检索结果-内蒙古大学图书馆

Evolution and Role of Optimizers in Training Deep Learning Models

IEEE/CAA Journal of Automatica Sinica 2024年第10期11卷 2039-2042页

作者： XiaoHao Wen MengChu Zhou Guangxi Normal University Guilin 541004China School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China the Helen and John C. Hartmann Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA IEEE

TO perform well,deep learning(DL)models have to be trained *** optimizer should be adopted?We answer this question by discussing how optimizers have evolved from traditional methods like gradient descent to more advanced techniques to address challenges posed by highdimensional and non-convex problem *** challenges include their hyperparameter sensitivity,balancing between convergence and generalization performance,and improving interpretability of optimization *** continue to seek robust,efficient,and universally applicable optimizers to advance the field of DL across various domains.

关键词： Which Deep continue

来源：评论

学校读者我要写书评

暂无评论

Intelligent Daycare: Enhancing Child Safety with IoT and Machine Learning Innovations 9

Intelligent Daycare: Enhancing Child Safety with IoT and Mac...

引用

9th International Conference on Communication and Electronics systems, ICCES 2024

作者： Prathyanga, Amisha Shyaminda, Pasindu Chamikara, Pasan Lakshan, Sachin Thelijjagoda, Samantha Kasthurirathna, Dharshana Sri Lanka Institute of Information Technology Department of Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350377972

Child safety and well-being in daycare settings are important, thus it is vital that the persons in charge be attentive to them. This research tries to solve the problem by introducing a smart and detailed monitoring system that utilizes new technology to enhance safety and support caretakers. The system has various innovative features, such as child missing detection, behavior and facial expression analysis, cry analysis and categorization, and fall detection. Using high-resolution cameras and on-device Edge AI capabilities, it ensures real-time surveillance of children's activities while protecting privacy. The approach integrates behavior and facial expression analysis to assess emotional states, cry recognition to discover childcare needs, as well as a useful fall detection system that can tell the difference between falls and other movements. All these parts synergize to hand over the necessary information to the caregivers on time and in a way that they can act upon. The quantitative experiments in real-time childcare centers show high accuracy through all the components, attesting to the system's reliability and durability. This research has important significance in improving the safety and the frequency response in daycare centers because it gives caregivers automated tools to quickly address the needs of children. While promising, the system has drawbacks, such as potential biases in data models and a reliance on ideal environmental circumstances. Future work intends to improve flexibility across varied daycare situations, improve accuracy through larger datasets, and investigate ethical frameworks for wider application. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

A Vulnerability Detection Method for Smart Contracts Based on Dynamic Meta Optimizer

引用

IEEE Internet of Things Journal 2025年第13期12卷 24904-24915页

作者： He, Daojing Gong, Wei Chan, Sammy Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Jiangxi University of Science and Technology School of Information Engineering Jiangxi Ganzhou China City University of Hong Kong Department of Electrical Engineering Hong Kong Hong Kong

With the increasingly complex blockchain technology environment and emerging security threats, the detection and prevention of vulnerabilities in blockchain smart contracts have become crucial for ensuring the healthy development of blockchain technology and avoiding substantial economic losses. Recently developed vulnerability detection methods for smart contracts suffer from the drawbacks of insufficient feature extraction and inadequate multitask detection. This paper proposes a multifaceted learning model, DLR, based on a dual-loop architecture of meta learning to address these issues by adopting model-agnostic meta-learning techniques. This model employs a syntax analyzer for targeted feature extraction, with graph information used as a supporting tool during the initial stage of feature engineering. Combined with an improved optimizer algorithm in the inner loop, the model can effectively learn and adjust based on the specific requirements of each task. In the outer loop, the model achieves efficient learning rate adjustment for multi-task learning by integrating the adaptive learning rate of the Adam optimizer with a global adjustment using simulated annealing strategy, thereby enhancing performance across diverse tasks. Experimental results demonstrate significant improvements in detection accuracy over state-of-the-art methods for three types of vulnerabilities, with our method achieving detection accuracies of 94.40%, 93.36%, and 94.33% for reentrancy, timestamp dependence, and integer overflow vulnerabilities, respectively. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Application of internet of things in healthcare domain

引用

Journal of Umm Al-Qura University for engineering and Architecture 2023年第1期14卷 1-12页

作者： Almotairi, Khaled H. Computer Engineering Department Computer and Information Systems College Umm Al-Qura University Makkah 21955 Saudi Arabia

Internet of things (IoT) enables machine-to-machine, human-to-human and machine-to-human interaction. Recent advancement in IoT systems has positively impacted the daily activities of humans, from accessing information to the delivery of service in real-time. This has improved healthcare management and services, especially in medical hospitals, for effective and timely access to diagnostic information and treatment of patients. Several existing research mainly focused on the design of IoT architecture, its challenges, and benefits to human society with minor or without considering applying IoT in the healthcare domain. To bridge this gap, this study investigates the implications of IoT integration in the healthcare management domain. It presents a detailed discussion on IoT utilization to improve the functionalities of hospital management system. It also discusses some potential emerging innovations that aids the development and application of IoT in hospital management systems. Investigations show that healthcare personnel can administer treatments to patients anytime–anywhere. Patients, especially the elderly are administered treatment, as well as monitoring their wellbeing while at home with the support of wearable sensor devices. Also, some of the challenges that impedes the integration of IoT application into healthcare domain includes generation of irrelevant huge amount of data, issues of security and privacy of patient information and high cost of IoT adoption. Furthermore, the future research trends in adoption of IoT to improve healthcare domain includes stroke and epileptic seizure predictions and prosthetic sensors which is used to retrieve relevant data or information to aid the treatment of a patient in real-time. © The Author(s) 2022.

关键词： Artificial intelligence Blockchain Healthcare Hospital Management Internet of things (IoT) Machine learning Security Smart equipment

来源：评论

学校读者我要写书评

暂无评论

An Efficient Intrusion Detection Framework for Industrial Internet of Things Security

引用

computer systems Science & engineering 2023年第7期46卷 819-834页

作者： Samah Alshathri Ayman El-Sayed Walid El-Shafai Ezz El-Din Hemdan Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

Recently,the Internet of Things(IoT)has been used in various applications such as manufacturing,transportation,agriculture,and healthcare that can enhance efficiency and productivity via an intelligent management console *** the increased use of Industrial IoT(IIoT)applications,the risk of brutal cyber-attacks also *** leads researchers worldwide to work on developing effective Intrusion Detection systems(IDS)for IoT infrastructure against any malicious ***,this paper provides effective IDS to detect and classify unpredicted and unpredictable severe attacks in contradiction to the IoT infrastructure.A comprehensive evaluation examined on a new available benchmark TON_IoT dataset is *** data-driven IoT/IIoT dataset incorporates a label feature indicating classes of normal and attack-targeting IoT/IIoT ***,this data involves IoT/IIoT services-based telemetry data that involves operating systems logs and IoT-based traffic networks collected from a realistic medium-scale IoT *** is to classify and recognize the intrusion activity and provide the intrusion detection objectives in IoT environments in an efficient ***,several machine learning algorithms such as Logistic Regression(LR),Linear Discriminant Analysis(LDA),K-Nearest Neighbors(KNN),Gaussian Naive Bayes(NB),Classification and Regression Tree(CART),Random Forest(RF),and AdaBoost(AB)are used for the detection intent on thirteen different intrusion *** performance metrics like accuracy,precision,recall,and F1-score are used to estimate the proposed *** experimental results show that the CART surpasses the other algorithms with the highest accuracy values like 0.97,1.00,0.99,0.99,1.00,1.00,and 1.00 for effectively detecting the intrusion activities on the IoT/IIoT infrastructure on most of the employed *** addition,the proposed work accomplishes high performance compared to other recent rela

关键词： Attacks intrusion detection machine learning deep learning industrial IoT TON_IoT dataset

来源：评论

学校读者我要写书评

暂无评论

A Robust Speech Encryption Method Using Segmentation and Chaotic Keys for Enhanced Audio Security 1

引用

3rd International Conference on Advances in Computing Research, ACR 2025

作者： Abu-Faraj, Mua’ad Al-Hyari, Abeer Alqadi, Ziad Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Department of Electrical Engineering Al-Balqa Applied University As Salt19117 Jordan Department of Computers and Networks Engineering Al-Balqa Applied University Amman15008 Jordan

ISBN: (数字)9783031876479

ISBN: (纸本)9783031876462

This paper presents an innovative method for safeguarding audio files. The proposed technique leverages an advanced primary key with a complex structure, offering a vast keyspace resistant to hacking. The private key includes details for segmenting the speech audio file and generating unique chaotic keys for encryption. These keys are extremely sensitive to minor changes in the primary key, flagging any slight alteration during decryption as a hacking attempt. The method is tested and implemented on various speech signals, with the results analyzed to highlight the main features and improvements. The findings demonstrate how the technique improves encryption and decryption by optimizing metrics such as MSE, PSNR, CC, and NSCR. Speed analysis verifies the method’s performance by maximizing the throughput of the speech cryptography process. The results are compared with existing approaches to show the superiority and enhancements provided. This method is straightforward to implement, as it does not require modifying the algorithm when altering the speech audio file or the private key, making it a versatile solution for various speech encryption needs. This research is highly relevant to network security, as it ensures the integrity and confidentiality of transmitted speech signals, preventing unauthorized access and improving overall communication security. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Earthworm Optimization with Improved SqueezeNet Enabled Facial Expression Recognition Model

引用

computer systems Science & engineering 2023年第8期46卷 2247-2262页

作者： N.Sharmili Saud Yonbawi Sultan Alahmari E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Computer Science and Engineering Department Gayatri Vidya Parishad College of Engineering for WomenVisakhapatnamAndhra PradeshIndia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia 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 UniversityRiyadh11564Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass *** techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or *** execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image ***,many studies presented an endwise structure for facial expression recognition by utilizing DL ***,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)*** presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing *** addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)***,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE ***-ranging experimental analysis is carried out to examine the performance of the proposed *** experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.

关键词： Facial expression recognition deep learning computer vision earthworm optimization hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

HazardNet: A thermal hazard prediction framework for datacenters

HazardNet: A thermal hazard prediction framework for datacen...

引用

作者： Seyedkazemi Ardebili, Mohsen Acquaviva, Andrea Benini, Luca Bartolini, Andrea Department of Electrical Electronic and Information Engineering University of Bologna Italy Integrated Systems Laboratory ETH Zurich Switzerland

Modern scientific discoveries rely on an insatiable demand for computational resources. To meet this ever-growing computing demand, the datacenters have been established, which are complex controlled environments that host thousands of computing nodes, storage, high-performance communication networks, cooling systems, etc. A datacenter consumes a large amount of electrical power (in the range of megawatts), which gets completely transformed into heat, creating complex spatial and temporal thermal dissipation problems. Therefore, although a datacenter contains sophisticated cooling systems, minor thermal issues/anomalies can potentially trigger a chain of events that leads to an imbalance between the heat generated by computing nodes and the heat removed by the cooling system, leading to thermal hazards. Thermal hazards are detrimental to datacenter operations as they can lead to IT and facility equipment damage as well as an outage of the datacenter, with severe societal and business losses. So, predicting the thermal hazard/anomaly is critical to prevent future disasters. In doing so, collecting and analyzing large-scale monitoring signals and methodology for anomaly detection and prediction are challenging tasks. In this manuscript, after providing a methodology for defining the thermal anomaly, we proposed HazardNet, a thermal hazard prediction framework that consists of a complete pipeline of deep learning models. We evaluated the proposed framework in two different scenarios. In the first scenario, we evaluated the model's performance over the entire study period, resulting in an F1-score of 0.98. In the second scenario, we enforced causality in the collected data by training and testing the model in two disjunct and consecutive periods, resulting in an F1-score of 0.87. Thanks to these promising results, HazardNet can capture the complex spatial and temporal dependency between datacenter operational parameters and thermal hazards and predict them in advance. ©

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Energy and Secure Efficient Routing for Wireless Sensor Networks

Performance Analysis of Energy and Secure Efficient Routing ...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Hussein, Zainab Mohammed Najim, Ali Hamza Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, Aisha Hassan Universiti Kebangsaan Malaysia Center for Cyber Security Faculty of Information Science and Technology Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Baghdad Iraq Department of Computer Technical Engineering Al-Diwaniyah Iraq College of Computer and Information Technology Computer Networking Systems Department University of Anbar Anbar Iraq Center for Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

Wireless Sensor Networks (WSNs) are essential for various applications, but their architecture makes them vulnerable to attacks. While traditional security methods like authentication and encryption offer some protection, they often fall short against specific node attacks. This paper introduces the Secure Energy Aware Routing (SEAR) strategy, which uses trust-based assessments to exclude malicious nodes while optimizing energy consumption. SEAR factors in node trust, hop time, and residual energy to ensure reliable data transmission through trustworthy nodes. MATLAB simulations on networks of varying sizes (100-500) compare SEAR with existing methods (EAD and EASER), demonstrating SEAR's superior performance. Results show significant improvements in packet delivery ratio (13-16%), network throughput (19-24 %), energy consumption (32-36%), packet loss (16-190/0), and end-to-end latency (21-26%), proving SEAR's effectiveness in enhancing WSN security, energy efficiency, and performance. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Development of a Bias Compensating Q-Learning Controller for a Multi-Zone HVAC Facility

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1704-1715页

作者： Syed Ali Asad Rizvi Amanda J.Pertzborn Zongli Lin IEEE the Department of Electrical and Computer Engineering Tennessee Technological UniversityCookevilleTN 38505 USA the Mechanical Systems and Controls Group in the Building Energy and Environment Division at the National Institute of Standards and Technology(NIST) GaithersburgMD 20899 USA the Charles L.Brown Department of Electrical and Computer Engineering University of VirginiaCharlottesvilleVA 22904-4743 USA

We present the development of a bias compensating reinforcement learning(RL)algorithm that optimizes thermal comfort(by minimizing tracking error)and control utilization(by penalizing setpoint deviations)in a multi-zone heating,ventilation,and air-conditioning(HVAC)lab facility subject to unmeasurable disturbances and unknown *** is shown that the presence of unmeasurable disturbance results in an inconsistent learning equation in traditional RL controllers leading to parameter estimation bias(even with integral action support),and in the extreme case,the divergence of the learning *** demonstrate this issue by applying the popular Q-learning algorithm to linear quadratic regulation(LQR)of a multi-zone HVAC environment and showing that,even with integral support,the algorithm exhibits bias issue during the learning phase when the HVAC disturbance is unmeasurable due to unknown heat gains,occupancy variations,light sources,and outside weather *** address this difficulty,we present a bias compensating learning equation that learns a lumped bias term as a result of disturbances(and possibly other sources)in conjunction with the optimal control *** results show that the proposed scheme not only recovers the bias-free optimal control parameters but it does so without explicitly learning the dynamic model or estimating the disturbances,demonstrating the effectiveness of the algorithm in addressing the above challenges.

关键词： HVAC control optimal tracking Q-learning reinforcement learning(RL)

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：