检索结果-内蒙古大学图书馆

3rd International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2023

作者： Abdelminaam, Diaa Salama Madbouly, Magda M. Zeid, Magdy Abd-Elghany Elatif Gomaa, Ibrahim Abd Abualigah, Laith Misr International University Faculty of Computer Science Cairo Egypt Benha University Faculty of Computers and Artificial Intelligence Benha Egypt Alexandria University Faculty of Computer and Data Science Alexandria Egypt Alobour High Institute for Computer and Informatics Computer Science Department Cairo Egypt Lebanese American University Department of Electrical and Computer Engineering Byblos13-5053 Lebanon Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Amman19328 Jordan Middle East University Meu Research Unit Amman11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pinang Pulau11800 Malaysia

ISBN: (纸本)9798350306231

Like most diseases that affect a human's life, car-diovascular disease is dangerous and unwanted for anyone who has heard of it as it brings a high risk of death. In today's world, most deaths are caused by heart disease as it could come from age, heritage, smoking, and many factors that could seem normal, and it doesn't matter what part of the world you are in. There must be a way to know or predict if this person is at high risk of cardiovascular disease. This paper and project talk about six algorithms: K-Nearest-Neighbour (KNN), Decision Tree (DT), Naive Bayes, Neural Network, Logistic Regression, and Support Vector Machine (SVM). The results came between 60% to 70% in one dataset and from 80 % to 90 % in the second. Still, they mostly favor the Neural Network algorithm as it can learn and model around complex relationships. The SVM showed different outputs between the two datasets as one is significantly larger than the other, possibly due to the outliers in both datasets being different and more complex in the larger one. Cardiovascular disease can be very dangerous, but finding and discovering it soon can be a lifesaver. These algorithms also can help find and predict it, as it was shown with not just decent, but good and respectable success rates for each one. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Liao, Liang Wan, Liang Liu, Mingsheng Li, Shusheng State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Northeastern University Shenyang China

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good tradeoff between speed and accuracy, two-branch architecture has been proposed in recent years. It treats spatial information and semantics information separately which allows the model to be composed of two networks both not heavy. However, the process of fusing features with two different scales becomes a performance bottleneck for many nowaday two-branch models. In this research, we design a new fusion mechanism for two-branch architecture which is guided by attention computation. To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion. To ensure that our module can be effective, we use Residual U-blocks (RSU) to build one of the two branches in our networks which aims to obtain better multi-scale features. Extensive experiments on Cityscapes and CamVid dataset show the effectiveness of our method. On Cityscapes, our light version network without pretrain weight can achieve 71.1% mIoU at 163 FPS on a single Nvidia RTX 3070 using full resolution images(1024×2048pix). And the large version can achieve 77.9% mIoU with a speed of 43 FPS which still reaches the real-time criterion. Our code and module has been open sourced at https://***/LikeLidoA/BiDGANet/tree/main Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CNN based Optimized Autoencoder for Satellite Image Compression

CNN based Optimized Autoencoder for Satellite Image Compress...

引用

Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), IEEE Conference on

作者： P. Sowmya Sri S. Karthi M. Kalaiyarasi S. Saravanan Computer Science and Engineering (Data Science) B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering V.S.B.Engineering College India Institute of AI & ML Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India Department of EEE B V Raju Institute of Technology Telangana India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

This paper introduces an innovative Convolutional Neural Network (CNN) based Optimized Autoencoder for the compression of satellite images, with a focus on high resolution Sentinel-2 and Landsat imagery. In this method, the Satellite images are resized and normalized before an optimal autoencoder architecture is implemented. The encoder compresses the image, while the decoder reconstructs it with minimum quality loss. Convolutional and down sampling layers in the encoder and up sampling layers in the decoder preserve image features. MSE, PSNR, SSIM, and CR were used to assess compression performance. The simulation outcomes show that the CNN-based Autoencoder can retain image quality across images with a high compression ratio of 512, an average MSE of 0.0064, an average PSNR of 25.214 dB, and an SSIM of 0.62. This satellite image compression approach is efficient enough for storage and transmission in satellite data applications.

关键词： Image quality Technological innovation Image coding Satellites Autoencoders Memory Real-time systems Satellite images Decoding Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Global Feature Enhancing and Fusion Framework for Strain Gauge Status Recognition 25

Global Feature Enhancing and Fusion Framework for Strain Gau...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Xu Zhang Peng Wang Chen Wang Zhe Xu Xiaohua Nie Wei Wang Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shang Hai China Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shanghai China National Engineering Research Center for Big Data Software Tsinghua University Beijing China School of Software Tsinghua University Beijing China National Key Laboratory of Strength and Structural Integrity Aircraft Strength Research Institute of China Xi'an Shaanxi China

ISBN: (纸本)9798400713316

Strain Gauge Status (SGS) recognition is crucial in the field of intelligent manufacturing based on the Internet of Things, as accurate identification helps timely detection of failed mechanical components, avoiding accidents. The loading and unloading sequences generated by strain gauges can be identified through time series classification (TSC) algorithms. Recently, deep learning models, e.g., convolutional neural networks (CNNs) have shown remarkable success in the TSC task, as they can extract discriminative local features from the subsequences to identify the time series. However, we observe only the local features may not be sufficient for expressing the time series, especially when the local sub-sequences between different time series are very similar, e.g., SGS data of aircraft wings in static strength experiments. Nevertheless, CNNs suffer from the limitation in extracting global features due to the nature of convolution operations. For extracting global features to more comprehensively represent the SGS time series, we propose two insights: (i) Constructing global features through feature engineering. (ii) Learning high-order relationships between local features to capture global features. To realize and utilize them, we propose a hypergraph-based global feature learning and fusion framework, which learns and fuses global features for semantic consistency to enhance the representation of SGS time series, thereby improving recognition accuracy. Our method designs are validated on industrial SGS and public UCR datasets, showing better generalization for unseen data in SGS recognition.

关键词： deep learning models

来源：评论

学校读者我要写书评

暂无评论

On the Element-Wise Representation and Reasoning in Zero-Shot Image Recognition: A Systematic Survey

arXiv

引用

arXiv 2024年

作者： Guo, Jingcai Rao, Zhijie Chen, Zhi Guo, Song Zhou, Jingren Tao, Dacheng Department of Computing The Hong Kong Polytechnic University Hong Kong School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD4072 Australia Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Alibaba Group Hangzhou311121 China College of Computing and Data Science Nanyang Technological University Singapore

Zero-shot image recognition (ZSIR) aims to recognize and reason in unseen domains by learning generalized knowledge from limited data in the seen domain. The gist of ZSIR is constructing a well-aligned mapping between the input visual space and the target semantic space, which is a bottom-up paradigm inspired by the process by which humans observe the world. In recent years, ZSIR has witnessed significant progress on a broad spectrum, from theory to algorithm design, as well as widespread applications. However, to the best of our knowledge, there remains a lack of a systematic review of ZSIR from an element-wise perspective, i.e., learning fine-grained elements of data and their inferential associations. To fill the gap, this paper thoroughly investigates recent advances in element-wise ZSIR and provides a sound basis for its future development. Concretely, we first integrate three basic ZSIR tasks, i.e., object recognition, compositional recognition, and foundation model-based open-world recognition, into a unified element-wise paradigm and provide a detailed taxonomy and analysis of the main approaches. Next, we summarize the benchmarks, covering technical implementations, standardized datasets, and some more details as a library [link]. Last, we sketch out related applications, discuss vital challenges, and suggest potential future directions. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction

arXiv

引用

arXiv 2023年

作者： Sun, Kai Zhang, Richong Mensah, Samuel Aletras, Nikolaos Mao, Yongyi Liu, Xudong Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China Department of Computer Science University of Sheffield Sheffield United Kingdom School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expressed. Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios, where the testing and training distributions differ. Most methods use domain adversarial neural networks that aim to reduce the domain gap between the labelled source and unlabelled target domains to improve target domain performance. However, this approach only aligns feature distributions and does not account for class-wise feature alignment, leading to suboptimal results. Semi-supervised learning (SSL) has been explored as a solution, but is limited by the quality of pseudo-labels generated by the model. Inspired by the theoretical foundations in domain adaptation [2], we propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagree on the unlabelled target data, in an effort to boost the target domain performance. Extensive experiments on benchmark cross-domain OTE datasets show that this approach is effective and performs consistently well in settings with large domain shifts. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

IMF: Interactive Multimodal Fusion Model for Link Prediction

arXiv

引用

arXiv 2023年

作者： Li, Xinhang Zhao, Xiangyu Xu, Jiaxing Zhang, Yong Xing, Chunxiao Department of Computer Science and Technology Tsinghua Univerisity Beijing China School of Data Science City Univerisity of Hong Kong Hong Kong School of Computer Science and Engineering Nanyang Technological Univerisity Singapore Singapore

Link prediction aims to identify potential missing triples in knowledge graphs. To get better results, some recent studies have introduced multimodal information to link prediction. However, these methods utilize multimodal information separately and neglect the complicated interaction between different modalities. In this paper, we aim at better modeling the inter-modality information and thus introduce a novel Interactive Multimodal Fusion (IMF) model to integrate knowledge from different modalities. To this end, we propose a two-stage multimodal fusion framework to preserve modality-specific knowledge as well as take advantage of the complementarity between different modalities. Instead of directly projecting different modalities into a unified space, our multimodal fusion module limits the representations of different modalities independent while leverages bilinear pooling for fusion and incorporates contrastive learning as additional constraints. Furthermore, the decision fusion module delivers the learned weighted average over the predictions of all modalities to better incorporate the complementarity of different modalities. Our approach has been demonstrated to be effective through empirical evaluations on several real-world datasets. The implementation code is available online at https://***/HestiaSky/IMF-Pytorch. © 2023, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Leaf Disease Identification using ResNet

Leaf Disease Identification using ResNet

引用

Artificial Intelligence and Knowledge Discovery in Concurrent engineering (ICECONF), International Conference on

作者： P. Sirenjeevi J. Madhu Karthick K. Agalya R. Srikanth T. Elangovan R. Nareshkumar Department of Artificial Intelligence and Data Science SRM Valliammai Engineering College Kattankulathur Chennai Department of Computer Science and Engineering A.V. C. College of Engineering Mayiladuthurai Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Department of Computer Science and Engineering Karpagam Academy of Higher Education Eachanari Coimbatore Department of Networking and Communication SRM Institute of Science and Technology Kattankulathur Chennai

The study of leaf diseases, as well as their detection and diagnosis, has been the subject of an increasing amount of research and attention as intelligent agricultural systems have become increasingly common and widely used. In order to explore the detection and classification of apple leaf illnesses, we made use of data sets containing examples of apple grey-spot disease, black star disease, cedar rust disease, and healthy leaves. SVM classifier for image segmentation, ResNet and VGG convolutional neural network models were utilized for comparison and improvement respectively. In our prosed method ResNet-18, which had less layers of the ResNet network, achieved greater recognition effects by obtaining an accuracy rate of 98.5 percent.

关键词： Support vector machines Deep learning Image segmentation Stars Transforms Knowledge discovery Hardware

来源：评论

学校读者我要写书评

暂无评论

Causal discovery with endogenous context variables

arXiv

引用

arXiv 2024年

作者： Günther, Wiebke Popescu, Oana-Iuliana Rabel, Martin Ninad, Urmi Gerhardus, Andreas Runge, Jakob Institute of Data Science Jena Germany Technische Universität Berlin Institute of Computer Engineering and Microelectronics Berlin Germany Dresden Germany Technische Universität Dresden Faculty of Computer Science Dresden Germany Leipzig Germany

Causal systems often exhibit variations of the underlying causal mechanisms between the variables of the system. Often, these changes are driven by different environments or internal states in which the system operates, and we refer to context variables as those variables that indicate this change in causal mechanisms. An example are the causal relations in soil moisture-temperature interactions and their dependence on soil moisture regimes: Dry soil triggers a dependence of soil moisture on latent heat, while environments with wet soil do not feature such a feedback, making it a context-specific property. Crucially, a regime or context variable such as soil moisture need not be exogenous and can be influenced by the dynamical system variables – precipitation can make a dry soil wet – leading to joint systems with endogenous context variables. In this work we investigate the assumptions for constraint-based causal discovery of context-specific information in systems with endogenous context variables. We show that naive approaches such as learning different regime graphs on masked data, or pooling all data, can lead to uninformative results. We propose an adaptive constraint-based discovery algorithm and give a detailed discussion on the connection to structural causal models, including sufficiency assumptions, which allow to prove the soundness of our algorithm and to interpret the results causally. Numerical experiments demonstrate the performance of the proposed method over alternative baselines, but they also unveil current limitations of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Optimizing Mobile Advertising with Reinforcement Learning and Deep Neural Networks

Optimizing Mobile Advertising with Reinforcement Learning an...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Nimma, Divya Kaur, Chamandeep Chhabra, Gunjan Selvi, V. Tyagi, Divya Balakumar, A. University of Southern Mississippi Data Analyst in UMMC United States Jazan University Department of Computer Science & Information Technology Jizan Saudi Arabia Graphic Era Hill University Dehradun Graphic Era Deemed to Be University Department of CSE Uttarakhand Dehradun India Mother Teresa Women's University Department of Computer Science Kodaikanal India Sanskaram University Haryana Jhajjar India K. Ramakrishnan College of Engineering Department of ECE Trichy India

ISBN: (纸本)9798331517953

Mobile advertising is also closely associated with contemporary digital marketing channels, where the projective targeting is critical in regard to businesses' potential performance. This research makes use of a combination of machine learning and reinforcement learning (RL) to determine the best place to post an ad considering the users' demographic and behavior. Deepening the neural networks (DNNs) in this regard, the method is expected to advance the efficiency of mobile advertising while delivering more relevant content to the target user. Purchasing tendency predictions in the report are based on Python-based models through a dataset from Kaggle that has incorporated user demographics (Gender, Age, Estimated Salary) and purchasing patterns. The missing values are first handled using the different techniques then normalization of the numerical data and one hot coding of the features such as the Device Type and the Location. Automatic feature are extracted with the help of DNNs which obviate the process of feature extraction. This approach proposed yielded an accuracy level of 98% a higher level as compared to the CNN and LSTM models. For decision-making reinforcement learning is used with the help of Deep Q-Network (DQN) and Policy gradient. DQNs predict Q-values for the actions (ad displays) and choose the best action, while Policy Gradient methods directly learn the policy by modifying the probabilities related to the actions based on the users' behavior. The training techniques used on both models include backpropagation and stochastic gradient descent, which enables the RL agent in the continuous implementation of better ad placement strategies. Here they used DNN to train the features and RL to optimize the training and then improve the on average click through rates and conversion rates which provides a better strategy towards advertising. © 2024 IEEE.

关键词： deep neural networks feature extraction machine learning Mobile advertising reinforcement learning

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：