检索结果-内蒙古大学图书馆

2022 IEEE Photonics Conference, IPC 2022

作者： Wei, Chengli Hu, Jonathan Menyuk, Curtis R. University of Mary Hardin-Baylor Department of Computer Science Engineering and Physics Belton United States Baylor University Department of Electrical and Computer Engineering Waco United States University of Maryland Department of Computer Science and Electrical Engineering Baltimore County Baltimore United States

We investigate directional bending sensors using negative curvature fibers with asymmetric nested tubes. The bend direction and radius can be determined by tracking the high-loss peaks at different transmission bands.... 详细信息

ISBN: (数字)9781665434874

ISBN: (纸本)9781665434874

关键词： Bending (forming)

来源：评论

学校读者我要写书评

暂无评论

Liver Disease Prediction Using Ensemble Technique 8

Liver Disease Prediction Using Ensemble Technique

引用

8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022

作者： Tanuku, Sai Rohith Kumar, Addike Ajay Somaraju, Sai Roop Dattuluri, Rushitaa Reddy, Madana Vamshi Krishna Jain, Sambhav Manipal University Department of Computer and Communication Engineering Manipal India Cmr College Department of Computer Science Engineering Telangana India Jntua College of Engineering Department of Electrical and Communication Technology Kalikiri India Ssn College of Engineering Department of Computer Science Engineering Maharashtra Ahmedabad India Bml Munjal University Department of Computer Science Engineering Haryana India Thapar Institute of Engineering and Technology Department of Computer Science Engineering Patiala India

ISBN: (纸本)9781665408165

Liver illness is one of the worst diseases on the planet. It occurs in the human body, most notably in the liver. The liver's primary function is to eliminate waste created by organisms, to store key vitamins required by the body so that they do not go to waste, and to digest meals. This is a highly terrible disease, and the first thing that has to be done is to limit the risk explored by this lethal disease, and early detection can assist save the organism. The amount of people that are disease in the world is approx. 3.5 percent. The number of advancements that are happening in prediction of the disease done through the help of machine learning classification techniques like KNN, random forest SVM, and logistic regression. Other deep learning methods are also incorporated to solve this problem such as artificial neural network and convolution neural network. The methods would definitely increase the life expectancy of the patient suffering from this disease and avoid the chronic liver disease (CLD). The data may be gathered in enormous quantities as a result of the widespread use of bar codes for superior marketable items, the automation of many commercial and government transactions, and the advancement of data gathering systems. The proposed system that has been used ensemble methods such as random forest, xgboost and gradient boost and are combined to get a greater accuracy. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System

Smart-Infinity: Fast Large Language Model Training using Nea...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Hongsun Jang Jaeyong Song Jaewon Jung Jaeyoung Park Youngsok Kim Jinho Lee Department of Electrical and Computer Engineering Seoul National University Department of Electrical and Computer Engineering University of Texas at Austin Department of Computer Science Yonsei University

The recent huge advance of Large Language Models (LLMs) is mainly driven by the increase in the number of parameters. This has led to substantial memory capacity requirements, necessitating the use of dozens of GPUs just to meet the capacity. One popular solution to this is storage-offloaded training, which uses host memory and storage as an extended memory hierarchy. However, this obviously comes at the cost of storage bandwidth bottleneck because storage devices have orders of magnitude lower bandwidth compared to that of GPU device memories. Our work, Smart-Infinity, addresses the storage bandwidth bottleneck of storage-offloaded LLM training using near-storage processing devices on a real system. The main component of Smart-Infinity is SmartUpdate, which performs parameter updates on custom near-storage accelerators. We identify that moving parameter updates to the storage side removes most of the storage traffic. In addition, we propose an efficient data transfer handler structure to address the system integration issues for Smart-Infinity. The handler allows overlapping data transfers with fixed memory consumption by reusing the device buffer. Lastly, we propose accelerator-assisted gradient compression/decompression to enhance the scalability of Smart-Infinity. When scaling to multiple near-storage processing devices, the write traffic on the shared channel becomes the bottleneck. To alleviate this, we compress the gradients on the GPU and decompress them on the accelerators. It provides further acceleration from reduced traffic. As a result, Smart-Infinity achieves a significant speedup compared to the baseline. Notably, SmartInfinity is a ready-to-use approach that is fully integrated into PyTorch on a real system. The implementation of Smart-Infinity is available at https://***/AIS-SNU/smart-infinity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Retail Customer Segmentation using RFM Quantiles and Clustering Technique 4

Online Retail Customer Segmentation using RFM Quantiles and ...

引用

4th International Conference on computer, Communication, Control and Information Technology, C3IT 2024

作者： Majilya, Mouli Maji, Giridhar Ghosh, Partha Sen, Soumya A.K.Choudhury School of Information Technology University of Calcutta Kolkata India Asansol Polytechnic Department of Electrical Engineering Asansol India Academy of Technology Department of Computer Science and Engineering Adisaptagram India

ISBN: (纸本)9798350389128

In the fiercely competitive landscape of modern business, making effective decisions is imperative for generating substantial revenue. With organizations employing diverse strategies to stay ahead, leveraging data for informed decision-making is crucial. Understanding individual preferences and purchasing behaviors can be challenging, but machine learning techniques offer a solution by organizing and analyzing vast datasets. Customer segmentation, particularly through K-means clustering, is instrumental in identifying target groups with similar attributes and interests. The present study focuses on customer clustering method-ologies to give businesses a competitive edge. By collecting, analyzing, and visualizing customer data, we aim to develop a data science model that utilizes K-means clustering and the RFM model (Recency, Frequency, Monetary) for existing customers. Utilizing the UK's e-commerce dataset, which delves into customer purchasing behaviors, we aim to group customers into clusters such as high-value customers, mid-range, and those at risk of churn based on RFM scores. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

SEMU5G: an Emulator for Improving Model Accuracy and Performance Evaluation of 5G Network Core Architectures based on SDN 10

SEMU5G: an Emulator for Improving Model Accuracy and Perform...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Zaki Hamidi, Eki Ahmad Lazuardi, Arga Valen Rahmansyah, Muhammad Litfan Novel Bajri, Salman Alfarizi Tulloh, Rohmat Negara, Ridha Muldina Ahdan, Syaiful Jupriyadi UIN Sunan Gunung Djati Bandung Electrical Engineering Department Bandung Indonesia Telkom University Telecommunication Technology School of Applied Science Bandung Indonesia The University Center of Excellence Intelligent Sensing-IoT Telkom University Indonesia Telkom University School of Electrical Engineering Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering & Computer Science Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Bandarlampung Indonesia

ISBN: (纸本)9798350377057

The rapid advancement of 5G Radio Access Network (RAN) architecture is facilitating the construction of 5G networks, marking a significant milestone in telecommunications evolution. Given the complexity of the 5G core architecture, traditional simulation methods are insufficient, necessitating novel approaches. Emulator systems are crucial for creating dynamic, controlled environments that enable exploration of real-world scenarios without physical constraints. SEMU5G, a 5G core emulator, SDN controller, and RAN simulator, utilizes Open5GS implemented in Docker Container for test system flexibility and isolation. Additionally, an SDN controller is integrated to monitor data flows in the User Plane Function (UPF) and gNB simulated by UERANSIM in Mininet-WiFi. This comprehensive integration facilitates effective and flexible real-world exploration, providing a dynamic and controlled test environment for 5G core research. Scenario testing comprises two stages: firstly, a fixed network topology is employed to compare resource usage and confirm successful SEMU5G integration. Secondly, a mobile network topology is utilized to implement a mobile device scenario and compare the Quality of Service (QoS) of SEMU5G with other available emulators. These stages ensure thorough evaluation of SEMU5G's performance and its comparative advantage over existing solutions. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding Based on Greedy Pairing Prediction-Error Expansion

引用

Journal of Electronic science and Technology 2022年第3期20卷 294-304页

作者： Yi-Nan Lin Gwo-Jen Chiou Cheng-Ying Yang Victor R.L.Shen Chiao-Chih Lai the Department of Electronic Engineering Ming Chi University of TechnologyNew Taipei 243303 the Department of Electrical Engineering “National Formosa University”Yunlin 632301 the Department of Computer Science University of TaipeiTaipei 10048 the Department of Computer Science and Information Engineering “National Taipei University”New Taipei 23741 the Department of Information Management Chaoyang University of TechnologyTaichung 413310 Acer Company Taipei 221

Reversible data hiding(RDH)is a method to embed messages into an image that human eyes are difficult to recognize the differences between the original image and the embedded *** method needs to make sure that the original image and the embedded information can be exactly *** prediction-error expansion(PEE)is a successful way to realize ***,it is fixed when pairing the conventional twodimensional prediction-error histogram(2D-PEH).So,the embedding capacity(EC)and embedding distortion(ED)are not *** this study,we propose a method called greedy pairing prediction-error expansion(GPPEE)based on pairwise RDH and demonstrate GPPEE can achieve a more efficient embedding goal and reduce ED.

关键词： Greedy pairing prediction-error expansion(GPPEE) prediction-error expansion(PEE) reversible data hiding(RDH) two-dimensional prediction-error histogram(2D-PEH)

来源：评论

学校读者我要写书评

暂无评论

Efficient Energy Optimization Techniques for Smart Grids Which Uses ML And DL Algorithms

Efficient Energy Optimization Techniques for Smart Grids Whi...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Singhal, Rishi Mehta, Deepak Sharma, Khushboo Noida Institute of Engineering & Technology Department of Electrical and Electronics Engineering Uttar Pradesh Greater Noida India Department of Computer Science Bangalore India Vivekananda Global University Department of Electrical Engineering Jaipur India

ISBN: (纸本)9798350357769

The current study emphasizes how important it is to have an electrostatic factor track system in order to keep track of different loads. The implementation of Energy Demand-Side Controlling (EDM) it smart grids is emphasized in particular. Using data mining with machine learning, the paper proposes an efficient Energy Disaggregation (ED) technique to solve challenges linked to energy and sustainability. In order to assess this model, benchmark information from the Residential Energy First, the publically available disintegration Dataset (REDD) must be employed. Consequently, by including data gathered from the Turks Electricity Equipment Dataset (TEAD), a collection of information on residential power use, research on the conveyance of electrical energy (ED) had in smart meter systems develops. In order to learn sequence-to-sequence patterns, adjust the Adax optimization approach for the ED domain, and fine-tune NILM neural networks, the study presents an upgraded training function. In several respects, BERT-NILM outperforms the state-of-the-art adaptation moment approximation (Adam) solver on REDD datasets when using a different training function. Using the TEAD dataset and BERT-NILM training, we have completed the research. © 2023 IEEE.

关键词： Adax Optimization BERT-NILM Data Mining Demand-Side Management Energy Disaggregation Internet of Things (IoT) Machine Learning NILM (Non-Intrusive Load Monitoring) REDD Dataset Smart Grids TEAD Dataset and Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Polymer graph neural networks for multitask property learning

引用

npj Computational Materials 2023年第1期9卷 1420-1429页

作者： Owen Queen Gavin A.McCarver Saitheeraj Thatigotla Brendan P.Abolins Cameron L.Brown Vasileios Maroulas Konstantinos D.Vogiatzis Department of Mathematics University of TennesseeKnoxvilleTN 37996-1320USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxvilleTN 37996-2250USA Department of Chemistry University of TennesseeKnoxvilleTN 37996-1600USA Eastman Chemical Company KingsportTN 37660USA

The prediction of a variety of polymer properties from their monomer composition has been a challenge for material informatics,and their development can lead to a more effective exploration of the material *** this work,POLYMERGNN,a multitask machine learning architecture that relies on polymeric features and graph neural networks has been developed towards this *** provides accurate estimates for polymer properties based on a database of complex and heterogeneous polyesters(linear/branched,homopolymers/copolymers)with experimentally refined *** POLYMERGNN,each polyester is represented as a set of monomer units,which are introduced as molecular graphs.A virtual screening of a large,computationally generated database with materials of variable composition was performed,a task that demonstrates the applicability of the POLYMERGNN on future studies that target the exploration of the polymer ***,a discussion on the explainability of the models is provided.

关键词： properties space polyester

来源：评论

学校读者我要写书评

暂无评论

The Analysis of Device-to-Device (D2D) Communication System Operating in 5G Underlaying Cellular Networks on Multiple Bands over Nakagami-m Fading Channels

引用

SN computer science 2025年第5期6卷 1-15页

作者： Shatnawi, Razan A. Khodeir, Mahmoud A. Al-Mistarihi, Mamoun F. Darabkh, Khalid A. Al-Zuraiqi, Eyad T. Qasaymeh, Mahmoud M. Electrical Engineering Department Faculty of Engineering Jordan University of Science and Technology P.O. Box 3030 Irbid 22110 Jordan Computer Engineering Department School of Engineering The University of Jordan Amman 11942 Jordan Department of Telecommunications Engineering Hijjawi Faculty for Engineering Technology Yarmouk University P.O. Box 566 Irbid 21163 Jordan Computer Engineering and Communication Department Tafila Technical University Tafila 66110 Jordan

In contrast to traditional cellular connection, device-to-device (D2D) communication is a direct connection amidst adjacent mobile users that does not pass through the base station (BS) and does not rely on network infrastructure to meet low power requirements and high data rate. Cellular networks and D2D connections were combined in underlay mode to address power usage concerns. In underlay D2D communication, licensed frequency bands are utilized by both D2D and cellular connections;due to resource sharing, these bands may overlap, which lowers service quality but boosts spectral efficiency. Most existing research exclusively discuss energy efficiency (EE) in the context of single cells. This article has taken into account the entire cellular network with D2D connections on various bands, and stochastic geometric theory has been used in order to obtain closed form expressions for the probability of successful transmission (STP), the average sum rate (ASR), and EE for D2D connection underlaid cellular networks over Nakagami-m fading channels. Results of simulations are used to validate analytical conclusions. Simulation results demonstrate that higher STP, higher ASR, and lower EE all result in enhanced system performance. In addition, as the shape parameter’s value m (Nakagami-m order) increases, the EE, ASR, and STP of D2D users improve, which enhances system performance. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Device-to-device communication Energy efficiency Nakagami-m fading channel Stochastic geometry

来源：评论

学校读者我要写书评

暂无评论

ArcText: A Unified Text Approach to Describing Convolutional Neural Network Architectures

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第4期3卷 526-540页

作者： Sun, Yanan Yen, Gary G. Xue, Bing Zhang, Mengjie Lv, Jiancheng Sichuan University College of Computer Science Chengdu610065 China Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States Victoria University of Wellington School of Engineering and Computer Science Wellington6140 New Zealand

The superiority of convolutional neural networks (CNNs) largely relies on their architectures that are usually manually crafted with extensive human expertise. Unfortunately, such kind of domain knowledge is not necessarily owned by every interested user. Data mining on existing CNNs can discover useful patterns and fundamental comments from their architectures, providing researchers with strong prior knowledge to design effective CNN architectures when they have no expertise in CNNs. There are various state-of-the-art data mining algorithms at hand, while there is only rare work on mining CNN architectures. One of the main reasons is the gap between CNN architectures and data mining algorithms. Specifically, the current CNN architecture descriptions cannot be exactly vectorized to feed to a data mining algorithm. In this article, we propose a unified approach, named ArcText, to describing CNN architectures based on text. Particularly, four different units and an ordering method have been elaborately designed in ArcText, to uniquely describe the same CNN architecture with sufficient information. Also, the resulted description can be exactly converted back to the corresponding CNN architecture. ArcText bridges the gap between CNN architectures and data mining researchers, and has the potential to be utilized to wider scenarios. © 2020 IEEE.

关键词： Data mining

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：