检索结果-内蒙古大学图书馆

19th International Conference on Artificial Intelligence: Methodology, systems, and Applications, AIMSA 2024

作者： Janjani, Pranav Palan, Mayank Shirude, Sarvesh Shegokar, Ninad Kazi, Faruk Centre of Excellence in Complex and Nonlinear Dynamical Systems VJTI Mumbai India

ISBN: (纸本)9783031815416

Traditional summary generation approaches are limited by their reliance on isolated sources of data, restraining the quantity and quality of information gathered. This introduces the possibility of falsified content and provides limited support for multilingual and multimodal data. This paper presents a novel approach to summarization that tackles such challenges by utilizing the strength of multiple sources to deliver a more exhaustive and informative understanding of intricate topics. It progresses beyond conventional, unimodal sources such as text documents, integrating a diverse range of data, including YouTube playlists, pre-prints, and Wikipedia pages. The aforementioned multimodal sources are converted into a unified textual representation, enabling a holistic analysis. This multifaceted approach empowers us to extract pertinent information from a wider array of sources. The primary tenet of this approach is to maximize information gain, maintain a high level of informativeness while minimizing information overlap, and encourage the generation of highly coherent summaries. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion

arXiv

引用

arXiv 2024年

作者： Janjani, Pranav Palan, Mayank Shirude, Sarvesh Shegokar, Ninad Kumar, Sunny Kazi, Faruk Centre of Excellence in Complex and Nonlinear Dynamical Systems VJTI Mumbai India

Recent advances in large language models (LLMs) have led to new summarization strategies, offering an extensive toolkit for extracting important information. However, these approaches are frequently limited by their reliance on isolated sources of data. The amount of information that can be gathered is limited and covers a smaller range of themes, which introduces the possibility of falsified content and limited support for multilingual and multimodal data. The paper proposes a novel approach to summarization that tackles such challenges by utilizing the strength of multiple sources to deliver a more exhaustive and informative understanding of intricate topics. The research progresses beyond conventional, uni-modal sources such as text documents and integrates a more diverse range of data, including YouTube playlists, pre-prints, and Wikipedia pages. The aforementioned varied sources are then converted into a unified textual representation, enabling a more holistic analysis. This multifaceted approach to summary generation empowers us to extract pertinent information from a wider array of sources. The primary tenet of this approach is to maximize information gain while minimizing information overlap and maintaining a high level of informativeness, which encourages the generation of highly coherent summaries. © 2024, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Community Detection and Impact of Bots on Sentiment Polarity of Twitter Networks

Community Detection and Impact of Bots on Sentiment Polarity...

引用

2021 Asian Conference on Innovation in Technology, ASIANCON 2021

作者： Gatkal, Suyash Panjwani, Dhwani Barhate, Sanket Mangla, Ritika Kazi, Faruk VJTI Centre of Excellence in Complex and Nonlinear Dynamical Systems Mumbai India

ISBN: (纸本)9781728185835

The globe has been dominated today by Online Social Networks (OSN) like Facebook, Instagram, and Twitter. However, the rise of popularity and attractiveness of these web-based services has also led to the rise of malicious accounts known as bots. Not only do they cause Internet traffic, but also a group of these accounts working together can spread disinformation, incorrect, or manipulated news. The detection of bots, as well as their interactions with their communities and the rest of the world, is essential. This paper focuses on plotting a network of Twitter users, based on a particular hashtag, and detecting the communities in it, followed by detecting and locating the bots in these communities. In addition to this, sentiment analysis is conducted on normal users' tweets as well as the bots in these communities. This paper also aims to identify the overall sentiment of the communities, and thus provide promising conclusions relating to bot behavior in the overall network. © 2021 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Twitter bot detection and their influence in hashtag manipulation 17

Twitter bot detection and their influence in hashtag manipul...

引用

17th IEEE India Council International Conference, INDICON 2020

作者： Barhate, Sanket Mangla, Ritika Panjwani, Dhwani Gatkal, Suyash Kazi, Faruk Centre of Excellence in Complex and Nonlinear Dynamical Systems Vjti Mumbai India

ISBN: (纸本)9781728169163

Twitter is an important platform for many activities such as communication, promotion and news. Twitter is starting to clamp down on removing content and accounts whose sole purpose is to spread disinformation at scale. The increasing number of bots on Twitter has led to a significant circulation of malicious content. It has the power of manipulating and influencing people negatively. Hence bot detection and finding their extent of influence is of prime importance. This research has used varied approaches for the detection of bots;a supervised machine learning approach which makes use of a unique feature called the bot score to determine the bot probability of a user. Secondly, using an unsupervised machine learning approach, users were divided into various clusters based on their activity. Furthermore, to assess the influence of users in hashtag manipulation, this research analyzed various categories of users in a hashtag and made promising conclusions. © 2020 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Shapley based Interpretable Semi-supervised Model for Detecting Similarity Index of Social Media Campaigns

Shapley based Interpretable Semi-supervised Model for Detect...

引用

2020 International Conference on Computational Science and Computational Intelligence, CSCI 2020

作者： Framewala, Aman Patil, Aum Kazi, Faruk Vjti Centre of Excellence in Complex and Nonlinear Dynamical Systems Mumbai India

ISBN: (纸本)9781728176246

Although significant research is done on fake news detection, the definition of a news being fake has always been ambiguous. This problem can be addressed by comparing such campaigns of fake news or harmful content with previously detected similar campaigns on social media. Detecting similar campaigns also helps in structured analysis of social media content useful for various applications including comparison of different marketing campaigns. In this paper authors showcase a novel semi-supervised learning approach for detecting similar campaigns and giving human-like explanations for those predictions. This is done by using a modified version of Artificial Immune System (AIS) for unsupervised detection of similar campaigns. We then use eXtreme Gradient Boosting (XGBoost) model for extracting rules from predictions which are further fed to Shapley Additive exPlanations (SHAP) to generate payoffs of each contributing feature. We demonstrate the approach using three different social media campaigns covering public outrage, marketing and public awareness. © 2020 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Real-Time Detailed Dynamic Model of the Mumbai System in HYPERSIM

Real-Time Detailed Dynamic Model of the Mumbai System in HYP...

引用

International Conference on Energy, Power and Environment: Towards Sustainable Growth (ICEPE)

作者： Mohit Patil Sunny Kumar Abhishek Pandey Polagani Pentayya Faruk Kazi Electrical Engineering Department Centre of Excellence (CoE) in Complex and Nonlinear Dynamical Systems (CNDS) VJTI Mumbai India Independent Director (Technical) DNHPDCL India

Advancement in technology has led the metro city to develop the power network rapidly. One of the megacity Mumbai has seen a rapid increase and complexity of power system with the addition of harmonic loads. All of these advancements need the development of new instrument and techniques for assuring grid stability and dependability. Electromagnetic transient (EMT) simulations performed on the network using HYPERSIM as EMT-type models are more exact and detailed than RMS-type models during transient simulations. This creates a standardized platform for analyzing and comparing various strategies and tactics. This study creates an EMT RT Mumbai dynamic model on HYPERSIM simulation, done on the basis of the existing Mumbai grid PSS/E model. The network’s architecture and components are updated from RMS to EMT. The Mumbai model’s transient fault analysis and static load flow calculations are performed in HYPERSIM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Short-Term Solar and Wind Generation Forecasting for the Western Region of India

Short-Term Solar and Wind Generation Forecasting for the Wes...

引用

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Dhwani Panjwani Sanket Barhate Rahul Rane Abhishek Pandey Faruk Kazi Centre of Excellence (CoE) in Complex and Nonlinear Dynamical Systems (CNDS) VJTI Mumbai India

ISBN: (纸本)9781665448796

With the increased emission of greenhouse gases from fossil fuels, which endanger the environment, Renewable Energy (RE) sources have been attracting much attention in today's world. Integration of RE in power generation introduces variability and ramp events in power outputs due to their intermittent nature which affects system balancing, reserve management or scheduling and commitment of producing units. As a result, forecasting generation aids in the reduction of uncertainty, which is crucial for streamlined power generation and use. This work aims to forecast wind and solar power generation of several stations for the Western region of India using the recent data collected from the Western Region Load Dispatch center (WRLDC) using the Long Short-Term Memory (LSTM) network. The concept of Wind Power Density (WPD) and target encoding was introduced as features in the model. Furthermore, this research offers promising results on the recent data and aims to send potential researchers in the power systems field, the right way.

关键词： Wind energy generation Renewable energy sources Power system measurements Uncertainty Greenhouse effect Wind power generation Solar power generation

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Islanding Detection Scheme For Grid-tied PV Microgrid

A Hybrid Islanding Detection Scheme For Grid-tied PV Microgr...

引用

IEEE India Conference (INDICON)

作者： Vishal Dixit Manav Jadhwani Abhishek Pandey Faruk Kazi Centre of Excellence (CoE) in Complex and Nonlinear Dynamical Systems (CNDS) VJTI Mumbai India

ISBN: (纸本)9781665441766

The use of distributed generation and the future ubiquity of microgrids have raised concerns about their protection, particularly islanding detection. Traditional passive islanding methods are not flexible enough to detect islanding in inverter-fed systems. This paper presents a hybrid island detection scheme that is more efficient and faster than passive island detection schemes used in isolation. The method is based on a combinatorial strategy of merging different passive schemes in effort to minimize detection time and the non detection zone (NDZ). This approach is simple to deploy and can adapt to any existing microgrid system. A simple form of this adaptable concept has been implemented and validated on a photovoltaic (PV) array-based microgrid model in MATLAB/Simulink. The obtained results demonstrate the proposed islanding detection technique’s efficacy.

关键词： Photovoltaic systems Islanding Merging Microgrids Mathematical models Hardware Relays

来源：评论

学校读者我要写书评

暂无评论

Twitter bot detection and their influence in hashtag manipulation

Twitter bot detection and their influence in hashtag manipul...

引用

IEEE India Conference (INDICON)

作者： Sanket Barhate Ritika Mangla Dhwani Panjwani Suyash Gatkal Faruk Kazi Centre of Excellence in Complex and Nonlinear Dynamical Systems VJTI Mumbai India

ISBN: (数字)9781728169163

ISBN: (纸本)9781728169170

Twitter is an important platform for many activities such as communication, promotion and news. Twitter is starting to clamp down on removing content and accounts whose sole purpose is to spread disinformation at scale. The increasing number of bots on Twitter has led to a significant circulation of malicious content. It has the power of manipulating and influencing people negatively. Hence bot detection and finding their extent of influence is of prime importance. This research has used varied approaches for the detection of bots; a supervised machine learning approach which makes use of a unique feature called the bot score to determine the bot probability of a user. Secondly, using an unsupervised machine learning approach, users were divided into various clusters based on their activity. Furthermore, to assess the influence of users in hashtag manipulation, this research analyzed various categories of users in a hashtag and made promising conclusions.

关键词： Social networking (online) Blogs Machine learning Forestry Media Feature extraction Information integrity

来源：评论

学校读者我要写书评

暂无评论

Explainability of SMOTE Based Oversampling for Imbalanced Dataset Problems

Explainability of SMOTE Based Oversampling for Imbalanced Da...

引用

International Conference on Information and Computer Technologies (ICICT)

作者： Aum Patil Aman Framewala Faruk Kazi Centre of Excellence in Complex & Nonlinear Dynamical Systems VJTI Mumbai India

ISBN: (数字)9781728172835

ISBN: (纸本)9781728172842

Since the advent of Artificial Intelligence (AI), the problem of imbalanced datasets and the lack of interpretability of complex AI models has been a matter of concern for the research community. These datasets contain a very low proportion of one class (minority class) and very large proportion of another class (majority class). Even though the quantitative representation is less for minority class they have high qualitative importance as the cost associated in case of misclassification in these domains is very high. The paper presents a novel solution to deal with the issue of imbalanced dataset by using the proven method of resampling Synthetic Minority Oversampling Technique (SMOTE). Further, the interpretability of such an approach is demonstrated by some powerful eXplainable AI (XAI) techniques such as LRP, SHAP and LIME. In this paper state-of-art models like Deep Learning and Boosting classifiers were trained to classify fraud instances with high accuracy and proved to be reliable by producing explanations for their predicted instances. The results of confusion matrices and explanations showcase excellent performance and reliability of the models.

关键词： Erbium Hafnium Computer science Machine learning Biological system modeling ITU

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：