检索结果-内蒙古大学图书馆

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Sales Prediction Using Machine Learning Models: Integration of PySpark and Power BI

A Comparative Study of Sales Prediction Using Machine Learni...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Sharif, MhD Saeed Tamang, Madhav Theeng Nepal, Anup Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

Retail management requires accurate sales forecasting for strategic planning, inventory control, and revenue maximisation. In this research, we are predicting sales using PySpark-built ML models and the Big Mart dataset. We evaluate and demonstrate the prediction skills of numerous machine learning algorithms, concentrating on XGBoost. Big Mart offers item weight, visibility, type, and outlet data. We use these properties as prediction model features. PySpark, a strong distributed computing platform, manages massive datasets for analysis and model training. In massive trials, we test decision trees (DT), XGBoost, linear regressions (LR), and random forests (RF). Training and testing enhance model accuracy. RMSE and R-squared measure our model quality. Our metrics evaluate the model’s data fit and prediction accuracy. XGBoost performed best with an RMSE of 1081 and an R-squared of 0.59. The XGBoost algorithm accurately predicts Big Mart sales. The model performs well because of its ensemble learning and understanding of intricate dataset links. We also used Power BI to present analytical insights, helping decision-makers design sales-estimated business plans. This study employed several machine learning algorithms, XGBoost gave the best performance. This research provides insights into how organisations might use these technologies to improve resource allocation and inventory management decision-making. ©2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Application of Clustering Algorithms to enhance Personalized Learning through Recommendation Model

Application of Clustering Algorithms to enhance Personalized...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Sharif, Mhd Saeed Tamang, Madhav Theeng Mani, Dyuthi Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

technology and education have recently changed student involvement with learning resources and educational experiences. It is very important to have a platform which can provide personalized learning resources and group students by learning patterns. The research develops recommendation systems and grouping algorithms to help students with their learning patterns and performance measures. To record multidimensional student learning experiences, demographics, learning activities, problem-solving behaviours, and performance measures are extracted and processed. This system makes personalised student suggestions via collaborative filtering, especially Alternating Least Squares (ALS). The model predicts learning materials and problem sets based on student preferences and ability levels by analysing historical student interactions with learning resources. The research also uses clustering methods like K-means clustering to group students with similar learning and performance patterns. Clustering analysis lets instructors discover student group traits and tailor interventions and support techniques. This research also examines temporal relationships in student learning sequences using sequential models. Sequential learning activities and problem-solving behaviour of students help recurrent neural networks (RNNs), or sequential pattern mining algorithms predict their next activities. This research used a huge dataset of over sixteen million exercise logs and applied collaborative filtering (ALS) and K-means clustering to find learning patterns. The ALS-based recommendation system achieved a Mean Squared Error (MSE) of 0.23, showed excellent predictive accuracy. Clustering grouped students by learning behaviours, enabling targeted interventions. This research improves personalised learning using machine learning and data analytics in education. The recommendation system can help instructors tailor training, give individualised support, and boost academic success for various

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Loan Approval: Harnessing the Power of K-Nearest Neighbors for Predictive Eligibility

Revolutionizing Loan Approval: Harnessing the Power of K-Nea...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Sharif, Mhd Saeed Tamang, Madhav Theeng Hussain, Niyas Jaheer Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

A bank has become a basic need of our daily lives. People use banks for several tasks, such as depositing or withdrawing money and borrowing loans. The number of loan applications is rising significantly. It is crucial for the bank and financial sectors to determine loan eligibility and approve loans to suitable applicants only. This study attempts to design a system which can easily predict loan eligibility with the application of several machine learning (ML) algorithms. We employed the five different machine learning algorithms to achieve this research’s aim. These algorithms were trained using the pre-processed dataset to create predictive models. F1 score, accuracy, Recall and Precision are used to evaluate the performance of the proposed approaches. The result showed that K-nearest neighbor (KNN) demonstrated outstanding performance, with an accuracy rate of 88.89%. The Random Forest (RF) model had an accuracy of 84.44%, whereas the Support Vector Machine (SVM) and Linear regression (LR) models achieved 82.22% and 80% accuracy, respectively. The Decision Tree (DT) algorithms showed the worst performance among the five algorithms, with an accuracy of 79.88%. The achievement of this research focuses on the possibility of machine learning algorithms as an efficient method for predicting loan eligibility in banks, contributing to the advancement of financial technology by automating and optimizing key banking processes, reducing processing times, and enhancing overall bank efficiency. ©2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

A Review of Predictive and Contrastive Self-supervised Learning for Medical Images

引用

Machine Intelligence research 2023年第4期20卷 483-513页

作者： Wei-Chien Wang Euijoon Ahn Dagan Feng Jinman Kim Biomedical and Multimedia Information Technology(BMIT)Research Group School of Computer ScienceThe University of SydneySydneyNSW2006Australia College of Science and Engineering James Cook UniversityCairnsQLD4811Australia

Over the last decade, supervised deep learning on manually annotated big data has been progressing significantly on computer vision tasks. But, the application of deep learning in medical image analysis is limited by the scarcity of high-quality annotated medical imaging data. An emerging solution is self-supervised learning (SSL), among which contrastive SSL is the most successful approach to rivalling or outperforming supervised learning. This review investigates several state-of-the-art contrastive SSL algorithms originally on natural images as well as their adaptations for medical images, and concludes by discussing recent advances, current limitations, and future directions in applying contrastive SSL in the medical domain.

关键词： Self-supervised learning(SSL) contrastive learning deep learning medical image analysis computer vision

来源：评论

学校读者我要写书评

暂无评论

Intelligent Internet of Things Attack Detection: Novel Approaches and Technologies

Intelligent Internet of Things Attack Detection: Novel Appro...

引用

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Saeed, Bakhtawar Arshad, Sobia Saeed, Sanay Muhammad Umar Azam, Muhammad Awais Akram, Adeel Gul, Shehla University of Engineering and Technology Taxila Computer Engineering Department Taxila Pakistan Taxila Pakistan School of Information Technology Technology Innovation Research Group Whitecliffe New Zealand

ISBN: (纸本)9798350315974

The Internet of Things (IoT) influences numerous facets of our daily lives, and artificial intelligence (AI)-based programs and applications are rapidly gaining popularity. Due to the vast adaptability of the IoT and the escalating data privacy concerns, classical AI algorithms may not be applicable in certain practical application domains. Federated learning (FL) has emerged as a viable technique for training distributed machine learning (ML) models while maintaining data privacy and security. In recent years, it has gained attention in the context of IoT security, particularly for detecting attacks on IoT devices and networks. In this article, we examine ML and DL in the context of the IoT and IoT attack detection. Then, we evaluate the most recent FL applications in IoT networks and IoT attack detection, investigating their potential to deliver a variety of IoT services, including security and privacy. Our work on detecting FL-IoT attacks has taught us a lot, and at the end, we suggest some directions for future research in this quickly growing field. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Prediction of the Pore-Pressure Built-Up and Temperature of Fire-Loaded Concrete with Pix2Pix

引用

computers, Materials & Continua 2024年第5期79卷 2907-2922页

作者： Xueya Wang Yiming Zhang Qi Liu Huanran Wang Mechanics and Materials Science Research Center Ningbo UniversityNingbo315211China Jinyun Institute Zhejiang Sci-Tech UniversityLishui321400China School of Civil Engineering and Architecture Zhejiang Sci-Tech UniversityHangzhou310018China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China

Concrete subjected to fire loads is susceptible to explosive spalling, which can lead to the exposure of reinforcingsteel bars to the fire, substantially jeopardizing the structural safety and stability. The spalling of fire-loaded concreteis closely related to the evolution of pore pressure and temperature. Conventional analytical methods involve theresolution of complex, strongly coupled multifield equations, necessitating significant computational efforts. Torapidly and accurately obtain the distributions of pore-pressure and temperature, the Pix2Pix model is adoptedin this work, which is celebrated for its capabilities in image generation. The open-source dataset used hereinfeatures RGB images we generated using a sophisticated coupled model, while the grayscale images encapsulate the15 principal variables influencing spalling. After conducting a series of tests with different layers configurations,activation functions and loss functions, the Pix2Pix model suitable for assessing the spalling risk of fire-loadedconcrete has been meticulously designed and trained. The applicability and reliability of the Pix2Pix model inconcrete parameter prediction are verified by comparing its outcomes with those derived fromthe strong couplingTHC model. Notably, for the practical engineering applications, our findings indicate that utilizing monochromeimages as the initial target for analysis yields more dependable results. This work not only offers valuable insightsfor civil engineers specializing in concrete structures but also establishes a robust methodological approach forresearchers seeking to create similar predictive models.

关键词： Fire loaded concrete spalling risk pore pressure generative adversarial network(GAN) Pix2Pix

来源：评论

学校读者我要写书评

暂无评论

AQROM:A quality of service aware routing optimization mechanism based on asynchronous advantage actor-critic in software-defined networks

引用

Digital Communications and Networks 2024年第5期10卷 1405-1414页

作者： Wei Zhou Xing Jiang Qingsong Luo Bingli Guo Xiang Sun Fengyuan Sun Lingyu Meng School of Information and Communication Guilin University of Electronic TechnologyGuilin541004China The 34th Research Institute of China Electronics Technology Group Corporation Guilin541004China Guangxi Key Laboratory of Optical Network and Optical Information Security Guilin541004China State Key Laboratory of Information Photonics and Optical Communications BeijingUniversity of Posts and TelecommunicationsBeijing100876China Department of Electrical and Computer Engineering University of New MexicoAlbuquerqueNM87131USA

In Software-Defined Networks(SDNs),determining how to efficiently achieve Quality of Service(QoS)-aware routing is challenging but critical for significantly improving the performance of a network,where the metrics of QoS can be defined as,for example,average latency,packet loss ratio,and *** SDN controller can use network statistics and a Deep Reinforcement Learning(DRL)method to resolve this *** this paper,we formulate dynamic routing in an SDN as a Markov decision process and propose a DRL algorithm called the Asynchronous Advantage Actor-Critic QoS-aware Routing Optimization Mechanism(AQROM)to determine routing strategies that balance the traffic loads in the *** can improve the QoS of the network and reduce the training time via dynamic routing strategy updates;that is,the reward function can be dynamically and promptly altered based on the optimization objective regardless of the network topology and traffic *** can be considered as one-step optimization and a black-box routing mechanism in high-dimensional input and output sets for both discrete and continuous states,and actions with respect to the operations in the *** simulations were conducted using OMNeT++and the results demonstrated that AQROM 1)achieved much faster and stable convergence than the Deep Deterministic Policy Gradient(DDPG)and Advantage Actor-Critic(A2C),2)incurred a lower packet loss ratio and latency than Open Shortest Path First(OSPF),DDPG,and A2C,and 3)resulted in higher and more stable throughput than OSPF,DDPG,and A2C.

关键词： Software-defined networks Asynchronous advantage actor-critic QoS-aware routing optimization mechanism

来源：评论

学校读者我要写书评

暂无评论

Multi-channel CNN to classify Nepali COVID-19 related tweets using hybrid features

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第3期15卷 2047-2056页

作者： Sitaula, Chiranjibi Shahi, Tej Bahadur Department of Electrical and Computer Systems Engineering Monash University Wellington Rd ClaytonVIC3800 Australia Earth Observation and AI Research Group Department of Infrastructure Engineering The University of Melbourne ParkvilleVIC3010 Australia School of Engineering and Technology Central Queensland University Rockhampton Australia Central Department of Computer Science and Information Technology Tribhuvan University TU Rd Kathmandu Kirtipur44618 Nepal

Because of the current COVID-19 pandemic’s increasing fears among people, it has triggered several health complications such as depression and anxiety. Such complications have not only affected developed countries but also developing countries such as Nepal. These complications can be understood from peoples’ tweets and comments posted online after their felicitous analysis and sentiment classification. Nevertheless, owing to the limited number of tokens and words in each tweet, it is crucial to capture multiple pieces of information associated with them for better understanding. In this study, we, first, represent each tweet by combining both syntactic and semantic information, called hybrid features. The syntactic information is generated from the bag-of-words method, whereas the semantic information is generated from the combination of the fastText-based (ft) and domain-specific (ds) methods. Second, we design a novel multi-channel CNN (MCNN) model, which ensembles the multiple CNNs, to capture multi-scale information for better classification. Last, we evaluate the efficacy of both the proposed feature extraction method and the MCNN model classifying tweets into three sentiment classes (positive, neutral, and negative) on the NepCOV19Tweets dataset, which is the only public COVID-19 tweets dataset in the Nepali language. The evaluation results show that the proposed hybrid features outperform individual feature extraction methods with the highest classification accuracy of 69.7% and the MCNN model outperforms the existing methods with the highest classification accuracy of 71.3% during classification. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： COVID-19

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：