检索结果-内蒙古大学图书馆

Demo2Test: Transfer Testing of Agent in Competitive Environment with Failure Demonstrations

ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY 2025年第2期34卷 1-28页

作者： Chen, Jianming Wang, Yawen Wang, Junjie Xie, Xiaofei Wang, Dandan Wang, Qing Xu, Fanjiang Chinese Acad Sci Inst Software Beijing Peoples R China Singapore Management Univ Singapore Singapore

The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are to construct a testing agent that competes with the target agent to induce its failures. These approaches usually focus on a single task, requiring much more time for multi-task testing. However, if the previously tested tasks (source tasks) and the task to be tested (target task) share similar agents or task objectives, the transferable knowledge in source tasks can potentially increase the effectiveness of testing in the target task. We propose Demo2Test for conducting transfer testing of agents in the competitive environment, i.e., leveraging the demonstrations of failure scenarios from the source task to boost the testing effectiveness in the target task. It trains a testing agent with demonstrations and incorporates the action perturbation at key states to balance the number of revealed failures and their diversity. We conduct experiments in the simulated robotics competitive environments of MuJoCo. The results indicate that Demo2Test outperforms the best-performing baseline with improvements ranging from 22.38% to 87.98%, and 12.69% to 60.98%, in terms of the number and diversity of discovered failure scenarios, respectively.

关键词： Computer systems organization Reliability Software and its engineering Software testing and debugging computing methodologies Adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Function Granularity for Serverless Machine Learning Application with GPU Sharing

引用

PROCEEDINGS OF THE ACM ON MEASUREMENT AND ANALYSIS OF computing SYSTEMS 2025年第1期9卷 1-28页

作者： Hui, Xinning Xu, Yuanchao Shen, Xipeng North Carolina State Univ Raleigh NC 27695 USA Univ Calif Santa Cruz Santa Cruz CA USA

Recent years have witnessed increasing interest in machine learning (ML) inferences on serverless computing due to its auto-scaling and cost-effective properties. However, one critical aspect, function granularity, has been largely overlooked, limiting the potential of serverless ML. This paper explores the impact of function granularity on serverless ML, revealing its important effects on the SLO hit rates and resource costs of serverless applications. It further proposes adaptive granularity as an approach to addressing the phenomenon that no single granularity fits all applications and situations. It explores three predictive models and presents programming tools and runtime extensions to facilitate the integration of adaptive granularity into existing serverless platforms. Experiments show adaptive granularity produces up to a 29.2% improvement in SLO hit rates and up to a 24.6% reduction in resource costs over the state-of-the-art serverless ML which uses fixed granularity.

关键词： Computer systems organization Cloud computing computing methodologies Planning and scheduling

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Game Theory-Based Feature Selection for Efficient Hand Grasp Classification Using Minimal Number of sEMG Signals

引用

ACM TRANSACTIONS ON computing FOR HEALTHCARE 2025年第1期6卷 1-22页

作者： Singh, Shashank kumar Chaturvedi, Amrita Indian Inst Technol BHU Dept Comp Sci & Engn Varanasi India

Deploying bio-electrical signals and image processing (visual) techniques are the two popular means to provide input to generate grasp control for robotic and prosthetic devices. Visual perception-based techniques rely on computationally expensive image processing algorithms and are affected by lighting conditions. In contrast, grasp control based on bio-electric signals such as surface electromyography (sEMG) is invariant to lighting conditions. It can reflect human intent to hand motion or grasp with lesser computational costs. In this article, we propose an efficient machine learning pipeline to classify hand grasp using a minimal number of sEMG sensors. A cooperative game theory-based feature selection technique is applied to find the representative feature subset. The feature selection method uses a modified marginal contribution based on the class distribution coefficient to generate feature ranking. This feature ranking is further used to find the most representative feature subset from the extracted feature set. Our proposed pipeline has been evaluated on a benchmark dataset and has achieved a classification accuracy of 98.20%, using single-channel EMG when coupled with the XGBoost classifier. Thorough assessments were conducted to confirm the reliability of the results obtained. Our proposed pipeline holds the potential to facilitate the development of cost-effective sEMG prosthetics.

关键词： Human-centered computing computing methodologies Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Layout-Agnostic Human Activity Recognition in Smart Homes through Textual Descriptions Of Sensor Triggers (TDOST)

引用

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT 2025年第1期9卷 1-38页

作者： Thukral, Megha Dhekane, Sourish gunesh Hiremath, Shruthi k. Haresamudram, Harish Ploetz, Thomas Georgia Inst Technol Sch Interact Comp Atlanta GA 30332 USA Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA USA

Human activity recognition (HAR) using ambient sensors in smart homes has numerous applications for human healthcare and wellness. However, building general-purpose HAR models that can be deployed to new smart home environments requires a significant amount of annotated sensor data and training overhead. Most smart homes vary significantly in their layouts, i.e., floor plans and the specifics of sensors embedded, resulting in low generalizability of HAR models trained for specific homes. We address this limitation by introducing a novel, layout-agnostic modeling approach for HAR systems in smart homes that utilizes the transferrable representational capacity of natural language descriptions of raw sensor data. To this end, we generate Textual Descriptions Of Sensor Triggers (TDOST) that encapsulate the surrounding trigger conditions and provide cues for underlying activities to the activity recognition models. Leveraging textual embeddings, rather than raw sensor data, we create activity recognition systems that predict standard activities across homes without (re-)training or adaptation to target homes. Through an extensive evaluation, we demonstrate the effectiveness of TDOST-based models in unseen smart homes through experiments on benchmark Orange4Home and CASAS datasets. Furthermore, we conduct a detailed analysis of how the individual components of our approach affect downstream activity recognition performance.

关键词： Human-centered computing Ubiquitous and mobile computing Empirical studies in ubiquitous and mobile computing computing methodologies Machine learning

来源：评论

学校读者我要写书评

暂无评论

Computer vision methods under rapid evolution for pathology image tasks

引用

HISTOPATHOLOGY 2025年第2期86卷 199-203页

作者： Maher, Nigel G. Scolyer, Richard A. Liu, Sidong Univ Sydney Melanoma Inst Australia Sydney NSW Australia Univ Sydney Fac Med & Hlth Sydney NSW Australia Royal Prince Alfred Hosp Tissue Pathol & Diagnost Oncol Sydney NSW Australia NSW Hlth Pathol Sydney NSW Australia Univ Sydney Charles Perkins Ctr Sydney NSW Australia Macquarie Univ Australian Inst Hlth Innovat Ctr Hlth Informat Sydney NSW Australia

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Soft computing Enabled Techniques for IoT Security: State-of-the-Art and Challenges Ahead 5th

A Comprehensive Review of Soft Computing Enabled Techniques ...

引用

5th International Conference on Data Science, Machine Learning and Applications

作者： Parabrahmachari, Sriram Narayanasamy, Srinivasan Sathyabama Inst Sci & Technol Dept Comp Sci & Engn Chennai 600119 Tamil Nadu India Rajalakshmi Engn Coll Dept Comp Sci & Engn Chennai 600119 Tamil Nadu India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

In the past ten years, the Internet of Things (IoT) has become a massive force in our daily lives, providing countless smart services that have improved human existence. Nevertheless, the increased availability and rapidly escalating demand for intelligent devices and networks mean that IoT is currently encountering unprecedented security challenges. While there are established security protocols in place for IoT, these conventional methods fall short in effectively addressing the escalating frequency and severity of attacks. The term 'security' is used to encompass various concepts, including integrity, confidentiality, and privacy. Therefore, a strong and up-to-date security system is necessary for the next generation of industrial IoT. One area of technological advancement that can address the ongoing and future challenges of IoT security is Soft computing. It has opened up many possible research avenues for detecting attacks and identifying abnormal behaviors in smart devices and networks. This paper explores the architecture of IoT and provides a comprehensive literature review of Soft computing based approaches to IoT security, including the different types of possible attacks. It also presents potential Soft computing-based solutions for IoT security and discusses open research issues along with future research scope.

关键词： Internet of Things (IoT) Security and privacy Soft computing Attacks computing methodologies

来源：评论

学校读者我要写书评

暂无评论

Human–machine interaction in building an English reference dataset for natural language processing tasks

引用

Language Resources and Evaluation 2025年 1-29页

作者： Žitko, Branko Gašpar, Angelina Bročić, Lucija Vasić, Daniel Grubišić, Ani Faculty of Science University of Split Ruđera Boškovića 33 Split 21000 Croatia Catholic Faculty of Theology University of Split Zrinsko Frankopanska 19 Split 21000 Croatia Faculty of Science and Education University of Mostar Matice hrvatske b.b. Mostar 88000 Bosnia and Herzegovina

Rich in information and annotated instances, a reference annotated dataset is essential for the training and evaluation of Natural Language Processing (NLP) tools. However, the creation of such linguistic resources is a tedious and time-consuming task involving lexical, syntactic, and semantic annotations, typically at the sentence level. Assuming we could speed up the human annotation process, we employed pre-trained models (spaCy, AllenNLP, EWISER) to automatically annotate a dataset of 664 sentences (6853 tokens, including 1598 predicates) taken from grammar books. A multi-layered annotation task encompassed Lemmatization (LEM), Part-of-Speech Tagging (UPOS, XPOS), Named Entity Recognition (NER), Dependency Parsing (DEP, HEAD), Coreference Resolution (COREF), Semantic Role Labelling (SRL), Predicate Sense Disambiguation (PSD) and Word Sense Disambiguation (WSD). Three annotators post-edited the noisy automatic annotations, and their average Inter-Annotator Agreement (IAA) for all annotation tasks at the token level was 0.91 and at the sentence level 0.74. Evaluation metrics including Accuracy, Precision, Recall, and F1 revealed disparities between machine and human annotations, along with correlations between machine annotations at both token and sentence levels. Manual error analysis identified instances where NLP tools failed to generate accurate annotations. A comparison of time spent per layer revealed that refining a pre-annotated subset of sentences required significantly less time than annotating them manually from scratch. This process resulted in an English reference dataset, tailored for the development of a hypergraph-based knowledge extraction model, known as the Natural Language 2 Semantic Hyper-graph Dataset (NL2SH) 1.0), which is accessible through CLARIN. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Artificial intelligence CCS concepts computing methodologies Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Filling the Void: Data-Driven Machine Learning-based Reconstruction of Sampled Spatiotemporal Scientific Simulation Data 24

Filling the Void: Data-Driven Machine Learning-based Reconst...

引用

Proceedings of the SC '24 Workshops of the International Conference on High Performance computing, Network, Storage, and Analysis

作者： Ayan Biswas Aditi Mishra Meghanto Majumder Subhashis Hazarika Alexander Most Juan Castorena Christopher Bryan Patrick McCormick James Ahrens Earl Lawrence Aric Hagberg Los Alamos National Lab Los Alamos U.S.A. Arizona State University Tempe U.S.A. Fujitsu Research of America Inc. Santa Clara U.S.A. Los Alamos National Lab Los Alamos U.S.A

ISBN: (纸本)9798350355543

As high-performance computing systems continue to advance, the gap between computing performance and I/O capabilities is widening. This bottleneck limits the storage capabilities of increasingly large-scale simulations, which generate data at never-before-seen granularities while only being able to store a small subset of the raw data. Recently, strategies for data-driven sampling have been proposed to intelligently sample the data in a way that achieves high data reduction rates while preserving important regions or features with high fidelity. However, a thorough analysis of how such intelligent samples can be used for data reconstruction is lacking. We propose a data-driven machine learning approach based on training neural networks to reconstruct full-scale datasets based on a simulation's sampled output. Compared to current state-of-the-art reconstruction approaches such as Delaunay triangulation-based linear interpolation, we demonstrate that our machine learning-based reconstruction has several advantages, including reconstruction quality, time-to-reconstruct, and knowledge transfer to unseen timesteps and grid resolutions. We propose and evaluate strategies that balance the sampling rates with model training (pretraining and fine-tuning) and data reconstruction time to demonstrate how such machine learning approaches can be tailored for both speed and quality for the reconstruction of grid-based datasets.

关键词： computing methodologies

来源：评论

学校读者我要写书评

暂无评论

The Random Hivemind: An ensemble deep learning application to the solar energetic particle prediction problem

引用

ADVANCES IN SPACE RESEARCH 2024年第12期74卷 6252-6263页

作者： O'Keefe, Patrick M. Sadykov, Viacheslav Kosovichev, Alexander Kitiashvili, Irina N. Oria, Vincent Nita, Gelu M. Francis, Fraila Chong, Chun-Jie Kosovich, Paul Ali, Aatiya Marroquin, Russell D. New Jersey Inst Technol Comp Sci Dept 323 Dr Martin Luther King Jr Blvd Newark NJ 07102 USA Georgia State Univ Phys & Astron Dept 25 Pk Pl NE Atlanta GA 30303 USA New Jersey Inst Technol Phys Dept 323 Dr Martin Luther King Jr Blvd Newark NJ 07102 USA NASA Res Pk NASA Ames Res Ctr Moffett Field CA 94035 USA Univ Calif San Diego Dept Phys 9500 Gilman Dr La Jolla CA 92093 USA

The application of machine learning and deep learning techniques, including the wide use of non-ensemble, conventional neural networks (CoNN), for predicting various phenomena has become very popular in recent years thanks to the efficiencies and the abilities of these techniques to find relationships in data without human intervention. However, certain CoNN setups may not work on some data- sets, especially if the parameters passed to it, including model parameters and hyperparameters, are arguably arbitrary in nature and need to continuously be updated with the need to retrain the model, especially if the additions of new features render old models obsolete. This concern can be partially alleviated by employing committees of neural networks that are identical in terms of input features and initialized randomly and "vote" on the decisions made by the committees as a whole. Yet, members of the committee have similar architectures and features passed to them, making it possible for the committee members to "agree" on identical sets of weights and biases for all nodes and edges. Members of these committees also cannot be expanded to accommodate new features and entire committees must therefore be retrained in order to do so. We propose the Random Hivemind (RH) approach, which helps to alleviate this concern by having multiple neural network estimators make decisions based on random permutations of features and prescribing a method to determine the weight of the decision of each individual estimator. The effectiveness of RH is demonstrated through experimentation in the predictions of hazardous Solar Energetic Particle (SEP) events by comparing it to that of using both CoNNs and the aforementioned setup of committees identical in input features in this application. Our results demonstrate that RH, while having a comparable or better performance than the CoNN and a Committee-based approach, demonstrates a lesser score spread for the individual experiments, and shows pro

关键词： Sun activity particle emission Solar-terrestrial relations computing methodologies boosting Machine learning Neural networks

来源：评论

学校读者我要写书评

暂无评论

Human-Aided Bots

引用

IEEE INTERNET computing 2018年第6期22卷 36-43页

作者： Kucherbaev, Pavel Bozzon, Alessandro Houben, Geert-Jan Delft Univ Technol Fac Elect Engn Math & Comp Sci Delft Netherlands

A chatbot is an example of a text-based conversational agent. While natural language understanding and machine learning techniques have advanced rapidly, current fully automated chatbots still struggle to serve their users well. Human intelligence, brought by crowd workers, freelancers, or even full-time employees can be embodied in the chatbot logic to fill the gaps caused by limitations of fully automated solutions. In this paper, we investigate human-aided bots, i.e., bots (including chatbots) using humans in the loop to operate. We survey industrial and academic examples of human-aided bots, discuss their differences and common patterns, and identify open research questions.

关键词： Human Computer Interaction Interactive Systems Learning Artificial Intelligence Natural Language Processing Software Agents Human Aided Bots Text Based Conversational Agent Natural Language Understanding Machine Learning Techniques Human Intelligence Chatbot Logic Internet Object Recognition Text Processing Machine Learning Natural Language Processing Bot Internet Man Machine Interface General Literature Introductory And Survey Information Technology And Systems Models And Principles User Machine Systems Human Centered computing computing methodologies Artificial Intelligence Distributed Artificial Intelligence Intelligent Agents Services computing Principles Of Services General Services Architectures

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：