检索结果-内蒙古大学图书馆

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Deepak Upadhyay Abhay Upadhyay Mridul Gupta Kunj Bihari Sharma Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

This paper investigates joint power and channel allocation under fading communication channels using Deep Reinforcement Learning (DRL). To this end, we design a DRL to allocate dynamic resources with different network condition properly and achieve the spectral efficiency improvement while reducing latency to meet lower bound in cost function as well keeping target fairness. Results show that our DRL-based approach can achieve better spectrum efficiency and latency than traditional algorithms while at the same time, sustaining a higher value of fairness index. In addition, it is observed that the DRL method also offers both adaptability (with fast adaptation to network changes) and robustness in performance but at a higher computational expense. Our results illustrate that the DRL-based technique may serve as a strong, scalable candidate in future wireless systems up to several orders of magnitude better than existing resource allocation schemes.

关键词： Fading channels Wireless communication Lower bound Spectral efficiency Heuristic algorithms Neural networks Deep reinforcement learning Robustness Resource management Next generation networking

来源：评论

学校读者我要写书评

暂无评论

First-principles density functional calculations for non-lead perovskites 12

First-principles density functional calculations for non-lea...

引用

Physics, Simulation, and Photonic engineering of Photovoltaic Devices XII 2023

作者： Esther, Emily Zhu, Peifen Henshaw, John Dept. of Mechanical Engineering Univ. of Tulsa 800 South Tucker Drive TulsaOK74104 United States Dept. of Electrical Engineering and Computer Science Univ. of Missouri 230 Jesse Hall ColumbiaMO65211 United States

ISBN: (纸本)9781510659377

The possibility of replacing lead in perovskites with other elements in 2D and 3D perovskites is explored. The most highly efficient perovskites are made with an inorganic-organic compound with lead. The influence on band structure, the density of states, and absorption coefficient are explored using first-principals density functional calculations. The advantages and disadvantages of 2D vs. 3D perovskites and their efficiency for energy conversion are also discussed. Ab initio DFT methods were used and implemented using a VASP software package. This research is important because perovskites solar cells are the most efficient solar cells currently studied by researchers, but they are prevented from being introduced to the market due to their instability. Perovskites are unstable and break down when they encounter things that they would commonly encounter during their application including moisture, high UV light, and excessive heat. When the perovskite structure starts to break down, lead is released into the environment. © 2023 SPIE.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Solutions to Predict the Impact of Lung Cancer with an Advanced Intelligent Computing Method 5

Evaluating the Solutions to Predict the Impact of Lung Cance...

引用

5th International Conference on Smart Systems and Inventive Technology, ICSSIT 2023

作者： Sundar, R. Ramadass, Sudhir Meeha, D. Subramanian, Balambigai Shankar, S. Siva Parasa, Gayatri Madanapalle Institute of Technology and Science Dept. of Computer Science and Engineering India Sterck Systems Chennai India Dr. Rangarajan Dr. Sakunthala Engg College Vel Tech Multi Tech Dept. of Information Technology Avadi Chennai India Dept. of Ece Kongu Engineering College Perundurai India Kg Reddy College of Engineering and Technology Dept. of Cse -AIandML Telangana Chilukuru India Koneru Lakshmaiah Education Foundation Dept. of Cse Vaddeswaram Andhra Pradesh Guntur India

ISBN: (纸本)9781665474672

Using symptoms as a basis for diagnosing lung cancer, Lung cancer detection was accomplished using several different machine-learning regression strategies. By comparing the efficacy of several regression algorithms for predicting lung cancer, considering factors including age, gender, chest discomfort, shortness of breath, alcohol intake, chronic illness, trouble swallowing, anxiety, and peer pressure. Lung cancer predictions and evaluations are made using regression methods such as the linear algorithm, polynomial regression, logistic regression, logarithmic regression, and multiple regression. With a predictive accuracy of 96%, multiple regression is superior to other regression techniques when identifying future lung cancer cases. The r-squared value, which can be calculated using several regression machine learning approaches, may also be used to evaluate the association between the various symptoms and lung cancer. Lung cancer is diagnosed using the r-squared value, which is calculated using several algorithms and takes into symptoms, including chronic illness. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Data Mining and AI Approaches for Early Detection and Management of Gastrointestinal Disorders 3

Data Mining and AI Approaches for Early Detection and Manage...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Natrayan, L. Ali, H. Mohammed Kaliappan, S. Kumar, Bura Vijay Saveetha School of Engineering Simats Dept. of Mechanical Engineering TN Chennai India Srm Institute of Science and Technology- Ramapuram Dept. of Mechanical Engineering TN Chennai India Lovely Professional University Division of Research and Development Punjab Phagwara India School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India

ISBN: (纸本)9798350343274

This study presents an innovative integration of Data Mining and Artificial Intelligence (AI) to advance early detection and management of gastrointestinal disorders. The methodology encompasses data preprocessing, feature selection, model development, and continuous monitoring for timely intervention. Preprocessing involves standardization and normalization to ensure consistent feature scaling and distribution. Addressing missing values and outliers is achieved using suitable methods such as mean imputation and robust statistical techniques. Feature selection methods, including Recursive Feature Elimination (RFE) and Principal Component Analysis (PCA), aid in identifying the most informative features associated with gastrointestinal disorders. Support Vector Machines (SVM) excels in binary classification, distinguishing healthy individuals from those with gastrointestinal disorders. Deep Neural Network (DNN) is employed for non-linear feature representation and classification. In conclusion, the proposed method showcased superior performance in critical parameters when compared to traditional methodologies. Its enhanced accuracy, sensitivity, specificity, and computational efficiency position it as a promising approach in the domain of Data Mining and AI for early detection and management of gastrointestinal disorders. This innovation holds potential for significant advancements, promising improved healthcare outcomes and better lives for individuals suffering from gastrointestinal disorders. © 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

PRAGyan - Connecting the Dots in Tweets

arXiv

引用

arXiv 2024年

作者： Ravi, Rahul Ginde, Gouri Rokne, Jon Dept. of Computer Science University of Calgary Canada Dept. of Electrical and Software Engineering University of Calgary Canada

As social media platforms grow, understanding the underlying reasons behind events and statements becomes crucial for businesses, policymakers, and researchers. This research explores the integration of Knowledge Graphs (KGs) with Large Language Models (LLMs) to perform causal analysis of tweets dataset. The LLM aided analysis techniques often lack dept. in uncovering the causes driving observed effects. By leveraging KGs and LLMs, which encode rich semantic relationships and temporal information, this study aims to uncover the complex interplay of factors influencing causal dynamics and compare the results obtained using GPT-3.5 Turbo. We employ a Retrieval-Augmented Generation (RAG) model, utilizing a KG stored in a Neo4j (a.k.a PRAGyan) data format, to retrieve relevant context for causal reasoning. Our approach demonstrates that the KG-enhanced LLM RAG can provide improved results when compared to the baseline LLM (GPT-3.5 Turbo) model as the source corpus increases in size. Our qualitative analysis highlights the advantages of combining KGs with LLMs for improved interpretability and actionable insights, facilitating informed decision-making across various domains. Whereas, quantitative analysis using metrics such as BLEU and cosine similarity show that our approach outperforms the baseline by 10%. © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Utilization of MFCC in Conjuction with Elaborated LSTM Architechtures for the Amplification of Lexical Descrimination in Acoustic Milieus Characterized by Pronounced Nocturnal Disturbance

Utilization of MFCC in Conjuction with Elaborated LSTM Archi...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Deepak Upadhyay Sonal Malhotra Ramesh Singh Rawat Mridul Gupta Somesh Mishra Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India

In this pioneering research endeavor, we delved into the intricate realm of speech recognition technology, aiming to surmount the formidable challenges posed by acoustically complex environments, notably those marred by pronounced nocturnal disturbance. Through the synergistic amalgamation of Mel-frequency cepstral coefficients (MFCC) and meticulously crafted Long Short-Term Memory (LSTM) architectures, we charted a transformative path toward the amplification of lexical discrimination. Our multifaceted approach not only enhanced the discernment of subtle linguistic nuances but also showcased unparalleled efficacy in the face of disruptive nocturnal noise. The meticulously calibrated fusion of advanced signal processing techniques and neural network architectures culminated in a novel paradigm, revolutionizing the landscape of speech recognition technology. By pushing the boundaries of computational linguistics, this study not only advances scientific understanding but also paves the way for real-world applications in domains reliant on precise and resilient speech recognition systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Credit Card Fraud Detection: A Machine Learning Framework

Enhancing Credit Card Fraud Detection: A Machine Learning Fr...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Mohammad Tarek Aziz Md. Maskat Sharif Sha Md Farid Tanjim Mahmud Sapayev Valisher Odilbek Uglu Mohammad Shamsul Arefin Abubokor Hanip Mohammad Shahadat Hossain Dept. of Computer Science and Engineering Dept. of Electronics and Telecommunication Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Department of Technology Wilmington University Delaware United States Dept. of Computer Science and Engineering Rangamati Science and Technology University Rangamati Bangladesh Department of General Professional Subjects Mamun University Khiva Uzbekistan Washington University of Science and Technology (WUST) Alexandria VA USA Dept. of Computer Science and Engineering University of Chittagong Chittagong Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

In the current digital age, credit card tracking is an essential component of financial security. The aim of this study is to use the 1,604,292 data in the Credit Card Transactions Prevention Dataset from Kaggle to create efficient fraud detection algorithms. 1,048,574 records in the dataset are put aside for training, and the remaining records are set aside for testing. Preprocessing techniques like one-hot encoding for classification parameters and label encoding for numbers are used to get the data ready for analysis. The preprocessed dataset is then used to train a variety of machine learning classifiers, such as Random Forest, Decision Tree, Gradient Boosting (GB), and Logistic Regression. The goal is to use binary target properties to identify fraudulent transactions. The Random Forest classifier obtains the highest accuracy, with an astonishing 99.47%, according to the results. Remarkably, the system exhibits infrequent occurrences of data loss, underscoring its resilience and efficiency in identifying fraudulent activity. This study emphasizes how important it is to fight credit card theft by using sophisticated machine-learning strategies and meticulous data pretreatment procedures. The results add to the continuing efforts to improve bank security and shield customers from fraudulent online transactions.

关键词： Training Logistic regression Machine learning algorithms Prevention and mitigation Credit cards Encoding Fraud Random forests Testing Resilience

来源：评论

学校读者我要写书评

暂无评论

Optimizing Satellite Constellations for Global Internet Coverage: A Comparative Analysis of Communication Protocols and Orbital Configuration

Optimizing Satellite Constellations for Global Internet Cove...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Pallab Banerjee Vivek Raj Biresh Kumar Kanika Thakur Dipra Mitra Purushottam Kumar Dept. of Computer Science Engineering Amity University Jharkhand Ranchi Jharkhand India Amity School of Information Technology Amity University Jharkhand Ranchi Jharkhand India Dept. of Computer Science Engineering Galgotia University Greater Noida campus Dept. of Computer Science Engineering Amity University Jharkhand Ranchi India

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

As a way to provide ubiquitous connectivity, satellite constellations are becoming more and more popular due to the growing need for worldwide internet access. In order to provide dependable and seamless worldwide internet coverage, this study investigates how satellite constellations might be optimized by comparing and contrasting communication protocols and orbital topologies. This ambitious aim involves a number of problems and complications, which are explored in the research along with the trade-offs and design considerations that must be made in order for the implementation to be effective. Two main elements form the framework of the comparative analysis. First, by considering factors like latency, data throughput, and coverage efficiency, it evaluates a range of communication protocols, including traditional geostationary satellites, Low Earth Orbit (LEO) constellations, and Medium Earth Orbit (MEO) satellites. Second, to ascertain the effect of various orbital configurations on worldwide internet coverage, the study considers satellite dispersion, orbital altitudes, and coverage patterns. By means of this study, the research endeavors to provide a valuable contribution to the current discussion on satellite constellations for worldwide internet coverage, therefore facilitating well-informed decisions about the design and implementation of these systems.

关键词： Earth Satellite constellations Adaptation models Protocols Uncertainty Low earth orbit satellites Propulsion Throughput Topology Planning

来源：评论

学校读者我要写书评

暂无评论

Blockchain Based Secure and Decentralized Smart Licensing of Charging Vehicles for Rajshahi City Corporation

Blockchain Based Secure and Decentralized Smart Licensing of...

引用

Information and Communication Technology for Sustainable Development (ICICT4SD), International Conference on

作者： Momenul Haque Subrata Kumer Paul Kamrul Islam Mursheda Nusrat Della Rakhi Rani Paul Sultan Fahim Dept. of Computer Science and Engineering Bangladesh Army University of Engineering & Technology Bangladesh Dept. of Computer Science and Engineering University of Rajshahi Rajshahi Bangladesh Dept. of Computer Science and Engineering Rabindra Maitree University Kusbtia Bangladesh Dept. of Information and Communication Engineering Bangladesh Army University of Engineering & Technology Bangladesh

The adoption of charging vehicles in Rajshahi has emerged as a significant step towards reducing air pollution and promoting a healthy, green city. However, the current centralized licensing system poses challenges such as time-consuming processes and the potential for fraudulent activities. To address these issues, this paper proposes the implementation of a secure and decentralized smart licensing system for charging vehicles in Rajshahi City Corporation, leveraging the smart capabilities of blockchain technology. By utilizing Hyperledger Fabric, the implementation generates blockchain based smart contracts that automate and streamline the licensing process smartly and efficiently. This approach ensures the immutability, transparency, and integrity of license records, minimizing the risk of fraud and enhancing overall efficiency. Additionally, the system incorporates the use of QR codes and an inquiry system to enhance the credibility of paper-based licenses. Compared to other digital licenses, this blockchain-based method significantly reduces risks and contributes to the development of a greener and more sustainable Rajshahi city environment. Furthermore, the introduction of a sustainable business policy, utilizing the G2C model, facilitates revenue generation and distribution fairly and equitably for all stakeholders involved in the charging vehicle ecosystem. This implementation not only offers cost benefits and efficiency improvements for drivers but also promotes a sustainable and environmentally friendly city.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approaches to Predict Post Covid-19 Severity: A Detail Case Study

Machine Learning Approaches to Predict Post Covid-19 Severit...

引用

Big Data Analytics in Bioinformatics (DABCon), International Conference on

作者： Richa Mathur Ritam Dutta Payal Bansal Rajeev Kumar Dept. of Computer Scinece & Engineering Poornima University Jaipur Rajasthan India Dept. of Computer Science & Engineering (IoT) Poornima Institute of Engineering & Technology Jaipur Rajasthan India Dept. of Electronics & Comm. Engineering Poornima Institute of Engineering & Technology Jaipur Rajasthan India Dept. of Computer Science & Engineering Moradabad Institute of Technology Moradabad Uttar Pradesh India

ISBN: (数字)9798350378047

ISBN: (纸本)9798350378054

The entire world has witnessed a horrific pandemic in last three years, whose long term and short-term impact to human body has been observed in large scale in these post covid-19 years. Machine learning (ML) techniques have been successfully implemented in medical field since last one decade. The emergence of post covid-19 pandemic symptoms are compelling researchers to re-search for minute detection and predict patient's probable infection rate. Long lasting chest pain, breathing issues, liver and kidney dialysis issues have been apparently visible as post covid-19 symptoms. In this paper, the journals regarding the prediction of covid-19 severity based on symptoms have been discussed. Several researchers have established deep learning-based models for the prediction. They have used the test data from the hospitals for their research process. The KNN models, ANN models, and SVM models have been discussed. The limitations of the past research process have been evaluated to be the biased test data set and missing values. The methodology that was used for the research process has been described. Mixed method of data collection was used for the research processes. The secondary data was collected from reliable sources for this research process. Considerable amount of test data has been retrieved from Kaggle database regarding post covid-19 patient's symptoms. The data analysis is performed on the Weka tool using various machine learning models.

关键词： COVID-19 Support vector machines Pandemics Pain Liver Machine learning Predictive models Nearest neighbor methods Reliability Kidney

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：