检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data

作者： Nathaniel Huber-Fliflet Jianping Zhang Peter Gronvall Fusheng Wei Philip Spinelli Data & Technology Ankura Consulting Group LLC Washington D.C. USA Construction Disputes & Advisory Ankura Consulting Group LLC New York City USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Text classification is a well-established area of machine learning that involves automatically categorizing text into predefined categories, such as positive or negative in sentiment analysis. It typically involves applying a machine learning algorithm to learn a predictive model from a set of labeled training texts and using the model to classify new texts. Large language models (LLMs) have been successfully applied to various natural language processing tasks, including text classification. There are two main approaches to text classification with LLMs: In-Context learning and Fine-Tuning. In-Context learning involves prompt engineering, allowing the model to learn a new task using only a few demonstration examples, while Fine-Tuning adjusts the model’s parameters with additional labeled data. Retrieval-Augmented Generation (RAG) is a retrieval process that enhances LLM performance by selecting relevant examples. This paper presents our work on utilizing In-Context learning and RAG to identify delay-related statements during the document review process of construction delay disputes. We also report the results of our experiments comparing the accuracy of In-Context learning with that of traditional machine learning algorithms, such as logistic regression and KNN.

关键词： Training Sentiment analysis machine learning algorithms Reviews Text categorization Retrieval augmented generation Predictive models Data models Delays Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

machine learning-Based Big Data Analytics in Smart Cities: A Survey of Current Trends and Future Research Directions

Machine Learning-Based Big Data Analytics in Smart Cities: A...

引用

IEEE/ACM International Symposium on Big Data Computing (BDC)

作者： Mariam Hassan Althabahi Mian Ahmad Jan Bouziane Brik Sebti Foufou Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

ISBN: (数字)9798350367300

ISBN: (纸本)9798350367317

Efficient utilization of Big data in smart cities is crucial for smooth operation of urban environments. machine learning-enabled big data analytics is essential for optimizing city operations, improving resource management, and enhancing the quality of urban life. By leveraging machine learning (ML) algorithms to process and analyze the vast amounts of data generated in smart cities, authorities can gain insights and make real-time data-driven decisions. This article provides a comprehensive survey of how ML techniques are applied to analyze the large volumes of data generated by smart cities to improve urban living. Various ML algorithms, such as supervised, unsupervised, and reinforcement learning (RL) are discussed by highlighting their roles in numerous applications. Moreover, their distinguishing features are examined, enabling the selection of the most suitable algorithms for various applications in smart cities. Finally, the survey explores various challenges and suggests numerous research directions.

关键词： Surveys Differential privacy machine learning algorithms Smart cities Federated learning Urban planning Supervised learning Reinforcement learning Big Data Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing QoS in Urban V2V Communications Through AI: A machine learning Approach in Vehicular Ad-Hoc Networks

Enhancing QoS in Urban V2V Communications Through AI: A Mach...

引用

IEEE Ecuador Technical Chapters Meeting (ETCM)

作者： Mateo Coello Jonathan Loor Ariana Jiménez Leticia Lemus Cárdenas Juan Pablo Astudillo León School of Mathematical and Computational Sciences Yachay Tech University Urcuqui Ecuador Departamento de Fundamentos del Conocimiento Universidad de Guadalajara México Communication Networks and Intelligent Services Research Group (ComNet Innova YT) Yachay Tech University Urcuqui Ecuador

ISBN: (数字)9798350391589

ISBN: (纸本)9798350391596

This study introduces a machine learning-based Quality of Service (QoS) model that significantly enhances Vehicle-to-Vehicle (V2V) communications within urban vehicular networks. To validate our model, we compared its performance against the conventional Enhanced Distributed Channel Access (EDCA) mechanism and a scenario without QoS enhancements. Simulations were conducted in an urban area of Buenos Aires, Argentina. We utilized Open Street Maps (OSM) to provide a realistic geographic foundation, ensuring our simulation environment closely mirrors actual urban settings. SUMO (Simulation of Urban Mobility) was employed to accurately model vehicular movements and interactions, facilitating a dynamic and realistic traffic flow simulation. The ns-3 (Network Simulator 3) was used for the network communication aspects, simulating complex network protocols and interactions with high fidelity. Together, these tools enabled comprehensive testing of the QoS model, highlighting its capacity to improve packet delivery ratio (PDR), reduce end-to-end delays, and enhance received throughput. The results underscore the potential of machine learning to significantly optimize vehicular network communications, paving the way for more efficient and reliable urban transportation systems.

关键词： machine learning algorithms Atmospheric modeling Wireless networks Urban areas Vehicular ad hoc networks Quality of service machine learning Throughput Delays Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Feature Fusion for Malware Traffic Detection Using Image Visualization and Transfer learning

Feature Fusion for Malware Traffic Detection Using Image Vis...

引用

International Conference on Communications and Signal Processing

作者： Sanjeev Kumar Yudhishthira Sapru K Purushottama Rao Cyber Security Technology Division Centre for Development of Advanced Computing Mohali India Indian Computer Emergency Response Team CERT-In Delhi India Department of Computer Applications NIT Tiruchirappalli Tamil Nadu India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

Malware threats have become increasingly sophisticated and more complex, making detecting and preventing them difficult. Traditional malware detection methods, such as signature-based detection, are no longer effective against new malware variants. Deep learning, especially convolution neural networks, has evolved significantly as end-to-end malware detection without much requirement of domain expert analysis for feature engineering. This research paper proposes a new image visualization-based malware detection and classification using transfer learning and machine learning classifiers. At first, the network traffic dumps (PCAPs) are transformed into grayscale images. After that, pre-trained CNN models, including VGG16, VGG19, EfficientNetB0, EfficientNetB1, and Xception, are customized to extract the textural features via transfer learning by adding a fully connected layer of different dimensions. Feature fusion is performed by stacking the extracted feature maps from different pre-trained models to form a single feature map. Finally, the fused feature maps are fed to train three machine learning models to obtain the best classifier. The hyperparameter optimization of all classifiers is performed using grid-search and randomized search algorithms. This study performs intensive experiments using 913 public image datasets, and the proposed method obtained 94.71% accuracy, which is an excellent performance even using a smaller dataset. The experiment results reveal that the proposed method is well-suited to deal with live malware traffic in real-world industrial IoT environments.

关键词： Visualization machine learning algorithms Transfer learning Stacking Neural networks Signal processing algorithms Telecommunication traffic

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Optimization: machine learning Applications in Inventory Management for E-commerce

Supply Chain Optimization: Machine Learning Applications in ...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： D Srinivas Twinkle Pravin D Sawant Fazla Rabby M. S. Vasu A. Roniboss School of Business SR University Warangal Telangana India M. M Institute of Management Maharishi Markandeshwar Deemed to be University Mullana Ambala Narayan Zantye College of Commerce Bicholim Goa Stanford Institute of Managment and Technology Australia Department of MBA Sree Rama Engineering College Tirupati Andhra Pradesh India Department of Chemistry Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science & Technology Chennai Tamilnadu India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

This study looks at how machine learning (ML) methods can be used in e-commerce inventory management to make demand forecasting and inventory optimisation more accurate and efficient. The literature review shows how important it is for online stores to keep track of their goods well and how machine learning algorithms might be able to help with this problem. Several machine learning techniques are talked about, such as supervised learning, reinforcement learning, and unsupervised learning, along with how they can be used in inventory management. The study makes up the suggested architecture for ML-based inventory management: importing data, preparing data, finding features, storing data, and the ML system. Real-world examples, like how Amazon uses AI in its forecasting, show that ML can be used in e-commerce product management and show its benefits. Real-world examples show that decision tree models and deep learning methods like recurrent neural networks (RNNs) and convolutional neural networks (CNNs) are useful for predicting demand and optimising supplies. But problems are pointed out, such as bad data, a lack of computing power, and models that are hard to understand. In the future, researchers will look into how to fix problems with machine learning algorithms, how to use new technologies like bitcoin and augmented reality, and how to make sure that AI is used in an ethical way and that customer data is kept safe. The study finds that machine learning has a lot of potential to change how e-commerce inventory is managed, which could lead to more efficiency and better decisions in the digital market.

关键词： Ethics machine learning algorithms Computational modeling Supply chains machine learning Inventory management Electronic commerce Optimization Unsupervised learning Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Cricket Player’s Performance Prediction Using machine learning

Cricket Player’s Performance Prediction Using Machine Learn...

引用

Artificial Intelligence and Data Engineering (AIDE), International Conference on

作者： Krishnaraj Rao N S Raghunandan K R Shamanth Rao Samarth Patil Sai Nandan Rathay Devadiga Dept of Information Science and Engg NMAM Institute of Technology Nitte(Deemed to be University Karnataka India Dept of Computer Science and Engg NMAM Institute of Technology Nitte(Deemed to be University Karnataka India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

This paper presents a predictive model for cricket player performance utilizing machine learning techniques to optimize team selection for competitive matches. By analyzing historical performance data, opponent dynamics, and stadium conditions, the model aims to identify the most suitable combination of players—comprising 6 batsmen, 3 bowlers, and 2 all-rounders. Key inputs, including pitch type, batting and bowling preferences, and winning probabilities, are integrated into a rule-based algorithm. Data is collected through web scraping from reputable sources such as ESPN Cricinfo, facilitating accurate predictions based on batting and bowling averages. The findings highlight the effectiveness of combining traditional cricketing knowledge with advanced data analytics to enhance decision-making in team management.

关键词： Analytical models Data analysis machine learning algorithms Accuracy Decision making machine learning Predictive models Prediction algorithms Data models Sports

来源：评论

学校读者我要写书评

暂无评论

Advancing Eye Disease and Glaucoma Diagnosis: A Comprehensive Survey of Deep learning, machine learning, and Hybrid Approaches

Advancing Eye Disease and Glaucoma Diagnosis: A Comprehensiv...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： B. Venkata Suresh Reddy Bhanu Prakash Battula Computer Science & Engineering JNTUK Kakinada Kakinada India Dept. of CSE-Data Science KKR & KSR Institute of Technology & Sciences Guntur India

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

Glaucoma stands as a serious global health issue among eye diseases because the condition leads to permanent blindness when proper diagnosis and treatment are not made in sufficient time. The detection and classification capabilities for these conditions have been significantly improved by recent developments in computational techniques that combine deep learning and traditional machine learning and hybrid models alongside clinical assessments. The survey explores 54 research studies regarding eye disease diagnosis which the authors divide into four distinct sections. Deep learning algorithms particularly CNN variants achieved outstanding success (93.5%) when used for retinal image segmentation together with disease classification tasks. Hybrid models equipped with machine learning and deep learning capabilities reached the maximum accuracy level at 95% for diagnosing diseases. SVMs and other traditional machine learning algorithms delivered accurate results for structured datasets through their performance while medical evaluations helped identify disease trajectories and disease elements. The study presents a thorough overview of the advantages along with drawbacks and potential applications for these analysis techniques in detecting and treating glaucoma along with other eye conditions.

关键词： Deep learning Glaucoma Surveys Image segmentation machine learning algorithms Accuracy Retina Trajectory Robots Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

A survey on machine learning in Internet of Things: algorithms, strategies, and applications

引用

INTERNET OF THINGS 2020年 12卷

作者： Messaoud, Seifeddine Bradai, Abbas Bukhari, Syed Hashim Raza Quang, Pham Tran Anh Ben Ahmed, Olfa Atri, Mohamed Univ Monastir Fac Sci Monastir Elect & Microelect Lab Environm St Monastir 5019 Tunisia Univ Poitiers XLIM Inst Bat SP2MI11 Bd Marie & Pierre Curie F-86962 Chasseneuil France COMSATS Univ Islamabad Dept Elect Engn Attock Campus Islamabad Pakistan Huawei France Boulogne France Univ Poitiers XLIM Inst Bat SP2MI11 Bd Marie & Pierre Curie F-86962 Chasseneuil France King Khalid Univ Coll Comp Sci Abha Saudi Arabia

In the IoT and WSN era, large number of connected objects and sensing devices are dedicated to collect, transfer, and generate a huge amount of data for a wide variety of fields and applications. To effectively run these complex networks of connected objects, there are several challenges like topology changes, link failures, memory constraints, interoperability, network congestion, coverage, scalability, network management, security, and privacy to name a few. Thus, to overcome these challenges and exploiting them to support this technological outbreak would be one of the most crucial tasks of modern world. In the recent years, the development of Artificial Intelligence (AI) led to the emergence of machine learning (ML) which has become the key enabler to figure out solutions and learning models in an attempt to enhance the QoS parameters of IoT and WSNs. By learning from past experiences, ML techniques aim to resolve issues in the WSN and IoT's fields by building algorithmic models. In this paper, we are going to highlight the most fundamental concepts of ML categories and algorithms. We start by providing a thorough overview of the WSN and IoT's technologies. We also discuss the vital role of ML techniques in driving up the evolution of these technologies. Then, as the key contribution of this paper, a new taxonomy of ML algorithms is provided. We also summarize the major applications and research challenges that leveraged ML techniques in the WSN and IoT. Eventually, we analyze the critical issues and list some future research directions. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Wireless sensor network Internet of Things machine learning categories machine learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Bias Origins in Training Dataset of Cardiovascular Disease using machine learning Classifier

Detection of Bias Origins in Training Dataset of Cardiovascu...

引用

AI-Driven Smart Healthcare for Society 5.0

作者： Jyoti Prakhar Md. Tanwir Uddin Haider Department of Computer Science and Engineering National Institute of Technology Patna Patna India

ISBN: (数字)9798331536336

ISBN: (纸本)9798331536343

Today, decision support systems are essential in various industries, where vital decisions are made using datasets such as health care systems. So, if the dataset is biased within healthcare systems, then it will hinder accurate disease identification. Thus, it emphasizes the need for the detection of bias origin to mitigate it and to enhance model performance and ensure rational decision-making. Seeing this fact, in this paper we have proposed a methodology for the detection of bias origin within cardiovascular disease. The proposed methodology identifies the biases’ origin due to the underrepresented class of the protected attribute in training dataset using machine learning models. For experimental evaluation, we selected a cardiovascular disease dataset and trained it using an ML algorithm. Then, we assessed it on a new test dataset i.e. CVD dataset consisting of four groups of females and males with cardiovascular disease or not. Furthermore, the performance metrics, including accuracy and mean absolute error (MAE), are evaluated to validate the under- represented samples, which are the primary cause of bias in the system. The results demonstrate that the proposed methodology is straightforward and effective in detecting the origin of bias.

关键词： Training Industries Decision support systems Accuracy machine learning algorithms Medical services machine learning Cardiovascular diseases

来源：评论

学校读者我要写书评

暂无评论

Optimization Control of HVAC System and Building Energy Management Based on machine learning

Optimization Control of HVAC System and Building Energy Mana...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Gangqiang Feng Xi'an Industrial Service Department Changqing Oilfield Branch Company Xi'an China

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

This paper discusses the optimal control and building energy management of building heating, ventilation and air conditioning (HVAC) systems based on deep Q networks (DQNs). Traditional control strategies often have difficulty adapting to the dynamic changes of the environment and the personalized needs of users. This paper studies a DQN algorithm based on reinforcement learning to learn the optimal control strategy through interaction with the environment to achieve the best balance between energy saving and comfort. First, the HVAC system is modeled as a Markov decision process (MDP), including three elements: state, action, and reward. Then, a DQN model is designed and implemented to improve the efficiency and stability of learning through experience replay and target network. Experience replay reduces the correlation between samples by randomly sampling past experience, while the target network reduces the oscillation during training by stabilizing the estimation of Q values. Finally, the application effect of DQN in HVAC system control is verified by verification. The specific data of the experimental results show that DQN performs well in energy efficiency. In terms of response speed, the response time of DQN to indoor and outdoor temperature fluctuations is 64.4 seconds, which is significantly faster than other traditional methods. In the adaptability score, DQN's highest adaptability score can reach 91.1 points. The DQN algorithm has significant advantages in HVAC system optimization control and building energy consumption management, and can achieve lower energy consumption and higher control accuracy.

关键词： Energy consumption HVAC machine learning algorithms Accuracy Markov decision processes Optimal control Ventilation Energy efficiency Optimization Building management systems

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：