检索结果-内蒙古大学图书馆

Lexicon-based fine-tuning of multilingual language models for low-resource language sentiment analysis

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1116-1125页

作者： Vinura Dhananjaya Surangika Ranathunga Sanath Jayasena Department of Computer Science and Engineering University of MoratuwaMoratuwaSri Lanka School of Mathematical and Computational Sciences Massey UniversityPalmerston NorthNew Zealand

Pre-trained multilingual language models (PMLMs) such as mBERT and XLM-R have shown good cross-lingual transferability. However, they are not specifically trained to capture cross-lingual signals concerning sentiment words. This poses a disadvantage for low-resource languages (LRLs) that are under-represented in these models. To better fine-tune these models for sentiment classification in LRLs, a novel intermediate task fine-tuning (ITFT) technique based on a sentiment lexicon of a high-resource language (HRL) is introduced. The authors experiment with LRLs Sinhala, Tamil and Bengali for a 3-class sentiment classification task and show that this method outperforms vanilla fine-tuning of the PMLM. It also outperforms or is on-par with basic ITFT that relies on an HRL sentiment classification dataset.

关键词： deep learning natural languages natural language processing

来源：评论

学校读者我要写书评

暂无评论

Hybrid RMDL-CNN for speech recognition from unclear speech signal

引用

International Journal of Speech Technology 2025年第1期28卷 195-217页

作者： Bhargava, Raja Arivazhagan, N. Babu, Kunchala Suresh Research Scholar Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering Potti Sriramulu Chaluvadi Mallikarjuna Rao college of Engineering and Technology Andhra Pradesh Vijayawada India

ASR is an effectual approach, which converts human speech into computer actions or text format. It involves extracting and determining the noise feature, the audio model, and the language model. The extraction and determination of the noise feature is a crucial aspect of speech recognition, serving as both a process of information compression and signal deconvolution. ASR schemes are mostly employed in smart homes, smart appliances, and biometric schemes. Yet, traditional approaches offer very low performance because of a noisy environment. Moreover, local differences and accents negatively influence the ASR scheme execution during the conversion of the speech signals. This paper introduces a hybrid RMDL-CNN method to address these challenges. At first, the input of unclear speech is carried out by the dataset. Then, signal pre-processing is done by employing a Gaussian filter. After that, voice enhancement is accomplished by employing nonlinear spectral subtraction. Later, the speech word is segmented from the enhanced output based on the Attentional Encoder-Decoder approach and finally, the speech is recognized using the proposed RMDL-CNN. The RMDL-CNN method is devised by the combination of RMDL and CNN. Furthermore, the established RMDL-CNN is accessed for its efficiency based on several values of k-group value, as well as learning data. In addition, the introduced RMDL-CNN approach for speech recognition achieved better accuracy, PPV, as well as NPV of 0.909, 0.947, and 0.917 for dataset 1. Moreover, the RMDL-CNN has achieved the highest accuracy of 0.909, PPV of 0.926 and NPV of 0.888 for dataset 2. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Appearance and motion-based unusual crowd events detection using multiple moving objects

引用

Multimedia Tools and Applications 2024年第42期83卷 90177-90189页

作者： Babu, K. Atlas, L. Godlin Sreeji, S. Arjun, K.P. Rasmi, A. Senthilvel, P. Gururama Computational Intelligence SRM Institute of Science & Technology Chengalpet Kattankulathur603203 India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gitam University Karnataka Bengaluru India Information Science and Engineering RRIT Bangalore India Saveetha University Chennai602 105 India

Unusual crowd analysis is an important problem in surveillance video due to their features cannot be extracted efficiently on the crowd scenes. To overcome this challenge, this paper introduced the appearance and motion based unusual events detection method by using multiple moving objects. This method includes appearance and motion based computation, and moving objects trajectory analysis. By using these all techniques, the unusual crowds and their activities can be obtained by analyzing moving objects size and the distance among multiple moving objects. Two benchmark datasets such as PETS 2009 and UMN are used for the experimental results. Also, several existing algorithms are compared with the proposed method to evaluate the effectiveness of the proposed work. The comparative analysis results proved that the proposed method achieved best accuracy for unusual crowd events. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： And trajectory analysis Appearance based analysis Distance based analysis Unusual crowd events detection

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Enhancing Digital Twin Security Systems with Explainable AI Techniques 3

A Comprehensive Survey on Enhancing Digital Twin Security Sy...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Lalithadevi, B. Krishnaveni, S. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

Digital Twin (DT) technology has emerged as a cornerstone in modern engineering, enabling real-time digital replication of physical assets for monitoring, diagnostics, and optimization. However, as DTs become increasingly integrated into critical infrastructure, their security has become a paramount concern. This paper presents a comprehensive survey on the integration of Explainable Artificial Intelligence (XAI) into Digital Twin security, highlighting the potential of XAI in enhancing the transparency, interpretability, and trustworthiness of AI - driven security mechanisms in DTs. We explore various XAI techniques, including model- agnostic approaches, interpretable neural networks, and rule-based systems, detailing their potential applications in bolstering the security of Digital Twins. Furthermore, we identify several key challenges in implementing XAI for DT security, such as the need for standardized metrics for interpretability, the trade-offs between model complexity and explainability, and the potential for adversarial attacks on explainable models. Through our analysis, we highlight the critical research gaps, including the security of Digital Twin (DT) systems and explores the integration of Explainable AI (XAI) to enhance transparency, interpretability, and trustworthiness. Outcomes include detailed XAI applications for DT security, identification of limitations, and a roadmap for future research. We discuss various XAI techniques, their applications, and the current challenges in implementing XAI for DT security. Our survey identifies key research gaps and offers a roadmap for future research in this emerging field. © 2025 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection and Classification in Streaming PMU Data in Smart Grids

引用

computer Systems science & engineering 2023年第9期46卷 3387-3401页

作者： A.L.Amutha R.Annie Uthra J.Preetha Roselyn R.Golda Brunet Department of Computational Intelligence SRM Institute of Science and TechnologyChennai603203India Department of Electrical and Electronics Engineering SRM Institute of Science and TechnologyChennai603203India Department of Computer Science and Engineering Government College of EngineeringSalem636011India

The invention of Phasor Measurement Units(PMUs)produce synchronized phasor measurements with high resolution real time monitoring and control of power system in smart grids that make *** are used in transmitting data to Phasor Data Concentrators(PDC)placed in control centers for monitoring purpose.A primary concern of system operators in control centers is maintaining safe and efficient operation of the power *** can be achieved by continuous monitoring of the PMU data that contains both normal and abnormal *** normal data indicates the normal behavior of the grid whereas the abnormal data indicates fault or abnormal conditions in power *** a result,detecting anomalies/abnormal conditions in the fast flowing PMU data that reflects the status of the power system is critical.A novel methodology for detecting and categorizing abnormalities in streaming PMU data is presented in this *** proposed method consists of three modules namely,offline Gaussian Mixture Model(GMM),online GMM for identifying anomalies and clustering ensemble model for classifying the *** significant features of the proposed method are detecting anomalies while taking into account of multivariate nature of the PMU dataset,adapting to concept drift in the flowing PMU data without retraining the existing model unnecessarily and classifying the *** proposed model is implemented in Python and the testing results prove that the proposed model is well suited for detection and classification of anomalies on the fly.

关键词： Smart Grid PMU data incremental learning classifying anomalies artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Comments on "relaxed Conditions for the Input-to-State Stability of Switched Nonlinear Time-Varying Systems"

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4233-4236页

作者： Şahan, Gökhan Trenn, Stephan Izmir Institute of Technology Department of Mathematics and Computational Science and Engineering Program Urla Izmir Turkey University of Groningen Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence Groningen9722BA Netherlands

This study addresses the deficiencies in the assumptions of the results in Chen and Yang, 2017 [1] due to the lack of uniformity. We first show the missing hypothesis by presenting a counterexample. Then we prove why they are wrong in that form and show the errors in the proof of the main result of [1]. Next, we compare the assumptions and related results of [1] with similar works in the literature. Lastly, we give suggestions to complement the shortcomings of the hypotheses and thus correct them. © 1963-2012 IEEE.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain Department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information Science and Technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： Data privacy distributed machine learning federated learning software frameworks

来源：评论

学校读者我要写书评

暂无评论

Brain Graph Super-Resolution for Enhanced Neurological Disorder Diagnosis

Brain Graph Super-Resolution for Enhanced Neurological Disor...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Roobini, M.S. Jebaraj, M. Samuel Sasirudh, P.B. Babu, K. Muneera, M. Nafees Sathvabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India

ISBN: (纸本)9798331543617

Functional brain data analysis is important in diagnosing neurological disorders, yet constructing high-resolution (HR) brain graphs from low-resolution (LR) although the data presents some computational challenges. This paper introduces the Brain Graph Super-Resolution (BGSR) method that leverages generative adversarial networks (GANs) to directly generate HR graphs from LR data. By bypassing complex image processes, BGSR enhances diagnostic accuracy efficiently while retaining the features. This paper explains BGSR' s methodology, detailing its implementation steps and emphasizing its potential to revolutionize neurological disorder diagnosis. Experimental results demonstrate BGSR's effectiveness in improving diagnostic precision compared to traditional methods. Furthermore, itdiscusses the broader implications of BGSR in advancing functional brain data analysis and suggests future research directions for further works and application in the field of medicine. BGSR is a promising tool for researchers and clinicians alike, offering insights into the minute workings of the brain and facilitating more accurate diagnosis and treatment of neurological disorders. Through its innovative approach, BGSR contributes to the ongoing efforts to unravel the complexities of the human brain and offers new avenues for understanding and addressing neurological disorders. Its streamlined methodology and enhanced diagnostic capabilities hold promise for improving patient outcomes and advancing the field of neuroscience. In the realm of neurological disorder analysis, conventional methods often grapple with issues of precision and struggle to cope with the brain data due to its complexity. This paper introduces a novel paradigm known as Brain Graph Super-Resolution (BGSR), a pioneering technique leveraging the potential of Generative Adversarial Networks (GANs) to synthesize high-resolution brain graphs directly from low-resolution data, by circumventing convoluted image processing wo

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Novel Multimodal Biometric Feature Extraction for Precise Human Identification

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 1349-1363页

作者： J.Vasavi M.S.Abirami Department of Computer Science and Engineering SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia Department of Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia

In recent years,biometric sensors are applicable for identifying impor-tant individual information and accessing the control using various identiﬁers by including the characteristics like aﬁngerprint,palm print,iris recognition,and so ***,the precise identiﬁcation of human features is still physically chal-lenging in humans during their lifetime resulting in a variance in their appearance or *** response to these challenges,a novel Multimodal Biometric Feature Extraction(MBFE)model is proposed to extract the features from the noisy sen-sor data using a modiﬁed Ranking-based Deep Convolution Neural Network(RDCNN).The proposed MBFE model enables the feature extraction from differ-ent biometric images that includes iris,palm print,and lip,where the images are preprocessed initially for further *** extracted features are validated after optimal extraction by the RDCNN by splitting the datasets to train the fea-ture extraction model and then testing the model with different sets of input *** simulation is performed in matlab to test the efﬁcacy of the modal over multi-modal datasets and the simulation result shows that the proposed meth-od achieves increased accuracy,precision,recall,and F1 score than the existing deep learning feature extraction *** performance improvement of the MBFE Algorithm technique in terms of accuracy,precision,recall,and F1 score is attained by 0.126%,0.152%,0.184%,and 0.38%with existing Back Propaga-tion Neural Network(BPNN),Human Identiﬁcation Using Wavelet Transform(HIUWT),Segmentation Methodology for Non-cooperative Recognition(SMNR),Daugman Iris Localization Algorithm(DILA)feature extraction techni-ques respectively.

关键词： Multimodalbiometric feature extraction ranking-baseddeepconvolution neural network noisy sensor data palm prints lip biometric iris recognition

来源：评论

学校读者我要写书评

暂无评论

On the Parameterized Complexity of Odd Coloring 11th

On the Parameterized Complexity of Odd Coloring

引用

11th International Conference on Algorithms and Discrete Applied Mathematics, CALDAM 2025

作者： Bhyravarapu, Sriram Kumari, Swati Vinod Reddy, I. The Institute of Mathematical Sciences HBNI Chennai India Department of Computer Science and Engineering IIT Bhilai Bhilai India

ISBN: (纸本)9783031834370

A proper vertex coloring of a connected graph G is called an odd coloring if, for every vertex v of G there is a color that appears odd number of times in the open neighborhood of v. The minimum number of colors required to obtain an odd coloring of G is called the odd chromatic number of G and it is denoted by χo(G). The problem of determining χo(G) is NP-hard. Given a graph G and an integer k, the Odd Coloring problem is to decide whether χo(G) is at most k. In this paper, we study the problem from the viewpoint of parameterized complexity. In particular, we study the problem with respect to structural graph parameters. We prove that the problem admits a polynomial kernel when parameterized by distance to clique. On the other hand, we show that the problem cannot have a polynomial kernel when parameterized by vertex cover number unless NP⊆Co-NP/poly. We show that the problem is fixed-parameter tractable when parameterized by distance to cluster, distance to co-cluster, or neighborhood diversity. We show that the problem is W[1]-hard parameterized by clique-width. Finally, we study the problem on restricted graph classes. We show that the problem can be solved in polynomial time on cographs and split graphs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Parameterization

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：