检索结果-内蒙古大学图书馆

13th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2025

作者： Pang, Lie Meng Ishibuchi, Hisao Nan, Yang Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9789819635054

To handle constrained multi-objective optimization problems (CMOPs), many constrained multi-objective evolutionary algorithms (CMOEAs) have been proposed. However, a recent study has shown that many of these CMOEAs do not perform well on real-world CMOPs. In contrast, NSGA-II, proposed over 20 years ago with a simple constrained dominance principle, has demonstrated better performance than recent CMOEAs on many real-world CMOPs. Motivated by NSGA-II’s promising results, this paper aims to further enhance its performance. We explore the idea of enhancing NSGA-II with a knee point for solving CMOPs. Specifically, a knee point is identified using the minimum distance from the estimated ideal point, and always included in the next population of NSGA-II. Experimental results show that this simple idea improves the performance of NSGA-II on real-world CMOPs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Tumor-TL: A Transfer Learning Approach for Classifying Brain Tumors from MRI Images 1st

Tumor-TL: A Transfer Learning Approach for Classifying Brain...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Bitto, Abu Kowshir Bijoy, Md. Hasan Imam Yesmin, Sabina Mia, Md. Jueal Department of Software Engineering Daffodil International University Dhaka1341 Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka1341 Bangladesh

ISBN: (纸本)9783031346187

An intracranial tumor is another name for a brain tumor, is a fast cell proliferation and uncontrolled bulk of tissue, and seems unaffected by the mechanisms that normally govern normal cells. The identification and segmentation of brain tumors are among the most common difficult and time-consuming tasks when processing medical images. MRI is a medical imaging technique that allows radiologists to see within body structures without requiring surgery. The information provided by MRI regarding human soft tissue contributes to the diagnosis of brain tumors. In this paper, we use several Convolutional Neural Network architectures to identify brain tumor MRI. We use a variety of pre-trained models such as VGG16, VGG19, and ResNet50, which we have found to be critical for reaching competitive performance. ResNet50 performs with an accuracy of 96.76% among all the models. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

User Recognition based on Gait Pattern via Smartwatch Accelerometer in Unrestricted Environment 3

User Recognition based on Gait Pattern via Smartwatch Accele...

引用

3rd International Conference on Communication, Computing and Digital Systems, C-CODE 2023

作者： Khan, Sheharyar Shah, Syed M Adnan Arsalan, Aamir Ahmed, Wakeel University of Engineering and Technology Taxila Department of Computer Science Taxila Pakistan Fatima Jinnah Women University Rawalpindi Department of Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350332391

Wearable gadgets are becoming a major constituent of our society due to a wide range of applications like financial transactions, unlocking automobiles, tracking health and fitness, and many more. Personal data is usually required to manage these services, however, most commercially available wearables devices either lack a user authentication mechanism or employ knowledge-based authentication like passwords, PINs, or pattern locks. In this growing digital age, it is really difficult for an individual to memorize such a huge number of passwords. In this research, we put forward a technique for recognizing users from their walking patterns recorded in real-life settings using a smartwatch accelerometer sensor. Ensemble classification techniques (bagging and boosting) are used for the purpose of user identification using the selected time domain features. Our proposed method attained the highest classification accuracy of 88.35% which transcends the existing user recognition schemes available in the literature. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Arithmetic Expression Evaluations with Membranes

引用

Chinese Journal of Electronics 2025年第1期23卷 55-60页

作者： Ping Guo Haizhu Chen Hui Zheng College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing China Department of Software Engineering Chongqing College of Electronic Engineering Chongqing China

Arithmetic operations and expression evaluations are fundamental in computing models. This paper firstly designs arithmetic membranes without priority rules for basic arithmetic operations, and then proposes an algorithm to construct expression P systems based on several of such membranes after designing synchronous and asynchronous transmission strategies among the membranes. For any arithmetic expression, an expression P system can be built to evaluate it effectively. Finally, we discuss different parallelism strategies through which different expression P systems can be built for an arithmetic expression.

关键词： Computational modeling Biological system modeling Parallel processing Biomembranes Compounds Arithmetic

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Wenhao Gu Li Gu Ziqiang Wang Ching Yee Suen Yang Wang Department of Computer Science and Software Engineering Concordia University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets.

关键词： Training Metalearning Adaptation models Handwriting recognition Visualization Technological innovation computer vision Text recognition Computational modeling Layout

来源：评论

学校读者我要写书评

暂无评论

Enhancing Viewer Engagement: Exploring Generative Long Short Term Memory in Dynamic Ad Customization for Streaming Media 5

Enhancing Viewer Engagement: Exploring Generative Long Short...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Ramagundam, Shashishekhar Karne, Niharika Troy University Software Development & Engineering in Content Discovery & Ai Department of computer Science Computer Science Montgomery Campus AL United States C & Rs Platform services DT Amtrak United States University of south alabama Department of electrical engineering Electrical engineering United States

ISBN: (纸本)9798331504403

In Ad customization, several approaches are employed to improve the relevance level of the message for monitoring the user performance according to the prior search history (e.g., retargeting) or by gathering particular information related to the customer (e.g., micro-targeting). Occasionally, the consumers view the ad developed by the other user, in this situation, the ads are viewed as something that can be related by the user. The quantity of information that is gathered openly or secretly can affect the user choice for the content displayed. However, the users remain as recipients of a strategy, that decides the best ad content. Therefore, an exploring Generative Artificial Intelligence-based Dynamic Ad Customization model for enhancing viewer engagement from streaming media is developed. In this paper, the Generative Long Short-Term Memory (GenLSTM) model is developed for examining customized advertising then includes the customization of specific message elements by individuals, variation in the level of ad customization, and in some cases perceived collaboration with others. Here, the customization classification is defined based on the modification in the marketing mix element that is created by the customer proactively as opposed to the company. In regards to customized advertising, 'ad is something that happens with the viewer'. The customization increases based on the sense of task engagement, strength of the perceived customer relationship with the company, attitude toward the ad, and perceptions of company trust/integrity. Finally, the experimental analysis is conducted based on the relationship with the company, company care, company trust, and task engagement to attain the overall impact on ad customization. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Object Recognition and Tracking System to Assist Visually Impaired: A Neural Network-Based Deep RBM Technique 1

Object Recognition and Tracking System to Assist Visually Im...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Patil, Sonal Ramagundam, Shashishekhar Sukumar, P. Khan, Mohiuddin Ali Patil, Nisha Deepak Nishant, Neerav G H Raisoni Institute of Engineering and Business Management HoD of CSE-IT Department Jalgaon India Software and Dev Engg4- SDET/ IT COMCAST MonroviaMD United States Department of Computer Science and Engineering Tamilnadu Erode India Jazan University Department of Computer & Network Engineering Jazan Saudi Arabia GCOERC Computer Engineering Nashik India School of Engineering Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350371802

Being able to see is fundamental to almost every aspect of our everyday lives, thus those who are visually impaired confront enormous obstacles. Thanks to recent developments in computer vision and computing, a system that can provide auditory input to visually impaired individuals regarding objects and their environments has been designed. Sequencing is crucial for preprocessing, feature selection, and model training. Although extremely accurate data input is still required for object detection, preparation is getting computationally cheaper. We were partially successful in reducing the image size by employing Gaussian Blur, which imparts a smoother appearance to the photos. We use color descriptors and Fourier transforms for feature extraction. Deep RBM training necessitates precise control over the attributes. In comparison to this method, current RBM and DNN algorithms look antiquated. The results demonstrated a notable enhancement in accuracy, reaching 98.31%. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Effective short text classification via the fusion of hybrid features for IoT social data

引用

Digital Communications and Networks 2022年第6期8卷 942-954页

作者： Xiong Luo Zhijian Yu Zhigang Zhao Wenbing Zhao Jenq-Haur Wang School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Shunde Innovation School University of Science and Technology BeijingFoshan528399China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083China Department of Electrical Engineering and Computer Science Cleveland State UniversityClevelandOH44115USA Department of Computer Science and Information Engineering National Taipei University of TechnologyTaipei10608China

Nowadays short texts can be widely found in various social data in relation to the 5G-enabled Internet of Things (IoT). Short text classification is a challenging task due to its sparsity and the lack of context. Previous studies mainly tackle these problems by enhancing the semantic information or the statistical information individually. However, the improvement achieved by a single type of information is limited, while fusing various information may help to improve the classification accuracy more effectively. To fuse various information for short text classification, this article proposes a feature fusion method that integrates the statistical feature and the comprehensive semantic feature together by using the weighting mechanism and deep learning models. In the proposed method, we apply Bidirectional Encoder Representations from Transformers (BERT) to generate word vectors on the sentence level automatically, and then obtain the statistical feature, the local semantic feature and the overall semantic feature using Term Frequency-Inverse Document Frequency (TF-IDF) weighting approach, Convolutional Neural Network (CNN) and Bidirectional Gate Recurrent Unit (BiGRU). Then, the fusion feature is accordingly obtained for classification. Experiments are conducted on five popular short text classification datasets and a 5G-enabled IoT social dataset and the results show that our proposed method effectively improves the classification performance.

关键词： Information fusion Short text classi fication BERT Bidirectional encoder representations fr 0om transformers Deep learning Social data

来源：评论

学校读者我要写书评

暂无评论

On the Implications of Human-Paper Interaction for software Requirements engineering Education 34

On the Implications of Human-Paper Interaction for Software ...

引用

34th International Conference on software engineering and Knowledge engineering, SEKE 2022

作者： Kamthan, Pankaj Department of Computer Science and Software Engineering Concordia University Montreal Canada

ISBN: (纸本)1891706543

It is broadly accepted that requirements engineering is one of the most important phases of a software project, and requires tools to be effective. For a variety of reasons, paper as a tool has lasted for millennia and remains ubiquitous. This paper makes a case for a contextual, conscientious, and evidence-based use of paper in a competency-oriented approach to software requirements engineering education (REE). It argues that the prophecies for the obsolescence of paper are premature, there are unique benefits in the use of paper, and the decision to use paper should be based on [0, 1] rather than (0, 1). In this regard, a need-centered conceptual model for human-paper interaction is proposed. The characteristics of paper that make it historically unique are reported and the affordances of paper relevant to REE are discussed. The REE-related activities that benefit from viewing paper as a boundary object and using different types of paper are highlighted and illustrated by means of examples. In advocating polyliteracy, the potential for a convergence of paper and digital media towards a harmonic coexistence is underscored. © 2022 Knowledge Systems Institute Graduate School. All rights reserved.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing ASD Diagnosis with Contrastive and Non-Contrastive Models from Neuroimaging Data 4

Enhancing ASD Diagnosis with Contrastive and Non-Contrastive...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Jha, Abhishek Mehta, Ishita Khan, Kainat Katarya, Rahul Delhi Technological University Department of Mechanical Engineering New Delhi India Delhi Technological University Department of Software Engineering New Delhi India Delhi Technological University Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350352931

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition which impacts social interaction, communication, and behavior. This study introduces a self-supervised learning approach for ASD prediction using resting-state functional MRI (rs-fMRI) scans from the ABIDE I dataset, employing contrastive and non-contrastive models. The contrastive model enhances learning by maximizing agreement between augmented views of the same scan, while the non-contrastive model reconstructs input data through an autoencoder. Both models, pre-trained on ImageNet, were fine-tuned for ASD classification using Resnet18. Our results show that the contrastive model achieved 97.6% accuracy, with a precision of 95.7%, recall of 99.2%, and F1 score of 97.4%. The non-contrastive model reached 95.4% accuracy, with precision, recall, and F1 scores of 99.3%, 96.46%, and 97.82%. These findings highlight the performance of self-supervised learning in ASD diagnosis, showcasing robust pattern-capturing capabilities for neuroimaging data. © 2024 IEEE.

关键词： Contrastive Learning

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：