and Genuine Patches Selection, can select pairs of copy-move and none copy-move patches. We train the proposed DSTNet on two large synthetic datasets and use the public datasets CASIA and Comofod for evaluation. The experiment shows that our method achieves excellent results. Particularly, we achieve a 5.4% higher F1 based on ground-truth of copy-move mask (GT-CM) on CASIA dataset. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Prediction of diabetes disease using Adaboost, Random Forest Algorithm and Logistic Regression 4

Prediction of diabetes disease using Adaboost, Random Forest...

引用

4th International Conference on Advancement in Electronics and Communication Engineering, AECE 2024

作者： Rastogi, Stuti Deol, Simmi Gera, Anju Singh, Pawan Kumar Sharma, Rupa Rani Singh, Kuldeep G. L. Bajaj Institute of Technology and Management Applied Computational Science and Engineering Greater Noida India G. L. Bajaj Institute of Technology and Management Computer Science and Engineering Greater Noida India G. L. Bajaj Institute of Technology and Management Applied Science Greater Noida India

ISBN: (纸本)9798350364729

Diabetes is sometimes called the silent killer as it takes long for the symptoms to appear. Diabetes is a common disease that can be prevented or postponed with early detection based on various features. In this paper, collect dataset from UCI repository having 17 attributes and 520 records of different patients. In addition to that, these attributes are pass to machine learning techniques like Random forest, Adaboost and Logistic regression, which is used to predict diabetes disease. The performance is measured in terms precision, recall and F-measures. It has been observed, during training phase random forest achieved 100% and testing phase 99.36% accuracy. The attained results seem to be more accurate and precise, as compared to existing techniques. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Exploring the Role of Internet of Things in Wireless Sensor Networks for Industry 4.0 Applications 1

Exploring the Role of Internet of Things in Wireless Sensor ...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Palarimath, Suresh Maran, Pyingkodi N.r, Wilfred Blessing Sujatha, T. Renuga, S. R.s, Chithra College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman Kongu Engineering College Department of Computer Application Erode India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Sri Krishna College of Engineering and Technology Department of Artificial Intelligence and Data Science Coimbatore India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India Ponjesly College of Engineering Department of Computer Science and Engineering Kanyakumari India

ISBN: (纸本)9798350365016

Recent developments in computer networking have made it possible to access information from a faraway location via either wireless or wired networks. The recent advancements in wireless infrastructure are directly responsible for the advent of wireless sensor networks, often known as WSNs. These networks make it easier to keep track of environmental happenings and activities, as well as document them and manage them. In WSNs, data relaying is accomplished through the use of a variety of routing strategies. Industry 4.0, also known as the fourth industrial revolution, is characterized by the incorporation of highly developed physical automation systems. These systems are made up of several pieces of machinery and gadgets that are linked together by sensors and are operated by software. The goal of the fourth industrial revolution is to improve the effectiveness and dependability of business processes. The Internet of Things (IoT) can be leveraged in manufacturing, which gives a means of linking engines, power grids, and sensors to the cloud in an industrial context. This is accomplished through the use of Industrial IoT. The purpose of this paper is to gain an understanding of how the Internet of Things functions in wireless sensor networks and its possible applications in a variety of settings. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Innovations in Machine Learning for Drug Discovery and Pharmaceutical Innovations 2

Algorithmic Innovations in Machine Learning for Drug Discove...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Sangeetha, M. Harin Fernandez, F. Mary Ganesh Ramachandran, A. Saravanan, S.K. Bhanumathi, M. University of Technology and Applied Sciences Department of Computer Engineering Nizwa Oman Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science Chennai India Saveetha School of Engineering Simats BigData and Network Security Department of Computers Science and Engineering Tamil Nadu Chennai India Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350384277

Algorithmic advancements in machine learning have transformed drug discovery and pharmaceutical innovation. This study examines how machine learning might speed medication development and pharmaceutical innovation. Data from genomes, chemistry, and clinical trials is collected to start the research. Careful data cleansing, normalization, and feature engineering prepare the data for model building. Random Forest, SVM, NN, Decision Tree, and Logistic Regression are tested for prediction. ROC AUC results show that Random Forest is the most accurate model at 86%. Ensemble approaches have drug discovery potential. Beyond accuracy, models are assessed for precision, false positive, and false negative rates. Drug discovery relies on precision to measure positive predictions. The Random Forest model makes the most accurate positive predictions at 0.87. However, false positives and negatives also matter in drug discovery. The Decision Tree model contains the falsest positives (35), underlining the need to reduce them to save resources. The Neural Network approach reduces false negatives to 12, ensuring good medication candidates are not overlooked. The results show that different machine learning models have trade-offs, underscoring the necessity for a personalized strategy depending on objectives and restrictions. Algorithmic breakthroughs in pharmaceutical innovation reduce medication development time by 40% and cost by 25%, according to the study. © 2024 IEEE.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Ultra-Low Power Designs and Strategies for Next-Generation Sensor Networks 7

Ultra-Low Power Designs and Strategies for Next-Generation S...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Gupta, Priyanka Revathi, V. Hameed, Ali Abduhussien Gupta, Manish Yadav, Suman Avdhesh Rao, Bolleddu Devananda Institute of Aeronautical Engineering Department of Computer Science and Engineering Telangana Hyderabad India New Horizon College of Engineering Department of Applied Sciences Bangalore India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq Lovely Professional University Phagwara India Iilm University Department of Computer Science & Engineering Uttar Pradesh Greater Noida India Mlr Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350350067

Energy-efficient design and operation are essential for next-generation sensor networks to persist and require less maintenance. This paper describes a novel energy-efficient sensor network. It uses superior data routing and aggregation. Three novel algorithms-EARA, DFAA, and Adaptive Data Sampling-make this strategy practicable. EARA sends data with little energy, DFAA collects all data to eliminate duplicates, and ADSA adjusts sample rates based on relevance and variability. Each piece of software sends, manages, and changes sample rates with minimal energy. This innovative energy-saving strategy is tested against static-duty cycling, non-adaptive data aggregation, fixed-rate data sampling, high-energy data transmission, centralized data routing, and unoptimized sensor node location. The recommended solution outperforms network lifetime, energy usage, data accuracy, latency, scalability, and dependability. Energy savings, ease of use, affordability, adaptability, long-lastingness, and network lifespan are usually better with the proposed response. Scatter plots illustrate how much better the proposed method saves energy and works properly. The EARA, DFAA, and ADSA algorithm-based techniques offer great potential for energy-efficient sensor networks. This strategy stabilizes and prolongs sensor network configurations by optimizing data pathways, aggregating data, and adaptively sampling data. The results show that it works, making it a novel strategy for the future generation of sensor networks that demand higher performance and less energy. © 2024 IEEE.

关键词： Adaptive Data Sampling Data Aggregation Data Management Energy Consumption Energy Efficiency Energy-Aware Routing Network Lifetime Performance Evaluation Sensor Networks Sustainability

来源：评论

学校读者我要写书评

暂无评论

Improving OTP Authentication with PQC Algorithms 14

Improving OTP Authentication with PQC Algorithms

引用

14th Global Information Infrastructure and Networking Symposium, GIIS 2024

作者： Khorkheli, L. Bourne, D. Chakravarty, V. Abraham, S. Satrya, Gandeva Bayu Mnaouer, Adel Ben School of Engineering Applied Science and Technology Canadian University Dubai Dubai United Arab Emirates College of Computer and Information Systems Prince Sultan University Riyadh Saudi Arabia

ISBN: (纸本)9798350384789

Over the past few years, two-factor authentication (2FA) has emerged as a reliable defense against various cyber-attacks, such as Man in the Middle (MITM) and cookie theft. By combining passphrase and one-time password (OTP) authentication, it has successfully preserved the privacy of users across multiple applications. However, recent advancements in quantum computing have posed a threat to the security of credentials. Quantum computers now possess the capability to penetrate standard encryption algorithms. To address this concern, this research aims to implement new post-quantum algorithms for encryption and secure transference of authentication credentials. Specifically, this research will explore NTRU, CRYSTALS-Dilithium, SPHINCS+, and FALCON while evaluating their performance benchmarks against each other within an OTP authentication system. The goal is to determine which algorithm best suits the scenario with enhanced resistance against quantum-related threats. © 2024 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Geometric behavior of the generalized Hadid-Luchko convolution operator in the open unit ball

Geometric behavior of the generalized Hadid-Luchko convoluti...

引用

2023 International Conference on Fractional Differentiation and Its Applications, ICFDA 2023

作者： Hadid, Samir B. Ibrahim, Rabha W. Obaiys, Suzan J. Nadia M. G, Al-Saidi Ajman University Department of Mathematics and Sciences College of Humanities and Sciences Ajman United Arab Emirates Ajman United Arab Emirates Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon University of Malaya Faculty of Computer Science and Information Technology Department of Computer System & Technology Kuala Lumpur Malaysia University of Technology Department of Applied Sciences Iraq

ISBN: (纸本)9798350321685

In this effort, by consuming the k-symbol calculus, we generalize the Hdid-Luchko function (the Mittag-Leffler function of several variables). Some inequalities are established containing the normalized type of this function. In addition, we illustrate a list of conditions on the function to recognize some special geometric properties in a unit ball. Our theory is based on the differential subordination of several variables. © 2023 IEEE.

关键词：

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：