检索结果-内蒙古大学图书馆

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Hang, Liu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

Although the current point cloud upsampling techniques are already capable of attaining arbitrary upsampling rates af-ter one training. However, during the upsampling process, it may be difficult to preserve the fine geometric details in the original point cloud, resulting in insufficient detail in the up-sampled results and poor performance on our collected leg da-taset. Moreover, the network structure of this method is relatively complex, with high computational complexity and in-creased training costs. To tackle the issues mentioned above, we propose a new attention enhanced multi-scale feature extraction method. First, we extract local features through multilayer perceptron, and then extract important channel and spatial feature information through attention mechanisms to obtain multi-scale feature representations for learning point-to-point distances. Compared with the Grad-PU method, our method reduces the size of network parameters by 54.41%, experi-mental results demonstrate that our approach achieves the state-of-the-art upsampling performance. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Homomorphic Encryption Library, Framework, Toolkit and Accelerator: A Review

引用

SN computer science 2024年第1期5卷 24页

作者： Dhiman, Shalini Mahato, Ganesh Kumar Chakraborty, Swarnendu Kumar Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Jote 791113 India

Homomorphic encryption ensures secure computation on encrypted data without the need for decryption beforehand. It enables the secure offloading of computations to untrusted servers. This paper provides a comprehensive description of multiple methods for conducting secure computations, along with the appropriate approaches and tools needed for successful implementation. Various strategies are outlined for selecting a suitable homomorphic encryption (HE) library, assisting developers and researchers in determining the most suitable library for their projects. To begin with, the paper presents a comparison of homomorphic encryption libraries based on different parameters. Additionally, it outlines the steps involved in choosing the right framework for effective implementation, comparing them based on various parameters. The Framework discussed in the paper supports a range of homomorphic encryption libraries and provides detailed information about them. Furthermore, the paper surveys three different homomorphic encryption accelerators and compares them to determine which one would maximize bootstrapping throughput when implemented. Lastly, the Fully Homomorphic Encryption-IBM toolkit is discussed. This toolkit supports the development of resources, primarily involved in the flow of messages. The paper concludes that secure computation is achievable by implementing the appropriate tools, considering their performance and implementation limitations. Moreover, the selection of the appropriate library, framework, and accelerator depends on the specific demands and requirements of the implementation chosen by the developer. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Evervault encryption engine HEaaN Homomorphic encryption IBM toolkit MS SEAL Pallisade

来源：评论

学校读者我要写书评

暂无评论

Empirical Investigation on Similarity Measures used in Recommendation Systems 15

Empirical Investigation on Similarity Measures used in Recom...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Chaparala, Pushya Muppa, Lakshmi Durga Shaik, Asma Vignan's Foundation for Science Technology and Research Department of Computer Science and Engineering Guntur India

ISBN: (纸本)9798350370249

Similarity measures play a crucial role in recommendation systems for quantifying the likeness between users or items within the system. These measures are fundamental in collaborative filtering, a widely used approach for generating personalized recommendations. This study analyses 29 distinct similarity measures including common one like Cosine, Jaccard, using metrics like recall, precision, and diversity on datasets like MovieLens and Bookcrossing. Findings from the result revealed that certain measures, such as PIP (Proximity Impact Popularity), CPCC (Constrained Pearson Correlation Coefficient), NHSM (New Heuristic Similarity Model), and COD (Adjusted Cosine Measure), consistently outperform others, particularly in aligning with user preferences due to consideration of rating scale differences, integration of multiple similarity aspects, and normalization of shared ratings. This paper underscores the critical role of selecting appropriate similarity measures to enhance recommendations and user satisfaction in collaborative filtering - based systems. © 2024 IEEE.

关键词： Collaborative filtering(CF) Content-based filtering(CB) Diversity Hybrid filtering(HF) Precision Recall Recommendation systems

来源：评论

学校读者我要写书评

暂无评论

Modeling and Evaluating Stock Market and Commodity Price Fluctuation Using Time Series Sequence Learning

引用

SN computer science 2025年第5期6卷 1-18页

作者： Veningston, K. Ronalda, M. Shaikh, Tawseef Ayoub Gazi, Farhaan Bhagat, Sanket Department of Computer Science and Engineering National Institute of Technology Srinagar Jammu and Kashmir Srinagar 190006 India

Algorithmic trading using neural network models has gained significant attention in predicting stock and commodity price fluctuations and understanding their dynamics. Deep learning techniques have shown significant results in predicting stock market prices in recent years. Modelling stock market price dynamics using sequence learning techniques leverages the historical trends and dependencies in price data to predict future price movements. This paper presents a comprehensive analysis of Autoregressive Integrated Moving Average (ARIMA), standard neural network, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) for forecasting stock movements in various industry stocks. The main objective is to assess the performance of each model in predicting stock price fluctuations. Each model undergoes systematic validation and evaluation based on key performance indicators such as accuracy, normalised root mean squared error (NRMSE), and Weighted Mean Absolute Percentage Error (WMAPE). The forecast made by each model is compared to the actual stock prices to measure the effectiveness of the forecasting methods. This paper presents a time series sequence learning approach for modelling and evaluating stock market price fluctuation. The proposed approach uses an LSTM network to learn the sequential patterns in stock price data. The LSTM network is trained on a historical dataset of stock prices, and it is then used to predict future stock prices. The proposed approach is evaluated on a dataset of stock prices from seven different industry domains, including Investment, Infrastructure, Information technology, Pharma, Fast Moving Consumer Goods and agri-business (FMCG), Vehicles, and Banking, which enables a comprehensive evaluation of various models. The results show that the proposed LSTM approach can achieve notable accuracy in predicting future stock prices. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Lt

关键词： Algorithmic trading Sequence learning Share price dynamics Stock market price forecast Time-series analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Detection of Fungal Diseases in Apple Plants Using YOLOv8 Algorithm

Deep Learning-Based Detection of Fungal Diseases in Apple Pl...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： BalaChandralekha, S. Thangakumar, J. Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350364828

Over the last decade, the identification of plant illnesses by automatic means has become a challenging field. In recent times, computer vision has made it feasible to identify diseases quickly and accurately, which has enhanced yield by allowing for the necessary treatment. Graph Neural Networks (GNNs), Convolutional Neural Networks (CNNs), Faster-CNN, Mask R-CNN, Siamese Networks, are the models built on deep learning have been applied to diagnose and cure crop disease. These models accomplish well when it comes to identifying plant diseases, but they have trouble with complex field images and frames with several leaves. The goal of this study is to enhance their application in real-world agriculture, where problems with intricate images and multiple leaves are frequent. This paper uses a YOLOv8 model to identify fungal diseases that affect apple leaves, including cedar rust, scab leaves, and black rot. The dataset used for the implementation was gathered from a Kaggle of 540 images, and the model obtained 86% mAP, outperforming the existing YOLOX model which has achieved 73%mAP. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Images Connect Us Together: Navigating a COVID-19 Local Outbreak in China Through Social Media Images

引用

Proceedings of the ACM on Human-computer Interaction 2024年第CSCW1期8卷 1-32页

作者： He, Changyang He, Lu Yang, Wenjie Li, Bo Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Zilber College of Public Health University of Wisconsin-Milwaukee Milwaukee United States

Social media images, curated or casual, have become a crucial component of communicating situational information and emotions during health crises. Despite its prevalence and significance in informational dissemination and emotional connection, there lacks a comprehensive understanding of visual crisis communication in the aftermath of a pandemic which is characterized by uncertain local situations and emotional fatigue. To fill this gap, this work collected 345, 423 crisis-related posts and 65, 376 original images during the Xi'an COVID-19 local outbreak in China, and adopted a mixed-methods approach to understanding themes, goals, and strategies of crisis imagery. Image clustering captured the diversity of visual themes during the outbreak, such as text images embedding authoritative guidelines and "visual diaries" recording and sharing the quarantine life. Through text classification of the post that visuals were situated in, we found that different visual themes highly correlated with the informational and emotional goals of the post text, such as adopting text images to convey the latest policies and sharing food images to express anxiety. We further unpacked nuanced strategies of crisis image use through inductive coding, such as signifying authority and triggering empathy. We discuss the opportunities and challenges of crisis imagery and provide design implications to facilitate effective visual crisis communication. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Behavior Using a Neutrosophic Deep Learning Model

引用

Neutrosophic Sets and Systems 2025年 76卷 288-310页

作者： Shitaya, Ahmed Mohamed Wahed, Mohamed El Syed Abd El Khalek, Saied Helemy Ismail, Amr Shams, Mahmoud Y. Salama, A.A. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Computer Science Faculty of computer and information sciences Suez Canal University Egypt Department. of Communication and Computer Engineering Air Defense University Egypt Department of Cybersecurity College of Engineering and Information Technology Buraydah Private Colleges Buraydah51418 Saudi Arabia Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt

We developed an information system using an object-oriented programming language and a distributed database (DDB) consisting of multiple interconnected databases across a computer network, managed by a distributed database management system (DDBMS) for easy access. An intelligent system was designed to assess the difficulty level of preliminary exams and select top-performing advanced students using a Neutrosophic Deep Learning Model. The dataset was randomly split into training (80%) and testing (20%) sets, and the model, trained with the Adam optimizer at a 0.001 learning rate over 50 epochs, incorporated early stopping based on validation loss. This system, implemented at a traditional Egyptian university, achieved a 95% accuracy in predicting student dropout. Student behavior, influenced by personal, environmental, and academic factors, is often evaluated subjectively, leading to inconsistent results. Traditional machine learning approaches struggle with the inherent uncertainty in behavioral data. To address this, we combined neutrosophic theory—a mathematical framework that accounts for truth, falsity, and indeterminacy—with deep learning, which excels at learning complex data relationships, to predict student outcomes such as dropout rates. Evaluating the model on student data, including attendance and grades, showed superior accuracy, achieving a determination coefficient of 0.95, demonstrating the approach's potential for identifying at-risk students and enabling targeted interventions. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

MASK6D: MASKED POSE PRIORS FOR 6D OBJECT POSE ESTIMATION 49

MASK6D: MASKED POSE PRIORS FOR 6D OBJECT POSE ESTIMATION

引用

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024

作者： Xie, Yuechen Jiang, Haobo Xie, Jin PCA Lab School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9798350344851

Robust 6D object pose estimation in cluttered or occluded conditions using monocular RGB images remains a challenging task. One reason is that current pose estimation networks struggle to extract discriminative, pose-aware features using 2D feature backbones, especially when the available RGB information is limited due to target occlusion in cluttered scenes. To mitigate this, we propose a novel pose estimation-specific pre-training strategy named Mask6D. Our approach incorporates pose-aware 2D-3D correspondence maps and visible mask maps as additional modal information, which is combined with RGB images for the reconstruction-based model pre-training. Essentially, this 2D-3D correspondence maps a transformed 3D object model to 2D pixels, reflecting the pose information of the target in camera coordinate system. Meanwhile, the integrated visible mask map can effectively guide our model to disregard cluttered background information. In addition, an object-focused pre-training loss function is designed to further facilitate our network to remove the background interference. Finally, we fine-tune our pre-trained pose prior-aware network via conventional pose training strategy to realize the reliable pose prediction. Extensive experiments verify that our method outperforms previous end-to-end pose estimation methods. © 2024 IEEE.

关键词： Object Pose Estimation Prior Learning Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Intensify Stroke Prediction Model Associated with Hypertensive State 3

Intensify Stroke Prediction Model Associated with Hypertensi...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Islam, Md. Rabiul Rahman, Mst. Sahela Paul, Radha Rani Hosen, Md. Fahad Khairunnahar, Mst. Nayeem, Md. Julker Pundra University of Science & Technology Dept. of Computer Science & Engineering Bogura5800 Bangladesh

ISBN: (纸本)9798350388282

Hypertension and stroke are significant worldwide health issues with high prevalence and complex health hazards. Hypertensive state implications include death or major complications such as myocardial infarction. This study leverages data from the Internet to foresee the prognosis for individuals with hypertensive strokes. There are two main components to the clinical outcome prediction in this study. The value of various variables is ranked by our model through the use of cross-validation techniques, recursive feature disposal, and classification algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). Our empirical cross-validation results demonstrate the remarkable predictive reliability of both LR and RF once repetitive features are removed, even with a smaller set of features and classifiers. Particularly in terms of accuracy, F1 score, and area under the receiver operating characteristic curve (AUC), logistic regression performs better than the other two classifiers. Likewise, we conducted independent prediction analyses for hypertension, hypertensive stroke, and stroke. The highest result of 96.15% is obtained using logistic regression for stroke prediction. The random forest classifier has an accuracy of 91.25% for hypertension, and combining stroke with a hypertension support vector classifier gives 91.72% accuracy. This demonstrates how well it might provide patients with hypertensive strokes with precise and trustworthy projections. Finally, our study illuminates the potentially useful prediction powers of particular algorithms in determining the prognosis of patients with hypertensive strokes. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Automated Lip Reading for Deaf 3

Deep Learning Based Automated Lip Reading for Deaf

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Prathyakshini Prathwini Pratheeksha Hegde, N. Vaishali Rashmi, N. Kumar, Archana Praveen NMAM Institute of Technology Department of Information Science and Engineering Karkala Nitte India NMAM Institute of Technology Department of Master of Computer Applications Karkala Nitte India NMAM Institute of Technology Department of Computer Science and Engineering Karkala Nitte India Manipal Academy of Education Manipal Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798350354171

Speech recognition systems play an integral role in numerous applications, from virtual assistants to accessibility tools. This paper offers a new viewpoint to speech recognition utilizing computer vision and deep learning techniques. The proposed system is trained on a sizable dataset comprising 700 video clips of individuals uttering predefined words, add up to approximately 3 GB of data. Leveraging TensorFlow and Keras, model architecture is designed incorporating convolutional and dense layers. The training process yielded promising results, with a training accuracy of 95.7% and a validation accuracy of 98.5%, indicative of robust classification performance. The integration of computer vision enriches the system's ability to extract meaningful features from audio-visual inputs, enhancing its overall recognition accuracy. Proposed method demonstrates significant potential for real-time speech recognition applications in different areas, like human-computer interaction and assistive technologies. © 2024 IEEE.

关键词： Assistive technology

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：