检索结果-内蒙古大学图书馆

Application of adaptive guard channel reservation under hard handoff constraint in wireless cellular network

International Journal of Wireless and Mobile Computing 2025年第2期28卷 170-185页

作者： Sahu, Promod Kumar Pati, Hemanta Kumar Pradha, Sateesh Kumar Department of Computer Science and Application Utkal University Vani Vihar Odisha Bhubaneswar India Department of Computer Science and Engineering International Institute of Information Technology Bhubaneswar Odisha Bhubaneswar India

Voice is the king of communication in wireless cellular network (WCN). Again, WCNs provide two types of calls, i.e., new call (NC) and handoff call (HC). Generally, HCs have higher priority than NCs because call dropping gives negative impact to users as compared to call blocking. So, to handle this problem some channels are reserved for HCs. If more channels are reserved for HCs, then handoff call dropping probability (HCDP) decreases at the same time as new call blocking probability (NCBP) increases;if fewer channels are reserved for HCs, HCDP increases and NCBP decreases. If channels are reserved for HCs by considering target HCDP then HCDP will be below the target and NCBP will be minimum for that target. So, keeping this in mind in this paper, we propose a mathematical model that estimates optimal number of guard channels (GCs) for HCs by considering target HCDP and keeping NCBP minimum. The mathematical model proposed assume static traffic parameters. However, in reality, the user traffic is dynamic and usually inherited through its testbed implementation. To obtain optimal performance we propose an adaptive GC reservation scheme by considering hard handoff constraint while implementing this model through testbed. Finally, we have verified testbed results with those of the model-based approach applying the parameters of different Global System for Mobile Communication (GSM) standards to evaluate its applicability to real systems. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Automatic Image Annotation Using Adaptive Convolutional Deep Learning Model

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 481-497页

作者： R.Jayaraj S.Lokesh Department of Computer Science and Engineering Hindusthan College of Engineering and TechnologyCoimbatore641032TamilnaduIndia Department of Computer Science and Engineering Hindusthan Institute of TechnologyCoimbatore641032TamilnaduIndia

Every day,websites and personal archives create more and more *** size of these archives is *** comfort of use of these huge digital image gatherings donates to their ***,not all of these folders deliver relevant indexing *** the outcomes,it is dif-ﬁcult to discover data that the user can be absorbed ***,in order to determine the signiﬁcance of the data,it is important to identify the contents in an informative *** annotation can be one of the greatest problematic domains in multimedia research and computer ***,in this paper,Adap-tive Convolutional Deep Learning Model(ACDLM)is developed for automatic image ***,the databases are collected from the open-source system which consists of some labelled images(for training phase)and some unlabeled images{Corel 5 K,MSRC v2}.After that,the images are sent to the pre-processing step such as colour space quantization and texture color class *** pre-processed images are sent to the segmentation approach for efﬁcient labelling technique using J-image segmentation(JSEG).Theﬁnal step is an auto-matic annotation using ACDLM which is a combination of Convolutional Neural Network(CNN)and Honey Badger Algorithm(HBA).Based on the proposed classiﬁer,the unlabeled images are *** proposed methodology is imple-mented in MATLAB and performance is evaluated by performance metrics such as accuracy,precision,recall and F1_*** the assistance of the pro-posed methodology,the unlabeled images are labelled.

关键词： Deep learning model J-image segmentation honey badger algorithm convolutional neural network image annotation

来源：评论

学校读者我要写书评

暂无评论

Early detection of stroke disease using patients previous medical data instil with deep learning

引用

Multimedia Tools and Applications 2025年第16期84卷 16853-16881页

作者： Diwan, Tausif Gajbhiye, Saurav M. Goydani, Purva R. Gannarpwar, Vedant R. Khandait, Harshal R. Tembhurne, Jitendra V. Sahare, Parul Department of Computer Science and Engineering Indian Institute of Information Technology Maharashtra Nagpur441108 India Department of Electronics and Communication Engineering Indian Institute of Information Technology Maharashtra Nagpur441108 India

Early detection of any disease and starting its treatment in this early stage are the most important steps in case of any life-threatening disease. Stroke is not an exception in this regard which is one of the leading causes of death and disability worldwide. We develop a simple but efficient deep neural network for the stroke prediction that accurately evaluates the probability of occurrence of stroke disease by treating this as a binary classification problem on one of the standard datasets named as Stroke Prediction Dataset available on Kaggle. With the help of effective pre-processing techniques such as SMOTE and FastICA on the noisy and imbalanced dataset, we could achieve improved performance for the binary classification of stroke prediction by employing a deep dense neural network. The architectural hyper-parameters are critically designed with the help of Keras Tuner and consisting of just ten layers in the deep dense neural network. With the help of this light weight deep dense model, we report an accuracy of 95%, AUC Score of 100% and F1-Score of 95% on a testing set. Moreover, we also present comparative illustration of various machine learning models for the aforesaid task along with the comparative illustration of various state of the arts with our proposed model for the stroke prediction. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Efficient Deployment Using CI/CD: Text Summarization Using NLP in Cloud 1

Efficient Deployment Using CI/CD: Text Summarization Using N...

引用

1st International Conference on AIML-Applications for engineering and technology, ICAET 2025

作者： Shingade, Bhuvan Hariharan, Siddharth Patole, Amol Singh, Kishan TPCT's Terna Engineering College Department of Computer Engineering Mumbai India Watumull Institute of Electronics Engineering and Computer Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798350355611

The core task in natural language processing (NLP) is text summarization, which condenses important information from large volumes of text into brief summaries. This study reviews text summarization strategies using NLP principles, focusing on two main methods: extractive and abstractive summarization. Abstractive techniques generate summaries by interpreting and rephrasing information, while extractive methods highlight key sentences or paragraphs from the original text. Our study examines various algorithms and models within both paradigms, leading to the development of a novel summarization model. Inspired by advancements in deep learning and transformer architectures, our model integrates state-of-the-art techniques to produce high-quality summaries. We discuss the architecture, training, and evaluation of our model, demonstrating its effectiveness on benchmark datasets. Lastly, we explore potential applications and future directions, emphasizing the importance of custom-built solutions for modern information processing tasks. © 2025 IEEE.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Microgrids with day-ahead energy forecasting for efficient energy management in smart grids: hybrid CS-RERNN

引用

Australian Journal of Electrical and Electronics engineering 2024年第3期21卷 213-227页

作者： Shirley, C.P. Pattar, Jagannath Kavitha Rani, P. Saini, Sumit Ranga, Jarabala Elangovan, D. Venkatakrishna Reddy, Ch. Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Mechanical Engineering Madanapalle Institute of Technology & Science Madanapalle India Department of M.Tech Computer Science and Engineering Sri Krishna College of Engineering and Technology Coimbatore India Department of Electrical Engineering School of Engineering & Technology Central University of Haryana Mahendergarh India Detartment of Electrical and Electronics Engineering Ramachandra College of Engineering Eluru India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Electrical and Electronics Engineering Chaitanya Bharathi institute of technology Hyderabad India

By integrating smart grid technology with home energy management systems, households can monitor and optimise their energy consumption. This allows for more efficient use of energy resources, reducing waste and lowering energy bills. In this manuscript, a hybrid approach is proposed for smart grid home energy management with microgrids and day-ahead energy forecasts. The proposed control approach combines the Circle Search (CS) algorithm and Recalling-Enhanced Recurrent Neural Network (RERNN). Commonly it is named as CS-RERNN technique. The novelty of this paper is to optimise energy consumption and production within microgrids, thereby contributing to the overall efficiency of the smart grid system. The proposed method is used to reduce the electricity cost, peak-to-average ratio (PAR), and maximising consumer comfort. Energy management is performed based on the CS algorithm. A smart home connected to the external power grid (PG) is managed by the proposed method. Here, load demand is predicted by using RERNN. By then, the performance of the proposed method is implemented in MATLAB platform. The proposed method shows a high efficiency of 96%, and 22 $ of low electricity bill cost compared with other existing methods such as Particle swarm optimisation (PSO), Cuckoo search algorithm (CSA, and Border collie Optimisation (BCO). ©, Engineers Australia.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art in Multi-faceted Feature Matching for E-Commerce: A Comprehensive Analysis

引用

Informatica (Slovenia) 2024年第12期48卷 97-106页

作者： Zareena, Noorbasha Rao, B. Tarakeswara Department of Computer Science and Systems Engineering AUTDR HUB Andhra University India Deparment of Computer Science and Engineering Kallam Haranadhareddy Institute of Technology Andhra Pradesh Guntur India

In this paper we provided an insightful exploration into the critical role of feature matching in enhancing the efficacy of e-commerce recommendation systems. By meticulously analyzing user data and product characteristics, feature matching significantly improves the personalization of product suggestions, thereby augmenting user experience and engagement in online shopping platforms. The paper reviews existing methodologies, including collaborative filtering, content-based filtering, hybrid models, and advanced deep learning approaches, which have collectively advanced the domain of personalized recommendations. Despite these advancements, the paper identifies key limitations such as scalability challenges, the cold start problem, over-specialization versus diversity in recommendations, and concerns over user privacy and data security. Through this comprehensive analysis, the survey makes substantial contributions by delineating the current state of the art, pinpointing critical gaps, and suggesting avenues for future research. The paper particularly emphasizes the need for dynamic adaptation in recommendation systems to keep pace with the fast-evolving e-commerce sector and changing consumer behaviors. Future research directions highlighted include the exploration of unsupervised and reinforcement learning models, the development of cross-domain recommendation systems, and the integration of emerging technologies, all aimed at fostering more nuanced, adaptable, and ethically responsible recommendation mechanisms. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2054-2066页

作者： Pfeiffer, Kilian Balaskas, Konstantinos Siozios, Kostas Henkel, Jorg Karlsruhe Institute of Technology Chair for Embedded Systems Karlsruhe76131 Germany University of Patras Department of Computer Engineering and Informatics Patras26504 Greece Aristotle University of Thessaloniki Department of Physics Thessaloniki54124 Greece

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped from the collaborative training. However, dropping devices in FL can degrade training accuracy and introduce bias or unfairness. Several works have tackled this problem on an algorithm level, e.g., by letting constrained devices train a subset of the server neural network (NN) model. However, it has been observed that these techniques are not effective w.r.t. accuracy. Importantly, they make simplistic assumptions about devices’ resources via indirect metrics, such as multiply accumulate (MAC) operations or peak memory requirements. We observe that memory access costs (that are currently not considered in simplistic metrics) have a significant impact on the energy consumption. In this work, for the first time, we consider on-device accelerator design for FL with heterogeneous devices. We utilize compressed arithmetic formats and approximate computing, targeting to satisfy limited energy budgets. Using a hardware-aware energy model, we observe that, contrary to the state of the art’s moderate energy reduction, our technique allows for lowering the energy requirements (by 4× ) while maintaining higher accuracy. © 1982-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

An Integrated Agricultural Financial Inclusion System Leveraging Supervised Machine Learning & Data Analytics 6

An Integrated Agricultural Financial Inclusion System Levera...

引用

6th International Conference on Mobile Computing and Sustainable informatics, ICMCSI 2025

作者： Rathi, Snehal Khedkar, Vijayshri Jadhav, Rutuja Kamate, Mugdha Potdar, Apurva Kamble, Prachi Computer Department Vishwakarma Institute of Information Technology Pune India Department of Computer Science & Engineering Symbiosis Institute of Technology Pune India

ISBN: (纸本)9798331522667

Agriculture is backbone of many economies but still farmers often face many challenges in accessing financial services or available resources for them, making informed crop choices and participating in government initiatives. Because of many farmers are not aware about all these things, to address these concerns, the proposed "Agricultural Financial Inclusion System" provides a comprehensive platform which integrates essential services with aim of improving farmers’ production and their financial awareness. Our system has a crop recommendation feature that helps farmers to choose the best suitable crop for their soil in the farm by taking climate and soil type into account. In order to make sure that farmers are aware about various available services/resources or any government schemes and able to take advantage of them, the platform also offers essential information on a variety of government initiatives, saving plans etc. By combining all these features, the Agricultural Financial Inclusion System encourage farmers to make smart choices which help them to enhance agricultural productivity and financial stability. In order to create more successful and sustainable agriculture sector, this integrated approach hopes to fill the gap between farmers and technology & resources they need. © 2025 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

The IoT resource allocation and scheduling using Elephant Herding Optimization (EHO-RAS) in IoT environment

引用

International Journal of Information technology (Singapore) 2024年第5期16卷 3283-3293页

作者： Mageswari, Umaa Deepak, Gerard Santhanavijayan, A. Mala, C. Department of Computer Science and Engineering National Institute of Technology Tamilnadu Trichy 620015 India Department of Computer Science and Engineering Manipal Institute of Technology Karnataka Bengaluru 560064 India

IoT is one of the most significant technological breakthroughs and promises a higher level of connection and control in the future. The IoT network continues to expand rapidly, and the IoT ecosystem comprises millions of interconnected ad hoc devices across the network. Effective resource utilization guarantees the improvement of service quality. Everything is connected to the Internet through the distribution system known as the Internet of Things (IoT). Plenty of gateways and resources are in IoT infrastructure. Resource allocation (RA) is challenging due to network heterogeneity and the diversity of IoT devices;numerous practical approaches, strategies, and implementations are being presented and employed to resolve the RA problem (RAP). IoT resource allocation and scheduling (RAS) performance is essential in such a system since RAS allocates resources to open gateways and handles mapping resources and gateways. A gateway is needed to connect to hundreds of resources in the IoT environment. The proposed work is based on the RAS problem and aims to achieve optimal RA in the IoT by using the Elephant Herding Optimization (EHO) algorithm to lower the total Communication Cost between gateways and resources. The proposed EHO algorithm has been contrasted with others already in use, and the results show that the suggested algorithm performs as expected. The proposed solution is superior to others regarding TCC and Convergence rate than Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Gray Wolf Optimization (GWO). © The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Communication cost EHO Fitness IoT Gateways IoT Resources Resource Allocation ToT

来源：评论

学校读者我要写书评

暂无评论

Conv-attention ViT for classification of multi-label class imbalanced data of lung thoracic diseases

引用

Multimedia Tools and Applications 2024年 1-30页

作者： Oommen, Lintu Nikhila Nagajyothi, Chiluka Chebrolu, Srilatha Department of Computer Science and Engineering National Institute of Technology Andhra Pradesh Tadepalligudem India

Chest X-ray image classification is a key study topic, and in order to increase performance and accuracy, the efficiency of vision transformers for this task has been examined. However, imbalanced datasets pose a significant challenge during model training, leading to biased results. The main focus is the classification of multi-labeled lung thoracic diseases using imbalanced data. To tackle class imbalance, synthetic data was generated using GANs and combined with images from diverse data sources, which enhanced generalization. To classify multi-labeled chest X-rays, this work proposes a Conv-Attention Vision Transformer (CA-ViT) model that uses local and global attention mechanisms to improve the average ROC-AUC score and F1-score. Proposed model, CA-ViT’s performance was evaluated on an imbalanced dataset and compared with ResNet-50, VGG-19, and ViT 32/384 models. The studies demonstrated that CA-ViT surpassed the performance of the other models, scoring an average ROC-AUC of 0.76 as opposed to 0.72, 0.75, and 0.68 for ResNet-50, VGG-19, and ViT 32/384 models, respectively. All models displayed improved assessment metrics when the dataset was balanced via synthetic data creation and the combination of several data distributions. When compared to the other models, CA-ViT performed best, earning an average ROC-AUC of 0.81. In contrast, the average ROC-AUC values for the ResNet-50, VGG-19, and ViT 32/384 models were 0.7, 0.73, and 0.79 respectively. CA-ViT achieved micro-average F1-score of 0.70. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

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：