检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Zhenglin Wu, Jialong Li, Pengfei Jiang, Yong Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Tongyi Lab Alibaba Group China

Temporal reasoning is fundamental to human cognition and is crucial for various real-world applications. While recent advances in Large Language Models have demonstrated promising capabilities in temporal reasoning, existing benchmarks primarily rely on rule-based construction, lack contextual depth, and involve a limited range of temporal entities. To address these limitations, we introduce Chinese Time Reasoning (CTM), a benchmark designed to evaluate LLMs on temporal reasoning within the extensive scope of Chinese dynastic chronology. CTM emphasizes cross-entity relationships, pairwise temporal alignment, and contextualized and culturally-grounded reasoning, providing a comprehensive evaluation. Extensive experimental results reveal the challenges posed by CTM and highlight potential avenues for improvement. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

lab.l distribution learning for scene text detection

引用

Frontiers of computer Science 2023年第6期17卷 5-12页

作者： Haoyu MA Ningning LU Junjun MEI Tao GUAN Yu ZHANG Xin GENG School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China ZTE Corporation Nanjing 210012China

Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved ***,existing methods usually need complex post-processing stages to process ambiguous lab.ls,i.e.,the lab.ls of the pixels near the text boundary,which may belong to the text or *** this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous *** use the lab.l distribution learning method to process the lab.l ambiguity of text annotation,which achieves a good performance without using additional post-processing *** on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.

关键词： scene text detection multi-task learning lab.l distribution learning

来源：评论

学校读者我要写书评

暂无评论

A genetic algorithm for multiple mobile data collectors' path planning in WSNs

A genetic algorithm for multiple mobile data collectors' pat...

引用

2012 International Conference on information Technology and Software Engineering, ITSE 2012

作者： Shen, Zhuowei Cao, Min Key Lab. of Computer Network and Information Integration School of Computer and Engineering Southeast University Nanjing China

ISBN: (纸本)9783642345210

In mobile data collector (MDC)-based wireless sensor networks, we need to design paths for MDCs for better data collection. In this paper, we use predictable mobility pattern and apply a heuristic algorithm to design paths of MDCs. The algorithm aims to make the time cost by MDCs covering the whole network as short as possible. The algorithm is taken by two steps. Firstly, choose the stop points, and then, construct the paths. Both steps are computed using genetic algorithm (GA). In choosing stop points algorithm, improved stochastic tournament selection is adopted to deal with restraints and special fitness is used to enhance differentiation of solutions. An asexual reproduction based GA with 2-opt optimization mechanism is used to construct MDCs' paths. As experiments show, the algorithm proposed in this paper performs better than greedy algorithm. © 2013 Springer-Verlag.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Optimization for AoI and Energy Consumption in C-V2X Enabled IoV

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and networking 2025年

作者： Zhang, Zheng Wu, Qiong Fan, Pingyi Cheng, Nan Chen, Wen Letaief, Khaled B. Jiangnan University School of Internet of Things Engineering Wuxi214122 China Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering State Key laboratory of Space Network and Communications Tsinghua University Beijing100084 China Xidian University State Key Lab. of ISN School of Telecom-munications Engineering Xi'an710071 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China Department of Electrical and Computer Engineer-ing Hong Kong

To address communication latency issues, the Third Generation Partnership Project (3GPP) has defined Cellular-Vehicle to Everything (C-V2X) technology, which includes Vehicle-to-Vehicle (V2V) communication for direct vehicle-to-vehicle communication. However, this method requires vehicles to autonomously select communication resources based on the Semi-Persistent Scheduling (SPS) protocol, which may lead to collisions due to different vehicles sharing the same communication resources, thereby affecting communication effectiveness. Non-Orthogonal Multiple Access (NOMA) is considered a potential solution for handling large-scale vehicle communication, as it can enhance the Signal-to-Interference-plus-Noise Ratio (SINR) by employing Successive Interference Cancellation (SIC), thereby reducing the negative impact of communication collisions. When evaluating vehicle communication performance, traditional metrics such as reliability and transmission delay present certain contradictions. Introducing the new metric Age of information (AoI) provides a more comprehensive evaluation of communication system. Additionally, to ensure service quality, user terminals need to possess high computational capabilities, which may lead to increased energy consumption, necessitating a trade-off between communication energy consumption and effectiveness. Given the complexity and dynamics of communication systems, Deep Reinforcement Learning (DRL) serves as an intelligent learning method capable of learning optimal strategies in dynamic environments. Therefore, this paper analyzes the effects of multi-priority queues and NOMA on AoI in the C-V2X vehicular communication system and proposes an energy consumption and AoI optimization method based on DRL. Finally, through comparative simulations with baseline methods, the proposed approach demonstrates its advances in terms of energy consumption and AoI. © 2017 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Non-blocking message total ordering protocol

引用

Science in China(Series F) 2008年第12期51卷 1919-1934页

作者： WANG Yun & WANG JunLing School of computer Science & Engineering, Southeast University key lab.of computer network & information integration, MOE, Nanjing 210096, China 1. School of Computer Science & Engineering Southeast University Key Lab of Computer Network & Information Integration MOE Nanjing 210096 China

Message total ordering is a critical part in active replication in order to maintain consistency among members in a fault tolerant group. The paper proposes a non-blocking message total ordering protocol （NBTOP） for distributed systems. Non-blocking property refers to that the members in a fault tolerant group keep on running independently without waiting for installing the same group view when a fault tolerant group evolves even when decision messages collide. NBTOP takes advantage of token ring as its logical control way. Members adopt re-requesting mechanism （RR） to obtain their lost decisions. Forward acknowledgement mechanism （FA） is put forth to solve decision collisions. The paper further proves that NBTOP satisfies the properties of total order, agreement, and termination. NBTOP is implemented, and its performance test is done. Comparing with the performance of Totem, the results show that NBTOP has a better total ordering delay. It manifests that non-blocking property helps to improve protocol efficiency.

关键词： total ordering protocol non-blocking active replication fault tolerance token ring

来源：评论

学校读者我要写书评

暂无评论

KGAPG: Knowledge-Aware Neural Group Representation Learning for Attentive Prescription Generation of Traditional Chinese Medicine

KGAPG: Knowledge-Aware Neural Group Representation Learning ...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Li, Shuchen Wang, Wei He, Jieyue MOE Southeast University Key Lab of Computer Network Information Integration Nanjing China

ISBN: (纸本)9781665401265

Prescriptions play an essential role in the process of Traditional Chinese Medicine (TCM) diagnosis and treatment. Prescription generation is to generate a set of herbs to treat the symptoms of a patient by analyzing the relationship between symptoms and herbs. Although there have been a couple of studies to generate prescriptions, they have ignored the implicit relationship between the different symptoms of the patients. In addition, abundant semantic information and interpretability of the knowledge graph can help to portray the complicated relationships between the various modules of TCM. Therefore, this paper proposes a Knowledge-Aware neural Group representation learning model for Attentive Prescription Generation of Traditional Chinese Medicine (KGAPG), which regards the prescription generation task as a group recommendation problem. More specifically, multiple symptoms of a patient are considered as a symptom group and the complicated semantic information between symptoms and herbs can be captured by the knowledge graph. The syndrome information of multiple symptoms which is summarized by a group aggregation method based on the attention mechanism is applied to simulate the actual process of TCM diagnosis and treatment. The experiment results demonstrate that KGAPG is effective on a TCM prescription benchmark dataset, and its evaluation indicators of Precision, Recall and NDCG exceed other state-of-the-art methods. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Calibration Bottleneck: Over-compressed Representations are Less Calibratable 41

Calibration Bottleneck: Over-compressed Representations are ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Deng-Bao Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Lab. of Computer Network and Information Integration Southeast University MOE China

Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance. Copyright 2024 by the author(s)

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A feedback-based timeout packets dropping strategy in real-time wireless sensor networks

引用

2nd World Congress on computer Science and information Engineering, CSIE 2011

作者： Shen, Zhuowei Xu, Peng Xu, Xiaoxi Key Lab. of Computer Network and Information Integration Ministry of Education School of Computer Sci. and Eng. Southeast University Nanjing China

ISBN: (纸本)9783642257681

Resource limited real-time wireless sensor network is a new type of application of sensor network. In this kind of networks, there are numerous invalid real-time packets, which have already expired or are destined to expire. In this paper, a feedback-based timeout packet dropping strategy (FBTPD) is proposed. With this strategy, timestamps are piggybacked in real-time packets. So that sink node can gather the historical information and estimate the future transmitting time of some sensor node. Then the estimated transmitting time is fed back to the sensor node in a feedback packet. The sensor node hereby drops the invalid realtime packets which will expire later. Simulation experiments reveal that: compared with other dropping policies, FBTPD can drop more invalid real-time packets, and can significantly improve the throughput of the non real-time packets. Thus FBTPD can efficiently boost the resources utilization in wireless sensor networks, especially in hybrid real-time wireless sensor networks. © Springer-Verlag Berlin Heidelberg 2012.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

A distributed topology control algorithm for k-connected dominating set in wireless sensor networks

A distributed topology control algorithm for k-connected dom...

引用

2007 2nd International Conference on Pervasive Computing and Applications, ICPCA'07

作者： Yun, Wang Kai, Li Qiang, Xu Lab. of Computer Network and Information Integration Southeast University Ministry of Education Nanjing 210096 China

ISBN: (纸本)1424409713

Potential applications have fostered the rapid development of wireless sensor network. Power control technology contributes as a fundamental part in fault tolerant topology control, through which simplified reliably connected and highly efficient topology can be constructed Distributed Topology Control algorithm (DTC) is firstly proposed in this paper. By removing heaviest weighted edges as possible, DTC efficiently decreases maximum communication radius so as to use less energy while keeping k-connectivity of dominating set in wireless sensor networks. This paper also formally proves the correctness of DTC, as well as its optimal property, namely minimizing the maximum communication radius. A localized distributed topology control algorithm (LDTC) is put forward in order to obtain an improved topology with at most r-hop localized topology knowledge. © 2007 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A novel secure routing system in overlay environment

引用

4th International Conference on Grid and Cooperative Computing - GCC 2005

作者： Su, Han Wang, Yun Department of Computer Science and Engineering Lab. of Computer Network and Information Integration Southeast University Nanjing 210096 China

ISBN: (纸本)3540305106

Routers are effective building blocks for Internet. It is almost impossible to modify router software only for applications. How to satisfy applications' specific requirements of communication is a big problem. Now more and more systems begin to place application oriented routing service on overlay networks. This paper compares several overlay routing systems based on route number and brings forward a novel routing system based on trust model. System design principles are discussed and system simulation performance is analyzed. The results show that the system is able to provide secure routing service to applications in the case of vicious nodes. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Routers

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：