检索结果-内蒙古大学图书馆

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Cleaver, Nathan Neshatian, Kourosh University of Canterbury Department of Computer Science and Software Engineering Christchurch New Zealand

ISBN: (纸本)9798350341072

Transfer learning is the ability to transfer knowledge from one context to another. This paper investigates, for the first time, the possibility of transfer learning on Monte Carlo Tree Search (MCTS). We use distributed parallel MCTS to construct game-playing models for one variant of chess and then transfer these models to another domain to play a different variant of chess. We also introduce a novel pruning mechanism for MCTS to cope with memory requirements of large game trees. Our results show that positive transfer learning in MCTS is possible, and in our case, highly successful. Transferred models significantly outperform models that have to be trained from scratch. © 2023 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Based on feature reconstruction and feature intersection, the Deep CTR Prediction Model 2

Based on feature reconstruction and feature intersection, th...

引用

2nd International Conference on Big Data, Information and computer Network, BDICN 2023

作者： Bian, Ning Wang, Li University of Science and Technology Liaoning College of Computer and Software Engineering Anshan China

ISBN: (纸本)9798350321364

Collecting a lot of feature data can enhance the prediction impact for the recommender system's CTR prediction task. The second-order feature cross factorization machine model, which is the most popular, has the ability to automatically learn implicit features based on existing features. The factorization machine model, however, has the following issues: (1) The encoding is fixed, and the same feature represents the same in various contexts. (2) The encoding type is single, and the feature is represented by a single weight vector, which cannot completely express the information of the feature. To harvest possible feature information, recommender systems employ neural networks. A novel method of feature intersection is created by the Compressed Interaction Network (CIN) component suggested in xDeepFM. In order to address the issue of encoding fixation in the factorization machine, the original feature encoding is reconstructed in this paper using xDeepFM in conjunction with the feature refinement network (FRNet). Additionally, different feature representations are expressed in various contexts for the same feature. To address the issue of a single encoding type in factorization machines, the field-aware interactive machine (FIM) component provides feature information at the domain and feature levels, respectively. The model is known as the Field-aware Feature Refinement Depth Factorization Machine (FRDFFM). On the Criteo dataset and the Avazu dataset, respectively, the suggested model was evaluated, and it produced promising results. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

20 Years of EPICS at Butler University: Experiences and Lessons Learned 53

20 Years of EPICS at Butler University: Experiences and Less...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Johnson, Lucas Linos, Panagiotis Butler University Computer Science and Software Engineering Department IndianapolisIN United States

ISBN: (纸本)9798350336429

This research-to-practice full paper discusses experiences and lessons learned from our EPICS@BUTLER (engineering Projects in Community Service at Butler) program. The program, housed within the department of computer science and software engineering, is part of a college of Liberal Arts and sciences and serves a diverse population of students with multi-disciplinary backgrounds. The EPICS curriculum is driven by a team-based service-learning pedagogical model. EPICS teams learn how to work together effectively while addressing the immediate IT needs of our non-profit partner clients, navigating their budgetary restrictions, and coping with any lack of existing IT infrastructure. During the 2020/2021 academic year, we launched an empirical study to review and assess EPICS@BUTLER. The study's main goal was to learn from the past 20 years of running the EPICS program by soliciting input from all parties involved. We aimed to improve and expand our service-learning model within an LAS context. More specifically, this study included surveying alumni and current undergraduate students in order to understand the successes and areas of potential improvement within our program. In addition, we conducted one-on-one interviews with our community non-profit partners as well as volunteer team mentors to assess the program's effectiveness and community impact. Based on the empirical data we gathered and analyzed, we discuss how the existing curriculum is effective at providing fulfilling experiences which help our alumni secure jobs after graduation. In addition, we found that the practice of allowing supervised teams to navigate their own EPICS projects helps them improve their professional maturity and interpersonal skills. In summary, this paper discusses an empirical study and aims to leverage the results gathered from our surveys and interviews in order to present a plan for continuous improvement and modernization of our on-going EPICS program. In closing, our paper descri

关键词： Course assessment EPICS Service-Learning software engineering Teamwork

来源：评论

学校读者我要写书评

暂无评论

Use of Audience Response Systems to Enhance Student Engagement in Online Synchronous Environments: An Exploratory Study 27

Use of Audience Response Systems to Enhance Student Engageme...

引用

27th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2023

作者： Nesbit, Trevor Department of Computer Science and Software Engineering University of Canterbury Christchurch New Zealand

ISBN: (纸本)9781713880325

Many higher education institutions adapted to the Covid-19 pandemic by switching their teaching into online mode making use of online synchronous sessions using technologies such as Zoom. It was common for lecturers to find it disconcerting that many students were not turning on their cameras and microphones and how this made it difficult to ascertain whether their students were engaged in the sessions at all. This paper examines the experiences of teaching staff in eight courses relating to the use of audience response systems (ARS) to improve the experiences of students and teaching staff when conducting synchronous online teaching sessions or hybrid sessions when they had some face-face students and some online students joining sessions synchronously. Literature is examined that shows the benefits relating to the use of ARS in synchronous online teaching sessions to include anonymity of student responses;enhancement of feedback between teaching staff and students;and teaching staff getting a better sense of student engagement during a session. An analysis of the eight cases presented confirms these benefits in the literature from the perspective of the teaching staff. The findings apply irrespective of the ARS being used and will be of relevance and interest to any teaching staff seeking to improve the experiences of students and teaching staff involved in synchronous online teaching sessions. © 2023 Proceedings of World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Camera Calibration Algorithms for Football Applications 4

Comparative Analysis of Camera Calibration Algorithms for Fo...

引用

4th International Workshop on Information Technologies: Theoretical and Applied Problems, ITTAP 2024

作者： Sorokivskyi, Oleksandr Hotovych, Volodymyr Nazarevych, Oleg Shymchuk, Grygorii Department of Computer Science Faculty of Computer Information Systems and Software Engineering Ternopil Ivan Puluj National Technical University Ternopil Ukraine

In solving the problem of automated analysis of football match video recordings, special video cameras are currently used. This work presents a comparative characterization of known algorithms and methods for video camera calibration, including those utilizing machine learning and neural networks, with the aim of identifying their shortcomings and forming a theoretical foundation for developing modern, more effective methods and algorithms. Specifically, it examines both algorithms that require more input data but operate quickly [1, 2] and more accurate algorithms using machine learning [3, 4, 5, 6, 5]. It is demonstrated that their main drawback is either accuracy or speed. More accurate algorithms using machine learning often do not specify the algorithm's operational speed, which precludes their use in real-time applications. The examined works that emphasize speed frequently lack the accuracy necessary for practical use in real-life scenarios. Copyright © 2024 for this paper by its authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust steganographic approach using generative adversarial network and compressive autoencoder

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Qasaimeh, Malik Qtaish, Alaa Abu Aljawarneh, Shadi Department of Computer Information Systems Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan Department of Software Engineering co-joint with the Department of Cyber Security Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan

Nowadays, social media applications and websites have become a crucial part of people’s lives;for sharing their moments, contacting their families and friends, or even for their jobs. However, the fact that these valuable data are transferred via the Internet and open channels, which are vulnerable to attacks and espionage, requires using defense methods to improve the security of data transmission. Recently, the progress of Deep Learning (DL) inspired researchers to use it with security methods such as steganography, the art of hiding secret data in unrelated content. DL and steganography combined enhanced the hiding properties, especially in the Coverless Image Steganography (CIS) methods. In this paper, we propose a Compressive Coverless Image Steganography (CCIS) model, which is a generated-based CIS, to improve the capacity and robustness of Steganography. This model uses the compressive autoencoder to compress the message, thus increasing the capacity, and uses the Generative Adversarial Network (GAN) to generate a stego image from the compressed vector, thus enhancing concealment ability, besides using a regression model and optimization method to extract the data. Another version was designed to enable sending binary messages by replacing the compressive autoencoder network with a robust mapping rule. Experiments show that the proposed model could improve the characteristics of Steganography. Furthermore, the proposed model could extract binary messages with 256 bits from attacked stego images with 99% recovery accuracy. Thus, capacity and robustness were enhanced using our model with both images and text as secret messages. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Federated Reinforcement Learning for Sharing Experiences Between Multiple Workers

Federated Reinforcement Learning for Sharing Experiences Bet...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Feng, Wenliang Liu, Han Peng, Xiaogang College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9798350303780

Reinforcement learning has been successfully applied in various fields, such as games and robots. However, there are still some issues in the traditional reinforcement learning paradigm that involves one agent per environment, such low efficiency in data generation and insufficient amount of training data. In this paper, we propose a federated reinforcement learning framework that utilizes multiple agents to generate data for simultaneous training of models. Specifically, the proposed framework allows the best performing agent to share its learning experience with other agents for improving the learning performance and protecting the privacy of agents. The proposed framework is applied to the Cart-pole, Acrobot and LunarLander environments in OpenAI Gym, and the results show that a significant improvement of the learning performance can be achieved by adopting our framework. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Recent Advancements and Challenges in Multimodal Sentiment Analysis: A Survey

Recent Advancements and Challenges in Multimodal Sentiment A...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Dong, Zhen-Xun Liu, Han College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9798350303780

Sentiment analysis aims to extract people's underlying attitudes, opinions and thoughts toward various topics, products and services. Sentiment analysis is a popularly adopted technique that involves applications across domains such as business, healthcare, government and marketing. Traditional sentiment analysis methods mainly focus on text contents. However, recent technological advancements have enabled the expression of opinions through different forms of media, such as images or audios, leading to sentiment analysis using multiple modalities rather than text alone. Multimodal sentiment analysis results in a more comprehensive understanding of the emotions and opinions expressed in a given content by combining information from different modalities. A model of multimodal sentiment analysis involves three main parts, namely, unimodal feature extraction, multimodal fusion and sentiment polarity prediction. This paper provides a comprehensive overview of multimodal fusion methods along with their corresponding model architectures. Moreover, several more recently released models are introduced and the strengths and limitations of these models are discussed comparatively. Finally, some challenges and future research directions are identified. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Ingenious IoT Based Crop Prediction System Using ML and EL

引用

computers, Materials & Continua 2024年第4期79卷 183-199页

作者： Shabana Ramzan Yazeed Yasin Ghadi Hanan Aljuaid Aqsa Mahmood Basharat Ali Department of Computer Science&IT Government Sadiq CollegeWomen UniversityBahawalpur63100Pakistan Department of Computer Science/Software Engineering Al Ain UniversityAl Ain64141UAE Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman University(PNU)Riyadh11671Saudi Arabia Agronomic Research Station Bahawalpur63100Pakistan

Traditional farming procedures are time-consuming and expensive as based on manual labor. Farmers haveno proper knowledge to select which crop is suitable to grow according to the environmental factors and soilcharacteristics. This is the main reason for the low yield of crops and the economic crisis in the agricultural sectorof the different countries. The use of modern technologies such as the Internet of Things (IoT), machine learning,and ensemble learning can facilitate farmers to observe different factors such as soil electrical conductivity (EC),and environmental factors like temperature to improve crop yield. These parameters play a vital role in suggestinga suitable crop to cope the food scarcity. This paper proposes a systemcomprised of twomodules, first module usesstatic data and the second module takes hybrid data collection (IoT-based real-time data and manual data) withmachine learning and ensemble learning algorithms to suggest the suitable crop in the farm to maximize the *** is used to train the model that predicts the crop. This system proposed an intelligent and low-cost solutionfor the farmers to process the data and predict the suitable *** implemented the proposed system in the *** efficiency and accuracy of the proposed system are confirmed by the generated results to predict the crop.

关键词： Machine learning Internet of Things sensors ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Topic Interpretability for Neural Topic Modeling Through Topic-Wise Contrastive Learning 40

Enhancing Topic Interpretability for Neural Topic Modeling T...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Gao, Xin Lin, Yang Li, Ruiqing Wang, Yasha Chu, Xu Ma, Xinyu Yu, Hailong Software Engineering Institution School of Computer Science Peking University Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Beijing China Peking University National Engineering Research Center of Software Engineering Beijing China School of Computer Science Center on Frontiers of Computing Studies Peking University China

ISBN: (纸本)9798350317152

Data mining and knowledge discovery are essential aspects of extracting valuable insights from vast datasets. Neural topic models (NTMs) have emerged as a valuable unsupervised tool in this field. However, the predominant objective in NTMs, which aims to discover topics maximizing data likelihood, often lacks alignment with the central goals of data mining and knowledge discovery which is to reveal interpretable insights from large data repositories. Overemphasizing likelihood maximization without incorporating topic regularization can lead to an overly expansive latent space for topic modeling. In this paper, we present an innovative approach to NTMs that addresses this misalignment by introducing contrastive learning measures to assess topic interpretability. We propose a novel NTM framework, named ContraTopic, that integrates a differentiable regularizer capable of evaluating multiple facets of topic interpretability throughout the training process. Our regularizer adopts a unique topic-wise contrastive methodology, fostering both internal coherence within topics and clear external distinctions among them. Comprehensive experiments conducted on three diverse datasets demonstrate that our approach consistently produces topics with superior interpretability compared to state-of-the-art NTMs. © 2024 IEEE.

关键词： Data mining

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：