检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2024年第6期48卷 185-198页

作者： Bajić, Filip Habijan, Marija Nenadić, Krešimir University Computing Centre University of Zagreb Zagreb10000 Croatia Faculty of Electrical Engineering Computer Science and Information Technology Osijek Osijek31000 Croatia

Data’s role is pivotal in the era of internet technologies, but unstructured data poses comprehension challenges. Data visualizations like charts have emerged as crucial tools for condensing complex information. Classifying charts and applying various processing techniques are vital to interpreting visual data. Traditional chart image classification methods rely on predefined rules and have limited accuracy. The advent of support vector machines (SVMs) and convolutional neural networks (CNNs) significantly improved the accuracy of these methods. This research evaluates our previously introduced Shallow convolutional neural network (SCNN) architecture for chart image classification, comprising four convolutional layers, two max-pooling layers, and one fully-connected layer. The network achieves state-of-the-art results, requiring smaller datasets and reduced computational resources. When two networks are combined into Siamese SCNN (SSCNN), emphasizing generalization, it achieves high accuracy with small datasets and excels in open-set classification. The evaluation process encompasses the utilization of six publicly available datasets. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Approximate String Matching Algorithm Using Multiple-Character Inverted Lists 5

Approximate String Matching Algorithm Using Multiple-Charact...

引用

5th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2024

作者： Thumsuwan, Soontaree Sangurai, Nuanprang Khancome, Chouvalit Rajabhat Rajanagarindra University Faculty of Science and Technology Department of Information Technology Chachoengsao Thailand Ramkhamhaeng University Faculty of Science Department of Computer Science Bangkok Thailand

ISBN: (纸本)9798331505998

Approximate string matching algorithms, which permit mismatched characters, are extensively employed in software featuring search tools, database management systems, and various applications and online services. Consequently, the development of new algorithms to facilitate faster and more accurate searches continues to pose a significant challenge for researchers. This research article introduces a novel approximate string matching algorithm, designated as m-IVLASM, derived from the Multiple-Character Inverted Lists data structure traditionally utilized for single pattern string matching. The proposed algorithm exhibits flexibility by allowing adjustable search parameters for each query, thereby enhancing search speed and efficiency compared to conventional methods. Operating in linear time, the algorithm demonstrates superior performance. Experimental results, derived from both random data and real-world datasets, provide compelling evidence that the new method significantly surpasses previous approaches in terms of effectiveness. The optimal efficiency for character length factor splitting was identified at values of 0.5 and 0.8. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Propagation-aware Q-coverage and Q-connectivity network design in relay-aided IoT sensor systems using heuristic and genetic algorithms

引用

Neural Computing and Applications 2025年 1-28页

作者： Thang, Nguyen Xuan Hanh, Nguyen Thi Son, Nguyen Van Tan, Nguyen Phuc Hung, To Quang Chien, Trinh Van Binh, Huynh Thi Thanh Faculty of Computer Science Hanoi University Nguyen Trai Hanoi Viet Nam Faculty of Interdisciplinary Digital Technology Phenikaa University Yen Nghia Ha Dong Hanoi12116 Viet Nam Faculty of Computer Science Phenikaa University Yen Nghia Ha Dong Hanoi12116 Viet Nam School of Information and Communication Technology Hanoi University of Science and Technology Dai Co Viet Hanoi Viet Nam

Wireless sensor networks play a crucial role in Internet of Things systems, whose development and prevalence have given rise to numerous challenges. One of the most notable problems regarding wireless sensor networks is the sensor deployment problem, where the objective is to minimize the number of nodes used and to satisfy the constraints of coverage and connectivity. In reality, sensors may be prone to errors and failures;therefore, simple coverage and simple connectivity cannot guarantee fault tolerance for a system. This leads to the concepts of Q-coverage and Q-connectivity, which indicates that each target needs q covering sensors and q node-disjoint paths to the base station. To minimize the number of nodes while still ensuring Q-coverage and Q-connectivity, we propose a heuristic algorithm and an algorithm based on the genetic algorithm. Besides, we construct various experiment scenarios and a realistic dataset to evaluate the efficiency of our proposed methods. The experiment results show that our proposed algorithms significantly outperform existing methods in both solution quality and running time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Connectivity Heuristic algorithm IoT networks Target coverage Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Expressive sign language system for deaf kids with MPEG-4 approach of virtual human character

引用

Journal of Ambient Intelligence and Humanized Computing 2024年 1-15页

作者： Ali, Itimad Raheem Kolivand, Hoshang Faculty of Business Informatics University of Information Technology and Communications Baghdad Iraq Department of Computer Science Liverpool Jone Moores University Liverpool United Kingdom

Children with language impairments during their significant developmental periods within ‎childhood are exposed to cognitive risk, social impairments, along with language. This is difficult ‎with children born deaf from hearing parents who own little or no experience of communicating ‎in sign language. This system presents the sign language in the context of British ‎Sign Language (BSL) for producing utterances through virtual characters. In capturing, Kinect ‎sensors use a motion capture sensor for motion actors. The connection uses sensors to read data, ‎connect to high-quality 3D scans, and then use these high-quality scans of the animated MPEG-4 ‎face and hand models. The main challenges of this system are the simultaneous capture of data ‎for the whole hand and the development of the MPEG-4 approach considering the animation ‎engines with descriptive sign language features. After synchronizing motion data from motion ‎capture results with Kinect, the combined hand character adjusts points, frames, and time with ‎virtual characters based on the motion of character actors. This study demonstrates the skills of ‎this sign language system instrumental in presenting an assessment by users, highlighting the ‎importance of the hand part in creating new accents and signs in BSL. We have validated this ‎system by testing the reliability and functionality of the virtual characters.‎. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Architecture for Superior IoT Threat Detection through Real IoT Environments

引用

computers, Materials & Continua 2024年第11期81卷 2299-2316页

作者： Bassam Mohammad Elzaghmouri Yosef Hasan Fayez Jbara Said Elaiwat Nisreen Innab Ahmed Abdelgader Fadol Osman Mohammed Awad Mohammed Ataelfadiel Farah H.Zawaideh Mouiad Fadeil Alawneh Asef Al-Khateeb Marwan Abu-Zanona Department of Computer Science Faculty of Computer Science and Information TechnologyJerash UniversityJerash26150Jordan Computer Engineering Department College of Engineering&Information Technology Buraydah CollegesBuraydah51418Saudi Arabia Faculty of Architecture and Design Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityDiriyahRiyadh13713Saudi Arabia Applied College King Faisal UniversityAl-Ahsa31982Saudi Arabia Department of Business Intelligence and Data Analysis Faculty of Financial Sciences and BusinessIrbid National UniversityIrbid21110Jordan Faculty of Information Technology Ajloun National UniversityAjlun26810Jordan Department of Management Information Systems College of Business AdministrationKing Faisal UniversityAl-Ahsa31982Saudi Arabia

As the Internet of Things(IoT)continues to expand,incorporating a vast array of devices into a digital ecosystem also increases the risk of cyber threats,necessitating robust defense *** paper presents an innovative hybrid deep learning architecture that excels at detecting IoT threats in real-world *** proposed model combines Convolutional Neural Networks(CNN),Bidirectional Long Short-Term Memory(BLSTM),Gated Recurrent Units(GRU),and Attention mechanisms into a cohesive *** integrated structure aims to enhance the detection and classification of complex cyber threats while accommodating the operational constraints of diverse IoT *** evaluated our model using the RT-IoT2022 dataset,which includes various devices,standard operations,and simulated *** research’s significance lies in the comprehensive evaluation metrics,including Cohen Kappa and Matthews Correlation Coefficient(MCC),which underscore the model’s reliability and predictive *** model surpassed traditional machine learning algorithms and the state-of-the-art,achieving over 99.6%precision,recall,F1-score,False Positive Rate(FPR),Detection Time,and accuracy,effectively identifying specific threats such as Message Queuing Telemetry Transport(MQTT)Publish,Denial of Service Synchronize network packet crafting tool(DOS SYN Hping),and Network Mapper Operating System Detection(NMAP OS DETECTION).The experimental analysis reveals a significant improvement over existing detection systems,significantly enhancing IoT security *** our experimental analysis,we have demonstrated a remarkable enhancement in comparison to existing detection systems,which significantly strength-ens the security standards of *** model effectively addresses the need for advanced,dependable,and adaptable security solutions,serving as a symbol of the power of deep learning in strengthening IoT ecosystems amidst the constantly evolving cyber threat *** achievemen

关键词： A hybrid deep learning model IoT threat detection real IoT environments cybersecurity attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Handling Imbalanced Data in Convolutional Neural Network on Apache Spark 14

Handling Imbalanced Data in Convolutional Neural Network on ...

引用

14th International Conference on information and Communication technology Convergence, ICTC 2023

作者： Aung, Thet Hsu Paing, Aye Myat Myat University of Information Technology Faculty of Computer Science Yangon Myanmar

ISBN: (纸本)9798350313277

With the growing pervasiveness of Big Data, many approaches have been made in several fields. The concept of big data has gained support as a result of this rising data advancement. Big data is required to show how things are related, predict future trends, and provide decision-makers with additional knowledge. Apache Spark is an effective, scalable, real-time data analytics engine that is rapidly taking over as the de facto center for big data and data science. Nowadays, how to completely collect and evaluate a huge amount of different and complicated data is a major problem. Due to these complicated data, one of the major problems is imbalanced data, which are distributed unevenly throughout the target class in datasets with;for example, one class label may contain many observations while the other may have a small number. As a result, the proposed algorithm, which is based on an oversampling method that evenly distributes the data, is used to address the problem of data imbalance. This study also emphasizes the Convolutional Neural Network (CNN), a deep learning model used with Apache Spark. The proposed system implementation is performed for balanced and imbalanced nature of NSL-KDD dataset, the benchmark dataset of intrusion detection. The experiment shows that the proposed sampling algorithm outperforms CNN models on Apache Spark compared with CNN on traditional platform. © 2023 IEEE.

关键词： Apache Spark Class Imbalance Deep Learning Oversampling

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Based on Curvelet Transform and Sparse Representation

引用

computer Systems science & Engineering 2023年第4期45卷 167-181页

作者： Israa Ismail Mohamed Meselhy Eltoukhy Ghada Eltaweel Department of Computer Science Faculty of Computers and InformaticsSuez Canal UniversityIsmailia51422Egypt Department of Information Technology University of JeddahCollege of Computing and Information Technology at KhulaisJeddahSaudi Arabia

Super-resolution techniques are used to reconstruct an image with a high resolution from one or more low-resolution image(s).In this paper,we proposed a single image super-resolution *** uses the nonlocal mean filter as a prior step to produce a denoised *** proposed algorithm is based on curvelet *** converts the denoised image into low and high frequencies(sub-bands).Then we applied a multi-dimensional interpolation called Lancozos interpolation over both *** parallel,we applied sparse representation with over complete dictionary for the denoised *** proposed algorithm then combines the dictionary learning in the sparse representation and the interpolated sub-bands using inverse curvelet transform to have an image with a higher *** experimental results of the proposed super-resolution algorithm show superior performance and obviously better-recovering images with enhanced *** comparison study shows that the proposed super-resolution algorithm outperforms the *** mean absolute error is 0.021±0.008 and the structural similarity index measure is 0.89±0.08.

关键词： Super-resolution Curvelet transform non-local means filter lancozos interpolation sparse representation

来源：评论

学校读者我要写书评

暂无评论

Modeling Cognitive-Affective Processes with Appraisal and Reinforcement Learning

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 771-782页

作者： Zhang, Jiayi Eurus Broekens, Joost Jokinen, Jussi Faculty of Information Technology University of Jyväskylä Jyväskylä Finland Leiden Institute of Advanced Computer Science Leiden University Leiden CA The Netherlands

Computational models can advance affective science by shedding light onto the interplay between cognition and emotion from an information processing point of view. We propose a computational model of emotion that integrates reinforcement learning (RL) and appraisal theory, establishing a formal relationship between reward processing, goal-directed task learning, cognitive appraisal, and emotional experiences. The model achieves this by formalizing four evaluative checks from the component process model (CPM) in terms of temporal difference learning updates: suddenness, goal relevance, goal conduciveness, and power. The formalism is task independent and can be applied to any task that is represented as a Markov decision problem (MDP) and solved using RL. We evaluate the model by predicting a range of human emotions based on a series of vignette studies, highlighting its potential to improve our understanding of the role of reward processing in affective experiences. © 2010-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Asynchronous Data Transmission Policy for Task Offloading in Edge-Computing Enabled Ultra-Dense IoT

引用

computers, Materials & Continua 2024年第12期81卷 4465-4483页

作者： Dayong Wang Kamalrulnizam Bin Abu Bakar Babangida Isyaku Liping Lei Department of Computer Science Faculty of ComputingUniversiti Teknologi MalaysiaJohor Bahru81310JohorMalaysia Department of Computer Science Faculty of Information Communication TechnologySule Lamido UniversityKafin Hausa741103JigawaNigeria School of Political Science and Public Administration East China University of Political Science and LawShanghai201620China

In recent years,task offloading and its scheduling optimization have emerged as widely discussed and signif-icant *** multi-objective optimization problems inherent in this domain,particularly those related to resource allocation,have been extensively ***,existing studies predominantly focus on matching suitable computational resources for task offloading requests,often overlooking the optimization of the task data transmission *** inefficiency in data transmission leads to delays in the arrival of task data at computational nodes within the edge network,resulting in increased service times due to elevated network transmission latencies and idle computational *** address this gap,we propose an Asynchronous Data Transmission Policy(ADTP)for optimizing data transmission for task offloading in edge-computing enabled ultra-dense *** dynamically generates data transmission scheduling strategies by jointly considering task offloading decisions and the fluctuating operational states of edge computing-enabled IoT *** contrast to existing methods,the Deep Deterministic Policy Gradient(DDPG)based task data transmission scheduling module works asynchronously with the Deep Q-Network(DQN)based Virtual Machine(VM)selection module in *** significantly reduces the computational space required for the scheduling *** continuous dynamic adjustment of data transmission bandwidth ensures timely delivery of task data and optimal utilization of network bandwidth *** reduces the task completion time and minimizes the failure rate caused by ***,the VM selection module only performs the next inference step when a new task arrives or when a task finishes its *** a result,the wastage of computational resources is further *** simulation results indicate that the proposed ADTP reduced average data transmission delay and service time by 7.11%and 8.09%,***,the tas

关键词： Bandwidth allocation edge computing internet of things task offloading reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization of Time Series Models for Predicting Networks Traffic

引用

computers, Materials & Continua 2023年第4期75卷 427-442页

作者： Reem Alkanhel El-Sayed M.El-kenawy D.L.Elsheweikh Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Department of Computer Science Faculty of Specific EducationMansoura UniversityEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia

Traffic prediction of wireless networks attracted many researchersand practitioners during the past decades. However, wireless traffic frequentlyexhibits strong nonlinearities and complicated patterns, which makes it challengingto be predicted accurately. Many of the existing approaches forpredicting wireless network traffic are unable to produce accurate predictionsbecause they lack the ability to describe the dynamic spatial-temporalcorrelations of wireless network traffic data. In this paper, we proposed anovel meta-heuristic optimization approach based on fitness grey wolf anddipper throated optimization algorithms for boosting the prediction accuracyof traffic volume. The proposed algorithm is employed to optimize the hyperparametersof long short-term memory (LSTM) network as an efficient timeseries modeling approach which is widely used in sequence prediction *** prove the superiority of the proposed algorithm, four other optimizationalgorithms were employed to optimize LSTM, and the results were *** evaluation results confirmed the effectiveness of the proposed approachin predicting the traffic of wireless networks accurately. On the other hand,a statistical analysis is performed to emphasize the stability of the proposedapproach.

关键词： Network traffic soft computing LSTM metaheuristic optimization

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：