检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Chen, Xiu-Zhi Huang, Hsiao-Wei Chen, Yen-Lin Dept. of Computer Science & Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9798331521165

Two approaches are available for WSOD: MIL and CAM. MIL-based methods are capable of addressing multiple targets and multiple class problems. However, these methods require the input of region proposals. In contrast, CAM-based methods are straightforward and more efficient, yet they are constrained by limited localization accuracy and are likely to be applicable only to single target classes. This study proposes a CAM-based WSOD method that is capable of addressing multi-object, multi-class tasks with high efficiency, which could prove beneficial for the development of specific consumer electronic applications, such as smart cameras and smart home devices. The proposed method was evaluated on two public datasets, demonstrating that it is significantly more efficient than the baseline method. © 2025 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Road Mark Detection for Advanced Driver Assistance Systems in Consumer Automotive Technology

Weakly Supervised Road Mark Detection for Advanced Driver As...

引用

Consumer Technology (ICCT-Pacific), International Conference on

作者： Xiu-Zhi Chen Xiao-Wei Huang Yen-Lin Chen Dept. of Computer Science & Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798331504120

ISBN: (纸本)9798331504137

Road mark detection is a critical component of Advanced Driver Assistance Systems (ADAS), ensuring accurate lane-keeping, navigation, and driver safety. However, the high cost of acquiring fully annotated datasets for supervised learning poses a significant challenge for real-world applications. This paper proposes a novel weakly supervised learning method for road mark detection tailored to consumer automotive technology. Leveraging weak annotations, the method efficiently learns to detect and classify road marks with minimal human intervention. The approach was evaluated on the publicly available CeyMo dataset, achieving a classification accuracy of 99.3% and a localization accuracy of 71.5%, demonstrating its effectiveness and practicality. The proposed method reduces the dependency on fully annotated data while maintaining competitive performance, making it a scalable solution for consumer-level ADAS applications. This work contributes to advancing cost-effective, reliable, and scalable ADAS technologies, paving the way for broader adoption in intelligent vehicles.

关键词： Location awareness Accuracy Weak supervision Intelligent vehicles Roads Supervised learning Safety Reliability Advanced driver assistance systems Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Principles of Machine Learning in Voice Recognition 2

Principles of Machine Learning in Voice Recognition

引用

2nd International Conference on Data Analytics, Computing and Artificial Intelligence, ICDACAI 2023

作者： Jiang, Tianyang Zhu, Yuke Feng, Haojun University of Shanghai for Science and Technology Usst Dept. School of Optical-Electrical and Computer Engineering Shanghai China Zhejiang Gongshang University Dept. School of Information and Electronic Engineering Hangzhou China Jurong Country Garden School Jurong China

ISBN: (纸本)9798350339765

Sounds carry a huge amount of information of our daily life and physical events. We hear sounds in complex environment and from increased amounts of electric devices, so audio recognition is definitely an important technology in human-computer interaction. In recent years, speech recognition technology developed rapidly. Summarizing recognition methods is necessary when there are too many methods to choose. This paper introduces some of the advanced technologies, Recurrent Neural Network, Convolutional Neural Network, Linear Regression, Multilayer Perceptron, Random Forest and their principle. © 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

CAM-Based High Efficient Weakly Supervised Multi-Object Multi-Class Detection Method

CAM-Based High Efficient Weakly Supervised Multi-Object Mult...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Xiu-Zhi Chen Hsiao-Wei Huang Yen-Lin Chen Dept. of Computer Science & Information Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

关键词： Location awareness Electric potential Accuracy Smart cameras Object detection Smart homes Computational efficiency Proposals Consumer electronics Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Reconnaissance Detection in Decentralised IoT System using Model-Contrastive Federated Learning

Reconnaissance Detection in Decentralised IoT System using M...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Rajdeep Kumar Dutta Bishal Chhetry Rakesh Matam Ferdous Ahmed Barbhuiya Dept. of Computer Science and Engineering Indian Institute of Information Technology Guwahati India

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

The detection of reconnaissance attacks is crucial for safeguarding Internet of Things (IoT) environments, which are inherently more vulnerable and resource-constrained compared to traditional computing systems. Traditional centralised detection methods face significant challenges, such as privacy concerns and limited scalability due to the need to aggregate raw data on a central server. These issues become particularly pronounced in IoT environments where devices are diverse and geographically distributed. To address these challenges, we propose ReconGuard, a novel approach leveraging Model Contrastive Federated Learning (MCFL). ReconGuard enables collaborative training across multiple IoT devices without the necessity of sharing raw data, thereby preserving user privacy and enhancing data security. The approach integrates contrastive learning techniques, which improve the model’s ability to discriminate between benign and malicious activities by contrasting positive (similar) and negative (dissimilar) data pairs. Our experimental results demonstrate that the ReconGuard-based detection system provides a scalable and privacy-preserving solution for identifying reconnaissance activities. These activities are often the initial step in more severe cyber threats, such as botnet attacks, which can lead to significant disruption and damage. By effectively detecting reconnaissance activities, ReconGuard enhances the overall cybersecurity framework of IoT environments. This research presents a viable and innovative method for improving cybersecurity in IoT systems, addressing the critical need for scalable, efficient, and privacy-preserving intrusion detection solutions. The use of MCFL in ReconGuard not only mitigates the challenges of data centralisation but also leverages the distributed nature of IoT networks to enhance robustness against cyber threats.

关键词： Training Data privacy Federated learning Scalability Reconnaissance Data models Telecommunications Internet of Things Servers Faces

来源：评论

学校读者我要写书评

暂无评论

The Correlation Between Architecture Smells, Package Stability and Reusability: A Case Study 4

The Correlation Between Architecture Smells, Package Stabili...

引用

4th IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2024

作者： Benidris, Mrwan Elfallah, Ehab A. Omar Cheema, Marwa Aslam Alsma, Mohammed Salah Addin Kadiki, Tareq Ziad Elbarsha, Abdelfattah University of Benghazi Faculty of Information Technology Dep. of Computer Science Libya Libyan International Medical University Faculty of Information Technology Dept. of Software Engineering Libya University of Benghazi Faculty of Public Health Health Informatics Department Libya

ISBN: (纸本)9798350372632

the design decisions made in the architecture of a software system are essential to its maintainability, and thus its quality is of great importance. Architecture smells (ASs) can be used to identify any quality issues within the system. To further explore the relationships between ASs, stability, and reusability, Spearman correlation coefficients will be calculated. This paper seeks to examine the connection between architecture smells, software stability, and reusability. To do this, we utilized a dataset created by other researchers and conducted an empirical study of the associations between five types of architecture smells and software stability and reusability. This research is necessary as there is a lack of in-dept. research on architecture smells and their relationship to software stability and reusability. We found a relationship between the presence of Feature Concentration in package and the stability and reusability of the package. Also, package's stability is affected by both Cyclic Dependency and Unstable Dependency. A slight positive correlation has been found between God Class and stability, as well as a very weak negative correlation between Unstable Dependency and reusability. Finally, we found a slight negative correlation between package stability and reusability. © 2024 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

An Extended Deep Learning based Solution for Screening COVID-19 CT-Scans 9

An Extended Deep Learning based Solution for Screening COVID...

引用

9th International Conference on Computing for Sustainable Global Development, INDIACom 2022

作者： Pandey, Dhiraj Pandey, Kavita Jss Academy of Technical Education Noida Dept. of Information Technology Noida India Jaypee Institute of Information Technology Noida Dept. of Computer Science Engineering and Information Technology Noida India

ISBN: (纸本)9789380544441

Due to immense pressure on the medical sector, there is a huge chance of human error in diagnosing the report of COVID-19 patients. For the detection of COVID-19, many Artificial Intelligence-based methodologies have been proposed. This work offers an ideal approach by a fusion of deep learning classifiers and medical images to provide a speedy and accurate identification of the COVID-19 virus by analyzing the user's CT-Scan images of the lungs. In this work, an adjusted rendition of ResNet101V2 that is improved by a Feature Pyramid Network for classifying the CT scan images into the categories: normal or COVID-19 positive, has been implemented. An accuracy of marginally significant has been obtained by ResNet101V2 with Feature Pyramid Network. The proposed FPN, using the deep learning technique, assured a satisfactory performance in terms of detecting COVID-19 in CT scan and gives a testing accuracy of 97.79%. The predicted results on test-cases are highly accurate using FPN and can assist the medical professionals in making a proper judgment. © 2022 Bharati Vidyapeeth, New Delhi.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach for Maintaining and Mining Frequent Episodes

An Efficient Approach for Maintaining and Mining Frequent Ep...

引用

International Conference on Artificial Intelligence in information and Communication (ICAIIC)

作者： Show-Jane Yen Yue-Shi Lee Dept. of Computer Science & Information Engineering Ming Chuan University Taoyuan Taiwan

Data mining technology plays a crucial role in the area of data analysis. Mining frequent episodes stands out as a pivotal task within this domain, enabling users to forecast future events based on present occurrences. Conventional methods for discovering frequent episodes typically follow a hierarchical approach, involving the generation of candidate episodes and subsequent scanning of sequence data to count their frequency, which can be quite time-consuming, as it necessitates repeated scans of the sequence data and the search for candidate episodes. In this paper, we introduce a novel approach for episode mining in a data stream. Our method distinguishes itself by scanning newly added data to update existing frequent episodes, all without the need for scanning the original data or searching for candidate episodes. The experiments also show that our approach is more efficient compared to other existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Notes Application using Android Studio and Cloud-based Data Management

Notes Application using Android Studio and Cloud-based Data ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Ratnam Dodda Maneesh Reddy Yanala Srija Pavishetti Dept. of Computer Science and Information Technology CVR College of Engineering Hyderabad India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

In today’s rapidly advancing technological land-scape, the widespread adoption of mobile applications has become a defining feature of our digital age. This research study presents a on the development of a mobile notes application using Android Studio, with the primary goal of offering users a versatile platform for creating and managing notes. The proposed notes application is designed with a simple and user-friendly interface, facilitating effortless note creation, editing, and deletion. Moreover, it has features like voice-to-text for making notes, text-to-speech for reading the notes aloud, note sharing for easily sharing ideas with others and image insertion for storing the photocopy of the written notes or diagrams based on user interest. This research work uses Android Studio as the integrated development environment (IDE) and utilizes the Java programming language for the app’s core functionalities. Furthermore, it incorporates Firebase Authentication to ensure secure user account management and the Firestore for Database for seamless storage and retrieval of notes. This research study provides an essential tool for students, professionals, and anyone seeking a convenient means to keep track of vital information. By combining mobile application development tools and cloud-based data management like Firebase, the application simplifies how information is managed, aligning with the way we live in the digital age.

关键词： Cloud computing Visualization Technological innovation Java Operating systems Image processing Speech recognition

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Secure Face Verification Scheme and Its Applications to Digital Surveillance

arXiv

引用

arXiv 2024年

作者： Wang, Huan-Chih Wu, Ja-Ling Dept. Computer Science and Information Engineering National Taiwan University Taipei Taiwan

Face verification is a well-known image analysis application and is widely used to recognize individuals in contemporary society. However, most real-world recognition systems ignore the importance of protecting the identity-sensitive facial images that are used for verification. To address this problem, we investigate how to implement a secure face verification system that protects the facial images from being imitated. In our work, we use the DeepID2 convolutional neural network to extract the features of a facial image and an EM algorithm to solve the facial verification problem. To maintain the privacy of facial images, we apply homomorphic encryption schemes to encrypt the facial data and compute the EM algorithm in the ciphertext domain. We develop three face verification systems for surveillance (or entrance) control of a local community based on three levels of privacy concerns. The associated timing performances are presented to demonstrate their feasibility for practical implementation. © 2024, CC BY.

关键词： Adversarial machine 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：