检索结果-内蒙古大学图书馆

Development of an Enhanced Quality Score Calculation Method for Accurate Assessment of Hotel Quality

学校读者我要写书评

暂无评论

Development of an Enhanced Quality Score Calculation Method ...

Advancements in computing (ICAC), International Conference on

作者： A. A. A. Gaweshini Athurugiriya Prasanna Sumathipala K.M. Tharindu Anupa Hemachandra Department of Data Science Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

In this research paper, an enhanced hotel quality scoring method (EHQSM), is presented as a revolutionary way to analyze hotel quality. The EHQSM combines sentiment analysis, HOLSERV Plus dimensions classification, and amenity scores to deliver a more thorough review. The study generates an overall sentiment score by doing sentiment analysis on reviews categorized into HOLSERV Plus dimensions then thoughtfully averaging it using dimensionspecific weights collected from a survey. The availability of necessary amenities is considered when calculating the amenity score. The novel feature of this approach is how the amenity score, and sentiment score are carefully combined and efficiently weighted using values from the survey. The result is an improved quality score that accurately and thoroughly describes the quality of hotel services. With the goal of facilitating informed decisions for both hotel owners and attentive tourists, this technique establishes an updated standard for the evaluation of hospitality quality.

关键词：

Mining Conditional Part Semantics with Occluded Extrapolation for Human-Object Interaction Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Guangzhi Guo, Yangyang Kankanhalli, Mohan Institute of Data Science National University of Singapore Singapore School of Computing National University of Singapore Singapore

Human-Object Interaction Detection is a crucial aspect of human-centric scene understanding, with important applications in various domains. Despite recent progress in this field, recognizing subtle and detailed interactions remains challenging. Existing methods try to use human-related clues to alleviate the difficulty, but rely heavily on external annotations or knowledge, limiting their practical applicability in real-world scenarios. In this work, we propose a novel Part Semantic Network (PSN) to solve this problem. The core of PSN is a Conditional Part Attention (CPA) mechanism, where human features are taken as keys and values, and the object feature is used as query for the computation in a cross-attention mechanism. In this way, our model learns to automatically focus on the most informative human parts conditioned on the involved object, generating more semantically meaningful features for interaction recognition. Additionally, we propose an Occluded Part Extrapolation (OPE) strategy to facilitate interaction recognition under occluded scenarios, which teaches the model to extrapolate detailed features from partially occluded ones. Our method consistently outperforms prior approaches on the V-COCO and HICO-DET datasets, without external data or extra annotations. Additional ablation studies validate the effectiveness of each component of our proposed method. © 2023, CC BY.

关键词： Extrapolation

Leveraging Old Knowledge to Continually Learn New Classes in Medical Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chee, Evelyn Lee, Mong Li Hsu, Wynne School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned. This is especially needed in the medical domain where continually learning from new incoming data is required to classify an expanded set of diseases. In this work, we focus on how old knowledge can be leveraged to learn new classes without catastrophic forgetting. We propose a framework that comprises of two main components: (1) a dynamic architecture with expanding representations to preserve previously learned features and accommodate new features;and (2) a training procedure alternating between two objectives to balance the learning of new features while maintaining the model’s performance on old classes. Experiment results on multiple medical datasets show that our solution is able to achieve superior performance over state-of-the-art baselines in terms of class accuracy and forgetting. Copyright © 2023, The Authors. All rights reserved.

关键词： Knowledge management

Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Deng, Ailin Xiong, Miao Hooi, Bryan School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Reliable application of machine learning is of primary importance to the practical deployment of deep learning methods. A fundamental challenge is that models are often unreliable due to overconfidence (Hendrycks & Gimpel, 2017). In this paper, we estimate a model's reliability by measuring the agreement between its latent space, and the latent space of a foundation model. However, it is challenging to measure the agreement between two different latent spaces due to their incoherence, e.g., arbitrary rotations and different dimensionality. To overcome this incoherence issue, we design a neighborhood agreement measure between latent spaces and find that this agreement is surprisingly well-correlated with the reliability of a model's predictions. Further, we show that fusing neighborhood agreement into a model's predictive confidence in a post-hoc way significantly improves its reliability. Theoretical analysis and extensive experiments on failure detection across various datasets verify the effectiveness of our method on both in-distribution and out-of-distribution settings. Copyright © 2023, The Authors. All rights reserved.

关键词： Reliability

Prism: Privacy-Preserving Inter-Site MRI Harmonization via Disentangled Representation Learning

学校读者我要写书评

暂无评论

Prism: Privacy-Preserving Inter-Site MRI Harmonization via D...

IEEE International Symposium on Biomedical Imaging

作者： Sarang Galada Tanurima Halder Kunal Deo Ram P. Krish Kshitij Jadhav Trust Lab Indian Institute of Technology Bombay School of Computing and Data Science Sai University Chennai Koita Centre for Digital Health Indian Institute of Technology Bombay

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multi-site MRI studies often suffer from site-specific variations arising from differences in methodology, hardware, and acquisition protocols, thereby compromising accuracy and reliability in clinical AI/ML tasks. We present PRISM (Privacy-preserving Inter-Site MRI Harmonization), a novel Deep Learning framework for harmonizing structural brain MRI across multiple sites while preserving data privacy. PRISM employs a dual-branch autoencoder with contrastive learning and variational inference to disentangle anatomical features from style and site-specific variations, enabling unpaired image translation without traveling subjects or multiple MRI modalities. Our modular design allows harmonization to any target site and seamless integration of new sites without the need for retraining or fine-tuning. Using multi-site structural MRI data, we demonstrate PRISM's effectiveness in downstream tasks such as brain tissue segmentation and validate its harmonization performance through multiple experiments. Our framework addresses key challenges in medical AI/ML, including data privacy, distribution shifts, model generalizability and interpretability. Code is available at https://***/saranggalada/PRISM

关键词： data privacy Privacy Image segmentation Translation Protocols Magnetic resonance imaging Autoencoders Contrastive learning Reliability Biomedical imaging

Internal Activation as the Polar Star for Steering Unsafe LLM Behavior

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Han, Peixuan Qian, Cheng Chen, Xiusi Zhang, Yuji Zhang, Denghui Ji, Heng Siebel School of Computing and Data Science University of Illinois Urbana-Champaign United States School of Business Stevens Institute of Technology United States

Large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks but also pose significant risks due to their potential to generate harmful content. Although existing safety mechanisms can improve model safety, they often lead to overly cautious behavior and fail to fully utilize LLMs’ internal cognitive processes. Drawing inspiration from cognitive science, where humans rely on reflective reasoning (System 2 thinking) to regulate language and behavior, we empirically demonstrate that LLMs also possess a similar capacity for internal assessment and regulation, which can be actively detected. Building on this insight, we introduce SafeSwitch, a framework that dynamically regulates unsafe outputs by monitoring and utilizing the model’s internal states. Our empirical results show that SafeSwitch reduces harmful outputs by over 80% on safety benchmarks while maintaining strong utility. Compared to traditional safety alignment methods, SafeSwitch delivers more informative and context-aware refusals, demonstrates resilience to unseen queries, and achieves these benefits while only tuning less than 6% of the original parameters. These features make SafeSwitch a promising approach for implementing nuanced safety controls in *** for this work are available at https://***/Hanpx20/SafeSwitch. © 2025, CC BY.

关键词： Safety engineering

GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Yuwen Xiong, Miao Hooi, Bryan School of Computing National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Label errors have been found to be prevalent in popular text, vision, and audio datasets, which heavily influence the safe development and evaluation of machine learning algorithms. Despite increasing efforts towards improving the quality of generic data types, such as images and texts, the problem of mislabel detection in graph data remains underexplored. To bridge the gap, we explore mislabelling issues in popular real-world graph datasets and propose GRAPHCLEANER, a post-hoc method to detect and correct these mislabelled nodes in graph datasets. GRAPHCLEANER combines the novel ideas of 1) Synthetic Mislabel dataset Generation, which seeks to generate realistic mislabels;and 2) Neighborhood-Aware Mislabel Detection, where neighborhood dependency is exploited in both labels and base classifier predictions. Empirical evaluations on 6 datasets and 6 experimental settings demonstrate that GRAPHCLEANER outperforms the closest baseline, with an average improvement of 0.14 in F1 score, and 0.16 in MCC. On real-data case studies, GRAPHCLEANER detects real and previously unknown mislabels in popular graph benchmarks: PubMed, Cora, CiteSeer and OGB-arxiv;we find that at least 6.91% of PubMed data is mislabelled or ambiguous, and simply removing these mislabelled data can boost evaluation performance from 86.71% to 89.11%1 © 2023, CC BY.

关键词： Benchmarking

Enhancing Hotel Customer Satisfaction Assessment with Semantic Search-based Scoring

学校读者我要写书评

暂无评论

Enhancing Hotel Customer Satisfaction Assessment with Semant...

Advancements in computing (ICAC), International Conference on

作者： K.M Tharindu Anupa Hemachandra Prasanna Sumathipala A.A.A Gaweshini Athurugiriya Department of Data Science Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

Within the hospitality sector, ensuring customer satisfaction takes precedence, particularly in economies such as Sri Lanka, where tourism serves as a vital growth catalyst. Interestingly, disparities often arise between customer ratings and their written evaluations. This study presents an innovative strategy that utilizes semantic search techniques to extract comprehensive insights from customer feedback, leading to the development of a robust hotel scoring system. By exploring intricate emotions via advanced linguistic analysis, this method reveals underlying cues that conventional metrics often overlook. The method's effectiveness is validated through a comparative study with established hotel ratings. This advancement not only refines precise customer satisfaction assessment for hotels but also bears strategic significance for countries aiming to fortify their tourism sectors. In this era centered around data, this research provides a pivotal standpoint for optimizing hospitality evaluation, thereby enriching guest experiences, and guiding well-informed operational choices.

关键词：

Visual Named Entity Linking: A New dataset and A Baseline

学校读者我要写书评

暂无评论

Visual Named Entity Linking: A New Dataset and A Baseline

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Sun, Wenxiang Fan, Yixing Guo, Jiafeng Zhang, Ruqing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

Visual Entity Linking (VEL) is a task to link regions of images with their corresponding entities in Knowledge Bases (KBs), which is beneficial for many computer vision tasks such as image retrieval, image caption, and visual question answering. While existing tasks in VEL either rely on textual data to complement a multi-modal linking or only link objects with general entities, which fails to perform named entity linking on large amounts of image data. In this paper, we consider a purely Visual-based Named Entity Linking (VNEL) task, where the input only consists of an image. The task is to identify objects of interest (i.e., visual entity mentions) in images and link them to corresponding named entities in KBs. Since each entity often contains rich visual and textual information in KBs, we thus propose three different sub-tasks, i.e., visual to visual entity linking (V2VEL), visual to textual entity linking (V2TEL), and visual to visual-textual entity linking (V2VTEL). In addition, we present a high-quality human-annotated visual person linking dataset, named WIKIPerson. Based on WIKIPerson, we establish a series of baseline algorithms for the solution of each sub-task, and conduct experiments to verify the quality of the proposed datasets and the effectiveness of baseline methods. We envision this work to be helpful for soliciting more works regarding VNEL in the future. The codes and datasets are publicly available at https://***/ict-bigdatalab/VNEL. © 2022 Association for Computational Linguistics.

关键词： Image retrieval