检索结果-内蒙古大学图书馆

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Duan, Zhuohui Feng, Hao Liu, Haikun Liao, Xiaofei Jin, Hai Li, Bangyu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world application. In this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems. © 2025 FAST. All Rights Reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Framework for Stock Price Forecasting with Sentimental Analysis 13

A Hybrid Deep Learning Framework for Stock Price Forecasting...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Banoth, Shobhan Yadala, Sucharitha Vice President-Data/Information Management Lead Engineer Citi Bank United States School of Computer Science and Engineering Vnr Vignana Jyothi Institute of Engineering & Technology Telangana Hyderabad India

ISBN: (纸本)9798350380583

Social media electronic word-of-mouth data affects stock market confidence and trading. As a result, stock market sentiment research of comments is essential for stock market forecasting. Unfortunately, English is becoming the de facto language for sentiment analysis. This study translates writings from places where English is not the local language into English so that multilingual sentiment analysis can be performed. In order to predict stock market movements, this research combined social media's unstructured data with structured data, such as transaction records and technical indicators. Parameter determination has a significant impact on the effectiveness of forecasting models;in recent years, deep-learning(DL) and machine-learning(ML) models have developed as effective means of dealing with anticipating issues. In order to anticipate stock market indices and business stock prices using hybrid data in places where English is not the native language, this research utilized Long-Short-Term Memory(LSTM) models that utilized the geneticalgorithm(GA) to choose parameters. The created LSTMGA model outperformed the other ML-strategies with different types of data in terms of accuracy when it came to generating forecasts using hybrid multilingual sentiment data. As a result, the stock market forecasting method that combines the suggested LSTMGA model with hybrid sentiment analysis is both practical and encouraging. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

data-Driven Power Flow Estimation for MVDC Distribution Systems Based on Physics-Embedded FCN

引用

IEEE Transactions on Smart Grid 2025年第4期16卷 2816-2829页

作者： Sun, Pingyang Wu, Rongcheng Shen, Zhiwei Wang, Hongyi Li, Gen Khalid, Muhammad Konstantinou, Georgios School of Electrical Engineering and Telecommunications UNSW Sydney Australia University of Technology Sydney Data Science Institute Australia Aalborg University Department of AAU energy Denmark Energy Technology and Computer Science Section Department of Engineering Technology Ballerup2750 Denmark King Fahd University of Petroleum and Minerals Electrical Engineering Department Interdisciplinary Research Center for Sustainable Energy Systems Dhahran31261 Saudi Arabia

Maintaining high prediction accuracy with varying grid topologies poses a significant challenge to adopting neural network (NN)-based approaches for power flow (PF) estimation in medium-voltage direct current (MVDC) distribution systems. This paper proposes a physics-embedded fully convolutional network (PEFCN) to improve the accuracy. Physics-embedded techniques are incorporated in the proposed PEFCN through 1) architecture reconstruction, and 2) loss function reformulation. Architecture is reconstructed by input channel conversion calculation in a new physics operation layer. This process offers physical connections among the three input matrix channels (voltage, current, and line conductance). Three new physics loss terms are included in the loss function to restrict the outliers violating the limits of converter power ratings and terminal MVDC voltages. The two operations enable the FCN to achieve improved prediction accuracy and strong generalization capabilities. Five MVDC distribution systems, characterized by different dc voltage levels and topology configurations, serve to validate the superiority of the proposed PEFCN over other NNs in the PF estimation for scenarios involving both fixed and varying system structures. Moreover, a modified IEEE 69-bus distribution system is further used to demonstrate the applicability of the proposed PEFCN for larger systems. © 2010-2012 IEEE.

关键词： DC distribution systems

来源：评论

学校读者我要写书评

暂无评论

INFOCON: CONCEPT DISCOVERY WITH GENERATIVE AND DISCRIMINATIVE INFORMATIVENESS 12

INFOCON: CONCEPT DISCOVERY WITH GENERATIVE AND DISCRIMINATIV...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Liu, Ruizhe Luo, Qian Yang, Yanchao HKU Musketeers Foundation Institute of Data Science The University of Hong Kong Hong Kong School of Electronics Engineering and Computer Science Peking University China Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong

We focus on the self-supervised discovery of manipulation concepts that can be adapted and reassembled to address various robotic tasks. We propose that the decision to conceptualize a physical procedure should not depend on how we name it (semantics) but rather on the significance of the informativeness in its representation regarding the low-level physical state and state changes. We model manipulation concepts - discrete symbols - as generative and discriminative goals and derive metrics that can autonomously link them to meaningful sub-trajectories from noisy, unlabeled demonstrations. Specifically, we employ a trainable codebook containing encodings (concepts) capable of synthesizing the end-state of a sub-trajectory given the current state - generative informativeness. Moreover, the encoding corresponding to a particular sub-trajectory should differentiate the state within and outside it and confidently predict the subsequent action based on the gradient of its discriminative score - discriminative informativeness. These metrics, which do not rely on human annotation, can be seamlessly integrated into a VQ-VAE framework, enabling the partitioning of demonstrations into semantically consistent sub-trajectories, fulfilling the purpose of discovering manipulation concepts and the corresponding sub-goal (key) states. We evaluate the effectiveness of the learned concepts by training policies that utilize them as guidance, demonstrating superior performance compared to other baselines. Additionally, our discovered manipulation concepts compare favorably to human-annotated ones while saving much manual effort. Our code is available at: https://***/InfoCon/. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

A IoT Edge Advanced VANET Technique for Vehicle Communication and Improve Safety in Hill Station Critical Scenario 8

A IoT Edge Advanced VANET Technique for Vehicle Communicatio...

引用

8th IEEE International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2023

作者： Murali, N. Beulah David, D. Saveetha School of Engineering Simats Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha School of Engineering Simats Institute of Information Technology Department of Data Analytics Tamilnadu Chennai India

ISBN: (纸本)9798350347791

The safety of the vehicles is given great importance by advanced intelligent transportation systems. We are here to make sure that swift transit vehicles and infrastructure communicate with one other quickly. The majority of the vehicles need regular monitoring for appropriate warnings and road maps to achieve their ultimate objective in a timely manner in the hill station bad environment, and travel in hairpin bends and risky turning in particular is a duty that is vital for ITS. Here, my study will provide a strategy for preventing accidents by applying a sophisticated early warning system before notifying the car in a certain circumstance. In order to prevent accidents, machine learning is a technique where the system automatically learns and enhances the rapid object detection stage in bobby pin road turning scenarios. Here, my study offers effective unsupervised learning of these characteristics based on the acquired data, which in turn serves as the foundation for the clustering I performed, which successfully builds a mobile ad hoc network. In this work, we suggested an innovative automated discovering vehicle prier that uses the UNetXST technique in real-time to notify warring for vehicle in three-way shining LED light with blinking mode, slowing warring message in display unit, and beep alarm sound. By combining V2I and V2V technologies and sending messages to the central traffic light management system, we highlighted safety and communication. In worst-case scenarios, we employ a v2v technology sensor to detect the vehicle that will cross the junction road, and we investigate two-way merging technology's potential to implement and resolve these problems in transparent object tracking in the turning system. We looked at future direction and hurdles at this time in addition to a case study illustrating a VANET-based scenario of a critical urban road turning, receiving the earliest notice to flee from a traffic collision, and experiencing the perfect EV momen

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

DuSSS: Dual Semantic Similarity-Supervised Vision-Language Model for Semi-Supervised Medical Image Segmentation 39

DuSSS: Dual Semantic Similarity-Supervised Vision-Language M...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

ISBN: (纸本)157735897X

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

TROPICAL: Transformer-Based Hypergraph Learning for Camouflaged Fraudster Detection 24

TROPICAL: Transformer-Based Hypergraph Learning for Camoufla...

引用

24th IEEE International Conference on data Mining, ICDM 2024

作者： Haghighi, Venus Soltani, Behnaz Shabani, Nasrin Wu, Jia Zhang, Yang Yao, Lina Sheng, Quan Z. Yang, Jian School of Computing Macquarie University SydneyNSW2109 Australia School of Computer Science and Engineering University of New South Wales NSW Australia CSIRO's Data61 Australia

ISBN: (纸本)9798331506681

Graph-based fraud detection has attracted increasing attention in recent years, reflecting its growing potential in mitigating sophisticated fraudulent activities. The main objective of graph-based fraud detection is to discern between fraud-sters and normal entities within graphs. As fraudsters adopt increasingly sophisticated camouflage tactics, combating them has become an urgent task. Despite the complex interactions within real-world networks involving high-order relations, ex-isting graph-based fraud detection methods often neglect non-pairwise relationships among entities in graphs. Thus, we empha-size the significance of investigating beyond pairwise relationships for building an effective fraud detection model. In this paper, we propose constructing a hypergraph from the original input graph to encapsulate comprehensive high-order relations and present TROPICAL, a novel TRansfOrmer-based hyPergraph LearnIng for detecting CAmouflaged maLicious actors in online social networks. TROPICAL learns representations by processing different hyperedge groups and incorporates positional encodings into the aggregated information to enhance their distinctiveness. Subsequently, the model feeds the learned aggregated sequential information into the transformer encoder, achieving rich rep-resentations for effective camouflaged fraudster detection. The superiority of TROPICAL is demonstrated through experiments conducted on two real-world datasets, compared against the state-of-the-art fraud detection models. The source codes and datasets of our work are available at https://***/TROPICAL. © 2024 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

HTCCN: Temporal Causal Convolutional Networks with Hawkes Process for Extrapolation Reasoning in Temporal Knowledge Graphs

HTCCN: Temporal Causal Convolutional Networks with Hawkes Pr...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Chen, Tingxuan Long, Jun Yang, Liu Wang, Zidong Wang, Yongheng Jin, Xiongnan School of Computer Science and Engineering Central South University Hunan China Big Data Institute Central South University Hunan China Zhejiang lab Zhejiang China

ISBN: (纸本)9798891761148

Temporal knowledge graphs (TKGs) serve as powerful tools for storing and modeling dynamic facts, holding immense potential in anticipating future facts. Since future facts are inherently unknowable, effectively modeling the intricate temporal structure of historical facts becomes paramount for accurate prediction. However, current models often rely heavily on fact recurrence or periodicity, leading to information loss due to prolonged evolutionary processes. Notably, the occurrence of one fact always influences the likelihood of another. To this end, we propose HTCCN, a novel Hawkes process-based temporal causal convolutional network designed for temporal reasoning under extrapolation settings. HTCCN employs a temporal causal convolutional network to model the historical interdependence of facts and leverages Hawkes to model link formation processes inductively in TKGs. Importantly, HTCCN introduces dual-level dynamics to comprehensively capture the temporal evolution of facts. Rigorous experimentation on four real-world datasets underscores the superior performance of HTCCN. ©2024 Association for Computational Linguistics.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization 30

FedMCP: Parameter-Efficient Federated Learning with Model-Co...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhao, Qianyi Qu, Chen Chen, Cen Fan, Mingyuan Wang, Yanhao East China Normal University School of Data Science and Engineering Shanghai China University of Massachusetts Amherst College of Information & Computer Sciences AmherstMA United States

ISBN: (纸本)9798331515966

With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despite being extensively studied, the existing methods for this problem still face two primary challenges. First, the huge number of parameters in large-scale PLMs leads to excessive communication and computational overhead. Second, the heterogeneity of data and tasks across clients poses a significant obstacle to achieving the desired fine-tuning performance. To address the above problems, we propose FedMCP, a novel parameter-efficient fine-tuning method with model-contrastive personalization for FL. Specifically, FedMCP adds two lightweight adapter modules, i.e., the global adapter and the private adapter, to the frozen PLMs within clients. In a communication round, each client sends only the global adapter to the server for federated aggregation. Furthermore, FedMCP introduces a model-contrastive regularization term between the two adapters. This, on the one hand, encourages the global adapter to assimilate universal knowledge and, on the other hand, the private adapter to capture client-specific knowledge. By leveraging both adapters, FedMCP can effectively provide fine-tuned personalized models tailored to individual clients. Extensive experiments on highly heterogeneous cross-task, cross-silo datasets show that FedMCP achieves substantial performance improvements over state-of-the-art FL fine-tuning approaches for PLMs. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Provision of Workload Allocation on Cloud Resources Using Machine Learning Techniques

Dynamic Provision of Workload Allocation on Cloud Resources ...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Saravanakumar, C. Prakash, M. Govindaraj, V. Government Polytechnic College Department of Computer Engineering Chennai600012 India Vellore Institute of Technology School of Computer Science and Engineering Vellore632 014 India MPHASIS Ltd SME- Data Science Chennai India

ISBN: (纸本)9798350319200

Cloud tasks are scheduled to the respective VM for execution. Scheduling process selects the resources and allocates the requesting task to them. The resources are selected in advance and then the request is forwarded for processing of tasks. It suffers the overestimation problem which means that the requested task size is less than the allocated resource level. Various scheduling problems are addressed but still the problem arises during the resource allocation. Auto scaling process is implemented in the cloud which allocates the resource based on the demand. The proposed model uses the dynamic method of cloud allocation and provisioning based on the workload level and resource level. Priority queue is implemented prior to the provisioning process for ordering the resource in specific order. The main aim of the proposed method is to allocate the resources using dynamic priority manner. The efficiency is achieved at maximum level by selecting and allocating the workload. © 2023 IEEE.

关键词： Cloud Computing Dynamic Provisioning Machine Learning Scheduling Virtual Machine

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：