检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Gongpei Wang, Tao Lang, Congyan Jin, Yi Li, Yidong Ling, Haibin Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University United States

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks. © 2024 Neura

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using an extended technology acceptance model to predict enterprise architecture adoption in making cities smarter

引用

Environment Systems and Decisions 2023年第1期43卷 36-53页

作者： Jnr, Bokolo Anthony Petersen, Sobah Abbas Department of Applied Data Science Institute for Energy Technology Os Alle 5 Halden 1777 Norway Department of Computer Science Norwegian University of Science and Technology NTNU Trondheim NO-7491 Norway

Presently cities are undergoing changes and transformations due to the adoption of information and communications technology. Enterprise Architecture (EA) is one of the approaches adopted by practitioners and researchers to facilitate smart city development as it can enhance the effectiveness of cities’ digital resources and sustainability capabilities. But, despite several literature on EA, studies on the adoption of EA to improve the sustainability of cities are still at the early stage. Besides, there are fewer studies that provided evidence on the adoption of EA to make cities sustainable grounded on established theoretical models and quantitative data. Therefore, this study aims to provide an understanding on the adoption of EA by different practitioners involved in a smart city project. Knowledge transfer and support services are integrated as new external variables needed to improve practitioners’ behavior intention and actual adoption of EA in making cities smarter. A model is developed grounded on an extension of Technology Acceptance Model (TAM), and data were collected via a cross-country survey. Partial least squares-structural equation modeling was employed to analyze the data. Findings from this study offer implications for research and practice and provide opportunities for future research. © 2022, The Author(s).

关键词： Enterprise architecture adoption Extended technology acceptance model Knowledge transfer Smart cities Support service Sustainable cities

来源：评论

学校读者我要写书评

暂无评论

Blood Test Report-Based Prediction and Classification of Diseases Using Artificial Neural Networks 1

Blood Test Report-Based Prediction and Classification of Dis...

引用

1st International Conference for Women in Computing, InCoWoCo 2024

作者： Kodipalli, Ashwini Prajwal, N. Vignesh, Vamshi B. Rao, Trupthi Gargi, N. Devamane, Shridhar B. Global Academy of Technology Dept. Artificial Intelligence & Data Science Karnataka Bangalore India School of Computing Amrita Vishwavidyapeetam Department of Computer Science Mysuru India

ISBN: (纸本)9798331518943

Through early intervention and individualized treatment plans, timely disease detection and personalized healthcare can advance patient results and reduce healthcare costs. With the aim to categorize medical conditions, we present a dataset in this study that includes blood sample parameters like haemoglobin, cholesterol, and glucose. To analyse these parameters, we created a three-layered artificial neural network (ANN). Achieving an accuracy of 93.42% on the test set, the ANN was trained and validated on the dataset. With the aim of reducing overfitting and enhance model generalization, dropout layers were added. Furthermore, a comparative analysis with various optimizers was carried out. The results highlight the ANN's potential as a means for timly diagnosis, personalized healthcare, improving patient outcomes and lowering long-term healthcare costs. They also demonstrate the ANN's ability to accurately classify diseases. © 2024 IEEE.

关键词： Anaemia ANN Artificial Neural Networks Blood Test Classification Deep learning

来源：评论

学校读者我要写书评

暂无评论

One-Shot Sequential Federated Learning for Non-IID data by Enhancing Local Model Diversity 24

One-Shot Sequential Federated Learning for Non-IID Data by E...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Naibo Deng, Yuchen Feng, Wenjie Fan, Shichen Yin, Jianwei Ng, See-Kiong Institute of Data Science National University of Singapore Singapore Singapore School of Mathematics and Statistics Changchun University of Technology Changchun China School of Computer Science and Technology Xidian University Xi'an China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (纸本)9798400706868

Traditional federated learning mainly focuses on parallel settings (PFL), which can suffer significant communication and computation costs. In contrast, one-shot and sequential federated learning (SFL) have emerged as innovative paradigms to alleviate these costs. However, the issue of non-IID (Independent and Identically Distributed) data persists as a significant challenge in one-shot and SFL settings, exacerbated by the restricted communication between clients. In this paper, we improve the one-shot sequential federated learning for non-IID data by proposing a local model diversity-enhancing strategy. Specifically, to leverage the potential of local model diversity for improving model performance, we introduce a local model pool for each client that comprises diverse models generated during local training, and propose two distance measurements to further enhance the model diversity and mitigate the effect of non-IID data. Consequently, our proposed framework can improve the global model performance while maintaining low communication costs. Extensive experiments demonstrate that our method exhibits superior performance to existing one-shot PFL methods and achieves better accuracy compared with state-of-the-art one-shot SFL methods on both label-skew and domain-shift tasks (e.g., 6%+ accuracy improvement on the CIFAR-10 dataset). Our code and supplementary are available online: https://***/NaiboWang/FedELMY. © 2024 ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Short Paper: "It’s Too Hot Under the Sun": Unveiling the Impact of Prolonged Heat Exposure on Rickshaw Pullers’ Brainwaves 24

Short Paper: "It’s Too Hot Under the Sun": Unveiling the Im...

引用

11th International Conference on Networking, Systems and Security, NSysS 2024

作者： Hasana, Maoyejatun Rahaman, Masfiqur Abedin, Razin Reaz Tahmid, Md Toki Tarin, Ishika Saha, Sudipa Tithi, Sutapa Dey Promi, Zarin Tasnim Noor, Kazi Abdun Sanjid, M.D. Zahidul Islam Dhrubo, Mahir Shahriar Akter, Samira Rahman, Tauhidur Al Islam, A.B.M. Alim Department of Computer Science and Engineering Bangladesh University of Engineering and Technology Dhaka Bangladesh Halıcıoğlu Data Science Institute University of California San Diego San DiegoCA United States Department of Computer Science and Engineering Brac University Dhaka Bangladesh Halıcıoğlu Data Science Institute University of California San Diego La Jolla CA United States

ISBN: (纸本)9798400711589

The changing climate is anticipated to result in more frequent and extended heat waves having catastrophic effects on urban areas. Prolonged exposure to extreme heat is believed to adversely affect both physiological and psychological well-being, particularly for outdoor workers. This study analyzed the effects of hot weather conditions on the brainwaves of rickshaw pullers by examining changes in EEG signals before and after driving rickshaws at different air temperatures and relative humidity levels. We selected six rickshaw pullers as participants for six levels of air temperature (°C) and humidity condition (%) in various outdoor areas in Dhaka city, Bangladesh, while driving rickshaws for a duration of 20 to 30 minutes. The acquired EEG data assists in assessing the effects of heat exposure on cerebral activity. Our statistical analysis shows that there is a positive association between heat stress and the alpha band power of brainwaves. © 2024 Copyright held by the owner/author(s).

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Orchestrating Plasticity and Stability: A Continual Knowledge Graph Embedding Framework with Bio-Inspired Dual-Mask Mechanism 16

Orchestrating Plasticity and Stability: A Continual Knowledg...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Song, Ailin Chen, Yuhong Wang, Yusong Zhong, Shuai Xu, Mingkun Guangdong Institute of Intelligence Science and Technology Hengqin Zhuhai China College of Computer and Data Science Fuzhou University Fuzhou China Tokyo Institute of Technology Tokyo Japan

Learning in biological systems involves the intricate modeling of diverse entities and their interrelations, leading to the evolution of logical knowledge networks with accumulating experience. Analogously, knowledge graphs serve as semantic representations of entity relationships, playing a vital role in natural language processing and graph representation learning. However, contemporary knowledge graph embedding models often neglect real-world event updates, while existing continual knowledge graph research predominantly relies on conventional learning methods that inadequately leverage graph structure, thereby compromising their continual learning capabilities. This study introduces a novel Continual mask Knowledge Graph Embedding framework (CMKGE), designed to address these limitations. CMKGE integrates semantic attributes, network structure, and continual learning mechanisms to capture the dynamic evolution of knowledge. Inspired by biological signal propagation and Dale’s principle, we introduce a dual-mask mechanism for neuronal inhibition and activation. This mechanism automatically filters critical old knowledge, enhancing model plasticity and stability. Through comprehensive evaluations on four datasets, we demonstrate CMKGE’s superiority over state-of-the-art continual embedding models. © 2024 A. Song1, Y. Chen1, Y. Wang, S. Zhong∗ & M. Xu∗.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

An Efficient Image to Speech Generation System for Visually Impaired Individuals Using Deep Learning Techniques 10

An Efficient Image to Speech Generation System for Visually ...

引用

10th International Conference on Advanced Computing and Communication Systems, ICACCS 2024

作者： Priyanka, G. Nivaashini, M. Shree Akshaya, B. Subashini, M. Ritish, G. Sri Ramakrishna Engineering College Department of Computer Science and Engineering Coimbatore India Sri Eshwar College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384369

As the world is becoming more visually oriented, visually impaired people are struggling to access and understand visual content. This paper aims to represent the model created to assist blind and visually impaired people. This method leverages deep learning techniques to convert images into meaningful audio outputs. It involves capturing input images and processing them using advanced deep-learning algorithms. The extracted features are translated into speech. The resulting auditory output provides an alternative sensory experience for individuals with visual impairments, enabling them to perceive and interpret visual information through sound. This study implements four deep learning models namely CNN-LSTM, Resnet34, YOLOv5 and Vision Transformer to process sequential visual data capturing intricate patterns and dependencies within images. By integrating these models in this work, the Image to audio converter not only achieves superior accuracy in image recognition but also enhances the richness and depth of the auditory output, creating a nuanced and immersive sensory experience for users. The performance of the proposed models was evaluated using several metrics and it was noted that vision transformer outperformed the remaining models. This seamless integration of deep learning models amplifies the study's effectiveness in translating diverse visual inputs into detailed and coherent auditory output, thereby enhancing accessibility and inclusivity for individuals with visual impairments. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Semantic-Driven Generative Information Extraction Framework Oriented to Patent Text 21

A Semantic-Driven Generative Information Extraction Framewor...

引用

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhao, Yushan Wang, Tengke Zhang, Shunxiang Anhui University of Science and Technology School of Mathematics and Big Data Huainan China Anhui University of Science and Technology School of Computer Science and Engineering Huainan China

ISBN: (纸本)9798350329223

Generative information extraction for patent text relies on a text-to-structure encoder-decoder framework, facilitating the automatic construction of patent knowledge bases. Existing models challenge to capture the long-range semantic dependencies due to the decentralized semantic context within the patent text, diminishing the accuracy of information extraction. In this work, we present a Semantic-driven Generative Information Extraction (SGIE) framework oriented to patent texts by enhancing and associating semantic context, leading to an improved information extraction performance. Information networks obtained from the pre-trained language model are used as information representations in the encoder layer, and based on an AMR (Abstract Meaning Representation) parser combined with patent schema knowledge, the patent-AMR graphs are created and viewed as semantic representations. The semantic-enhanced information representations are acquired by alignment from the same level of semantic and information representations, so then the global information representation is gained by gated fusing all semantic-enhanced information representations. A patent scheme knowledge-constrained decoder is employed beam search to generate information based on the semantic order decided, so patent technical information is extracted. Experimental results show that the proposed model is highly accurate and efficient in patent texts and is promising. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Beyond Labels and Topics: Discovering Causal Relationships in Neural Topic Modeling 24

Beyond Labels and Topics: Discovering Causal Relationships i...

引用

33rd ACM Web Conference, WWW 2024

作者： Tang, Yi-Kun Huang, Heyan Shi, Xuewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics Liaoning Dalian China

ISBN: (纸本)9798400701719

Topic models that can take advantage of labels are broadly used in identifying interpretable topics from textual data. However, existing topic models tend to merely view labels as names of topic clusters or as categories of texts, thereby neglecting the potential causal relationships between supervised information and latent topics, as well as within these elements themselves. In this paper, we focus on uncovering possible causal relationships both between and within the supervised information and latent topics to better understand the mechanisms behind the emergence of the topics and the labels. To this end, we propose Causal Relationship-Aware Neural Topic Model (CRNTM), a novel neural topic model that can automatically uncover interpretable causal relationships between and within supervised information and latent topics, while concurrently discovering high-quality topics. In CRNTM, both supervised information and latent topics are treated as nodes, with the causal relationships represented as directed edges in a Directed Acyclic Graph (DAG). A Structural Causal Model (SCM) is employed to model the DAG. Experiments are conducted on three public corpora with different types of labels. Experimental results show that the discovered causal relationships are both reliable and interpretable, and the learned topics are of high quality comparing with eight start-of-the-art topic model baselines. © 2024 ACM.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Corner Key Point Extracted Deep Learning Framework Based Birds Species Classification 8

Corner Key Point Extracted Deep Learning Framework Based Bir...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Devi, M. Shyamala Jamal Mohammed, R. Hemanth, S. Harish Raj, B. Gajapathy, R. Kamalesh, P. Panimalar Engineering College Department of Computer Science and Engineering Tamilnadu Chennai India Panimalar Engineering College Department of Artificial Intelligence and Data Science Tamilnadu Chennai India

ISBN: (纸本)9798331505462

Climate change and habitat destruction have caused the extinction of many bird species. Classifying bird species is a crucial aspect of ornithology, as it aids in the comprehension of species distribution, habitat needs, and environmental changes that impact bird populations. Ornithologists can use variations in bird species distributions to measure the health of a particular environment. Expert ornithologists have relied heavily on visual inspection, which can be tedious, time-consuming, and unreliable when classifying bird species. The development of technology can be used to categorize the bird species. This paper proposes Corner Key Filtered VGG16 (CKP-VGG16) that categorizes eight bird species with high accuracy. The execution was carried out using the 4000 bird images from the KAGGLE Birds species dataset. First, the CKP-VGG16 model separates the images of birds, and then it labels each image. After data augmentation on the labeled images, 84,000 bird images are produced. The augmented images are transformed into grayscale versions, which are then used in filtering techniques to produce Corner Key Point Filtered (CKP) bird image. The performance is analyzed by applying the CKP filtered bird images to the current CNN models. The application demonstrates that the suggested CKP-VGG16 model performs significantly well in classifying bird species, with a high accuracy of 99.7%. © 2024 IEEE.

关键词： Birds

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：