检索结果-内蒙古大学图书馆

2024 International Conference on Machine Learning, Pattern Recognition and Automation engineering, MLPRAE 2024

作者： Li, Bohang Jiang, Gaozhe Li, Ningxin Song, Chaoda Department of Data Science Shopee Pte. Ltd. Singapore Institute of Operations Research and Analytics National University of Singapore Singapore Fu Foundation School of Engineering and Applied Science Columbia University United States School of Engineering Department of Computer and Data Sciences United States

ISBN: (纸本)9798400709876

Since the beginning of the internet era, there has been an explosion of growth in structured data (such as numbers, symbols, and labels) as well as unstructured data (including images, videos, and text). Efficient and accurate mixed query of these two types of data is a key technology to achieve high-quality information retrieval, and it is also a major challenge that needs to be solved urgently in the industry. In this study, we employ an advanced Transformer model that combines strategies and fine-tuning techniques for multi-task learning. Specifically, the model is first pre-trained on a large-scale, general-purpose dataset to learn different types of data representations and basic language comprehension skills. After that, we fine-tuned the parameters of the model to better suit these specific data processing tasks for specific application scenarios, such as image annotation, video content analysis, and structured data query. At the heart of the model is the self-attention mechanism, which allows the model to automatically emphasize the important parts and ignore irrelevant information when processing the input data. In addition, we have introduced task-specific adaptation layers that are designed to add additional processing power to the original Transformer architecture, such as a semantic analysis layer for unstructured text data and a relational extraction layer for structured data. This combination of general pre-training and task-specific fine-tuning allows the model to flexibly process and integrate information from different data sources, improving processing efficiency and accuracy. Experimental results show that the model performs well in a variety of data processing tasks, significantly improves the accuracy and efficiency of information retrieval, and verifies the strong potential and adaptability of large language models in processing mixed data types. © 2024 ACM.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ding, Lichao Zhao, Jing Lu, Kai Hao, Zenghao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

FedTop:a constraint-loosed federated learning aggregation method against poisoning attack

引用

Frontiers of computer science 2024年第5期18卷 233-235页

作者： Che WANG Zhenhao WU Jianbo GAO Jiashuo ZHANG Junjie XIA Feng GAO Zhi GUAN Zhong CHEN School of Computer Science Peking UniversityBeijing 100871China Peking University Chongqing Research Institute of Big Data Chongqing 401329China China Unicom Beijing 100033China National Engineering Research Center for Software Engineering Peking UniversityBeijing 100871China

Federated learning(FL)is a decentralized machine learning paradigm,which has significant advantages in protecting data privacy[1].However,FL is vulnerable to poisoning attacks that malicious participants perform attacks by injecting dirty data or abnormal model parameters during the local model training and aim to manipulate the performance of the global model[2].

关键词： constraint loose aggregation

来源：评论

学校读者我要写书评

暂无评论

HAM: Hybrid Associations Models for Sequential Recommendation (Extended abstract) 39

HAM: Hybrid Associations Models for Sequential Recommendatio...

引用

39th IEEE International Conference on data engineering, ICDE 2023

作者： Peng, Bo Ren, Zhiyun Parthasarathy, Srinivasan Ning, Xia The Ohio State University Department of Computer Science and Engineering United States The Ohio State University Department of Biomedical Informatics United States The Ohio State University Translational Data Analytics Institute Department of Computer Science and Engineering United States The Ohio State University Translational Data Analytics Institute Department of Biomedical Informatics Department of Computer Science and Engineering United States

ISBN: (纸本)9798350322279

Sequential recommendation aims to identify and recommend the next few items of users' interest. It becomes an effective tool to help users select their favorite items from a variety of options. A key challenge in sequential recommendation is to learn the patterns and dynamics, which are most pertinent to inform future interactions of users. With the prosperity of deep learning, many deep models, particularly based on recurrent neural networks [1] and with attention mechanisms [2] , [3] , have been developed for sequential recommendation purposes. However, our analysis demonstrates that, these deep models, particularly those with attention mechanisms, may not always learn meaningful attention weights from the extremely sparse recommendation data, and thus, could degrade the recommendation performance. Therefore, in this study, instead of deep models, we develop novel, effective and efficient hybrid associations models (HAM) to better learn from the sparse and limited recommendation data. This study has been published in IEEE Transactions on Knowledge and data engineering. Please refer to the full manuscript [4] for more details. © 2023 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

An Industrial Robot Path Planning Method Based on Improved Whale Optimization Algorithm 1

引用

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Huang, Peixin Dong, Chen Chen, Zhenyi Zhen, Zihang Jiang, Lei College of Computer and Data Science Fuzhou University Fuzhou350116 China Fuzhou China Department of Computer Science and Engineering University of South Florida TampaFL33620 United States College of Computer and Cyber Security Fujian Normal University Fuzhou350007 China

ISBN: (数字)9789819998937

ISBN: (纸本)9789819998920

With the development of technology, robots are gradually being used more and more widely in various fields. Industrial robots need to perform path planning in the course of their tasks, but there is still a lack of a simple and effective method to implement path planning in complex industrial scenarios. In this paper, an improved whale optimization algorithm is proposed to solve the robot path planning problem. The algorithm initially uses a logistic chaotic mapping approach for population initialization to enhance the initial population diversity, and proposes a jumping mechanism to help the population jump out of the local optimum and enhance the global search capability of the population. The proposed algorithm is tested on 12 complex test functions and the experimental results show that the improved algorithm achieves the best results in several test functions. The algorithm is then applied to a path planning problem and the results show that the algorithm can help the robot to perform correct and efficient path planning. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

Medical Material Allocation using Multi-Queue Scheduling during Pandemics

Medical Material Allocation using Multi-Queue Scheduling dur...

引用

2024 International Conference on science, Technology, engineering and Management, ICSTEM 2024

作者： Divya Priya, D. Subramaniam, Suthashini Kumar, P. Vinoth Theam, Lim Jit Ayyasamy, Ramesh Kumar Krishnan, Kesavan Department of Computer Science Engineering MLR Institue of Technology Hyderabad India Perak Kampar Malaysia Department of Artificial Intelligence and Data Science St Joseph's Institute of Technology OMR CHENNAI India Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798350376913

In this study, we implemented a multi-level queue scheduling algorithm for a hospital with three wards: General, Pandemic, and Arogya Sree. The Pandemic ward uses priority scheduling, while the others use FCFS. It also calculates distances to nearby airports based on geolocation to identify oxygen airlift points. This work allows us to eliminate human interference in resource allocation by automating the process based on priority derived from the doctor’s diagnosis. This ensures that maximum efficiency is reached. The common people faced many problems during the pandemic, mainly related to costs incurred and resource availability. We want to solve this by removing the human factor from the equation. © 2024 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

DeepVec: State-Vector Aware Test Case Selection for Enhancing Recurrent Neural Network

引用

IEEE Transactions on Software engineering 2025年第6期51卷 1702-1723页

作者： Jiang, Zhonghao Yan, Meng Huang, Li Sun, Weifeng Liu, Chao Sun, Song Lo, David Chongqing University School of Big Data and Software Engineering China Chongqing Normal University School of Computer and Information Science China Singapore Management University School of Information Systems Singapore

Deep Neural Networks (DNN) have realized significant achievements across various application domains. There is no doubt that testing and enhancing a pre-trained DNN that has been deployed in an application scenario is crucial, because it can reduce the failures of the DNN. DNN-driven software testing and enhancement require large amounts of labeled data. The high cost and inefficiency caused by the large volume of data of manual labeling, and the time consumption of testing all cases in real scenarios are unacceptable. Therefore, test case selection technologies are proposed to reduce the time cost by selecting and only labeling representative test cases without compromising testing performance. Test case selection based on neuron coverage (NC) or uncertainty metrics has achieved significant success in Convolutional Neural Networks (CNN) testing. However, it is challenging to transfer these methods to Recurrent Neural Networks (RNN), which excel at text tasks, due to the mismatch in model output formats and the reliance on image-specific characteristics. What’s more, balancing the execution cost and performance of the algorithm is also indispensable. In this paper, we propose a state-vector aware test case selection method for RNN models, namely DeepVec, which reduces the cost of data labeling and saves computing resources and balances the execution cost and performance. DeepVec selects data using uncertainty metric based on the norm of the output vector at each time step (i.e., state-vector), and similarity metric based on the direction angle of the state-vector. Because test cases with smaller state-vector norms often possess greater information entropy and similar changes of state-vector direction angle indicate similar RNN internal states. These metrics can be calculated with just a single inference, which gives it strong bug detection and model improvement capabilities. We evaluate DeepVec on five popular datasets, containing images and texts as well as commonl

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

Visual Computing Unified Application Using Deep Learning and computer Vision Techniques

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第1期18卷 59-74页

作者： Sowmya, B.J. Meeradevi Seema, S. Dayananda, P. Supreeth, S. Shruthi, G. Rohith, S. Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Karnataka Bengaluru India Department of Artificial Intelligence and Machine Learning Ramaiah Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering M S Ramaiah Institute of Technology Karnataka Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Karnataka Manipal India School of Computer Science and Engineering REVA University Karnataka Bengaluru India Department of Electronics & Communication Engineering Nagarjuna College of Engineering & Technology Karnataka Bengaluru India

Vision Studio aims to utilize a diverse range of modern deep learning and computer vision principles and techniques to provide a broad array of functionalities in image and video processing. Deep learning is a distinct class of machine learning algorithms that utilize multiple layers to gradually extract more advanced features from raw input. This is beneficial when using a matrix as input for pixels in a photo or frames in a video. computer vision is a field of artificial intelligence that teaches computers to interpret and comprehend the visual domain. The main functions implemented include deepfake creation, digital ageing (de-ageing), image animation, and deepfake detection. Deepfake creation allows users to utilize deep learning methods, particularly autoencoders, to overlay source images onto a target video. This creates a video of the source person imitating or saying things that the target person does. Digital aging utilizes generative adversarial networks (GANs) to digitally simulate the aging process of an individual. Image animation utilizes first-order motion models to create highly realistic animations from a source image and driving video. Deepfake detection is achieved by using advanced and highly efficient convolutional neural networks (CNNs), primarily employing the EfficientNet family of models. © 2024 by the authors of this article. Published under CC-BY.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

LQTTrack:Multi-Object Tracking by Focusing on Low-Quality Targets Association

引用

computers, Materials & Continua 2024年第10期81卷 1449-1470页

作者： Suya Li Ying Cao Hengyi Ren Dongsheng Zhu Xin Xie Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information EngineeringHenan UniversityKaifeng475001China College of Information Science and Technology&Artificial Intelligence Nanjing Forestry UniversityNanjing210037China School of Computer Nanjing University of Posts and TelecommunicationsNanjing210023China

Multi-object tracking(MOT)has seen rapid improvements in recent ***,frequent occlusion remains a significant challenge in MOT,as it can cause targets to become smaller or disappear entirely,resulting in lowquality targets,leading to trajectory interruptions and reduced tracking *** from some existing methods,which discarded the low-quality targets or ignored low-quality target ***,with a lowquality association strategy(LQA),is proposed to pay more attention to low-quality *** the association scheme of LQTTrack,firstly,multi-scale feature fusion of FPN(MSFF-FPN)is utilized to enrich the feature information and assist in subsequent data ***,the normalized Wasserstein distance(NWD)is integrated to replace the original Inter over Union(IoU),thus overcoming the limitations of the traditional IoUbased methods that are sensitive to low-quality targets with small sizes and enhancing the robustness of low-quality target ***,the third association stage is proposed to improve the matching between the current frame’s low-quality targets and previously interrupted trajectories from earlier frames to reduce the problem of track fragmentation or error tracking,thereby increasing the association success rate and improving overall multi-object tracking *** experimental results demonstrate the competitive performance of LQTTrack on benchmark datasets(MOT17,MOT20,and DanceTrack).

关键词： Low-quality targets association strategy feature fusion multi-object tracking tracking-by-detection

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Prediction Using Convolutional Neural Networks Pre Trained Architecture

Alzheimer's Disease Prediction Using Convolutional Neural Ne...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Sahil, P Sam Sinha, Bhawesh K Akash, Thirumala K Ahmed, Mohammed Riyaz HKBK College of Engineering Computer Science and Engineering Bangalore India Swami Vivekananda University Data Science and Engineering West Bengal Kolkata India Analyst 1 Infrastructure Service DXC Technology Bangalore India HKBK College of Engineering Electronics and Communication Engineering Bangalore India

ISBN: (纸本)9798350379525

Alzheimer's Disease (AD) is a progressive neu-rodegenerative disorder that significantly impacts memory and cognitive abilities. Accurate early-stage diagnosis is critical for implementing preventive measures before irreversible brain damage occurs. This paper presents a novel approach for AD prediction using convolutional neural networks (CNN) with pre-trained architectures, leveraging transfer learning to enhance classification accuracy. MRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset were used, categorized into three classes: AD (Alzheimer's Disease), CI (Mild Cognitive Impaired) and CN (Common Normal). The proposed method em-ploys pre-trained models such as VGG16, DenseNet121, Xception, ResNet152V2, NasNetLarge and InceptionResNetV2, fine-tuned for AD detection. Experimental results demonstrate that our approach achieved classification exceeding 90 % for precision and recall, highlighting the effectiveness of CNNs in handling large-scale medical data. These findings underscore the potential of deep learning models for supporting clinical diagnosis, reducing time and cost, and aiding in the early detection of Alzheimer's Disease. © 2024 IEEE.

关键词： Convolutional 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：