检索结果-内蒙古大学图书馆

Deep Learning-Based Natural Language Processing Model and Optical Character Recognition for Detection of Online Grooming on Social Networking Services

引用

computer Modeling in Engineering & sciences 2025年第5期143卷 2079-2108页

作者： Sangmin Kim Byeongcheon Lee Muazzam Maqsood Jihoon Moon Seungmin Rho Department of Security Convergence Chung-Ang UniversitySeoul06974Republic of Korea Department of Computer Science COMSATS University IslamabadAtock CampusAttock43600Pakistan Department of Data Science Duksung Women's UniversitySeoul01369Republic of Korea Department of Industrial Security Chung-Ang UniversitySeoul06974Republic of Korea

The increased accessibility of social networking services(SNSs)has facilitated communication and information sharing among ***,it has also heightened concerns about digital safety,particularly for children and adolescents who are increasingly exposed to online grooming *** and accurate identification of grooming conversations is crucial in preventing long-term harm to ***,research on grooming detection in South Korea remains limited,as existing models trained primarily on English text and fail to reflect the unique linguistic features of SNS conversations,leading to inaccurate *** address these issues,this study proposes a novel framework that integrates optical character recognition(OCR)technology with KcELECTRA,a deep learning-based natural language processing(NLP)model that shows excellent performance in processing the colloquial Korean *** the proposed framework,the KcELECTRA model is fine-tuned by an extensive dataset,including Korean social media conversations,Korean ethical verification data from AI-Hub,and Korean hate speech data from Hug-gingFace,to enable more accurate classification of text extracted from social media conversation *** results show that the proposed framework achieves an accuracy of 0.953,outperforming existing transformer-based ***,OCR technology shows high accuracy in extracting text from images,demonstrating that the proposed framework is effective for online grooming *** proposed framework is expected to contribute to the more accurate detection of grooming text and the prevention of grooming-related crimes.

关键词： Online grooming KcELECTRA natural language processing optical character recognition social networking service text classification

来源：评论

学校读者我要写书评

暂无评论

Label Aggregation with Self-Supervision Enhanced Graph Transformer 26

Label Aggregation with Self-Supervision Enhanced Graph Trans...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Liu, Jiacheng Tang, Feilong Hou, Xiaofeng Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Data Science and Engineering East China Normal University Shanghai China

ISBN: (纸本)9781643684369

Aggregating noisy labels produced by the crowd of workers to generate true labels is a challenging problem in crowdsourcing. The key behind label aggregation is to effectively utilize the hidden information (e.g., characteristics of workers and questions which are often missing) in the labeling process. Existing methods mainly generated aggregation models based on the complicated Bayesian model or some strong assumptions. Recently, deep learning-based methods attempt to automate label aggregation but need various labels. These all make them hard to deploy to real-world applications. In fact, abundant information in the process of crowdsourcing itself can be extremely helpful to aggregate the labels. In this paper, we propose ATHENA (lAbel aggregaTion witH sElf-supervision eNhanced grAph transformer) to aggregate labels by utilizing the self-supervision signals in crowdsourcing. Firstly, we propose a transformer-based graph neural network that can learn from the crowdsourcing topology and features. Then, we use self-supervision signals inherently included in the dataset to help to aggregate the labels. To be specific, we identify the answer-based self-supervision signal that can predict the answer of any user given to different tasks. In our evaluations, we compare the proposed ATHENA with the other 11 representative methods on 10 datasets. Our experimental results demonstrate that ATHENA is highly effective in aggregating labels and obtains much better performance than existing methods. © 2023 The Authors.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Mobile Application as Community Social Media 6

Mobile Application as Community Social Media

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Pahlevi, Teuku Ryan Haryanto, Johannes Adha, Rahmat Alfian, Bayu Warnars, Harco Leslie Hendric Spits Widiono, Rahayu Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Binus Online Learning Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798350398496

Today's society is different from the past, where the speed of the internet is getting more sophisticated, and the existing gadget technology is getting faster, and of course, this is also changing the lifestyle of today's people, which of course almost half of their daily life is spent in front of gadgets. On the one hand, this is undoubtedly very good and supports humans in carrying out their daily life activities, but on the other hand, this raises new problems where humans start to lack time to communicate and socialize with each other and often making them stressed and anxious because they are already tired and do not know how to socialize anymore. This paper begins with a model and implementation of a very simple mobile application that behaves as a social media inspired by *** as a social media for academics. The design of this mobile application is done by using use case diagrams to describe existing processes and class diagrams to describe class relationships. © 2023 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Harnessing Insights for Optimizing Healthcare: Disease Prediction and Beyond 5th

Harnessing Insights for Optimizing Healthcare: Disease Predi...

引用

5th International Symposium on Signal and Image Processing, ISSIP 2024

作者： Chatterjee, Soham Gupta, Ritwika Das Latifi, Shpetim Behera, Tapan Kumar Department of Statistics and Data Science CHRIST Deemed to be University Bangalore India Department of Computer Science AAB College Pristina Kosovo Technical Architect Independent Researcher BostonMA United States

ISBN: (纸本)9789819795147

This study offers a novel method for developing classification approaches for disease prediction. Exploratory analysis and meticulous data preprocessing were conducted to understand the relationships between symptoms and illnesses. The research involved assessing various machine learning models, including the random forest classifier, through cross-validation techniques, resulting in the identification of a high-performing model with an impressive accuracy rate. In addition, this study incorporates data visualization techniques to gain insights into symptom–disease connections. The study’s focus on data visualization and optimization strategies in health demonstrates the potential to transform healthcare by providing precise diagnoses and predicting diseases, ultimately improving patient outcomes. This research underscores the efficacy of data-driven techniques and their integration into recommendation and disease prediction systems, emphasizing the significance of data visualization and optimization strategies in health. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorithm 1

Tropical Cyclone Detection and Tracking Using YOLOv8 Algorit...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Rout, Saroja Kumar Kumar, Kottu Santosh Sahu, Ruchismita Barik, Shekharesh Pradhan, Samarendra Department of Information Technology Hyderabad India Department of Artificial Intelligence and Machine Learning Hyderabad India Templecity Institute of Technology and Engineering Department of Computer Science & Engineering Bhubaneswar India DRIEMS University Department of Computer Science & Engineering Cuttack India Data scientist Jayapur Cuttack India

ISBN: (纸本)9798350361780

Coastal areas around the world face a great threat from tropical cyclones, which makes timely and accurate identification essential for efficient disaster response. An enhanced method for detecting tropical cyclones is proposed in this work using the YOLOv8 (You Only Look Once version 8) object identification algorithm. Using the real-time object recognition capabilities of YOLOv8, the methodology is designed to tackle the challenges associated with finding cyclonic structures in satellite data. To detect crucial features typical of tropical cyclones - like cloud formations, circular symmetry, and dynamic atmospheric fluctuations - the YOLOv8 architecture is improved. To ensure its adaptability to different climatic circumstances, the model is trained using a varied dataset of labeled satellite photos. The YOLOv8-based methodology is superior to existing methods in detecting tropical cyclones with accuracy and efficiency almost in real-time, as demonstrated by the experimental results. Because of the algorithm's excellent precision, recall, and computing economy, early warning systems and catastrophe preparedness can benefit greatly from it. This research contributes to the ongoing effort to develop detection approaches for increased resilience in vulnerable coastal areas, while also utilizing YOLOv8's capabilities to address the global threat posed by tropical cyclones. This study can help clarify the necessity of improving models and conducting better observations of Tropical Cyclones. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Exploring Novel CNN Architectures for Deep Learning-Based Liver Tumor Occurrence Prediction

Exploring Novel CNN Architectures for Deep Learning-Based Li...

引用

2023 Intelligent Computing and Control for Engineering and Business Systems, ICCEBS 2023

作者： Kalaiselvi, P. Anusuya, S. Kumaravel, A. Esther, C. Gomathy, G. Aravind, Arun Sri Sairam Engineering College Department of Artificial Intelligence and Data Science India Simats Engineering Department of Computer Science and Engineering India Biher Department of Information Technology India

ISBN: (纸本)9798350394580

According to the authorized findings of,' Hepatocellular carcinoma (HCC)' a common in the human species, liver located, tumor,90 % of its occurrences demand any sort of support for predicting them in advance, if possible. For this purpose, Image Processing, Text Mining, and Deep learning techniques are handled with effective pre-processing methods in the recent research works to improve the results available so far. A majority of contribution by the researchers finds it challenging mostly in selecting suitable architectures for deep learning as most of the previous literature studies show the lacking of details on feasibility and justifiability in specifying the architectures. In this article, it is aimed at the primary goal of such studies as the first attempt on varying architectures in terms of profile and position of layers and observing the performance for recognizing the liver Tumor from the Image-data sets. The CNN architecture of neural network like AlexNet, VGGnet, ResNet, LeNet are standard architectures, based on this liver tumor dataset is implemented in customized architecture and its produced best performance with accuracy of 92.4 %. And It is compared with MeanderHandPD, Breast cancer and Liver Tumor datasets, the proposed architecture shows higher performance for Liver Tumor images. © 2023 IEEE.

关键词： AlexNet DeepLearning4j F-Measure Hepatocellular carcinoma Precision ROC SoftMax VGG

来源：评论

学校读者我要写书评

暂无评论

Disease Diagnosis System Using IoT Empowered with Fuzzy Inference System

引用

computers, Materials & Continua 2022年第3期70卷 5305-5319页

作者： Talha Mahboob Alam Kamran Shaukat Adel Khelifi Wasim Ahmad Khan Hafiz Muhammad Ehtisham Raza Muhammad Idrees Suhuai Luo Ibrahim A.Hameed Department of Computer Science and Information Technology Virtual University of PakistanLahorePakistan School of Information and Physical Sciences The University of NewcastleAustralia Department of Computer Science and Information Technology Abu Dhabi UniversityAbu DhabiUnited Arab Emirates School of Computer Science National College of Business Administration&EconomicsLahorePakistan Sir Syed College of Computer Science University of Engineering and TechnologyLahorePakistan Department of Data Science University of the PunjabLahorePakistan Department of ICT and Natural Sciences Norwegian University of Science and TechnologyTrondheimNorway

Disease diagnosis is a challenging task due to a large number of associated *** in the diagnosis process arises frominaccuracy in patient attributes,missing data,and limitation in the medical expert’s ability to define cause and effect relationships when there are multiple interrelated *** paper aims to demonstrate an integrated view of deploying smart disease diagnosis using the Internet of Things(IoT)empowered by the fuzzy inference system(FIS)to diagnose various *** Fuzzy Systemis one of the best systems to diagnose medical conditions because every disease diagnosis involves many uncertainties,and fuzzy logic is the best way to handle *** proposed system differentiates new cases provided symptoms of the ***,it becomes a time-sensitive task to discriminate symptomatic *** proposed system can track symptoms firmly to diagnose diseases through IoT and FIS smartly and *** coefficients have been employed to predict and compute the identified disease’s severity for each sign of *** study aims to differentiate and diagnose COVID-19,Typhoid,Malaria,and *** study used the FIS method to figure out the disease over the use of given data related to correlating with input *** tool is utilised for the implementation of *** procedure on the aforementioned given data presents that affectionate disease can derive from the *** results of our proposed method proved that FIS could be utilised for the diagnosis of other *** study may assist doctors,patients,medical practitioners,and other healthcare professionals in early diagnosis and better treat diseases.

关键词： Disease diagnosis system COVID-19 healthcare biomedical rules extraction

来源：评论

学校读者我要写书评

暂无评论

Unveiling Patterns, Visualizations, and Trends from Patient Diabetes data 5th

Unveiling Patterns, Visualizations, and Trends from Patient ...

引用

5th International Symposium on Signal and Image Processing, ISSIP 2024

作者： Gupta, Ritwika Das Chatterjee, Soham Latifi, Shpetim Behera, Tapan Kumar Department of Statistics and Data Science CHRIST Deemed to be University Bangalore India Department of Computer Science AAB College Pristina Kosovo Technical Architect Independent Researcher BostonMA United States

ISBN: (纸本)9789819795147

The important role that exploratory data analysis, or EDA, plays in the context of diabetes prediction is explored in this work. EDA is used as a key component of a multimodal strategy to identify unique characteristics linked to diabetes. EDA offers insights that aid in the creation of prediction models by sifting through the complex patterns present in the medical data. The focus is on using EDA to fully grasp the data landscape while also comprehending the distinct features of diabetes. This investigation is critical to accurately categorizing people into discrete risk groups and emphasizes the use of domain-specific knowledge in enhancing diabetes prediction techniques. The research suggests using specific EDA techniques to gain deep insights and lead proactive responses. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biomedical engineering

来源：评论

学校读者我要写书评

暂无评论

Multi-StudentNet: a Semi-supervised Deep-Learning Framework for Endometrial Segmentation in Transvaginal Ultrasound Images

Multi-StudentNet: a Semi-supervised Deep-Learning Framework ...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Peng, Boyuan Liu, Yiyang Zhu, Xin Huang, Jie Wang, Wenwen Fang, Li Zhou, Qin Graduate Department of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Chiyodaku Tokyo Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of Obstetrics and Gynecology Tongji Hospital Huazhong University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9798350350548

Semi-supervised learning (SSL) is a promising solution for the problem of insufficient medical labeled data. However, it is still a challenging task to segment transvaginal ultrasound (TVUS) images because of their poor contrast and speckle noise. In this study, we propose Multi-StudentNet, a semi-supervised deep-learning framework for endometrial segmentation in TVUS images. This method employs multiple student models to effectively integrate labeled and unlabeled data, improving the reliability and performance of segmentation while significantly reducing the need for extensive manual labeling. By leveraging the weights of multiple models, our framework facilitates feature sharing, which enhances model robustness. Specifically, Multi-StudentNet achieves a Dice coefficient (DSC) of 0.81 and a specificity of 0.99. Our multi-student models consistently outperform single-student models across various conditions, including normal, polyp, and cancer cases. Extensive experiments demonstrate that Multi-StudentNet achieves state-of-the-art performance in both accuracy and robustness. © 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

Dynamic Task Offloading and Service Migration Optimization in Edge Networks

引用

International Journal of Crowd science 2023年第1期7卷 16-23页

作者： Han, Yibo Li, Xiaocui Zhou, Zhangbing Nanyang Institute of Big Data Research Nanyang Institute of Technology Nanyang473004 China Beijing100083 China Computer Science Department TELECOM SudParis Evry 91000 France

In recent years, edge computing has emerged as a promising paradigm for providing flexible and reliable services for Internet of things (IoT) applications. User requests can be offloaded and processed in real time at the edge of a network. However, considering the limited storage and computing resources of IoT devices, certain services requested by users may not be configured on current edge servers. In this setting, user requests should be offloaded to adjacent edge servers or requested edge servers should be configured by migrating certain services from the former, further reducing the service access delay of user requests and the energy consumption of IoT devices in such networks. To address this issue, in this study, we model this dynamic task offloading and service migration optimization problem as the multiple dimensional Markov decision process and propose a deep q-learning network (DQN) algorithm to achieve fast decision-making, an approximate optimal task offloading, and service migration solution. Experimental results show that our algorithm performs better than existing baseline approaches in terms of reducing the service access delay of user requests and the energy consumption of IoT devices in edge networks. © The author(s) 2023. The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://***/licenses/by/4.0/).

关键词： Reinforcement 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：