检索结果-内蒙古大学图书馆

23rd EPIA Conference on Artificial Intelligence, EPIA 2024

作者： Wallace, Richard J. Insight Centre for Data Analytics and Department of Computer Science University College Cork Cork Ireland

ISBN: (纸本)9783031734991

We still do not have an adequate understanding of heuristic methods used for solving constraint satisfaction problems (CSPs). An example involves the effects of preprocessing, an essential means of improving CSP search. The traditional explanation for its beneficial effect is that the resulting "problem reduction" leaves fewer possibilities to explore. Recently, however, it was shown that when dynamic variable ordering heuristics are used, other factors related to domain size reduction are much more important. This paper extends this analysis and explores some implications of this new perspective. The key idea is that pattern of domain reductions produced by preprocessing transmits information that guides heuristic decisions. Treating domain reduction as a code and the set of reductions as a message of length n transmitted to the search algorithm, we distinguish two factors, message discriminability and code quality, and show that greater problem reduction enhances both. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Pavement Condition Assessment: A Comprehensive Review of Affordable Sensing Technologies for Cycle Tracks 11

Enhancing Pavement Condition Assessment: A Comprehensive Rev...

引用

11th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2025

作者： Garcia, Jeziel Antonio Ayala Shah, Syed Baig, Muhammad Hassam Qureshi, Waqar Shahid Ullah, Ihsan School of Computer Science University of Galway Galway Ireland Insight SFI Research Centre for Data Analytics University of Galway Galway Ireland

ISBN: (纸本)9789897587450

This paper explores the potential of low-cost sensing technologies for assessing the condition of cycling track pavement. As cycling gains popularity, the demand for efficient pavement maintenance solutions increases. Machine survey-based pavement condition assessment often relies on expensive, specialized equipment, which is not always suitable for cycle tracks due to limited budgets and accessibility, hence the need for low-cost solutions. The integration of low-cost sensing technologies and data collection, such as inertial measurement units (IMUs), low-cost imaging sensors, and crowdsourced data collection, presents a promising alternative for cycle track pavement surface assessment. This paper highlights the advantages of employing out-of-the-shelf devices such as smartphones with GPS, cameras, and IMU, or action cameras with GPS and IMU to collect images, their location, and vehicle vibration in a specific orientation. This data is then used to estimate pavement roughness, detect surface distress, and compute pavement surface condition. Literature reviews reveal a significant gap in the utilization of these technologies for cycle tracks, suggesting a promising area for further research and application. Furthermore, it proposes a software framework for data collection and visualization to combine these technologies to enhance the efficiency and reliability of pavement assessment for cycling infrastructure at a lower cost than machine-based pavement assessment and faster and more quantitative than manual surveys. This paper emphasizes the need for more practical and scalable solutions that support the maintenance of sustainable transportation systems. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Conformal Prediction Techniques for Electricity Price Forecasting 9th

Conformal Prediction Techniques for Electricity Price Forec...

引用

9th International Workshop on Advanced analytics and Learning on Temporal data, AALTD 2024

作者： O’Connor, Ciaran Prestwich, Steven Visentin, Andrea SFI CRT in Artificial Intelligence School of Computer Science & IT University College Cork Cork Ireland Insight Centre for Data Analytics School of Computer Science & IT University College Cork Cork Ireland

ISBN: (纸本)9783031770654

Integrating the erratic production of renewable energy into the electricity grid poses numerous challenges. One approach to stabilising market prices and reducing energy losses due to curtailments is the deployment of batteries. Efficient electricity arbitrage is crucial to make investments in storage systems financially viable;trading solutions to achieve this rely on price forecasting techniques. This study delves into the application of Conformal Prediction (CP) techniques, including Ensemble Batch Prediction Intervals (EnbPI) and Sequential Predictive Conformal Inference for Time Series (SPCI), for generating probabilistic forecasts in the Irish electricity market. Recent advancements in CP have addressed temporal considerations inherent in time series forecasting, eliminating the need for exchangeability assumptions. Our study demonstrates that despite potential efficiency trade-offs, CP methods consistently yield precise and reliable prediction intervals, ensuring comprehensive coverage. We assess the impact of CP on the financial results of a simulated trading algorithm. Monetary outcomes achieved with EnbPI and SPCI outperform those of both split CP and traditional quantile regression models, highlighting the practical superiority of CP in electricity price forecasting. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Children’s Faces from Cropped Lip and Nose Images: A Large Mask Inpainting Approach for Privacy-Conscious Cleft data 5th

Reconstructing Children’s Faces from Cropped Lip and Nose...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Atputharuban, Daniel Anojan Theopold, Christoph Lawlor, Aonghus The Insight Centre for Data Analytics School of Computer Science University College Dublin Dublin Ireland Children’s Health Ireland at Temple Street Dublin Ireland

ISBN: (纸本)9789819638628

Cleft lip and Palate (CLP) is a congenital anomaly that leads to deformities in the orofacial regions at birth. While Cleft deformities can be fully corrected through primary Cleft repair surgery followed by secondary interventions, accurately representing the outcomes of primary Cleft repair is crucial for planning subsequent treatments. However, current surgical assessment methods are subjective and often result in discrepancies among clinicians. Although deep learning solutions have been explored as alternatives for providing objective measurements, the limited availability of Cleft data—primarily due to privacy concerns—raises concerns about their accuracy in real-world applications. Transfer learning with pretrained facial deep learning models, which are typically trained on full-face images, cannot be directly applied to Cleft conditions because clinical Cleft datasets generally consist of cropped facial images focusing on Cleft-prone areas, lacking full facial representations. To address this challenge, we propose a pipeline that generates synthetic full-face images of children from these cropped Cleft prone facial regions. The proposed inpainting model preserves Cleft-prone regions while generating semantically appealing whole face regions with continuity. These synthetic images serve as a valuable resource for analyzing anomalies using pretrained facial deep learning models trained on whole faces, which have demonstrated success in identifying fine and subtle facial details. Additionally, our approach enhances patient privacy and mitigates risks associated with model inversion attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Beyond Correlation: Evaluating Multimedia Quality Models with the Constrained Concordance Index

引用

IEEE Transactions on Multimedia 2025年

作者： Ragano, Alessandro Martinez, Helard Becerra Hines, Andrew University College Dublin Insight Centre for Data Analytics the School of Computer Science Dublin Ireland

This study investigates the evaluation of multimedia quality models, focusing on the inherent uncertainties in subjective Mean Opinion Score (MOS) ratings due to factors like rater inconsistency and bias. Traditional statistical measures such as Pearson's Correlation Coefficient (PCC), Spearman's Rank Correlation Coefficient (SRCC), and Kendall's Tau (KTAU) often fail to account for these uncertainties, leading to inaccuracies in model performance assessment. We introduce the Constrained Concordance Index (CCI), a novel metric designed to overcome the limitations of existing metrics by considering the statistical significance of MOS differences and excluding comparisons where MOS confidence intervals overlap. Through comprehensive experiments across various domains including speech and image quality assessment, we demonstrate that CCI provides a more robust and accurate evaluation of instrumental quality models, especially in scenarios of low sample sizes, rater group variability, and restriction of range. Our findings suggest that incorporating rater subjectivity and focusing on statistically significant pairs can significantly enhance the evaluation framework for multimedia quality prediction models. This work not only sheds light on the overlooked aspects of subjective rating uncertainties but also proposes a methodological advancement for more reliable and accurate quality model evaluation. © 2025 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Scheduling for Shared Manufacturing Systems 6

Multi-agent Scheduling for Shared Manufacturing Systems

引用

6th International Conference on Industry 4.0 and Smart Manufacturing, ISM 2024

作者： Duran, Ege Ozturk, Cemalettin O'Sullivan, Barry SFI Centre for Research Training in AI School of Computer Science IT University College Cork Ireland Department of Process Energy & Transport Engineering Munster Technological University Cork Ireland Insight SFI Research Centre for Data Analytics School of Computer Science & IT University College Cork Ireland

Advances in digitization and resource-sharing business models have created new opportunities for manufacturing companies, enhancing competitiveness and resilience. However, these benefits bring computational challenges in efficiently planning and scheduling shared resources. Therefore, there is a need for scalable and quick solutions for practical applications. Shared manufacturing systems share characteristics with parallel machine scheduling, allowing for the application of advancements from this domain. This research focuses on Multi-Agent Parallel Machine Scheduling (MAPMS) in shared manufacturing, specifically addressing scenarios involving two parallel machines and distinct agents managing exclusive, set of non-overlapping orders. The study introduces a novel multi-objective mixed integer programming (MIP) model for order scheduling across multiple facilities, accounting for sequence-dependent setup times between orders. It also proposes a new heuristic method designed for industrial use. Benchmark instances demonstrate the practicality of both the MIP model and heuristic, contributing valuable insights into MAPMS challenges in shared manufacturing environments. © 2025 The Authors.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Tracking Lesion Evolution Using a Boundary Enhanced Approach for MS Change Segmentation (BEAMS)

Tracking Lesion Evolution Using a Boundary Enhanced Approac...

引用

Workshop on Longitudinal Disease Tracking and Modeling with Medical Images and data, LDTM 2024, 5th International Workshop on Multiscale Multimodal Medical Imaging, MMMI 2024, 1st Workshop on Machine Learning for Multimodal/-sensor Healthcare data, ML4MHD2024 and Workshop on Multimodal Learning and Fusion Across Scales for Clinical Decision Support, ML-CDS 2024 held in conjunction with the 27th International Conference on Medical Image Computing and computer Assisted Intervention, MICCAI 2024

作者： Mathur, Prateek Kelly, Brendan S. Killeen, Ronan P Lawlor, Aonghus School of Computer Science University College Dublin Dublin Ireland School of Medicine University College Dublin Dublin Ireland Insight SFI Research Centre for Data Analytics Dublin Ireland St. Vincent’s University Hospital Dublin Ireland

ISBN: (纸本)9783031845246

Multiple sclerosis (MS) is a chronic disease of the Central Nervous System (CNS) primarily characterised on Magnetic Resonance Imaging (MRI) by hyper-intense lesions. Accurate and timely identification of new lesions or growth in existing lesions has a tremendous impact on treatment planning and patient care. Early detection can lead to prompt intervention possibly slowing the disease progression. However, this task is challenging, costly and often prone to observer bias. Our approach consists of three key components (1) redefining the lesion segmentation problem as a change detection challenge focusing only on new and enhancing lesions;(2) adding an additional boundary detection task to an existing Convolutional Neural Network (CNN) to provide detailed context regarding the shape, size, and evolution of enhancing lesions;(3) evaluating the Fβ loss objective as an alternative to traditional segmentation loss objectives, aiming to optimise the model’s sensitivity and specificity. Furthermore, we employ Gradient-weighted Class Activation Mapping (GradCAM) to visualise the network’s attention, aiding in the interpretation and validation of our approach. By providing an objective evaluation, our method aims to streamline clinical decision-making processes for improved patient outcomes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Intent Identification Using Few-Shot and Active Learning with User Feedback 25th

Intent Identification Using Few-Shot and Active Learning wi...

引用

25th International Conference on Web Information Systems Engineering, WISE 2024

作者： Yuvaraj, Senthil Ganesan Benatallah, Boualem Motahari-Nezhad, Hamid Reza Rabhi, Fethi School of Computer Science and Engineering University of New South Wales Sydney Australia Insight SFI Research Centre on Data Analytics Dublin City University Dublin Ireland UpBrains AI Inc. RestonVA United States Macquarie University Sydney Australia

ISBN: (纸本)9789819605729

Collaboration tools contain many intents in workplace conversation, and identifying these intents is important to increase workplace productivity. However, labelling these intents for a large collection of conversations is expensive and data availability for new intents is quite limited. The pre-trained models show outstanding results in text classification tasks and large language models have recently produced accurate models with few samples. We explored few-shot learning methods and active learning strategies for this problem. Our proposed method, "SetFit with AL" is a combination of Sentence Transformer Fine-tuning (SetFit) and active learning for intent identification. This method fine-tunes a sentence-transformer model to develop accurate models. The intent classification evaluation dataset was used to evaluate this method. The results show that our proposed method outperforms state-of-the-art large language model GPT-3.5 and is comparable to GPT-4. This method also can utilize user feedback to adapt to new data and develop personalized models. Thus, the contribution of this paper is that fine-grained intents are identified using minimal data and the model is adaptable based on user feedback. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

MetaKG: From data Collection to User Interaction

MetaKG: From Data Collection to User Interaction

引用

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Saeed Hamood Alsamhi Ammar Hawbani Mohan Timilsina Edward Curry Insight Centre for Data Analytics University of Galway Galway Ireland School of Computer Science Shenyang Aerospace University Shenyang China

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

The emergence of the Metaverse as a new platform for human interaction could revolutionize several sectors. This paper provides a new “Metaverse Knowledge Graph” (MateKG) framework to enhance user interaction, data management, and knowledge representation in the virtual environment. The building and interacting MetaKGs is proposed to allow for efficient and successful data management, organization, and exploitation. The novel framework comprises several layers: infrastructure, data gathering, Knowledge Graph (KG), user interaction, evaluation and enhancement, and applications. We discuss several approaches, storage options, ontology designs for KG creation, and data-collecting sources. We look at customization strategies, accessibility concerns for the user interaction layer, and user interface design. Furthermore, we showcase case studies and MetaKG applications in e-commerce, smart cities, healthcare, and entertainment. We provide a starting point for creating reliable and efficient MetaKGs that serve a range of applications and domains.

关键词： Metaverse Smart cities Soft sensors Buildings Entertainment industry Knowledge graphs Medical services data collection Electronic commerce Reliability

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Scheduling for Shared Manufacturing Systems

引用

Procedia computer science 2025年 253卷 727-736页

作者： Ege Duran Cemalettin Ozturk Barry O’Sullivan SFI Centre for Research Training in AI School of Computer Science & IT University College Cork Ireland Department of Process Energy & Transport Engineering Munster Technological University Cork Ireland Insight SFI Research Centre for Data Analytics School of Computer Science & IT University College Cork Ireland

关键词： Multiagent systems Scheduling planning parallel 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：