检索结果-内蒙古大学图书馆

2nd International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2023

作者： Lohith, N. Adnan Raqeeb, S. Sai Manoj Reddy, Poreddy Sunil Kumar, Chekuri Venkata Anand Kumar, M. Chakravarthi, Bharathi Raja Department of Information Technology National Institute of Technology Karnataka Surathkal India Insight SFI Research Centre for Data Analytics Data Science Institute National University of Ireland Galway Galway Ireland

ISBN: (纸本)9783031584947

Everyone now uses social media to communicate information and ideas, which has become a requirement for everyone. Social media posts can offend people or be helpful or educational for them. Memes are one type of media that is disseminated in this way through direct messages, videos, or photographs. A meme is an image or video that captures the opinions and sentiments of a particular group of people. Memes can be trolling or not, and they include an image and text that express an emotion. Most memes are unique to a particular linguistic group of people. The most frequent cause of this is different languages. Memes must be categorized since studying them can help us understand the interests of each user. As both are necessary for interpretation, the meme cannot be considered acceptable if we only gaze at the text or the image. In this article, we provided a method for categorizing memes in Telugu that considers both the meme’s text and visual features, classifies trolling and non-trolling memes, attempt to determine the emotion the meme conveys and categorizes the meme according to the domain it belongs to. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks 38

The Map Equation Goes Neural: Mapping Network Flows with Gra...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Blöcker, Christopher Tan, Chester Scholtes, Ingo Data Analytics Group Department of Informatics University of Zurich Switzerland Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science Julius-Maximilians-Universität Würzburg Germany

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lifelong Graph Learning for Graph Summarization

arXiv

引用

arXiv 2024年

作者： Frank, Jonatan Hoffmann, Marcel Lell, Nicolas Richerby, David Scherp, Ansgar Data Science and Big Data Analytics Ulm University Germany University of Essex Colchester United Kingdom

Summarizing web graphs is challenging due to the heterogeneity of the modeled information and its changes over time. We investigate the use of neural networks for lifelong graph summarization. After observing the web graph at a point in time, we train a network to summarize graph vertices. We apply this trained network to summarize the vertices of the changed graph at the next point in time. Subsequently, we continue training and evaluating the network to perform lifelong graph summarization. We use the GNNs Graph-MLP and GCN, as well as an MLP baseline, to summarize the temporal graphs. We compare 1-hop and 2-hop summaries. We investigate the impact of reusing parameters from a previous snapshot by measuring backward and forward transfer as well as forgetting rate. Our extensive experiments are on two series of ten weekly snapshots, from 2012 and 2022, of a web graph with over 100M edges. They show that all networks predominantly use 1-hop information to determine the summary, even when performing 2-hop summarization. Due to the heterogeneity of web graphs, in some snapshots, the 2-hop summary produces up to ten times as many vertex classes as the 1-hop summary. When using the network trained on the last snapshot from 2012 and applying it to the first snapshot of 2022, we observe a strong drop in accuracy. We attribute this drop over the ten-year time warp to the strongly increased heterogeneity of the web graph in 2022. The source code and additional resources are available at https://***/jofranky/ Lifelong-Graph-Summarization-with-Neural-Networks. Copyright © 2024, 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

Enhancement of PVDF/LiCl membrane performance by modifying the membrane surface using zeolite NaY and ZCC spray coating method for Dunaliella salina microalgae dewatering

引用

Materials Today: Proceedings 2022年 65卷 2940-2945页

作者： Widiastuti, Nurul Sukma Ningtiar, Ellyzia Nafilah, Fitrin Tamam Ibnu Ali, Badrut Setyo Purnomo, Adi Qodar Romadiansyah, Taufik Department of Chemistry Institut Teknologi Sepuluh Nopember Faculty of Science and Data Analytics Surabaya Sukolilo 60111 Indonesia

Utilization of Dunaliella salina microalgae as a raw material for bioethanol production encountered problems in terms of harvesting microalgae. The dilute solution and the size of the microalgae are too small to be a challenge in harvesting microalgae. In this study, the surface modification of PVDF/LiCl membrane with Zeolite NaY and Zeolite-Carbon Composite (ZCC) was carried out by spray coating for harvesting Dunaliella salina microalgae. Zeolite NaY was synthesized by hydrothermal method at 100 °C for 7 h and ZCC was synthesized by sucrose impregnation on zeolite. All membranes were characterized using Scanning Electron Microscope (SEM) and Fourier Transform Infra Red (FTIR) instruments, as well as Water Contact Angle (WCA) test and membrane performance test for harvesting Dunaliella salina microalgae The results showed that Zeolite NaY and ZCC coatings have been shown to increase the hydrophilicity and performance of PVDF/LiCl membranes for harvesting Dunaliella salina microalgae. The increase in the hydrophilicity of the membrane was indicated by decreasing the contact angle of the PVDF/LiCl membrane from 84.14° to 69.2° for 0.10% PVDF/LiCl/ZCC membrane. The coating of zeolite NaY 0.15% into PVDF/LiCl membrane enhanced the permeability from 148.53 ± 32.98 L/m2h to 173.40 ± 8.42 L/m2h, while the coating of 0.10% ZCC into PVDF/LiCl membrane enhanced the water permeability into 208.48 ± 27.99 L/m2h. Furthermore, the selectivity also increased from 97.64% to 100% rejection in microalgae dewatering process. This shows that selectively modified zeolite NaY and ZCC membranes are only able to pass seawater as a microalgae culture medium. © 2022

关键词： Microalgae

来源：评论

学校读者我要写书评

暂无评论

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimizing Radiotherapy Treatment Plans in Oropharyngeal Cancer

DE-ConvGraph 3D UNet: A Novel Deep Learning Model for Optimi...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Murugadoss, Bhuvanashree Amudha, J. Sugumaran, Vijayan Amrita Vishwa Vidyapeetham School of Computing Department of Computer Science and Engineering Karnataka Bengaluru India Oakland University Center for Data Science and Big Data Analytics RochesterMI United States Oakland University Department of Decision and Information Sciences RochesterMI United States

ISBN: (纸本)9798350359527

Automated radiotherapy treatment planning aims to improve treatment accuracy and efficiency. However, the prevalent Knowledge-Based Planning (KBP) method faces issues like lengthy manual problem formulation and challenges in accurately modeling human anatomy and processing high-dimensional data. This work focuses on treatment plan optimization and considers deep learning as a potential solution. Deep learning algorithms, by virtue of their ability to learn from large quantities of data and model complex relationships, can automate the formulation of the optimization problem in KBP, saving significant time and effort. However, despite these compelling advantages, it should be noted that the current convolution-based encoder-decoder models used for radiotherapy treatment plan optimization have a limited capability in capturing long-range dependencies between distant voxels. This work aims to introduce 'DE-ConvGraph 3D UNet', a novel deep learning model, to address these limitations and optimize radiotherapy treatment plans for oropharyngeal cancer. The proposed 'DE-ConvGraph 3D UNet' model includes a Graph Convolutional Network (GCN) component to capture long-range dependencies between distant voxels. Furthermore, the dual-encoder structure of the model combines the strengths of GCN and 3D Convolutional U-Net, enabling global relationships and local pattern capturing in a 3D patient volume. Experiments were conducted using the benchmark dataset-OpenKBP-Opt. The proposed model shows improvements in performance in comparison to state-of-The-Art U-Net variants in terms of mean squared voxel-wise error, dose volume histogram points and clinical criteria satisfaction. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Response to yarmolinsky, tzoulaki, gunter, et al

引用

Journal of the National Cancer Institute 2024年第5期116卷 766-767页

作者： Jing Sun Xue Li Department of Big Data in Health Science School of Public Health and Center of Clinical Big Data and Analytics of The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou Zhejiang China.

来源：评论

学校读者我要写书评

暂无评论

Cancer Diseases Diagnosis Using Deep Transfer Learning Architectures 1st

Cancer Diseases Diagnosis Using Deep Transfer Learning Archi...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Promy, Tania Ferdousey Joya, Nadia Islam Turna, Tasfia Haque Sukhi, Zinia Nawrin Ashraf, Faisal Bin Uddin, Jia Department of Computer Science and Engineering School of Data Science Brac University Dhaka Bangladesh AI and Big Data Department Endicott College Woosong University Daejeon Korea Republic of

ISBN: (纸本)9783031346187

Cancer is a lethal disease among the diseases in the world. It is clinically known as ‘Malignant Neoplasm’ which is a vast group of diseases that encompasses unmonitored cell expansion. It can begin anywhere in the body such as the breast, skin, liver, lungs, brain, and so on. As reported by the National Institutes of Health (NIH), the projected growth of new cancer cases is forecast at 29.5 million and cancer-related deaths at 16.4 million through 2040. There are many medical procedures to identify the cancer cell, such as mammography, MRI, CT scan, which are common methods for cancer diagnosis. The methods used above have been found to be ineffective and necessitate the development of new and smarter cancer diagnostic technologies. Persuaded by the phenomena of medical image classification using deep learning, our recommended initiative targets to analyze the performance of different deep transfer learning models for cancer cell diagnosis. In this paper, we have used VGG16, Inception V3 and MobileNet V2 deep architectures to diagnosis the breast cancer (KAU-BCMD dataset), lung cancer (IQ-OTH/NCCD dataset) and skin cancerHam10000). Experimental results demonstrate that VGG16 architecture shows comparatively higher accuracy by exhibiting 98.5% of accuracy for breast cancer, 99.90% for lung cancer and 93% for skin cancer dataset. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Special Topic on Reinforcement Learning and Intelligent Decision

引用

ZTE Communications 2023年第3期21卷 1-2页

作者： GAO Yang Department of Computer Science and Technology Nanjing University National Institute of Healthcare Big Data at Nanjing University

Over the past few years,deep reinforcement learning(RL)has made remarkable progress in a range of applications,including Go games,vision-based control,and generative dialogue *** error-and-trial mechanisms,deep RL enables data-driven optimization and sequential decision-making in uncertain *** to traditional programming or heuristic optimization methods,deep RL can elegantly balance exploration and exploitation and handle environmental *** a result,this learning paradigm has attracted increasing attention from both academia and industry and is paving a new path for largescale complex decision-making applications.

关键词： handle optimization programming

来源：评论

学校读者我要写书评

暂无评论

A Case Study on Economic Impact Assessment of Developing Single Drill Level in Sublevel Stoping Method

引用

Journal of The Institution of Engineers (India): Series D 2024年第1期105卷 119-125页

作者： Samanta, Gopinath Sinha, Suranjan Dey, Tapan Process Technology Group Tata Steel Ltd. Jamshedpur831001 India Department of Mining Engineering Bengal Engineering and Science University Shibpur711103 India Data and Analytics TCS Kolkata700156 India

Sublevel stoping is one of the most successful mining methods in respect of higher production, mechanization and safety. The method is a cost-effective and safe mining solution for steeply dipping vein deposits where high-level mechanization can be adopted. Progress of stope development and rate of production drilling are vital aspects in mine economics and profitability. Any change in the stope design stage effect total stope development, production drilling and explosive consumption. Hence, to optimize the mining cost and to maintain sustainable ore production by preparing stope ready for production in lesser time, an innovative stope design solution and drilling and blasting design can be applied in the sublevel stoping method. In this paper, a case study has been discussed and analyzed from an Indian copper mine where stope design practice was changed from two sub-level to a single sub-level. This modification leads to a change in production drilling design with a 115 mm diameter hole in place of a 57 mm diameter hole. The explosive consumption is also varying with this change in mining method. From the case study in five stopes, it has been observed that the development and drilling costs have been reduced by 32% each. Although the explosive cost is slightly increasing, the overall cost is reduced by 24% in the modified design with the single sublevel stoping method. The stope preparation time is reduced by five months on average for each stope. Hence, the modified stope design, as per results available from the case study area are encouraging and this modified method can be widely applied in different mines. © The Institution of Engineers (India) 2023.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Wheat Leaf Disease Identification Based on a Fusion Model Integrating Attention Mechanisms and Channel-Spatial Reconstruction Convolution 5

Wheat Leaf Disease Identification Based on a Fusion Model In...

引用

5th International Conference on big data and Artificial Intelligence and Software Engineering, ICBASE 2024

作者： Xie, Haifan Zou, Rongxin Yang, Zicong Jin, Aitong Wang, Junxi Li, Yu Zhuhai College of Science and Technology Department of Computer Zhuhai China Zhuhai College of Science and Technology Department of Big Data Zhuhai China Institute of Intelligent Manufacturing and Aviation Zhuhai College of Science and Technology ZhuHai China Zhuhai College of Science and Technology Alibaba Cloud Big Data Application College Zhuhai China

ISBN: (纸本)9798331506612

With the continuous growth in food demand and the escalating importance of crop health, the challenges posed by the high costs and low efficiency of traditional wheat leaf disease detection methods have become increasingly acute. In light of the intricacies and low discernibility of the morphological and color characteristics of wheat leaf diseases and pests in natural environments, this study introduces a novel and efficient recognition and classification model, SCC2f-CSPDarknet53-CBAM, offering a precise and rapid solution for identifying diseases and pests, thereby supporting early prevention and scientific management. By incorporating the SCC-C2f module into the base of C2f-CSPDarknet53, this model enhances the efficiency of network feature fusion and the capability to extract critical features. Furthermore, the integration of the ResBlock-CBAM module at the terminal end bolsters the generalization and recognition abilities for targets. The study employs the Wheat Leaf Disease dataset, which is constructed through a blend of online and offline methods, with meticulous data processing, for training purposes. Experimental results reveal that the SCC2f-CSPDarknet53-CBAM model achieves an average recognition accuracy of 99.54% in the task of wheat leaf disease detection and classification, surpassing mainstream models in recent years, showcasing remarkable accuracy and adaptability. © 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

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：