检索结果-内蒙古大学图书馆

Edge artificial intelligence for big data: a systematic review

Neural Computing and Applications 2024年第19期36卷 11461-11494页

作者： Hemmati, Atefeh Raoufi, Parisa Rahmani, Amir Masoud Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Computer Engineering Central Tehran Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan

Edge computing, artificial intelligence (AI), and machine learning (ML) concepts have become increasingly prevalent in Internet of Things (IoT) applications. As the number of IoT devices continues to grow, relying solely on cloud computing for real-time data processing and analysis is proving to be more challenging. The synergy between edge computing and AI is particularly intriguing due to AI's reliance on rapid data processing, a capability facilitated by edge computing. Edge AI represents a significant paradigm shift, leveraging AI within edge computing frameworks to reduce reliance on internet connections and mitigate data latency issues. This approach accelerates data processing, supporting use cases that demand real-time inference. Additionally, as cloud storage costs continue to rise, the feasibility of streaming and storing large volumes of data comes into question. Edge AI offers a compelling solution by performing big data analytics closer to the end device where edge computing is deployed. This paper presents a systematic literature review (SLR) of 85 articles published between 2018 and 2023 within Edge AI. The study provides a comprehensive examination of the analysis of measurement environments and assesses factors applied to Edge AI for big data. It offers taxonomies specific to Edge AI within the big data domain, presents case studies, and outlines the challenges and open issues inherent in Edge AI for big data. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Object Detection using Patch Based Image Classifier and Gradient Importance Map

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 2407-2416页

作者： Jain, Vanita Pillai, Manu S. Jain, Achin Dubey, Arun Kumar Department of Electronic Science University of Delhi Delhi India Center for Research in Computer Vision University of Central Florida Orlando United States Bharati Vidyapeeth’s College of Engineering New Delhi India

Image classification in computer vision has seen tremendous amount of success in recent years. Deep learning has played a pivotal role in achieving human level performance in many image recognition challenges and benchmarks. Even though, image classification has been so successful, no other closely related domains have taken advantage from the efforts put into development of image classification methods. One such closely related field is of Object Detection. Object detection or localisation is a computer vision problem whose solutions have not been victorious enough to human level performance. Many challenges arise when developing object detection models for newly generated domains, one of which is labelling of datasets. Preparation of dataset is one of the most cumbersome and expensive task to accomplish while developing an object detection model. Although, image classifiers are used as a feature extractor in object detection training regimes, their localisation abilities are barely studied. In this paper, we propose an object detection training regime, that does not rely on bounding box labelled datasets, hence unsupervised in nature, and is solely based on trained image classifiers. We build up on our hypothesis, that, "if an image classifier is able to predict what object is in the input image, then it must have information about where the object is, we just need a mechanism to extract that information from it". Precisely, we divide the input image into patches of same size and employ a parameter restricted convolutional classifier on each patches to predict whether it contains the object or not, we call this our patch-based image classifier (the object here is the prediction of the trained image classifier). The training of the patch-based classifier is not straightforward as there is no true labels for each patches on which we can reduce the binary cross-entropy. Therefore, we propose a loss function weighted by the importance map, which we generate using Grad

关键词： Deep learning Grad-CAM Image classification Object detection

来源：评论

学校读者我要写书评

暂无评论

A QoS-based technique for load balancing in green cloud computing using an artificial bee colony algorithm

引用

Journal of Experimental and Theoretical Artificial Intelligence 2025年第2期37卷 307-342页

作者： Tabagchi Milan, Sara Jafari Navimipour, Nima Lohi Bavil, Hamed Yalcin, Senay Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan Department of Computer Engineering University of Applied Sciences & Technology Tabriz Iran Department of Computer Engineering Nisantasi University Istanbul Turkey

Nowadays, high energy amount is being wasted by computing servers and personal electronic devices, which produce a high amount of carbon dioxide. Thus, it is required to decrease energy usage and pollution. Many applications are utilised by green computing to save energy. Scheduling of tasks acts as an important process to reach the mentioned goals. It is worth stating that the vital characteristic of task scheduling in green clouds is the load balancing of tasks on virtual machines. Efficient load balancing moves tasks from overloaded to underloaded virtual machines to maintain the Quality of Service (QoS). This issue is an NP-complete problem, so this research suggests a new technique based on the behavioural structure of artificial bee behaviour. This method aims to improve QoS while lowering energy usage in green computing. In addition, the honey bees are considered the removed tasks from overloaded virtual machines and a candidate for migrating selected tasks with the lowest priority. The CloudSim testing findings demonstrate that the technique is successful in QoS, makespan, and energy usage compared to other ways. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

A Framework for Promoting Passive Breast Cancer Monitoring: Deep Learning as an Interpretation Tool for Breast Thermograms

引用

Iranian Journal of Medical Physics 2024年第4期21卷 237-248页

作者： Firouzmand, Mohamad Majidzadeh, Keivan Jafari, Maryam Haghighat, Shahpar Esmaeili, Rezvan Moradi, Leila Misaghi, Nima Ensafi, Mahsa Batmanghelich, Fatemeh Keyvanpour, Mohammad Reza Shojaedini, Seyed Vahab Biomedical engineering Department Iranian Research Organization for Science & Technology Tehran Iran Breast Cancer Research Center Motamed Cancer Institute ACECR Tehran Iran Department of Computer Engineering Faculty of Engineering Islamic Azad University E-Campus Tehran Iran Department of Computer Engineering Faculty of Engineering Alzahra University Tehran Iran

Introduction: Several types of cancer can be detected early through thermography, which uses thermal profiles to image tissues in recent years, thermography has gained increasing attention due to its non-invasive and radiation-free nature. There is a growing need for thermographic images of breast cancer lesions in different nationalities and ages to develop this technique, however. This study aims to introduce a dataset of breast thermograms. Material and Methods: In this study, thermographic images of breast cancer from Iranian samples were prepared and confirmed due to the limited number of breast thermogram databases. The prepared database was tested using artificial intelligence and another well-known DMR database (Database for Mastology research) in this study to determine its reliability. Results: A variety of deep learning architectures and transfer learning are used to evaluate these databases for accuracy, sensitivity, speed, training compliance, and validation compliance. According to best-fitted structures for both types of databases, the database obtained from this study has a quality comparable to the DMR reference database, with minimum accuracy, sensitivity, specificity, precision, and F-score of 80%, 86%, 86%, 88%, and 87%, respectively. Conclusion: Using thermography as a method of early breast screening is demonstrated to be effective. In comparison to DMR, the lower statistics of the proposed database (between 2 and 7 percent) indicates that more diverse breast thermograms should be captured in conjunction with improvements to imaging equipment as well as adherence to thermography recording protocols in order to improve the reliability and efficiency of the database. © (2024), (Mashhad University of Medical sciences). All rights reserved.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Source-Free Domain Adaptive Semantic Segmentation Via Importance-Aware and Prototype-Contrast Learning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha China College of Engineering and Design Hunan Normal University Changsha China

Domain adaptive semantic segmentation enables robust pixel- wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A hybrid memory architecture supporting fine-grained data migration

引用

Frontiers of computer science 2024年第2期18卷 31-41页

作者： Ye CHI Jianhui YUE Xiaofei LIAO Haikun LIU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Department of Computer Science Michigan Technological UniversityMichigan 49931USA

Hybrid memory systems composed of dynamic random access memory(DRAM)and Non-volatile memory(NVM)often exploit page migration technologies to fully take the advantages of different memory *** previous proposals usually migrate data at a granularity of 4 KB pages,and thus waste memory bandwidth and DRAM *** this paper,we propose Mocha,a non-hierarchical architecture that organizes DRAM and NVM in a flat address space physically,but manages them in a cache/memory *** the commercial NVM device-Intel Optane DC Persistent Memory Modules(DCPMM)actually access the physical media at a granularity of 256 bytes(an Optane block),we manage the DRAM cache at the 256-byte size to adapt to this feature of *** design not only enables fine-grained data migration and management for the DRAM cache,but also avoids write amplification for Intel Optane *** also create an Indirect Address Cache(IAC)in Hybrid Memory Controller(HMC)and propose a reverse address mapping table in the DRAM to speed up address translation and cache ***,we exploit a utility-based caching mechanism to filter cold blocks in the NVM,and further improve the efficiency of the DRAM *** implement Mocha in an architectural *** results show that Mocha can improve application performance by 8.2%on average(up to 24.6%),reduce 6.9%energy consumption and 25.9%data migration traffic on average,compared with a typical hybrid memory architecture-HSCC.

关键词： non-volatile memory hybrid memory system data migration fine-grained caching

来源：评论

学校读者我要写书评

暂无评论

Automatic text summarization using deep reinforced model coupling contextualized word representation and attention mechanism

引用

Multimedia Tools and Applications 2024年第1期83卷 733-762页

作者： Aliakbarpour, Hassan Manzuri, Mohammad Taghi Rahmani, Amir Masoud Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Computer Engineering Department Sharif University of Technology Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

With the rapid and unprecedented growth of textual data in recent years, there is a remarkable need for automatic text summarization models to retrieve useful information from these large numbers of textual documents without human intervention within a reasonable time. Text summarization is commonly performed based on extractive and abstractive paradigms. Although different machine learning and deep learning based methods have been proposed for the task of text summarization during the last decades, they are still in their early steps of development and their potential has yet to be fully explored. Accordingly, a new summarization model is proposed in this paper which takes advantage of both extractive and abstractive text summarization models as a single unified model based on the strategy gradient of reinforcement learning. The proposed model also employs the combination of convolutional neural network and gated recurrent unit in both extraction and abstraction modules besides attention mechanism. Moreover, language models, namely Word2Vec and BERT, are used as the backbone of the proposed model to better express sentence semantics as a word vector. We conducted our experiments on widely-studied text summarization datasets (CNN\Daily Mail and DUC-2004) and according to the empirical results, not only the proposed model achieved higher accuracy compared to both extractive and abstractive summarization models in terms of ROUGE metric but also its generated summaries presented higher saliency and readability based on human evaluation. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Solar Cell Defect Detection using Deep-Learning Segmentation with Two-Fold Training 9

Solar Cell Defect Detection using Deep-Learning Segmentation...

引用

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

作者： Narayanan, Mathiyazhagan Mohan, Ramya Rajinikanth, Venkatesan Center for Research and Innovation Department of Computer Science and Engineering TN Chennai602105 India

ISBN: (纸本)9798350377972

Recently, the applications of Deep Learning (DL) methodologies have been extensively utilized across numerous areas to extract critical solutions from selected databases. The DL Segmentation Tool (DLST) is frequently utilized to extract and assess selected segments from digital images captured using various modalities. This study intends to propose a DLST to analyze the selected database for the identification of defects in solar cells. The proposed DLST encompasses several phases: (i) image acquisition and resizing, (ii) application of an image preprocessing technique to improve defect visibility, (iii) execution of the segmentation process utilizing a selected DL-model to extract the defect, and (iv) comparison of the segmented region with a binary mask and calculation of performance metrics. The created DLST incorporates the VGG-UNet, with VGG19 serving as the model's backbone. This work implemented a two-fold training approach for improved outcomes. The experimental result is validated using selected image metrics, demonstrating that the proposed DLST yields superior values of Jaccard (91.31%), Dice (95.38%), and Accuracy (96.18%) in comparison to other chosen DL models. © 2024 IEEE.

关键词： Image acquisition

来源：评论

学校读者我要写书评

暂无评论

A nano-scale arithmetic and logic unit using a reversible logic and quantum-dots

引用

Journal of Supercomputing 2024年第1期80卷 395-412页

作者： Navimipour, Nima Jafari Ahmadpour, Seyed-Sajad Yalcin, Senay Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Department of Computer Engineering Nisantasi University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou64002 Taiwan

The arithmetic and logic unit (ALU) is a key element of complex circuits and an intrinsic part of the most widely recognized complex circuits in digital signal processing. Also, recent attention has been brought to reversible logic and quantum-dot cellular automata (QCA) because of their intrinsic capacity to decrease energy dissipation, which is a crucial need for low-power digital circuits. QCA will be the preferred technology for developing the subsequent generation of digital systems. These technologies played a substantial role in the design of the ALU for operations such as multiplication, subtraction, and division. In developing reversible logic and QCA technologies, the ALU is frequently studied as a central unit. Implementing an efficient ALU with low quantum cost and a small number of cells based on an efficient reversible block can solve all previous issues. Therefore, this research constructs a Feynman gate, a Fredkin gate, and full adder circuits using reversible logic and QCA technology. Using all of the specified circuits, a 20-operation ALU is constructed. The power consumption of the proposed ALU under various energy ranges demonstrated significant improvements over earlier designs. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Features Fusion for Colorectal Cancer Detection from Histopathology Images 9

Deep Learning and Features Fusion for Colorectal Cancer Dete...

引用

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

作者： Rajinikanth, Venkatesan Mohan, Ramya Narayanan, Mathiyazhagan Center for Research and Innovation Department of Computer Science and Engineering TN Chennai602105 India

ISBN: (纸本)9798350377972

Modern hospitals have extensively adopted the automatic disease examination methods to detect diseases from biomedical images of selected modalities. These methods reduce the diagnostic burden and enhance detection accuracy. This study seeks to create a Deep-Learning (DL) tool for the analysis of histopathology images related to colorectal cancer (CC). This DL-tool consists of the following stages: image collection and resizing, feature extraction using a selected DL-scheme, feature reduction through 50% dropout and serial feature fusion to create the Fused-Features-Vector (FFV), followed by binary classification and 3-fold cross-validation to validate the results. This study initially examines traditional DL-models for classification using SoftMax. Based on the results, the two best models are selected to generate the FFV. This study examines the features of VGG16 and ResNet101 to produce the FFV, thereby validating the effectiveness of the proposed scheme. The CC detection utilizing the FFV achieved an accuracy exceeding 95%, confirming that the developed scheme yields improved results on the selected data. © 2024 IEEE.

关键词： Lung cancer

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：