检索结果-内蒙古大学图书馆

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Chempavathy., B. Prabhu, S. Nagendra Varshitha, D.R. Vinita Lokeswari, Yaratapalli New Horizon College of Engineering Department of Cse Bengaluru India Srm Institute of Science Technology Kattankulathur School of Computing Department of Computational Intelligence Chennai603203 India

ISBN: (纸本)9781665400527

The present era of technology had a tremendous influence on society. With the advancements in the artificial intelligence and machine learning domains, machines are trying to impersonate humans. Chabot's are gaining popularity in this aspect and have changed the patterns of conversations between humans and computers. With the creation of these virtual assistants, the conversational services have been improvised. Basically, a Chabot is a software program programmed to interact with humans using artificial intelligence in messaging platforms. Nowadays, Chabot's are not just restricted to one field, they can be used in numerous fields in different forms. The Chabot introduced in this paper mainly concerns itself with college activities. College campuses are vast in the area. If a particular person has a query about which he wants to inquire, the individual would have to shuttle from here and there in order to gather the information for the query. So, the main intention of this research is to develop a college friendly chatterbot sooner or later, servicing the scholars. The tools used are artificial intelligence, such as natural language input and deep learning methods like deep neural networks. This uses LSTM, an extension of RNN, in order to process the user input. It trains the Chabot using these techniques and gives a response. All the data of the Chabot, which is the input given by the human, will be stored in a database and the data will be saved every time a query is asked for future use. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fine-grained sentiment analysis using neural networks to identify guest preferences based on online reviews 1

Fine-grained sentiment analysis using neural networks to ide...

引用

1st International Conference on Computer, Power and Communications, ICCPC 2022

作者： Rosewelt, L. Antony Kovarasan, Rajesh Kambattan Ponmalar, Sridevi P. Computer Science and Engineering Sri Sai Ram Institute of Technology Chennai India Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Chennai India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Chennai India

ISBN: (纸本)9798350397840

Online reviews are a sort of user-generated content that sway not only prospective guests' reservation decisions but also provide timely feedback to hotels on how to enhance their service offerings in response to guest feedback. Customer preferences can be inferred from online hotel evaluations by analysing the reviews for subtle indications of approval or disapproval of specific features. Sentiment component extraction, feature pair identification (FPI), and sentiment orientation analysis are all basic activities in fine-grained sentiment analysis. Yet, current fine-grained sentiment analysis techniques fail to identify FPIs reliably, particularly when dealing with review evaluations. To boost the efficiency of FPI detection, we develop a new convolutional neural network (i.e., CNN) model that can fully exploit unstructured and structured information. In addition, we present a modified fine-grained sentiment analysis methodology that integrates a term clustering algorithm for 'aspect terms' to determine a correct 'customer sentiment intensity value' for each evaluated aspect, rather than a simple 'positive' or 'negative' rating. At last, we undertake an empirical analysis of hotel web reviews to demonstrate the rationality and benefits of the suggested methodology. The empirical findings show that our suggested method can effectively identify consumer preferences from online evaluations of hotels and can enhance the effectiveness of FPI identification. Furthermore, we discover that different sorts of clients have distinct tastes in the amenities offered by hotels. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks

arXiv

引用

arXiv 2025年

作者： Buehler, Markus J. Laboratory for Atomistic and Molecular Mechanics Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology CambridgeMA02139 United States

We present an agentic, autonomous graph expansion framework that iteratively structures and refines knowledge in situ. Unlike conventional knowledge graph construction methods relying on static extraction or single-pass learning, our approach couples a reasoning-native large language model with a continually updated graph representation. At each step, the system actively generates new concepts and relationships, merges them into a global graph, and formulates subsequent prompts based on its evolving structure. Through this feedback-driven loop, the model organizes information into a scale-free network characterized by hub formation, stable modularity, and bridging nodes that link disparate knowledge clusters. Over hundreds of iterations, new nodes and edges continue to appear without saturating, while centrality measures and shortest path distributions evolve to yield increasingly distributed connectivity. Our analysis reveals emergent patterns—such as the rise of highly connected "hub" concepts and the shifting influence of "bridge" nodes—indicating that agentic, self-reinforcing graph construction can yield open-ended, coherent knowledge structures. Applied to materials design problems, we present compositional reasoning experiments by extracting node-specific and synergy-level principles to foster genuinely novel knowledge synthesis, yielding cross-domain ideas that transcend rote summarization and strengthen the framework’s potential for open-ended scientific discovery. We discuss other applications in scientific discovery and outline future directions for enhancing scalability and interpretability. © 2025, CC BY-NC-ND.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Water Quality Analysis Using Machine Learning Techniques 2nd

Water Quality Analysis Using Machine Learning Techniques

引用

2nd International Conference on Deep sciences for computing and Communications, IconDeepCom 2023

作者： Kumar, M. Gobinath, T. Karthikeyan, M. Saravana Arun, C. Chettinad College of Engineering and Technology NH 67 Karur-Trichy Higways Puliyur CF Po Tamilnadu Karur639114 India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Tamilnadu Chennai India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Tamilnadu Chennai India

ISBN: (纸本)9783031689048

The most crucial resource that must be preserved by humans is water. Due to numerous environmental and societal causes, the quality of the water is deteriorating day by day. In order to take remedial action in the best way possible, it is essential to regularly evaluate the quality of the water we consume. The purpose of this study is to use supervised machine learning techniques to examine the quality of water. Many supervised machine learning methods are employed in these applications. The relationship between the features and their related labels, the size of the datasets, and the applications all affect how well the machine learning technique performs. This study considers the K Nearest Neighbor method, Support Vector Machine algorithm, Logistic Regression technique, and Random Forest Classifier algorithm when evaluating the water quality. The Random Forest method performs better in terms of training and testing accuracy than other algorithms among the several supervised machine learning approaches used in our work. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Precise Analysis of Covariance Identifiability for Activity Detection in Grant-Free Random Access

arXiv

引用

arXiv 2024年

作者： Luo, Shengsong Ma, Junjie Xu, Chongbin Wang, Xin the Department of Communication Science and Engineering Fudan University Shanghai200433 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

We consider the identifiability issue of maximum-likelihood based activity detection in massive MIMO-based grant-free random access. An intriguing observation by Chen et al. [1] indicates that the identifiability undergoes a phase transition for commonly-used random user signatures as L2, N and K tend to infinity with fixed ratios, where L, N and K denote the user signature length, the total number of users, and the number of active users, respectively. In this letter, we provide a precise analytical characterization of the phase transition based on a spectral universality conjecture. Numerical results demonstrate excellent agreement between our theoretical predictions and the empirical phase transitions. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

Prediction of Rental Demands using different Machine Learning Algorithms

Prediction of Rental Demands using different Machine Learnin...

引用

2023 International Conference on Computer Communication and Informatics, ICCCI 2023

作者： Ravikumar, S. Vijay, K. Pavithra, S. Prithi, S. Kannan, Sriram Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineeirng Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India VIT University School of Computer Science and Engineering Chennai India SRM IST School of Computing Department of Computational Intelligence Kattankulathur India Sri Sivasubramaniya Nadar College of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350348217

A Bike rental expectation conjectures the interest for bikes rentals in reliance of climate conditions like the temperature and calendric data. In bike rental frameworks, it is vital that the managers have to realize the number of bikes to be placed in each and every station. This include empowers them in or-ganizing the necessary number of bikes at each station and choose whether a specific station needs to have additional number of bikes or it is not re-quired. In this venture we will foresee the no of bikes required for explicit climate and climatic conditions. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Dermoscopy Textures with an Ensemble Feedback of Multilayer Perceptron 1st

Classification of Dermoscopy Textures with an Ensemble Feedb...

引用

1st International Conference on Deep sciences for computing and Communications, IconDeepCom 2022

作者： Prabhu Chakkaravarthy, A. Saravanan, T.R. Udayakumar, Sridhar Subasini, C.A. Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Campus Chennai India Department of Information Technology Mettu University Mettu Ethiopia St. Joseph’s Institute of Technology Old Mamallapuram Road Chennai India

ISBN: (纸本)9783031276217

Aim: To build a perfection classification of skin cancer dataset in the form of textured parameters. The input images are taken from ISIC 2019 dataset. The images are converted into textures like contrast, homogeneity, energy and correlation using GLCM feature extraction. Materials and method: Multilayer perceptron’s, or MLPs, can approximate any continuous function with a single hidden layer. They can be used in supervised learning to model the correlation of inputs and outputs between pairs of inputs and outputs. To optimize performance, models are trained to minimize error by adjusting their parameters, or weights and biases. Result: The input classification elements like contrast, correlation, energy and homogeneity are taken for classification, the initial with normal Multi-layer perceptron classification generates the sample input of 65.5% but the object is carried over ensemble classification again with Multi-layer perceptron generates 93.5% classification accuracy. Conclusion: On comparing the outcomes from the normal classification and the ensemble classification with Multi-Layer Perceptron, the ensemble model generates the maximum classification accuracy without breaking the sample of classification dataset. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Video Streaming Web Application with AI Botsusing NLP

Deep Learning Video Streaming Web Application with AI Botsus...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： P. Sridevi Ponmalar Shivam Singh Rahul Kumar Agrahari Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India

In this digital age, online learning has become increasingly prevalent, but learners often struggle with asking questions and getting immediate clarification. To address this issue, this research paper proposes a solution in the form of a web application that uses deep learning, AI bots, and NLP to generate keywords and provide real-time responses to user queries during video playback. The title of the paper is "Deep Learning Video Streaming Web Application with AI Bots using NLP". It highlights the application's key features and technologies used, including deep learning, AI bots, and natural language processing (NLP). The problem addressed in this paper is the difficulty learners face when seeking real-time answers to their questions during online video tutorials. The proposed solution aims to address this issue by providing a platform that allows users to add questions and answers to a database, which can then be accessed during video playback. The solution presented in this paper uses a combination of deep learning, AI bots, and NLP to generate relevant keywords and provide real-time responses to user queries. The paper outlines the methodology used to develop the application and discusses the results obtained from testing the platform. The analysis output shows that the proposed solution can effectively address the issue of real-time question answering during online video tutorials. The application's use of deep learning, AI bots, and NLP allows for a more personalized and interactive learning experience. The merits of this work lie in the potential to revolutionize the online learning experience by enabling learners to ask questions and get immediate answers. Possible applications of this research include the development of similar web applications for other domains, such as customer service or technical support. Additionally, the findings of this study may inspire further research on the use of deep learning, AI bots, and NLP in online learning and other fiel

关键词：

来源：评论

学校读者我要写书评

暂无评论

Salt Deposits Identification Using Enhanced U-net-based Mixed Attention Loss Function for Semantic Segmentation 2

Salt Deposits Identification Using Enhanced U-net-based Mixe...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Anitha, D. Al-Attabi, Kassem Priyanka, M.S. Soujanya, Thota Bhuvaneshwarri, I. Srm Institute Of Science And Technology School Of Computing Department Of Computational Intelligence Tamilnadu Kattankulathur India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute Of Technology Department Of AI-ML Bengaluru India Sr University School Of Agricultural Sciences Telangana Warangal India Government College Of Engineering Department Of Information Technology Tamil Nadu Erode India

ISBN: (纸本)9798350381665

Numerous areas of Earth's surface with huge accumulations of oil and gas have high salt deposits under surface. Determining such deposits assists several countries in enhancing the storage capacity of petroleum reserves and exploring new ones. However, determining such a deposit is challenging because expert seismic images need human interpretation of salt bodies, which causes biased and greatly variable translations. This research proposes the Enhanced U-net with Mixed Attention Loss Function (EU-net-based MALF) to automatically and accurately identify whether or not the seismic images have salt deposit regions. Initially, the images are gathered from Tomlinson Geophysical Services (TGS) dataset to evaluate the model performance. Then, the nearest neighbor interpolation method and min-max normalization are employed for image resizing and normalizing. At last, the EU-net-MALF is performed for semantic segmentation. The EU-net-MALF achieves a better accuracy of 98.26% compared to existing methods like fully convolutional DenseNet, U-Net and deep supervision, and Interactive Salt Segmentation based on Convolutional Neural Network and GraphCut (SaltISCG). © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Quantum Teleportation and EntanglementBased Quantum Blind Signature Protocol for Quantum Secure Communication in Security Service Bases 23

Quantum Teleportation and EntanglementBased Quantum Blind Si...

引用

Proceedings of the 5th International Conference on Information Management & Machine Intelligence

作者： Sumathy G Suresh A Udendhran R Maheshwari A Arun Prasath Selvaraj Department of Computational Intelligence SRM Institute of Science and Technology India Networking and Communications SRM Institute of Science and Technology India Department of Computational Intelligence SRM IST India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology India

ISBN: (纸本)9798400709418

Quantum teleportation and entanglement-based quantum blind signature protocol were promising new technologies for secure communication between security service bases. They were secure against a variety of attacks, including eavesdropping, signatory disavowal, verifier denial, and forgery. The protocol worked by using quantum entanglement to create a shared secret state between the security service bases. This shared secret state was then used to generate a quantum signature for each message sent between the bases. The signature was then verified by the receiving base using the shared secret state. Compared to classical blind signature schemes, the main advantages of the quantum entanglement-based quantum blind signature protocol were its information-theoretic security and reduced complexity and noise. However, this protocol also faced some challenges, such as preparing and storing entangled states, performing quantum operations and measurements, and ensuring the trustworthiness of the third party. Despite these challenges, the quantum entanglement-based quantum blind signature protocol was a promising new technology for secure communication between security service like military bases. It had the potential to revolutionize the way that military bases communicated with each other, making it possible to send secure messages without revealing the content or identity of the messages.

关键词：

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：