检索结果-内蒙古大学图书馆

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hailong Yu Xinyu Ma Xu Chu Yasha Wang Rengyu Wu Qiang Zhou School of Computer Science Peking University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Shenzhen Center for Prehospital Care Shenzhen China

Unexpected drug-drug interactions (DDIs) may occur when drugs are taken at the same time. Harmful DDIs can reduce drug efficacy and even increase unintended toxicity, putting patients treated with different drugs at risk. Previous works on DDI prediction mainly rely on hand-engineered domain knowledge, which is laborious to obtain and cannot handle the problem of sparse positive samples in DDI prediction. Even though some works attempt to handle data sparsity from the perspective of data distribution to improve the generalization ability of the model, they are limited to negative samples distribution. To address these limitations, we propose a novel method, Graph Mixup for Positive Sample Augmentation (GMPSA), to effectively combine positive drug molecule graphs and extend the training distribution to alleviate the problem of sparse positive samples. To model the graph signals and graph structures jointly, we map source graphs to the fused gromov-wasserstein metric space, then minimizes the weighted sum of transportation distances between the distributions of the source graphs and the objective graph in this metric space. By doing so, interpolated positive samples improve the the generalization error of the model. Experiments results on a real-word dataset show that our method effectively improve the perfomermance in DDI prediction on a state-of-the-art architecture. Further studies also verify the robustness and generalizability of GMPSA under different GNN backbones and parameter settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SODFormer: Streaming Object Detection with Transformer Using Events and Frames

arXiv

引用

arXiv 2023年

作者： Li, Dianze Li, Jianing Tian, Yonghong The National Engineering Research Center for Visual Technology School of Computer Science Peking University Beijing100871 China The Peng Cheng Laboratory Shenzhen518000 China

DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively leverage rich temporal cues and fuse two heterogeneous visual streams remains a challenging endeavor. To address this challenge, we propose a novel streaming object detector with Transformer, namely SODFormer, which first integrates events and frames to continuously detect objects in an asynchronous manner. Technically, we first build a large-scale multimodal neuromorphic object detection dataset (i.e., PKU-DAVIS-SOD) over 1080.1k manual labels. Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance. Finally, an asynchronous attention-based fusion module is proposed to integrate two heterogeneous sensing modalities and take complementary advantages from each end, which can be queried at any time to locate objects and break through the limited output frequency from synchronized frame-based fusion strategies. The results show that the proposed SODFormer outperforms four state-of-the-art methods and our eight baselines by a significant margin. We also show that our unifying framework works well even in cases where the conventional frame-based camera fails, e.g., high-speed motion and low-light conditions. Our dataset and code can be available at https://***/dianzl/SODFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

DarkFed: A Data-Free Backdoor Attack in Federated Learning

arXiv

引用

arXiv 2024年

作者： Li, Minghui Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Zhang, Leo Yu Wang, Yichen School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Leveraging Temporal Causal Discovery Framework to Explore Event-Related EEG Connectivity 24th

Leveraging Temporal Causal Discovery Framework to Explore Ev...

引用

24th International Conference on Human-computer Interaction, HCII 2022

作者： Fang, Shao-Xun Chiu, Tsai-Feng Huang, Chih-Sheng Chuang, Chun-Hsiang Department of Computer Science and Engineering National Taiwan Ocean University Keelung Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan College of Artificial Intelligence and Green Energy National Yang Ming Chiao Tung University Taipei City Taiwan College of Electrical Engineering and Computer Science National Taipei University of Technology Taipei City Taiwan Artificial Intelligence Research and Development Department ELAN Microelectronics Corporation Hsinchu Taiwan Research Center for Education and Mind Sciences College of Education National Tsing Hua University Hsinchu Taiwan Institute of Information Systems and Applications College of Electrical Engineering and Computer Science National Tsing Hua University Hsinchu Taiwan

ISBN: (纸本)9783031196782

Deciphering the cause-and-effect relationships between brain regions not only can provide insights into the mechanism of brain networking but also facilitate the development of the brain-computer interface. Numerous studies have adopted effective connectivity measurements such as transfer entropy or multivariate autoregressive model to investigate the synchronous neuronal coupling across brain regions. Recent successes with representation learning in deep neural networks deserve further investigation on their capability for causal discovery. To this end, this study modified the Temporal Causal Discovery Framework (TCDF) with a sliding-window approach to explore the event-related intra-brain electroencephalogram (EEG) dynamics. The TCDF used a convolution neural network with an attention mechanism to predict causal direction among multi-channel time series data. The resultant array of attention scores was used to gauge the causality magnitude. The TCDF was first validated through a simulation study, followed by real EEG data collected in a virtual reality-based multitasking experiment. Results showed that the time-varying causality magnitudes were positively correlated with the predefined regression coefficients of simulated data, and the TCDF could successfully capture the coupling between brain regions, particularly for adjacent channels. However, some issues were raised in modeling as the number of channels increased or the causal order became larger. The current findings might shed some light on the development of deep learning-based causality analysis. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

MULSAM: Multidimensional Attention with Hardware Acceleration for Efficient Intrusion Detection on Vehicular CAN Bus

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Xu, He Shi, Xiaokang Liu, Hansheng Wang, Yanwen Lu, Jiwu Zeng, Haibo Li, Renfa Wu, Di Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology Hunan Changsha410082 China Hunan University College of Electrical and Information Engineering Hunan Changsha410082 China Hunan University Shenzhen Research Institute Shenzhen518000 China Virginia Tech Department of Electrical and Computer Engineering BlacksburgVA24061 United States Hunan University College of Computer Science and Electronic Engineering Hunan Changsha410082 China

Controller Area Network (CAN) protocol is an efficient standard enabling communication among Electronic Control Units (ECUs). However, the CAN bus is vulnerable to malicious attacks because of a lack of defense features. In this article, a novel vehicle Intrusion Detection System (IDS) is developed. The challenge is that existing techniques of Intrusion Detection Systems (IDS) rarely consider attacks with small-batch, which are characterized by their small attack scale and concealed attack patterns, posing a significant threat to driving safety. To solve this problem, we developed an algorithm model that merges Multi-dimensional Long Short-Term Memory (MD-LSTM) and Self-Attention Mechanism (SAM), shortly named MULSAM. The MULSAM model was compared with other baseline models, including Stacked LSTM, MD-LSTM, etc. Experiments show that our approach has the best detection accuracy (98.98%) and training stability. Further, to speed up the inference of MULSAM on edge, the hardware accelerator is implemented on FPGA devices using technologies such as parallelization, modular, pipeline, and fixed-point quantization. Experiments show that our FPGA-based acceleration scheme has a better energy efficiency than the CPU platform. Even with a certain degree of quantification, the acceleration model for MULSAM still displays a high detection accuracy of 98.81% and a low latency of 1.88 ms. © 1982-2012 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Large-Scale Sorting with Optimized Bandwidth Utilization

引用

ACM Transactions on Reconfigurable technology and Systems 2025年第2期18卷 1-27页

作者： Mingqian Sun Guangwei Xie Fan Zhang Wei Guo Xitian Fan Li Chen Jiayu Du School of Cyber Science and Engineering Southeast University Nanjing China School of Computer Science Fudan University Shanghai China National Digital Switching System Engineering and Technological Research Center Zhengzhou China Hongzhen Information Technology Co. Ltd Shanghai China Purple Mountain Laboratories Nanjing China

Fast sorting of large-scale data is an essential task for data centers. In previous works, the existing computational model of sorting kernel still results in lower bandwidth utilization on the external memory bus. And the execution of merge operations in merge sort circuit on FPGAs depends on control commands from the host CPU. In this case, the merge sort circuit is not fully offloaded to hardware layer for acceleration, resulting in a performance loss. We design an on-chip merge sort controller to efficiently command the merge sort process. The proposed controller has the ability to schedule multiple on-chip computing kernels simultaneously in a more efficient mode, thus ensuring that the circuit has a better bandwidth utilization. Meanwhile, fundamental factors affecting the performance of merge sort are studied and analyzed, and we propose a high-performance merge sort architecture. Results show that using the proposed controller-centered architecture, an overall improvement of 20%–30% in sorting throughput can be achieved. Compared with the state-of-the-art previous merge sorting implementation on FPGA, our circuit can achieve 1.22/1.46\(\times\) speedup.

关键词： Merge sort FPGA system architecture on-chip controller

来源：评论

学校读者我要写书评

暂无评论

Seastar: A Cache-Efficient and Load-Balanced Key-Value Store on Disaggregated Memory

Seastar: A Cache-Efficient and Load-Balanced Key-Value Store...

引用

IEEE International Conference on Cluster Computing

作者： Jingwen Du Fang Wang Dan Feng Dexin Zeng Sheng Yi Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China China School of Computer Science and Technology Huazhong University of Science and Technology China Shenzhen Huazhong University of Science and Technology Research Institute China

ISBN: (数字)9798350358711

ISBN: (纸本)9798350358728

In modern datacenters, memory disaggregation un-packs monolithic servers to build independent network-connected compute and memory pools, greatly improving resource uti-lization. Existing memory-disaggregated key-value stores adopt ownership sharing or ownership partitioning for request scheduling and they all show poor performance and scalability. The former generates multiple cache misses and multiple network round trips due to poor cache locality, while the latter fails to fully use resources on all Compute Nodes (CNs) due to load imbalance. In this paper, we propose Seastar, a fast and scalable key-value store that achieves high cache locality as well as load balancing. To enable high concurrency and ensure linearizability, Seastar exploits a self-verification version chain to provide out-of-place atomic updates and ensure consistent reads. To improve cache locality, Seastar leverages a pair-based ownership assigning scheme to assign the processing permission of requests corre-sponding to each key to a CN pair through two independent hash functions. To ensure load balancing among CNs, Seastar proposes a decentralized power-of-two-choices routing scheme to route the requests to the less-loaded CNs in CN pairs for handling. Experimental results demonstrate that Seastar improves the throughput by up to 6.7x and significantly reduces the latency compared with state-of-the-art memory-disaggregated key-value stores.

关键词： Concurrent computing Hash functions Protocols Processor scheduling Scalability Cluster computing Load management Throughput Routing Servers

来源：评论

学校读者我要写书评

暂无评论

A GNN-Based Learning Approach for Energy Optimization in Relay-Assisted IoT Networks

A GNN-Based Learning Approach for Energy Optimization in Rel...

引用

IEEE Conference on Wireless Communications and Networking

作者： Huapeng Yang Han Ji Zhangqin Huang Xiping Wu Beijing Engineering Research Center for IoT Software and Systems College of Computer Science Beijing University of Technology Beijing China School of Electrical and Electronic Engineering University College Dublin Dublin Ireland The National Mobile Communications Research Laboratory School of Information Science and Engineering Southeast University Nanjing China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Minimizing energy consumption is critical for the long-range (LoRa) Internet of Things (IoT) networks, to extend the battery lifetime of end devices (EDs) while reducing the maintenance cost. To overcome the excessive computational complexity required by the traditional optimization methods, learning approaches such as deep neural network (DNN) and reinforcement learning (RL) have been researched in wireless networks, where star topologies are widely employed. In contrast, LoRa usually deploys relays to assist the connection between the EDs and the gateway (GW), leading to a much more complex network topology. Consequently, DNN and RL would become less effective in LoRa, since those methods are difficult to learn the complex network topology constructed by LoRa. In this paper, we propose a learning method based on graph neural network (GNN), which is known for its prominent ability to capture and represent intricate graph-structural dependencies, to tackle the energy optimization problem for relay-assisted LoRa. Specifically, the multi-hop LoRa network is modeled as a directed graph, with channel state information (CSI) defined as node features, while the spreading factor and transmission power are deemed labels. A hierarchical message aggregation mechanism is proposed to effectively capture the multi-hop structural dependencies, followed by the process of inductive learning. Results show that against conventional optimization algorithms, the proposed method can achieve near-optimal energy consumption with a gap of 10% to 16%, while reducing the runtime by about six orders of magnitude. Compared to DNN, the GNN-based model can provide an energy saving of up to 32%, at a similar level of inference time.

关键词： Energy consumption Runtime Wireless networks LoRa Artificial neural networks Spread spectrum communication Complex networks Graph neural networks Topology Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Using Lock-Free Design for Throughput-Optimized Cache Eviction 25

Using Lock-Free Design for Throughput-Optimized Cache Evicti...

引用

Abstracts of the 2025 ACM SIGMETRICS International Conference on Measurement and Modeling of computer Systems

作者： Chao Dong Fang Wang Hong Jiang Dan Feng Key Laboratory of Information Storage System (Wuhan National Laboratory for Optoelectronics) Engineering Research Center of data storage systems and Technology (School of Computer Science and Technology) Ministry of Education of China Huazhong University of Science and Techonolgy Wuhan Hubei China Department of Computer Science and Engineering University of Texas at Arlington Arlington Texas USA

ISBN: (纸本)9798400715938

This paper presents a practical approach to cache eviction algorithm design, called Mobius, that optimizes the concurrent throughput of caches and reduces cache operation latency by utilizing lock-free data structures, while maintaining high cache hit ratios. Mobius includes two key designs. First, Mobius employs two lock-free FIFO queues to manage cache items, ensuring that all cache operations are executed efficiently in concurrency. Second, Mobius integrates a consecutive detection mechanism that merges multiple modifications during eviction into a single operation, thereby reducing data races. The implementation of Mobius in CacheLib and RocksDB highlights its high concurrency in both synthetic and real-world workloads.

关键词： cache eviction policy

来源：评论

学校读者我要写书评

暂无评论

Structural-Aware Disentangled Learning with CLIP for Hyperbolic Zero-Shot Sketch-Based Image Retrieval*

Structural-Aware Disentangled Learning with CLIP for Hyperbo...

引用

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

作者： Qing Zhang Jing Zhang Feilong Bao Xiangdong Su Guanglai Gao School of Computer Science Inner Mongolia University Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China National and Local Joint Engineering Research Center of Mongolian Information Processing Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The zero-shot sketch-based image retrieval task faces two key challenges: domain gap and knowledge transfer. Our innovation is recognizing that directly aligning cross-domain features weakens the discriminative ability of the model, as it overlooks the asymmetry between sketches and images. Additionally, Euclidean space is inadequate for capturing the hierarchical structure, which limits the performance of the model on complex data. To address these issues, we propose a Structural-Aware Disentangled Learning network (termed SADLnet) that incorporates CLIP and hyperbolic geometry. Specifically, we use CLIP to extract visual features from each domain to enhance the domain generalization of the model. Furthermore, we design a structure-guided disentanglement strategy to decompose image representations into sketch-related and sketch-unrelated features, addressing the domain gap. Moreover, we project the retrieval features into hyperbolic space to capture hierarchical information, improving feature discrimination in retrieval tasks. Extensive experiments demonstrate that SADLnet establishes new state-of-the-art performance on three datasets.

关键词： Geometry Adaptation models Visualization Technological innovation Disentangled representation learning Image retrieval Signal processing Feature extraction Data models Speech processing

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：