检索结果-内蒙古大学图书馆

Intelligent Technologies (CONIT), International Conference on

作者： Nandu Vasudevan S Sachin Kumar Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (数字)9798350349900

ISBN: (纸本)9798350349917

This research uses an English-Malayalam dataset taken from YouTube comments to investigate improper language detection in multilingual settings. To capture the subtleties of language usage—such as code-mixing—that are common in the under-resourced Dravidian language family, we use autoencoders and ensemble techniques using BERT models as features. We use LIME in addition to improve interpretability. A lazy classifier that uses a variety of classifiers also helps to determine which classifier is the most efficient. Supervised learning methods are enhanced by unsupervised k-means clustering. Our results surpass standards and demonstrate the effectiveness of our method in offensive language identification. The field’s understanding is advanced by this confluence of methodologies.

关键词： Video on demand Social networking (online) Scalability Supervised learning Bidirectional control Benchmark testing Encoding

来源：评论

学校读者我要写书评

暂无评论

End-to-End Portfolio Optimization Using Transformer Encoder Model for Long Positions Strategy 1

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Srivatsan, K. Lal, G. Jyothish Gopalakrishnan, E.A. Ravi, Vinayakumar Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India Amrita School of Computing Amrita Vishwa Vidyapeetham Bangalore India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia

ISBN: (数字)9789819736904

ISBN: (纸本)9789819736898

Portfolio optimization has received considerable scholarly attention in recent years due to its potential for consistent returns. In our work, we developed a deep learning-based portfolio optimization model by integrating a Transformer Encoder Model with a Sharpe Loss Function. The main objective is to predict portfolio values and assign weights to assets using an end-to-end approach with a Sharpe Loss Function and evaluate our model against existing techniques in thematic sector portfolio optimization for the Indian stock market. We focused on six sectors of the NIFTY50 index (Services, PSE, MNC, Commodities, Manufacturing, and Financial Services). Our model consistently outperformed classical models in terms of CAGR and Portfolio Return Value across all time periods considered (2008–2010, 2011–2013, 2012–2015, 2016–2019, and 2019–2022), with the Hierarchical Risk Parity model closely following in terms of Portfolio Returns. Additionally, our model achieved higher Returns on Investment (ROI) in three out of the five thematic sectors (Services, PSE, MNC, respectively) compared to existing models (29%, 81%, and 71% ROI versus 18%, 51%, and 26% ROI, respectively). For the NIFTY Financial Services sector, our model obtained an ROI of 29%, which existing models did not evaluate. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Portfolio optimization Sharpe loss function Transformer models

来源：评论

学校读者我要写书评

暂无评论

Finding Network Motifs: A comparative study between ILP and Symmetric Rank-One NMF 3

Finding Network Motifs: A comparative study between ILP and ...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Aadharsh Aadhithya, A. Sachin Kumar, S. Rejathalal, Vinith Sujadevi, V.G. Poornachandran, Prabaharan Soman, K.P. Amrita Vishwa Vidyapeetham Center for Computational Engineering and Networking Coimbatore India Amrita Vishwa Vidhyapeetham Centre for Internet Studies and Artificial Intelligence Kerala Amritapuri India

ISBN: (纸本)9798350338607

This paper compares the performance of two popular methods, an integer linear programming (ILP) based method and a non-negative matrix factorization (NMF) based approximation, for identifying network motifs. Our analysis demonstrates that the ILP-based method is highly accurate but computationally expensive, whereas the NMF-based method is faster and more scalable but less accurate. The choice of method should depend on the specific research question and the size and complexity of the network being analyzed. We also highlight the need for further research to develop more efficient and accurate methods for identifying network motifs, especially for very large and complex networks. Understanding the significance of network motifs and their functions can lead to new therapeutic strategies and improved diagnostics for a wide range of *** addition, we provide an easy-to-use Matlab code implementation for researchers to get started with analyzing their own network motifs. Our code is based on both the ILP-based method, and can be customized to suit the specific needs of the user. This implementation can help facilitate the wider adoption of network motif analysis and enable researchers to gain a deeper understanding of complex systems. © 2023 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Glaucoma Detection Using CNN and Study on Class Imbalance Problem 6th

Glaucoma Detection Using CNN and Study on Class Imbalance Pr...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： U, Nitish Prem Kumar, Pradeesh M, Nimal Madhu V, Hareesh Variyar, V. V. Sajith Center for Computational Engineering and Networking Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore641112 India Department of Electrical Engineering National Institute of Technology Calicut Kerala Kozhikode India

ISBN: (纸本)9783031503269

Glaucoma refers to eye disorders that result in harm to the optic nerve, leading to either vision loss or blindness. Without treatment glaucoma tends to worsen gradually over time, making early detection and treatment crucial. Deep learning based on CNN was used for the detection of glaucoma using fundus images. But deep learning requires datasets which contain huge amounts of labelled high-quality images to predict with high accuracy. It is because of the need to extract important and complex patterns or features from the images for tuning its parameters and to reduce the model’s loss. But often the availability of such datasets is scarce and sometimes the datasets available will be highly imbalanced. In this paper, the issue of an imbalanced dataset has been addressed by using 2 sets of data augmentation techniques and GAN to make the dataset balanced and thereby increase the size of the dataset. The first set includes operations such as changing rotation, height, flipping etc. The second set includes operations such as changing hue, saturation, and contrast. The second set of augmentation provided the best result with an accuracy of 0.821 when compared with the rest of the approaches. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Extraction Technique for Hand Gesture Recognition System 6th

Robust Feature Extraction Technique for Hand Gesture Recogni...

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Yadukrishnan, V. Anilkumar, Abhishek Arun, K.S. Madhu, M. Nimal Hareesh, V. Center for Computational Engineering and Networking Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore641112 India Department of Electrical Engineering National Institute of Technology Calicut Kerala Kozhikode India

ISBN: (纸本)9783031503269

Hand gesture recognition (HGR) is a vital and versatile technology widely employed in various applications such as gaming, robotics, and interactive media. Beyond its broad utility, HGR systems play a crucial role in facilitating interactions for individuals with disabilities, empowering them with newfound capabilities. This paper introduces an innovative approach to feature extraction, leveraging Autoencoders to derive essential characteristics from the data. The extracted features are subsequently utilized for a comparative analysis of the accuracy achieved across different data sizes within the same dataset. By mapping the visual vocabulary of images, the Autoencoder generates a unified vector, which is then fed into Support Vector Machine (SVM), Naive Bayes, and K-Nearest Neighbor (KNN) classifiers. Through this research, we aim to enhance the efficiency and effectiveness of hand gesture recognition systems, fostering advancements in human-computer interaction and augmenting the quality of life for individuals with disabilities. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Time Series Forecasting for CO2 Emission 6th

Deep Learning-Based Time Series Forecasting for CO2 Emission

引用

6th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Anilkumar, Abhishek Yadukrishnan, V. Nimal Madhu, M. Hareesh, V. Premjith, B. Center for Computational Engineering and Networking Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore641112 India Department of Electrical Engineering National Institute of Technology Calicut Kerala Kozhikode India

ISBN: (纸本)9783031362453

The research paper provides a comprehensive and effective comparison of various deep learning (DL) models applied to univariate data of carbon dioxide (CO2) concentrations spanning from 1870 to 2021, focusing on five European countries: the United Kingdom (UK), Germany, France, Ukraine, and Italy. The primary aim of the study is to contribute to a better understanding of climate change and to facilitate the development of policies and actions to mitigate CO2 emissions. Three DL models, namely long short-term memory (LSTM), convolutional neural network-long short-term memory (CNN-LSTM), and dynamic mode decomposition (DMD), are employed and thoroughly evaluated in this research. A novel aspect of this paper lies in the spatiotemporal modeling and forecasting capabilities, which enable simultaneous analysis for multiple countries using DMD. The results show that DMD outperforms other DL models, such as LSTM and CNN-LSTM, in accurately capturing data trends and forecasting future CO2 values with the highest precision. The findings presented in this research paper have significant implications for advancing our understanding of climate change dynamics and guiding more effective measures to tackle CO2 emissions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Random Fourier Features based approach for Covid-19 Twitter Sentiment Classification using Machine Learning and Deep Learning

Random Fourier Features based approach for Covid-19 Twitter ...

引用

Intelligent Technologies (CONIT), International Conference on

作者： E. Vignesh Sachin Kumar S Neethu Mohan K. P. Soman Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India

The outbreak of Corona has significantly impacted the daily lives of thousands of people. Many individuals turned to social media for guidance and information during this pandemic. However, while social media can be a valuable source of information, it also presents certain drawbacks such as the spread of misinformation. Despite this, social media played an essential role in sharing accurate health information and providing support for individuals struggling with mental health during the pandemic. Social networking sites like Twitter provided a means for individuals to connect and share their experiences during this difficult time. To evaluate the impact of COVID-19, we propose a strategy that utilizes sentiment analysis of tweets from Twitter users. This analysis can help identify the emotions that people are feeling towards COVID-19, such as hope, pessimism, fear, annoyance, sadness, or nervousness. We utilized feature engineering techniques for sentiment analysis to categorize tweets into positive, negative, or neutral categories. We also utilized machine learning models to evaluate the effectiveness of various feature extraction and engineering techniques. In addition, we utilized class imbalance strategies to address the imbalance of emotion classes. Our study compares different feature extraction methods for text data, including statistical methods, word embedding-based methods, kernel feature maps, and hybrid methods. We achieved superior accuracy, precision, f1-score, and recall compared to previous studies when applied to the Covid Senti - A, Covid Senti -B, and Covid Senti -C datasets. Our findings suggest the assessment of public sentiment towards COVID-19 through the analysis of social media data can be a useful resource.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Approach to Dysarthric Speech Intelligibility Level Classification Using Transformers

arXiv

引用

arXiv 2023年

作者： Chowdary, Paleti Nikhil Aravind, Vadlapudi Sai Vardhan, Gorantla V.N.S.L. Vishnu Akshay, Menta Sai Aashish, Menta Sai Jyothish Lal, G. Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India

Dysarthria is a speech disorder that hinders communication due to difficulties in articulating words. Detection of dysarthria is important for several reasons as it can be used to develop a treatment plan and help improve a person's quality of life and ability to communicate effectively. Much of the literature focused on improving ASR systems for dysarthric speech. The objective of the current work is to develop models that can accurately classify the presence of dysarthria and also give information about the intelligibility level using limited data by employing a few-shot approach using a transformer model. This work also aims to tackle the data leakage that is present in previous studies. Our whisper-large-v2 transformer model trained on a subset of the UASpeech dataset containing medium intelligibility level patients achieved an accuracy of 85%, precision of 0.92, recall of 0.8 F1-score of 0.85, and specificity of 0.91. Experimental results also demonstrate that the model trained using the 'words' dataset performed better compared to the model trained on the 'letters' and 'digits' dataset. Moreover, the multiclass model achieved an accuracy of 67%. © 2023, CC BY.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Approach to Dysarthric Speech Intelligibility Level Classification Using Transformers

A Few-Shot Approach to Dysarthric Speech Intelligibility Lev...

引用

International Conference on Computing and networking Technology (ICCNT)

作者： Paleti Nikhil Chowdary Menta Sai Akshay Vadlapudi Sai Aravind Menta Sai Aashish Gorantla V N S L Vishnu Vardhan G. Jyothish Lal. Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore India

Dysarthria is a speech disorder that hinders communication due to difficulties in articulating words. Detection of dysarthria is important for several reasons as it can be used to develop a treatment plan and help improve a person’s quality of life and ability to communicate effectively. Much of the literature focused on improving ASR systems for dysarthric speech. The objective of the current work is to develop models that can accurately classify the presence of dysarthria and also give information about the intelligibility level using limited data by employing a few-shot approach using a transformer model. This work also aims to tackle the data leakage that is present in previous studies. Our whisper-large-v2 transformer model trained on a subset of the UASpeech dataset containing medium intelligibility level patients achieved an accuracy of 85%, precision of 0.92, recall of 0.8 F1-score of 0.85, and specificity of 0.91. Experimental results also demonstrate that the model trained using the ’words’ dataset performed better compared to the model trained on the ’letters’ and ’digits’ dataset. Moreover, the multiclass model achieved an accuracy of 67%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring a genotype based formalisation for tree adjoining grammar derivations

引用

International Journal of Information Technology (Singapore) 2021年第5期13卷 2119-2128页

作者： Menon, Vijay Krishna K P, Soman Center for Computational Engineering and Networking Amrita Vishwa Vidyapeetham Coimbatore Tamil Nadu India

Tree Adjoining Grammars (TAGs) are very useful psycholinguistic formalisms for syntax and dependency analysis of phrase structures. Since natural languages are finitely ambiguous, TAGs are ideal to model them being mildly context sensitive. But these grammars are very hard to parse as they have a worst case complexity of O(n⁶). In reality most conventional TAG parsing algorithms run in O(n³) and give the most probable parse, but trying to extract multiple ambiguous parses for a given phrase degrades the performance of the traditional TAG parsing algorithms toward worst case runtime, especially for longer sentences. Ambiguity in TAGs are not as well understood as in CFGs due to their complex derivation process;hence one of the ways to understand it is to find a finite set of ambiguous derivations for the given phrase structure. In this article we extend the definition of the containing formalism introduced as GATAGs on which a genetic algorithm can be deployed in order to find ambiguous derivation structures for longer sentences. We shall formalise the genotypes, phenotypes and the fitness functions for the entailing genetic algorithm, exploring various avenues for their efficient computations. Our main objective here is to explore the possibility of random derivations evolving to good derivations though a natural selection. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Evolutionary parsing Feature unification Formalism GATAG Genetic algorithm Lexicalisation Tree adjoining grammar

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：