检索结果-内蒙古大学图书馆

Telugu Language Analysis with XLM-RoBERTa: Enhancing Parts of Speech Tagging for Effective Natural Language Processing

引用

SN Computer science 2025年第2期6卷 1-13页

作者： Bharathi Mohan, G. Prasanna Kumar, R. Krishna Jayanth, K. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

This research investigates the efficacy of XLM-RoBERTa, a potent deep learning architecture rooted in transformer networks, for Part-of-Speech (POS) tagging—a foundational task in Natural Language Processing (NLP). The study narrows its focus to address the formidable UCD Telugu dataset, renowned for its intricate morphological characteristics that pose challenges to accurate tagging. Through meticulous fine-tuning of the pre-trained XLM-RoBERTa model. This study adeptly discerns and exploit intricate syntactic and semantic patterns underpinning the interplay between lexical elements and their respective POS tags. The rigorous evaluation regimen, complemented by a comprehensive statistical comparison with the Multilingual BERT model, conclusively establishes XLM-RoBERTa’s superiority. This advanced model attains a remarkable accuracy score of 91%, decisively surpassing the Multilingual BERT model, which achieves an accuracy of 88%. These findings not only underscore XLM-RoBERTa’s prowess in precise POS tagging, especially in the context of morphologically rich languages like Telugu, but also carry significant implications for the broader NLP community. This research unlocks valuable insights and positions XLM-RoBERTa as an exemplar of reliability and robustness in POS tagging. Furthermore, it extends an invitation for further exploration and innovation in deep learning architectures within the NLP domain. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bert Multilingual Bert NLP Parts-of-speech tagging Telugu XLM-RoBERTa

来源：评论

学校读者我要写书评

暂无评论

End-To-End Encrypted Agriculture Chatbot 8

End-To-End Encrypted Agriculture Chatbot

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Reddy, Pennabadi Devendra Reddy, K Satya Sampath Jayanth, P. Kavitha, C.R. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798350367904

Agriculture sector is considered to be one of the most prominent sectors in the Indian economy. Farmers constantly face challenges such as a lack of information on best practices, disease detection, and market information. An End-to-End Agriculture chatbot can solve this problem by providing real-time information and support to farmers to enhance their productivity. This paper introduces a secure End-to-End Agriculture chatbot designed with strong encryption techniques to ensure data security. The proposed system will use the different asymmetric algorithm, a well-established public key cryptography method, to establish a safe and secure platform. Users sensitive data like soil reports and crop information will be encrypted using a widely available public key before sending it to the chatbot. After then, the chatbot uses its safe private key to decode the data. The asymmetric encryption method makes sure that the data being sent can only be accessed by authorized parties. © 2024 IEEE.

关键词： Encryption algorithms

来源：评论

学校读者我要写书评

暂无评论

Advancing Supply Chain Management: Cloud-Based Demand Forecasting Solutions 3

Advancing Supply Chain Management: Cloud-Based Demand Foreca...

引用

3rd International Conference for Advancement in Technology, ICONAT 2024

作者： Spoorthi, M. Rao, Subhiksha Suresh Mishra, Sahil Rajagopal, Shinu M Prashanth, Mrudula Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350354171

On-demand information that can be provided throughout all parts of the supply chain network and through cloud-based supply chain management system optimizes resource flow, enhances cooperation, and increases adaptability. The study delves into the amalgamation of AWS (Amazon Web Services) cloud solutions into demand projections for use in supply chain oversight. Inventory levels optimization, production planning streamlining and, thus, global supply chain efficiency tailoring all hinge on one factor: demand forecasting. Adopting AWS cloud services elicits a plethora of benefits;ranging from - but not limited to - scalability, flexibility and cost efficiency. AWS avails an array of instruments and provisions that enable entities to sift through copious historical data seamlessly. They can mix this with extrinsic determinants like market dynamism or even seasonal oscillations so as to arrive at those ever-accurate demand forecasts. On another front altogether is AWS' ability to handle storage, processing plus visualization capabilities for data silos integration towards seamless real-time updates delivery on forecast reports. © 2024 IEEE.

关键词： Amazon Forecast Cloud computing demand forecasting real-time supply chain management

来源：评论

学校读者我要写书评

暂无评论

Intelligent and Real-Time Intravenous Drip Level Indication 4th

Intelligent and Real-Time Intravenous Drip Level Indication

引用

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Krishnapriya, V.S. Suresh, Namita Srilakshmi, S.R. Abhishek, S. Anjali, T. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9789819965854

The ability of medical technology to diagnose and cure illnesses more successfully has revolutionised the healthcare sector. However, there is still a gap in monitoring intravenous (IV) drip bottles in real time. Real-time monitoring of IV bottles is crucial to prevent backflow of blood from the patient to the empty drip bottle, which can lead to severe consequences, including the patient's death. To address this issue, an Internet of Things (IoT)-based IV drip monitoring system has been proposed. The system incorporates a device that detects the fluid solution level and informs medical personnel via a buzzer and a website that shows the IV drip fluid levels of each patient in real time. This feature enables nurses to monitor each patient’s fluid intake and take necessary actions, thereby avoiding potential risks associated with overconsumption. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Bottles

来源：评论

学校读者我要写书评

暂无评论

Enhancing Digital Image Security using Visual Cryptography Integrated with AES and RSA Encryption Techniques 3

Enhancing Digital Image Security using Visual Cryptography I...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Adabala, Prajna Aasritha Gowtham, Rajani Sai Venkata Jaishitha, Thambi Rishisri, Vadluri Sai Kavitha, C.R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331518592

Visual cryptography (VC) designed to secure visual information such as images and text by dividing it into multiple shares. A key advantage of visual cryptography is its ability to decrypt information without the need for computational devices, using simple human visual perception. The paper is centered on visual cryptography with examples such as Visual Secret Sharing, Advanced Encryption Standard (AES), and Rivest-Shamir-Adleman (RSA) during the encryption and decryption stages. The specific algorithms' efficiency in increasing security and improving image quality is discussed. The quality and overall accuracy of the reconstructed images are measured by the Peak Signal-to-Noise Ratio (PSNR). The benchmark images are used to compare the results in terms of encryption and decryption time and PSNR value. The findings signify the integration of AES and RSA in improving security without compromising image quality and computational complexity. © 2024 IEEE.

关键词： AES Decryption Encryption RSA Visual Cryptography

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Evolutionary Algorithm Based on Decomposition—Dynamic Resource Allocation with Mixture Model 2nd

A Multi-objective Evolutionary Algorithm Based on Decomposi...

引用

2nd International Conference on Advances in Data-driven computing and Intelligent Systems, ADCIS 2023

作者： Alagumathi, M. Thangavelu, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9789819995301

Multi-objective evolutionary algorithm based on decomposition (MOEA/D) is the basis for studying the concept of multi-objective optimization problems on the basis of decomposition. MOEA/D has computational complexity in solving the multi-objective optimization sub-problems. To reduce computational complexity, in 2009, Zhang et al. proposed a method called MOEA/D-DRA (MOEA/D-Dynamic Resource Allocation). In MOEA/D-DRA, each sub-problem utilizes the computational resources dynamically in a different way. The construction of weight vectors is very important for the success of these algorithms. They actually define the search directions and distribution of the Pareto optimal solutions (POS). This paper proposes a weight vector generation method using uniform design and a mixture model (called MOEA/D-DRA-MM). The MOEA/D-DRA-MM builds a new weight vector generation method that makes the distribution of the weights uniform and broadens the diversity and convergence. MOEA/D-DRA-MM uses two weight vectors that are obtained by uniform design with a mixture distribution. Simulation results suggest that MOEA/D-DRA-MM may provide better convergence and diversity with respect to inverted generational distance and hypervolume metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Speech using Telugu Language and Deep Learning Models 1

Emotion Recognition from Speech using Telugu Language and De...

引用

1st IEEE International Conference on Communications and Computer science, InCCCS 2024

作者： Aditya, S. Satwik, Vaka R. Krishna, Vamsi V. Vimal, C. Palaniswamy, Suja Pati, Peeta Basa Department of Computer Science & Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350358858

This research involves the use of deep learning techniques to detect emotions, in Telugu speech signals, a research domain that has received little attention. Amrita speech emotion dataset-1 (ASED-1) consisting of 550 signals representing five categories. Surprise, anger, happiness, neutrality, and sadness. We explore how well various deep learning models can recognize emotions from speech. Our approach involves training models such as Convolutional Neural Networks (CNNs) Long Short-Term Memory (LSTM) networks and Multi-Layer Perceptron (MLPs) on a portion of the data and evaluating their performance on a test set. The MLP model achieved an accuracy rate of 84% although this was constrained by the size of the dataset. The CNN model showed results with decreasing trends in both training and validation loss indicating learning and generalization abilities. Similarly, the AlexNet architecture demonstrated a decline in both training and validation loss suggesting a fit without overfitting. Additionally, we included a machine learning classifier at the layer. Observed different accuracies across various models. The RNN model achieved an encouraging accuracy rate on the test data showing potential for emotion classification tasks but also room for improvement, through complex architectures or larger datasets. This research paper adds to the knowledge, in the field of emotion recognition, in Telugu speech by emphasizing the difficulties and possibilities of using deep learning techniques in this domain. © 2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Speech to Action for Assisting Deaf Communities 8th

Speech to Action for Assisting Deaf Communities

引用

8th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2024

作者： Krishna, Vunnam Vamsi Naini, Dheeraj Reddy Reddy, Vaka Satwik Sakri, Aditya Rajesh Radha, D. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bangalore India

ISBN: (纸本)9789819766802

In response to the changing world we live in, this groundbreaking project aims to redefine how people interact within the deaf and hard of hearing communities. The main goal is to develop a system that can understand and translate sign language while also preserving the aspect of emotion. By leveraging the power of technologies like speech recognition, emotional analysis, and deep learning techniques like CNN, LSTM an extensive system has been designed to adapt and respond in real time. This ensures that translated sign language maintains its subtleties for an enriching communication experience. Extensive testing of the system has been conducted as a part of the feedback loop by gathering information using the application. The results have confirmed its accuracy in translating languages and capturing emotions leading to empathetic interactions within the community. This work represents an advancement in how the hearing impaired interact within the communities, highlighting the importance of inclusivity, in advancements. It signifies a milestone toward envisioning a future where the captivating essence of communication effortlessly transcends through expressive sign language ultimately improving user experiences. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition from Speech, Text, and Facial Expressions Using Meta-Learning 1

引用

International Conference on Applied Soft computing and Communication Networks, ACN 2023

作者： Laalitya, Garapati Vaishnavi, Koduvayur Satyanarayana Rohith, T. Kavitha, C.R. Palaniswamy, Suja Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (数字)9789819720040

ISBN: (纸本)9789819720033

This paper presents a meta-learning methodology for emotion detection in multimedia content. The proposed approach uses three distinct models: Siamese network, convolutional neural network (CNN), and recurrent neural network (RNN) to identify emotions in a self-produced database of 1200 video and audio files. The Siamese network compares input files with reference to emotions to determine the emotion of the input file, while CNN classifies the input files into several emotion categories. In cases where data is scarce or insufficient to tackle a particular problem, meta-learning becomes a powerful strategy for quickly adapting to new scenarios and training with a limited set of examples. To enhance performance across various tasks, it is crucial to train a well-refined meta-learning model on a range of learning tasks. The justification for incorporating meta-learning in this study for emotion recognition lies in its versatility and adaptability, as it enables effective adaptation to novel environments and challenges. The performance of the models is evaluated against traditional machine learning methods, and the results show that the meta-learning approach achieves state-of-the-art performance on the self-created dataset. The suggested meta-learning strategy has the potential to enhance the precision and adaptability of current emotion detection methods. Additionally, it can be expanded to various domains and applications, including speech recognition and sentiment analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Music Recommendation System based on Big Data using Pyspark 9

Music Recommendation System based on Big Data using Pyspark

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Jain, Nikunj Sah, Nabin Kumar Hawari, Jawed Khare, Sangita Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Bengaluru India

ISBN: (纸本)9798350394474

In the evolving landscape of digital music consumption, personalized song recommendation systems play a pivotal role in enhancing user engagement and satisfaction. This article presents an in-depth exploration and analysis of an innovative song recommendation framework designed to address the challenges of delivering tailored music experiences. Utilizing advanced machine learning techniques, especially K-Means Clustering Algorithm and data analytics, the proposed system aims to offer song suggestions according to user preferences. The proposed system introduces a hybrid song recommendation system that combines the two distinct approaches i.e. Content and Collaborative based filtering. Various algorithms were implemented for Content based filtering whereas Hadoop and Pyspark was used for implementation of Collaborative filtering. Wide research and Evaluations based on various metrics were considered. The research also draws the strengths and drawbacks or limitations of Content based Recommendation over Collaborative based Recommendation System. The results highlight the system's capability to overcome limitations eventually enhancing user experience by offering a better experience. © 2024 IEEE.

关键词： Recommender systems

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：