检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Nikolaidis, Panagiotis Zoulkarni, Asim Baras, John Department of Electrical & Computer Engineering The Institute for Systems Research University of Maryland College ParkMD20742 United States

The need to satisfy the QoS requirements of multiple network slices deployed at the same base station poses a major challenge to network operators. The problem becomes even harder when the desired QoS involves packet delays. In that case, network utility maximization is not directly applicable since the utilities of the slices are unknown. As a result, most related works learn online the utilities of all slices and how to split the resources among them. Unfortunately, this approach does not scale well for many slices. Instead, it is needed to perform learning separately for each slice. To this end, we develop a bandwidth demand estimator;a network function that periodically receives as input the traffic of the slice and outputs the amount of bandwidth that its MAC scheduler needs to deliver the desired QoS. We develop the bandwidth demand estimator for QoS involving packet delay metrics based on a model-based reinforcement learning algorithm. We implement the algorithm on a cellular testbed and conduct experiments with time-varying traffic loads. Results show that the algorithm delivers the desired QoS but with significantly less bandwidth than non-adaptive approaches and other baseline online learning algorithms. © 2023, CC BY.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Scenario Generation for Cooling,Heating,and Power Loads Using Generative Moment Matching Networks

引用

CSEE Journal of Power and Energy systems 2022年第6期8卷 1730-1740页

作者： Wenlong Liao Yusen Wang Yuelong Wang Kody Powell Qi Liu Zhe Yang Department of Energy Technology Aalborg UniversityAalborg 9220Denmark School of Electrical Engineering and Computer Science KTH Royal Institute of TechnologyStockholmSE-10044Sweden State Grid Tianjin Chengxi Electric Power Supply Branch Tianjin 300100China Department of Chemical Engineering University of UtahUT 84112America Key Laboratory of Smart Grid of Ministry of Education Tianjin UniversityTianjin 300072China

Scenario generations of cooling,heating,and power loads are of great significance for the economic operation and stability analysis of integrated energy *** this paper,a novel deep generative network is proposed to model cooling,heating,and power load curves based on generative moment matching networks(GMMNs)where an auto-encoder transforms highdimensional load curves into low-dimensional latent variables and the maximum mean discrepancy represents the similarity metrics between the generated samples and the real *** training the model,the new scenarios are generated by feeding Gaussian noises to the scenario generator of the *** the explicit density models,the proposed GMMN does not need to artificially assume the probability distribution of the load curves,which leads to stronger *** simulation results show that the GMMN not only fits the probability distribution of multiclass load curves very well,but also accurately captures the shape(e.g.,large peaks,fast ramps,and fluctuation),frequency-domain characteristics,and temporal-spatial correlations of cooling,heating,and power ***,the energy consumption of generated samples closely resembles that of real samples.

关键词： Deep learning generative moment matching networks integrated energy systems scenario generations

来源：评论

学校读者我要写书评

暂无评论

SPL: A Socratic Playground for Learning Powered by Large Language Model

SPL: A Socratic Playground for Learning Powered by Large Lan...

引用

2024 Joint of the Human-Centric eXplainable AI in Education and the Leveraging Large Language Models for Next Generation Educational Technologies Workshops, HEXED-L3MNGET 2024

作者： Zhang, Liang Lin, Jionghao Kuang, Ziyi Xu, Sheng Hu, Xiangen Institute for Intelligent Systems University of Memphis MemphisTN38152 United States Department of Electrical and Computer Engineering University of Memphis MemphisTN38152 United States School of Computer Science Carnegie Mellon University PittsburghPA15213 United States School of Psychology Shaanxi Normal University Xi’an710062 China School of Psychology Central China Normal University Wuhan430079 China Department of Applied Social Sciences Hong Kong Polytechnic University Hong Kong

Dialogue-based Intelligent Tutoring systems (ITSs) have significantly advanced adaptive and personalized learning by automating sophisticated human tutoring strategies within interactive dialogues. However, replicating the nuanced patterns of expert human communication remains a challenge in Natural Language Processing (NLP). Recent advancements in NLP, particularly Large Language Models (LLMs) such as OpenAI’s GPT-4, offer promising solutions by providing human-like and context-aware responses based on extensive pre-trained knowledge. Motivated by the effectiveness of LLMs in various educational tasks (e.g., content creation and summarization, problem-solving, and automated feedback provision), our study introduces the Socratic Playground for Learning (SPL), a dialogue-based ITS powered by the GPT-4 model, which employs the Socratic teaching method to foster critical thinking among learners. Through extensive prompt engineering, SPL can generate specific learning scenarios and facilitates efficient multi-turn tutoring dialogues. The SPL system aims to enhance personalized and adaptive learning experiences tailored to individual needs, specifically focusing on improving critical thinking skills. Our pilot experimental results from essay writing tasks demonstrate SPL has the potential to improve tutoring interactions and further enhance dialogue-based ITS functionalities. Our study, exemplified by SPL, demonstrates how LLMs enhance dialogue-based ITSs and expand the accessibility and efficacy of educational technologies. © 2024 Copyright for this paper by its authors.

关键词： Problem solving

来源：评论

学校读者我要写书评

暂无评论

A Novel Face Inpainting Approach Based on Guided Deep Learning 4

A Novel Face Inpainting Approach Based on Guided Deep Learni...

引用

4th International Conference on Communications, Signal Processing, and their Applications, ICCSPA 2020

作者： Salem, Nermin M. Mahdi, Hani M.K. Abbas, Hazem M. Electrical Engineering Department Future University in Egypt Cairo Egypt Computer and Systems Engineering Department Ain Shams University Cairo Egypt

ISBN: (纸本)9781728165356

In the last few years, deep learning has shown significant improvement for many computer vision open problems, especially Image inpainting. Image inpainting is the process of filling missing regions across images. One of the most challenging problems in image inpainting is face inpainting. In this work, a new novel approach for face inpainting is proposed which can capture and preserve the identity of each human face in images while reproducing the missing irregular region in images. A two-stage cascaded model is proposed. It is composed of a shape-predictor of the key-points of the face followed by an inpainting network. The shape-predictor identifies the human face's structure-preserving its local points, i.e. eyes, mouth, nose, and then the inpainting network fills any random-irregular missing regions guided by the obtained knowledge as a priori. The effectiveness of the proposed model was evaluated using the CelebA dataset. The obtained results from the trained model outperform the recently proposed technique with contextual attention. © 2020 IEEE

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Hybridization of Wavelet Decomposition and Machine Learning for Brain Waves based Emotion Recognition

Hybridization of Wavelet Decomposition and Machine Learning ...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Mirna Ali Saeed Mian Qaisar Tamanna Anurulafchar Electrical and Computer Engineering Department Effat University Jeddah Saudi Arabia LINEACT Laboratory CESI Engineering School Villeurbanne France Computer science Department Effat University Jeddah Saudi Arabia

Emotion recognition has sparked the interest of researchers from a variety of disciplines. Studies have demonstrated that brain signals may be utilized to characterize a wide range of emotional states. Electroencephalogram (EEG) measures the cerebral activity. Therefore, by exploiting the EEG signals the emotion states can be determined. In this study the EEG signals undergoes through filtering, segmentation, Wavelet Packet Decomposition (WPD), feature mining, and classification. The machine learning algorithms used for classifications are “Decision Tree” (DT), “Support Vector Machine” (SVM), and K-Nearest Neighbor” (K-NN) algorithms are used for categorization. Their performance is compared for automatically identifying the emotion state. It is determined that the best performer is SVM. It has attained 98.2% accuracy, 97.3% precision, 97.3% recall, 98.7% specificity, 97.3% F1, 97.3% kappa, and 99.3% AUC.

关键词： Emotion recognition Technological innovation Machine learning algorithms Smart cities Signal processing algorithms Support vector machine classification Signal processing

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue Detection

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue D...

引用

2023 International Conference on Sustainable Technology and engineering, i-COSTE 2023

作者： Xie, Shuaiyue Chuah, Joong Huang Ting Chai, Grace Mei University of Southampton Electronics and Computer Science SouthamptonSO171BJ United Kingdom University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur50603 Malaysia University of Southampton Malaysia Smart Manufacturing Systems Research Group Iskandar Puteri Johor79100 Malaysia

ISBN: (纸本)9798350329711

Driver fatigue is a significant cause of road accidents. Effective real-time fatigue detection systems are necessary to improve road safety. Utilizing a lightweight and fast model and creating an effective fatigue judgment rule is important in detecting fatigue in real-time. In this research, we propose a fatigue detection model based on You Look Only Once version 8 (YOLOv8) model to detect driver's facial features and use percentage of eyelid closure over the pupil over time (PERCLOS) and Percentage of Open Mouth (POM) indicators to identify fatigue. This research is divided into two parts. The first part involves creating, labeling, and preprocessing the dataset. We use the YawDD dataset as the original dataset and manually label a new dataset using the Roboflow platform. We then preprocessed the new dataset to train the YOLOv8 model for face features detection. In the second part, we established a multi-indicator fatigue determination rule that uses PERCLOS and POM indicators and set a threshold to determine whether the driver is fatigue. By combining the YOLOv8 model with the fatigue determination rules based on PERCLOS and POM, we successfully built a model to identify a driver's fatigue. Finally, the fatigue detection model based on YOLOv8 achieves a high accuracy rate of 96.9% and a high speed of 11.4 ms/frame in face features detection, surpassing other traditional models and previous generations of YOLO models. This model can effectively detect fatigue in both driver-driving pictures and videos. © 2023 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Objective Optimization Algorithm Guided by Recurrent Neural Network

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Hu, Yaru Ou, Junwei Suganthan, Ponnuthurai Nagaratnam Pedrycz, Witold Wang, Rui Zheng, Jinhua Zou, Juan Song, Yanjie School of Computer Science and School of Cyberspace Security Xiangtan University Xiangtan China College of Engineering KINDI Center for Computing Research Qatar University Doha Qatar Department of Electrical and Computer Engineering University of Alberta Edmonton AB Canada College of Systems Engineering National University of Defense Technology Changsha China School of Reliability and Systems Engineering Beihang University Beijing China

In recent years, prediction-based algorithms have attracted much attention for solving dynamic multi-objective optimization problems in the evolutionary computing community. However, this class of algorithms still has potential for further improvements by enhaneing the historical information extraction approach to balance convergence and diversity. In this paper, we propose a dynamic multi-objective optimization algorithm based on a recurrent neural network to balance the population’s convergence and diversity in dynamic environments. The recurrent neural network model in the proposed algorithm employs online learning in order to constantly improve according to the increasing evolutionary information. Meanwhile, differing from most existing prediction-based algorithms, the learning machine is not limited by assumptions, such as linear or nonlinear correlation, when it predicts new solutions for future evolutionary environments. Besides, an auxiliary strategy is performed, which adaptively introduces the random or mutated solutions according to the error losses between the prediction solutions and the optimal solutions in the whole optimization process. The experimental results show that the proposed algorithm is more effective for handling dynamic multi-objective optimization problems than several recent algorithms. IEEE

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Signaling-based Robust Incentive Designs with Randomized Monitoring

引用

IFAC-PapersOnLine 2023年第2期56卷 1754-1759页

作者： Sina Sanjari Subhonmesh Bose Tamer Başar Department of Electrical and Computer Engineering at University of Illinois Urbana-Champaign Illinois USA Coordinated Science Laboratory at University of Illinois Urbana-Champaign Illinois USA

Incentive design problems entail hierarchical decision-making where a leader crafts a strategy to induce a desired response from a follower. Such dynamic games with decentralized information structures have been well-studied under three assumptions-the leader must have access to the follower's observations, actions, and the objective function. Lack of knowledge on any of these can potentially lead to performance loss for the leader. In this paper, we first study a setup where the leader observes the follower's action through a random monitoring channel and learns about the follower's observation through a follower-designed signal. In this setup, we establish the existence of a signaling-based incentive equilibrium strategy for the leader that induces honest reporting and desired control response from the follower. Then, we study a setting, where the follower's costs are parametric, but the parameters are not known to the leader. We construct an incentive strategy that reduces the sensitivity of the leader's performance to uncertainty in the parameter, close to an initial estimate. More generally, for the case when the leader's knowledge about the follower's cost and distributions of cost-relevant random variables is inaccurate, we establish the existence of a robust incentive equilibrium strategy that bounds the performance loss from the inaccuracy in the model.

关键词： Differential and dynamic games multi-agent systems robustness analysis data-driven decision making hierarchical multilevel and multilayer control

来源：评论

学校读者我要写书评

暂无评论

Exploring Continuous Awareness Modelling for Improving Worker Safety and Trust*

Exploring Continuous Awareness Modelling for Improving Worke...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Andrey Solovov Mohammad Zarei Vishal Gautam Bruno Ferreira Gustavo Assunção Antonio Marin-Hernandez Paulo Menezes Department of Electrical and Computer Engineering University of Coimbra Coimbra Portugal Institute of Systems and Robotics University of Coimbra Coimbra Portugal Universidad Veracruzana Xalapa Mexico

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

The Industry 5.0 Human-Robot Interaction (HRI) goals have the potential for significantly reducing production costs, but require factory workers to trust that robots will not cause them physical harm when sharing the workspace in order to be achieved. To this end, we propose a model that adjusts the robot’s actions to an estimate of the workers’ awareness of its behavior. Its premise is that mutual awareness should be continuous, and if no recent visual contact has been established, then the robot should adapt its range of motion and speed in order to minimize the intersection between the robot’s space and the worker’s space. On the other hand, if the worker steadily establishes visual contact from times to times, the robot operates under a normal or a faster configuration. After a period of habituation, this awareness model can be further tweaked to continuously improve production times, while improving worker’s safety and trust. We present preliminary results of a pilot study with 32 participants, to asses if the existence of this awareness model impacts the outcomes of the combined task. The obtained tepidly optimistic results are the key to build upon in future designs.

关键词： Visualization Adaptation models Costs Service robots Human-robot interaction Production facilities Safety Motion control Fifth Industrial Revolution

来源：评论

学校读者我要写书评

暂无评论

Multi-user Visible Light Communications with Probabilistic Constellation Shaping and Precoding

arXiv

引用

arXiv 2025年

作者： Nguyen, Thang K. Pham, Thanh V. Le, Hoang D. Nguyen, Chuyen T. Pham, Anh T. Department of Computer Science and Engineering The University of Aizu Fukushima Japan Department of Mathematical and Systems Engineering Shizuoka University Shizuoka Japan School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam

This paper proposes a joint design of probabilistic constellation shaping (PCS) and precoding to enhance the sum-rate performance of multi-user visible light communications (VLC) broadcast channels subject to signal amplitude constraint. In the proposed design, the transmission probabilities of bipolar M-pulse amplitude modulation (M-PAM) symbols for each user and the transmit precoding matrix are jointly optimized to improve the sum-rate performance. The joint design problem is shown to be a complex multivariate non-convex problem due to the non-convexity of the objective function. To tackle the original non-convex optimization problem, the firefly algorithm (FA), a nature-inspired heuristic optimization approach, is employed to solve a local optima. The FA-based approach, however, suffers from high computational complexity. Thus, using zero-forcing (ZF) precoding, we propose a low-complexity design, which is solved using an alternating optimization approach. Additionally, considering the channel uncertainty, a robust design based on the concept of end-to-end learning with autoencoder (AE) is also presented. Simulation results reveal that the proposed joint design with PCS significantly improves the sum-rate performance compared to the conventional design with uniform signaling. For instance, the joint design achieves 17.5% and 19.2% higher sum-rate for 8-PAM and 16-PAM, respectively, at 60 dB peak amplitude-to-noise ratio. Some insights into the optimal symbol distributions of the two joint design approaches are also provided. Furthermore, our results show the advantage of the proposed robust design over the non-robust one under uncertain channel conditions. © 2025, CC BY.

关键词： Convex optimization

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：