检索结果-内蒙古大学图书馆

Hyperparameter Tuned Deep Learning Enabled Cyberbullying Classification in Social Media

computers, Materials & Continua 2022年第12期73卷 5011-5024页

作者： Mesfer Al Duhayyim Heba G.Mohamed Saud S.Alotaibi Hany Mahgoub Abdullah Mohamed Abdelwahed Motwakel Abu Sarwar Zamani Mohamed I.Eldesouki Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityMuhayel AseerSaudi Arabia Faculty of Computers and Information Computer Science DepartmentMenoufia UniversityEgypt Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl KharjSaudi Arabia

Cyberbullying(CB)is a challenging issue in social media and it becomes important to effectively identify the occurrence of *** recently developed deep learning(DL)models pave the way to design CB classifier models with maximum *** the same time,optimal hyperparameter tuning process plays a vital role to enhance overall *** study introduces a Teacher Learning Genetic Optimization with Deep Learning Enabled Cyberbullying Classification(TLGODL-CBC)model in Social *** proposed TLGODL-CBC model intends to identify the existence and non-existence of CB in social media ***,the input data is cleaned and pre-processed to make it compatible for further *** by,independent recurrent autoencoder(IRAE)model is utilized for the recognition and classification of ***,the TLGO algorithm is used to optimally adjust the parameters related to the IRAE model and shows the novelty of the *** assuring the improved outcomes of the TLGODLCBC approach,a wide range of simulations are executed and the outcomes are investigated under several *** simulation outcomes make sure the improvements of the TLGODL-CBC model over recent approaches.

关键词： Social media deep learning cyberbullying cybersecurity hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

A Control Lyapunov Function-Based Approach for Particle Nanomanipulation via Optical Tweezers

A Control Lyapunov Function-Based Approach for Particle Nano...

引用

American Control Conference (ACC)

作者： Melika Golgoon Alireza Mohammadi Mark W. Spong Department of Systems Engineering Erik Jonsson School of Engineering and Computer Science University of Texas at Dallas Richardson TX USA Department of Electrical and Computer Engineering University of Michigan-Dearborn MI USA

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

Considering the non-affine-in-control system gov- erning the motion of a spherical particle trapped inside an opti- cal tweezer, this paper investigates the problem of stabilization of the particle position at the origin through a control Lyapunov function (CLF) framework. The proposed CLF framework enables nonlinear optimization-based closed-loop control of position of tiny beads using optical tweezers and serves as a first step towards design of effective control algorithms for nanomanipulation of biomolecules. After deriving necessary and sufficient conditions for having smooth uniform CLFs for the optical tweezer control system under study, we present a static nonlinear programming problem (NLP) for generation of robustly stabilizing feedback control inputs. Furthermore, the NLP can be solved in real-time with no need for running computationally demanding algorithms. Numerical simulations demonstrate the effectiveness of the proposed control frame- work in the presence of external disturbances and initial bead positions that are located far away from the laser beam.

关键词： Sufficient conditions Biomedical optical imaging Optical design Optical feedback Molecular biophysics Laser feedback Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

How to leverage diverse demonstrations in offline imitation learning 24

How to leverage diverse demonstrations in offline imitation ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Sheng Yue Jiani Liu Xingyuan Hua Ju Ren Sen Lin Junshan Zhang Yaoxue Zhang Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China and Zhongguancun Laboratory Beijing China Department of Computer Science University of Houston Texas Department of Electrical and Computer Engineering University of California Davis

Offline Imitation Learning (IL) with imperfect demonstrations has garnered increasing attention owing to the scarcity of expert data in many real-world domains. A fundamental problem in this scenario is how to extract positive behaviors from noisy data. In general, current approaches to the problem select data building on state-action similarity to given expert demonstrations, neglecting precious information in (potentially abundant) diverse state-actions that deviate from expert ones. In this paper, we introduce a simple yet effective data selection method that identifies positive behaviors based on their resultant states – a more informative criterion enabling explicit utilization of dynamics information and effective extraction of both expert and beneficial diverse behaviors. Further, we devise a lightweight behavior cloning algorithm capable of leveraging the expert and selected data correctly. In the experiments, we evaluate our method on a suite of complex and high-dimensional offline IL benchmarks, including continuous-control and vision-based tasks. The results demonstrate that our method achieves state-of-the-art performance, outperforming existing methods on 20/21 benchmarks, typically by 2-5x, while maintaining a comparable runtime to Behavior Cloning (BC).

关键词：

来源：评论

学校读者我要写书评

暂无评论

AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR Data

arXiv

引用

arXiv 2025年

作者： Zhu, Haoran Dong, Zhenyuan Topollai, Kristi Choromanska, Anna Learning Systems Laboratory Department of Electrical and Computer Engineering New York University 370 Jay Street NY United States

As opposed to human drivers, current autonomous driving systems still require vast amounts of labeled data to train. Recently, world models have been proposed to simultaneously enhance autonomous driving capabilities by improving the way these systems understand complex real-world environments and reduce their data demands via self-supervised pre-training. In this paper, we present AD-L-JEPA (aka Autonomous Driving with LiDAR data via a Joint Embedding Predictive Architecture), a novel self-supervised pre-training framework for autonomous driving with LiDAR data that, as opposed to existing methods, is neither generative nor contrastive. Our method learns spatial world models with a joint embedding predictive architecture. Instead of explicitly generating masked unknown regions, our self-supervised world models predict Bird’s Eye View (BEV) embeddings to represent the diverse nature of autonomous driving scenes. Our approach furthermore eliminates the need to manually create positive and negative pairs, as is the case in contrastive learning. AD-L-JEPA leads to simpler implementation and enhanced learned representations. We qualitatively and quantitatively demonstrate high-quality of embeddings learned with AD-L-JEPA. We furthermore evaluate the accuracy and label efficiency of AD-L-JEPA on popular downstream tasks such as LiDAR 3D object detection and associated transfer learning. Notably, our method achieves up to a 5× speed-up in pre-training time compared with the state-of-the-art (SOTA) approaches and consistently delivers better performance when fine-tuned on different amounts of labeled data compared to SOTA. More impressively, the experiments show that even when the first layers of the encoders of ADL-JEPA are randomly initialized while the remaining layers are initialized as pre-trained, our method still yields positive transfers, whereas the competitor method suffer from the negative transfers in this case. Systematic experimental results demonstrate that

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

A population randomization-based multi-objective genetic algorithm for gesture adaptation in human-robot interaction

引用

science China(Information sciences) 2021年第1期64卷 188-200页

作者： Luefeng CHEN Wanjuan SU Min LI Min WU Witold PEDRYCZ Kaoru HIROTA School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Electrical and Computer Engineering University of Alberta Tokyo Institute of Technology

In recent years, vision-based gesture adaptation has attracted great attention from many experts in the field of human-robot interaction, and many methods have been proposed and successfully applied, such as particle swarm optimization and genetic algorithm. However, the reduction of the error and energy consumption of a robot while paying attention to more subtle attitude changes is very important and *** view of these problems, we propose a population randomization-based multi-objective genetic *** gesture signal is processed with a slight change by imitating the biological evolution mechanisms. In the proposed algorithm, a random out-of-order matrix is added in the process of population evolution synthesis to prevent the premature grouping convergence of the new population. The weights of the objective function and the elite retention strategy are adopted, and the most adaptable individuals in each generation are inherited directly in the next generation without any recombination or mutation. To verify the effectiveness of the algorithm, preliminary application experiments are performed on the gesture adaptation of a robotic arm. The results are compared with the original signal, and the comparison shows that by using the proposed method, the energy consumption is reduced, and the end error is decreased to less than 3 mm while ensuring the tracking effect of the robotic arm. These obtained results meet the communication requirements for human-robot interactions such as handshakes. Moreover, the proposed method has better performance, uses less energy, and has a smaller tracking error than the particle swarm optimization, the single-objective genetic algorithm, and the traditional multi-objective genetic algorithm. A preliminary application experiment indicates that the robotic arm can adapt to human gestures in real time.

关键词： multi-objective genetic algorithm gesture adaptation human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multi-Strategy Aquila Optimization with Deep Learning Driven Crop Type Classification on Hyperspectral Images

引用

computer systems science & engineering 2023年第10期47卷 375-391页

作者： Sultan Alahmari Saud Yonbawi Suneetha Racharla ELaxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa King Abdulaziz City for Science and Technology P.O Box 6086Riyadh 11442Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of AIML Aditya Engineering CollegeSurempallemAndhra PradeshIndia Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Hyperspectral imaging instruments could capture detailed spatial information and rich spectral signs of observed *** spatial information and spectral signatures of hyperspectral images(HSIs)present greater potential for detecting and classifying fine *** accurate classification of crop kinds utilizing hyperspectral remote sensing imaging(RSI)has become an indispensable application in the agricultural *** is significant for the prediction and growth monitoring of crop *** the deep learning(DL)techniques,Convolution Neural Network(CNN)was the best method for classifying HSI for their incredible local contextual modeling ability,enabling spectral and spatial feature *** article designs a Hybrid Multi-Strategy Aquila Optimization with a Deep Learning-Driven Crop Type Classification(HMAODL-CTC)algorithm *** proposed HMAODL-CTC model mainly intends to categorize different types of crops on *** accomplish this,the presented HMAODL-CTC model initially carries out image preprocessing to improve image *** addition,the presented HMAODL-CTC model develops dilated convolutional neural network(CNN)for feature *** hyperparameter tuning of the dilated CNN model,the HMAO algorithm is ***,the presented HMAODL-CTC model uses an extreme learning machine(ELM)model for crop type classification.A comprehensive set of simulations were performed to illustrate the enhanced performance of the presented HMAODL-CTC *** comparison studies reported the improved performance of the presented HMAODL-CTC algorithm over other compared methods.

关键词： Crop type classification hyperspectral images agricultural monitoring deep learning metaheuristics

来源：评论

学校读者我要写书评

暂无评论

OLLIE: imitation learning from offline pretraining to online finetuning 24

OLLIE: imitation learning from offline pretraining to online...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Sheng Yue Xingyuan Hua Ju Ren Sen Lin Junshan Zhang Yaoxue Zhang Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China and Zhongguancun Laboratory Beijing China Department of Computer Science University of Houston Texas Department of Electrical and Computer Engineering University of California Davis

In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the naïve combination of existing offline IL and online IL methods tends to behave poorly in this context, because the initial discriminator (often used in online IL) operates randomly and discordantly against the policy initialization, leading to misguided policy optimization and un-learning of pretraining knowledge. To overcome this challenge, we propose a principled offline-to-online IL method, named OLLIE, that simultaneously learns a near-expert policy initialization along with an aligned discriminator initialization, which can be seamlessly integrated into online IL, achieving smooth and fast finetuning. Empirically, OLLIE consistently and significantly outperforms the baseline methods in 20 challenging tasks, from continuous control to vision-based domains, in terms of performance, demonstration efficiency, and convergence speed. This work may serve as a foundation for further exploration of pretraining and finetuning in the context of IL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Discounted Iterative Adaptive Critic Designs With Novel Stability Analysis for Tracking Control

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1262-1272页

作者： Mingming Ha Ding Wang Derong Liu School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China Faculty of Information Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of TechnologyBeijing 100124China Department of Electrical and Computer Engineering University of Illinois at ChicagoChicago IL 60607 USA IEEE

The core task of tracking control is to make the controlled plant track a desired *** traditional performance index used in previous studies cannot eliminate completely the tracking error as the number of time steps *** this paper,a new cost function is introduced to develop the value-iteration-based adaptive critic framework to solve the tracking control *** the regulator problem,the iterative value function of tracking control problem cannot be regarded as a Lyapunov function.A novel stability analysis method is developed to guarantee that the tracking error converges to *** discounted iterative scheme under the new cost function for the special case of linear systems is ***,the tracking performance of the present scheme is demonstrated by numerical results and compared with those of the traditional approaches.

关键词： Adaptive critic design adaptive dynamic programming(ADP) approximate dynamic programming discrete-time nonlinear systems reinforcement learning stability analysis tracking control value iteration(VI)

来源：评论

学校读者我要写书评

暂无评论

Time-Sensitive Local Differential Privacy-Based Federated Learning for Vehicular Digital Twin Networks 1st

Time-Sensitive Local Differential Privacy-Based Federated Le...

引用

1st International Symposium on Intelligent Computing and Networking, ISICN 2024

作者： Sun, Kangkang Xu, Hansong Zhang, Xiaojin Hua, Kun Li, Jianhua Shanghai Key Laboratory of Integrated Administration Technologies for Information Security School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical Engineering California Polytechnic State University San Luis ObispoCA93407 United States

ISBN: (纸本)9783031674464

The Vehicular Digital Twin Network (VDTN) integrates digital twin (DT) models of connected and autonomous vehicles (CAVs) to facilitate smart sensing, management, and collaboration in the physical realm. VDTN synchronizes extensive data on roads, vehicles, and operators, including sensitive information like user location and driving habits. To address these privacy concerns and enhance model efficiency, we introduce a time-sensitive local differential privacy-based federated learning framework (FedTS) tailored for VDTN. This framework assigns varying privacy levels to DT models during model-sharing intervals, considering the time sensitivity of VDTNs. Comparative analysis with state-of-the-art algorithms, such as differentially-private stochastic gradient descent (DP-SGD), demonstrates significant improvements in both security and model performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Resilient Operation of DC Standalone Microgrids: Experimental Validation of Hybrid RNN-PI Control for Pulse Load Management

Resilient Operation of DC Standalone Microgrids: Experimenta...

引用

2025 IEEE Green Technologies Conference, GreenTech 2025

作者： Aghmadi, Ahmed Mohammed, Osama A. Florida International University Energy Systems Research Laboratory Department of Electrical and Computer Engineering MiamiFL33174 United States

ISBN: (纸本)9798331520182

Effective energy storage system (ESS) management is critical for enhancing the performance of standalone DC microgrids, particularly when integrating renewable energy sources such as photovoltaic (PV) or wind systems. This research describes a new hybrid control technique to improve DC microgrid operations' efficiency and resiliency, especially when handling critical loads. This research presents a hybrid closed-loop control technique that uses Recurrent Neural Networks (RNNs) and Proportional-Integral (PI) controllers to address the complex issues of dynamic load situations and transient disturbances. The RNN evaluates voltage errors to generate accurate reference currents, which the PI controllers then adjust to improve the performance of the bidirectional converter. Unlike standard PI-PI controls, our hybrid approach is particularly effective at regulating pulsed power loads (PPLs) and enhancing system response to transitory situations. The experimental results show that the RNN-PI control scheme significantly improves voltage regulation and transient responsiveness, exceeding conventional performance and resilience techniques. This approach provides a convincing solution for enhancing microgrid systems' stability and efficiency in various real-world applications. © 2025 IEEE.

关键词： Electric load distribution

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：