检索结果-内蒙古大学图书馆

2022 OPJU international Technology conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Jagyasi, Deepak Raut, Archana R. G H Raisoni College of Engineering Department of Computer Science Engineering Maharashtra Nagpur India

ISBN: (纸本)9781665492942

Organizations are using AI and ML to identify the opportunities in various domains. This paper examines the effect of incorporating Environment, Social, and Governance (ESG) criteria in evaluation of the long-term value and performance of organizations. Specifically, this paper proposes a model that uses artificial intelligence and machine learning to analyse ESG data and helps to determine which organizations are more likely to achieve long-term success. Then there is application of this model to a sample of publicly traded companies to assess its efficacy. Our results suggest that organizations with higher ESG scores are more likely to have better long-term performance and value. The implementation of the ESG analysis tool and machine learning model helps in identifying the organizations which are performing well in the environment, social and governance aspects along with considering their financial outlook. This paper focuses on discussion of the proposed model evaluating the ESG index, and thus helping the investors, organizations, and retail individuals on the performance of the organization selected by using AI and ML. Every organization needs advanced technology for its business, AI and ML works for that and helps in reduction of the manual efforts and also helps to create a standardized model which if developed well could be evolved as one of the important aspects for individuals and corporates alike to be considered before making their investment decisions. © 2023 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Malicious ADS -B data Generation Based on Improved GAN 9

Malicious ADS -B data Generation Based on Improved GAN

引用

9th IEEE international conference on Big data Security on Cloud (BigdataSecurity) / 9th IEEE international conference on High Performance and Smart Computing (IEEE HPSC) / 9th IEEE international conference on Intelligent data and Security (IEEE IDS)

作者： Lei, Jin Jiang, Ruifang Wu, Zhijun Civil Aviat Univ China Sch Safety Sci & Engn Tianjin Peoples R China

ISBN: (纸本)9798350312935

Automatic dependent surveillance broadcast (ADS -B) system sends messages over unencrypted wireless channels without any information integrity protection measures, and its messages are at risk of interception and tampering, which can easily lead to impersonation and forgery attacks. At present, although the ADS -B data anomaly detection model based on machine learning has excellent performance in predicting normal samples, the machine learning model may face different degrees of risk in each stage of its life cycle due to the existence of a large number of attackers in real scenes. To build secure and reliable machine learning systems, exploit potential vulnerabilities. Aiming at the ADS -B abnormal data detection model based on machine learning, this paper studies a construction method of poisoning data with strong applicability and establishes attack model. By injecting malicious data generated by the Generative adversarial network into the machine learning model, the performance of the trained model deteriorates and data misclassification occurs. Experimental results show that the malicious ADS -B data generation method proposed in this paper achieves good results, which lays a foundation for optimizing system defense technology and guaranteeing ADS -B security.

关键词： ADS-B Generative adversarial netwo machine learning malicious data security

来源：评论

学校读者我要写书评

暂无评论

Shifted Interpolation for Differential Privacy 41

Shifted Interpolation for Differential Privacy

引用

41st international conference on machine learning (ICML)

作者： Bok, Jinho Su, Weijie J. Altschuler, Jason Univ Penn Dept Stat & Data Sci Philadelphia PA 19104 USA

Noisy gradient descent and its variants are the predominant algorithms for differentially private machine learning. It is a fundamental question to quantify their privacy leakage, yet tight characterizations remain open even in the foundational setting of convex losses. This paper improves over previous analyses by establishing (and refining) the "privacy amplification by iteration" phenomenon in the unifying framework of f-differential privacy-which tightly captures all aspects of the privacy loss and immediately implies tighter privacy accounting in other notions of differential privacy, e.g., (epsilon, delta)-DP and Renyi DP. Our key technical insight is the construction of shifted interpolated processes that unravel the popular shifted-divergences argument, enabling generalizations beyond divergence-based relaxations of DP. Notably, this leads to the first exact privacy analysis in the foundational setting of strongly convex optimization. Our techniques extend to many settings: convex/strongly convex, constrained/unconstrained, full/cyclic/stochastic batches, and all combinations thereof. As an immediate corollary, we recover the f-DP characterization of the exponential mechanism for strongly convex optimization in Gopi et al. (2022), and moreover extend this result to more general settings.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

LOOPED TRANSFORMERS ARE BETTER AT learning learning ALGORITHMS 12

LOOPED TRANSFORMERS ARE BETTER AT LEARNING LEARNING ALGORITH...

引用

12th international conference on learning Representations, ICLR 2024

作者： Yang, Liu Lee, Kangwook Nowak, Robert D. Papailiopoulos, Dimitris University of Wisconsin Madison United States

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. (2022). However, the absence of an inherent iterative structure in the transformer architecture presents a challenge in emulating the iterative algorithms, which are commonly employed in traditional machine learning methods. To address this, we propose the utilization of looped transformer architecture and its associated training methodology, with the aim of incorporating iterative characteristics into the transformer architectures. Experimental results suggest that the looped transformer achieves performance comparable to the standard transformer in solving various data-fitting problems, while utilizing less than 10% of the parameter count. © 2024 12th international conference on learning Representations, ICLR 2024. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis Through machine learning: Fatal Road Crashes in Delhi, India

Predictive Analysis Through Machine Learning: Fatal Road Cra...

引用

2024 international conference on Intelligent and Innovative Practices in engineering and Management, IIPEM 2024

作者： Mahajan, Navita Kaur, Navleen Srivastava, Anshul Sabharwal, Tanupreet Gill, Sahaj Mittal, Raghav Jain, Kavya Amity University Noida Amity International Business School Noida India Amity University Online Department of Information Technology Noida India

ISBN: (纸本)9798350390049

Road crashes are the sixth leading cause of death in India. At present, most of the metropolitan cities of India are going through the burden of rising road accidents and an associated increase in fatalities. Among them, Delhi accounts for one of the highest number of road accidents in India. The study has explored the ongoing trend of fatal road crashes in Delhi from 2004 to 2022 using the data concerned. Least square Method is the most efficient way for prediction of future to forecast data using Time Series Analysis. The results of this study show that the number of fatal crashes will decrease until the year 2027 provided the strict control measures continued to be followed. © 2024 IEEE.

关键词： Highway accidents

来源：评论

学校读者我要写书评

暂无评论

Asymptotics of Feature learning in Two-layer Networks after One Gradient-step 41

Asymptotics of Feature Learning in Two-layer Networks after ...

引用

41st international conference on machine learning, ICML 2024

作者： Cui, Hugo Pesce, Luca Dandi, Yatin Krzakala, Florent Lu, Yue M. Zdeborová, Lenka Loureiro, Bruno Lausanne1015 Switzerland Lausanne1015 Switzerland Harvard University School of Engineering and Applied Sciences United States PSL CNRS ParisF-75230 Cedex 05 France

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al., 2022), we model the trained network by a spiked Random Features (sRF) model. Further building on recent progress on Gaussian universality (Dandi et al., 2023), we provide an exact asymptotic description of the generalization error of the sRF in the high-dimensional limit where the number of samples, the width, and the input dimension grow at a proportional rate. The resulting characterization for sRFs also captures closely the learning curves of the original network model. This enables us to understand how adapting to the data is crucial for the network to efficiently learn nonlinear functions in the direction of the gradient - where at initialization it can only express linear functions in this regime. Copyright 2024 by the author(s)

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

machine learning and engineering feature approaches to detect events perturbing the indoor microclimate in Ringebu and Heddal stave churches (Norway)

引用

international JOURNAL OF BUILDING PATHOLOGY AND ADAPTATION 2024年第1期42卷 35-47页

作者： Miglioranza, Pietro Scanu, Andrea Simionato, Giuseppe Sinigaglia, Nicholas Califano, America Univ Padua Dept Phys & Astron Padua Italy Norwegian Univ Sci & Technol Dept Mech & Ind Engn Trondheim Norway

Purpose Climate-induced damage is a pressing problem for the preservation of cultural properties. Their physical deterioration is often the cumulative effect of different environmental hazards of variable intensity. Among these, fluctuations of temperature and relative humidity may cause nonrecoverable physical changes in building envelopes and artifacts made of hygroscopic materials, such as wood. Microclimatic fluctuations may be caused by several factors, including the presence of many visitors within the historical building. Within this framework, the current work is focused on detecting events taking place in two Norwegian stave churches, by identifying the fluctuations in temperature and relative humidity caused by the presence of people attending the public events. Design/methodology/approach The identification of such fluctuations and, so, of the presence of people within the churches has been carried out through three different methods. The first is an unsupervised clustering algorithm here termed "density peak," the second is a supervised deep learning model based on a standard convolutional neural network (CNN) and the third is a novel ad hoc engineering feature approach "unexpected mixing ratio (UMR) peak." Findings While the first two methods may have some instabilities (in terms of precision, recall and normal mutual information [NMI]), the last one shows a promising performance in the detection of microclimatic fluctuations induced by the presence of visitors. Originality/value The novelty of this work stands in using both well-established and in-house ad hoc machine learning algorithms in the field of heritage science, proving that these smart approaches could be of extreme usefulness and could lead to quick data analyses, if used properly.

关键词： Clustering Wood Microclimate Heritage buildings machine learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A hybrid deep learning approach for Assamese toxic comment detection in social media 2

A hybrid deep learning approach for Assamese toxic comment d...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Neog, Mandira Baruah, Nomi Dibrugarh University Dibrugarh786004 India

The presence of toxic comments on online platforms creates significant barriers to encouraging positive conversation and user involvement. The present research introduces a novel hybrid deep learning methodology that combines Bidirectional long-short-term memory (BiLSTM) and Convolutional Neural Network (CNN) architectures to improve toxic comment identification. The major goal is to improve accuracy and efficiency in detecting Assamese toxic content, particularly on social media sites. Due to insufficient existing datasets, information is manually gathered from a wide range of public domains, allowing for a thorough evaluation of the performance of the hybrid method. We used two alternative activation functions in our experiments: sigmoid and softmax. The sigmoid activation obtained 88.43% accuracy, while the softmax activation outperformed with 90.51% accuracy. We have also made an effort to use our suggested Approach in Bengali and Hindi, two additional Indian languages. Due to their comparable Subject-Object-Verb (SOV) linguistic structure to Assamese, we chose these languages, and the results have been fairly encouraging. The findings from the research are extremely significant since they highlight that the hybrid deep learning approach is a promising option for effectively identifying toxic comments on social media networks. © 2024 Elsevier B.V.. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Leveraging machine learning Algorithms for predicting Churn in Telecom industries 6

Leveraging Machine Learning Algorithms for predicting Churn ...

引用

6th international conference on Electronics, Communication and Aerospace Technology, ICECA 2022

作者： Subramanian, R. Raja Lakshmi, M. Lavanya, M. Roy, M. Kanitha Gabriela Krishnaveni, K. Yogeswari, T. Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Virudhunagar India

ISBN: (纸本)9781665482714

Customers are essential to the operation of business. Customer churn can have a variety of effects. Predicting customer attrition must be a key component of every business. This aids in identifying clients who are about to end their subscription to a service. The mobile telecom market recently transitioned from being one that was expanding quickly to one that was saturated. The goal of telecommunications firms is to shift their attention from attracting new, large customers to maintaining existing ones. Knowing which clients are likely to switch to a competitor in the future is important because of this. The model machine learning methods(classifiers) like logistic regression, decision tree, gaussian classifier, random forest classifier, polynomial kernel SVM support vector machine) classifier, RBF (Radial basis Function) kernel SVM classifier, Sigmoid kernel SVM classifiers for churn prediction for telecommunications firms. On the supplied data set, a comparison of the algorithms' works effectiveness is made. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Investigating Context-Aware Sentiment Classification Using machine learning Algorithms 1

引用

8th international conference on Computers, Management and Mathematical Sciences, ICCM 2022

作者： Kumarr, P. Ashok Vardhan, B. Vishnu Chirankjeevi, P. ACE Engineering College Telangana Hyderabad India JNTUH College of Engineering Telangana Manthini India ACE Engineering College Telangana Hyderabad India

ISBN: (数字)9783031511677

ISBN: (纸本)9783031511660

In today’s world knowing the opinion of people is a widely used research topic in natural language processing, and context-aware sentiment analysis has emerged as an important research area in recent years. This chapter conducts a survey of context-aware sentiment classification using machine learning algorithms. In this, first, provide an overview of the key concepts and challenges in context-aware sentiment analysis, and then review the existing literature on context-aware sentiments using machine learning algorithms. The chapter classifies the studies depending on the types of machine learning (ML)-based algorithms used, which are supervised, unsupervised, and deep neural network–based learning, and discusses the strengths and weaknesses of each approach. Furthermore, we identify the major challenges in context-aware sentiment analysis using machine learning techniques, such as data sparsity, context feature selection, and model interpretability, and discuss the potential solutions and future directions. We also provide a summary of the applications of context-aware sentiments using ML techniques in different domains, which are marketing, customer service, restaurants, politics, and health. This survey gives a detailed overview by considering present state-of-the-art context-aware sentiment classification using machine learning algorithms and highlights potential opportunities along with challenges in this field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Sentiment analysis

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：