检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Mi, Jiacong Zu, Yi Wang, Zhuoyuan He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Jiangsu Nanjing210018 China

Medication recommendation using Electronic Health Records (EHR) is challenging due to complex medical data. Current approaches extract longitudinal information from patient EHR to personalize recommendations. However, existing models often lack sufficient patient representation and overlook the importance of considering the similarity between a patient’s medication records and specific medicines. Therefore, an Attention-guided Collaborative Decision network (ACDNet) for medication recommendation is proposed in this paper. Specifically, ACDNet utilizes attention mechanism and Transformer to effectively capture patient health conditions and medication records by modeling their historical visits at both global and local levels. ACDNet also employs a collaborative decision framework, utilizing the similarity between medication records and medicine representation to facilitate the recommendation process. The experimental results on two extensive medical datasets, MIMIC-III and MIMIC-IV, clearly demonstrate that ACDNet outperforms state-of-the-art models in terms of Jaccard, PR-AUC, and F1 score, reaffirming its superiority. Moreover, the ablation experiments provide solid evidence of the effectiveness of each module in ACDNet, validating their contribution to the overall performance. Furthermore, a detailed case study reinforces the effectiveness of ACDNet in medication recommendation based on EHR data, showcasing its practical value in real-world healthcare scenarios. © 2023, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Attention Is Not What You Need: Revisiting Multi-Instance Learning for Whole Slide Image Classification

arXiv

引用

arXiv 2024年

作者： Liu, Xin Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Lab. of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle NSW2308 Australia

Although attention-based multi-instance learning algorithms have achieved impressive performances on slide-level whole slide image (WSI) classification tasks, they are prone to mistakenly focus on irrelevant patterns such as staining conditions and tissue morphology, leading to incorrect patch-level predictions and unreliable interpretability. Moreover, these attention-based MIL algorithms tend to focus on salient instances and struggle to recognize hard-to-classify instances. In this paper, we first demonstrate that attention-based WSI classification methods do not adhere to the standard MIL assumptions. From the standard MIL assumptions, we propose a surprisingly simple yet effective instance-based MIL method for WSI classification (FocusMIL) based on max-pooling and forward amortized variational inference. We argue that synergizing the standard MIL assumption with variational inference encourages the model to focus on tumour morphology instead of spurious correlations. Our experimental evaluations show that FocusMIL significantly outperforms the baselines in patch-level classification tasks on the Camelyon16 and TCGA-NSCLC benchmarks. Visualization results show that our method also achieves better classification boundaries for identifying hard instances and mitigates the effect of spurious correlations between bags and labels. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

An improved Schnorr-based multi-signature scheme with application to blockchain 3

An improved Schnorr-based multi-signature scheme with applic...

引用

3rd IEEE International Conference on Civil Aviation Safety and information Technology, ICCASIT 2021

作者： Li, Chunlan Wu, Yulong Yu, Feng Computer Science and Engineering School of Software Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

ISBN: (纸本)9781665425186

A multi-signature scheme allows a group of signers to jointly generate a signature on a common message, which can be verified by anyone, making the signature more compact. Multi-signature has the advantage of fast verification, and it helps reduce bandwidth and the cost of validation and storage. Recently, the multi-signature has drawn much attention because its advantages are desirable for blockchain and cryptocurrency. However, the traditional Schnorr-based multisignature scheme suffers from an excessive number of communications. This paper proposes an improved Schnorr-based multi-signature scheme ASMS, which reduces one round of communication in a traditional scheme, supporting public key aggregation. Thus, it is suitable for e-business and e-government affairs scenarios. As an application, we implemented our solution in Fabric, an enterprise blockchain platform, using chaincode technology. © 2021 IEEE

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model

arXiv

引用

arXiv 2024年

作者： Shi, Jiang-Xin Zhang, Chi Wei, Tong Li, Yu-Feng National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing University China National Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University China

Pre-trained vision-language models like CLIP have shown powerful zero-shot inference ability via image-text matching and prove to be strong few-shot learners in various downstream tasks. However, in real-world scenarios, adapting CLIP to downstream tasks may encounter the following challenges: 1) data may exhibit long-tailed data distributions and might not have abundant samples for all the classes;2) There might be emerging tasks with new classes that contain no samples at all. To overcome them, we propose a novel framework to achieve efficient and long-tailed generalization, which can be termed as Candle. During the training process, we propose compensating logit-adjusted loss to encourage large margins of prototypes and alleviate imbalance both within the base classes and between the base and new classes. For efficient adaptation, we treat the CLIP model as a black box and leverage the extracted features to obtain visual and textual prototypes for prediction. To make full use of multi-modal information, we also propose cross-modal attention to enrich the features from both modalities. For effective generalization, we introduce virtual prototypes for new classes to make up for their lack of training images. Candle achieves state-of-the-art performance over extensive experiments on 11 diverse datasets while substantially reducing the training time, demonstrating the superiority of our approach. The source code is available at https://***/shijxcs/Candle. 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

Disease Diagnosis with Cost-Sensitive Grouped Features Based on Deep Reinforcement Learning

Disease Diagnosis with Cost-Sensitive Grouped Features Based...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Yikemaiti Sataer Zhiqiang Gao Xuelian Li School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China School of Foreign Studies Nanjing University of Posts and Telecommunications

Traditional machine learning algorithms rely on the assumption that all features of a given dataset are available for free. However, in disease diagnosis, acquiring features requires a certain cost because there are many concerns, such as monetary data collection costs, patient discomfort in medical procedures, and privacy impacts of data collection that require careful consideration. Moreover, some medical examination items are grouped in the real world, such as lab tests that return multiple measurements, resulting in naturally grouped features. In this work, to consider features that come in groups, we propose a novel feature selection method for disease diagnosis with cost-sensitive grouped features based on deep reinforcement learning (RL). We optimize the objective which is a trade-off between the cost of grouped features and the diagnostic accuracy, by training deep RL models. In addition, the approach is flexible, as it can be improved with new deep reinforcement learning algorithms. We evaluate the effectiveness of the proposed method on four publicly available datasets. Compared with the existing competitive feature selection methods, the proposed method can achieve higher learning accuracy with lower feature costs. This paper takes disease diagnosis as an example, and the proposed method is universal for problems with grouped features of different domains. (The source code is available at https://***/r/DRL-CSGF- Y821).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Timo: In-memory temporal query processing for big temporal data

Timo: In-memory temporal query processing for big temporal d...

引用

作者： Zheng, Xiao Liu, Houkai Wang, Xiujun Wu, Xuangou Yu, Feng School of Computer Science and Technology Anhui University of Technology Maanshan China Institute for Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Engineering Laboratory for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Maanshan China School of Computer Science and Engineering & School of Software Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

Today's internet applications generate massive temporal data anywhere and anytime. Although some disk-based temporal systems are currently available, they suffer from poor I/O performance, especially when applied in intelligent applications deployed in the cloud and edge environments. Therefore, how to process temporal operations with low latency and high throughput becomes a crucial problem for efficient data processing. This paper proposes Timo, a distributed in-memory temporal query and analytic model for big temporal data. Firstly, a space-efficient temporal index is proposed to support more efficiently query performance with less memory space than the state-of-art methods. Secondly, based on the temporal locality feature of temporal queries, Timo proposes a partitioner mechanism, which utilizes forward scan algorithm, to improve query throughput. Thirdly, some optimal strategies are proposed to improve the execution process of temporal query and analysis, which reduce intermediate result data size and improve the throughput much further. Lastly, we implement the Timo system on the Apache Spark platform, which extends Spark dataset API with temporal query and analysis API functions for users. Extensive experimental results show that the Timo system outperforms other Spark-based temporal systems in terms of both query latency and throughput. © 2021 John Wiley & Sons, Ltd.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

KGRN: Knowledge Graph Relational Path network for Target Prediction of TCM Prescriptions 17th

KGRN: Knowledge Graph Relational Path Network for Target Pre...

引用

17th International Conference on Intelligent Computing, ICIC 2021

作者： Gong, Zhuo Zhang, Naixin He, Jieyue School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Southeast University Nanjing210018 China

ISBN: (纸本)9783030845315

Accurately predicting the effect targets of Traditional Chinese Medicine (TCM) prescriptions is essential for exploring the molecular mechanism and clarifying the mechanism of TCM. Although some scholars have used network pharmacology to study the target prediction of TCM prescriptions, all of them are for the analysis of a specific prescription-disease association, and the universal method for predicting effect targets of TCM prescriptions has not discovered yet. Therefore, this paper proposes a Knowledge Graph Relational Path network for Target Prediction of TCM Prescriptions (KGRN), which can integrate prescription’s molecular and target information through the Knowledge Graph (KG). At the same time, the semantic information and high-level structure of the knowledge graph are extracted through Knowledge Graph Embedding and Graph Neural networks, which can effectively capture the correlation between the prescriptions and the targets. Moreover, by emphasizing the KG relations when aggregating neighborhood information, the Relational Path network of the KGRN model has the ability to capture the relationship dependence in the KG path, which enhances the ability to predict the relationship between the prescriptions and the targets. The experiments under multiple configurations demonstrate that KGRN outperforms the related competitive benchmarks. © 2021, Springer Nature Switzerland AG.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

In-band network-Wide Telemetry for Topology-Varying LEO Satellite networks

In-band Network-Wide Telemetry for Topology-Varying LEO Sate...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Yan Zhang Tian Pan Qiang Fu Yan Zheng Xinyu Feng Jiang Liu Haipeng Yao Tao Huang Purple Mountain Laboratories Nanjing China Beijing University of Posts and Telecommunications Beijing China Ministry of Education Key Laboratory of Computer Network and Information Integration (Southeast University) China RMIT University Melbourne Australia

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Driven by technological advances and new business models, we have seen a renewed interest in LEO satellite constellations. The deployment of large-scale LEO satellite networks is becoming a reality. The network topology changes periodically, as satellites orbit the Earth. This imposes a great challenge to network monitoring. Meanwhile, as a new network monitoring method, In-band network Telemetry (INT) can provide per-hop granular telemetry metadata, needed to tackle the mobile nature of LEO satellite constellations. Given this, we apply INT to LEO satellite networks for real-time fine-grained monitoring. We propose a path planning solution to identify the paths for network-wide telemetry and the paths for disseminating the telemetry data to the ground facilities. By taking advantage of the predictable satellite trajectories and topology variations, the path planning solution is designed to achieve network-wide coverage and minimize telemetry overhead. We take the LEO48 constellation as an example to visually show the detailed paths of the monitoring scheme. We conduct experiments on different sizes of networks to evaluate the original path planning algorithm and the improved balanced algorithm in this paper, demonstrating the timeliness and balance of the telemetry solution.

关键词： Satellite constellations Visualization Satellites network topology Low earth orbit satellites Prediction algorithms Real-time systems Trajectory Telemetry Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Constructive Method Based on Dynamic Solution Space for Travelling Salesman Problem

A Constructive Method Based on Dynamic Solution Space for Tr...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Xiaoxin Bai LuLi LuLi Hanqian Wu School of Computer Science and Engineering Southeast University China School of Cyber Science and Engineering Southeast University China Suzhou Centennail College China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University China

Neural combinatorial optimization (NCO) has emerged as a promising field to solve the combinatorial optimization problem (COP) as automatically learning the solvers less relying on domain-specific expert knowledge. Constructive Method (ConsM) is the most widely used approach in NCO for solving various COPs and their variations. However, few literature elucidates the underlying principles of ConsM, hindering further optimization. In this paper, we analyze the efficiency principle of ConsM for COPs from the perspective of discrete solution space and summarize its design principles. These principles can serve as guidelines for designing novel constructive policy. Based on these principles, we reviewed the existing ConsM models and identified that the design of existing decoder introduced certain noises, which negatively impacted the policy performance. Therefore, we designed a novel decoder in line with the aforementioned principles. Notably, our method can be applied to all ConsM models and yielded significant improvements compared to the original. We evaluated our method on Traveling Salesman Problem(TSP) and the experimental results verified the effectiveness and efficiency of our method, supporting our analysis of ConsM. In particular, we reduced the average optimality gap from 1.16% to 0.62% for TSP100 compared to Sym-NCOs, keeping the hyperparameters constant.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Brainnetformer: Decoding Brain Cognitive States with Spatial-Temporal Cross Attention

Brainnetformer: Decoding Brain Cognitive States with Spatial...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Leheng Sheng Wenhan Wang Zhiyi Shi Jichao Zhan Youyong Kong Chien-Shiung Wu College Southeast University China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

Learning about the cognitive state of the brain has always been a popular topic. Based on the fact that fluctuations of brain signals and functional connectome (FC) relate to specific human behaviors, deep learning based methods have shown promising results on the prediction of such behaviors by analyzing biological signals. Existing methods either model from static perspectives or apply spatial-temporal graph convolution to extract dynamic properties. However, the static information and dynamic information can reflect global brain activities and local brain activities respectively. Thus, we propose BrainNetFormer to incorporate both static and dynamic properties for human behavior prediction. To be specific, a spatial cross attention module and a temporal cross attention module are introduced for information fusion. In addition, since a specific behavior of subjects can be decomposed into a series of subtasks, we introduce a sub-task regularization loss to assist in training and empower the model to recognize subtasks at each moment. Experiments on the HCP-Task dataset demonstrate the superior performance of the proposed model.

关键词： Training Convolution Fuses Magnetic resonance imaging Predictive models Brain modeling Behavioral sciences

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：