检索结果-内蒙古大学图书馆

DeepSeq2Drug: An expandable ensemble end-to-end anti-viral drug repurposing benchmark framework by multi-modal embeddings and transfer learning

引用

computers in Biology and Medicine 2024年 175卷 108487-108487页

作者： Xie, Weidun Yu, Jixiang Huang, Lei For, Lek Shyuen Zheng, Zetian Chen, Xingjian Wang, Yuchen Liu, Zhichao Peng, Chengbin Wong, Ka-Chun Department of Computer Science City University of Hong Kong Hong Kong SAR Kowloon Tong China Cutaneous Biology Research Center Massachusetts General Hospital Harvard Medical School BostonMA United States Sir William Dunn School of Pathology University of Oxford United Kingdom College of Information Science and Engineering Ningbo University Ningbo China Shenzhen Research Institute City University of Hong Kong Shenzhen China Hong Kong Institute for Data Science City University of Hong Kong Hong Kong SAR Kowloon Tong China

Drug repurposing is promising in multiple scenarios, such as emerging viral outbreak controls and cost reductions of drug discovery. Traditional graph-based drug repurposing methods are limited to fast, large-scale virtual screens, as they constrain the counts for drugs and targets and fail to predict novel viruses or drugs. Moreover, though deep learning has been proposed for drug repurposing, only a few methods have been used, including a group of pre-trained deep learning models for embedding generation and transfer learning. Hence, we propose DeepSeq2Drug to tackle the shortcomings of previous methods. We leverage multi-modal embeddings and an ensemble strategy to complement the numbers of drugs and viruses and to guarantee the novel prediction. This framework (including the expanded version) involves four modal types: six NLP models, four CV models, four graph models, and two sequence models. In detail, we first make a pipeline and calculate the predictive performance of each pair of viral and drug embeddings. Then, we select the best embedding pairs and apply an ensemble strategy to conduct anti-viral drug repurposing. To validate the effect of the proposed ensemble model, a monkeypox virus (MPV) case study is conducted to reflect the potential predictive capability. This framework could be a benchmark method for further pre-trained deep learning optimization and anti-viral drug repurposing tasks. We also build software further to make the proposed model easier to reuse. The code and software are freely available at http://***. © 2024

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Joint User Scheduling and Computing Resource Allocation Optimization in Asynchronous Mobile Edge Computing Networks

arXiv

引用

arXiv 2024年

作者： Cang, Yihan Chen, Ming Pan, Yijin Yang, Zhaohui Hu, Ye Sun, Haijian Chen, Mingzhe The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211100 China College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China International Joint Innovation Center Zhejiang University Haining314400 China Hangzhou310027 China The Department of Industrial and System Engineering University of Miami Coral GablesFL33146 United States The School of Electrical and Computer Engineering The University of Georgia AthensGA30602 United States The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States

In this paper, the problem of joint user scheduling and computing resource allocation in asynchronous mobile edge computing (MEC) networks is studied. In such networks, edge devices will offload their computational tasks to an MEC server, using the energy they harvest from this server. To get their tasks processed on time using the harvested energy, edge devices will strategically schedule their task offloading, and compete for the computational resource at the MEC server. Then, the MEC server will execute these tasks asynchronously based on the arrival of the tasks. This joint user scheduling, time and computation resource allocation problem is posed as an optimization framework whose goal is to find the optimal scheduling and allocation strategy that minimizes the energy consumption of these mobile computing tasks. To solve this mixed-integer non-linear programming problem, the general benders decomposition method is adopted which decomposes the original problem into a primal problem and a master problem. Specifically, the primal problem is related to computation resource and time slot allocation, of which the optimal closed-form solution is obtained. The master problem regarding discrete user scheduling variables is constructed by adding optimality cuts or feasibility cuts according to whether the primal problem is feasible, which is a standard mixed-integer linear programming problem and can be efficiently solved. By iteratively solving the primal problem and master problem, the optimal scheduling and resource allocation scheme is obtained. Simulation results demonstrate that the proposed asynchronous computing framework reduces 87.17% energy consumption compared with conventional synchronous computing counterpart. Copyright © 2024, The Authors. All rights reserved.

关键词： Energy transfer

来源：评论

学校读者我要写书评

暂无评论

Harmonic attentive multimodal neural network for movie recommendation 4

Harmonic attentive multimodal neural network for movie recom...

引用

2020 4th International Workshop on Advanced Algorithms and Control engineering, IWAACE 2020

作者： Wang, J.X. Guo, Y. Qi, T.M. Tang, Q.F. Department of Computer Science and Engineering East China University of Science and Technology Shanghai200237 China Business Intelligence and Visualization Research Center National Engineering Laboratory for Big Data Distribution and Exchange Technologies Shanghai200436 China Shanghai Engineering Research Center of Big Data and Internet Audience Shanghai200072 China

A multimodal neural network based on harmonic self-attention was proposed for movie recommendation. This method can deal with the multi-source data and learn representations of users and items well. The multimodal neural network mainly consists of three sub-networks, ResNet, Bert, and LSTM. In addition, the harmonic self-attention mechanism can explore the user's preference from the perspective of time. Experimental results show that compared with other three latest recommendation methods, HSMNN shows better performance in terms of HR and NDCG. © Published under licence by IOP Publishing Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Intelligent waste sorting for sustainable environment: A hybrid deep learning and transfer learning model

引用

Gondwana research 2024年

作者： Kumar Lilhore, Umesh Simaiya, Sarita Dalal, Surjeet Radulescu, Magdalena Balsalobre-Lorente, Daniel Department of Computer Science and Engineering Galgotias University Greater Noida Uttar Pradesh India Department of Computer Science and Engineering Amity University Gurugram Haryana India Institute of Doctoral and Post-Doctoral Studies University Lucian Blaga of Sibiu Sibiu Romania UNEC Research Methods Application Center Azerbaijan State University of Economics (UNEC) Baku 1001 Istiqlaliyyat Str. 6 Azerbaijan Department of Applied Economics I University Castilla-La Mancha Spain Department of Management Faculty of Economics and Management Czech University of Life Sciences Prague Prague 16500 Czech Republic Economic Research Center (WCERC) Western Caspian University Baku Azerbaijan

The significance of waste disposal, classification, and monitoring has dramatically increased due to the increase in industrial development and the progress of intelligent urbanization. Since the last few decades, the utilization of Deep learning techniques has grown increasingly in waste management research. The efficiency of a waste reuse and recycling process relies on its capacity to restore resources to their original state, thereby minimizing pollution and promoting an ecologically sustainable framework. Selecting the optimal deep-learning method for classifying and predicting waste is challenging and time-consuming. This paper proposed intelligent garbage categorization using Bidirectional Long Short-Term Memory (Bi-LSTM) and CNN-based transfer learning to improve environmental sustainability. Organic and recyclable garbage are separated. To simplify trash categorization, a hybrid model combines TL-based CNN and Bi-LSTM. This study extensively examined the suggested technique with numerous CNN computational methods, including VGG-19, ResNet-34, AlexNet, ResNet-50, and VGG-16, using the ’TrashNet Waste’ database. Key findings show that our hybrid model outperforms existing models. Our classification accuracy is 96.78 %, 5.27 % higher than the best model. Our model also reduces misclassification by 7.25 %, proving its reliability. This comprehensive examination examined the computer models’ trash classification performance and provided specific viewpoints. The results explain each technique's pros and cons and show how useful they are in real-world circumstances. Waste classification is practical and sophisticated with a hybrid model. The effectiveness and cleverness of this model improve sustainable environmental practices. The proposed method's excellent performance suggests its seamless integration into practical waste management solutions. © 2024 International Association for Gondwana research

关键词： Convolutional neural network (CNN) Deep learning Smart Waste Management Transfer Learning Waste classification

来源：评论

学校读者我要写书评

暂无评论

ColonCLIP: An Adaptable Prompt-Driven Multi-Modal Strategy for Colonoscopy Image Diagnosis

ColonCLIP: An Adaptable Prompt-Driven Multi-Modal Strategy f...

引用

IEEE International Symposium on Biomedical Imaging

作者： Shuangyi Tan Yinqi Cai Xutao Lin Wei Qi Zhen Li Xiang Wan Guanbin Li The Chinese University of Hong Kong (Shenzhen) Shenzhen Research Institute of Big Data School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Department of Gastrointestinal Endoscopy Guangdong Provincial Key Laboratory of Colorectal and Pelvic Floor Diseases Biomedical Innovation Center The Sixth Affiliated Hospital Sun Yat-Sen University Department of Gastroenterology The Second Hospital of Hebei Medical University

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Colonoscopies serve as a pivotal instrument for colorectal cancer detection and diagnosis. Images in colonoscopy reports typically contain valuable information from the procedure, but manual annotation of these images is laborious and time-consuming due to the high volume of daily procedures. The situation is further complicated when a few images with new image categories reflecting the complex nature of colorectal conditions and the flexibility of annotations occur. Conventional uni-modal lesion classification models fall short in accommodating these new categories, while multi-modal finetuning methods often compromise the integrity of original category knowledge when integrating new ones, leading to subpar mixed-category test performance. In response to these challenges, we present the first comprehensive, open-access colonoscopy image diagnosis dataset OpenColonDB and introduce ColonCLIP. Through the integration of prompts during both training and testing, ColonCLIP effectively learns the features of basic categories and retains knowledge of these features even when a small amount of data with new categories is introduced. This ensures the accuracy of mixed category predictions after adaptation. Our experiments validate the efficacy of our approach, and the GitHub link is https://***/Zoe-TAN/ColonCLIP-OpenColonDB.

关键词： Training Annotations Instruments Colonoscopy Manuals Colorectal cancer Lesions

来源：评论

学校读者我要写书评

暂无评论

OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition

arXiv

引用

arXiv 2024年

作者： Xiang, Qiuchi Cheng, Jintao Luo, Jiehao Wu, Jin Fan, Rui Chen, Xieyuanli Tang, Xiaoyu School of Data Science and Engineering Xingzhi College South China Normal University Shanwei516600 China School of Electronic and Information Engineering South China Normal University Guangdong Foshan528225 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong College of Intelligence Science and Technology National University of Defense Technology Changsha China College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and realtime efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Adaptive Curriculum Learning for Semi-supervised Segmentation of 3D CT-Scans 28th

Adaptive Curriculum Learning for Semi-supervised Segmentati...

引用

28th International Conference on Neural Information Processing, ICONIP 2021

作者： Nartey, Obed Tettey Yang, Guowu Agyapong, Dorothy Araba Yakoba Wu, JinZhao Sarpong, Asare K. Frempong, Lady Nadia Big Data Research Center School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China The School of Computer Science and Electronic Information Guangxi University Nanning530004 China Biomedical Engineering Program Kwame Nkrumah University of Science and Technology Kumasi Ghana School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Medicine Department of Radiology and Imaging Sciences Emory University 1364 Clitton Rd. AtlantaGA30322 United States

ISBN: (纸本)9783030921842

Semi-supervised learning algorithms make use of both labelled training data and unlabelled data. However, the visual domain gap between these sets poses a challenge which prevents deep learning models from obtaining the results they have achieved most especially in the field of medical imaging. Recently, self-training with deep learning has become a powerful approach to leverage labelled training and unlabelled data. However, a challenge of generating noisy pseudo-labels and placing over-confident labelling belief on incorrect classes leads to deviation from the solution. To solve this challenge, the study investigates a curriculum-styled approach for deep semi-supervised segmentation which relaxes and treats pseudo-labels as continuous hidden variables by developing an adaptive pseudo-label generation strategy to jointly optimized the pseudo-label generation and selection process. A regularization scheme is further proposed to smoothen the probability outputs and sharpen the less represented pseudo-label regions. The proposed method was evaluated on three publicly available computer Tomography (CT) scan benchmarks and extensive experiments on all modules have demonstrated the efficacy of the proposed method. © 2021, Springer Nature Switzerland AG.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

ImplantFormer: Vision Transformer based Implant Position Regression Using Dental CBCT data

arXiv

引用

arXiv 2022年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Wu, Peixi Shen, Linlin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China The School of Dentistry Shenzhen University Shenzhen China

Implant prosthesis is the most appropriate treatment for dentition defect or dentition loss, which usually involves a surgical guide design process to decide the implant position. However, such design heavily relies on the subjective experiences of dentists. In this paper, a transformer-based Implant Position Regression Network, ImplantFormer, is proposed to automatically predict the implant position based on the oral CBCT data. We creatively propose to predict the implant position using the 2D axial view of the tooth crown area and fit a centerline of the implant to obtain the actual implant position at the tooth root. Convolutional stem and decoder are designed to coarsely extract image features before the operation of patch embedding and integrate multi-level feature maps for robust prediction, respectively. As both long-range relationship and local features are involved, our approach can better represent global information and achieves better location performance. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed ImplantFormer achieves superior performance than existing methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Near-Field Beam Focusing Pattern and Grating Lobe Characterization for Modular XL-Array

Near-Field Beam Focusing Pattern and Grating Lobe Characteri...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Xinrui Li Zhenjun Dong Yong Zeng Shi Jin Rui Zhang National Mobile Communications Research Laboratory and Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing China Purple Mountain Laboratories Nanjing China The Chinese University of Hong Kong (Shenzhen) and Shenzhen Research Institute of Big Data Shenzhen China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore

In this paper, we investigate the near-field modelling and analyze the beam focusing pattern for modular extremely large-scale array (XL-array) communications. As modular XL-array is physically and electrically large in general, the accurate characterization of amplitude and phase variations across its array elements requires the non-uniform spherical wave (NUSW) model, which, however, is difficult for performance analysis and optimization. To address this issue, we first present two ways to simplify the NUSW model by exploiting the unique regular structure of modular XL-array, termed sub-array based uniform spherical wave (USW) models with different or common angles, respectively. Based on the developed models, the near-field beam focusing patterns of XL-array communications are derived. It is revealed that compared to the existing collocated XL-array with the same number of array elements, modular XL-array can significantly enhance the spatial resolution, but at the cost of generating undesired grating lobes. Fortunately, different from the conventional far-field uniform plane wave (UPW) model, the near-field USW model for modular XL-array exhibits a higher grating lobe suppression capability, thanks to the non-linear phase variations across the array elements. Finally, simulation results are provided to verify the near-field beam focusing pattern and grating lobe characteristics of modular XL-array.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Training under Label Noise by Over-parameterization

arXiv

引用

arXiv 2022年

作者： Liu, Sheng Zhu, Zhihui Qu, Qing You, Chong Center for Data Science New York University United States Electrical and Computer Engineering University of Denver United States Department of EECS University of Michigan United States Google Research New York City United States

Recently, over-parameterized deep networks, with increasingly more network parameters than training samples, have dominated the performances of modern machine learning. However, when the training data is corrupted, it has been well-known that over-parameterized networks tend to overfit and do not generalize. In this work, we propose a principled approach for robust training of over-parameterized deep networks in classification tasks where a proportion of training labels are corrupted. The main idea is yet very simple: label noise is sparse and incoherent with the network learned from clean data, so we model the noise and learn to separate it from the data. Specifically, we model the label noise via another sparse over-parameterization term, and exploit implicit algorithmic regularizations to recover and separate the underlying corruptions. Remarkably, when trained using such a simple method in practice, we demonstrate state-of-the-art test accuracy against label noise on a variety of real datasets. Furthermore, our experimental results are corroborated by theory on simplified linear models, showing that exact separation between sparse noise and low-rank data can be achieved under incoherent conditions. The work opens many interesting directions for improving over-parameterized models by using sparse over-parameterization and implicit regularization. © 2022, CC BY.

关键词： Separation

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：