检索结果-内蒙古大学图书馆

5th International Conference on Deep Learning, Artificial Intelligence and Robotics, ICDLAIR 2023

作者： Saran, Naveen Kesswani, Nishtha Saharan, Ravi Department of Computer Science Central University of Rajasthan NH-8 Rajasthan Bandarsindri305817 India Department of Computer Science and Engineering Central University of Rajasthan NH-8 Rajasthan Bandarsindri305817 India Department of Data Science & Analytics Central University of Rajasthan NH-8 Rajasthan Bandarsindri305817 India

ISBN: (纸本)9783031609343

The Internet of Things (IoT) has tremendously impacted people’s daily lives in recent years. Researchers and corporations also show interest in diverse IoT applications, such as the Internet of Medical Things (IoMT). In various aspects, security issues are the most important area of IoT, specifically for IoMT. The healthcare industry’s primary concern is safeguarding patient data from numerous intrusion attacks. It is essential to develop an effective and secure Intrusion Detection System (IDS) for IoMT. In this research article, we have proposed an efficient Intrusion Detection System (IDS) to identify intrusion attacks on the Internet of Medical Things (IoMT). We have developed a robust Intrusion Detection System (IDS) by employing a variety of Deep Learning (DL) techniques such as Simple Recurrent Neural Networks (S-RNN), Long Short-Term Memory Networks (LSTM) and Gated Recurrent Units (GRU) on a publicly available healthcare dataset. The experiment’s findings showed very high accuracy rates of intrusion detection using Simple Recurrent Neural Network (S-RNN), Long Short Term Memory Network (LSTM), Gated Recurrent Units (GRU) classification techniques compared to the state-of-art techniques. The overall accuracy of the experimented Intrusion Detection Systems was more than 99 % for all the implemented DL classification techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

data-Driven Analysis of EV Energy Prediction and Planning of EV Charging Infrastructure 9

Data-Driven Analysis of EV Energy Prediction and Planning of...

引用

9th IEEE International Conference on Big data Computing Service and Applications, BigdataService 2023

作者： Palaniappan, Arul Bhukya, Purnima Chitti, Sai Kiran Gao, Jerry San Jose State University Department of Applied Data Science San Jose United States San Jose State University Department of Applied Data Science Department of Computer Engineering San Jose United States

ISBN: (纸本)9798350333794

To reduce the current crisis on energy and environmental problems, the adoption of electric vehicles is an effective way. But limited access and availability of charging infrastructure are restricting the EV market development. This paper presents data-driven analysis of current EV charging infrastructure to plan future EV infrastructure in the city. This paper tackles the problem using three approaches. The first approach that is covered in this paper is to predict the number of EV charging stations that need to be implemented in a geographic location. This is done using the SARIMAX model on the California EV charging station dataset that is preprocessed to be split into zip codes. The second approach that is tackled by this paper is the energy consumption prediction by an EV charging station. This information is useful to allow planners to understand how much energy is consumed by an EV station across multiple different time periods. An optimized Meta-Fusion regression model based on a stacked model is proposed for this approach and is applied to the Palo Alto charging station dataset. The third approach utilized the K-means clustering algorithm on the Palo Alto charging station dataset to predict the optimal location for EV charging stations in that city. The SARIMAX mode had an R2 score of 0.97, a MAE of 6.50, and RMSE of 17.43 when predicting EV station counts in the zip code 92101. The stacked model had an R2 score of 0.98, a MAE of 0.91 and an RMSE of 2.26 when predicting the daily energy consumption by an EV station. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Machine Learning on Smart Home data for Prediction of Electrical Energy Consumption

Evaluation of Machine Learning on Smart Home Data for Predic...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Widianto, Mochammad Haldi Gunawan, Alexander Agung Santoso Heryadi, Yaya Budiharto, Widodo Bina Nusantara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Computer Science Department Bina Nusantara University Jl. K.H.Syahdan No. 9 Palmerah Kemanggisan Jakarta11480 Indonesia

ISBN: (纸本)9798350320954

Electrical energy consumption is always increasing, and this causes the supply of electrical energy to be increased to compensate. One solution is to predict electricity energy consumption using Artificial Intelligence (AI) technology in Smart Homes. Several studies' solutions for predicting electrical energy consumption usually focused only on performance but rarely evaluated Machine Learning (ML) by correlation for feature selection and utilized interpretability model. This study uses an ML model for predicting utilization (Linear Regression, Decision Tree, Random Forest, and XGBoost). Then, Feature Selection utilizes correlation to choose the best feature. After that, the interpretability model utilizes Local Interpretable Model-agnostic Explanations (LIME). The results show that XGBoost has the best Root Mean Squared Error (RMSE) value (0.318) with a percentage of the number of train and test data (90/10). After that, by eliminating features that correlate with 0.01, XGBoost improves with an increase of (0.018) to become (0.3). Then from LIME. This work also gets positive feature from XGBoost such as: "Furnance, Well dan Living Room". © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparing lesson plan-driven and ask-me-anything chatbots: teaching a UNIX Shell course

引用

Discover Education 2025年第1期4卷 1-23页

作者： Berengueres, Jose Department of Computer Science KTH Royal Institute of Technology Stockholm Sweden College of IT (Affiliation During Data Collection) UAE University Abu Dhabi United Arab Emirates

GPT-based models have enabled the creation of natural language chatbots that support both Inquiry-Based and Structured Learning approaches. This study offers a direct comparison of these two paradigms within a UNIX Shell scripting course by means of two chatbots: a Lesson Plan-Driven chatbot that ensures all students cover the same topics systematically, and an Ask-Me-Anything (AMA) chatbot more suited to exploratory learning. We compared two particular chatbots—Harvard’s CS50 (as an AMA chatbot) and OS315 (ours), as a lesson plan-driven chatbot—through four surveys. Results show a Net Promoter Score (NPS) of + 45 CI[25, 66] (N = 55) for the least performing lesson plan-driven chatbot and + 35 CI[11, 58.5] (N = 40) for the AMA chatbot. The majority of students favored a blend of human and chatbot instruction. Additionally, we discuss factors such as cost, accessibility, and why the same chatbot architecture, when applied to a data Visualization course yields a lower NPS of + 9 CI[−6, + 23]. © The Author(s) 2025.

关键词： AI tutor Automated tutor Hybrid paradigm Survey

来源：评论

学校读者我要写书评

暂无评论

A Global Geometric Analysis of Maximal Coding Rate Reduction 41

A Global Geometric Analysis of Maximal Coding Rate Reduction

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Peng Liu, Huikang Pai, Druv Yu, Yaodong Zhu, Zhihui Qu, Qing Ma, Yi Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor United States Antai College of Economics and Management Shanghai Jiao Tong University Shanghai China Department of Electrical Engineering and Computer Science University of California Berkeley United States Department of Computer Science and Engineering The Ohio State University Columbus United States Institute of Data Science University of Hong Kong Hong Kong

The maximal coding rate reduction (MCR2) objective for learning structured and compact deep representations is drawing increasing attention, especially after its recent usage in the derivation of fully explainable and highly effective deep network architectures. However, it lacks a complete theoretical justification: only the properties of its global optima are known, and its global landscape has not been studied. In this work, we give a complete characterization of the properties of all its local and global optima, as well as other types of critical points. Specifically, we show that each (local or global) maximizer of the MCR2 problem corresponds to a low-dimensional, discriminative, and diverse representation, and furthermore, each critical point of the objective is either a local maximizer or a strict saddle point. Such a favorable landscape makes MCR2 a natural choice of objective for learning diverse and discriminative representations via first-order optimization methods. To validate our theoretical findings, we conduct extensive experiments on both synthetic and real data sets. Copyright 2024 by the author(s)

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Towards Federated Learning on Fresh datasets 20

Towards Federated Learning on Fresh Datasets

引用

20th IEEE International Conference on Mobile Ad Hoc and Smart Systems, MASS 2023

作者： Wu, Chen Xiao, Mingjun Wu, Jie Xu, Yin Zhou, Jinrui Sun, He University of Science and Technology of China School of Data Science China University of Science and Technology of China School of Computer Science and Technology & Suzhou Institute for Advanced Research China Temple University Department of Computer and Information Sciences United States

ISBN: (纸本)9798350324334

Federated Learning (FL) is an emerging privacy-preserving distributed computing paradigm that enables numerous clients to collaboratively train machine learning models without the need for transmitting the private datasets of clients to the FL server. Unlike most existing research where the local datasets of clients are considered to be unchanging over time during the whole FL process, we consider such scenarios in this paper where the local datasets of clients need to be updated periodically, and the server can stimulate clients to use as fresh as possible datasets to train their local models. Our objective is to determine a client selection strategy to minimize the loss of global model for FL with a limited budget. To this end, we leverage the concept of Age of Information (AoI) to quantify the freshness of local datasets and theoretically analyze the convergence bound of our AoI-aware FL system. Based on the convergence bound, we formalize our problem as a restless multi-armed bandit problem. Then, we devise a Whittle's-Index-based Client Selection algorithm, called WICS, to tackle the client selection problem. Extensive simulations show that the proposed algorithm can reduce the training loss and improve learning accuracy compared to state-of-the-art algorithms. © 2023 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Challenges and Recommendations for Improving Logistic Skills Through Simulation-Based Learning Technology

Challenges and Recommendations for Improving Logistic Skills...

引用

2025 International Conference on Advancement in data science, E-learning and Information System, ICADEIS 2025

作者： Sirait, Tamsir Hasudungan Meyliana Arifin, Yulyani Yulianto, Budi Bina Nusantara University Binus Graduate Program Jakarta Indonesia Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

Simulation-based learning is one of the most powerful tools to support the educational process. This learning offers an opportunity to learn based on experiences that are very similar to real-world environments. In the context of logistics, which can be considered a complex system, significant efforts are required to enhance students' understanding and practical skills. For that reason, simulations are used so that benefits such as skills and knowledge in the field of logistics can be achieved. However, there are currently several challenges in developing simulation-based learning in higher education. These challenges include the need for simulations that are appropriate for the current learning context, where the students are generally from Generation Z, and how to improve their learning quality in the era of Industry 4.0. To address these challenges, more suitable simulations need to be developed, and higher education institutions must carefully examine how to develop them, including identifying the essential components in the development of simulations for logistics learning. In this research, a systematic literature review using the PRISMA method and also creating a conceptual model of simulation that better meets the current needs of logistics education will be proposed. The results of this research can be used as a basis for developing updated simulations to better prepare students for the challenges of Industry 4.0. © 2025 IEEE.

关键词： industry 4.0 logistics simulation development simulation learning simulation learning component

来源：评论

学校读者我要写书评

暂无评论

Hybrid Design for Privacy Preserved Image Representation in a Cloud Environment 1

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Vijay, K. Sorna Shanthi, D. Jaeyalakshmi, M. Vignesh, P. Yuvaraja, M. Department of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India

ISBN: (数字)9789819789467

ISBN: (纸本)9789819789450

The digital era has made seamless sharing and keeping of media such as images on cloud platforms an integral part of our lives. Still, there is a big issue about user privacy and data security in these repositories. We have thus created a very strong system that is able to do image encryption and decryption so as to protect the privacy of users while at the same time making their pictures accessible. Our system uses hybrid encryption where we try to prevent even cloud service providers from accessing the original files hence ensuring that only the owner who has been authenticated through password based authentication can decrypt or access them. In this way, it allows maintaining high privacy standards without sacrificing user convenience. It starts with preparing photos for encryption so that they are kept safe during transmission and storage. When needed by a user, images are decrypted by our system and become available only to authorized users. Consequently, users can comfortably leave their private photo albums on cloud storage systems knowing too well that their friends cannot access them thereby increasing trust in using cloud services for storing sensitive information. The aim of this work is to increase user privacy and data security in cloud repositories through employing this encryption technique. The users are guaranteed that their private details are not exposed to others enabling them to use cloud storage efficiently without interfering with their privacy at all. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

PROVABLE SIM-TO-REAL TRANSFER IN CONTINUOUS DOMAIN WITH PARTIAL OBSERVATIONS 11

PROVABLE SIM-TO-REAL TRANSFER IN CONTINUOUS DOMAIN WITH PART...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Hu, Jiachen Zhong, Han Jin, Chi Wang, Liwei School of Computer Science Peking University China Center for Data Science Peking University China Department of Electrical and Computer Engineering Princeton University United States National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Center for Data Science Peking University Beijing Institute of Big Data Research China

Sim-to-real transfer, which trains RL agents in the simulated environments and then deploys them in the real world, has been widely used to overcome the limitations of gathering samples in the real world. Despite the empirical success of the sim-to-real transfer, its theoretical foundation is much less understood. In this paper, we study the sim-to-real transfer in continuous domain with partial observations, where the simulated environments and real-world environments are modeled by linear quadratic Gaussian (LQG) systems. We show that a popular robust adversarial training algorithm is capable of learning a policy from the simulated environment that is competitive to the optimal policy in the real-world environment. To achieve our results, we design a new algorithm for infinite-horizon average-cost LQGs and establish a regret bound that depends on the intrinsic complexity of the model class. Our algorithm crucially relies on a novel history clipping scheme, which might be of independent interest. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unified binary and multiclass margin-based classification

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 6810-6860页

作者： Yutong Wang Clayton Scott Department of Electrical Engineering and Computer Science and Michigan Institute of Data Science Department of Electrical Engineering and Computer Science and Department of Statistics University of Michigan Ann Arbor MI

The notion of margin loss has been central to the development and analysis of algorithms for binary classification. To date, however, there remains no consensus as to the analogue of the margin loss for multiclass classification. In this work, we show that a broad range of multiclass loss functions, including many popular ones, can be expressed in the relative margin form, a generalization of the margin form of binary losses. The relative margin form is broadly useful for understanding and analyzing multiclass losses as shown by our prior work (Wang and Scott, 2020, 2021). To further demonstrate the utility of this way of expressing multiclass losses, we use it to extend the seminal result of Bartlett et al. (2006) on classification-calibration of binary margin losses to multiclass. We then analyze the class of Fenchel-Young losses, and expand the set of these losses that are known to be classification-calibrated.

关键词： classification loss functions consistency margins label encodings

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：