检索结果-内蒙古大学图书馆

Characterization of Memory Access in Deep Learning and Its Implications in Memory Management

computers, Materials & Continua 2023年第7期76卷 607-629页

作者： Jeongha Lee Hyokyung Bahn Institute of Artificial Intelligence and Software Ewha UniversitySeoul03760Korea Department of Computer Science and Engineering Ewha UniversitySeoul03760Korea

Due to the recent trend of software intelligence in the Fourth Industrial Revolution,deep learning has become a mainstream workload for modern computer *** the data size of deep learning increasingly grows,managing the limited memory capacity efficiently for deep learning workloads becomes *** this paper,we analyze memory accesses in deep learning workloads and find out some unique characteristics differentiated from traditional ***,when comparing instruction and data accesses,data access accounts for 96%–99%of total memory accesses in deep learning workloads,which is quite different from traditional ***,when comparing read and write accesses,write access dominates,accounting for 64%–80%of total memory ***,although write access makes up the majority of memory accesses,it shows a low access bias of 0.3 in the Zipf ***,in predicting re-access,recency is important in read access,but frequency provides more accurate information in write *** on these observations,we introduce a Non-Volatile Random Access Memory(NVRAM)-accelerated memory architecture for deep learning workloads,and present a new memory management policy for this *** considering the memory access characteristics of deep learning workloads,the proposed policy improves memory performance by 64.3%on average compared to the CLOCK policy.

关键词： Memory access deep learning machine learning memory access memory management CLOCK

来源：评论

学校读者我要写书评

暂无评论

Utilizing Evidential Reasoning (ER) Approach for software Components Selection

引用

SN computer Science 2025年第3期6卷 1-13页

作者： Ahmad, Nabot Al-Qerem, Ahmad Omar, Firas Jebreen, Issam Department of Software Engineering Al Zaytoonah University of Jordan Amman Jordan Computer Science Department Zarqa University Zarqa Jordan Business Intelligence Department Al Zaytoonah University of Jordan Amman Jordan Software Engineering Department Middle East University Amman Lebanon

software component selection is one of the most challenging problems for software developers to meet customer needs. Despite various methods researchers propose to aid in component selection, a gap exists in addressing the complexities of decision-making under uncertainty. This study utilizes the Evidential Reasoning (ER) approach, which effectively handles multi-criteria decision-making (MCDM) scenarios to evaluate software components for an online bookstore. The methodology involves assessing quality attributes using the ER approach incorporating evaluation grades, weights, and belief degrees to manage information uncertainty. The results demonstrate that the ER approach provides a robust framework for software component selection leading to informed decisions. This approach offers significant advantages in scenarios where traditional MCDM methods are insufficient, thereby enhancing the reliability of component selection in software engineering. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decision making Evidential reasoning Multi-criteria software component

来源：评论

学校读者我要写书评

暂无评论

3-Multi ranked encryption with enhanced security in cloud computing

引用

Digital Communications and Networks 2023年第2期9卷 313-326页

作者： YeEun Kim Junggab Son Reza M.Parizi Gautam Srivastava Heekuck Oh Major in Bio Artificial Intelligence Dept.of Computer Science and EngineeringHanyang UniversityAnsanRepublic of Korea Department of Computer Science Kennesaw State UniversityMariettaUSA Department of Software Engineering Kennesaw State UniversityMariettaUSA Department of Mathematics and Computer Science Brandon UniversityBrandonCanada Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Dept.of Computer Science and Engineering Hanyang UniversityAnsanRepublic of Korea

Searchable Encryption(SE)enables data owners to search remotely stored ciphertexts selectively.A practical model that is closest to real life should be able to handle search queries with multiple keywords and multiple data owners/users,and even return the top-k most relevant search results when *** refer to a model that satisfies all of the conditions a 3-multi ranked search ***,SE schemes that have been proposed to date use fully trusted trapdoor generation centers,and several methods assume a secure connection between the data users and a trapdoor generation *** is,they assume the trapdoor generation center is the only entity that can learn the information regarding queried keywords,but it will never attempt to use it in any other manner than that requested,which is impractical in real *** this study,to enhance the security,we propose a new 3-multi ranked SE scheme that satisfies all conditions without these security *** proposed scheme uses randomized keywords to protect the interested keywords of users from both outside adversaries and the honest-but-curious trapdoor generation center,thereby preventing attackers from determining whether two different queries include the same ***,we develop a method for managing multiple encrypted keywords from every data owner,each encrypted with a different *** evaluation demonstrates that,despite the trade-off overhead that results from the weaker security assumption,the proposed scheme achieves reasonable performance compared to extant schemes,which implies that our scheme is practical and closest to real life.

关键词： Searchable encryption Multi-keyword search Multiple data owners/users Ranked search Enhanced security

来源：评论

学校读者我要写书评

暂无评论

AI-Based Early Detection of Coronary Artery Disease Using Atherosclerosis Inflammatory and MicroRNA Biomarkers in Angina Patients 6

AI-Based Early Detection of Coronary Artery Disease Using At...

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Sajid, Muhammad Hassan, Ali Khan, Dilshad Ahmed Abbas Gilani, Sayed Tanveer Khan, Shoab Ahmed Bakhshi, Asim Dilawar CEME National University of Sciences and Technology Department of Computer and Software Engineering Islamabad Pakistan Rawalpindi Pakistan MCS National University of Sciences and Technology Department of Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350355703

Coronary artery disease (CAD) is one of the most common causes of sudden cardiac arrest and is responsible for a high percentage of global mortality. Early diagnosis of CAD in patients with chest pain is challenging. Coronary angiography, an invasive procedure that is not widely available in developing countries, confirms the diagnosis of CAD. It is imperative to establish noninvasive biomarkers for the early diagnosis of CAD in patients with angina. Motivated by two recent medical diagnostic studies that used novel molecular (microRNA) and chemical (atherosclerosis-inflammatory) biomarkers for early detection of CAD, the proposed study explores the hidden potential of novel biomarkers using machine learning (ML). The study combines the biomarkers of two medical studies and presents a NUMS-NIHD dataset. From the complete dataset, the best feature set is shortlisted after an extensive evaluative search in the biomarker feature space. Ten ML classifiers are applied to the selected biomarker inputs, including clinical, chemical, and molecular cardiac biomarkers. To select optimal biomarker-classifier combinations, experiments use K-fold cross-validation. The results of K-fold cross-validation are validated against a hold-out set of data. The results are then compared to current state-of-the-art benchmark studies. The detection strategy achieved an accuracy of 90.18%, a sensitivity of 92.33 % and a specificity of 100.00%. The proposed study validated previous medical diagnostic studies and significantly improved the results. These ML biomarkers-classifier combinations can be used to exclude healthy individuals non-invasively before angiography. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

High Performance Automatic ROI Extraction from Hand Images with Convolutional Neural Networks 8

High Performance Automatic ROI Extraction from Hand Images w...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Kosmaz Sunnetci, Betul Bingol, Ozkan Gedikli, Eyup Ekinci, Murat Gumushane University Department of Mathematical Engineering Gümüşhane Turkey Gumushane University Department of Software Engineering Gümüşhane Turkey Karadeniz Technical University Department of Software Engineering Trabzon Turkey Karadeniz Technical University Department of Computer Engineering Trabzon Turkey

ISBN: (纸本)9798331531492

Automatic ROI extraction from hand images is a critical step in palmprint recognition. Traditional methods involve steps such as identifying the region of the hand, finding the valleys between the fingers and marking the palm area. Some of these processes are performed manually and some are performed with image processing techniques. However, these methods are time-consuming, vulnerable to human error, and computationally redundant. In this study, a deep learning-based convolutional neural network is developed for high-performance automatic ROI extraction from hand images. The proposed method eliminates the hand segmentation process and provides a solution where the palm region can be automatically selected directly. This reduces processing time, minimizes human error and improves overall accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Tracking daily paths in home contexts with RSSI fingerprinting based on UWB through deep learning models

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Polo-Rodríguez, A. Valera, J.C. Peral, J. Gil, D. Medina-Quero, J. Department of Computer Engineering Automation and Robotics University of Granada Granada18071 Spain Alicante03690 Spain Department of Software and Computing Systems University of Alicante Alicante03690 Spain

The field of human activity recognition has evolved significantly, driven largely by advancements in Internet of Things (IoT) device technology, particularly in personal devices. This study investigates the use of ultra-wideband (UWB) technology for tracking inhabitant paths in home environments using deep learning models. UWB technology estimates user locations via time-of-flight and time-difference-of-arrival methods, which are significantly affected by the presence of walls and obstacles in real environments, reducing their precision. To address these challenges, we propose a fingerprinting-based approach utilizing received signal strength indicator (RSSI) data collected from inhabitants in two flats (60 m2 and 100 m2) while performing daily activities. We compare the performance of convolutional neural network (CNN), long short-term memory (LSTM), and hybrid CNN+LSTM models, as well as the use of Bluetooth technology. Additionally, we evaluate the impact of the type and duration of the temporal window (future, past, or a combination of both). Our results demonstrate a mean absolute error close to 50 cm, highlighting the superiority of the hybrid model in providing accurate location estimates, thus facilitating its application in daily human activity recognition in residential settings. © The Author(s) 2024.

关键词： Ultra-wideband (UWB)

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

Detection of Man-in-the-Middle Attack Through Artificial Intelligence Algorithm 12th

Detection of Man-in-the-Middle Attack Through Artificial Int...

引用

12th International Symposium on Intelligent Manufacturing and Service Systems, IMSS 2023

作者： Taştan, Ahmet Nail Gönen, Serkan Barışkan, Mehmet Ali Kubat, Cemallettin Kaplan, Derya Yıltaş Pashaei, Elham Computer Engineering Department Istanbul Gelisim University İstanbul Turkey Software Engineering Department Istanbul Gelisim University İstanbul Turkey Aeronautical Engineering Department Istanbul Gelisim University İstanbul Turkey Computer Engineering Department Istanbul University-Cerrahpaşa İstanbul Turkey

ISBN: (纸本)9789819960613

The amalgamation of information technologies and progressive wireless communication systems has profoundly impacted various facets of everyday life, encompassing communication mediums, occupational procedures, and living standards. This evolution, combined with enhanced wireless communication quality, has culminated in an exponential rise in interconnected devices, including domestic appliances, thereby birthing the Internet of Things (IoT) era. This proliferation, facilitated by cloud computing enabling remote device control, concurrently intensifies cybersecurity threats. Traditional Information and Communication Technology (ICT) architectures, characterized by a hub-and-spoke model, are inherently vulnerable to illicit access and Man-in-the-Middle (MITM) intrusions, thereby endangering information confidentiality. Leveraging Artificial Intelligence (AI) can ameliorate this scenario, enhancing threat training and detection capabilities, enabling precise and preemptive attack countermeasures. This research underscores the criticality of addressing the security implications accompanying technological advancements and implementing protective measures. Deploying AI algorithms facilitates efficient passive attack identification and alleviates network device burdens. Specifically, this study scrutinized the ramifications of an MITM attack on the system, emphasizing the detection of this elusive threat using AI. Our findings attest to AI’s efficacy in detecting MITM attacks, promising significant contributions to future cybersecurity research. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Student’s Health Exercise Recognition Tool for E-Learning Education

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 149-161页

作者： Tamara al Shloul Madiha Javeed Munkhjargal Gochoo Suliman AAlsuhibany Yazeed Yasin Ghadi Ahmad Jalal Jeongmin Park Department of Humanities and Social Science Al Ain UniversityAl Ain15551UAE Department of Computer Science Air UniversityIslamabad44000Pakistan Department of Computer Science and Software Engineering United Arab Emirates UniversityAl Ain15551UAE Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Computer Science and Software Engineering Al Ain UniversityAl Ain15551UAE Department of Computer Engineering Korea Polytechnic UniversitySiheung-siGyeonggi-do237Korea

Due to the recently increased requirements of e-learning systems,multiple educational institutes such as kindergarten have transformed their learning towards virtual *** student health exercise is a difficult task but an important one due to the physical education needs especially in young *** proposed system focuses on the necessary implementation of student health exercise recognition(SHER)using a modified Quaternion-basedfilter for inertial data refining and data fusion as the pre-processing ***,cleansed data has been segmented using an overlapping windowing approach followed by patterns identification in the form of static and kinematic signal ***,these patterns have been utilized to extract cues for both patterned signals,which are further optimized using Fisher’s linear discriminant analysis(FLDA)***,the physical exercise activities have been categorized using extended Kalmanfilter(EKF)-based neural *** system can be implemented in multiple educational establishments including intelligent training systems,virtual mentors,smart simulations,and interactive learning management methods.

关键词： E-learning exercise recognition online physical education student’s healthcare

来源：评论

学校读者我要写书评

暂无评论

Defect Detection Model Using Time Series Data Augmentation and Transformation

引用

computers, Materials & Continua 2024年第2期78卷 1713-1730页

作者： Gyu-Il Kim Hyun Yoo Han-Jin Cho Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Korea Contents Convergence Software Research Institue Kyonggi UniversitySuwon-si16227Korea Department of Energy IT Engineering Far East UniversityEumsung-gun27601Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Korea

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much ***,detecting anomalies is very difficult due to data imbalance,temporal dependence,and ***,methodologies for data augmentation and conversion of time series data into images for analysis have been *** paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to *** method of data augmentation is set as the addition of *** involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the *** addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into *** enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the *** anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat *** allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies *** performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to ***,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training *** proposed method can provide an important springboard for research in the field of anomaly detection using time series ***,it helps solve problems such as analyzing complex patterns in data lightweight.

关键词： Defect detection time series deep learning data augmentation data transformation

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：