检索结果-内蒙古大学图书馆

Incremental Least-Recently-Used Algorithm: Good, Robust, and Predictable Performance

IEEE Transactions on Mobile Computing 2025年第07期24卷 6658-6672页

作者： Zhang, Jinbei Chen, Chunpeng Cai, Kechao Lui, John C.S Sun Yat-sen University School of Electronic and Communication Engineering Shenzhen China The Chinese University of Hong Kong Department of Computer Science & Engineering N.T. Shatin Hong Kong

This paper proposes a replacement algorithm for file caching in mobile edge computing (MEC) networks. While there are numerous schemes for file replacement, it remains a challenge to achieve good, robust, and predictable performance simultaneously. To address this challenge, we introduce a general scheme called Incremental Least-Recently-Used (iLRU), which builds on the classic Least-Recently-Used (LRU) algorithm. iLRU initially caches only a "portion" of the file upon the first request and incrementally caches more when there are more requests for the file. In this regard, the request frequency can be inferred from the cached size without incurring additional overhead, where a larger cached size represents a higher request frequency. We derive the theoretical hit ratio of iLRU based on the Time-to-Live (TTL) analysis. With the Time-to-Live (TTL) analysis, we can theoretically derive the hit ratio and properties of iLRU and notably show that iLRU allocates more cache space to popular files, resulting in a higher hit ratio than LRU. Simulation results demonstrate the superior performance of iLRU and validate the accuracy of the theoretical hit ratio. Furthermore, we conduct simulations over various real-world traces to show that iLRU outperforms existing schemes across various real-world traces, defenestrating the robustness of iLRU. © 2025 IEEE. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning Approaches for Guava Disease Detection

引用

SN computer science 2025年第4期6卷 1-28页

作者： Paramesha, K. Jalapur, Shruti Hanok, Shalini Puttegowda, Kiran Manjunatha, G. Kumara, Bharath Department of Computer Science and Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of Computer Science and Engineering Christ University Karnataka Bengaluru India Department of Electronics and Communication Engineering ATME College of Engineering Karnataka Mysuru India Department of Electronics and Communication Engineering Vidyavardhaka College of Engineering Karnataka Mysuru India Department of CSD PES Institute of Technology and Management Karnataka Shivamogga India Department of ECE MS Ramaiah University of Applied Science (MSRUAS) Karnataka Bangalore India

A larger proportion of crops face disease outbreaks, making agricultural output difficult. Detecting and predicting diseases at an early stage can enhance productivity. Guava, a tropical and subtropical fruit, is cultivated in various countries. In regions such as Bangladesh, Pakistan, India, and South America, guava cultivation faces significant challenges due to diseases like Canker, Dot, Mummification, Phytophthora, Scab, and Styler and Root. Traditional diagnosis methods based on visual observation are often unreliable and time-consuming. To address this, we developed an automated system leveraging deep learning techniques. Our study utilized a dataset comprising 4046 guava leaf images categorized into these seven disease classes. We compared the performance of traditional methods with deep learning approaches using vision transformers and transfer learning. The results demonstrate the superiority of deep learning methods over traditional approaches, where traditional machine learning model SVM gave accuracy near 78% and deep learning methods gave over 90%. The transfer learning method gave an accuracy of nearly 97% and on the other hand, the vision transformer gave accuracy of 98%. This offers a promising solution for early disease detection in guava crops. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Accuracy Deep learning Guava disease Leaf images Machine learning

来源：评论

学校读者我要写书评

暂无评论

RouteNow: Ensuring Least Hop Routing towards SDIoT based Backup Hospital Networks

RouteNow: Ensuring Least Hop Routing towards SDIoT based Bac...

引用

2024 IEEE Global communications Conference, GLOBECOM 2024

作者： Sarkar, Kounteya Misra, Sudip Sonu, Mayank Iit Department of Computer Science and Engineering Kharagpur India Iit Department of Electronics and Electrical Communication Engineering Kharagpur India

ISBN: (纸本)9798350351255

This work proposes routeNow, a routing algorithm designed for wireless Software Defined Internet of Things by dynamic path relaxation based on real-time heuristic that always gives the best least hop path. This is aimed towards providing an alternative backup network for a smart hospital that functions independently on the failure of the primary hospital network. Given a pair of source and destination nodes, a central controller with a global network view first calculates a minimum hop path greedily by minimizing the remaining distance to destination. Hence, the path so found is relaxed dynamically by substituting certain links with other links keeping the hop count constant if a new path is found with a lesser latency than the previous one. For this, the controller maintains a matrix containing real-time delay between neighboring IoT nodes given the current network state and whose values are periodically refreshed using a heuristic function based on actual delay measurements. This enables the controller to dynamically modify routing paths. Simulation analysis of routeNow shows that it formulates routing paths with significant less time even with large networks and by always maintaining a route with least hops, on average a least latency path is also ensured. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Outage Probability Analysis for D2D-Enabled Heterogeneous Cellular Networks with Exclusion Zone:A Stochastic Geometry Approach

引用

computer Modeling in engineering & sciences 2024年第1期138卷 639-661页

作者： Yulei Wang Li Feng Shumin Yao Hong Liang Haoxu Shi Yuqiang Chen School of Computer Science and Engineering Macao University of Science and TechnologyTaipaMacaoChina Department of Broadband Communication Peng Cheng LaboratoryShenzhenChina School of Artificial Intelligence Dongguan PolytechnicDongguanChina

Interference management is one of the most important issues in the device-to-device(D2D)-enabled heterogeneous cellular networks(HetCNets)due to the coexistence of massive cellular and D2D devices in which D2D devices reuse the cellular *** alleviate the interference,an efficient interference management way is to set exclusion zones around the cellular *** this paper,we adopt a stochastic geometry approach to analyze the outage probabilities of cellular and D2D users in the D2D-enabled *** main difficulties contain three aspects:1)how to model the location randomness of base stations,cellular and D2D users in practical networks;2)how to capture the randomness and interrelation of cellular and D2D transmissions due to the existence of random exclusion zones;3)how to characterize the different types of interference and their impacts on the outage probabilities of cellular and D2D *** then run extensive Monte-Carlo simulations which manifest that our theoretical model is very accurate.

关键词： Device-to-device(D2D)-enabled heterogeneous cellular networks(HetCNets) exclusion zone stochastic geometry(SG) Matérn hard-core process(MHCP)

来源：评论

学校读者我要写书评

暂无评论

Metaheuristics Based Node Localization Approach for Real-Time Clustered Wireless Networks

引用

computer Systems science & engineering 2023年第1期44卷 1-17页

作者： R.Bhaskaran P.S.Sujith Kumar G.Shanthi L.Raja Gyanendra Prasad Joshi Woong Cho Department of Information Technology PSNA College of Engineering and TechnologyDindigul624622India Department of Computer Science and Engineering MEA Engineering CollegeMallapuram679325KeralaIndia Department of Electronics and Communication Engineering Rajalakshmi Institute of TechnologyKuthambakkamChennai600124India Department of Electronics and Communication Engineering Sri Eshwar College of EngineeringCoimbatore641202India Department of Computer Science and Engineering Sejong UniversitySeoul05006Korea Department of Software Convergence Daegu Catholic UniversityGyeongsan38430Korea

In recent times,real time wireless networks have found their applicability in several practical applications such as smart city,healthcare,surveillance,environmental monitoring,*** the same time,proper localization of nodes in real time wireless networks helps to improve the overall functioning of *** study presents an Improved Metaheuristics based Energy Efficient Clustering with Node Localization(IM-EECNL)approach for real-time wireless *** proposed IM-EECNL technique involves two major processes namely node localization and ***,Chaotic Water Strider Algorithm based Node Localization(CWSANL)technique to determine the unknown position of the ***,an Oppositional Archimedes Optimization Algorithm based Clustering(OAOAC)technique is applied to accomplish energy efficiency in the ***,the OAOAC technique derives afitness function comprising residual energy,distance to cluster heads(CHs),distance to base station(BS),and *** performance validation of the IM-EECNL technique is carried out under several aspects such as localization and energy efficiency.A wide ranging comparative outcomes analysis highlighted the improved performance of the IM-EECNL approach on the recent approaches with the maximum packet delivery ratio(PDR)of 0.985.

关键词： Wireless networks real time applications clustering node localization energy efficiency metaheuristics

来源：评论

学校读者我要写书评

暂无评论

Circuit Design using Quantum Dot Technology 1

Circuit Design using Quantum Dot Technology

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Manjunath, T.C. Kuravatti, Prakash Rajarajeswari College of Engineering Department of Computer Science & Engineering Bangalore India Rajeev Institute of Technology Department of Electronics and Communication Engineering Hassan India

ISBN: (纸本)9798331529246

In this paper, the harnessing QCA for High-Performance, Low-Power Arithmetic Circuits w.r.t. the focusing on Multipliers and Square Circuits is presented. The background in relation to this work is presented next. Quantum-dot Cellular Automata (QCA) is an emerging technology in nano-electronics that offers promising advantages over traditional CMOS (Complementary Metal-Oxide-Semiconductor) technology, including low power consumption, high operational speeds, and exceptional integration capabilities. These features position QCA as a potential successor to CMOS in various applications. Multipliers, critical components in digital signal processing, and square circuits, essential for mathematical computations, significantly impact system throughput and power efficiency. This research focuses on designing QCA-based multiplier and square circuits to leverage these advantages. Methods, Results, and Concluding Remarks w.r.t. the work is given here. The QCA-based multiplier was constructed using binary adders and AND gates, while a comparative analysis was conducted between QCA and CMOS technologies to evaluate performance. The evaluation considered parameters such as cell count, area, and energy dissipation, utilizing the QCA Designer tool for validation. Results demonstrate that QCA designs offer significant improvements in terms of reduced power dissipation and area requirements compared to CMOS. These findings highlight the potential of QCA technology to enhance the efficiency and integration of critical components in digital systems, marking it as a transformative approach in nano-electronics. © 2025 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

DeepFakeGuard: Safeguarding Digital Platforms Against Fake Profiles Using AI 4

DeepFakeGuard: Safeguarding Digital Platforms Against Fake P...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Swarna Sudha, M. Manjula, S. Bharathi, Indira Krishnasamy, Valarmathi Vijayalakshmi, K. Ramco Institute of Technology Department of Computer Science and Engineering Rajapalayam India School of Computer Science and Engineering Vellore Institute of Technology Chennai India PSR Engineering College Department of Electronics and Communication Engineering Sivakasi India

ISBN: (纸本)9798331523923

This research introduces DeepFakeGuard, a hybrid deep learning framework designed to detect fake profiles on social media platforms, addressing the growing threat of fraudulent accounts online. DeepFakeGuard integrates multiple data modalities, including textual, visual, behavioral, and network features, to accurately classify profiles as real or fake. Leveraging advanced deep learning models such as BERT for textual analysis, ResNet for image processing, and LSTM for modeling behavioral patterns, DeepFakeGuard provides a comprehensive and robust solution for identifying fake profiles across diverse platforms. The framework processes a rich set of profile characteristics, including account information, posting behavior, post sentiment, and network relationships, ensuring a multi-dimensional analysis of social media accounts. The hybrid architecture of DeepFakeGuard merges outputs from individual sub-models, which are then processed through dense layers for final classification using a sigmoid activation function. This multi-faceted approach significantly enhances detection accuracy, precision, and recall compared to traditional methods. The framework is highly scalable and adaptable to various social media platforms, offering a versatile tool for strengthening online security. With strong performance metrics, including high classification accuracy, DeepFakeGuard demonstrates its potential for real-world applications in mitigating the risks associated with fake profiles. By fostering secure and trustworthy social media environments, this research contributes to the ongoing fight against fraudulent accounts, paving the way for safer online interactions. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based approach for detection of lung cancer using self adaptive sea lion optimization algorithm (SA-SLnO)

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12933-12947页

作者： Pradhan, Kanchan Chawla, Priyanka Rawat, Sanyog School of Computer Science and Engineering Lovely Professional University Punjab Phagwara India Department of Electronics and Communication Engineering Manipal University Jaipur India

The main intent of this paper is to design and implement a novel methodology for lung cancer prediction using the patient's health record. Feature extraction is performed using two well-performing approaches like principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE). As an innovative contribution, a novel optimized correlation-based weighted feature extraction method named as self adaptive sea lion optimization algorithm (SA-SLnO) has been proposed that uses the latest meta-heuristic algorithm to optimize the weights. The number of hidden neurons in RNN is optimized by the proposed SA-SLnO. The major objective of this proposed lung cancer diagnosis model is to minimize the MSE among the actual and predicted outputs. The experimental findings demonstrate that the proposed model outperforms existing methodologies in terms of accuracy, sensitivity, and precision, FPR, FNR, and F1-score. Experimental finding demonstrates that proposed work outperforms PSO-RNN, GWO-RNN, GSO-RNN, and SLnO-RNN in terms of accuracy by 1.7 percent, 2%, 5%, and 2.7%, respectively. Similarly, the proposed lung cancer diagnosis model performed better when all performance metrics are examined on two datasets. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization

引用

computers, Materials & Continua 2024年第9期80卷 4791-4812页

作者： Ahmad Yahiya Ahmad Bani Ahmad Jafar Alzubi Sophers James Vincent Omollo Nyangaresi Chanthirasekaran Kutralakani Anguraju Krishnan Department of Accounting and Finance Faculty of BusinessMiddle East UniversityAmman11831Jordan Faculty of Engineering Al-Balqa Applied UniversitySalt19117Jordan Department of Mathematics Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo210-40601Kenya Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesChennai602105India Department of Electronics and Communication Engineering Saveetha Engineering College(Autonomous)Chennai602105India Department of Computer Science and Engineering Kongunadu College of Engineering and Technology(Autonomous)TholurpattiTrichy621215India

In recent years,wearable devices-based Human Activity Recognition(HAR)models have received significant *** developed HAR models use hand-crafted features to recognize human activities,leading to the extraction of basic *** images captured by wearable sensors contain advanced features,allowing them to be analyzed by deep learning algorithms to enhance the detection and recognition of human *** lighting and limited sensor capabilities can impact data quality,making the recognition of human actions a challenging *** unimodal-based HAR approaches are not suitable in a real-time ***,an updated HAR model is developed using multiple types of data and an advanced deep-learning ***,the required signals and sensor data are accumulated from the standard *** these signals,the wave features are *** the extracted wave features and sensor data are given as the input to recognize the human *** Adaptive Hybrid Deep Attentive Network(AHDAN)is developed by incorporating a“1D Convolutional Neural Network(1DCNN)”with a“Gated Recurrent Unit(GRU)”for the human activity recognition ***,the Enhanced Archerfish Hunting Optimizer(EAHO)is suggested to fine-tune the network parameters for enhancing the recognition *** experimental evaluation is performed on various deep learning networks and heuristic algorithms to confirm the effectiveness of the proposed HAR *** EAHO-based HAR model outperforms traditional deep learning networks with an accuracy of 95.36,95.25 for recall,95.48 for specificity,and 95.47 for precision,*** result proved that the developed model is effective in recognizing human action by taking less ***,it reduces the computation complexity and overfitting issue through using an optimization approach.

关键词： Human action recognition multi-modal sensor data and signals adaptive hybrid deep attentive network enhanced archerfish hunting optimizer 1D convolutional neural network gated recurrent units

来源：评论

学校读者我要写书评

暂无评论

Testing the Feasibility of Linear Programs with Bandit Feedback 41

Testing the Feasibility of Linear Programs with Bandit Feedb...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Gangrade, Aditya Gopalan, Aditya Saligrama, Venkatesh Scott, Clayton Department of Electrical Computer Engineering Boston University United States Department of Electrical Engineering and Computer Science University of Michigan United States Department of Electrical Communication Engineering Indian Institute of Science India

While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem. We initiate the study of testing such feasibility assumptions, and in particular address the problem in the linear bandit setting, thus characterising the costs of feasibility testing for an unknown linear program using bandit feedback. Concretely, we test if ∃x : Ax ≥ 0 for an unknown A ∈ m×d, by playing a sequence of actions xt ∈ d, and observing Axt + noise in response. By identifying the hypothesis as determining the sign of the value of a minimax game, we construct a novel test based on low-regret algorithms and a nonasymptotic law of iterated logarithms. We prove that this test is reliable, and adapts to the 'signal level,' Γ, of any instance, with mean sample costs scaling as Õ(d2/Γ2). We complement this by a minimax lower bound of Ω(d/Γ2) for sample costs of reliable tests, dominating prior asymptotic lower bounds by capturing the dependence on d, and thus elucidating a basic insight missing in the extant literature on such problems. Copyright 2024 by the author(s)

关键词： Software testing

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：