检索结果-内蒙古大学图书馆

2023 International Conference on Advances in Computation, communication and information Technology, ICAICCIT 2023

作者： Vinutha, C.B. Vivek, V. Pandeya, Megha Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350344387

Machine learning relies heavily on time series forecasting, which has a wide range of uses, including although not limited to forecasting air quality, traffic patterns, and power use. Recent developments in deep training and matrix factorization models, however, have shown competitive performance and are emerging as alternatives. However, a fundamental disadvantage of these contemporary models over more established ones is their complexity. The Gradient Boosted Regression Tree, a well-known machine learning baseline, and popular deep learning models are compared in this work. We convert the time series forecast challenge into a window-based prediction issue, which is akin to (DNN) models. In addition, we design the GBRT model's input and output structure. In order to construct a single input instance to simulate a multi-output GBRT model, we concatenate the desired values with additional characteristics for each training window before flattening them. Using nine datasets, we undertake a thorough investigation and evaluate eight cutting-edge deep learning models recently presented at prestigious conferences. The findings show that a simple GBRT model performs much better than the state-of-the-art DNN models evaluated in this research thanks to the window-based input transformation. © 2023 IEEE.

关键词： Deep Learning DNN and Temporal Regularized Matrix Factorization Feature engineering Gradient Boosted Regression Trees (GBRT) Time Series Forecasting

来源：评论

学校读者我要写书评

暂无评论

Improved Adaptive Fairness-Indexed Technique for Congestion Control in Underwater Networks 3

Improved Adaptive Fairness-Indexed Technique for Congestion ...

引用

3rd International Conference on communication, Control, and Intelligent Systems, CCIS 2024

作者： Balaji Vijayan, V. Manojee, K.S. Mohammed Ibrahim, M. Nivethitha, R. Thamaraimanalan, T. Ranjithkumar, M. Hkbk College of Engineering Department of Information Science and Engineering Karnataka Bengaluru India Kongunadu College of Engineering and Technology Department of Information Technology Tamilnadu Trichy India Sona College of Technology Department of Computer Science and Engineering Tamilnadu Salem India K.S.R. College of Engineering Department of Computer Science and Engineering Tamilnadu Thiruchengode India Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamilnadu Coimbatore India Knowledge Institute of Technology Department of Computer Science and Business Systems Tamilnadu Salem India

ISBN: (纸本)9798331528201

In underwater acoustic sensor networks (UASNs), effective congestion control is essential for ensuring reliable data transmission and resource efficiency, especially in the face of challenging environmental factors such as water velocity, pressure, temperature, and salinity. This paper introduces a novel Adaptive Fairness-Indexed Congestion Control (AFICC) mechanism that employs Q-learning to dynamically adjust transmission rates among nodes, ensuring equitable resource distribution and minimizing congestion. Our simulations, conducted with 100 nodes at depths of up to 1000 meters, reveal that AFICC significantly outperforms two existing algorithms: Rate-Based Congestion Control (RBCC) and Energy-Aware Congestion Control (EACC). Specifically, AFICC achieved a Packet Delivery Ratio (PDR) of 93%, compared to 85% for RBCC and 80% for EACC. Additionally, the End-to-End Delay was reduced to an average of 150 milliseconds with AFICC, while RBCC and EACC recorded delays of 220 milliseconds and 210 milliseconds, respectively. AFICC also demonstrated a 25% improvement in Energy Efficiency over EACC and maintained a Jain's Fairness Index of 0.92, surpassing the 0.82 and 0.78 indices achieved by RBCC and EACC, respectively. These results confirm that AFICC offers a robust framework for congestion control in UASNs, effectively adapting to fluctuating underwater conditions while ensuring reliable communication and equitable resource allocation. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Spectral Efficient Hybrid Beamforming Design for Full-Duplex Cell-Free Massive MIMO System

Spectral Efficient Hybrid Beamforming Design for Full-Duplex...

引用

2024 IEEE Global communications Conference, GLOBECOM 2024

作者： Chen, Yingyang Wu, Jiayuan Li, Jing Chen, Xuan Li, Qiang Wang, Li Jinan University College of Information Science and Technology Guangzhou510632 China Guangzhou University School of Electronics and Communication Engineering Guangzhou510006 China Beijing University of Posts and Telecommunications School of Computer Science Beijing100876 China

ISBN: (纸本)9798350351255

In this paper, we investigate a full-duplex (FD) cell-free massive multiple-input multiple-output (mMIMO) system. To cope with the cross-link interference, especially the interaccess point (inter-AP) interference, we formulate a sum spectral efficiency maximization problem by jointly optimizing the digital and analog beamforming at FD AP and digital precoder at the uplink user equipment. To solve it, we present a fully digital design first by utilizing successive convex approximations and majorization-minimization to obtain a closed-form solution in each iteration. After that, we exploit the Riemannian manifold to get a hybrid design, which is shown to approximate the fully digital one well. Simulation results show that the proposed design enhances the sum spectral efficiency as well as uplink performance effectively when compared to other benchmarks. © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Developments in Oncological Diagnostic Imaging: Revolutionary Approaches to Cancer Treatment

AI-Powered Developments in Oncological Diagnostic Imaging: R...

引用

2023 International Conference on Advances in Computation, communication and information Technology, ICAICCIT 2023

作者： Singh, Shweta Ashwini, B. Vivek, V. Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350344387

This project aims to demonstrate new uses of deep learning techniques in the detection of cancer. A huge body of examples that show the desired behaviour may be used to train a system using deep learning, which is a family of algorithms. Introduction of deep learning methods to tumour imaging may help pathologists identify and categorise cancer early on so that patients can get the right therapies to improve their chances of surviving or recovering. Utilising statistics and other analytical techniques and ScienceDirect have data, it appears that since the late 1990s, a sharp increase in research on deep learning technologies in medical imaging has been motivated by the exceptionally high mortality rates of some cancer types in order to address the concomitant issues of a more precise recognition and the identification of cancer types to use effective therapies for cancer. This study also identifies the institutions, nations, and intellectual subject areas with the greatest levels of intellectual output in multiple disciplines as the origins of the trajectory of deep learning technology in cancer detection. According to Amara's law, this novel technique may result in a change in the way that cancer diagnoses and treats its many forms. When they can submit digital photos to laboratories in other developed nations to have malignancy kinds diagnosed, this fresh innovation may also aid developing regions, narrowing the present healthcare divide as much as feasible. © 2023 IEEE.

关键词： Cancer Detection Cancer Types Deep Learning Early Diagnosis Machine Learning Medical Imaging Metastatic Cancer Pathologists and Clinical Oncology Therapies Tumour Imaging

来源：评论

学校读者我要写书评

暂无评论

An Exhaustive Meta-Analysis on Consumer Retention Forecasting Using Advanced Machine Learning Techniques 3

An Exhaustive Meta-Analysis on Consumer Retention Forecastin...

引用

3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023

作者： Shreenidhi, H.S. Yadav, Dhyan Chandra Swetha, G. Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka562112 India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India

ISBN: (纸本)9798350343274

In this meta-analysis, we present a robust approach for consumer retention forecasting by integrating advanced machine learning algorithms. The method comprises three core algorithms: Consumer Behaviour Neural Network (CBNN), Retention Decision Trees (RDT), and Long Short-Term Memory for Retention (LSTM-R). The objective is to model intricate relationships within consumer behaviours and accurately predict their retention probabilities. CBNN a key component, adeptly captures intricate patterns within consumer behaviour data. It involves multiple hidden layers with activation functions, enabling accurate prediction of retention probabilities based on input features. The flowchart for CBNN showcases the training process involving forward and backward passes, underlining its deep learning approach. RDT this method utilizes decision tree algorithms to predict consumer retention decisions. By recursively splitting the dataset based on information gain, RDT efficiently models consumer behaviour, as depicted in the flowchart. information gain is maximized to create a robust predictive model. LSTM-R tailored for temporal data in consumer retention prediction, leverages specialized LSTM architecture. It effectively processes sequential consumer interactions, crucial for accurate prediction of consumer retention probabilities. The proposed method integrates these algorithms, leveraging historical consumer data, and conducts a comprehensive meta-analysis to evaluate their predictive performance. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Managing Cloud Networks: A Classification of SDN-Enabled Clouds

Managing Cloud Networks: A Classification of SDN-Enabled Clo...

引用

2023 International Conference on Advances in Computation, communication and information Technology, ICAICCIT 2023

作者： Singh, Vaishali Kehkeshan Jallal, S. Das, Sunanda Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350344387

The idea of separating the management plane from the data-forwarding gear was first introduced by Software-Defined Networking (SDN), which has brought about a revolutionary new age in networking. This innovation makes networks programmable, flexible, and dynamically reconfigurable. These characteristics have great potential for the field of computer science in the cloud, where dynamic adjustments and reconfiguration are essential owing to on-demand consumption patterns. The many simulation and empirical assessment techniques that have been created expressly for SDN-enabled cloud settings are also highlighted by us. Finally, study conducted perform a critical review of the state of the research, highlighting gaps and suggesting possibilities for further study. © 2023 IEEE.

关键词： application framework cloud computing hardware resources programmable controller resource provisioning simulation and energy modeling Software-Defined Networking (SDN)

来源：评论

学校读者我要写书评

暂无评论

Nodal Transmission in 5G Wireless Networking

Nodal Transmission in 5G Wireless Networking

引用

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

作者： Agrawal, Trapty Kakati, Pallabi Das, Sunanda Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India

ISBN: (纸本)9798350357769

The increase in data transmission network speed and reliability is inextricably linked to the fast growth of information technology. This calls for the ongoing improvement and upgrading of current standards. Next-generation communication networks are being developed and deployed with diligence by several organizations. This article provides a thorough examination of the software options available that are designed for analyzing and evaluating data network behaviors. It specifically emphasizes tools with substantial built-in functionality and flexibility that are ideally suited for mobile communication systems. It becomes clear that the NS3 network simulator is the best option. This article provides an overview as well as a unique NS3 solution that makes it possible to estimate the dependability of data transmission from a network node's first movement to its removal from a base station. © 2023 IEEE.

关键词： 5G Wireless Networking communication Networks Data Transmission Interference Analysis Network Security Nodal Transmission NS3 Network Simulator Signal Quality And Distribution Algorithms Simulation Modeling

来源：评论

学校读者我要写书评

暂无评论

Beyond The Internet of Things: Imagining IoT's Structure and Potential Routes

Beyond The Internet of Things: Imagining IoT's Structure and...

引用

2023 International Conference on Advances in Computation, communication and information Technology, ICAICCIT 2023

作者： Varalakshmi, K.R. Mahesh, T.R. Singh, Akhilendra Pratap Presidency University Department of Electronics and Communication Engineering Karnataka Bangalore India Faculty of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350344387

wireless sensor system technology has made it possible for ubiquitous sensing, which affects many aspects of contemporary life. Indicators of environmental health, from sensitive ecologies as well as biodiversity to urban settings, may now be measured, inferred, and understood. The Internet of Things is enabled by the extensive utilization of these devices in a network that facilitates communication and action. In this network, the actuators and sensors smoothly interact with our environment as data is exchanged across platforms to provide a unified operational view. Near field communication (NFC) is the upcoming technology that will enable the transformation of the worldwide web into a fully integrated Future Internet. This technology is being advanced through the adoption of variousenabling device methods, such as tags, audience members, encased sense and actuators nodes, and nodes for near field interaction. The demand for data-on-demand, using complex and straightforward queries, increases significantly as studies transition from web to web2 to web3. This study presents a cloud-centric vision for the worldwideimplementation of the Internet of Things. The future of IoT research is expected to be influenced by many significant technology enablers and their corresponding application domains, which are emphasized. A cloud architecture based on the interplay of public as well as private clouds and employing Aneka is shown. Study conducted elaborate on the need of unity, the global web, and distributed processing in our last section of our IoT vision for the community of technical researchers. © 2023 IEEE.

关键词： Cloud-centric Internet of Things Data storage and analytics Internet of Things (IoT) New protocols Participatory Sensing Quality of Service (QoS) Radio Frequency Identification (RFID) User-cantered cloud-based paradigm Visualization Wireless Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Resource-Aware Routing Protocol in Resource-Constrained Opportunistic Networks

引用

computers, Materials & Continua 2022年第2期70卷 4147-4167页

作者： Aref Hassan Kurd Ali Halikul Lenando Slim Chaoui Mohamad Alrfaay Medhat A.Tawfeek Department of Computer Systems and Communication Technologies Faculty of Computer Science and Information TechnologyUniversiti Malaysia Sarawak(UNIMAS)Kota Samarahan94300Malaysia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka2014KSA Unit-Lab of Sciences of Electronics Technologies of Information and TelecommunicationsSfax UniversitySfaxTunisia Department of Basic Sciences First Common Year DeanshipJouf UniversitySakaka2014KSA Department of Computer Sciences College of Computer and Information SciencesJouf UniversitySakaka2014KSA Department of Computer Sciences Faculty of Computers and InformationMenoufia UniversityEgypt

Recently,Opportunistic Networks(OppNets)are considered to be one of the most attractive developments of Mobile Ad Hoc Networks that have arisen thanks to the development of intelligent *** are characterized by a rough and dynamic topology as well as unpredictable contacts and contact *** is forwarded and stored in intermediate nodes until the next opportunity ***,achieving a high delivery ratio in OppNets is a challenging *** is imperative that any routing protocol use network resources,as far as they are available,in order to achieve higher network *** this article,we introduce the Resource-Aware Routing(ReAR)protocol which dynamically controls the buffer usage with the aim of balancing the load in resource-constrained,stateless and non-social *** ReAR protocol invokes our recently introduced mutual informationbased weighting approach to estimate the impact of the buffer size on the network performance and ultimately to regulate the buffer consumption in real *** proposed routing protocol is proofed conceptually and simulated using the Opportunistic Network Environment *** show that the ReAR protocol outperforms a set of well-known routing protocols such as EBR,Epidemic MaxProp,energy-aware Spray and Wait and energy-aware PRoPHETin terms of message delivery ratio and overhead ratio.

关键词： Opportunistic networks mobile ad hoc networks routing protocols resource-constrained networks load balancing buffer management

来源：评论

学校读者我要写书评

暂无评论

Optimal Bandwidth Utilization Techniques for IoT Device Networks using Edge Computing 4

Optimal Bandwidth Utilization Techniques for IoT Device Netw...

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Dankan Gowda, V. Vijayakumar, G. Chandrasekar, J. Shekhar, R. Prasad, K.D.V. Senthil Kumar, C. Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India V.S.B. Engineering College Department of Information Technology Tamilnadu Karur India Tamilnadu Chennai India Alliance University Department of Computer Science and Engineering Karnataka Bangalore India Symbiosis Institute of Business Management Hyderabad India Pune India Vellore Institute of Technology School of Computer Science Engineering & Information Systems Department of Information Technology Vellore632014 India

ISBN: (纸本)9798350354218

The IoT devices have persisted on growing at a very fast pace and this has proven very challenging in managing the network bandwidth. This paper spins the new concept of increasing the IoT networks bandwidth by adopting the edge computing strategies. It also offers data processing near the sources which reduces the load on the central servers and cuts down data transfer requirements. The usage of the Dynamic Bandwidth Allocation algorithm in the proposed method also enhances the priority of the imperative data and scales up the transmission rates according to the network status. The number of data units achieve higher values, the latency is less and overall, better results have been obtained for the total network performance. Consequently, the results obtained presented pathways through which the bandwidth challenge in IoT could be addressed by means of edge computing to enhance IoT capacity in the corresponding surroundings. © 2024 IEEE.

关键词： Frequency allocation

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：