检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wagner, Eitan Slavutsky, Yuli Abend, Omri School of Computer Science and Engineering Department of Statistics and Data Science Hebrew University of Jerusalem Israel

ISBN: (纸本)9798891761643

Although language model scores are often treated as probabilities, their reliability as probability estimators has mainly been studied through calibration, overlooking other aspects. In particular, it is unclear whether language models produce the same value for different ways of assigning joint probabilities to word spans. Our work introduces a novel framework, ConTestS (Consistency Testing over Spans), involving statistical tests to assess score consistency across interchangeable completion and conditioning orders. We conduct experiments on post-release real and synthetic data to eliminate training effects. Our findings reveal that both Masked Language Models (MLMs) and autoregressive models exhibit inconsistent predictions, with autoregressive models showing larger discrepancies. Larger MLMs tend to produce more consistent predictions, while autoregressive models show the opposite trend. Moreover, for both model types, prediction entropies offer insights into the true word span likelihood and therefore can aid in selecting optimal decoding strategies. The inconsistencies revealed by our analysis, as well their connection to prediction entropies and differences between model types, can serve as useful guides for future research on addressing these limitations. © 2024 Association for Computational Linguistics.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Unsupervised machine learning approach for tailoring educational content to individual student weaknesses

引用

High-Confidence Computing 2024年第4期4卷 91-104页

作者： Shabab Intishar Rahman Shadman Ahmed Tasnim Akter Fariha Ammar Mohammad Muhammad Nayeem Mubasshirul Haque Sriram Chellappan Jannatun Noor Department of Computer Science and Engineering BRAC UniversityDhaka 1212Bangladesh Department of Computer Science and Engineering University of South FloridaFL 33620USA Computing for Sustainability and Social Good(C2SG)Research Group Department of Computer Science and EngineeringSchool of Data and SciencesBRAC UniversityDhaka 1212Bangladesh

By analyzing data gathered through Online Learning(OL)systems,data mining can be used to unearth hidden relationships between topics and trends in student ***,in this paper,we show how data mining techniques such as clustering and association rule algorithms can be used on historical data to develop a unique recommendation system *** our implementation,we utilize historical data to generate association rules specifically for student test marks below a threshold of 60%.By focusing on marks below this threshold,we aim to identify and establish associations based on the patterns of weakness observed in the past ***,we leverage K-means clustering to provide instructors with visual representations of the generated *** strategy aids instructors in better comprehending the information and associations produced by the *** clustering helps visualize and organize the data in a way that makes it easier for instructors to analyze and gain insights,enabling them to support the verification of the relationship between *** can be a useful tool to deliver better feedback to students as well as provide better insights to instructors when developing their *** paper further shows a prototype implementation of the above-mentioned concepts to gain opinions and insights about the usability and viability of the proposed system.

关键词： Recommendation system Clustering F-P growth Apriori Associative pattern E-learning sphere Online learning

来源：评论

学校读者我要写书评

暂无评论

Part-Whole Relational Few-Shot 3D Point Cloud Semantic Segmentation

引用

computers, Materials & Continua 2024年第3期78卷 3021-3039页

作者： Shoukun Xu Lujun Zhang Guangqi Jiang Yining Hua Yi Liu School of Computer Science and Artificial Intelligence Aliyun School of Big Data and School of SoftwareChangzhou UniversityChangzhou213164China Department of Computer Science University of AberdeenKing’s CollegeAberdeenAB243FXUK

This paper focuses on the task of few-shot 3D point cloud semantic *** some progress,this task still encounters many issues due to the insufficient samples given,e.g.,incomplete object segmentation and inaccurate semantic *** tackle these issues,we first leverage part-whole relationships into the task of 3D point cloud semantic segmentation to capture semantic integrity,which is empowered by the dynamic capsule routing with the module of 3D Capsule Networks(CapsNets)in the embedding ***,the dynamic routing amalgamates geometric information of the 3D point cloud data to construct higher-level feature representations,which capture the relationships between object parts and their ***,we designed a multi-prototype enhancement module to enhance the prototype ***,the single-prototype enhancement mechanism is expanded to the multi-prototype enhancement version for capturing rich ***,the shot-correlation within the category is calculated via the interaction of different samples to enhance the intra-category *** studies prove that the involved part-whole relations and proposed multi-prototype enhancement module help to achieve complete object segmentation and improve semantic ***,under the integration of these two modules,quantitative and qualitative experiments on two public benchmarks,including S3DIS and ScanNet,indicate the superior performance of the proposed framework on the task of 3D point cloud semantic segmentation,compared to some state-of-the-art methods.

关键词： Few-shot point cloud semantic segmentation CapsNets

来源：评论

学校读者我要写书评

暂无评论

Sparse representation scheme with enhanced medium pixel intensity for face recognition

引用

CAAI Transactions on Intelligence Technology 2024年第1期9卷 116-127页

作者： Xuexue Zhang Yongjun Zhang Zewei Wang Wei Long Weihao Gao Bob Zhang State Key Laboratory of Public Big Data Institute for Artificial IntelligenceCollege of Computer Science and TechnologyGuizhou UniversityGuiyangGuizhouChina Department of Computer and Information Science University of MacaoAvenida da UniversidadeTaipaMacaoChina

Sparse representation is an effective data classification algorithm that depends on the known training samples to categorise the test *** has been widely used in various image classification *** in sparse representation means that only a few of instances selected from all training samples can effectively convey the essential class-specific information of the test sample,which is very important for *** deformable images such as human faces,pixels at the same location of different images of the same subject usually have different ***,extracting features and correctly classifying such deformable objects is very ***,the lighting,attitude and occlusion cause more *** the problems and challenges listed above,a novel image representation and classification algorithm is ***,the authors’algorithm generates virtual samples by a non-linear variation *** method can effectively extract the low-frequency information of space-domain features of the original image,which is very useful for representing deformable *** combination of the original and virtual samples is more beneficial to improve the clas-sification performance and robustness of the ***,the authors’algorithm calculates the expression coefficients of the original and virtual samples separately using the sparse representation principle and obtains the final score by a designed efficient score fusion *** weighting coefficients in the score fusion scheme are set entirely ***,the algorithm classifies the samples based on the final *** experimental results show that our method performs better classification than conventional sparse representation algorithms.

关键词： computer vision face recognition image classification image representation

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based method for detection of copy-move forgery in videos

引用

Neural Computing and Applications 2025年第14期37卷 8451-8464页

作者： Elbarougy, Reda Abdelfatah, Osama Behery, G.M. El-Badry, Noha M. Department of Artificial Intelligence and Data Science College of Computer Science and Engineering University of Ha’il Ha’il81481 Saudi Arabia Department of Information Technology Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Computer Science Faculty of Computer and Artificial Intelligence Damietta University New Damietta Kafr Saad Egypt Department of Mathematics Faculty of Science Damietta University New Damietta Kafr Saad Egypt

Video forgery is one of the most serious problems affecting the credibility and reliability of video content. Therefore, detecting video forgery presents a major challenge for researchers due to the diversity of forgery types, the modernity of the programs used in forgery operations, and the abundance of information and content present in videos. The seriousness of this issue arises from the widespread use of videos in vital fields that require very high accuracy with no room for doubt or error, such as courtrooms, journalism, and others. Copy-move forgery is one of the most common and dangerous types of video forgery because of the difficulty in identifying it with the naked eye and the great diversity of forgery techniques involved in this particular type. One of the biggest challenges researchers have faced in the past is the complexity of the steps required to detect forgery in videos, leading to significant computational complexity and time consumption. The proposed method also aims to achieve better results than previous methods while reducing computational operations. Ultimately, forgery is detected with great efficiency. Compared to previous methods used for detecting copy-move forgery in the Rewind dataset, the proposed method achieves the highest F1, reaching 0.86, with a significant difference of 0.13 compared to the best result of the previous methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A novel framework integrating ensemble transfer learning and Ant Colony Optimization for Knee Osteoarthritis severity classification

引用

Multimedia Tools and Applications 2024年第39期83卷 86923-86954页

作者： Malik, Isra Yasmin, Mussarat Iqbal, Ahmed Raza, Mudassar Chun, Chang-Jae Al-antari, Mugahed A. Department of Computer Science COMSATS University Islamabad Wah Campus Wah Cantt44000 Pakistan Department of Computer Science Sir Syed Case Institute of Technology Islamabad45230 Pakistan Department of Computer Science HITEC University Taxila Taxila47080 Pakistan Department of Artificial Intelligence and Data Science College of AI Convergence Daeyang AI Center Sejong University Seoul05006 Korea Republic of

Knee Osteoarthritis (KOA), the most prevalent joint disease, significantly impacts elderly mobility due to progressive cartilage degeneration. Early prediction is crucial for preventing disease progression and guiding effective treatment plans. This paper proposes an EnsembleTL-ACO, fully automated, computer-aided diagnosis (CAD) system for accurate and rapid KOA severity grading. The proposed CAD system leverages an ensemble transfer learning strategy to extract robust deep features by fusing multiple deep learning models. It combines features from two consecutive AI models: (1) AlexNet for implicit class-wise deep feature extraction from preprocessed data, and (2) a custom IsrNet for further feature depth. Unsupervised k-means clustering based on PCA dimensionality reduction decomposes each class into subgroups, further refining features. Finally, Ant Colony Optimization (ACO) selects the most informative features. Evaluated on the Osteoarthritis Initiative (OAI) dataset, the proposed system achieves high accuracy in classifying the five KOA severity grades. With 1000 optimized features, it reaches average overall accuracies of 89.89% and 85.44% using Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers, respectively. This surpasses recent deep learning methods, demonstrating significant improvement. This novel CAD system presents a promising solution for practical applications, offering an accurate AI-powered tool for KOA diagnosis and management. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

An artificial intelligence framework for explainable drift detection in energy forecasting

引用

Energy and AI 2024年第3期17卷 368-379页

作者： Chamod Samarajeewa Daswin De Silva Milos Manic Nishan Mills Harsha Moraliyage Damminda Alahakoon Andrew Jennings Centre for Data Analytics and Cognition La Trobe UniversityAustralia Department of Computer Science Virginia Commonwealth UniversityRichmondUSA

Accurate energy consumption forecasting is crucial for reducing operational costs, achieving net-zero carbon emissions, and ensuring sustainable buildings and cities of the future. Despite the frequent use of Artificial Intelligence (AI) algorithms for learning energy consumption patterns and predictions in Building science, relying solely on these techniques for energy demand prediction addresses only a fraction of the challenge. A drift in energy usage can lead to inaccuracies in these AI models and subsequently to poor decision-making and interventions. While drift detection techniques have been reported, a reliable and robust approach capable of explaining identified discrepancies with actionable insights has not been discussed in extant literature. Hence, this paper presents an Artificial Intelligence framework for energy consumption forecasting with explainable drift detection, aimed at addressing these challenges. The proposed framework is composed of energy embeddings, an optimized dimensional model integrated within a data warehouse, and scalable cloud implementation for effective drift detection with explainability capability. The framework is empirically evaluated in the real-world setting of a multi-campus, mixed-use tertiary education setting in Victoria, Australia. The results of these experiments highlight its capabilities in detecting concept drift, adapting forecast predictions, and providing an interpretation of the changes using energy embeddings.

关键词： Building energy consumption forecasting Explainable drift detection Energy embedding Dimensional modeling

来源：评论

学校读者我要写书评

暂无评论

Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis 38

Point-PRC: A Prompt Learning Based Regulation Framework for ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Sun, Hongyu Ke, Qiuhong Wang, Yongcai Chen, Wang Yang, Kang Li, Deying Cai, Jianfei Department of Computer Science Renmin University of China China Department of Data Science & AI Monash University Australia

This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt tuning. However, we observe that the improvement on downstream tasks comes at the expense of a severe drop in 3D domain generalization. To resolve this challenge, we present a comprehensive regulation framework that allows the learnable prompts to actively interact with the well-learned general knowledge in large 3D models to maintain good generalization. Specifically, the proposed framework imposes multiple explicit constraints on the prompt learning trajectory by maximizing the mutual agreement between task-specific predictions and task-agnostic knowledge. We design the regulation framework as a plug-and-play module to embed into existing representative large 3D models. Surprisingly, our method not only realizes consistently increasing generalization ability but also enhances task-specific 3D recognition performances across various 3DDG benchmarks by a clear margin. Considering the lack of study and evaluation on 3DDG, we also create three new benchmarks, namely base-to-new, cross-dataset and few-shot generalization benchmarks, to enrich the field and inspire future research. Code and benchmarks are available at https://***/auniquesun/Point-PRC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tensor-based forward-backward algorithms in the physics-informed coupled hidden markov model

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1052-1066页

作者： Zhang, Shunli Yang, Laurence T. Zhang, Yue Lu, Zhixing Cui, Zongmin School of Computer and Big Data Science Jiujiang University Jiujiang332005 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Hainan University Haikou570228 China Department of Computer Science St. Francis Xavier University AntigonishNSB2G2W5 Canada

Imposing data-driven with physical laws for user activity prediction could effectively solve various physical problems such as smart care, surveillance, and human-robot. In the growing field of artificial intelligence, the application of activity prediction based on the physical coupled hidden Markov model (CHMM) and tensor theory with physical properties has attracted increasing attentions. However, existing CHMMs usually only consider the time-series characteristic of data, while ignoring physical characteristics of user activity such as periodicity, timing, and correlation. Moreover, they are all matrix-based models, which could not holistically analyze the dependencies among physical states. The aforementioned disadvantages lead to lower prediction accuracy of the CHMM. To remove these disadvantages, three physics-informed tensor-based CHMMs are first constructed by incorporating prior physical knowledge. Then, the corresponding forward-backward algorithms are designed for resolving the evaluation problem of the CHMM. These algorithms could overall model multiple physical features by imposing physics and prior knowledge into the CHMM during training to improve the precision of probabilistic computing. The algorithms reduce the dependence of the model on training data by adding physical features. Finally, the comparative experiments show that our algorithms have better performances than existing prediction methods in precision and efficiency. In addition, further self-comparison experiments verify that our algorithms are effective and practical. Impact Statement-Through the analysis of users' behavior habits, consumption habits, preferences, etc., users? potential needs may be discovered. This discovery could help predict users' activities. If a waiter predicts the user's next activity. He gives her/him unexpected services to meet users' next needs. Obviously, it would significantly improve user satisfaction. In addition, connecting the front and rear products co

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Support for the Prompt Identification and Understanding of the Broader Spectrum of Autism in Children 5

Artificial Intelligence Support for the Prompt Identificatio...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Julaiha, A.G. Noorul Hemamalini, S. Preiya, V. Sathya Sathyamoorthy, K. Priyanka, V. Rajalakshmi Institute of Technology Centre for Data Science Department of Computer Science & Engineering Chennai India Panimalar Engineering College Department of Artificial Intelligence & Data Science Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518097

This research work presents a novel language intervention system for Tamil-speaking children with autism spectrum disorder (ASD). The system satisfies the considerable requirement for tools aimed at one more section of population that has actually been forgotten by mainstream economics. Traditional language learning applications often lack specificity for diverse linguistic contexts, focusing on general learning rather than the unique challenges faced by ASD children. The proposed solution leverages Deep Learning (DL) modules to transform partial spoken Tamil words into complete, child-friendly vocabulary. This system goes beyond simple word completion;it incorporates interactive features to engage children with ASD and promote active learning. Preliminary evaluations yielded promising results, suggesting the system's potential in enhancing communication skills among Tamil-speaking children with ASD. This paper research study reviews the limitations of existing language learning tools and the rationale behind employing a DL-based approach. We discuss the specific DL architecture (e.g., Recurrent Neural Networks) envisioned for the system and how it will be trained on a corpus of Tamil speech data. This study also investigate the potential advantages beyond vocabulary learning, such as improved sentence formulation and the development of practical language abilities. Future ambitions include broadening the system's scope to include more languages, refining the DL model through ongoing training with enriched datasets, and conducting extensive user research with varied ASD populations. Validation across demographics is critical to ensuring the system's efficiency and generality. This research has the potential to bridge the language acquisition gap for Tamil-speaking children with ASD, empowering them to develop crucial communication skills and fostering their social inclusion. © 2024 IEEE.

关键词： Recurrent neural networks

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：