检索结果-内蒙古大学图书馆

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

Computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A semantic and emotion-based dual latent variable generation model for a dialogue system

引用

CAAI Transactions on Intelligence Technology 2023年第2期8卷 319-330页

作者： Ming Yan Xingrui Lou Chien Aun Chan Yan Wang Wei Jiang State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijingChina School of Information and Communications Engineering Communication University of ChinaBeijingChina Key Laboratory of Acoustic Visual Technology and Intelligent Control System Communication University of ChinaBeijingChina Department of Electrical and Electronic Engineering The University of MelbourneMelbourneVictoriaAustralia School of Data Science and Intelligent Media Communication University of ChinaBeijingChina

With the development of intelligent agents pursuing humanisation,artificial intelligence must consider emotion,the most basic spiritual need in human *** emotional dialogue systems usually use an external emotional dictionary to select appropriate emotional words to add to the response or concatenate emotional tags and semantic features in the decoding step to generate appropriate ***,selecting emotional words from a fixed emotional dictionary may result in loss of the diversity and consistency of the *** propose a semantic and emotion-based dual latent variable generation model(Dual-LVG)for dialogue systems,which is able to generate appropriate emotional responses without an emotional *** from previous work,the conditional variational autoencoder(CVAE)adopts the standard transformer ***,Dual-LVG regularises the CVAE latent space by introducing a dual latent space of semantics and *** content diversity and emotional accuracy of the generated responses are improved by learning emotion and semantic features ***,the average attention mechanism is adopted to better extract semantic features at the sequence level,and the semi-supervised attention mechanism is used in the decoding step to strengthen the fusion of emotional features of the *** results show that Dual-LVG can successfully achieve the effect of generating different content by controlling emotional factors.

关键词： conditional variational autoencoder dual latent space emotional responses latent variable generation

来源：评论

学校读者我要写书评

暂无评论

A General Theory for Kernel Packets: from state space model to compactly supported basis

arXiv

引用

arXiv 2024年

作者： Ding, Liang Tuo, Rui School of Data Science Fudan University China Department of Industrial and System Engineering Texas A&M University United States

It is well known that the state space (SS) model formulation of a Gaussian process (GP) can lower its training and prediction time both to O(n) for n data points. We prove that an m-dimensional SS model formulation of GP is equivalent to a concept we introduce as the general right Kernel Packet (KP): a transformation for the GP covariance K such that Pmi=0 aiDt(j)K(t, ti) = 0 holds for any t ≤ t1, 0 ≤ j ≤ m − 1, and m + 1 consecutive points ti, where Dt(j)f(t) denotes j-th derivative acting on t. We extend this idea to the backward SS model formulation, leading to the left KP for next m consecutive points: Pmi=0 biDt(j)K(t, tm+i) = 0 for any t ≥ t2m. By combining both left and right KPs, we can prove that a suitable linear combination of these covariance functions yields m KP functions compactly supported on (t0, t2m). KPs improve GP prediction time to O(log n) or O(1), enable broader applications including GP’s derivatives and kernel multiplications, and can be generalized to multi-dimensional additive and product kernels for scattered data. © 2024, CC BY.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

A novel myocarditis detection combining deep reinforcement learning and an improved differential evolution algorithm

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1347-1360页

作者： Jing Yang Touseef Sadiq Jiale Xiong Muhammad Awais Uzair Aslam Bhatti Roohallah Alizadehsani Juan Manuel Gorriz Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversiti MalayaKuala LumpurMalaysia Centre for Artificial Intelligence Research(CAIR) Department of Information and Communication TechnologyUniversity of AgderGrimstadNorway Department of Creative Technologies Air UniversityIslamabadPakistan School of Information and Communication Engineering Hainan UniversityHaikouHainanChina Institute for Intelligent Systems Research and Innovation(IISRI) Deakin UniversityWaurn PondsVictoriaAustralia Data Science and Computational Intelligence Institute University of GranadaGranadaSpain

Myocarditis is a serious cardiovascular ailment that can lead to severe consequences if not promptly *** is triggered by viral infections and presents symptoms such as chest pain and heart *** detection is crucial for successful treatment,and cardiac magnetic resonance imaging(CMR)is a valuable tool for identifying this ***,the detection of myocarditis using CMR images can be challenging due to low contrast,variable noise,and the presence of multiple high CMR slices per *** overcome these challenges,the approach proposed incorporates advanced techniques such as convolutional neural networks(CNNs),an improved differential evolution(DE)algorithm for pre-training,and a reinforcement learning(RL)-based model for *** this method presented a significant challenge due to the imbalanced classification of the Z-Alizadeh Sani myocarditis dataset from Omid Hospital in *** address this,the training process is framed as a sequential decision-making process,where the agent receives higher rewards/penalties for correctly/incorrectly classifying the minority/majority ***,the authors suggest an enhanced DE algorithm to initiate the backpropagation(BP)process,overcoming the initialisation sensitivity issue of gradient-based methods like back-propagation during the training *** effectiveness of the proposed model in diagnosing myocarditis is demonstrated through experimental results based on standard performance ***,this method shows promise in expediting the triage of CMR images for automatic screening,facilitating early detection and successful treatment of myocarditis.

关键词： classification differential evolution myocarditis reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Condition Monitoring of Low Voltage Motors in Harsh Environments with Ladybug Beetle Optimization and Context-Aware Graph Convolutional Networks 4

Enhanced Condition Monitoring of Low Voltage Motors in Harsh...

引用

4th International Conference on Sustainable Expert systems, ICSES 2024

作者： Rajasekar, P. Tiwari, Praveen Prakash Sharmila, L. Garg, Akriti Srinivas, Rayudu Tallapragada, V. V. Satyanarayana Srm Institute of Science and Technology Department of Data Science and Business System Tamil Nadu Kattankulathur603203 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai600062 India Mahatma Jyotiba Phule Rohilkhand University Department of Electrical Engineering Uttar Pradesh Bareilly243006 India Aditya College of Engineering & Technology Department of Electrical and Electronics Engineering Andhra Pradesh Surampalem533437 India School of Engineering Mohan Babu University Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517102 India

ISBN: (纸本)9798331540364

Low voltage motors are essential in many applications in contemporary industrial settings, as they power machines and guarantee efficient operations. However, these motors often operate in harsh environments where they are exposed to factors such as extreme temperatures, moisture, dust, and vibrations, which can lead to premature wear and failure. This paper proposes a hybrid method for low voltage motor condition monitoring in challenging industrial environments. The proposed method is the combined execution of Ladybug Beetle Optimization algorithm (LBOA) and Heterogeneous Context-Aware Graph Convolutional Network (HCAGCN). Hence it is named as LBOA-HCAGCN technique. Initially, the input data is collected from Triboelectric vibration sensors. Then, the collected data is fed into preprocessing utilizing Generalized Multi-kernel Maximum Correntropy Kalman Filter (GMKMCKF). This filter normalizes and cleans the data by effectively removing noise. Recursive Hilbert Transform (RHT) is used to extract time domain features such as mean, Root Mean Square (RMS), Peak-to-Peak Value, Skewness, and Kurtosis. Then the extracted features are given to HCAGCN for classify the motor health conditions such as normal, broken-bar, bowed-bar, bowed-rotor, faulty bearing, and voltage imbalance. In general, HCAGCN does not express adapting optimization strategies to determine optimal parameters to classify motor conditions. Hence, the LBOA is used to optimize the weight parameter of the HCAGCN which accurately classify motor conditions. The proposed LBOA-HCAGCN is implemented in MATLAB. Performance indicators such as Mean Absolute Error (MAE), Precision, and Accuracy were used to analyze the effectiveness of the proposed approach. Comparing the proposed LBOA-HCAGCN methodology to other existing techniques like Deep Residual Neural Network (DRNN), Convolutional Neural Network (CNN), and Recursive Neural Network (RNN), it achieves 25.8%, 26.4%, and 24.7% greater accuracy, 26.7%, 29.4%, and

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Res-GC Net: A Road Extraction Method with Multi-Scale Simplified Attention Mechanism for Remote Sensing Images

Res-GC Net: A Road Extraction Method with Multi-Scale Simpli...

引用

Information systems and Computing Technology (ISCTech), International Conference on

作者： Haomeng Wu Yi Wang Yulin Shen Di Wu Boqun Zhang Ze Liu System Demonstration Center Harbin Space Star Data System Technology Co. Ltd Heilongjiang China College of Information and Communication Engineering Harbin Engineering University Harben China Urban Intelligent Computing Department Harbin Space Star Data System Technology Co. Ltd. Harben China

ISBN: (数字)9798350379860

ISBN: (纸本)9798350379877

In the field of remote sensing image analysis, the accurate extraction of road networks is a critical task, particularly in scenarios with complex backgrounds and narrow shapes. To address this challenge, this study introduces a multi-scale GC Block network module that significantly enhances the effective location information in feature maps by simplifying the computation of spatial and channel attention. The module proposed in this paper improves the adaptability to complex road network backgrounds and reduces the computational load of parameters, thereby accelerating the reasoning speed. The network module is designed with flexibility, maintaining consistent input and output dimensions, and supports plug- and-play functionality. Furthermore, an automatically updating head structure has been designed, which effectively suppresses invalid location information in the mask matrix through multiple iterative processes, achieving high boundary segmentation. In experimental evaluations on the CHN6- CUG dataset, the Res-GC Net was compared with traditional semantic segmentation methods, with the key metric of road Intersection over Union (IOU) showing a 5.3% improvement over the best baseline result. The results demonstrate that our network exhibits a significant advantage in capturing road details and recognizing roads that are partially obscured.

关键词： Head Attention mechanisms Accuracy Shape Roads Semantic segmentation Feature extraction data mining Iterative methods Remote sensing

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Smart Manhole Management system for Real-time Status, Water Level, and Gas Detection

IoT-Enabled Smart Manhole Management System for Real-time St...

引用

2024 International Conference on Intelligent systems for Cybersecurity, ISCS 2024

作者： Imran, Md Asif Masfequier Rahman Swapno, S.M. Chhabra, Gunjan Kaushik, Keshav Anzum Mahi, Md. Arif Islam, Md Babul Haque, Rezaul Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Graphic Era Hill University Department of Cse Uttarakhand Dehradun India Graphic Era Deemed to Be University Uttarakhand Dehradun India School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India Modeling Electronic and System Engineering Unical Dept. of Computer Rende Italy Applied Bahari Big Data Research House Dhaka Bangladesh Modeling Electronic and System Engineering Unical Department of Computer Rende Italy

ISBN: (纸本)9798350375237

Regular monitoring of the maintenance manhole system is imperative to uphold the city's health and cleanliness standards. Our study offers an intelligent manhole that monitors the manhole's condition, water level, and gases. We tested the status, gas, and water levels of our revolutionary, innovative manhole in several places. Our system's Blink app position tracking of our smart manhole is critical. This capability improves monitoring efficiency and speeds up issue resolution. Our work revolutionizes municipal utility maintenance and safety by optimizing manhole performance. Integrating a Node MCU, GPS module, gas sensor, ultrasonic sensor, and Android Blynk software creates a complete real-time monitoring and data-collecting system. Combining these technologies, our Manhole Monitoring system improves safety and streamlines maintenance, making municipal infrastructure more robust and efficient. This paper highlights the promising features of IoT and shows how it may be used to improve the smart manhole. In the future, this creative method may result in a more durable and better intelligent city. © 2024 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

Securing IoT-Based Home Automation systems Through Blockchain Technology: Implementation

Securing IoT-Based Home Automation Systems Through Blockchai...

引用

2023 International Conference on system, Computation, Automation and Networking, ICSCAN 2023

作者： Palanivel, N. Madhan, K. Kumar, C. Santhosh Sarathkumar, R. Ragupathi, T. Deivanai, S. Manakula Vinayagar Institute of Technology Department of CSE Puducherry India Mailam Engineering College Department of CSE Tamil Nadu Mailam India Er.Perumal Manimekalai College of Engineering Depte of Cse Hosur India Sri Krishna College of Engineering and Technology Department of Ece Coimbatore India Srm Institute of Science and Technology Department of Data Science and Business System Tamilnadu Kattankulathur India

ISBN: (纸本)9798350315127

Cybersecurity is the large subject matter that connects everything, processes, units and technologies. Network safety is a set of policies and settings. They are the integrity, accessibility and availability of facts and networks. Confidentiality of Software and Hardware Use. Today's community threats are continuously evolving and the surroundings is an increasing number of complex. Similarly, the clever domestic has emerge as a low-security threat. That's why it is so vital to remain secure online. Due to the vulnerability of the clever domestic network, there are purposes in many areas, such as users, locations, data, etc. Some clever units may additionally be lacking from your clever home. The machine has been hardened so that passwords can be scrambled. Unencrypted passwords can be searched on the machine or in the software. The safety of the clever domestic community is pretty high. Prioritize linked gadgets to forestall hackers from gaining access to them. Access to touchy or private data. Failure to do so should put your complete clever domestic community at risk. This learn about builds a mannequin to analyze specific protection problems in clever domestic conversation networks. This lookup wants to use qualitative methods, such as anecdotes. A lookup evaluation was once fundamental to raise out this study. and Other applicable records on the secondary facts series techniques used. Several research have been carried out on the protection threats associated to clever domestic networks and the use of applied sciences derived from block chain technology. Reduce protection troubles and defend your intelligence. Secure your domestic network. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Enhancing Battery State of Charge Prediction in Autonomous systems through Experimental Observer Implementation

Enhancing Battery State of Charge Prediction in Autonomous S...

引用

Electrical engineering and Automatic Control (ICEEAC), International Conference on

作者： Mohammed Amine Zafrane Ahmed Said Nouri Electronic department Signal System and Data Lab University of Science and Technologies of Oran- Algeria Elecrical engineering department Sfax. the National Engineering School of Sfax –ENIS- Tunisia

ISBN: (数字)9798350349740

ISBN: (纸本)9798350349757

Nowadays, ensuring optimal battery performance is indispensable, especially in autonomous navigation scenarios. Our research aims at revolutionizing battery monitoring through a cost-effective, highly reliable system applying Kalman observer and ATMega08 microcontroller technologies. We initiate with methodical sensor identification experiments to evaluate precision and linearity, followed by behavior modeling. Implementing a Kalman filter-based observer on the microcontroller enables precise state of charge (SOC) monitoring by effectively correcting errors and filtering noise. Our system's adaptability is demonstrated through successful validation across various battery types, including lithium-ion and lead-acid, with a focus on parameters like voltage, current, power, and SOC. By introducing an interruptions during discharge, the proposed system accurately tracks voltage fluctuations, like a 1-volt change from 10.3 V to 9.3 V, providing reliable SOC indications, crucial for optimal energy management in autonomous navigation. Furthermore, we enhance data acquisition quality through a user interface LabView, continuously integrating with our monitoring system for optimal energy management insights during navigation.

关键词： Voltage fluctuations Phase measurement Microcontrollers Noise Linearity Observers Batteries

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Enabled Decision-Making Framework for Multi-UAV Mission Planning: A Multiagent Deep Reinforcement Learning Perspective 49

Digital Twin-Enabled Decision-Making Framework for Multi-UAV...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Tan, Longyan Hai, Xingshuo Ma, Ke Fan, Dongming Qiu, Huaxin Feng, Qiang National University of Singapore Department of Statistics and Data Science Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Reliability and System Engineering Beihang University Beijing China School of Transportation Science and Engineering Beihang University Beijing China Flying College Beihang University Beijing China

ISBN: (纸本)9798350331820

The utilization of multiple unmanned aerial vehicles (multi-UAVs) greatly enhances the quality of public services, whereas presents challenges to effective mission planning. Existing research predominantly concentrates on task allocation and path planning, with limited emphasis on integrating UAV deployment and task allocation. Despite the promise of learning-based approaches for joint optimization, their applicability to sim-to-real problems remains restricted. In this paper, we propose a hierarchical decision-making framework empowered by digital twin (DT) technology to enhance resource-efficient utilization and facilitate realtime mission planning. In the upper layer, a swarm of UAVs is divided into subgroups using a K-means method and strategically deployed to corresponding task regions. In the lower layer, a DT-enabled reinforcement learning approach is adopted to leverage real-world experiences. Specifically, we employ a multiagent deep Q learning algorithm to optimize the training process, where each agent interacts with the DT environment through original and target networks to acquire an optimal strategy. The proposed approach is evaluated using simulations that demonstrate its effectiveness in achieving high-quality plans. © 2023 IEEE.

关键词： Decision making

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：