检索结果-内蒙古大学图书馆

Setting up SLAs using a dynamic pricing model and behavior analytics in business and marketing strategies in cloud computing

引用

Personal and Ubiquitous Computing 2023年第6期27卷 2225-2241页

作者： Mehlabani, Ehsan Gorjian Javadpour, Amir Zhang, Chongqi Ja’fari, Forough Sangaiah, Arun Kumar Department of Probability and Statistics Guangzhou University Guangzhou510006 China Harbin Institute of Technology Shenzhen China ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900-347 Portugal Department of Computer Engineering Sharif University of Technology Tehran Iran International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Yunlin64002 Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon

Increasing amounts of data are being generated every year. Sustainable computing systems have become capable of extracting and learning information from the underlying data. Edge and AI (artificial intelligence) are expanding into industrial systems requiring new computing and networking infrastructure. Due to this, SLA computing is becoming increasingly challenging to handle in these emerging cloud environments. The cloud is a service that provides virtual resources to users. Qualitative and quantitative findings in market-oriented approaches are one of the most common methods for managing virtual and physical machines in a network. When allocating services, price is an important factor to consider. In this study, we aim to determine the initial price of VMs while considering the dynamic pricing model in a competitive, sustainable computing system. Besides negotiation-based trading, a multifactor architecture is used for trading in the marketplace. Based on the simulation results, it was found that the performance could be improved by categorizing the VMs based on regression. According to the simulation results, the cloud market system provides a better service-level agreement (SLA) and response time when assigning virtual machines to the market. Based on the results, we found that using the regression method for categorizing the VMs to manage the market improved the SLA. © 2023, The Author(s).

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Joint Learning for Multitasking Models 1

引用

7th International Conference on Data science and Engineering, ICDSE 2021

作者： Chemmanam, Ajai John Jose, Bijoy A. Cyber Physical Systems Lab Department of Electronics Cochin University of Science and Technology Kerala Kochi India Cyber Physical Systems Lab Department of Computer Science Cochin University of Science and Technology Kerala Kochi India

ISBN: (数字)9789811944536

ISBN: (纸本)9789811944529

Artificial intelligence using neural networks has made tremendous progress in the field of computer vision. State-of-the-art models have been developed for various computer vision tasks such as image classification, object detection, image segmentation and keypoint estimation. Many of these models are tuned to get highest benchmark scores on curated datasets for any single specific task. However, deploying them to industrial use cases often requires multiple models to be used sequentially or as an ensemble to address different business use cases. Better hardware, model optimisation techniques such as quantisation and pruning have been widely used to improve the performance of individual models. In most cases, the features extracted by a model is not effectively used by the subsequent models. Each model will have its own pre- and post-processing which is a considerable overhead when scaled to industry requirements. We explore the concept of multitasking architectures and propose a joint learning approach to train a multitasking model that can do object detection, keypoint estimation and instance segmentation together using a single forward pass through it. Learning to predict multiple closely related tasks should help the model to learn better representations of the trained data and become robust to overfitting. Our best performing model achieved 32.26 frames per second (fps) with 41.2 AP on object detection, 38.2 AP on instance segmentation and 53.0 AP on keypoint estimation tasks when evaluated on COCO validation dataset. A lighter version of the model was able to process at 41.66 fps, enabling real-time computations for most use cases. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Proposed 3D chaos-based medical image cryptosystem for secure cloud-IoMT eHealth communication services

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1-28页

作者： El-Shafai, Walid Khallaf, Fatma El-Rabaie, El-Sayed M. El-Samie, Fathi E. Abd Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Ahram Canadian University Giza 6th October City Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh84428 Saudi Arabia

Medical image encryption is a mandatory process in various healthcare, Internet of Medical Things (IoMT) and cloud services. This paper provides a robust cryptosystem based on a 3D chaotic map for the medical image encryption in secure IoMT and cloud services. The proposed encryption method depends on a 3D chaotic map. With this map, a nonlinear ciphering process is implemented for pixel value diffusion and position permutation. Five operations are conducted in the suggested cryptosystem on the medical images to be transmitted in order to attain a high security level. These operations are 3D chaos generation, chaos histogram equalization, row rotation, column rotation, and XOR operation. To validate the suggested cryptosystem, different medical images with different characteristics are tested. Moreover, the suggested cryptosystem and more recent state-of-the-art security systems are discussed and analyzed in a comparative study. Different assessment parameters are adopted to assess the suggested cryptosystem, which reveals high security performance. The simulation outcomes show that the suggested cryptosystem is trustworthy. Furthermore, it offers high robustness levels and recommended security levels for utilization in healthcare, IoMT and cloud service applications. It is observed that the amount of average entropy obtained by the proposed 3D chaos cryptosystem is 7.95 which is very close to its best value of 8, and the average NPCR value is 99.62% which is also much close to its supreme value of 99.60%. In addition, all other results scored for the test evaluation parameters on the suggested cryptosystem are superior to those of the traditional security systems. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Video and image quality improvement using an enhanced optimized dehazing technique

引用

Multimedia Tools and Applications 2024年 1-19页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

The detrimental effects of atmospheric haze frequently plague outdoor imagery. This phenomenon arises from the scattering of light by minute particles within the ambient environment surrounding the scene to be imaged. Haze engenders an overall whitening of the image, leading to diminished contrast. To address these issues and enhance the quality of hazy images and videos, an enhanced dehazing technique is proposed. The proposed technique includes image enhancement before the optimal dehazing process. The enhancement stage entails the implementation of both homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE), serving to control the image dynamic range, while concurrently heightening the image contrast. The culminating stage encompasses an optimized dehazing technique, adept at expunging haze-induced artifacts from images. The homomorphic processing and CLAHE, applied in the pre-processing step, establish a foundation for the subsequent dehazing procedure. This proposed methodology is systematically applied to a gamut of visual outputs, including visible videos, Near-Infrared (NIR) frames, and authentic hazy images. Comparative evaluations of the proposed technique, homomorphic-processing-based enhanced dehazing, and standalone dehazing techniques is undertaken on different video types encompassing five frames. It is evident that the proposed technique, synergizing the homomorphic processing, CLAHE, and dehazing, outperforms alternative strategies. Furthermore, the proposed technique is subjected to a comparative study with various existing dehazing techniques over real hazy images. The assessment depends on Peak Signal-to-Noise Ratio (PSNR), correlation, and entropy metrics. The results underscore the efficacy of the proposed technique, particularly in terms of spectral entropy enhancement of dehazed frames. For both visible and NIR frames, the percentages of enhancement by the proposed technique are 17.66% and 118.48%, respectively. ©

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

EQUIVARIANT GRAPH MECHANICS NETWORKS WITH CONSTRAINTS 10

EQUIVARIANT GRAPH MECHANICS NETWORKS WITH CONSTRAINTS

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Huang, Wenbing Han, Jiaqi Rong, Yu Xu, Tingyang Sun, Fuchun Huang, Junzhou Tsinghua University China Department of Computer Science and Technology Tsinghua University China Tencent AI Lab Department of Computer Science and Engineering University of Texas Arlington United States

Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and commonly geometrically-constrained. Current methods, particularly the ones based on equivariant Graph Neural Networks (GNNs), have targeted on the first two challenges but remain immature for constrained systems. In this paper, we propose Graph Mechanics Network (GMN) which is combinatorially efficient, equivariant and constraint-aware. The core of GMN is that it represents, by generalized coordinates, the forward kinematics information (positions and velocities) of a structural object. In this manner, the geometrical constraints are implicitly and naturally encoded in the forward kinematics. Moreover, to allow equivariant message passing in GMN, we have developed a general form of orthogonality-equivariant functions, given that the dynamics of constrained systems are more complicated than the unconstrained counterparts. Theoretically, the proposed equivariant formulation is proved to be universally expressive under certain conditions. Extensive experiments support the advantages of GMN compared to the state-of-the-art GNNs in terms of prediction accuracy, constraint satisfaction and data efficiency on the simulated systems consisting of particles, sticks and hinges, as well as two real-world datasets for molecular dynamics prediction and human motion capture. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Enhancing visual clarity in hazy media: a comprehensive approach through preprocessing and feature fusion attention-based dehazing

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

Particles in the atmosphere, such as dust and smoke, can cause visual clarity problems in both images and videos. Haze is the result of the interaction between airborne particles and light, which is scattered and attenuated. Hazy media present difficulties in a variety of applications due to the reduced contrast and loss of essential information. In response, dehazing techniques have been introduced to bring hazy videos and images back to clarity. Here, we provide a novel technique for eliminating haze. It comprises preprocessing steps before dehazing. Preprocessing is applied to hazy images through homomorphic processing and Contrast Limited Adaptive Histogram Equalization (CLAHE). We present a dehazing technique referred to as the pre-trained Feature Fusion Attention Network (FFA-Net) that directly lets dehazed images be restored from hazy or preprocessed hazy inputs without requiring the determination of atmospheric factors, such as air light and transmission maps. The FFA-Net architecture incorporates a Feature Attention (FA) method to do this task. We assess the proposed technique in a variety of circumstances, including visible frames, Near-Infrared (NIR) frames, and real-world hazy images. Evaluation criteria like entropy, correlation, and Peak Signal-to-Noise Ratio (PSNR) are used to compare the quality of dehazed frames or images to their hazy counterparts. Furthermore, histogram analysis and spectral entropy are adopted to determine the effectiveness of the proposed technique in comparison to existing dehazing techniques. Comparative results are presented for both real-world and simulated environments. The benefits of the proposed technique are demonstrated by a comparison of the results obtained from the standalone pre-trained FFA-Net and the proposed comprehensive methodology. Moreover, a thorough assessment is carried out for comparing the effectiveness of the proposed FFA-Net technique to those of some current dehazing techniques on real hazy images. T

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Automatic extraction of lightweight and efficient neural network architecture of heavy convolutional architectures to predict microsatellite instability from hematoxylin and eosin histology in gastric cancer

引用

Neural Computing and Applications 2024年第25期36卷 15295-15321页

作者： Rostami, Habib Ashkpour, Maryam Behzadi-Khormouji, Hamed Mokhtari, Maral Khayati, Armin Keshavarz, Ahmad Talatian Azad, Saeed Tabesh, Yahya Computer Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran Artificial Intelligence and Intelligent Healthcare Lab Artificial Intelligence and Data Mining Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Faculty of New Science and Technologies University of Tehran Tehran Iran Department of Computer Science Imec-IDLab University of Antwerp Sint-Pietersvliet 7 Antwerp2000 Belgium Shahid Faghihi Hospital Shiraz University of Medical Sciences Shiraz Iran Department of Computer Science Engineering and IT School of Electrical and Computer Engineering Shiraz University Shiraz Iran Electrical Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran IoT and Signal Processing Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Department of Mathematical Sciences Sharif University of Technology Tehran Iran

Cancers have emerged as a significant concern due to their impact on public health and society. The examination and interpretation of tissue sections stained with Hematoxylin and Eosin (H&E) play a crucial role in disease assessment, particularly in cases like gastric cancer. Microsatellite instability (MSI) is suggested to contribute to the carcinogenesis of specific gastrointestinal tumors. However, due to the nonspecific morphology observed in H&E-stained tissue sections, MSI determination often requires costly evaluations through various molecular studies and immunohistochemistry methods in specialized molecular pathology laboratories. Despite the high cost, international guidelines recommend MSI testing for gastrointestinal cancers. Thus, there is a pressing need for a new diagnostic modality with lower costs and widespread applicability for MSI detection. This study aims to detect MSI directly from H&E histology slides in gastric cancer, providing a cost-effective alternative. The performance of well-known deep convolutional neural networks (DCNNs) and a proposed architecture are compared. Medical image datasets are typically smaller than benchmark datasets like ImageNet, necessitating the use of off-the-shelf DCNN architectures developed for large datasets through techniques such as transfer learning. Designing an architecture proportional to a custom dataset can be tedious and may not yield desirable results. In this work, we propose an automatic method to extract a lightweight and efficient architecture from a given heavy architecture (e.g., well-known off-the-shelf DCNNs) proportional to a specific dataset. To predict MSI instability, we extracted the MicroNet architecture from the Xception network using the proposed method and compared its performance with other well-known architectures. The models were trained using tiles extracted from whole-slide images, and two evaluation strategies, tile-based and whole-slide image (WSI)-based, were employed and comp

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Integrated Analysis of Remote Sensing Imagery for Geological Characterization of Volcanic Terrain: A Focus on Lithology, Geomorphology, and Structure 15

Integrated Analysis of Remote Sensing Imagery for Geological...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Nath, Somalin Shekhar, Sushant Gusain, Raj Vidyarthi, Anurag Prakash, Rishi Gowri, R. Indian Institute of Technology National Centre for Geodesy Kanpur India Propagation Research Lab Department of Electronics & Communication Engineering Dehradun India Graphic Era Hill University Department of Computer Science Engineering Dehradun India

ISBN: (纸本)9798350370249

This study employs advanced radar imaging techniques to conduct a comprehensive analysis of a volcanic terrain, unraveling its geological intricacies through the lenses of lithology, geomorphology, and structural features. The research harnesses the power of synthetic aperture radar (SAR) data to provide unprecedented insights into the Earth's surface, facilitating a holistic understanding of the volcanic landscape. The investigation begins with the utilization of radar backscatter data to discern lithological variations within the volcanic terrain. By correlating radar signatures with known lithological compositions, the study aims to delineate distinct geomorphological units and unveil the spatial distribution of volcanic materials. Additionally, the analysis extends to geomorphological features, employing radar imagery to delineate landforms associated with volcanic activity such as lava flows, calderas, and volcanic cones. Furthermore, the study delves into the structural characteristics of the volcanic terrain, employing radar interferometry techniques to detect and quantify ground deformation associated with identification of fault lines, fractures, and other structural anomalies that contribute to the overall geological context. The integration of these diverse datasets results in a multidimensional understanding of the volcanic landscape, offering valuable insights for geological mapping, hazard assessment, and resource management. The findings of this research contribute to advancing the field of remote sensing and geological exploration, highlighting the efficacy of radar imagery in unraveling the geological complexity of volcanic terrains. Such knowledge is crucial for informed decision-making in areas prone to volcanic activity, ultimately enhancing our ability to mitigate geological risks and promote sustainable development in volcanic regions. © 2024 IEEE.

关键词： Geomorphology Synthetic Aperture Radar Tectonic Structures Volcanic Terrain

来源：评论

学校读者我要写书评

暂无评论

Classification on Compressed DNA Sequences: Correlation-Based Feature Extraction Using Self-Supervised Learning

Classification on Compressed DNA Sequences: Correlation-Base...

引用

IEEE EMBS Conference on Biomedical Engineering and sciences (IECBES)

作者： Sheena K. S. Madhu S. Nair Department of Computer Science Artificial Intelligence & Computer Vision Lab Cochin University of Science and Technology Kochi Kerala India

ISBN: (数字)9798350383409

ISBN: (纸本)9798350383416

Next-generation sequencing is producing data at an exponential rate, which creates immense computation hurdles for reliably and efficiently storing, transmitting, and analysing the data. Compression plays a vital role in managing the challenges associated with the growing volume of genomic data. Direct analysis over the compressed representations of DNA sequences can facilitate scalability, enabling the analysis of larger datasets within reasonable computational resources. The proposed scheme develops a methodology to extract meaningful features from compressed DNA sequences that maintain a high correlation with features from the original sequences. We employed deep learning techniques to maximize feature correlation between original and compressed sequence representations. This approach ensures that the features derived from compressed sequences are as informative and representative as those from the original sequences. We evaluated the proposed method with various state-of-the-art approaches for genomic sequence analysis using a dataset that includes genome sequences of different viruses. According to the results, the features extracted from compressed sequences are discriminative for the classification task; thus, downstream analysis of genomic sequences is possible without decompression.

关键词： Sequential analysis Correlation Sequences computer viruses Scalability Genomics Self-supervised learning Feature extraction Reliability Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection in Internet of Blended Environment Using Ensemble of Heterogeneous Autoencoders(E-HAE)

引用

computer Systems science & Engineering 2023年第9期46卷 3261-3284页

作者： Lelisa Adeba Jilcha Deuk-Hun Kim Julian Jang-Jaccard Jin Kwak ISAA Lab. Department of AI Convergence NetworkAjou UniversitySuwon16499Korea ISAA Lab. Institute for Information and CommunicationAjou UniversitySuwon16499Korea Department of Computer Science and Information Technology Massey UniversityAuckland0745New Zealand Department of Cyber Security Ajou UniversitySuwon16499Korea

Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or *** growing use of Internet of Things(IoT)technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation,as it facilitates multiple new attack vectors to emerge *** such,existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection *** address this problem,we designed a blended threat detection approach,considering the possible impact and dimensionality of new attack surfaces due to the aforementioned *** collectively refer to the convergence of different technology sectors as the internet of blended *** proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational *** extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02%detection ***,performance of the proposed approach was compared with various single model(autoencoder)-based network intrusion detection approaches:autoencoder,variational autoencoder,convolutional variational autoencoder,and long short-term memory variational *** proposed model outperformed all compared models,demonstrating F1-score improvements of 4.99%,2.25%,1.92%,and 3.69%,respectively.

关键词： Network intrusion detection anomaly detection TON_IoT dataset smart grid smart city smart factory digital healthcare autoencoder variational autoencoder LSTM convolutional variational autoencoder ensemble learning

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：