检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Lv, Xingtai Ding, Ning Zhang, Kaiyan Hua, Ermo Cui, Ganqu Zhou, Bowen Department of Electronic Engineering Tsinghua University China Shanghai AI Laboratory China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9798891761643

Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will compromise performance, can be scalably effective when reduced parameters are precisely targeted. Specifically, applying the low-dimensional module only to the attention layer - resolves this issue and enhances both effectiveness and efficiency. We refer to this structure as Low-dimensional Projected Attention (LPA) and provide an explanatory analysis. Through extensive experimentation at parameter scales of 130M, 370M, and scaling up to 3B, we have validated the effectiveness and scalability of LPA. Our results show that LPA model can save up to 12.4% in time while achieving an approximate 5% improvement in test perplexity (ppl) and on downstream tasks compared with the vanilla Transformer. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Minimum Active Component Count Formant and Inverse Formant Filters Designs 47

Minimum Active Component Count Formant and Inverse Formant F...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Nako, Julia Tsirimokou, Georgia Psychalinos, Costas University of Patras Electronics Laboratory Physics Department Rio Patras Greece University of Ioannina Department of Computer Science & Engineering Ioannina Greece

ISBN: (纸本)9798350365597

Active-RC filter topologies capable of extracting the waveform of vowels from the associated glottal pulse trains as well as of performing the inverse procedure, are presented in this paper. Both are implemented using only few operational-amplifiers as active elements, offering minimization of the active component count and, also, of the dc power dissipation. The provided simulation results, obtained using the OrCAD PSpice suite, in both frequency and time-domain, confirm the operation of the presented structures. © 2024 IEEE.

关键词： Operational amplifiers

来源：评论

学校读者我要写书评

暂无评论

Empowering Healthcare: Edge Computing and ML for Early Heart Attack Detection And Prevention 6

Empowering Healthcare: Edge Computing and ML for Early Heart...

引用

6th International Conference on Pattern Analysis and Intelligent Systems, PAIS 2024

作者： Kenioua, Laid Lejdel, Brahim Abdelhamid, Nedioui Mohamed Liap Laboratory University of El Oued El Oued39000 Algeria University of Eloued Computer Science Department Algeria

ISBN: (纸本)9798350350265

Heart diseases are a major cause of death among humans, and early detection of such conditions plays a crucial role in saving many lives. Due to technological advances, especially in the field of health care, we have created a health care system aimed at detecting heart diseases, including heart attacks, especially in remote areas. Our approach involves working within an edge computing environment to mitigate network issues and ensure real-time performance. This is achieved by integrating Internet of Things (IoT) devices and a local server to store and archive information locally, while also establishing a connection with the cloud to process broad sets of data. It ensures that the computational and processing capabilities of devices at the edge are used to carry out training and prediction operations instead of relying on the remote cloud. This allows for improved application responsiveness, privacy preservation, and reduced reliance on an Internet connection. Our study focuses on three different machine learning algorithms (K-Nearest Neighbor (KNN), Random Forest algorithm, and Support Vector Machine (SVM)) and compares their results with the output of the model used. The results showed the superiority of the Random Forest algorithm through model accuracy and... faster training performance and prediction time of less than 42 seconds, with the highest correct prediction percentage reaching 90 percent. Our work focuses on evaluating the effectiveness of the proposed models as well as evaluating their processing time. © 2024 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

AutoML for Explainable Anomaly Detection (XAD)

AutoML for Explainable Anomaly Detection (XAD)

引用

The Provenance of Elegance in Computation - Essays Dedicated to Val Tannen 2024

作者： Myrtakis, Nikolaos Tsamardinos, Ioannis Christophides, Vassilis Department of Computer Science University of Crete Heraklion Greece ETIS Laboratory CY Cergy Paris Université ENSEA France

ISBN: (纸本)9783959773201

Numerous algorithms have been proposed for detecting anomalies (outliers, novelties) in an unsupervised manner. Unfortunately, it is not trivial, in general, to understand why a given sample (record) is labelled as an anomaly and thus diagnose its root causes. We propose the following reduced-dimensionality, surrogate model approach to explain detector decisions: approximate the detection model with another one that employs only a small subset of features. Subsequently, samples can be visualized in this low-dimensionality space for human understanding. To this end, we develop PROTEUS, an AutoML pipeline to produce the surrogate model, specifically designed for feature selection on imbalanced datasets. The PROTEUS surrogate model can not only explain the training data, but also the out-of-sample (unseen) data. In other words, PROTEUS produces predictive explanations by approximating the decision surface of an unsupervised detector. PROTEUS is designed to return an accurate estimate of out-of-sample predictive performance to serve as a metric of the quality of the approximation. Computational experiments confirm the efficacy of PROTEUS to produce predictive explanations for different families of detectors and to reliably estimate their predictive performance in unseen data. Unlike several ad-hoc feature importance methods, PROTEUS is robust to high-dimensional data. © Nikolaos Myrtakis, Ioannis Tsamardinos, and Vassilis Christophides;licensed under Creative Commons License CC-BY 4.0.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimizing Hybrid Recommendations: VADER-Enhanced Sentiment Analysis 24

Optimizing Hybrid Recommendations: VADER-Enhanced Sentiment ...

引用

7th International Conference on Networking, Intelligent Systems and Security, NISS 2024

作者： Darraz, Nossayba Karabila, Ikram El-Ansari, Anas Alami, Nabil El Mallahi, Mostafa Sidi Mohamed Ben Abdellah University High Normal School Department of Mathematics and Computer Science Ipi Laboratory Fez Morocco Mohammed First University Polydisciplinary Faculty Computer Science Department Masi Laboratory Nador Morocco Mohammed First University Higher School of Technology Masi Laboratory Nador Morocco

ISBN: (纸本)9798400709296

Recommendation systems are essential tools for assisting users in discovering relevant and personalized content. The optimization of hybrid recommendations by incorporating sentiment analysis is explored. By analyzing sentiments expressed in user-generated content, such as reviews and feedback, valuable insights into user preferences are gained. Leveraging sentiment analysis improves the effectiveness of recommendations, leading to enhanced user experiences and increased engagement. Our proposed approach utilizes Singular Value Decomposition (SVD) for collaborative filtering, TF-IDF with Lasso for content-based filtering, and VADER for sentiment analysis. We convert continuous sentiment scores into discrete ratings and replace initial ratings with sentiment-derived ones from user reviews. The resulting hybrid system offers improved RMSE and recommendations tailored to user preferences, showcasing the potential of sentiment-aware approaches in enhancing recommendation systems. Additionally, we propose a hybrid recommendation system with NMF and DecisionTreeRegressor-based models, which outperformed all other models with an impressively low RMSE score of 0.092. © 2024 ACM.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware Precoding for Dual-Polarized Downlink Massive MIMO LEO Satellite Communications

引用

Space(science & Technology) 2024年第1期4卷 69-78页

作者： Yan Huang Li You Kezhi Wang Xiqi Gao National Mobile Communications Research Laboratory Southeast UniversityNanjing 210096China Purple Mountain Laboratories Nanjing 211100China Department of Computer Science Brunel UniversityLondon UxbridgeUK

Low Earth Orbit (LEO) satellite communications (SATCOM) are important for wireless networks and offer better global wireless access services than higher altitude SATCOM options. SATCOM performance is affected by the number of antennas, which is usually constrained by the satellite space. In this paper, the application of dual-polarized technology is considered to assist LEO SATCOM. Compared with single-polarized antennas, dual-polarized antennas utilize two different polarization orientations to transmit and receive data. This can improve the quality of service (QoS) performance, as it allows for twice the amount of data to be transmitted over the same time–frequency resources. Specifically, we characterize the dual-polarized channel in massive multiple-input multiple-output (MIMO) LEO SATCOM and investigate the precoding design for enhancing the system performance. In particular, a precoding optimization problem is formulated, which aims to jointly optimize the system throughput and the QoS performance. We divide the problem into two stages and develop novel algorithms for each stage to obtain the precoding vectors. The numerical results demonstrate that the dual-polarized technology can improve the system throughput, and the proposed algorithm leads to a higher percentage of users achieving their QoS requirements compared to conventional approaches.

关键词： two different polarization orientations QoS aware low earth orbit downlink dual polarized precoding wireless networks satellite communications

来源：评论

学校读者我要写书评

暂无评论

Community Smell Occurrence Prediction on Multi-Granularity by Developer-Oriented Features and Process Metrics

引用

Journal of computer science & Technology 2022年第1期37卷 182-206页

作者： Zi-Jie Huang Zhi-Qing Shao Gui-Sheng Fan Hui-Qun Yu Xing-Guang Yang Kang Yang Department of Computer Science and Engineering East China University of Science and TechnologyShanghai 200237China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai 200237China Shanghai Engineering Research Center of Smart Energy Shanghai 200237China

Community smells are sub-optimal developer community structures that hinder *** studies performed smell prediction and provided refactoring guidelines from a top-down aspect to help community ***,refactoring smells also requires bottom-up effort from every ***,supportive measures and guidelines for them are not available at a fine-grained *** recent work revealed developers'personalities and working states could influence community smells'emergence and variation,we build prediction models with experience,sentiment,and development process features of developers considering three smells including Organizational Silo,Lone Wolf,and Bottleneck,as well as two related classes including smelly developer and smelly *** predict the five classes in the individual granularity,and we also generate forecasts for the number of smelly developers in the community *** proposed models achieve F-measures ranging from 0.73 to 0.92 in individual-wide within-project,time-wise,and cross-project prediction,and mean R2 performance of 0.68 in community-wide Smelly Developer *** also exploit SHAP(SHapley Additive exPlanations)to assess feature importance to explain our *** conclusion,we suggest developers with heavy workload should foster more frequent communication in a straightforward and polite way to build healthier communities,and we recommend community shepherds to use the forecasting model for refactoring planning.

关键词： community smell developer sentiment socio-technical analysis empirical software engineering

来源：评论

学校读者我要写书评

暂无评论

A Mutual Information-Based Assessment of Reverse Engineering on Rewards of Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第5期4卷 1089-1100页

作者： Chen, Tong Liu, Jiqiang Baker, Thar Wu, Yalun Xiang, Yingxiao Li, Yike Niu, Wenjia Tong, Endong Zomaya, Albert Y. Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China College of Computing and Informatics University of Sharjah Department of Computer Science Sharjah27272 United Arab Emirates The University of Sydney School of Computer Science Sydney2006 Australia

Rewards are critical hyperparameters in reinforcement learning (RL), since in most cases different reward values will lead to greatly different performance. Due to their commercial value, RL rewards become the target of reverse engineering by the inverse reinforcement learning (IRL) algorithm family. Existing efforts typically utilize two metrics to measure the IRL performance: the expected value difference (EVD) and the mean reward loss (MRL). Unfortunately, in some cases, EVD and MRL can give completely opposite results, due to MRL focusing on whole state-space rewards, while EVD only considering partly sampled rewards. Such situation naturally rises to one fundamental question: whether current metrics and assessment are sufficient and accurate for more general use. Thus, in this article, based on the metric called normalized mutual information of reward clusters (C-NMI), we propose a novel IRL assessment;we aim to fill this research gap by considering a middle-granularity state space between the entire state space and the specific sampling space. We utilize the agglomerative nesting algorithm (AGNES) to control dynamical C-NMI computing via a fourth-order tensor model with injected manipulated trajectories. With such a model, we can uniformly capture different-dimension values of MRL, EVD, and C-NMI, and perform more comprehensive and accurate assessment and analyses. Extensive experiments on several mainstream IRLs are experimented in object world, hence revealing that the assessing accuracy of our method increases 110.13% and 116.59%, respectively, when compared with the EVD and MRL. Meanwhile, C-NMI is more robust than EVD and MRL under different demonstrations. © 2020 IEEE.

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Malware Detection using Deep Learning with SMOTE and Noise-based Augmentation 6

Enhancing Malware Detection using Deep Learning with SMOTE a...

引用

6th International Conference on Advanced Aspects of Software Engineering, ICAASE 2024

作者： Khadidja, Belattar Mehdi Mohamed, Ait Mohamed, Abdellaoui Imene, Akkouche Okba, Zobiri Computer Science Department University of Algiers Algiers Algeria Laboratory of Research in Artificial Intelligence University of Science and Technology Houari Boumediene Algiers Algeria

ISBN: (纸本)9798331522810

The increasing prevalence of malware poses a significant security threat to financial institutions, businesses, and individuals. Tackling this growing issue requires innovative methods for the accurate and rapid identification and classification of malware, facilitating comprehensive behavioral analysis. Deep learning has emerged as a powerful tool for malware detection due to its ability to identify complex patterns and anomalies in data. This study investigates the application of a custom-designed Convolutional Neural Network (CNN) alongside a hybrid CNN-Long Short-Term Memory (LSTM) model, utilizing augmentation techniques for image-based malware classification. The augmentation methods employed include the Synthetic Minority Over-sampling Technique (SMOTE) and the additive noise. Using the MalImg dataset, the custom-built CNN achieved an impressive classification accuracy of 99.89%, and the hybrid CNN-LSTM model reached 99.68%. Both models outperformed existing state-of-The-Art approaches. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Behaviour-diverse automatic penetration testing:a coverage-based deep reinforcement learning approach

引用

Frontiers of computer science 2025年第3期19卷 15-24页

作者： Yizhou YANG Longde CHEN Sha LIU Lanning WANG Haohuan FU Xin LIU Zuoning CHEN Zhongguancun Laboratory Beijing 100081China Zhejiang Lab Hangzhou 311121China National Research Centre of Parallel Computer Engineering and Technology Wuxi 214000China Faculty of Geographical Science Beijing Normal UniversityBeijing 100875China Department of Earth System Science Tsinghua UniversityBeijing 100084China

Reinforcement Learning(RL)is gaining importance in automating penetration testing as it reduces human effort and increases ***,given the rapidly expanding scale of modern network infrastructure,the limited testing scale and monotonous strategies of existing RLbased automated penetration testing methods make them less effective in practical *** this paper,we present CLAP(Coverage-Based Reinforcement Learning to Automate Penetration Testing),an RL penetration testing agent that provides comprehensive network security assessments with diverse adversary testing behaviours on a massive *** employs a novel neural network,namely the coverage mechanism,to address the enormous and growing action spaces in large *** also utilizes a Chebyshev decomposition critic to identify various adversary strategies and strike a balance between *** results across various scenarios demonstrate that CLAP outperforms state-of-the-art methods,by further reducing attack operations by nearly 35%.CLAP also provides enhanced training efficiency and stability and can effectively perform pen-testing over large-scale networks with up to 500 ***,the proposed agent is also able to discover pareto-dominant strategies that are both diverse and effective in achieving multiple objectives.

关键词： network security penetration testing reinforcement learning artificial intelligence

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：