检索结果-内蒙古大学图书馆

2nd International Conference on Augmented Intelligence and Sustainable Systems, ICAISS 2023

作者： Mayuranathan, M. Akilandasowmya, G. Jayaram, B. Velrani, K. Sundara Kumar, M Jogendra Vidhya, R.G. Srm Valliammai Engineering College Department of Computer Science Engineering India Sri Sairam Institute of Technology Department of Computer Communication and Engineering India Rmk Engineering College Department: Computer Science and Business Systems Tamilnadu Gummidipoondi Taluk Tiruvallur District Kavaraipettai India School of Computing Sathyabama Institute of Technology Information Technology India Koneru Lakshmaiah Education Foundation Department of Cse AP Vaddeswaram India Hkbk College of Engineering Department of Ece Bangalore India

ISBN: (纸本)9798350325799

Recently, AI and NLP have been used to improve customer care. Customer support relies on event extraction and relevant data. In customer support applications, AI-based algorithms extract events. Event extraction identifies and extracts specific events or activities from textual data like customer service chats, emails, and social media interactions. Customer support teams may discover issues, trends, and improve the customer experience by automatically extracting events. Customer support event extraction can be done using AI-based models. Event extraction relies on named entity recognition (NER), sentiment analysis, and text classification. NER classifies customer names, product names, and problem keywords. Text classification classifies client issues into preset categories like billing, technical support, or product feedback, while sentiment analysis assesses the customer's emotional tone. Event extraction AI models use machine learning algorithms. Support vector machines (SVM) and random forests can be trained on annotated customer support data to reliably classify events. Recurrent neural networks (RNNs) and transformers can capture complicated patterns in textual data, making them promising event extraction methods. Customer support applications benefit from AI-based event extraction algorithms. It frees up support teams to focus on client issues by automating evaluation and categorization. It also helps firms identify emerging trends and enhance their products and services to answer client complaints. AI-based customer support event extraction models face hurdles. Labeled training data is costly and time-consuming to obtain. Ensuring model generalizability across multiple domains or languages is ongoing research. In conclusion, AI-based event extraction in customer support systems can improve customer experiences and support team efficiency. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Semantic Analysis Using Deep Learning for Predicting Stock Trends

引用

Procedia Computer Science 2024年 235卷 820-829页

作者： Manisha Galphade V.B. Nikam Dhanalekshmi Yedurkar Prabhishek Singh Thompson Stephan Department of Computer Science & Engineering School of Computing MIT Art Design & Technology University Pune India Department of Computer Engineering & IT Veermata Jijabai Technological Institute Mumbai India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India

Company Investors and financial professionals mostly rely on quarterly reports to help them decide the ways to invest in stocks and assess the company's current performance. Quarterly company reports offer an abstracted perspective of the company's overall past performance, as well as its present situation and the market value of its market share. Financial text streams in quarterly report are unstructured naturally, but they represent cooperative expressions that are of important in any financial decision for stake holder. It will be both daunting and necessary to procedure intelligence of unstructured textual data. In this study, we address important queries related with the explosion of interest in a method to extract useful information from unstructured data and the way to work out if such insight provides any hints regarding the trends of financial markets. There is a lack of availability in the labeled dataset for financial sentiment analysis applications. The pre-trained language model employs very little labeled parameters that is used for a variety of domain specific corpora including financial sentiment analysis. In this paper, FinBERT, a model built on the BERT framework, to address linguistics challenges in the financial domain. The proposed work uses twelve transformer layers and twelve attention layers with several million parameters. The design of encoder and decoder comprises of several attention layers along with RNN. This arrangement aids to recognize instances processing the strongest relation between the words within a particular sentence. The experimentation results shows that the presented method surpass the state-of-the-art methods for financial datasets. The results are also compared with other existing models using the same financial dataset. It is observed that the FinBERT attains an accuracy of 84.77% on quarterly reports despite using a lesser training set.

关键词： Deep learning emotion mining financial analysts investors sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

DropDim: A Regularization Method for Transformer Networks

arXiv

引用

arXiv 2023年

作者： Zhang, Hao Qu, Dan Shao, Keji Yang, Xukui The School of the Information Engineering University Zhengzhou450000 China Jiangnan Institute of Computing Technology China

We introduce DropDim, a structured dropout method designed for regularizing the self-attention mechanism, which is a key component of the transformer. In contrast to the general dropout method, which randomly drops neurons, DropDim drops part of the embedding dimensions. In this way, the semantic information can be completely discarded. Thus, the excessive co-adapting between different embedding dimensions can be broken, and the self-attention is forced to encode meaningful features with a certain number of embedding dimensions erased. Experiments on a wide range of tasks executed on the MUST-C English-Germany dataset show that DropDim can effectively improve model performance, reduce over-fitting, and show complementary effects with other regularization methods. When combined with label smoothing, the WER can be reduced from 19.1% to 15.1% on the ASR task, and the BLEU value can be increased from 26.90 to 28.38 on the MT task. On the ST task, the model can reach a BLEU score of 22.99, an increase by 1.86 BLEU points compared to the strong baseline. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Interpretation of the Challenges and Solutions for Agriculture-based Supply Chain Management using Blockchain and IoT

An Interpretation of the Challenges and Solutions for Agricu...

引用

International Conference on computing Methodologies and Communication (ICCMC)

作者： M. Surya S. Manohar Department of Computer Science and Engineering School of Computing SRM Institute of Science and Technology Tamilnadu India

Healthcare, the smart grid, and supply chain management are some of the industries where IoI(Internet of Things) technology is improving. Also, it improves the way humans communicate with each other, the atmosphere, and the people around them. Internet of things achieves this by using wearable technology, embedded sensors, and automated systems. The number, types, and sizes of IoT devices are increasing. There are issues with security, authenticity, reliability, and scalability. Because of the expected growth in IoT, IoT systems must be reliable and maintainable. Blockchain has helped solve IoT network problems. Blockchain improves trust, immutability, transparency, and release of agricultural data collection, processing, and sharing. Blockchain and IOT will streamline precision farming and transform normal farms into the Internet of Smart Farms. This study describes the IoT systems have issues, and blockchain-based solutions are suggested. Additionally, it discusses current research on the degree to which blockchain technology and Internet of Things networks. IoT integration inside the blockchain issues are also covered. This article proposes to double connect IoT and blockchain using recent computing techniques. This research work intends to make data processing and storage decentralized, secure and anonymous, and seamless and fast using blockchain technology and services.

关键词： Smart agriculture Supply chain management Costs Supply chains Transforms Blockchains Smart grids

来源：评论

学校读者我要写书评

暂无评论

Application of Explicit Group Sparse Projection in Optimizing 5G Network Resource Allocation and Topology Design 4

Application of Explicit Group Sparse Projection in Optimizin...

引用

4th IEEE Asian Conference on Innovation in technology, ASIANCON 2024

作者： Manukonda, Kodanda Rami Reddy Swamy, Hemanth Sankar, R. Chidambaranathan, C.M. Haribabu, K. Saranya, K. Ibm Department of Consulting India Motorola Solutions India Chennai Institute of Technology Department of Eee Kundrathur Chennai India School of Computing Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Mlr Institute of Technology Department of Ece Dundigal Hyderabad India Dhanalakshmi College of Engineering Department of Ai & Ds Tambaram Chennai India

ISBN: (纸本)9798350354218

The growing adoption of 5G networks in diverse domains like IoT, smart cities, healthcare, and industrial automation necessitates advanced optimization techniques. While existing approaches have shown promise, they are often limited by computational intensity, lack of adaptability, and specific focus on geometric constraints. This paper presents EGSP-5G, a novel methodology employing Explicit Group Sparse Projection (EGSP) for 5G network resource allocation and topology design. Its capability to achieve targeted sparsity levels allows for efficient utilization of network resources, thereby making it a versatile and powerful tool for various optimization tasks. Remarkably, EGSP-5G achieved a resource utilization rate of 90.02% and a throughput of 110.32 in networks comprising 1000 nodes. It stands as a robust and versatile solution for optimizing 5G networks across diverse application domains. © 2024 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

What Affects the Adoption of Metaverse in Education? A SEM-based Approach 20

What Affects the Adoption of Metaverse in Education? A SEM-b...

引用

20th International Joint Conference on Computer Science and Software engineering, JCSSE 2023

作者： Rohan, Rohani Roy, Pranab Vanijja, Vajirasak Funilkul, Suree Mukherjee, Subhodeep Pal, Debajyoti School of Information Technology King Mongkut's University of Technology Thonburi Bangkok Thailand Jk Laxmipat University Department of Computer Science and Engineering Jaipur India Department of Operations Management Visakhapatnam India Kmutt Innovative Cognitive Computing Research Center Bangkok Thailand

ISBN: (纸本)9798350300505

Metaverse is an emerging 3D digital space that augments the real world and the virtual world. It has been envisioned to be the trendsetter for future education having tremendous potential. However, the success of any new technology depends on its mass adoption and widespread societal diffusion. Therefore, it becomes important to understand the factors that can lead to its success by ensuring widespread adoption. In this work, we investigate the different psychological gratifications of the educational usage of Metaverse under the lens of the Uses and Gratification (UGT) theory. Particularly, we propose and test a research model by using the Structural Equation Modelling (SEM) approach by considering four fundamental psychological gratifications of autonomy, achievement, affiliation, and dominance, together with two additional factors of hedonic motivation and student personality. Data is collected from two Asian universities, and results show the importance of autonomy, hedonic motivation, and personality in predicting Metaverse adoption. © 2023 IEEE.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

MMCo-Clus - An Evolutionary Co-clustering Algorithm for Gene Selection (Extended abstract) 39

MMCo-Clus - An Evolutionary Co-clustering Algorithm for Gene...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Cui, Laizhong Acharya, Sudipta Mishra, Sumit Pan, Yi Huang, Joshua Zhexue Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Queen's University School of Computing ON Canada Indian Institute of Information Technology Department of Cse Assam Guwahati India Chinese Academy of Sciences Shenzhen Institute of Advanced Technology China

ISBN: (纸本)9798350322279

Dimensionality reduction through feature selection becomes inevitable to overcome the problem of the Curse of dimensionality. In this article, we propose a feature (gene) selection method for high dimensional gene expression (GE) data through a Multi-objective optimization-based Multi-view Co-Clustering algorithm (named MMCo-Clus). A thorough comparative analysis with existing feature selection algorithms using external/internal evaluation metrics supports our proposed method's potency. © 2023 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics

arXiv

引用

arXiv 2024年

作者： Wang, Jiahao Yang, Sikun Koeppl, Heinz Cheng, Xiuzhen Hu, Pengfei Zhang, Guoming School of Computer Science and Technology Shandong University China School of Computing and Information Technology Great Bay University China Department of Electrical Engineering and Information Technology Technische Universität Darmstadt Germany

Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are especially suitable for dealing with noisy and incomplete count data. Among these models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still fails to capture the time-varying transition dynamics that are commonly observed in real-world count time sequences. To mitigate this gap, a non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time, and the evolving transition matrices are modeled by sophisticatedly-designed Dirichlet Markov chains. Leveraging Dirichlet-Multinomial-Beta data augmentation techniques, a fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance due to its capacity to learn non-stationary dependency structure captured by the time-evolving transition matrices. © 2024, CC BY.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Prediction of High Heating Value Using ANN Technique Aftermath Natural Disasters 21

Prediction of High Heating Value Using ANN Technique Afterma...

引用

2024 IEEE/ACS 21st International Conference on Computer Systems and Applications, AICCSA 2024

作者： Thakur, Disha Kumar, Sanjay Sharma, Bhisham Dhaou, Imed Ben UIT Himachal Pradesh University Department of Civil Engineering Shimla India UIT Himachal Pradesh University Department of Electrical Engineering Shimla India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura Centre for Research Impact & Outcome Punjab 140401 India Hekma School of Engineering Computing and Design Dar Al-Hekma University Department of Computer Science Jeddah Saudi Arabia

ISBN: (纸本)9798331518240

Natural disasters, particularly earthquakes and floods, can generate substantial waste, presenting challenges for waste management and energy recovery. This study explores the application of machine learning, specifically Artificial Neural Networks (ANN), to optimize Waste-to-Energy (WTE) conversion processes for disaster-generated Municipal Solid Waste (MSW). Using data from Sundernagar City, India, we constructed and evaluated multiple ANN models (collectively named ANNSNAGAR) to estimate High Heating Value, HHV, based on ultimate/elemental analysis of MSW. The models were rigorously assessed using statistical error metrics. Our best-performing network, with a 9-50-1 architecture (ANNMS), achieved a mean absolute percentage error (MAPE) of 1.47%, demonstrating high predictive accuracy. © 2024 IEEE.

关键词： Artificial Neural Network Energy Energy Content Machine learning Municipal Solid Waste

来源：评论

学校读者我要写书评

暂无评论

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

引用

Computers, Materials & Continua 2024年第1期78卷 1363-1379页

作者： Kwok Tai Chui Brij B.Gupta Varsha Arya Miguel Torres-Ruiz School of Science and Technology Hong Kong Metropolitan UniversityHong Kong999077China Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Center for Advanced Information Technology Kyung Hee UniversitySeoul02447Korea Symbiosis Centre for Information Technology Symbiosis International UniversityPuneMaharashtra411042India Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon School of Computing Skyline University CollegeSharjah1797United Arab Emirates Department of Business Administration Asia UniversityTaichung41354Taiwan Center for Interdisciplinary Research University of Petroleum and Energy StudiesDehradun248007India Department of Computer Science&Engineering Chandigarh UniversityChandigarh160036India Centro de Investigación en Computación Instituto Politécnico NacionalUPALM-ZacatencoMexico City07320Mexico

The visions of Industry 4.0 and 5.0 have reinforced the industrial *** have also made artificial intelligence incorporated as a major *** machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe *** learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two *** response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning *** is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative *** algorithm also adaptively adjusts the portion of training data to balance the learning rate and training *** proposed algorithm is evaluated and analyzed using ten benchmark *** with other algorithms from existing works,SA-ITL improves the accuracy of all *** studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

关键词： Deep learning incremental learning machine fault diagnosis negative transfer transfer learning

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：