检索结果-内蒙古大学图书馆

Enhancing text understanding of decoder-based model by leveraging parameter-efficient fine-tuning method

Neural Computing and Applications 2025年第9期37卷 6899-6913页

作者： Feroze, Wasif Cheng, Shaohuan Jimale, Elias Lemuye Jakhro, Abdul Naveed Qu, Hong School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Information Technology Shaheed Benazir Bhutto University Naushahro Feroze Campus Naushahro Feroze Pakistan

Machine reading comprehension (MRC) is a fundamental natural language understanding task in natural language processing, which aims to comprehend the text of a given passage and answer questions based on it. Understanding implicit information, deducing the logical structure of information, and connecting context from different pieces of information make the MRC task difficult. Most current state-of-the-art approaches for MRC are using encoder-based models. However, no earlier research proposed a decoder-only model for MRC question-answering datasets, although language models based on this category achieved unprecedented performance in different generative tasks. In this paper, we propose a parameter-efficient fine-tuning framework that effectively increases MRC capabilities on decoder-only large language models. This framework designs the process for MRC and introduces the low-rank adaptation (LoRA) method to effectively fine-tune the large model with many parameters, even with lower hardware resource requirements than the previous methods. In addition, we also integrate a quantized model inference strategy for the fine-tuned model to improve practicability further. We conducted experiments on four types of MRC datasets. After extensive experiments, our results show that our model achieved a significant performance boost over baselines and outperformed other strong models for MRC. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Event Management System Using Spatial and Event Attribute Information

引用

SN computer science 2025年第3期6卷 1-9页

作者： Setia, Sonia Anjli, Km Bisht, Upasana Jyoti Raj, Dharm Department of Computer Science & Engineering Sharda School of Engineering & Technology Sharda University Uttar Pradesh Greater Noida India Department of Computer Science Institute of Innovation in Technology & Management Delhi Janakpuri India Department of Computer Science and Engineering ITS Engineering College Greater Noida India

The event management mechanism matches messages that have been subscribed to and events that have been published. To identify the subscriptions that correspond to the occurrence inside the category, it must first run a clustering operation on the subscription message data and determine the category to which the event belongs. In this work, we offer an on-the-fly publish-subscribe technique that can handle on-the-fly subscription changes and category modifications in a distributed environment, as well as the synchronization of spatial information and event attribute information. Additionally, without any prior information, clustering and matching processes can be carried out rapidly. The publish-subscribe method is implemented on a distributed system, and a load-balancing solution is proposed for the algorithm on the distributed system. We then constructed our cluster and used real data to empirically evaluate the suggested publish-subscribe technique. Experiments show that incorporating both similarity and relevance with frequency, compared to focusing on similarity alone, significantly decreases the number of categories which need to be matched for events. This leads to a 15.5% improvement in the speed of matching events and subscriptions. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Clustering algorithms Distributed systems Publish-and-subscribe systems

来源：评论

学校读者我要写书评

暂无评论

Ladon: High-Performance Multi-BFT Consensus via Dynamic Global Ordering 25

Ladon: High-Performance Multi-BFT Consensus via Dynamic Glob...

引用

20th European Conference on computer Systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2025

作者： Lyu, Hanzheng Xie, Shaokang Niu, Jianyu Feng, Chen Zhang, Yinqian Beschastnikh, Ivan Canada Southern University of Science and Technology China Canada Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering SUSTech China

ISBN: (纸本)9798400711961

Multi-BFT consensus runs multiple leader-based consensus instances in parallel, circumventing the leader bottleneck of a single instance. However, it contains an Achilles’ heel: the need to globally order output blocks across instances. Deriving this global ordering is challenging because it must cope with different rates at which blocks are produced by instances. Prior Multi-BFT designs assign each block a global index before creation, leading to poor performance. We propose Ladon, a high-performance Multi-BFT protocol that allows varying instance block rates. Our key idea is to order blocks across instances dynamically, which eliminates blocking on slow instances. We achieve dynamic global ordering by assigning monotonic ranks to blocks. We pipeline rank coordination with the consensus process to reduce protocol overhead and combine aggregate signatures with rank information to reduce message complexity. Ladon’s dynamic ordering enables blocks to be globally ordered according to their generation, which respects inter-block causality. We implemented and evaluated Ladon by integrating it with both PBFT and HotStuff protocols. Our evaluation shows that Ladon-PBFT (resp., Ladon-HotStuff) improves the peak throughput of the prior art by ≈ 8× (resp., 2×) and reduces latency by ≈ 62% (resp., 23%), when deployed with one straggling replica (out of 128 replicas) in a WAN setting. © 2025 Copyright held by the owner/author(s).

关键词： Network protocols

来源：评论

学校读者我要写书评

暂无评论

BNSENTMIX: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis 1

BNSENTMIX: A Diverse Bengali-English Code-Mixed Dataset for ...

引用

1st Workshop on Language Models for Low-Resource Languages, LoResLM 2025 - co-located at the 31st International Conference on Computational Linguistics, COLING 2025

作者： Alam, Sadia Farhan Ishmam, Md. Alvee, Navid Hasin Shahnewaz Siddique, Md. Kamal, Abu Raihan Mostofa Azam Hossain, Md. Department of Computer Science and Engineering Islamic University of Technology Bangladesh

ISBN: (纸本)9798891762152

The widespread availability of code-mixed data in digital spaces can provide valuable insights into low-resource languages like Bengali, which have limited annotated corpora. Sentiment analysis, a pivotal text classification task, has been explored across multiple languages, yet code-mixed Bengali remains underrepresented with no large-scale, diverse benchmark. Code-mixed text is particularly challenging as it requires the understanding of multiple languages and their interaction in the same text. We address this limitation by introducing BNSENTMIX, a sentiment analysis dataset on code-mixed Bengali comprising 20,000 samples with 4 sentiment labels, sourced from Facebook, YouTube, and e-commerce sites. By aggregating multiple sources, we ensure linguistic diversity reflecting realistic code-mixed scenarios. We implement a novel automated text filtering pipeline using fine-tuned language models to detect code-mixed samples and expand code-mixed text corpora. We further propose baselines using machine learning, neural networks, and transformer-based language models. The availability of a diverse dataset is a critical step towards democratizing NLP and ultimately contributing to a better understanding of code-mixed languages. © 2025 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

Digital Over-the-Air Computation: Achieving High Reliability via Bit-Slicing

引用

IEEE Transactions on Wireless Communications 2025年第5期24卷 4101-4114页

作者： Liu, Jiawei Gong, Yi Huang, Kaibin The University of Hong Kong Department of Electrical and Electronics Engineering Hong Kong Hong Kong Southern University of Science and Technology Department of Electrical and Electronics Engineering Shenzhen518055 China

6G mobile networks aim to realize ubiquitous intelligence at the network edge via distributed learning, sensing, and data analytics. Their common operation is to aggregate high-dimensional data, which causes a communication bottleneck that cannot be resolved using traditional orthogonal multi-access schemes. A promising solution, called over-the-air computation (AirComp), exploits channels' waveform superposition property to enable simultaneous access, thereby overcoming the bottleneck. Nevertheless, its reliance on uncoded linear analog modulation exposes data to perturbation by noise and interference. Hence, the traditional analog AirComp falls short of meeting the high-reliability requirement for 6G. Overcoming the limitation of analog AirComp motivates this work, which focuses on developing a framework for digital AirComp. The proposed framework features digital modulation of each data value, integrated with the bit-slicing technique to allocate its bits to multiple symbols, thereby increasing the AirComp reliability. To optimally detect the aggregated digital symbols, we derive the optimal maximum a posteriori detector that is shown to outperform the traditional maximum likelihood detector. Furthermore, a comparative performance analysis of digital AirComp with respect to its analog counterpart with repetition coding is conducted to quantify the practical signal-to-noise ratio (SNR) regime favoring the proposed scheme. On the other hand, digital AirComp is enhanced by further development to feature awareness of heterogeneous bit importance levels and its exploitation in channel adaptation. Lastly, simulation results demonstrate the achivability of substantial reliability improvement of digital AirComp over its analog counterpart given the same channel uses. © 2002-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Evolutionary recurrent neural network based on equilibrium optimization method for cloud-edge resource management in internet of things

引用

Neural Computing and Applications 2025年第6期37卷 4957-4969页

作者： Ebrahimi Mood, Sepehr Rouhbakhsh, Adel Souri, Alireza Department of Computer Science Yazd University Yazd Iran Department of Computer Engineering Faculty of Engineering Haliç University Istanbul34060 Turkey School of Electrical and Electronic Engineering Shandong University of Technology Zibo255000 China

Cloud computing is an emerging field in information technology, enabling users to access a shared pool of computing resources. Despite its potential, cloud technology presents various challenges, with one of the most significant being resource management within the cloud environment. Specifically, the allocation of physical machines (PMs) to virtual machines (VMs) in the Infrastructure as a service (IaaS) layer aims to achieve optimal efficiency. To address this challenge, we propose an evolutionary recurrent neural network (RNN) for resource allocation, enhanced by the equilibrium optimization (EO) algorithm. This method improves the generalization performance and reduces the architecture complexity of RNNs, while ensuring better adaptability to various demand patterns in cloud environments. Additionally, the effectiveness of RNNs heavily relies on the quality of training data;hence, we generate appropriate training data to facilitate the development of an efficient resource management model. Through extensive simulations, our method demonstrates superior performance compared to traditional algorithms. However, it is worth noting that this study is primarily based on simulation results, highlighting the need for real-world validation to confirm its practical applicability. The proposed method's applicability to different cloud computing environments and scenarios, including various service models (IaaS, PaaS, and SaaS) and deployment models (public, private, and hybrid), is also briefly discussed. Future studies should explore the computational efficiency and potential optimization techniques of the EO-RNN approach and consider real-world implementations to validate its effectiveness and uncover practical challenges. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Hybrid CatBoost and SVR Model for Earthquake Prediction Using the LANL Earthquake Dataset

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第14期49卷 93-110页

作者： Kaushal, Arush Gupta, Ashok Kumar Sehgal, Vivek Kumar Department of Computer Science and Information Technology Jaypee University of Information Technology Solan171234 India Department of Civil Engineering Jaypee University of Information Technology Solan171234 India

Earthquakes have the potential to cause catastrophic structural and economic damage. This research explores the application of machine learning for earthquake prediction using LANL (Los Alamos National Laboratory) dataset. The data, obtained from a laboratory stick-slip friction experiment, simulate real earthquakes through digitized acoustic signals recorded against the time to failure of a granular layer. We introduced a hybrid model combining CatBoost and Support Vector Regression (SVR) to predict the time of the next earthquake, evaluating its performance against individual CatBoost and SVR models. The hybrid model demonstrated superior accuracy with a Mean Absolute Error (MAE) of 0.0825, outperforming the individual models. We implemented feature engineering to optimize the predictive capability of the models. Additionally, we compared our hybrid model's performance with previous studies to validate its efficacy. Our findings underscore the potential of machine learning, particularly hybrid models, in enhancing earthquake prediction accuracy. This study highlights the robustness and effectiveness of the hybrid CatBoost-SVR model, paving the way for advanced AI algorithms in seismology and contributing to improved disaster preparedness and mitigation strategies. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Stick-slip

来源：评论

学校读者我要写书评

暂无评论

DNN-STACK: a stacking technique based on deep neural network for detecting copy-move forgery

引用

Neural Computing and Applications 2025年第6期37卷 4989-5004页

作者： Krishnalal, G. Jagathy Raj, V.P. Madhu, G. Arun, K.S. School of Engineering Cochin University of Science and Technology Kerala Cochin682022 India School of Management Studies Cochin University of Science and Technology Kerala Cochin682022 India Department of Computer Applications Cochin University of Science and Technology Kerala Cochin682022 India

In recent years, detecting image forgery has become an important topic because of the availability of efficient and sophisticated image-editing software. Copy-move forgery, which involves copying a section of an image and pasting it to a different location inside the same image, is one of the most popular tampering techniques that alter the identity of a given image. This paper presents DNN-STACK, a deep neural network-based stacking scheme to identify copy-move forgery by effectively combining the predictions yielded by different base-level models. To extract hierarchical representations from the given images and generate base-level predictions, the proposed approach uses five distinct but complementary deep learning-based base-level models. After that, a consensus prediction is generated using the proposed DNN-STACK model, which can infer the nonlinear relationship between the base-level predictions. Experimental evaluation on three publicly available datasets, such as MICC-F600, MICC-F2000, and FAU, reveals the fact that the proposed DNN-STACK model outperforms the existing forgery detection techniques, significantly improving detection accuracy across varying image resolutions and attack types, including rotation, scaling, noise, and compression levels. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Disease Detection and Classification in Jackfruit Leaves: An Efficient Deep Learning-Based Approach 3rd

Automated Disease Detection and Classification in Jackfrui...

引用

3rd International Conference on Trends in Electronics and Health Informatics, TEHI 2023

作者： Saha, Dip Kumar Mahmud Joy, Md. Ashif Reza, Md. Rokonuzzaman Shovon, Reduanul Bari Department of Computer Science and Engineering American International University-Bangladesh Kuratoli Bangladesh Department of Computer Science and Engineering United International University Dhaka Bangladesh Department of Computer Science and Engineering The International University of Scholars Dhaka Bangladesh Department of Computer Science and Engineering Military Institute of Science and Technology Dhaka Bangladesh

ISBN: (纸本)9789819739363

Jackfruit is the national fruit of Bangladesh, and one of the most consumed fruits in India, Sri Lanka, Philippines, Indonesia, Malaysia, Australia, and many more countries. The every year due to diseases jackfruit production stays lower than the expectation. The early identification of these diseases is crucial for agricultural productivity, and our research showcases the effectiveness of deep learning techniques in addressing this issue. This study introduces an innovative approach to detect and classify two common jackfruit leaf diseases, algal spot and black spot, combining the YOLOv8 object detection model and the EfficientNetB7 pre-trained deep convolutional neural network model. The models trained on 6,360 images of those two diseases and our methodology achieved an accuracy of 99.9% on training and 99.5% on testing. This work represents a valuable contribution to agriculture, emphasizing the synergy between cutting-edge technology and age-old challenges, with the potential to positively impact the agricultural industry and global food security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Citrus fruits

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Decision-Based Clustering for Efficient Data Aggregation in Mobile UWSNs

引用

computers, Materials & Continua 2025年第4期83卷 259-279页

作者： Aadil Mushtaq Pandith Manni Kumar Naveen Kumar Nitin Goyal Sachin Ahuja Yonis Gulzar Rashi Rastogi Rupesh Gupta Department of Computer Science and Engineering Lovely Professional UniversityJalandhar144402PunjabIndia Department of Computer Science and Engineering Chandigarh UniversityMohali140413PunjabIndia Salesforce Inc. DallasTX 75201USA Department of Computer Science and Engineering School of Engineering and TechnologyCentral University of HaryanaMahendragarh123031HaryanaIndia Department of Management Information Systems College of Business AdministrationKing Faisal UniversityAl-Ahsa31982Saudi Arabia Department of Computer Application Sir Chhotu Ram Institute of Engineering and TechnologyCh.Charan Singh UniversityMeerut250001Uttar PradeshIndia Chitkara University Institute of Engineering and Technology Chitkara UniversityRajpura140401PunjabIndia

Underwater wireless sensor networks(UWSNs)rely on data aggregation to streamline routing operations by merging information at intermediate nodes before transmitting it to the ***,many existing data aggregation techniques are designed exclusively for static networks and fail to reflect the dynamic nature of underwater ***,conventional multi-hop data gathering techniques often lead to energy depletion problems near the sink,commonly known as the energy hole ***,cluster-based aggregation methods face significant challenges such as cluster head(CH)failures and collisions within clusters that degrade overall network *** address these limitations,this paper introduces an innovative framework,the Cluster-based Data Aggregation using Fuzzy Decision Model(CDAFDM),tailored for mobile *** proposed method has four main phases:clustering,CH selection,data aggregation,and *** CH selection,a fuzzy decision model is utilized to ensure efficient cluster head selection based on parameters such as residual energy,distance to the sink,and data delivery likelihood,enhancing network stability and energy *** the aggregation phase,CHs transmit a single,consolidated set of non-redundant data to the base station(BS),thereby reducing data duplication and saving *** adapt to the changing network topology,the re-clustering phase periodically updates cluster formations and reselects *** results show that CDAFDM outperforms current protocols such as CAPTAIN(Collection Algorithm for underwater oPTical-AcoustIc sensor Networks),EDDG(Event-Driven Data Gathering),and DCBMEC(Data Collection Based on Mobile Edge Computing)with a packet delivery ratio increase of up to 4%,an energy consumption reduction of 18%,and a data collection latency reduction of 52%.These findings highlight the framework’s potential for reliable and energy-efficient data aggregation mobile UWSNs.

关键词： Clustering data aggregation data collection fuzzy model monitoring UWSN

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：