检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Chenyang Zou, Difan Cao, Yuan Department of Statistics and Actuarial Science School of Computing and Data Science The University of Hong Kong Hong Kong Department of Computer Science School of Computing and Data Science Institute of Data Science The University of Hong Kong Hong Kong Department of Statistics and Actuarial Science School of Computing and Data Science Department of Mathematics The University of Hong Kong Hong Kong

Adam has become one of the most favored optimizers in deep learning problems. Despite its success in practice, numerous mysteries persist regarding its theoretical understanding. In this paper, we study the implicit bias of Adam in linear logistic regression. Specifically, we show that when the training data are linearly separable, the iterates of Adam converge towards a linear classifier that achieves the maximum ∞-margin in direction. Notably, for a general class of diminishing learning rates, this convergence occurs within polynomial time. Our result shed light on the difference between Adam and (stochastic) gradient descent from a theoretical perspective. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal Knowledge Extrapolation Based on Fine-Grained Tensor Graph Attention Network for Responsible AI

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第2期6卷 448-457页

作者： Yang, Jing Huang, Chengxuan Yang, Xiangli Yang, Laurence T. Gao, Yuan Liu, Cong Zhengzhou University School of Computer Science and Artificial Intelligence Zhengzhou570001 China Duke University Graduate School Department of Computer Science DurhamNC27708 United States Dublin Institute of Technology School of Tourism and Hospitality Management Dublin9P3C+W7 Ireland Hainan University School of Computer Science and Technology Haikou570228 China St. Francis Xavier University Department of Computer Science AntigonishNSB2G 2W5 Canada Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China

Knowledge guidance is crucial for bridging the gap between high-level artificial intelligence (AI) ethics principles and the practical implementation of responsible AI systems. Diverging from static knowledge inference and temporal interpolation, the task of temporal knowledge extrapolation, which entails predicting future facts based on the evolution of historical facts, poses formidable challenges that remain largely unsolved. In existing temporal extrapolation methods, the structural learning of concurrent facts is primarily addressed by utilizing relation-aware graph neural networks. However, the temporal validity of facts leads to the sparsity of temporal subgraphs, where inherent coarse-level learning mechanisms hinder the capture of nuanced and scarce local semantics. Thus, this article proposes a fine-grained tensor graph attention network (F-GAT) that promotes representation learning of concurrent facts on sparse subgraphs by effectively distinguishing the significance of entities and relations within triplets and acquiring self-attention across diverse triplet contexts. Based on F-GAT, this article proposes a recurrent evolution network [recurrent evolution graph attention network (RE-GAT)] for temporal knowledge extrapolation. RE-GAT employed gated recurrent units to iteratively capture the sequential patterns between adjacent temporal facts, while simultaneously learning enriched embedding through the dual influence of historical factors and structural factors. The competitive results achieved by comparing the entity and relationship prediction performance of the proposed RE-GAT model with advanced methods on six public benchmarks demonstrate the effectiveness of RE-GAT for temporal extrapolation. © 2020 IEEE.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Comprehensive analysis of various imputation and forecasting models for predicting PM2.5 pollutant in Delhi

引用

Neural Computing and Applications 2025年 1-18页

作者： Karnati, Hemanth Soma, Anuraag Alam, Adnan Kalaavathi, B. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of IoT School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India

Understanding and predicting air quality is pivotal for public health and environmental management, especially in urban areas like Delhi. This study utilizes a comprehensive dataset from the Central Pollution Control Board, detailing air pollutant concentrations at the ITO (Income Tax Office), Delhi station, from 2017 to 2023. Our focus on pollutants such as PM2.5, PM10, NO2, NH3, SO2, ozone, and CO highlights the challenges posed by missing data in environmental studies. Through the application of several imputation models, including KNN, linear regression, forward fill + backward fill, Fourier + KNN, linear interpolation, and statistical methods, we identified combination of forward fill and backward fill as the most effective method for addressing data gaps, specifically for ozone measurements. Building on this imputed dataset, we employ various forecasting models to predict PM2.5 levels, a critical pollutant. Our exploration includes time series and deep learning approaches, such as LSTM, Bi-LSTM, CNN-LSTM, GRU, Deep AR, WaveNet, TCN, ARIMA, SARIMA, and Prophet. The performance of these models is evaluated using daily data, with Bi-LSTM and LSTM with attention emerging as the top performers due to their accuracy in predicting PM2.5 concentrations. The implications of our findings extend beyond academic interest, offering practical insights for environmental policy and health advisories in Delhi. By demonstrating the efficacy of specific imputation and forecasting techniques, our research contributes to the broader effort of improving air quality monitoring and prediction. The success of Bi-LSTM and LSTM with attention models, in particular, suggests a promising avenue for future studies aiming to enhance the precision of environmental forecasts. © The Author(s) 2025.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Smart Air Monitoring with IoT-based MQ-2, MQ-7, MQ-8, and MQ-135 Sensors using NodeMCU ESP32 9th

Smart Air Monitoring with IoT-based MQ-2, MQ-7, MQ-8, and MQ...

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Easterline, Laurent Michelle Putri, Alyssia Az-Zahra Ravica Atmaja, Patricia Sherryn Dewi, Adhe Lingga Prasetyo, Anang Computer Science Department School of Computer Science Bina Nusantara University Semarang Campus Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

The increasing population and number of vehicles lead to a significant growth in air pollution. This occurrence causes a serious issue that may impair the environment and public health. To monitor the level of air pollution, it is necessary to develop a device capable of accurately assessing pollution levels. Therefore, this research aims to implement the Internet of Things (IoT) to develop an air monitoring system. This system collects sensor data and transmits data to a cloud-based platform for analysis and visualization. Integrating multiple sensors enhances the system's ability to detect various pollutants commonly found indoors and outdoors. In addition, the air monitoring device includes a sensor to detect fire-causing gas such as hydrogen gas, and a sensor to measure the temperature and humidity levels of the surrounding areas. The effectiveness of the system is demonstrated through experimental tests conducted under various environmental conditions. The test results showed CO2 levels below 5,000 ppm, CO gas levels below 25 ppm, and other gases within safe limits, indicating that air pollution in Semarang on April 14, 2024, was considered safe or normal. The temperature and humidity levels experienced a decrease of 0.008495% and 0.6787%, respectively. Meanwhile, CO2 and H2 decreased exponentially by 0.1697% and 0.0269%, respectively. The error analysis between the DHT11 sensor and BMKG data indicates that the temperature measurements have an error rate of 1.05%, while the humidity measurements have an error rate of 1.04%. The results show that the developed system offers an efficient and cost-effective solution for continuous air quality monitoring, with potential applications in smart cities, industrial environments, and indoor spaces to reduce health risks associated with air pollution. © 2024 The Authors.

关键词： Temperature measurement

来源：评论

学校读者我要写书评

暂无评论

Differentiable Deformation Graph-Based Neural Non-rigid Registration

引用

Communications in Mathematics and Statistics 2023年第1期11卷 151-167页

作者： Wanquan Feng Hongrui Cai Junhui Hou Bailin Deng Juyong Zhang School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026People’s Republic of China School of Data Science University of Science and Technology of ChinaHefei 230026People’s Republic of China Department of Computer Science City University of Hong KongHong KongPeople’s Republic of China School of Computer Science and Informatics Cardiff UniversityCardiffUK

The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target *** the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local *** this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based ***,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair ***,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional *** model is trained in a self-supervised manner and thus can be used for arbitrary datasets without *** experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.

关键词： Differentiable deformation graph Non-rigid registration

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Framework for Temporal Cognitive Diagnosis in Online Learning Systems

引用

Journal of computer science & Technology 2023年第6期38卷 1203-1222页

作者：刘嘉聿汪飞马海平黄振亚刘淇陈恩红苏喻 School of Data Science University of Science and Technology of ChinaHefei 230026China State Key Laboratory of Cognitive Intelligence Hefei 230088China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Hefei 230026China School of Computer Science and Technology University of Science and Technology of ChinaHefei 230026China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601China School of Computer Science and Artificial Intelligence Hefei Normal UniversityHefei 230061China

Cognitive diagnosis is an important issue of intelligent education systems,which aims to estimate students'proficiency on specific knowledge *** existing studies rely on the assumption of static student states and ig-nore the dynamics of proficiency in the learning process,which makes them unsuitable for online learning *** this paper,we propose a unified temporal item response theory(UTIRT)framework,incorporating temporality and random-ness of proficiency evolving to get both accurate and interpretable diagnosis ***,we hypothesize that stu-dents'proficiency varies as a Wiener process and describe a probabilistic graphical model in UTIRT to consider temporali-ty and randomness ***,based on the relationship between student states and exercising answers,we hy-pothesize that the answering result at time k contributes most to inferring a student's proficiency at time k,which also re-flects the temporality aspect and enables us to get analytical maximization(M-step)in the expectation maximization(EM)algorithm when estimating model *** UTIRT is a framework containing unified training and inferenc-ing methods,and is general to cover several typical traditional models such as Item Response Theory(IRT),multidimen-sional IRT(MIRT),and temporal IRT(TIRT).Extensive experimental results on real-world datasets show the effective-ness of UTIRT and prove its superiority in leveraging temporality theoretically and practically over TIRT.

关键词： cognitive diagnosis probabilistic graphical model item response theory(IRT) stochastic process expectation maximization(EM)algorithm

来源：评论

学校读者我要写书评

暂无评论

Smart Monitoring System for Quality Assessment of Batik Industry Wastewater Through IoT and Machine Learning Classification

Smart Monitoring System for Quality Assessment of Batik Indu...

引用

2024 International Conference on Artificial Intelligence and Mechatronics System, AIMS 2024

作者： Aldiki Febriantono, M. School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350350524

Industrial batik wastewater has dangerous chemicals, so it needs careful checking and study. This research used IoT technology to gather data on the wastewater's quality, including things like pH, how much oxygen it needs to break down organic matter (BOD), how much oxygen it needs to break down chemicals (COD), temperature, and the amount of heavy metals. Then, the data was analyzed using simple Machine Learning methods, with algorithms like SVM, KNN, DT, Naive Bayes, Regression, and AdaBoost, to sort the wastewater into different quality types. The study found that these methods were really accurate, which is very important for managing waste well. This research helps in creating easy and effective ways to deal with environmental problems from the batik industry. Using IoT and Machine Learning gives a clear picture of the wastewater and leads to better, eco-friendly ways of handling it. The AdaBoost algorithm did the best, with the highest scores in accuracy (96.32%), precision (95.34%), and how well it identified relevant data (95.80%). © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Detecting Hate Speech on Indonesian Twitter Using Logistic Regression 6

Detecting Hate Speech on Indonesian Twitter Using Logistic R...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： William, Fabio Valentino Esene, Jensen Ramadhaniel Putra Nabiilah, Ghinaa Zain Moniaga, Jurike V. Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Hate speech on social media has become a significant issue, particularly due to the diverse nature of these platforms where people from around the world interact. Social media, intended as a place for communication and connection, has unfortunately also become a place for expressing hate towards individuals or groups. Numerous studies have been conducted to understand and address this problem. These hateful messages can target people based on their race, religion, ethnicity, sexual orientation, disability, or any other factor that can be used to divide. This particular research focuses on detecting hate speech on Indonesian Twitter. The methodology involves several steps: data collection, data preparation, data analysis, validation and testing, evaluation. By implementing Natural Language Processing techniques for Logistic Regression, this study aims to contribute valuable insights for future research on hate speech detection especially within Indonesian social media. The expected outcome is to enhance the understanding and detection of hate speech, thereby helping to create a safer and more inclusive online environment. © 2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

The Impact of Artificial Intelligence in the Creative Industries: Design and Editing

The Impact of Artificial Intelligence in the Creative Indust...

引用

2024 International of Seminar on Application for Technology of Information and Communication, iSemantic 2024

作者： Clarencia, Eryka Tiranda, Tirsa Gracella Achmad, Said Sutoyo, Rhio Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350366648

The rapid development of artificial intelligence has had a significant influence in various ways, one of which is in the creative design and editing industry. The use of AI in the creative sector has multiple impacts and new challenges for the creative industry. AI as a tool can increase the efficiency and productivity of creative workers. However, the rapid development of AI can also cause job displacement, which becomes a challenge for creative workers. Therefore, creative workers need to adapt to the use of AI in the creative industry by equipping themselves with skills and knowledge in operating AI as a collaboration tool. In addition, it is also necessary to consider the ethics of using AI in the creative industry. For example, privacy, copyright, and transparency should be maintained so as not to cause ethical problems such as plagiarism and data biases. This research aims to determine the impact of AI and provide an understanding of its ethical use in the creative industry. This research was conducted using the PRISMA method to collect research papers related to this study. This research also investigates how creative workers deal with the challenges that arise due to the use of AI in the creative industry. © 2024 IEEE.

关键词： Artificial intelligence creative industries creative thinking ethical impact

来源：评论

学校读者我要写书评

暂无评论

Utilizing data Augmentation Methods to Generalize DeepFake Classifier

Utilizing Data Augmentation Methods to Generalize DeepFake C...

引用

2024 International Conference on Artificial Intelligence, Blockchain, Cloud Computing, and data Analytics, ICoABCD 2024

作者： Pho, Julius Gerald Gouw, Christian Arifin Lucky, Henry Suhartono, Derwin School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350368451

DeepFakes are fabricated audiovisual media. As technology advances, the tools for making DeepFakes have increased. Due to this, making DeepFakes are more accessible to a lot of people. As a result, some people use it irresponsibly such as hoaxes and scams. To combat this, a reliable DeepFake detector is needed. EfficientNet-B0has been used and has the highest success rate in detecting DeepFakes. Moreover, utilizing dynamic face cutout has only been proven to increase the accuracy rate of detecting DeepFakes. Because of this, we decide to implement EfficientNet-B0and face augmentation with the hopes of having a reliable DeepFake detection model. For comparison, three experiments using three different models were done. The three models include EfficientNet-B0 with Multi-task Cascaded Convo-lutional Networks (MTCNN), EfficientNet-B0 with MTCNN and Face-CutOut, and EfficientNet-B0 with MTCNN and a common data augmentation method. The experiments showed that The EfficientNet-B0and MTCNN model yielded the best results, reaching above the 90% mark on the Accuracy, AUC-ROC, and Fl-Score. When face augmentation was implemented, the results faced a slight decrease of around 1% on the Accuracy, AUC-ROC, and Fl-Score compared to the model using only EfficientNet-B0 and MTCNN. However, the EfficientNet-B0 and MTCNN model implemented with Face-Cutout has the best AUC-ROC score, above the model using only EfficientNet-B0 and MTCNN, which has a score of 97.82%. The results demonstrate that data augmentation is effective in enhancing model generalization. © 2024 IEEE.

关键词： computer crime

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：