检索结果-内蒙古大学图书馆

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Mikawa, Kenta Kobayashi, Manabu Goto, Masayuki Hirasawa, Shigeichi Tokyo City University Department of Information Systems Kanagawa Japan Waseda University Center for Data Science Tokyo Japan Waseda University School of Creative Science and Engineering Tokyo Japan Waseda University Research Institute for Science and Engineering Tokyo Japan

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

With the development of information technology, a wide variety of data have been accumulated, and there are many methods for analyzing such data. In this study, we model the input data and the metrics between the data based on the assumption that each metric is generated from a continuous latent variable. Specifically, we assume that the input data are generated using low-dimensional latent variables and their projection matrices. We describe a method for estimating the latent variables. Because the generative model defined in this study cannot obtain the Q function analytically, we use the Monte Carlo EM algorithm to approximate the Q function and investigate an efficient parameter estimation method. Experiments using artificial data and the 20 newsgroups dataset demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Input output programs

来源：评论

学校读者我要写书评

暂无评论

Cursive Hand writing Recognition Using Neural Networks with VGG-16

Cursive Hand writing Recognition Using Neural Networks with ...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Anushka Anil Rangari Swagat Das Rajeswari D Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India

Recognition of cursive handwritten text from photographs is a method for finding handwritten text. Identification is difficult because every author has a distinctive writing style. The proposed work uses cutting-edge technologies including RNN, KNN, MLP, and CRNN twith VGG16 to push the boundaries of character and handwriting recognition. Additionally, it compares neural networks to CNNwith VGG16 and finds that neural networks are more accurate. In the first stage, image acquisition, the scanned image is acquired along with its normalization, feature extraction, and segmentation. Additionally, it combines with the most effective feature extraction technique to improve the accuracy of our model. It also compares the accuracy with six uniquepretreat. approach, which are image segmentation image data generator data augmentation closed loop pre-processing, sigmoid Stretching and geometric *** provides the highest accuracy (98.36%) when using data augmentation. CNN has the highest accuracy (95.25%) when using picture segmentation. The third experiment's results for the image data generator show that CNN produced the best results (92.47%), while the highest model, RNN, gave closed loop processing accuracy of 92.20%. a change in geometry KNN has the highest accuracy at 95.39%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

data organization limits the predictability of binary classification

arXiv

引用

arXiv 2024年

作者： Jing, Fei Zhang, Zi-Ke Zhang, Yi-Cheng Zhang, Qingpeng Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong Center for Digital Communication Studies Zhejiang University Hangzhou310058 China Department of Physics University of Fribourg Chemin du Musée 3 Fribourg1700 Switzerland

The structure of data organization is widely recognized as having a substantial influence on the efficacy of machine learning algorithms, particularly in binary classification tasks. Our research provides a statistical physics framework from the perspective of statistical physics, revealing that the upper bound of binary classification predictability on a given dataset is equivalent to obtaining the ground state energy of the canonical ensemble of classifiers on fixed data patterns, primarily constrained by the inherent qualities of the data. Through both theoretical reasoning and empirical examination on dozens of real datasets, we employed standard objective functions, evaluative metrics, and binary classifiers to arrive at two principal conclusions. Firstly, we show that the theoretical upper bound of binary classification on actual datasets can be theoretically attained as the ground state energy of corresponding partition functions, regardless of any specific algorithms. This upper boundary represents a calculable equilibrium between the learning loss and the metric of evaluation. Secondly, we have computed the precise upper bounds for three commonly used evaluation metrics, uncovering a fundamental uniformity with our overarching thesis: the upper bound is intricately linked to the organization of dataset’s characteristics, independent of the classifier in use. Furthermore, our subsequent analysis uncovers a detailed relationship between the upper limit and the level of class overlap within the binary classification data. This relationship is instrumental for pinpointing the most effective feature subsets for use in feature engineering. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Music Recommendation based on Facial Expressions using data Augmentation

Music Recommendation based on Facial Expressions using Data ...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Tanisha Kapoor Arnaja Ganguly D Rajeswari Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

Emotion recognition from facial expressions plays a pivotal role in human-computer interaction, psychology, marketing, and various other domains. This research paper presents a comprehensive study and implementation of an automated emotion recognition system based on deep learning techniques. The project addresses the challenge of accurately classifying a wide range of emotions from facial images in real-time. Leveraging Convolutional Neural Networks (CNNs) and modern deep learning approaches, the system demonstrates high accuracy in identifying emotions, including happiness, sadness, anger, and more. This project used the image dataset FER-2013 for the mood prediction portion of the project, and Spotify music data to predict emotions for music recommendation. Both the datasets utilized are freely available on Kaggle. The proposed system can achieve an accuracy of 91.23% in predicting the users’ emotion based on their facial expressions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Mitigating Security Threats in IoT Environment 5

Machine Learning Approach for Mitigating Security Threats in...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Saini, Harnit Bala, Saroj Ida, S.Jhansi Kumar, K. Suresh Swetha, Shankerpally Divyabarathi, P. Ajay Kumar Garg Engineering College Department of Cse Ghaziabad India Ajay Kumar Garg Engineering College Department of Mca Ghaziabad India R.M.K Engineering College Department of Computer Science and Business Systems Kavaraipettai India Kongu Engineering College Department of Cse Erode India Cvr College of Engineering Department of Information Technology Telangana India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India

ISBN: (纸本)9798350321425

In today's world, a huge amount of data and information is transferred through wireless networks. The Internet of Things (IoT) is a complex network that consists of diverse sensors, devices, and things, which often have limited resources and are susceptible to various security threats, including Distributed Denial of Service (DDoS) attacks. These networks are vulnerable to a variety of cyber threats and privacy issues. Intrusions are harmful activities that can damage a network. IoT networks are particularly vulnerable to security threats. The Bi-Layer Intrusion Detection Model (BIDM) identifies intrusions based on the optimal features selected in the Optimal Feature Vector Selection (OFVS) phase. This scheme not only prevents attacks, but also serves as a defense against legitimate threats. The proposed technique was evaluated using the KDD CUP 99 dataset, a well-known Intrusion Detection System (IDS) benchmark. The performance of the proposed scheme was further analyzed using the NSL-KDD and CICIDS-2017 datasets. The performance of OFVS was also investigated using the relatively new IoT Network Intrusion dataset. The implementation was carried out in Jupyter Notebook using the Python programming language. Matplotlib, Scikit-learn, pandas, and NumPy were some of the packages used in the implementation. The proposed framework achieved high accuracy rates, with NB at 97.4%, SVM at 96.1%, and DT at 98.1%. By utilizing this approach, the security of IoT networks can be significantly enhanced, and the risks associated with DDoS attacks can be mitigated. © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Approximate secular equations for the cubic regularization subproblem 22

Approximate secular equations for the cubic regularization s...

引用

Proceedings of the 36th International Conference on Neural Information Processing systems

作者： Yihang Gao Man-Chung Yue Michael K. Ng Department of Mathematics The University of Hong Kong Pokfulam Hong Kong Musketeers Foundation Institute of Data Science The University of Hong Kong Pokfulam Hong Kong

ISBN: (纸本)9781713871088

The cubic regularization method (CR) is a popular algorithm for unconstrained non-convex optimization. At each iteration, CR solves a cubically regularized quadratic problem, called the cubic regularization subproblem (CRS). One way to solve the CRS relies on solving the secular equation, whose computational bottleneck lies in the computation of all eigenvalues of the Hessian matrix. In this paper, we propose and analyze a novel CRS solver based on an approximate secular equation, which requires only some of the Hessian eigenvalues and is therefore much more efficient. Two approximate secular equations (ASEs) are developed. For both ASEs, we first study the existence and uniqueness of their roots and then establish an upper bound on the gap between the root and that of the standard secular equation. Such an upper bound can in turn be used to bound the distance from the approximate CRS solution based ASEs to the true CRS solution, thus offering a theoretical guarantee for our CRS solver. A desirable feature of our CRS solver is that it requires only matrix-vector multiplication but not matrix inversion, which makes it particularly suitable for high-dimensional applications of unconstrained non-convex optimization, such as low-rank recovery and deep learning. Numerical experiments with synthetic and real data-sets are conducted to investigate the practical performance of the proposed CRS solver. Experimental results show that the proposed solver outperforms two state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Approximate Secular Equations for the Cubic Regularization Subproblem

arXiv

引用

arXiv 2022年

作者： Gao, Yihang Yue, Man-Chung Ng, Michael K. Department of Mathematics The University of Hong Kong Pokfulam Hong Kong Musketeers Foundation Institute of Data Science The University of Hong Kong Pokfulam Hong Kong

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Colour Correction and Detail Enhancement in Underwater Images using Hybrid Real-ESRGAN

Colour Correction and Detail Enhancement in Underwater Image...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Vijay Chandar Vishnu G Nair D Rajeswari Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

The motive of underwater image enhancement is to improve and enhance the quality of photographs taken underwater. Various traditonal image processing techniques and deep learning models have been developed to work on this task. But most often the deep learning models and conventional methods of image processing work in silos, leading to subpar results. This research proposes a strategy that utilizes a combination of both approaches to solve this issue. Initially, traditional image processing techniques like colour correction and image stretching are used to enhance the colour of the images. The enhanced images are then fed into a custom Real-ESRGAN model that has been fine-tuned on an underwater image dataset to optimize performance in this context. This hybrid approach has the potential to outperform the models utilizing either traditional or deep learning methods in isolation by leveraging the strengths of both. In addition, batch processing is used in the pipeline to efficiently handle multiple images at the same time. This effectively addresses the scalability problem that arises frequently in image enhancement tasks. With eye-catching visuals, the proposed methodology achieves a Peak Signal-to-Noise Ratio (PSNR) of 23.66 and a Mean Squared Error (MSE) of 0.28, suggesting excellent image restoration and noise reduction. The qualitative assessments show that the improved image graphs have better colour, contrast, and clarity than the originals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Predictive Maintenance in Supply Chain Management systems

Leveraging Machine Learning for Predictive Maintenance in Su...

引用

2024 International Conference on science, Technology, engineering and Management, ICSTEM 2024

作者： Sharan, Bediga Vijai, C. Srivastava, Kingshuk Singla, Atul Bhati, Indira Kumar, T.Ch. Anil School of CS & AI SR University Telangana Warangal India Department of Commerce and Business Administration Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai62 India Department of Data Science UPES Uttarakhand Dehradun India Lovely Professional University Phagwara India India Department of Mechanical Engineering Vignan's Foundation for Science Technology and Research Vadlamudi Andhra Pradesh Guntur522213 India

ISBN: (纸本)9798350376913

The purpose of this exploratory research is to investigate the incorporation of machine literacy (ML) techniques for prediction conservation in supply chain management (SCM) systems. The successful operation of force chains is essential to the success of an organization in the modern business environment, which is always shifting and transitioning. When it comes to preemptively managing outfit failures, performing in expensive time-outs, and functional dislocations, conventional conservation techniques frequently fall short unexpectedly. To analyze literal data, detector inputs, and external variables, the utilization of machine learning algorithms makes it possible to anticipate conservation requirements. Through the utilization of prophetic analytics, supply chain management systems can identify hidden faults in the outfit, which enables visionary conservation actions. This study assesses various machine learning models and algorithms that have been adapted to forecast conservation circumstances in supply chain management (SCM) systems. Specific variables such as monitoring the status of the outfit and recognizing failure patterns are taken into consideration. In the end, the purpose of the investigation is to provide insight into the actual implementation of machine learning-driven prophetic conservation methods. This will enable organizations to improve their overall performance and optimize their force chain operations. © 2024 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Cross-mode Knowledge Adaptation for Bike Sharing Demand Prediction using Domain-Adversarial Graph Neural Networks

arXiv

引用

arXiv 2022年

作者： Liang, Yuebing Huang, Guan Zhao, Zhan Department of Urban Planning and Design The University of Hong Kong Hong Kong Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong

For bike sharing systems, demand prediction is crucial to ensure the timely re-balancing of available bikes according to predicted demand. Existing methods for bike sharing demand prediction are mostly based on its own historical demand variation, essentially regarding it as a closed system and neglecting the interaction between different transportation modes. This is particularly important for bike sharing because it is often used to complement travel through other modes (e.g., public transit). Despite some recent progress, no existing method is capable of leveraging spatiotemporal information from multiple modes and explicitly considers the distribution discrepancy between them, which can easily lead to negative transfer. To address these challenges, this study proposes a domain-adversarial multi-relational graph neural network (DA-MRGNN) for bike sharing demand prediction with multimodal historical data as input. A temporal adversarial adaptation network is introduced to extract shareable features from demand patterns of different modes. To capture correlations between spatial units across modes, we adapt a multi-relational graph neural network (MRGNN) considering both cross-mode similarity and difference. In addition, an explainable GNN technique is developed to understand how our proposed model makes predictions. Extensive experiments are conducted using real-world bike sharing, subway and ride-hailing data from New York City. The results demonstrate the superior performance of our proposed approach compared to existing methods and the effectiveness of different model components. Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

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：