检索结果-内蒙古大学图书馆

2025 IEEE International Students' Conference on Electrical, Electronics and Computer science, SCEECS 2025

作者： George, Angelina Beena, B.M. Bengaluru Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science & Engineering India

ISBN: (纸本)9798331529833

Data centers are vital to modern computing but contribute significantly to carbon emissions due to their high energy consumption. To address this, machine learning models can optimize resource allocation by analyzing sensor metrics. In this study, the Random Forest Regressor was chosen for its ability to capture sensor behavior, even showing negative R2 values, aligning with observed patterns. Meanwhile, k-Nearest Neighbors (kNN) emerged as the best model for learning from the same data, despite irregularities, with R2 values ranging between 0.6 and 1. This analysis supports sustainable data center management by enhancing energy efficiency and minimizing environmental impact. Future work will explore the integration of these models into simulation environments. © 2025 IEEE.

关键词： Carbon sequestration

来源：评论

学校读者我要写书评

暂无评论

Advanced Financial Sentiment Analysis using FinBERT to Explore Sentiment Dynamics 3

Advanced Financial Sentiment Analysis using FinBERT to Explo...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Baghavathi Priya, S. Kumar, Madhav Nitheesh Prakash, J.D. Krithika, N. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798331527549

This research investigates the incorporation of sophisticated Natural Language Processing (NLP) methods in the intricate field of finance. In particular, it utilizes FinBERT, a tailored language model created to understand the complex subtleties of financial text data, in conjunction with assessments of DistilBERT and Bidirectional Encoder Representations from Transformers (BERT). The main goal is to create a strong preprocessing framework that improves the interpretative ability of models for sentiment classification designed for financial uses while providing an in-depth evaluation of the comparative performance of the models. Through extensive empirical validation, our approach demonstrates that FinBERT outperforms the other models in accurately capturing subtle sentiment variations and financial terminology. The comparative study underlines the compromises between computational efficiency and precision, with DistilBERT providing a streamlined option. This research emphasizes FinBERT’s transformative capabilities in analyzing financial sentiment and simultaneously delivering essential insights into the comparative strengths and weaknesses of other approaches, presenting a comprehensive viewpoint to inform decision-making within the financial sector. Upon comprehensive analysis of the methods used in this paper, it is shown that FinBERT is best at capturing hidden features within the data and able to work well with unseen data also with an average accuracy of 89.6% over all the 3 classes that are present in the dataset. The suggested framework has the potential to greatly improve predictive analytics and risk management approaches, allowing for more informed, precise, and prompt financial decisions in intricate market conditions. © 2025 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

A Blockchain Based Decentralized Application System for Vanet FDIA Detection 3rd

A Blockchain Based Decentralized Application System for Vane...

引用

3rd International Conference on computing and Communication Networks, ICCCN 2023

作者： Preeti, Grover Sanjeev Kumar, Prasad School of Computing Science and Engineering Galgotias University Uttar Pradesh NCR Greater Noida India

ISBN: (纸本)9789819726707

The growing prominence of intelligent transportation systems (ITS) has led to increased research on vehicular ad hoc networks (VANETs). Blockchain technology offers promising solutions for ensuring data security, integrity, and immutability within VANETs. However, VANETs remain vulnerable to false data injection attacks (FDIAs), which can significantly disrupt network operations and endanger safety. This paper proposes a novel approach using a blockchain-based decentralized application system (Dapp) for FDIA detection in VANETs. The Dapp leverages smart contracts to manage crucial aspects like data provenance, reputation, and consensus mechanisms. It uses POS consensus algorithm to guarantee data consistency and fault tolerance even in the presence of malicious nodes. To manage the vehicular data, users can access the system via Dapp, an Ethereum—distributed application. By integration of blockchain-based IPFS-Dapps system and AI/ML/big data model with blockchain are aim of the research article for providing the solutions for false data injection attacks (FDIA). We collect the data through Radio Channels, Smart Sensors, Smart Antennas and RSU and than uploaded using Dapp and than we classified nodes from smart contract and finally send it to Ethereum. We used a machine learning SVR algorithm, i.e., vehicular network-based support vector regression (VBSVR) to identify an attacker node. We have written the pseudocode for using IPFS with Ethereum, proposed research methodology includes integration of blockchain and Dapps with smart contract, integration of AI/ML/big data models with blockchain, and integration of ML Oracle under blockchain that are ideal for detection of false injection attacks nodes, and same is logged in IPFS Decentralized Server. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Pattern Recognition in Lung Disease Classification: Leveraging Convolutional Neural Networks that Employs Local Phase Quantization Features 15

Pattern Recognition in Lung Disease Classification: Leveragi...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Sree, M. Ramya Siddhartha, Mettu Reddy, Poli Vamsi Vardhan Singh, Tripty Nair, Rekha R. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India Alliance University Alliance School of Advanced Computing Dept. of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350370249

Lung diseases are wide group of diseases related to the respiratory system, and is ranging from acute infections to chronic disorders with multifactorial causes. Recognition of the lung disease is very crucial in the proper diagnosis, forecasting through prognosis, and remedies. Hence proposed lung disease classification with feature extraction technique. The proposed work carried out feature extraction with Gray-Level Co-occurrence Matrix (GLCM) and Local Phase Quantization (LPQ) combined with Convolutional Neural Network(CNN). The goal is to create a model that reduces diagnostic errors, ensuring more precise early detection and classification of pulmonary disorders. This initiative facilitates the advancement of pulmonary medicine by promoting accurate radiologic imaging, while future directions emphasize integrating medical workflows to enable personalized and timely diagnosis and treatment. Additionally, the ResNet model demonstrates superior performance in hernia detection, achieving a test accuracy of 89.43% for GLCM based feature extraction and Pneumonia detection with 79.20% test accuracy for LPQ based feature extraction. © 2024 IEEE.

关键词： CNNs Deep learning Early detection Feature extraction GLCM Local Phase Quantization Lung disease diagnosis Medical imaging Texture analysis

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection Model for Early Prediction of Metabolic Syndrome 4

A Hybrid Feature Selection Model for Early Prediction of Met...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sreepadh, A.S. Sheshu, P. Reshiha, R.G. Kumar, T Vinay Jeyakumar, Gurusamy Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9798331523923

Metabolic Syndrome (MetS) is a medical condition that increases the risk of cardiovascular diseases, stroke, and type 2 diseases. Some of the symptoms of MetS are high blood pressure, elevated blood sugar, excess body fat, and abnormal cholesterol levels. All these symptoms are interconnected, which has made early diagnosis of MetS critical. In current medical strategies, there is no personalized medication which leads to unfavorable health outcomes and further increased risks. This paper aims to address these challenges by identifying optimal feature subsets required for the early prediction of MetS. To get the optimal features a hybrid model is proposed in this paper. The proposed model utilizes both the filter method and the wrapper method. Firstly, features are selected using the correlation coefficient (CC) method which is a filter method, and then the selected features are further refined using genetic algorithm (GA) which is a wrapper method. This hybrid model increases the prediction accuracy and reduces computational cost. The methodology of the proposed model, its experimental setup, the results obtained, and the inferences gained are presented in this paper. © 2025 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Cross-Language Code Mapping with Transformer Encoder-Decoder Model 8th

Cross-Language Code Mapping with Transformer Encoder-Decode...

引用

8th International Symposium on Intelligent Informatics, ISI 2023

作者： Naik, M. V. Deepak Jayaraman, Swaminathan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9789819721467

In the dynamic field of software development, knowledge of multiple programming languages is increasingly valued. To address the demand for cross-language systems, our research investigates code translation and proposes a new approach using transformer models to map cross-language codes. We draw inspiration from the success of transformer-based neural networks in natural language processing and apply these models to the complex world of programming languages. A central hypothesis is that transformers can effectively translate code between languages, acting as a bridge between programming paradigms. We develop a custom transformer encoder-decoder model for program-to-program translation that is initialized with a dataset containing C++ programs and corresponding codes in Haxe, Kotlin, Python, and Java. The cooperation between the encoder and the decoder allows a smooth translation of the code, which shows considerable adaptability. Through fine-tuning with data from other programming languages like Kotlin and Python, our model extends its translation capabilities. Enabling Haxe as an intermediate language further facilitates translation to target languages like Java. This adaptability, based on a transformer-based architecture, effectively meets the challenges of an ever-evolving programming environment. It should be noted that our approach differs from large language models in terms of programming complexity and capturing OOP design patterns. In addition to translation, our research paves a way for code visualization using tools such as Java interactive visualization environment. "Cross-Language Code Mapping with Transformer Models" marks a significant advance towards automatic code translation in object-oriented programming, enriching developer tool kits and promoting collaboration across language boundaries in software engineering. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

First-principles calculations to study the optical/electronic properties of 2D VS2 with Z doping（Z=N,P,As,F,Cl and Br）

引用

Progress in Natural science:Materials International 2022年第2期32卷 236-241页

作者： Yuanyuan Cui Wei Fan Yujie Ren Guang Yang Yanfeng Gao School of Materials Science and Engineering Shanghai University East China Institute of Computing Technology

Monolayer VS2is expected to be an encouraging candidate for optoelectronic devices owing to its excellent optical/electrical *** this paper,first-principles calculations were conducted to figure out the optical/electrical performance of 2 D VS2doped with Z doping（Z=N,P,As,F,Cl and Br）.The results show that there was a downward trend in formation energies when the doping element ranged from left to right and from bottom to top in the periodictable of ***2became more conductive with N,P and As doping,and transited from the semiconducting to metallic state with F,Cl and Br *** the optical properties,N,P,As and Br doping reduced the reflectivity of pristine VS2in the near-infrared region（0.6 eV-1.6 eV）.Moreover,P,F,Cl and Brdoping reduced the migration energy barrier of Li atoms in VS2,which may help to design the rechargeable Li ion batteries with high rate capability.

关键词： 2D VS2 Doping Diffusion barriers First-principles calculations Optical properties

来源：评论

学校读者我要写书评

暂无评论

Big Data Application in Cancer Classification by Analysis of RNA-seq Gene Expression 3

Big Data Application in Cancer Classification by Analysis of...

引用

3rd IEEE International Conference on Intelligent Technologies, CONIT 2023

作者： Amruth, A. Ramanan, R. Paul, Rhea Vishal, S. Saravanan, S. Amrita School of Computing Dept. of Computer Science and Engineering Bengaluru India Amrita School of Computing Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350338607

Computer science domain has got massive developments in the past decade, especially in the field of Big Data and Artificial Intelligence. Many industries are adopting these technologies to improve their products and services. Healthcare is one such industry which comes across voluminous data. Big Data platform is used to process the data and subsequently AI models can be used for prediction or classification. This paper focuses on proposing a Spark based pipeline to reduce the time required to process the voluminous data. With the aid of this new pipeline, we classify the type of cancer through analysis of RNA-seq gene expression levels. The Spark-based pipeline is run on default standalone mode and on a cluster. The study recorded that the Spark-based pipeline run on cluster mode improved the performance approximately by 11 times (regarding processing costs) when compared to the performance of Python-based pipeline. © 2023 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Designing for Security: A Model for Aged Users’ Mobile Banking Applications in South Africa 3rd

Designing for Security: A Model for Aged Users’ Mobile Bank...

引用

3rd International Conference on Advances in computing Research, ACR 2025

作者： Goronga, Rumbidzai Da Veiga, Adéle Lotriet, Hugo School of Computing College of Science Engineering and Technology University of South Africa Pretoria South Africa

ISBN: (纸本)9783031876462

Aged users face unique challenges as they use mobile banking applications, and financial institutions must adapt and include security in the design of mobile banking applications to cater to the unique needs of this demographic. Aging can result in physical challenges and disabilities that impact the use of mobile banking applications;however, these are not the only factors that could affect the usage of mobile banking applications by aged users. Multiple security factors need to be considered. By segmenting the aged by physical impairments and challenges, mobile banking application design possibilities for the aged are not fully realized. This paper proposes a conceptual model for mobile banking applications for aged users in South Africa. The conceptual model is derived from an analysis of current literature and is founded on the Extended Unified Theory of Acceptance and Use of Technology (UTAUT2), which may provide insights for designing secure mobile banking applications for aged users. A scoping literature review was carried out using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method, which involved the analysis of a total of 15 articles. The review of the existing literature indicated that limited research existed that examined the factors that impact the security of mobile banking applications for aged users in South Africa. Therefore, the conceptualized model could serve as a reference for the investigation of aged users’ perceptions of the security of mobile banking applications, which could inform the design of secure mobile banking applications for aged users. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of an Intelligent Traffic Management System Using Vehicular Networks 3

Design and Simulation of an Intelligent Traffic Management S...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Tapan Datta, P. Lalith Kumar, D. Tanoj, S. Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

In this study, the reasearch is focused on the simulation of vehicular communication networks, especially intelligent traffic systems, to enhance dependability, safety, and optimality in communication. The simulation is performed using the OMNeT++ simulator and is integrated with the Veins framework that uses the IEEE 802.11p protocol for V2V and V2I communications. Importing real-world traffic scenarios into the framework is obtained via the use of SUMO through TraCIScenarioManager. Other features of the framework include the definition of mobility models, dynamic obstacles, and detailed radio propagation modeling. TraCIDemo11p is used for mobility and communication by both RSUs and vehicles with applications in beaconing and channel switching. The whole framework analyzes smart traffic management solutions, providing as much insight into their performance based upon the communication reliability and overall efficiency in vehicular networks. © 2025 IEEE.

关键词： Highway administration

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：