检索结果-内蒙古大学图书馆

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

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Sign Comm: A Real-Time Indian Sign Language Recognition System Using Deep Learning for inclusive communication 2

Sign Comm: A Real-Time Indian Sign Language Recognition Syst...

引用

2nd IEEE International Conference on Emerging Research in Computational Science, ICERCS 2024

作者： Ilakkia, A. Kanchanadevi, P. Abirami, A. Rajan, R. Muthukumaran, K. Artificial Intelligence and Data Science Sri Manakula Vinayagar Engineering Puducherry India St. Joseph College of Arts and Science Department of Computer Science Cuddalore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

Individuals who are deaf often utilize sign language for communication. In Sign Language, the symbols or motions are arranged grammatically. Every motion is referred to as a sign. Indian Sign Language Recognition using Deep Learning model describes the creation of SignComm, which improves communication for those with hearing loss by translating Indian Sign Language (ISL) motions into text. To identify and interpret ISL gestures in real-time. The paper describes the difficulties the deaf community faces due to the dearth of real-time sign language interpretation services. It suggests a method that uses an Automatic Sign Detection system with deep learning models. The research describes current systems and their shortcomings, such as the lack of real-time translation tools and the difficulties the deaf community faces in obtaining sign language interpretation. Next, it presents the suggested system, SignComm, which has benefits including quick sign language decoding, a user-friendly platform that is easy to use and can foster an inclusive atmosphere in public areas and educational institutions a literature review that examines several deep learning models and their applicability to the project is included in the paper. It emphasizes the potential of the ResNet-50 architecture and the significance of a unique ISL dataset. The benefits of the suggested method, including its accuracy, inclusivity, and capacity to address communication barriers, are highlighted in the paper. Additionally, it outlines the steps involved in the implementation process, such as gathering data, training the ResNet model, and deploying in real time. A user-friendly experience for converting ISL gestures into text is the main goal of the intricate user interface design. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

QuMIN: quantum multi-modal data fusion for humor detection

引用

Multimedia Tools and Applications 2025年第18期84卷 18855-18872页

作者： Phukan, Arpan Haq Khan, Anas Anwarul Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna Bihta Bihar Patna801106 India Kalinga Institute of Industrial Technology Odisha Bhubaneswar751024 India School of AI and Data Science Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India

Humour detection has attracted considerable attention due to its significance in interpreting dialogues across text, visual, and acoustic modalities. However, effective methods to map correlations among different modalities remain an active area of research. In this study, we go beyond traditional machine learning techniques by introducing a Variational Quantum Circuit (VQC) that capitalizes on the inherent quantum properties of superposition, entanglement, and interference. Our proposed model, Quantum Multi-Modal data Fusion (QuMIN), is designed to better capture and reproduce the interaction across modalities, as well as the internal correlations within each modality. Our introduction of the novel VQC, which augments the DialogueRNN baseline with only an additional 4,809 parameters, signifies a substantial advancement in multi-modal humor detection with improvements of 12.34% in precision, 8.84% in recall and 10.57% in F1 score compared to the state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Hybrid Semantic/Bit Communication Based Networking Problem Optimization

Hybrid Semantic/Bit Communication Based Networking Problem O...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Xia, Le Sun, Yao Niyato, Dusit Zhang, Lan Zhang, Lei Imran, Muhammad Ali University of Glasgow James Watt School of Engineering Glasgow United Kingdom Nanyang Technological University College of Computing and Data Science Singapore Clemson University Department of Electrical and Computer Engineering United States

ISBN: (纸本)9798350351255

This paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a novel and practical next-generation cellular network where two modes of semantic communication (SemCom) and conventional bit communication (BitCom) coexist, namely hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of message throughput for both SemCom and BitCom links. Next, we comprehensively develop a knowledge matching-aware two-stage tandem packet queuing model and theoretically derive the average packet loss ratio and queuing latency. Combined with several practical constraints, we then formulate a joint optimization problem for UA, MS, and BA to maximize the overall message throughput of HSB-Net. Afterward, we propose an optimal resource management strategy by employing a Lagrange primal-dual method and devising a preference list-based heuristic algorithm. Finally, numerical results validate the performance superiority of our proposed strategy compared with different benchmarks. © 2024 IEEE.

关键词： Frequency allocation

来源：评论

学校读者我要写书评

暂无评论

h5bench: A unified benchmark suite for evaluating HDF5 I/O performance on pre-exascale platforms

h5bench: A unified benchmark suite for evaluating HDF5 I/O p...

引用

作者： Bez, Jean Luca Tang, Houjun Breitenfeld, Scot Zheng, Huihuo Liao, Wei-Keng Hou, Kaiyuan Huang, Zanhua Byna, Suren Scientific Data Division Lawrence Berkeley National Laboratory BerkeleyCA United States HDF Group ChampaignIL United States Data Science Group Argonne National Laboratory LemontIL United States Electrical and Computer Engineering Department Northwestern University EvanstonIL United States Computer Science Department Northwestern University EvanstonIL United States Department of Computer Science and Engineering The Ohio State University OH United States

Parallel I/O is a critical technique for moving data between compute and storage subsystems of supercomputers. With massive amounts of data produced or consumed by compute nodes, high-performant parallel I/O is essential. I/O benchmarks play an important role in this process;however, there is a scarcity of I/O benchmarks representative of current workloads on HPC systems. Toward creating representative I/O kernels from real-world applications, we have created h5bench, a set of I/O kernels that exercise hierarchical data format version 5 (HDF5) I/O on parallel file systems in numerous dimensions. Our focus on HDF5 is due to the parallel I/O library's heavy usage in various scientific applications running on supercomputing systems. The various tests benchmarked in the h5bench suite include I/O operations (read and write), data locality (arrays of basic data types and arrays of structures), array dimensionality (one-dimensional arrays, two-dimensional meshes, three-dimensional cubes), I/O modes (synchronous and asynchronous). In this paper, we present the observed performance of h5bench executed along several of these dimensions on existing supercomputers (Cori and Summit) and pre-exascale platforms (Perlmutter, Theta, and Polaris). h5bench measurements can be used to identify performance bottlenecks and their root causes and evaluate I/O optimizations. As the I/O patterns of h5bench are diverse and capture the I/O behaviors of various HPC applications, this study will be helpful to the broader supercomputing and I/O community. © 2024 Lawrence Berkeley National Laboratory, The HDF Group, UChicago Argonne, LLC and The Authors. Concurrency and Computation: Practice and Experience published by John Wiley & Sons Ltd.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Token2vec: A Joint Self-Supervised Pre-Training Framework Using Unpaired Speech and Text 48

Token2vec: A Joint Self-Supervised Pre-Training Framework Us...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yue, Xianghu Ao, Junyi Gao, Xiaoxue Li, Haizhou National University of Singapore Department of Electrical and Computer Engineering Singapore Shenzhen Research Institute of Big Data Shenzhen China The Chinese University of HongKong School of Data Science Shenzhen China

ISBN: (纸本)9781728163277

Self-supervised pre-Training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-Text joint pre-Training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-Training one step further and propose token2vec, a novel joint pre-Training framework for unpaired speech and text based on discrete representations of speech. Specifically, we introduce two modality-specific tokenizers for speech and text. Based on these tokenizers, we convert speech/text sequences into discrete speech/text token sequences consisting of similar language units, thus mitigating the domain mismatch problem and length mismatch problem, which are caused by the distinct characteristics between speech and text. Finally, we feed the discrete speech and text tokens into a modality-Agnostic Transformer encoder and pre-Train with token-level masking language modeling (tMLM). Experiments show that token2vec is significantly superior to various speech-only pre-Training baselines, with up to 17.7% relative WER reduction. Token2vec model is also validated on a non-ASR task, i.e., spoken intent classification, and shows good transferability. © 2023 IEEE.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Brain Connectivity Using Deep Learning Algorithms 1

Brain Connectivity Using Deep Learning Algorithms

引用

2023 1st DMIHER International Conference on Artificial Intelligence in Education and Industry 4.0, IDICAIEI 2023

作者： Jiet, Moses Makuei Kamble, Aahash Puri, Chetan Gajanan Verma, Prateek Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Data Science Maharashtra Wardha442001 India

ISBN: (纸本)9798350338423

The integration of deep learning into the examination of brain connectivity marks a transformative era in understanding neural networks. This article provides a concise overview of the burgeoning field of deep learning in brain connectivity analysis. It defines the concept, explores functional and structural connectivity, outlines practical applications, delves into the algorithms involved, compares traditional methods vs advanced deep learning approaches for brain connectivity and highlights its revolutionary impact in clinical practice. In deep learning, brain connectivity investigates neural links using advanced artificial intelligence. Functional connectivity, powered by deep neural networks, reveals patterns in brain activity linked to cognition, emotion, and decision-making. Structural connectivity, often utilizing graph neural networks, reconstructs intricate neural pathways. This technology shows significant progress in diagnosing conditions like Alzheimer's, schizophrenia, and autism. As it evolves, its clinical importance becomes evident, offering early disease detection, tailored treatments, and a deeper understanding of neurological disorders. Beyond clinical applications, deep learning in brain connectivity opens avenues for advancements in brain-computer interfaces, enhanced rehabilitation therapies, and precise interventions. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Agricultural Water Conservation through AI-Enhanced Solar IoT Networks 3

Agricultural Water Conservation through AI-Enhanced Solar Io...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Maniraj, S.P. Monisha, J. Amutha, R. Kavitha, R. Shriidhar, P.J. Srinivasan, C. Srm Institute of Science and Technology School of Computing Department of Data Science and Business Systems Kattankulathur Tamilnadu Chennai India Tamil Nadu Chennai India Ultra College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Madurai India Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Vinayaka Missions Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India Saveetha Universityi Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

With the increasing water shortage and climatic uncertainty, creative strategies for effective water management in agriculture are necessary. This research investigates the integration of Artificial Intelligence (AI), particularly Artificial Neural Networks (ANN), with solar-powered Internet of Things (IoT) networks to enhance water utilization in agricultural activities. The proposed system facilitates accurate irrigation scheduling using real-time data from soil moisture sensors, meteorological stations, and crop health monitoring devices. The ANN model analyses this data to predict ideal irrigation schedules and volumes, minimizing water waste while improving crop yields. The solar-powered IoT framework provides sustainability and reduces dependence on traditional energy sources. Field trials indicate that the AI-enhanced system may promote water saving by as much as 30% relative to traditional irrigation techniques. Moreover, using AI enables adaptive learning, enabling the system to enhance its irrigation tactics using historical and real-time data. This novel method conserves water resources and fosters sustainable agriculture practices, coinciding with global initiatives to address water shortages and assure food security. The findings underscore the potential of technology-based solutions to revolutionize agricultural water management for a sustainable future. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A GPS-based Face Attendance Register System using Android Applications stored in the Cloud 18

A GPS-based Face Attendance Register System using Android Ap...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Murali, N. Rajesh, R. Sridharan, S. Mariadas, A. Emmanuel Peo Murugan, S. Palani Manikandan, S. E.G.S. Pillay Engineering College Department of Department of Computer Science and Engineering Tamil Nadu Nagapattinam India E.G.S. Pillay Engineering College Department of Computer Science and Engineering Tamil Nadu Nagapattinam India University College of Engineering Department of Computer Science and Engineering Tamil Nadu Thirukkuvalai India E.G.S. Pillay Engineering College Department of Artificial Intelligence and Data Science Tamil Nadu Nagapattinam India E.G.S. Pillay Engineering College Department of Information Technology Tamil Nadu Nagapattinam India

ISBN: (纸本)9789380544519

The system is a face-based attendance system for students that make use of multi-CNN (Convolutional Neural Network) technology with GPS tracking. The device simplifies the process of taking attendance for both teachers and students while offering precise and effective attendance monitoring. The method makes use of GPS tracking to pinpoint the location of student and get confirmation of their attendance. The multi CNN technology is utilized to improve the attendance's accuracy. Tracking multiple CNN models are combined in the multi-CNN system to increase the process's accuracy for tracking attendance. Additionally, the system makes use of facial recognition technologies to make sure. The appropriate pupil is noted as present. When a student leaves a class, the department head and parents are both notified at the same time. A web-based dashboard and a mobile app for students and teachers make up the system. Every database is kept in cloud storage. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： android application cloud storage Face-based attendance gps technology image recognition

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：