检索结果-内蒙古大学图书馆

Multi-stage Conditional GAN Architectures for Person-Image Generation 1

1st International Conference and 2nd International Conference on Deep Learning Theory and Applications, DeLTA 2020 and DeLTA 2021

作者： Kurupathi, Sheela Raju Dumpala, Veeru Stricker, Didier Department of Computer Science Technical University of Kaiserslautern Kaiserslautern Germany Augmented Vision German Research Center for Artificial Intelligence Kaiserslautern Germany

ISBN: (数字)9783031373206

ISBN: (纸本)9783031373190

Generating realistic human images has been of great value in recent times due to their varied application in Robotics, computer Graphics, Movie Making, and Games. Advancements in Artificial Intelligence (AI) and Machine learning (ML) lead to the rapid growth of integrating every aspect into AI and ML. There are many deep learning models like Variational Auto Encoders (VAE), Stacked Hourglass networks and Generative Adversarial Networks (GANs) for solving human-image generation. However, it is still difficult for these models to generalize well to the real-world person-image generation task qualitatively. In this paper, we develop a multi-stage model based on Conditional GANs, which could synthesize the new image of the target person given the image of the person and the target (novel) pose desired in real-world scenarios. The model uses 2D keypoints to represent human poses. We propose a Multi-stage Person Generation (MPG) model, in which we have modified the Generator architecture of Pose Guided Person Image Generation (PG2) resulting in two approaches. The first three-stage person generation approach has an additional generator integrated to base architecture and has trained the model end-to-end. The second two-stage person generation approach has a novel texture feature block in stage-II and has been trained incrementally to improve the generation of human-images qualitatively. The proposed two-stage MPG approach has generated promising results on Market-1501 Dataset. The claims are supported by benchmarking the proposed models with recent state-of-the-art models. We also show how the multi-stage conditional GAN architectures influence the process of human-image synthesis. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Long Short-Term Memory and Gated Recurrent Unit Based Smart Vessel Trajectory Prediction Using Automatic Identification System Data

引用

computers, Materials & Continua 2024年第10期81卷 1789-1808页

作者： Umar Zaman Junaid Khan Eunkyu Lee Sajjad Hussain Awatef Salim Balobaid Rua Yahya Aburasain Kyungsup Kim Department of Computer Engineering Chungnam National UniversityDaejeon34134Republic of Korea Department of Environmental IT Engineering Chungnam National UniversityDaejeon34134Republic of Korea Autonomous Ship Research Center Samsung Heavy IndustriesDaejeon34051Republic of Korea ICAROS Center(PRISMA Lab) University of Naples Federico IINaples80131Italy Department of Computer Science College of Computer Science and Information TechnologyJazan UniversityJazan45142Saudi Arabia

Maritime transportation,a cornerstone of global trade,faces increasing safety challenges due to growing sea traffic *** study proposes a novel approach to vessel trajectory prediction utilizing Automatic Identification System(AIS)data and advanced deep learning models,including Long Short-Term Memory(LSTM),Gated Recurrent Unit(GRU),Bidirectional LSTM(DBLSTM),Simple Recurrent Neural Network(SimpleRNN),and Kalman *** research implemented rigorous AIS data preprocessing,encompassing record deduplication,noise elimination,stationary simplification,and removal of insignificant *** were trained using key navigational parameters:latitude,longitude,speed,and *** aware processing through trajectory segmentation and topological data analysis(TDA)was employed to capture dynamic *** using a three-month AIS dataset demonstrated significant improvements in prediction *** GRU model exhibited superior performance,achieving training losses of 0.0020(Mean Squared Error,MSE)and 0.0334(Mean Absolute Error,MAE),with validation losses of 0.0708(MSE)and 0.1720(MAE).The LSTM model showed comparable efficacy,with training losses of 0.0011(MSE)and 0.0258(MAE),and validation losses of 0.2290(MSE)and 0.2652(MAE).Both models demonstrated reductions in training and validation losses,measured by MAE,MSE,Average Displacement Error(ADE),and Final Displacement Error(FDE).This research underscores the potential of advanced deep learning models in enhancing maritime safety through more accurate trajectory predictions,contributing significantly to the development of robust,intelligent navigation systems for the maritime industry.

关键词： Trajectory prediction AIS data smart vessel deep learning LSTM GRU

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis on Filipino COVID-19 Tweets During Pandemic Period Using Modified K-Means and Ensemble Model with Supervised Machine Learning Algorithms as Base Estimators 10

Sentiment Analysis on Filipino COVID-19 Tweets During Pandem...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Sindayen, Carlo Danilo V. Gaite, Fernando Luis C. Rogando, Francis Thomas G. Acula, Donata D. University of Santo Tomas Department of Computer Science Manila Philippines University of Santo Tomas Research Center for Natural and Applied Sciences Department of Computer Science Manila Philippines

ISBN: (纸本)9798350363104

Since 2020, the COVID-19 pandemic has prompted a global shift to online living. Sentiment Analysis, a Natural Language Processing method, categorizes text data into positive, negative, or neutral sentiments. This study analyzed COVID-19-related tweets in Filipino, English, or Taglish using clustering and classifier algorithms. Clustering methods included Modified K-means with PCA, Percentile Method, and Weighted Average. Classifiers comprised the Combination Ensemble Model and individual Base Estimators like Complement Naive Bayes, Support Vector Machine, Logistic Regression, and Random Forest. The Modified K-Means through a PCA and Percentile method divided the dataset into 6 clusters, with an average of 0.4276, 15334.6503, and 0.8361 for Silhouette Coefficient, Calinski-Harabasz and Davies-Bouldin scores, respectively. The Combination Ensemble achieved mean accuracies ranging from 56.4824% to 96.1268% based on cluster. Based on the paired t-test, the modified K-Means with PCA and Percentile did not significantly improve over the modified K-Means with a weighted average approach. The Combination Ensemble was a significant improvement over Multinomial Naive Bayes but was not a significant improvement as compared with each Base Estimator. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Coupling Mobile Brain Imaging and Virtual Reality Omnidirectional Treadmill to Explore Attenuated Situational Awareness during Distracted Walking

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期16卷 1063-1076页

作者： Chuang, Chun-Hsiang Chiu, Tsai-Feng Hsu, Hao-Che Lin, Shih-Syun National Tsing Hua University Research Center for Education and Mind Sciences College of Education The Institute of Information Systems and Applications College of Electrical Engineering and Computer Science Hsinchu300 Taiwan National Tsing Hua University Research Center for Education and Mind Sciences Hsinchu300 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300193 Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung20224 Taiwan

Walking while engaging in distracting activities affects our perception of changes happening on the road, leading to exposure to hazardous conditions. This study aimed to evidence that pedestrians who become distracted when absorbed in their smartphones fail to maintain situational awareness. Thirty-six recruited participants performed a psychomotor vigilance task and a wayfinding task designed to simulate a multitasking scenario;meanwhile, an auditory oddball paradigm presented to participants tested their situational awareness of an external stimulus. The experiment was conducted in virtual reality (VR) environment with an omnidirectional treadmill. Participant's behavioral and electroencephalographic (EEG) responses were measured and analyzed using a newly proposed brain network measure, phase locking distance (PLD), to capture multitasking-associated couplings between brain regions. The current study supports the notion that multitasking can lead to diminished behavioral performance and changes in walking patterns. Despite the increased interregional brain connectivity, which may be an adaptive response to heightened cognitive demands, the associated reduction in event-related EEG activity suggests competition for neural resources during multitasking. Moreover, the observed EEG activities could indicate additional information processing capacity limitations and provide evidence of decreased situational awareness during multitasking, thereby increasing susceptibility to potentially hazardous situations. © 2016 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Adaptive Resource Planning for AI Workloads with Variable Real-Time Tasks

引用

computers, Materials & Continua 2023年第3期74卷 6823-6833页

作者： Sunhwa Annie Nam Kyungwoon Cho Hyokyung Bahn Department of Computer Science and Engineering Ewha UniversitySeoul03760Korea Embedded Software Research Center Ewha UniversitySeoul03760Korea

AI(Artificial Intelligence)workloads are proliferating in modernreal-time *** the tasks of AI workloads fluctuate over time,resourceplanning policies used for traditional fixed real-time tasks should be *** particular,it is difficult to immediately handle changes inreal-time tasks without violating the deadline *** cope with thissituation,this paper analyzes the task situations of AI workloads and findsthe following two ***,resource planning for AI workloadsis a complicated search problem that requires much time for ***,although the task set of an AI workload may change over time,thepossible combinations of the task sets are known in *** on theseobservations,this paper proposes a new resource planning scheme for AIworkloads that supports the re-planning of *** of generatingresource plans on the fly,the proposed scheme pre-determines resourceplans for various combinations of ***,in any case,the workload isimmediately executed according to the resource plan ***,the proposed scheme maintains an optimized CPU(Central Processing Unit)and memory resource plan using genetic algorithms and applies it as soonas the workload *** proposed scheme is implemented in the opensourcesimulator SimRTS for the validation of its *** show that the proposed scheme reduces the energy consumptionof CPU and memory by 45.5%on average without deadline misses.

关键词： Resource planning artificial intelligence real-time system task scheduling optimization problem genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Accurate threat hunting in industrial internet of things edge devices

引用

Digital Communications and Networks 2023年第5期9卷 1123-1130页

作者： Abbas Yazdinejad Behrouz Zolfaghari Ali Dehghantanha Hadis Karimipour Gautam Srivastava Reza M.Parizi Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical and Software Engineering University of CalgaryAlbertaCanada Department of Mathematics and Computer Science Brandon UniversityBrandonCanada College of Computing and Software Engineering Kennesaw State UniversityGAUSA Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Department of Computer Science and Mathematics Lebanese American UniversityBeirut1102Lebanon

Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire ***,they can allow malicious software installed on end nodes to penetrate the *** paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge *** proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority *** evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.

关键词： IIoT Threat hunting Edge devices Multi-class anomalies Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

Augmenting Internet of Medical Things Security:Deep Ensemble Integration and Methodological Fusion

引用

computer Modeling in Engineering & sciences 2024年第12期141卷 2185-2223页

作者： Hamad Naeem Amjad Alsirhani Faeiz MAlserhani Farhan Ullah Ondrej Krejcar Faculty of Informatics and Management Center for Basic and Applied ResearchUniversity of Hradec KraloveHradec Kralove50003Czech Republic Department of Computer Science College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Department of Computer Engineering&Networks College of Computer and Information SciencesJouf UniversityAl Jouf72388Saudi Arabia Cybersecurity Center Prince Mohammad Bin Fahd UniversityAl JawharahKhobarDhahran34754Saudi Arabia

When it comes to smart healthcare business systems,network-based intrusion detection systems are crucial for protecting the system and its networks from malicious network *** protect IoMT devices and networks in healthcare and medical settings,our proposed model serves as a powerful tool for monitoring IoMT *** study presents a robust methodology for intrusion detection in Internet of Medical Things(IoMT)environments,integrating data augmentation,feature selection,and ensemble learning to effectively handle IoMT data *** rigorous preprocessing,including feature extraction,correlation removal,and Recursive Feature Elimi-nation(RFE),selected features are standardized and reshaped for deep learning *** using the BAT algorithm enhances dataset *** deep learning models,Transformer-based neural networks,self-attention Deep Convolutional Neural Networks(DCNNs),and Long Short-Term Memory(LSTM)networks,are trained to capture diverse data *** predictions form a meta-feature set for a subsequent meta-learner,which combines model *** classifiers validate meta-learner features for broad algorithm *** comprehensive method demonstrates high accuracy and robustness in IoMT intrusion *** were conducted using two datasets:the publicly available WUSTL-EHMS-2020 dataset,which contains two distinct categories,and the CICIoMT2024 dataset,encompassing sixteen *** results showcase the method’s exceptional performance,achieving optimal scores of 100%on the WUSTL-EHMS-2020 dataset and 99%on the CICIoMT2024.

关键词： Cyberattack ensemble learning feature selection intrusion detection smart cities machine learning BAT augmentation

来源：评论

学校读者我要写书评

暂无评论

Improving the Resource Allocation in IoT Systems Based on the Integration of Reinforcement Learning and Rule-Based Approaches in Multi-agent Systems 8

Improving the Resource Allocation in IoT Systems Based on th...

引用

8th International Conference on Smart Cities, Internet of Things and Applications, SCIoT 2024

作者： Yarahmadi, Hossein Navidi, Hamidreza Challenger, Moharram University of Antwerp Department of Computer Science Belgium Islamic Azad University Department of Computer Engineering Borujerd Branch Borujerd Iran Shahed University Department of Mathematics and Computer Science Tehran Iran University of Antwerp Flanders Make Strategic Research Center Department of Computer Science Flanders Belgium

ISBN: (纸本)9798350374674

In recent years, the spread of Multi-agent Systems (MAS) and Reinforcement Learning (RL) as a subdomain of Machine Learning (ML) has affected many fields, such as Cyber-Physical Systems (CPS) and the Internet of Things (IoT). There are many Multi-agent Reinforcement Learning (MARL) applications in CPS and IoT, including energy management, smart transportation systems, job scheduling, etc. Due to the fact that the RL and MARL are slow processes, it is necessary to improve and accelerate them. In this study, we review some applications of MAS in the CPS and IoT. To improve the decision-making in MAS, we apply a combination of learning and reasoning (rule-based). We tested the performance of our proposed method in smart homes for 4 distinct tasks, including Face Detection and Window Blind Control, Finger Touch and Gate Control, Weather Check and Thermostat Control, and Temperature Check and Start Fan to assess its efficacy. We applied our method to the job scheduling problem using two parameters: process unit and bandwidth. The results reveal that the proposed approach performed better than the bankruptcy methods based on these criteria. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Bolt Classification for a Retail Motorcycle Shop in Thailand 27

Fast and Accurate Bolt Classification for a Retail Motorcycl...

引用

27th International computer science and Engineering Conference, ICSEC 2023

作者： Angkapiyasiri, Monchai Phimoltares, Suphakant Research Center Faculty of Science Department of Mathematics and Computer Science Bangkok Thailand

ISBN: (纸本)9798350342109

People have begun to improve their purchase of products and food via online applications because of the ongoing global pandemic. Especially, purchasing products through online applications is popular due to their convenience. Hence, numerous riders need motorcycles to work for delivery. As a result, critical spare parts such as durable and beautiful bolts are highly demanded for maintenance. We collect the best-selling bolts of 19 classes from a motorcycle shop to develop a bolt classification procedure and improve business opportunities. A combination of principal component analysis, median cut algorithm, and structural analysis, is used for extracting a set of features. Then, five classification models, which are multi-layer perceptron, random forest, decision tree, support vector machine, and logistic regression, are used to assign the most appropriate class for each bolt. The experiment results show that the multi-layer perceptron performs better than the other classification models. © 2023 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Solving dynamic optimization problems using parent–child multi-swarm clustered memory (PCSCM) algorithm

引用

Neural Computing and Applications 2024年第31期36卷 19549-19583页

作者： Mohammadpour, Majid Mostafavi, Seyedakbar Mirjalili, Seyedali Department of Computer Engineering Yazd University Yazd Iran Center for Artificial Intelligence Research and Optimization Torrens University Australia Brisbane Australia Faculty of Electrical Engineering and Computer Science VŠB-TU Ostrava Czech Republic

The Particle Swarm Optimization (PSO) algorithm faces several inherent challenges when applied to dynamic and large-scale optimization problems. These challenges encompass the issues of outdated particle memory, inadequate scalability in high-dimensional search spaces, the incapability to detect environmental changes, a continual trade-off between exploration and exploitation, and the potential loss of population diversity within the problem space. To address these challenges, we propose a novel hybrid PSO algorithm, denoted as Parent–Child Multi-Swarm Clustered Memory (PCSCM). PCSCM is explicitly designed to leverage an enhanced memory system, capable of mitigating the issue of outdated particle memory after convergence, and efficiently adapting to changing environmental conditions. This innovative memory system retains and retrieves promising solutions from the past when environmental alterations occur. Additionally, PCSCM introduces clustering mechanisms for particles within each swarm, aimed at augmenting diversity within the problem space. This clustering strategy substantially bolsters the algorithm’s performance in tracking evolving optimal solutions and positively contributes to its scalability. Crucially, the clustering approach is implemented not only for the main population but also for stored solutions in memory, which collectively strike a balance between exploration and exploitation. In the proposed method, particle swarms are divided into parent and child swarms, with parent swarms dedicated to preserving diversity;while, child swarms focus on identifying local solutions. These clustering and memory strategies are consistently applied within each sub-swarm to effectively address the challenges posed by high-dimensional search spaces. In addition to addressing challenges related to dynamic optimization, our proposed Parent–Child Multi-Swarm Clustered Memory (PCSCM) algorithm introduces an innovative mechanism for detecting environmental changes. This n

关键词： Chaos theory

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：