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： Shiri, Fatemeh Guo, Xiao-Yu Far, Mona Golestan Yu, Xin Haffari, Gholamreza Li, Yuan-Fang Department of Data Science & AI Monash University Australia Australian Institute for Machine Learning University of Adelaide Australia School of Electrical Engineering and Computer Science University of Queensland Australia

ISBN: (纸本)9798891761643

Large Multimodal Models (LMMs) have achieved strong performance across a range of vision and language tasks. However, their spatial reasoning capabilities are under-investigated. In this paper, we construct a novel VQA dataset, Spatial-MM, to comprehensively study LMMs' spatial understanding and reasoning capabilities. Our analyses on object-relationship and multi-hop reasoning reveal several important findings. Firstly, bounding boxes and scene graphs, even synthetic ones, can significantly enhance LMMs' spatial reasoning. Secondly, LMMs struggle more with questions posed from the human perspective than the camera perspective about the image. Thirdly, chain of thought (CoT) prompting does not improve model performance on complex multi-hop questions involving spatial relations. Lastly, our perturbation analysis on GQA-spatial reveals that LMMs are much stronger at basic object detection than complex spatial reasoning. We believe our new benchmark dataset and in-depth analyses can spark further research on LMMs spatial reasoning. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Product Quality Evaluation using Hybrid LSTM-FCNN Model and GWO Algorithm for Social Media Sentiment Analysis 8

An Enhanced Product Quality Evaluation using Hybrid LSTM-FCN...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Raj Kumar, V.S. Kumaresan, T. Kanna, P. Rajesh Jagadeesan, S. Showmiya, P. Nithin, P. Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India Bannari Amman Institute of Technology Department of Computer Science and Engineering Erode India Nandha Engineering College Department of Computer Science and Engineering Erode India Nehru Institute of Technology Department of Computer Science - Cyber Security Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Erode India

ISBN: (纸本)9798350367904

Sentiment analysis is still in its developing era, and sometimes, struggles are faced in evaluating user sentiment due to the use of traditional models to analyze the relationship structures in social media interactions. To tackle the issue, we proposed an innovative approach Hybrid LSTM neural network and a fully connected neural network (FCNN) integrated with the Grey Wolf Optimization (GWO) algorithm. The objective of this proposed method is to improve sentiment analysis by employing the LSTM to capture the sequence of data and improve the ability of FCNNs to improve feature extraction and the analysis process. The proposed system process initiated with the data preprocessing of input Twitter sentiment dataset transformed into a suitable input to the Hybrid LSTM-FCNN neural network. Then, temporal dependency of the data captured by LSTM and FCNN is used to extract the features. The GWO method mimics the grey wolf hunting behaviour, for optimizing the proposed Hybrid LSTM-FCNN model's parameters to enhance the classification accuracy. The system models start with the initialization of the model, parameters, and training the models using the dataset to reduce the cross-entropy loss, estimating the testing dataset from unseen data and fine-tuning using GWO as necessary. Results demonstrate significant improvements in sentiment categorization compared to traditional methods. The Hybrid LSTM-FCNN model, enhanced with GWO, effectively captures nuanced sentiment patterns, leading to more accurate classification. Additionally, GWO's computational efficiency contributes to scalability. In conclusion, our proposed approach offers a promising solution for enhancing product quality evaluation through advanced neural network architectures and optimization algorithms applied to social media sentiment analysis. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Bio-inspired visual neural network for stop-and-go wave perception in high-density crowd 4

Bio-inspired visual neural network for stop-and-go wave perc...

引用

4th International Conference on computer Vision, Application, and Algorithm, CVAA 2024

作者： Jiang, Wei Hu, Bin State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China Department of Computer Science College of Computer Science & Technology Guizhou University Guiyang550025 China Artificial Intelligence Research Institute of Guizhou University Guizhou University Guiyang550025 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

In high-density crowd, a unique visual motion effect called stop-and-go wave occurs, which could evolve to trampling and compression incidents. However, few computational models have been reported for stop-and-go wave perception form the angle of computer vision. On the bases of the neural structures of the locusts’ vision systems and the frequency resonance properties of the interneuronal (INs) neurons in locust’s brains, this paper investigates a bio-inspired visual neural network (sgWPNN) for stop-and-go wave perception in high-density crowd scenes. The proposed sgWPNN firstly visually stabilizes the image frames;and then converts the spatial intensity visual information to the frequency domain for extracting crowd’s motion cues;finally, sgWPNN output membrane potential impulses to identify the occurring of stop-and-go wave in the field of view. Videos filmed high-density crowd activities in two scenarios demonstrate the effectiveness of sgWPNN in the perception against to the unique stop-and-go wave effect in moving crowd scenes. This work discusses the biological inspired processing of dynamic visual information in crowd activity perception, which can provide some new ideas for crowd activity detection and behavior analysis. © 2025 SPIE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Personality Prediction Using Machine Learning 1

Personality Prediction Using Machine Learning

引用

1st International Conference on Computational Intelligence for Information, Security and Communication Applications, CIISCA 2023

作者： Pooja, K. Rakshitha, G.H. Spoorthi, S. Kamal, Shoaib Rao, Trupthi Ashwini, K. Global Academy of Technology Department of Computer Science and Engineering Bangalore India Global Academy of Technology Department of Artificial Intelligence and Data Science Bangalore India

ISBN: (纸本)9798350339727

With the growth of social networks, a wide range of methodologies have been developed to describe users' personalities only based on their language and social media use habits. Persona prediction is very popular these days. It examines consumer behaviour and records the user's ideas, emotions, and so on. There has been a sufficient amount of research in this field over the years. This survey provides an overview of the numerous methods tried to predict personality and behaviour from the use of the social media content. The capacity to anticipate the personality attributes of users can help create a variety of specialised goods or services. The concluding phase then provides the future characteristics and directives. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Reliable Entropy-Induced Anchor Learning for Incomplete Multi-View Subspace Clustering

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5293-5306页

作者： Shen, Qiangqiang Guo, Zihou Wang, Hanzhang Xu, Yanhui Chen, Yongyong Wang, Shiqi Liang, Yongsheng City University of Hong Kong Department of Computer Science Hong Kong Harbin Institute of Technology School of Science Shenzhen518055 China Nanjing University of Posts and Telecommunications College of Electronic and Optical Engineering Nanjing210023 China School of Computer Science and Technology Shenzhen518055 China School of Electronics and Information Engineering Shenzhen518055 China Shenzhen Technology University College of Big Data and Internet Shenzhen518118 China

Under large-scale data with missing views, fast incomplete multi-view clustering (IMVC) with anchor learning is of critical importance due to its linear complexity O(n). However, existing anchor-based methods only explore the column orthogonality of anchor points, where their arbitrary column orthogonal basis vectors have weak constraint relationships with real samples and significant deviations from more representative anchors, thereby impeding the precise representation of sample similarities. To solve this issue, we propose a Reliable Entropy-induced anchor learning for incomplete Multi-view subspace Clustering (REMC), which performs an entropy approximation term to learn more representative anchors, and we prove that the information entropy minimization can be relaxed into the 2,1-norm paradigm. Specifically, the proposed REMC first integrates anchor learning and subspace clustering to produce multiple view-specific bipartite graphs and capture the high-order correlations by imposing these bipartite graphs with the tensor nuclear norm. Then, we fuse all the view-specific bipartite graphs to build a consensus bipartite graph with entropy approximation regularization, and hence the proposed REMC can produce a more discriminative similarity graph, preserving each non-zero element in its column close to 1, while the other elements are approaching 0. Besides, an efficient algorithm is designed to solve the proposed REMC. Numerous results show the superior performance of our method on both the complete and incomplete data. © 1991-2012 IEEE.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Intelligent Predictive Model for Hepatitis C 3

Intelligent Predictive Model for Hepatitis C

引用

3rd IEEE International Conference on Artificial Intelligence, ICAI 2023

作者： Shahzadi, Mehreen Bukhari, Faisal Shafi, Numan University of the Punjab Faculty of Computing & Information Technology Department of Data Science Lahore Pakistan University of Engineering and Technology Department of Computer Science Lahore Pakistan

ISBN: (纸本)9798350322125

Hepatitis C is the liver's festering that can lead to severe liver damage, usually caused by the hepatitis C virus. Hepatitis C has different stages. It is tough to cure in it's last stages;at the same time, it is expensive and painful process. The current research, however, is an alternative precaution to this issue. Hepatitis C can be predicted early by using multiple factors. The dataset related to hepatitis C was not publicly available. To overcome this challenge, the healthy and HCV effected samples were collected from different hospitals in Punjab. A questionnaire based survey was taken including different HCV related factor i.e. gender, weight loss, hives/ rashes, swelling, jaundice, drug addiction history, hepatic encephalopa-thy (drowsiness, slurred speech), Ascites (fluid buildup in belly/ abdomen), spider angiomas (Spiderlike blood vessels), shared syringe usage, medical history, and severeness. Different cleaning, scaling, and feature selection techniques were applied to collect the best feature data. After selection, various machine learning algorithms were applied. Random forest, KNN, Decision Tree, SVC, and MLP were used, but MLP yielded optimal results in all classification algorithms. We have gained 95.9 % accuracy when tested on unknown data based on the MLP model. As the predictions' results were satisfactory, it would be helpful for the people and act as a critical awareness. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence based machine learning algorithm for prediction of cancer in female anatomy

引用

Multimedia Tools and Applications 2025年第16期84卷 15735-15761页

作者： Ghantasala, G S Pradeep Hung, Bui Thanh Chakrabarti, Prasun R, Sathiyaraj Pellakuri, Vidyullatha Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Karnataka Bangalore India Data Science Laboratory Faculty of Information Technology Industrial University of Ho Chi Minh city Ho Chi Minh City Viet Nam Deputy Provost ITM SLS Baroda University Gujarat Vadodara India Department of CSE GITAM School of Technology GITAM University Bengaluru India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur India

Breast and cervical cancers account for more than 85 percent of all cancer-related fatalities in developing nations, according to the World Cancer Research Fund. As a result, breast and cervical cancer have become one of the leading causes of mortality among women worldwide. This field is still in its infancy, with only a few studies in gynaecology and computer science looking into the detection of breast and cervical cancer. According to the researchers, medical records and early testing from individuals with breast and cervical cancer will be used in this study to determine the prognosis of those suffering from the diseases. To assess our cervical cancer predictions, we employed machine learning models such as Optimized Hybrid Ensemble Classifier (OHEC), which were trained on patient behavior and variables revealed to be associated with patient behavior. The datasets in this study have a substantial number of missing values, and the distribution of those values has been altered as a function of the missing values. OHEC classifier performance has been shown to improve when the number of features is reduced and the problem of high-class imbalance is resolved, because the accuracy, sensitivity, and specificity of the classifier, as well as the number of false positives, were used to demonstrate the success of feature selection in the suggested model's predictive analysis. This has been demonstrated through the use of numerous tests involving categorization challenges. The study underscores the critical significance of early detection and prognosis in combating breast and cervical cancers, which remain leading causes of mortality worldwide. Through the utilization of machine learning models like the OHEC, the authors have demonstrated the potential for improved predictive accuracy and clinical outcomes. The findings highlight the importance of addressing challenges such as missing data and class imbalance in enhancing the performance of predictive models for effective

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

An Evaluation Of Hospital Accreditation From The Survey With Text Vector Analysis Techniques 20

An Evaluation Of Hospital Accreditation From The Survey With...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Prapunwattana, Dittaphong Imsombut, Aurawan Suwannahitatorn, Picha Saethang, Thammakorn Kasetsart University Biomedical Data Science Master's Program Faculty of Science Bangkok Thailand Kasetsart University Faculty of Science Department of Computer Science Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9798350300505

The Healthcare Accreditation Institute has an assessment and certification process for hospitals applying for Healthcare Accreditation. The assessment process requires a large number of text-based reports. The purpose of this research was to study the text analysis of the self-assessment reports of healthcare facilities and surveyor reports on issues related to the pharmaceutical system to evaluate and rate the accreditation of medical facilities. The natural language text vector analysis technique, together with the Universal Sentence Encoder (USE) was compared to Learning Lightweight Language-agnostic Sentence Embeddings (LEALLA) for encoding data into a high-dimensional format. Next the sentence encoding feature was fed through a machine learning procedure, including artificial neural networks, logistic regression, and support vector machines to classify nursing facility accreditation ratings. The experimental results showed that the USE embedding yielded better performance than the LEALLA embedding across all models with a precision of 0.70 but took slightly longer to encode feature sentences. This research could improve the performance of the analysis and scoring. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Expand-and-Cluster: Parameter Recovery of Neural Networks 41

Expand-and-Cluster: Parameter Recovery of Neural Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Martinelli, Flavio Şimşek, Berfin Gerstner, Wulfram Brea, Johanni Department of Life Sciences and Computer Sciences EPFL Lausanne Switzerland Center for Data Science NYU New York United States

Can we identify the weights of a neural network by probing its input-output mapping? At first glance, this problem seems to have many solutions because of permutation, overparameterisation and activation function symmetries. Yet, we show that the incoming weight vector of each neuron is identifiable up to sign or scaling, depending on the activation function. Our novel method 'Expand-and-Cluster' can identify layer sizes and weights of a target network for all commonly used activation functions. Expand- and-Cluster consists of two phases: (i) to relax the non-convex optimisation problem, we train multiple overparameterised student networks to best imitate the target function;(ii) to reverse engineer the target network's weights, we employ an ad-hoc clustering procedure that reveals the learnt weight vectors shared between students - these correspond to the target weight vectors. We demonstrate successful weights and size recovery of trained shallow and deep networks with less than 10% overhead in the layer size and describe an 'ease-of-identifiability' axis by analysing 150 synthetic problems of variable difficulty. Copyright 2024 by the author(s)

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Analysis of the 5Rs in Thailand Medication Error Classification through Natural Language Processing 20

Analysis of the 5Rs in Thailand Medication Error Classificat...

引用

20th International Joint Conference on computer science and Software Engineering, JCSSE 2023

作者： Udomnuchaisup, Peachyasitt Imsombut, Aurawan Suwannahitatorn, Picha Saethang, Thammakorn Kasetsart University Biomedical Data Science Master's Program Faculty of Science Bangkok Thailand Kasetsart University Faculty of Science Department of Computer Science Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9798350300505

Medication errors threaten patient safety considerably, underscoring the necessity for enhanced detection and prevention techniques. A prevalent classification system in hospitals relies on the standard practice of medication administration known as the Five Rights (5R). This study seeks to develop an NLP-based tool designed to expand 5R error categorization coverage and alleviate the workload of medical professionals. The proposed method focuses on Thai medical text, incorporating Thai and English vocabulary. In this investigation, we developed a supervised learning classification framework using the Universal Sentence Encoder (USE) for sentence embedding, followed by an Artificial Neural Network (ANN) for model training. Additionally, we explored a zero-shot classification model employing pre-trained Large Language Models (PLMs). Our findings reveal that the supervised learning classification model provides the most favorable performance, albeit with the limitation of reliance on labeled datasets, which can be resource intensive. Conversely, the zero-shot classification framework's performance is less optimal. However, future advancements in Thai medical PLMs may improve efficacy and present a viable alternative for medical data analysis without dependence on labeled datasets. This initiative lays the groundwork for potential future applications and advantages within Thailand's medical domain. © 2023 IEEE.

关键词： 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：