检索结果-内蒙古大学图书馆

2022 International Conference on Electronic Information engineering, Big Data, and computer technology, EIBDCT 2022

作者： Yu, Jing Lang, Yue Li, Xuewen Zhang, Jin Zheng, Shaojie Gong, Jibing School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China Key Laboratory for Software Engineering of Hebei Province Yanshan University Qinhuangdao066004 China

ISBN: (纸本)9781510655133

Explainable recommendation systems, which can produce high-accuracy recommendations and help users make quick decisions, have become a hotspot in research field. Most of existing research algorithms committed to improving the accuracy of recommendation, but ignored the interpretability of recommendation. We propose a semantic recommendation algorithm through Reinforcement Learning and weighted meta-paths which analyzes and selects the meta-path, and uses Reinforcement Learning network to train the weight of meta-path. This method can effectively solve data sparsity, improve the accuracy of recommendation, and increase interpretability. Compared with the baseline method, indicators of the recommended methods for integrating Reinforcement Learning with Heterogeneous Information Networks have been greatly improved, as verified and compared on a real MovieLens 1M dataset. Experimental results prove that the algorithm can effectively improve the accuracy and interpretability of the recommendation. © 2022 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Azerbaijani sign language recognition using machine learning approach 2

Azerbaijani sign language recognition using machine learning...

引用

2nd International Conference on Robotics and Artificial Intelligence, RoAI 2021

作者： Aliyev, Samir Almisreb, Ali Abd Turaev, Sherzod Department of IT Infrastructure Solution R.I.S.K. Company BakuAZ1022 Azerbaijan Department of Computer Science and Engineering International University of Sarajevo Sarajevo71210 Bosnia and Herzegovina Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University Al Ain United Arab Emirates

Sign Language recognition is one of the essential and focal areas for researchers in terms of improving the integration of speech and hearing-impaired people into common society. The main idea is to detect the hand gestures of impaired people and convert them to understandable formats, such as text by leveraging advanced approaches. In this paper, we present our contribution to the improvement of Azerbaijani Sign Language (AzSL). We worked on AzSL Alphabet static signs real-time recognition. The method applied in this work is Object Classification and Recognition by leveraging pre-trained lightweight Convolutional Neural Networks models. At first, a dataset containing near to 1000 images has been collected, then interesting objects on images have been labeled with bounding boxing option. To build, train, evaluate and deploy the relevant model, TensorFlow Object Detection API with Python has been employed. MobileNet v2 pre-trained model has been leveraged for this task. In the trial experiment with four sign classes (A, B, C, E) and 5000 step numbers 15.2% training loss and 83% evaluation mean average precision results have been obtained. In the next step of model deployment experiments with all 24 static signs of AzSL, 49700 and 27700 steps (180 and 100 epochs, respectively) 6.4% and 18.2% training losses, 66.5% and 71.6% mAP outcomes gained, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Research on NetPad Teaching Mode Based on ARCS Motivational Model 17th

Research on NetPad Teaching Mode Based on ARCS Motivational ...

引用

17th International Conference on computer Science and Education, ICCSE 2022

作者： Zhang, Jing Gao, Jinghui Lei, Siran Chen, Ruxian Li, Ya Rao, Yongsheng Institute of Computing Science and Technology Guangzhou University Guangzhou China Software Engineering Institute of Guangzhou Guangzhou China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (纸本)9789819924455

Stimulating and maintaining students’ learning motivation is the key to fully mobilizing the enthusiasm of students’ active participation and realizing the unity of students’ learning and teachers’ teaching. The ARCS motivational model is an instructional design model proposed by Professor Keller that focuses on motivating and sustaining students’ learning motivation. Additionally, NetPad is a web-based dynamic mathematics software with powerful functions and user-friendly interface, it can be organically integrated with teaching, enrich the teaching style, and strengthen students’ learning motivation. In this paper, we propose the NetPad motivational teaching mode based on the ARCS model and NetPad. This mode consists of four procedures: interesting cases introduction, detailed cases explanation, group inquiry, and mutual evaluation and sharing. Each procedure is progressive and complementary, reflecting the hierarchy of motivational teaching from shallow to deep and the synergy of motivation stimulating and maintaining. The teaching practice under the guidance of this mode has verified its effectiveness. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motivation

来源：评论

学校读者我要写书评

暂无评论

Casciff: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks

SSRN

引用

SSRN 2023年

作者： Zhu, Hongjun Yuan, Shun Liu, Xin Chen, Kuo Jia, Chaolong Qian, Ying School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Engineering Research Center of Software Quality Assurance Testing and Assessment Chongqing400065 China School of Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland1010 New Zealand

Utilizing the vast amount of data available online to model and predict this diffusion is of great importance in various fields. Existing approaches for information cascade prediction fall into three main categories: feature-driven methods, point process-based methods, and deep learning-based methods. Among them, deep learning-based methods, characterized by their superior learning and representation capabilities, mitigate the shortcomings inherent in the other ***, current deep learning methods still face several persistent challenges. In particular, accurate representation of user attributes remains problematic due to factors such as fake followers and complex network configurations. Previous algorithms that focused on the sequential order of user activations often neglected the rich insights offered by activation timing. Furthermore, these techniques often fail to holistically integrate temporal and structural aspects, thus missing the nuanced propagation trends inherent in information *** address these issues, we propose the Cross-Domain Information Fusion Framework (CasCIFF), which is tailored for information cascade prediction. This framework exploits multi-hop neighborhood information to make user embeddings robust. When embedding cascades, the framework intentionally incorporates timestamps, endowing it with the ability to capture evolving patterns of information diffusion. In particular, CasCIFF seamlessly integrates the tasks of user classification and cascade prediction into a consolidated framework, thereby allowing the extraction of common features that prove useful for all tasks, a strategy anchored in the principles of multi-task learning. After extensive experiments conducted on publicly available datasets, the results demonstrate CasCIFF’s superiority over established baseline methods in terms of prediction accuracy. © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Defending Against Backdoor Attacks via Region Growing and Diffusion Model

Defending Against Backdoor Attacks via Region Growing and Di...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Haoquan Wang Shengbo Chen Xijun Wang Hong Rao Yong Chen School of Software Nanchang University Nanchang China School of Computer and Information Engineering Henan University Kaifeng China School of Electronics and Information Technology Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

The widespread adoption of deep neural networks (DNNs) is a testament to their profound impact on various domains. However, they are vulnerable to backdoor attacks. Previous defense strategies suffer from requiring additional prior knowledge or performance decreases. To tackle these challenges, we propose a new method to mitigate the impact of backdoor triggers. Specifically, we first devise a simple yet effective detection mechanism based on the region growing algorithm, which enables the identification of triggers within training data without necessitating prior knowledge. Then, we leverage the diffusion model to eliminate the inserted triggers while recovering the data information at the triggers’ locations. Finally, the processed data are fed into the current model for label recovery. Extensive experiments on the CIFAR10, Tiny Imagenet, and GTSRB datasets demonstrate that our method can defend against backdoor attacks effectively and surpasses the state-of-the-art defenses in terms of both main task accuracy (ACC) and backdoor task attack success rate (ASR).

关键词： Analytical models Accuracy Training data Artificial neural networks Diffusion models Data models

来源：评论

学校读者我要写书评

暂无评论

CasCIFF: A Cross-Domain Information Fusion Framework Tailored for Cascade Prediction in Social Networks

arXiv

引用

arXiv 2023年

The explosive growth of the Internet has elevated social networks to a pivotal role in information propagation, reshaping conventional paradigms of information distribution. Utilizing the vast amount of data available online to model and predict this diffusion is of great importance in various fields. Existing approaches for information cascade prediction fall into three main categories: feature-driven methods, point process-based methods, and deep learning-based methods. Among them, deep learning-based methods, characterized by their superior learning and representation capabilities, mitigate the shortcomings inherent in the other methods. However, current deep learning methods still face several persistent challenges. In particular, accurate representation of user attributes remains problematic due to factors such as fake followers and complex network configurations. Previous algorithms that focused on the sequential order of user activations often neglected the rich insights offered by activation timing. Furthermore, these techniques often fail to holistically integrate temporal and structural aspects, thus missing the nuanced propagation trends inherent in information cascades. To address these issues, we propose the Cross-Domain Information Fusion Framework (CasCIFF), which is tailored for information cascade prediction. This framework exploits multi-hop neighborhood information to make user embeddings robust. When embedding cascades, the framework intentionally incorporates timestamps, endowing it with the ability to capture evolving patterns of information diffusion. In particular, CasCIFF seamlessly integrates the tasks of user classification and cascade prediction into a consolidated framework, thereby allowing the extraction of common features that prove useful for all tasks, a strategy anchored in the principles of multitask learning. After extensive experiments conducted on publicly available datasets, the results demonstrate CasCIFF’s superiority over e

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Interactive Web API Recommendation for Mashup Development based on Light Neural Graph Collaborative Filtering

Interactive Web API Recommendation for Mashup Development ba...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jiayan Xiang Wanjun Chen Yang Wang Bowen Liang Zihao Liu Guosheng Kang School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology HNUST Xiangtan China

With the development of Mashup technique, the number of Web APIs released on the Web continues to grow year by year. However, it is a challenging issue to find and select the desirable Web APIs among the large amount of Web APIs. Consequently, interactive Web API recommendation is used to alleviate the difficulty of service selection, when users or developers try to invoke Web APIs for solving their business requirements or software development requirements. Currently, there are several collaborative filtering based approaches proposed for Web API recommendation, while their recommendation performance is limited on both optimality and scalability. This paper proposes a light neural graph collaborative filtering based Web API recommendation approach, named LNGCF. Specifically, LNGCF learns user and item embeddings by linearly propagating them on the user-item interaction graph, and uses the weighted summation of the embeddings learned at all layers as the final embedding. Such simple, linear, and neat model is much easier to implement and train. A set of experiments are conducted on a real-world dataset. Experimental results demonstrate the substantial improvements on both optimality and scalability over the baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Log-Based Anomaly Detection with Inexact Labels via Multi-Instance Learning

Weakly-Supervised Log-Based Anomaly Detection with Inexact L...

引用

International Conference on software engineering (ICSE)

作者： Minghua He Tong Jia Chiming Duan Huaqian Cai Ying Li Gang Huang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China School of Computer Science Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China

ISBN: (数字)9798331505691

ISBN: (纸本)9798331505707

Log-based anomaly detection is essential for maintaining software availability. However, existing log-based anomaly detection approaches heavily rely on fine-grained exact labels of log entries which are very hard to obtain in real-world systems. This brings a key problem that anomaly detection models require supervision signals while labeled log entries are unavailable. Facing this problem, we propose a new labeling strategy called inexact labeling that instead of labeling an log entry, system experts can label a bag of log entries in a time span. Furthermore, we propose MIDLog, a weakly supervised log-based anomaly detection approach with inexact labels. We leverage the multiinstance learning paradigm to achieve explicit separation of anomalous log entries from the inexact labeled anomalous log set so as to deduce exact anomalous log labels from inexact labeled log sets. Extensive evaluation on three public datasets shows that our approach achieves an F1 score of over 85% with inexact labels.

关键词： software Labeling Anomaly detection software engineering

来源：评论

学校读者我要写书评

暂无评论

Rnntcs: A Test Case Selection Method for Recurrent Neural Networks

SSRN

引用

SSRN 2023年

作者： Wu, Xiaoxue Shen, Jinjin Zheng, Wei Lin, Lidan Sui, Yulei Semasaba, Abubakar Omari Abdallah School of Information Engineering Yangzhou University Yangzhou China School of Software Engineering Northwestern Polytechnical University Xi’an China School of Computer Science University of Technology Sydney Sydney Australia

Recurrent Neural Network (RNN) is a typical feedback neural network, which is particularly effective in processing time-series data tasks such as image description, text generation and classification, etc. However, its safety and quality issues have aroused strong concern in academia and industry. One of the most commonly used methods to ensure RNN-driven software quality is testing and optimising RNN. Its core idea is to introduce human efforts to label test cases so that many labelled test cases can be used to trigger faults in RNNs. But this brings a huge overhead. Therefore, it is of great importance to study the test case selection method for RNN. Current research on test case selection for RNN has achieved some results from the stateful view of RNN, but there are still some problems, such as a low bug detection rate, poor inclusiveness, and lack of diversity. In this paper, according to the structural characteristics of RNNs, we propose an RNN test case selection method, RNNtcs, which combines clustering and uncertainty to select test cases that can touch RNN bugs as much as possible, thus reducing the cost of labeling. To evaluate RNNtcs, we conduct experiments on popular image datasets, text datasets and RNN models. The experimental results show that the RNNtcs method is superior to DeepState in bug detection effectiveness, inclusiveness and diversity, and the test cases selected by the RNNtcs method can effectively improve the robustness of RNN models. © 2023, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Data-driven Online Decision Support for Hotel Site Selection 9

Data-driven Online Decision Support for Hotel Site Selection

引用

9th Edition of IEEE Region 10 Humanitarian technology Conference, R10-HTC 2021

作者： Kumarage, Imal Weerakeshara, Nuwanga Chamika, Thanuja Rathnapala, Heshan Nawinna, Dasuni Gamage, Narmada Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Information Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9781665432405

Location is one of the fundamental factors that determine hotel success. The location, once selected, cannot be changed without a significant investment. This research aims to identify the location-specific factors that affect Sri Lankan coastal hotels. The factors that affect the location rating have been assessed under location attraction, accessibility, and popularity. An ensemble learning model has been trained to predict the location score of a hypothetical location, assess the manner accessibility affects hotel performance, and predict location popularity based on the surrounding competition. The results show that this method can assess hotel location and performance, with significant accuracy and the identified location-related factors that contribute to a hotel's success can be used by hoteliers and investors to improve decision making. © 2021 IEEE.

关键词： Location

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：