检索结果-内蒙古大学图书馆

Transfer Learning with Foundational Models for Time Series Forecasting using Low-Rank Adaptations

Information Fusion 2025年 123卷

作者： Germán-Morales, M. Rivera-Rivas, A.J. del Jesus Díaz, M.J. Carmona, C.J. Andalusian Research Institute in Data Science and Computational Intelligence Department of Computer Science University of Jaen Jaen E-23071 Spain Leicester School of Pharmacy DeMontfort University Leicester LE1 7RH United Kingdom

Foundational Models are an emerging widely used technique of Generative Artificial intelligence. These models are distinguished by their scalability and the ease with which they can be adapted through the exploitation of Transfer Learning. The availability of high computational power and large datasets have supported their development, achieving a high generalization capacity due to the enormous and heterogeneous amounts of data used in their initial training. These characteristics contribute to a solid base that can be adapted or adjusted to a wide range of tasks, increasing their applicability. This study proposes the methodology LLIAM, a straightforward adaptation of a kind of Foundational Models, Large Language Models, for the Time Series Forecasting task. An adequate time-series prompting schema and Low-Rank Adaptations are used to enhance the knowledge of the model with diverse time series datasets, known as the fine-tuning phase. A study divided in two stages has been performed for evaluating the effectiveness of the proposed methodology. Initially, a comparison was made between the performance of LLIAM and different state-of-the-art Deep Learning algorithms, including Recurrent Neural Networks and Temporal Convolutional Networks, as well as a LLM-based method, TimeLLM. Following this, a zero-shot study is presented in order to evaluate the generalization capacity of the proposed methodology with time series datasets from unknown domains not considered in the model training. The outcomes of this investigation demonstrate the efficacy of LLIAM, highlighting that this straightforward and general approach can attain competent results without the necessity for applying complex modifications. This work also encourages the use of available resources (such as these pre-trained models) and efficient fine-tuning techniques to avoid unnecessary and costly training, narrowing the gap between the goals of traditional Artificial intelligence and Green Artificial Intellige

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Toward Responsible Artificial intelligence Systems: Safety and Trustworthiness 8th

Toward Responsible Artificial Intelligence Systems: Safety a...

引用

8th International Conference on Engineering of Computer-Based Systems, ECBS 2023

作者： Herrera, Francisco Department Computer Sciences and Artificial Intelligence Andalusian Research Institute on Data Science and Computational Intelligence University of Granada Granada Spain

ISBN: (纸本)9783031492518

This short paper associated to the invited lectures introduces two key concepts essential to artificial intelligence (AI), the area of trustworthy AI and the concept of responsible AI systems, fundamental to understand the technological, ethical and legal context of the current framework of debate and regulation of AI. The aim is to understand their dimension and their interrelation with the rest of the elements involved in the regulation and auditability of AI algorithms in order to achieve safe and trusted AI. We highlight concepts in bold in order to fix the moment when they are described in context. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Accuracy improvements in linguistic fuzzy modeling

引用

丛书名： Studies in fuzziness and soft computing

2003年

作者： Jorge Casillas Francisco Herrera Óscar Cordón Luis Magdalena

来源：评论

学校读者我要写书评

暂无评论

Large-scale group decision-making method based on knowledge differentiation and the grouping of alternatives into modifiable scenarios

引用

Procedia Computer science 2022年 214卷 927-934页

作者： José Ramón Trillo Enrique Herrera-Viedma María José Higueras-Ruiz Sergio Alonso Juan Antonio Morente-Molinera Francisco Javier Cabrerizo Department of Computer Science and Artificial Intelligence Andalusian Research Institute of Data Science and Computational Intelligence DaSCI University of Granada Granada 18071 Spain Department of Information and Communication University of Granada Granada 18071 Spain Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada 18071 Spain

Nowadays, group decision-making is an everyday event, since we usually live in a community. Nevertheless, when the number of participants is large, it starts to generate a lot of information that is complex to manage, and unlike group decision-making, where the participants are usually experts, when the number of participants increases, not all of them are, which generates a conflict of interest because the value of the vote of an expert and a (non-expert) user is worth the same. Moreover, it may happen that not all participants who start a process will finish it and not all of them will be able to make all the assessments, since they do not know all the options. Therefore, to solve all the drawbacks, this paper presents a large-scale group decision-making system in a modifiable scenario environment that groups participants according to their preferred alternative and also performs knowledge differentiation, clustering them into experts and users. This allows for optimising the consensus process, as the consensus is made by comparing the clusters and the participants with each other.

关键词： Large-Scale Group Decision-Making Consensus Clustering Modifiable Scenarios Knowledge Differentiation

来源：评论

学校读者我要写书评

暂无评论

Advances in Artificial intelligence 1

引用

丛书名： Lecture Notes in Computer science

1000年

作者： Francisco Herrera Sergio Damas Rosana Montes Sergio Alonso Óscar Cordón Antonio González Alicia Troncoso

ISBN: (数字)9783030003746

ISBN: (纸本)9783030003739

This book constitutes the refereed proceedings of the 18th Conference of the Spanish Association for;Artificial intelligence, CAEPIA 2018, held in Granada, Spain, in October 2018.;The 36 full papers presented were carefully selected from 240 submissions. The Conference of the Spanish Association of;Artificial intelligence (CAEPIA) is a biennial forum open to researchers from all over the world to present and discuss their latest scientific and technological advances in Antificial intelligence (AI). Authors are kindly requested to submit unpublished original papers describing relevant research on AI issues from all points of view: formal, methodological, technical or applied.

关键词： Artificial intelligence Algorithm Analysis and Problem Complexity Discrete Mathematics in Computer science data Structures Image Processing and Computer Vision Models and Principles

来源：评论

学校读者我要写书评

暂无评论

Local Attention: Enhancing the Transformer Architecture for Efficient Time Series Forecasting

Local Attention: Enhancing the Transformer Architecture for ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Ignacio Aguilera-Martos Andrés Herrera-Poyatos Julián Luengo Francisco Herrera Department of Computer Science and Artificial Intelligence Andalusian Institute of Data Science and Computational Intelligence (DaSCI) University of Granada Spain

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Transformers have emerged as a highly effective architecture for natural language processing and computer vision. Of late, there has been a surge in initiatives aimed at refining this architecture to enhance its applicability to long sequence time-series forecasting, yielding promising *** paper introduces Local Attention, an efficient attention mechanism tailored for time series data. This mechanism exploits the continuity properties of time series and the principle of locality in order to compute less attention scores. We provide an Θ(n log n) algorithm to implement Local Attention based on tensor algebra results, which contrasts to the Θ(n 2 ) time and memory complexity of the original attention *** experimental analysis shows that the vanilla transformer with Local Attention outperforms state of the art models based on probabilistic attention mechanisms. These findings affirm the effectiveness of our approach and outline a spectrum of future challenges in long sequence time series forecasting.

关键词： Attention mechanisms Tensors Time series analysis Refining Neural networks Computer architecture Transformers

来源：评论

学校读者我要写书评

暂无评论

MULTICAST: MULTI CONFIRMATION-LEVEL ALARM SYSTEM BASED on CNN and LSTM to MITIGATE FALSE ALARMS for HANDGUN DETECTION in VIDEO-SURVEILLANCE

arXiv

引用

arXiv 2021年

作者： Olmos, R. Pérez-Hernández, Francisco Tabik, S. Lamas, Alberto Herrera, F. Dpt. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada 18071 Spain Dpt. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada 18071 Spain

Despite the constant advances in computer vision, integrating modern single-image detectors in real-time handgun alarm systems in video-surveillance is still debatable. Using such detectors still implies a high number of false alarms and false negatives. In this context, most existent studies select one of the latest single-image detectors and train it on a better dataset or use some pre-processing, post-processing or data-fusion approach to further reduce false alarms. However, none of these works tried to exploit the temporal information present in the videos to mitigate false detections. This paper presents a new system, called MULTI Confirmation-level Alarm SysTem based on Convolutional Neural Networks (CNN) and Long Short Term Memory networks (LSTM) (MULTICAST), that leverages not only the spacial information but also the temporal information existent in the videos for a more reliable handgun detection. MULTICAST consists of three stages, i) a handgun detection stage, ii) a CNN-based spacial confirmation stage and iii) LSTM-based temporal confirmation stage. The temporal confirmation stage uses the positions of the detected handgun in previous instants to predict its trajectory in the next frame. Our experiments show that MULTICAST reduces by 80% the number of false alarms with respect to Faster R-CNN based-single-image detector, which makes it more useful in providing more effective and rapid security responses. Copyright © 2021, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Ying Bi, Bing Xue, Mengjie Zhang: Genetic programming for image classification—an automated approach to feature learning

引用

Genetic Programming and Evolvable Machines 2022年第4期23卷 589-590页

作者： Zafra, Amelia Department of Computer Science and Numerical Analysis Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Cordoba Cordoba Spain

来源：评论

学校读者我要写书评

暂无评论

Building Consensus in Group Decision-Making with Intuitionistic Reciprocal Preference Relations: An Analysis of Various Protocols of Information Granularity Distribution

Building Consensus in Group Decision-Making with Intuitionis...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Gonzalez-Quesada, Juan Carlos Cabrerizo, Francisco Javier Herrera-Viedma, Enrique Pedrycz, Witold Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Department of Computer Science and Artificial Intelligence Granada18071 Spain University of Alberta Department of Electrical & Computer Engineering EdmontonABT6R 2V4 Canada

ISBN: (纸本)9781665410205

On the one hand, to model experts' preferences in group decision-making, intuitionistic reciprocal preference relations have widely been used because they allow for accommodating hesitation degrees, which are inherent to all decision-making processes. On the other hand, an optimization of information granularity distribution has recently been applied to establish consensus during group decision-making processes. Concretely, a symmetric and uniform distribution of information granularity has been considered for intuitionistic reciprocal preference relations. However, there exist other protocols of information granularity distribution that could be used. Therefore, we aim to analyze all the information granularity distribution protocols and determine their effectiveness in building consensus through intuitionistic reciprocal preference relations. The performance of the different protocols is discussed by conducting some numerical experiments that help provide insights into the effectiveness of the protocols to build consensus. © 2024 IEEE.

关键词： Information granules

来源：评论

学校读者我要写书评

暂无评论

Software Product Quality Models, Developments, Trends, and Evaluation

引用

SN Computer science 2020年第3期1卷 1-24页

作者： Galli, Tamas Chiclana, Francisco Siewe, Francois Institute of Artificial Intelligence (IAI) Faculty of Computing Engineering and Media De Montfort University Leicester United Kingdom Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI) University of Granada Granada Spain Software Technology Research Laboratory (STRL) Faculty of Computing Engineering and Media De Montfort University Leicester United Kingdom

Software product quality models have evolved in their abilities to capture and describe the abstract notion of software quality since the 1970s. Many models constructed deal with a specific part of software quality only which makes them ineligible to assess the quality of software products as a whole. Former publications failed to thoroughly examine and list all the available models which attempt to describe each known property of software product quality. This paper discovers such complete software product quality models published since 2000;moreover, it endeavours to measure the relevance of each model quantitatively by introducing indicators with regard to the scientific and industrial community. The identified 23 software product quality model classes differ significantly in terms of publication intensity, publication range, quality score average, relevance score and the 12-month average of the Google Relative Search Index. The results offer a foundation for selecting the appropriate software product quality model for use or for extension if newly identified quality properties need to be connected to a general context. Furthermore, the experiences accumulated on the field of software product quality modelling motivated researchers to successfully transfer the concepts to other areas where abstract entities need to be compared or assessed including the quality of higher educational teaching and business processes, which is also briefly highlighted in the paper. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Execution tracing Quality assessment software engineering Software product quality model

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：