检索结果-内蒙古大学图书馆

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Karuppasamy, ArunaDevi Oman College of Management and Technology Department of Computer Science and Management Information System Muscat Oman

ISBN: (纸本)9798350335095

Breast cancer is one of the most common type of cancer affecting women worldwide, and a leading cause of cancer-related deaths. Histopathology image analysis plays a vital role in breast cancer diagnosis. Early diagnosis and accurate classification of breast cancer histopathology images can help for effective treatment. In recent years, deep learning-based image classification methods have shown promising results in automated breast cancer diagnosis. Earlier, Convolutional Neural Network(CNN) had a huge attention in image classification tasks, and also obtained a good performances in histopathology image classification. Recently, Vision Transformer (ViT) based on self-attention mechanism has shown promising results in computer vision tasks, including image classification. In this paper, we review recent ViT-based model for breast cancer histopathology image classification. Furthermore, we summarize the results obtained from our experiments with both CNN and ViT-based models in breast cancer histopathology image classification. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Combating Digital Deception: Machine Learning Approaches for Detecting Political Misinformation and Clickbait on Social Media 6

Combating Digital Deception: Machine Learning Approaches for...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Harindi, Dewmini Perera, Nirmal Liyanage, Chamath Dematagoda, Hirushini Fernando, Harinda Rathnayake, Samadhi Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798331517878

This paper presents machine learning-based strategies for mitigating the problem of misinformation in social media, with a special focus on political misinformation detection and clickbait detection. The following research work attempts to address the pressing issue of the rapid spread of false or misleading information by making use of deep recurrent neural networks (RNN s) combined with semi-supervised learning methodologies. For political misinformation detection, a hybrid model integrating Long Short-Term Memory (LSTM) networks with fully connected layers was developed, achieving 94.22 % accuracy on the CIC Truth Seeker dataset. Clickbait detection was made using a sequential architecture that combines LSTM and Gated Recurrent Units (GRU) layers with Simple RNN layers to achieve an accuracy of 96% on test data. This study underlines the effectiveness of different machine learning techniques in battling misinformation that would contribute to online dignity in political discourse and ensure better public communication in a digital world. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Improving Route-Finding Performance of Dijkstra Algorithm and Maintaining Path Visual Cue Using Douglas-Peucker Algorithm 23

Improving Route-Finding Performance of Dijkstra Algorithm an...

引用

8th International Conference on Sustainable information Engineering and technology, SIET 2023

作者： Pinandito, Aryo Kharisma, Agi Putra Akbar, Muhammad Aminul Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia Media Game and Mobile Technology Laboratory Information System Department Faculty of Computer Science Universitas Brawijaya Malang Indonesia

ISBN: (纸本)9798400708503

Smartphones and their mobile applications have become an inseparable part of modern daily life. One of them is a public transportation app that helps people commute with public transportation. Many public transportation service providers have mobile applications as a companion for their customers to improve their quality of service. The application provides useful information and/or important features regarding their service, such as timetables or route finding for public transit. Such features run a slow algorithm to provide real-time or time-based information to the users. Dijkstra is one example of an algorithm that allows users to find the shortest path from one location to another in a public transit network. However, Dijkstra is categorized as a greedy algorithm because it looks at all possible solutions. It takes longer for Dijkstra to find the optimum solution when the number of points in a network graph is high. This study attempted to improve the overall route-finding processing time and reduce the memory footprint while keeping the visual cue of a route path reasonably consistent by utilizing Douglas-Peucker line simplification algorithm to simplify the path and reduce the number of points that Dijkstra algorithm processes. The result suggested that Douglas-Peucker simplification process took 0.5% additional memory footprint and put 5.13% additional processing time into the overall route-finding processing time. However, it reduces the overall memory footprint and processing time by 72.56% and 80.83%, respectively. The result conveyed a significant improvement in the practical implementation of Douglas-Peucker algorithm to reduce the input for the Dijkstra algorithm in finding the optimal route, thereby improving the overall route-finding performance. © 2023 ACM.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Sagittarius: Floating Self Navigating Robot for Monitor the Water Quality of Rural Reservoirs 6

Sagittarius: Floating Self Navigating Robot for Monitor the ...

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Pedige, Nishan Ilandara Abeywarna, Thaveesha Amarasinge, Randheera Bandara, Menuka Nawarathna Javakody, Anuradha Gamage, Narmada Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka

ISBN: (纸本)9798331517878

This paper proposes an optimal solution for monitoring water quality in Sri Lanka, where reservoirs are essential for daily life and agriculture, especially in rural areas. Despite its importance, 3.6 million communities are affected by severe water quality problems, contributing to a high incidence of chronic kidney diseases. While water purification plants are the only solution, high salinity and hardness often make these sources unsuitable. Many rural reservoirs remain unpurified but could potentially provide safe water if properly monitored and maintained. Yet water sources are frequently contaminated by chemical waste and activities associated with agricultural business but effective solutions for continuous water quality monitoring are lacking. This study introduces an autonomous robot equipped with advanced sensors to monitor critical water quality parameters in real-time. By integrating machine learning for data analysis and prediction, Sagittarius enables continuous assessment of reservoir water quality, providing timely insights for public health protection. Field tests demonstrate a prediction accuracy exceeding 98.5%, supporting proactive water management and monitoring. This system has shown potential to aid in early detection of contamination, informing authorities promptly for preventive actions, and enabling sustainable water usage. This solution can significantly contribute to public health protection and informed water resource management decisions. © 2024 IEEE.

关键词： Reservoirs (water)

来源：评论

学校读者我要写书评

暂无评论

Matched design method for concatenated trellis-coded modulation

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND computer SCIENCES 1996年第11期E79A卷 1911-1917页

作者： Wadayama, T Wakasugi, K Kasahara, M Faculty of Computer Science and System Engineering Okayama Prefectural University Soja-shi 719-11 Japan Department of Electronics and Information Science Kyoto Institute of Technology Kyotoshi 606 Japan

A new design method, which is referred to as the matched design method, for concatenated trellis-coded modulation (TCM) is presented. Most of the conventional concatenated TCM employs TCM designed to maximize the minimum squared Euclidean free distance, d(free)(2). With the matched design method, we maximize d(1)(2)(t) instead of d(free)(2), where d(1)(2)(t) is the effective minimum squared Euclidean distance (MSED) when the outer code has a t-error correcting capability. The effective MSED is derived from the Euclidean/Hamming (E/H) joint weight distribution of terminated TCM. We here assume the concatenated TCM whose transmitted symbol corresponds to a symbol of outer code. The new classes of 2-dimensional(2D) and 4-dimensional(4D) codes are found by a computer search. Under the performance measures of the effective MSED or the effective multiplicity, these codes are superior to the conventional codes such as the Ungerboeck's 2D-codes when those are used as an inner code. We disclose an interesting fact that the new class of codes using rate-1/2 encoder is superior to the class of codes using rate-2/3 encoder. This fact implies that the codes using rate-1/2 encoder have two advantages: 1) better overall decoding performance and 2) less decoding complexity.

关键词： trellis-coded modulation concatenated code weight distribution

来源：评论

学校读者我要写书评

暂无评论

Cluster-Based Saliency-Guided Content-Aware Image Retargeting

引用

Journal of Electronic Science and technology 2017年第2期15卷 141-146页

作者： Li-Wei Kang Ching-Yu Tseng Chao-Long Jheng Ming-Fang Weng Chao-Yung Hsu Graduate School of Engineering Science and Technology and the Department of Computer Science and Information Engineering MPI Corporation Hsinchu Changing Information Technology Inc.Hsinchu 308 Institute for Information Industry Taipei 106 automation and Instrumentation System Development Sec. China Steel CorporationKaohsiung 81233

Straightforward image resizing operators without considering image contents （e.g., uniform scaling） cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content- aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.

关键词： Index Terms--Content-aware image retargeting image resizing multimedia adaptation saliency detection seam carving.

来源：评论

学校读者我要写书评

暂无评论

Flood alerts system with android application 6

Flood alerts system with android application

引用

6th ICT International Student Project Conference, ICT-ISPC 2017

作者： Napiah, Mohamad Nazrin Idris, Mohd Yamani Idna Ahmedy, Ismail Asri Ngadi, Md. Department of Computer System & Technology Faculty of Computer Science & Information Technology University of Malaya Malaysia Department of Computer Science Faculty of Computing Universiti Teknologi Malaysia Malaysia

ISBN: (纸本)9781538629963

Internet of things (IoT) is technology that connected anything and everything to the Internet. IoT is the newest technology rapidly widen in its usage. This technology brings new products such as disaster monitoring. Flood disaster is the main concern in Malaysia because every year there are flood occurred. We can use this technology to do monitoring activity that people are not able to do it in 24 hours and inform to the user in real time. In this paper, we propose IoT approach that known as flood alerts system with Android application. This system will monitor the potential drainage usually occur flooding and share the info in real time to people nearby. © 2017 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Behavior Relativity of Petri Nets

引用

Journal of computer Science & technology 2002年第6期17卷 770-780页

作者：蒋昌俊王怀清廖少毅 Department of Computer Science and Engineering Tongji University Shanghai 200092 P.R. ChinaThe School of Information Science and Engineering Ningbo University Ningbo 315211 P.R. ChinaDepartment of Computer Science and Technology University of Sha Department of Information System City University of Hong Kong Kowloon Hong Kong P.R. China

This paper presents a novel methodology for modelling and analyzing of behav-ior relations of concurrent systems. The set of all firing sequences of a Petri net is an importanttool for describing the dynamic behavior of concurrent systems. In this paper, the behaviorrelativity of two concurrent subsystems in their synchronous composition is presented. Such be-havior relativities, including Controlled Relativity, United Relativity, Interactive Relativity andExclusive Relativity, are defined respectively. The properties of the relativities are discussed indetail. The analysis method for these properties is based on minimum T-invariants, when twosubsystems are live bounded Petri nets. A well-known example has also been analyaed usingthe new methodology to demonstrate the advantages of the proposed methodology.

关键词： Petri网行为相对性系统分析

来源：评论

学校读者我要写书评

暂无评论

Cluster-preserving sampling algorithm for large-scale graphs

引用

Science China(information Sciences) 2023年第1期66卷 60-76页

作者： Jianpeng ZHANG Hongchang CHEN Dingjiu YU Yulong PEI Yingjun DENG National Digital Switching System E&T Research Center Information Engineering University Network Systems Department of the Strategic Support Force School of Computer Science and Technology Eindhoven University of Technology Center for Applied Mathematics Tianjin University

Graph sampling is a very effective method to deal with scalability issues when analyzing largescale graphs. Lots of sampling algorithms have been proposed, and sampling qualities have been quantified using explicit properties(e.g., degree distribution) of the sample. However, the existing sampling techniques are inadequate for the current sampling task: sampling the clustering structure, which is a crucial property of the current networks. In this paper, using different expansion strategies, two novel top-leader sampling methods(i.e., TLS-e and TLS-i) are proposed to obtain representative samples, and they are capable of effectively preserving the clustering structure. The rationale behind them is to select top-leader nodes of most clusters into the sample and then heuristically incorporate peripheral nodes into the sample using specific expansion strategies. Extensive experiments are conducted to investigate how well sampling techniques preserve the clustering structure of graphs. Our empirical results show that the proposed sampling algorithms can preserve the population's clustering structure well and provide feasible solutions to sample the clustering structure from large-scale graphs.

关键词： graph sampling clustering structure top-leader nodes expansion strategies large-scale graphs

来源：评论

学校读者我要写书评

暂无评论

AI-Based Child Care Parental Control system 4

AI-Based Child Care Parental Control System

引用

4th International Conference on Advancements in Computing, ICAC 2022

作者： Jayasekara, Udara Maniyangama, Hansindu Vithana, Kalhan Weerasinghe, Tharana Wijekoon, Janaka Panchendrarajan, Rrubaa Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Sri Lanka Department of Computer System Engineering Sri Lanka Institute of Information Technology Sri Lanka

ISBN: (纸本)9798350398090

Due to the prevalence of the COVID-19 epidemic around the globe, children were compelled to engage in remote learning through online platforms, hence mobile phone has become one of their predominant devices. Mobile device with Internet access offers a major outlet for education, entertainment, and social connection, but this combination can lead to several significant bad sequences such as online exploitation, harmful addictions, and other negative impacts of online social networking. To address harmful effects, parental controls are becoming more crucial, yet Sri Lankan parents are less aware of this. Consequently, this study proposes a parental control system to monitor their child's activities. Android, Microsoft Azure, Java, Python, OpenCV, MySQL, and FastAPI are among the most prominent technologies utilized in the proposed application's development. The suggested approach focuses primarily on the Sri Lankan context and aims to enhance parental digital literacy while safeguarding children from cyber threats. Yielded results showed the proposed mobile application for the identification of toxic words, drugs & alcohol content, game character images, and Instagram Sinhala comments severity as 94%, 95%, 97%, and 55% respectively in controlled experiments. © 2022 IEEE.

关键词： Control systems

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：