检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Xu, Chaonong Kong, Weiming Liu, Min Zhang, Mingming Li, Chao Gong, Luqi Beijing Key Lab of Petroleum Data Mining Beijing China Institute of Intelligent Computing Zhejiang Lab Hangzhou China Bupt School of Computer Science National Pilot Software Engineering School Beijing China

ISBN: (纸本)9798350330717

In high-throughput intelligent computing scenarios, multi-device parallelism strategies based on data parallelism or pipeline parallelism have been extensively utilized to accelerate large deep neural network model inference. data parallelism offers nearly linear improvement in inference speed, but it is limited by the memory capacity of a single device which constrains the model size. On the other hand, pipeline parallelism can support larger models, but the total communication of the activations among devices is high, which limits the improvement of the inference speed. To address the demand for efficient model inference in high-throughput heterogeneous scenarios, we proposes a hybrid parallelism strategy that combines data parallelism and pipeline parallelism. The strategy involves grouping heterogeneous device clusters and then employing inter-group data parallelism along with intra-group pipeline parallelism. Moreover, we propose an algorithm to find an optimal hybrid parallel inference strategy with maximum throughput. The control variables of the strategy includes the number of groups, group-device assignments and model partition ratios. Our experimental evaluation demonstrates that compared to PipeEdge, a pipeline parallel inference framework for heterogeneous cluster, our strategy can achieve 1.7× -3.4× acceleration in an 8-device heterogeneous cluster without loss of accuracy. © 2023 IEEE.

关键词： data parallelism heterogeneous cluster hybrid parallelism model inference pipeline parallelism

来源：评论

学校读者我要写书评

暂无评论

Integrating Artificial Intelligence and Multiple Intelligences for Advanced Educational Models

Integrating Artificial Intelligence and Multiple Intelligenc...

引用

2024 International Conference on Electrical, Electronics and computing Technologies, ICEECT 2024

作者： Palarimath, Suresh Maran, Pyingkodi Venkateswaran, R. Wilfred Blessing, N.R. Shiny, K.V. Renuga, S. University of Technology and Applied Sciences College of Computing and Information Sciences Salalah Oman Kongu Engineering College Department of Computer Applications Erode India University of Technology and Applied Sciences College of Computing and Information Sciences Ibri Oman Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798350378092

The aim of educational innovation is to foster students' creative and problem-solving skills via the integration of several disciplines, including science, technology, engineering, art, and mathematics. Efficiently identifying and fostering the various abilities of pupils continues to be a crucial obstacle. This research presents a sophisticated educational approach that combines the notion of multiple intelligences with artificial intelligence (AI) technology to tackle this problem. This concept improves the teaching environment by including intelligent auxiliary services for instructors and students via the use of smart speech and picture interaction. Artificial intelligence (AI) integrated into the multiple intelligence's framework enables the ability to observe, analyze, and implement personalized teaching tactics in real-time using machine learning. The suggested AI-assisted education paradigm aims to enhance teacher-student interactions and facilitate personalized instruction. The study provides evidence that this technique successfully facilitates personalized and captivating learning experiences, promoting students' diverse talents and augmenting their creativity and problem-solving capabilities. This approach seeks to fundamentally transform conventional educational techniques by addressing the disparity between existing educational practices and the future requirements of the workforce. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Reliable Multi-Robot Navigation Platform with Collision Avoidance

An Efficient and Reliable Multi-Robot Navigation Platform wi...

引用

2021 IEEE MIT Undergraduate Research Technology Conference, URTC 2021

作者： Crafts, David Sousa, Jake McLellan, William Robson, Nathan Pham, Cuong School of Computing and Data Science Wenworth Institute of Technology Boston United States

ISBN: (纸本)9781665405959

With the ever-increasing demand for consumer goods, companies are pivoting towards semi or fully autonomous robotic warehouses to efficiently fulfill orders. Large companies have become increasingly reliant on autonomous robotic warehouse solutions, however, the demand from small to medium-sized companies has increased dramatically [8]. These companies often rely on manual solutions, such as forklifts, to traverse their warehouses. In 2019, forklifts accounted for 79 work related deaths and 8,140 nonfatal injuries [9]. Warehouse accidents are the direct result of their fast paced, ever-changing nature. With warehouses containing a multitude of static and dynamic variables, an open-source robotics platform is needed that can safely traverse a warehouse, preventing unnecessary death and injury. The proposed solution allows for the safe and effective navigation of these environments utilizing a path-planning algorithm in tandem with a dynamic obstacle avoidance algorithm. The dynamic obstacle avoidance algorithm uses LiDAR sensor data to detect and avoid obstacles along a path. The path-planning algorithm uses a map of a warehouse environment that accounts for static objects, such as shelves, and generates an efficient path from a starting point to a goal point. These algorithms are simulated in Gazebo allowing for a detailed visual of the platform's performance. These algorithms, together, create a platform that allows for robots to autonomously navigate to desired destinations while safely avoiding a myriad of obstacles. © 2021 IEEE.

关键词： Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

STAR: Stepwise Task Augmentation and Relation Learning for Aspect Sentiment Quad Prediction

arXiv

引用

arXiv 2025年

作者： Lai, Wenna Xie, Haoran Xu, Guandong Li, Qing Department of Computing Hong Kong Polytechnic University Hong Kong School of Data Science Lingnan University Hong Kong School of Computer Science Data Science Institute University of Technology Sydney SydneyNSW Australia Department of Computing The Hong Kong Polytechnic University Hong Kong

Aspect-based sentiment analysis (ABSA) aims to identify four sentiment elements, including aspect term, aspect category, opinion term, and sentiment polarity. These elements construct the complete picture of sentiments. The most challenging task, aspect sentiment quad prediction (ASQP), predicts these elements simultaneously, hindered by difficulties in accurately coupling different sentiment elements. A key challenge is insufficient annotated data that limits the capability of models in semantic understanding and reasoning about quad prediction. To address this, we propose stepwise task augmentation and relation learning (STAR), a strategy inspired by human reasoning. STAR constructs auxiliary data to learn quadruple relationships incrementally by augmenting with pairwise and overall relation tasks derived from training data. By encouraging the model to infer causal relationships among sentiment elements without requiring additional annotations, STAR effectively enhances quad prediction. Extensive experiments demonstrate the proposed STAR exhibits superior performance on four benchmark datasets. © 2025, CC BY-NC-SA.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Study on the Reliability of Visual XAI Methods for X-Ray Images

A Study on the Reliability of Visual XAI Methods for X-Ray I...

引用

21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023

作者： Stodt, Jan Madan, Manav Reich, Christoph Filipovic, Luka Ilijas, Tomi Institute for Data Science Cloud Computingand IT Security Furtwangen University Furtwangen Germany University Donja Gorica Podgorica81000 Montenegro Arctur d.o.o. Nova GoricaSI-5000 Slovenia

ISBN: (纸本)9781643684000

The YOLO series of object detection algorithms, including YOLOv4 and YOLOv5, have shown superior performance in various medical diagnostic tasks, surpassing human ability in some cases. However, their black-box nature has limited their adoption in medical applications that require trust and explainability of model decisions. To address this issue, visual explanations for AI models, known as visual XAI, have been proposed in the form of heatmaps that highlight regions in the input that contributed most to a particular decision. Gradient-based approaches, such as Grad-CAM [1], and non-gradient-based approaches, such as Eigen-CAM [2], are applicable to YOLO models and do not require new layer implementation. This paper evaluates the performance of Grad-CAM and Eigen-CAM on the VinDrCXR Chest X-ray Abnormalities Detection dataset [3] and discusses the limitations of these methods for explaining model decisions to data scientists. © 2023 The authors and IOS Press.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

CareerBoost: A Hybrid RAG-NLP Job Recommendation Framework

CareerBoost: A Hybrid RAG-NLP Job Recommendation Framework

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Sanskruti Deshmukh Aaryaman Bajaj Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

The proposed system presents a novel approach to job recommendation and resume enhancement, leveraging advanced Natural Language Processing (NLP) techniques and Retrieval-Augmented Generation (RAG). We introduce a comprehensive system that combines semantic search, FAISS-based similarity matching, and a fine-tuned GPT-2 model to provide personalized job recommendations and actionable resume improvement suggestions. The evaluation, conducted through offline metrics and online A/B testing with 5,000 users, demonstrates significant improvements over traditional keyword-matching approaches. The RAG-based system achieved a 25.8% increase in recommendation relevance (Precision@10), a 45.7% increase in user engagement, and a 41.2% increase in job application rates. Furthermore, users who applied the system’s resume enhancement suggestions saw a 9.0% improvement in subsequent job matches. These results highlight the potential of AI-driven systems to revolutionize online recruitment and career development, while also emphasizing the need for ongoing consideration of ethical implications and fairness in AI-assisted hiring processes.

关键词： Measurement Ethics Career development Accuracy Engineering profession Semantic search Resumes Natural language processing Recruitment Testing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Mobile Microclimate System

Enhanced Mobile Microclimate System

引用

2021 IEEE MIT Undergraduate Research Technology Conference, URTC 2021

作者： Zeng, Qian Ying Ramsey, Donovan Yu, Chen-Hsiang School of Computing and Data Science Wentworth Institute of Technology Boston United States

ISBN: (纸本)9781665405959

Collecting data on temperature, humidity, and other environmental aspects is important in architectural fieldwork when trying to understand how these factors affect vernacular architecture. The devices for collecting this kind of data are expensive and cumbersome. Architecture specialists must carry multiple devices for the fieldwork and most of them need a physical computer connection to view the data. We propose a new mobile system that simplifies the current procedure for microclimate data collection. Compared with other existing devices, our solution is cheaper, more compact, and no need to have a wire connection to an external computer. Our solution uses Raspberry Pi 4, retail humidity, temperature, and light sensors, as well as a web application for keeping track of observed buildings and monitoring their microclimate data. This research is an extension to our previous work with improvements, such as making the web application responsive and lightweight along with improving security and providing data analysis of collected information. © 2021 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Analyze Decentralized Personal Health data using Solid, Digital Consent, and Federated Learning 14

Analyze Decentralized Personal Health Data using Solid, Digi...

引用

14th International Conference on Semantic Web Applications and Tools for Health Care and Life sciences, SWAT4HCLS 2023

作者： Sun, Chang van Soest, Johan Dumontier, Michel Institute of Data Science Faculty of Science and Engineering Maastricht University Maastricht Netherlands Department of Advanced Computing Sciences Faculty of Science and Engineering Maastricht University Maastricht Netherlands Brightlands Institute of Smart Society Faculty of Science and Engineering Maastricht University Maastricht Netherlands GROW School for Oncology and Reproduction Maastricht University Medical Centre Maastricht Netherlands

TIDAL is a Solid (SOcial Linked data)-based, citizen-centric data platform that facilitates interactions by citizens and researchers for health research. In this demonstration, we will show how TIDAL 1) can store personal data in Solid pods as RDF with well-known health-related vocabularies (e.g., SNOMED CT), 2) controls access to query fine-grained subsets of personal data, 3) enables researchers to post a human- and machine-readable digital consent using data Privacy Vocabulary, and 4) uses federated learning to analyze personal health data from multiple individuals using a Personal Health Train framework. TIDAL offers a new data paradigm of sharing and using personal data for research and ultimately increase the availability of personal data for societal relevant uses. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Constraining the Higgs potential with neural simulation-based inference for di-Higgs production

引用

Physical Review D 2024年第5期110卷 056004页

作者： Radha Mastandrea Benjamin Nachman Tilman Plehn Department of Physics Physics Division Berkeley Institute for Data Science Institut für Theoretische Physik Interdisciplinary Center for Scientific Computing (IWR)

Determining the form of the Higgs potential is one of the most exciting challenges of modern particle physics. Higgs pair production directly probes the Higgs self-coupling and should be observed in the near future at the High-Luminosity LHC. We explore how to improve the sensitivity to physics beyond the Standard Model through per-event kinematics for di-Higgs events. In particular, we employ machine learning through simulation-based inference to estimate per-event likelihood ratios and gauge potential sensitivity gains from including this kinematic information. In terms of the Standard Model Effective Field Theory, we find that adding a limited number of observables can help to remove degeneracies in Wilson coefficient likelihoods and significantly improve the experimental sensitivity.

关键词： Effective field theory Extensions of Higgs sector Signatures with Higgs bosons Artificial neural networks Bayesian methods Machine learning

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Intrusion Prevention: A Review of Techniques and Applications 7th

Explainable AI for Intrusion Prevention: A Review of Techniq...

引用

7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023

作者： Chandre, Pankaj R. Vanarote, Viresh Patil, Rajkumar Mahalle, Parikshit N. Shinde, Gitanjali R. Nimbalkar, Madhukar Barot, Janki Department of Computer Science and Engineering MIT School of Computing MIT ADT University Loni Kalbhor India Department of Information Technology MIT School of Computing MIT ADT University Loni Kalbhor India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology Kondhawa India Department of Computer Science and Engineering Vishwakarma Institute of Information Technology Kondhawa India Silver Oak University Ahmedabad India

ISBN: (纸本)9789819937578

Intrusion prevention has become a critical concern in today's increasingly complex and interconnected digital systems. Traditional intrusion prevention methods often rely on rule-based approaches that can be inflexible and prone to false positives and false negatives. The emergence of explainable artificial intelligence (AI) techniques has the potential to provide more accurate and interpretable solutions for intrusion prevention. This review paper surveys the current state of the art in explainable AI techniques for intrusion prevention, including their strengths and limitations. We begin by providing an overview of intrusion prevention and the challenges faced by traditional methods. We then explore the different types of explainable AI techniques, such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley Additive Explanations (SHAP), and Integrated Gradients, and their application to intrusion prevention. We also discuss the different types of datasets and evaluation metrics used in explainable AI-based intrusion prevention, including public datasets such as NSL-KDD and UNSW-NB15. Finally, we highlight the future research directions in explainable AI-based intrusion prevention, including the need for larger and more diverse datasets, better evaluation metrics, and more comprehensive explainable AI models. Overall, this review paper provides a comprehensive overview of the state of the art in explainable AI for intrusion prevention, and serves as a valuable resource for researchers and practitioners in the field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Additives

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：