检索结果-内蒙古大学图书馆

Informatica (Slovenia) 2023年第7期47卷 115-126页

作者： Oraibi, Zakariya A. Albasri, Safaa Department of Computer Science College of Education for Pure Sciences Unviersity of Basrah Basrah Iraq Electrical Engineering Department College of Engineering Mustansiriyah University Baghdad Iraq

The world witnessed big changes in 2019 when a new virus called coronavirus affected the lives of hundreds of millions of individuals and led to huge disruptions in healthcare systems. Early prediction of this virus was a top priority to limit its damage and save countless lives. Many advanced artificial intelligence technologies like deep learning have used chest X-ray images for this task. In this paper, a new CNN architecture is introduced to classify chest X-ray images. The new model is applied on a 256 × 256 × 3 input image and consists of six convolutional blocks. In addition, we improve the performance of our model by adding regularization techniques, including batch normalization and dropout. We tested our model using an imbalanced COVID-19 dataset of 5000 COVID and Non-COVID images. Four metrics were used to test the new model: sensitivity, specificity, precision, and F1 score. In experiments, we achieved a sensitivity rate of 97%, a specificity rate of 99.32%, a precision rate of 99.90%, and F1 score of 97.73% despite being provided with fewer training images. In conclusion, we proposed a light deep learning model capable of achieving high prediction accuracy that outperformed the best deep learning methods in terms of specificity and achieved high sensitivity result. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis on Optimal Routing in Wireless Mesh Network Using Optimization and Machine/Deep Learning Algorithms 3

Comprehensive Analysis on Optimal Routing in Wireless Mesh N...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kumar, Kaata Ranjith Bala, K. Srinivas, Kalyanapu Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India Vaagdevi Engineering College Department of Computer Science and Engineering Warangal India

ISBN: (纸本)9798331508456

Wireless Mesh Networks (WMNs) is an important component of wireless communications by enhancing the network coverage. The mesh network topology is interconnecting all nodes in the cluster. However, the existing approaches utilized for optimal routing in WMN face challenges such as increased delays, packet loss, network congestion that lead to inefficient data transmission. WMN has an ability to deliver efficient performance even with a large number of devices. Additionally, WMNs support a wide range of applications, by using its effectiveness in various scenarios. The fundamental architecture of a mesh network integrates multiple wireless nodes interconnected through base stations for efficient routing communication. Mesh networks able to adopt different client-based structures, including infrastructure and hybrid configurations. Optimization, learning techniques and Software defined network methods are utilized for efficient optimal routing to enhance the efficiency of data transmission, while reducing delay. In this study, routing-based optimization and Machine (ML), Deep Learning (DL) algorithms are reviewed along with its advantages and limitations. The performance ML or DL model is utilized for optimal routing in WMN is evaluated based on performance metrics such as Delay, Throughput, Packet Delivery Ratio (PDR) and Connected Client Ration (CCR). © 2025 IEEE.

关键词： Wireless mesh networks (WMN)

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Convolutional Neural Network with Pose Estimation for Human Activity Recognition

引用

computer Systems Science & engineering 2023年第2期44卷 1719-1733页

作者： S.Nandagopal G.Karthy A.Sheryl Oliver M.Subha Department of Computer Science and Engineering Nandha College of TechnologyErode638052TamilnaduIndia Department of Electronics and Communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126TamilnaduIndia Department of Computer Science and Engineering St.Joseph's College of EngineeringChennai600119TamilnaduIndia Department of Electronics and Communication Engineering University College of Engineering NagercoilNagercoil629004TamilnaduIndia

Human Action Recognition(HAR)and pose estimation from videos have gained signiﬁcant attention among research communities due to its applica-tion in several areas namely intelligent surveillance,human robot interaction,robot vision,*** considerable improvements have been made in recent days,design of an effective and accurate action recognition model is yet a difﬁcult process owing to the existence of different obstacles such as variations in camera angle,occlusion,background,movement speed,and so *** the literature,it is observed that hard to deal with the temporal dimension in the action recognition *** neural network(CNN)models could be used widely to solve *** this motivation,this study designs a novel key point extraction with deep convolutional neural networks based pose estimation(KPE-DCNN)model for activity *** KPE-DCNN technique initially converts the input video into a sequence of frames followed by a three stage process namely key point extraction,hyperparameter tuning,and pose *** the keypoint extraction process an OpenPose model is designed to compute the accurate key-points in the human ***,an optimal DCNN model is developed to classify the human activities label based on the extracted key *** improving the training process of the DCNN technique,RMSProp optimizer is used to optimally adjust the hyperparameters such as learning rate,batch size,and epoch *** experimental results tested using benchmark dataset like UCF sports dataset showed that KPE-DCNN technique is able to achieve good results compared with benchmark algorithms like CNN,DBN,SVM,STAL,T-CNN and so on.

关键词： Human activity recognition pose estimation key point extraction classiﬁcation deep learning RMSProp

来源：评论

学校读者我要写书评

暂无评论

Rucklidge-based memristive chaotic system:Dynamic analysis and image encryption

引用

Chinese Physics B 2023年第10期32卷 298-309页

作者：蹇璨岭田泽安梁波胡晨阳王桥陈靖翕 College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China College of Mathematics and Big Data Guizhou Education UniversityGuiyang 550018China College of Mechanical Engineering Guizhou UniversityGuiyang 550025China

A new four-dimensional(4D)memristive chaotic system is obtained by introducing a memristor into the Rucklidge chaotic system,and a detailed dynamic analysis of the system is *** sensitivity of the system to parameters allows it obtains 16 different attractors by changing only one *** various transient behaviors and excellent spectral entropy and C0 complexity values of the system can also reflect the high complexity of the system.A circuit is designed and verified the feasibility of the system from the physical ***,the system is applied to image encryption,and the security of the encryption system is analyzed from multiple aspects,providing a reference for the application of such memristive chaotic systems.

关键词： chaotic system memristor intermittent chaos multi-transient behavior image encryption

来源：评论

学校读者我要写书评

暂无评论

An optimal detection of android malware using dynamic attention-based LSTM classifier

引用

Journal of Intelligent and Fuzzy Systems 2023年第1期44卷 1425-1438页

作者： Jebin Bose, S. Kalaiselvi, R. Department of Computer Science and Engineering Noorul Islam Centre for Higher Education Kumaracoil India Department of Computer Science and Engineering R.M.K College of Engineering and Technology Puduvoyal Gummidipoondi India

In today's world, Android has become the most significant and standard operating system for smartphones. The acceptance of the rapidly growing android system has outcome in a significant enhancement in the number of malware on comparing earlier days. There were several antimalware programs that are designed efficiently for protecting the sensitive data of the user in a mobile system from the occurrence of such attacks. Detection of malware system based on deep learning model along with the use of optimization technique is presented in this work. Initially, android malware dataset input is acquired and the normalization process is done. The feature selection is carried along with the optimization technique Recurrent Tuna Swarm Optimization. By this, an optimal selection of features can be attained. © 2023 - IOS Press. All rights reserved.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Cardiovascular Disease Utilizing Machine Learning Techniques: Evaluating the Predictive Capabilities of Seven Algorithms

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer Science and Mathematics 2024年第1期5卷 263-276页

作者： Mijwil, Maad M. Faieq, Alaa K. Aljanabi, Mohammad Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq College of Engineering University of Information Technology and Communications Baghdad Iraq Department of Computer College of Education Aliraqia University Baghdad Iraq Imam Ja’afar Al-Sadiq University Iraq

Heart disease is the leading cause of death in developed countries, as it causes many deaths annually. Despite the availability of effective treatments, heart disease remains a significant challenge to public health, so early detection is essential in enhancing patient outcomes and reducing mortality. Artificial intelligence seeks to help physicians make the right decisions about a patient's health condition. In this regard, the authors decided to utilize machine learning techniques (k-nearest neighbor, decision tree, linear regression, support vector machine, naïve bayes, multilayer perceptron, random forest) to contribute to the classification of the heart disease dataset, where it is determined whether a person is suffering or not. After that, the execution of all techniques will be measured, and the accuracy of each technique will be compared to determine the most suitable performer. The public dataset is organized from the UC Irvine machine learning repository and have significantly different characteristics. The dataset will be divided such that 80% of the data is designated for training and 20% is designated for testing. This article concluded that the adequate performance is for the multilayer perceptron technique, as it gained an accuracy of more than 88%, while the poor performance is for the decision tree technique, as it gained an accuracy of more than 79%. © 2024 college of education, Al-Iraqia University. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Locomotion Rule Rmbedding Long Short-Term Memory Network with Attention for Human Locomotor Intent Classification Using Multi-Sensors Signals

引用

computers, Materials & Continua 2024年第6期79卷 4349-4370页

作者： Jiajie Shen Yan Wang Dongxu Zhang Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of EducationColleague of Computer Science and TechnologyJilin UniversityChangchun130012China College of Software and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun130012China

Locomotor intent classification has become a research hotspot due to its importance to the development of assistive robotics and wearable *** work have achieved impressive performance in classifying steady locomotion ***,it remains challenging for these methods to attain high accuracy when facing transitions between steady locomotion *** to the similarities between the information of the transitions and their adjacent steady ***,most of these methods rely solely on data and overlook the objective laws between physical activities,resulting in lower accuracy,particularly when encountering complex locomotion modes such as *** address the existing deficiencies,we propose the locomotion rule embedding long short-term memory(LSTM)network with Attention(LREAL)for human locomotor intent classification,with a particular focus on transitions,using data from fewer sensors(two inertial measurement units and four goniometers).The LREAL network consists of two levels:One responsible for distinguishing between steady states and transitions,and the other for the accurate identification of locomotor *** classifier in these levels is composed of multiple-LSTM layers and an attention *** introduce real-world motion rules and apply constraints to the network,a prior knowledge was added to the network via a rule-modulating *** method was tested on the ENABL3S dataset,which contains continuous locomotion date for seven steady and twelve transitions *** results showed that the LREAL network could recognize locomotor intents with an average accuracy of 99.03%and 96.52%for the steady and transitions states,*** is worth noting that the LREAL network accuracy for transition-state recognition improved by 0.18%compared to other state-of-the-art network,while using data from fewer sensors.

关键词： Lower-limb prosthetics deep neural networks motion classification

来源：评论

学校读者我要写书评

暂无评论

Experiences Memory Network for Video Semantic Segmentation 15

Experiences Memory Network for Video Semantic Segmentation

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Deore, Shalaka Shahabad, Alfiya Raskar, Shobha Pathak, Akanksha Deore, Atharva Dalvi, Harsh Department of Computer Engineering Modern Education Society's Wadia College of Engineering Pune411001 India

ISBN: (纸本)9798331300579

Human memory, while remarkable, struggles to retain and recall intricate details from various experiences. This abstract proposes a novel "Experience Memory Network" to address this limitation in the context of video semantic segmentation. The network functions as a fully connected architecture, comprising information storage units that retain data on individual video frames and relations that capture the connections between them. To facilitate efficient information retrieval and updates, the network incorporates specialized read and write modules. This architecture empowers the system to leverage past experiences (stored in the memory network) to perform semantic segmentation on new video frames. Essentially, the network learns from each frame and utilizes this knowledge to understand and segment subsequent frames, leading to improved overall performance. The segmentation evaluation of Experience Memory Network yields two crucial metrics: mean region similarity (80.2%), indicating the overall overlap between predicted and true regions, and mean contour accuracy (84.2%), which specifically assesses how well predicted contours align with actual object boundaries. Analysing both metrics together provides a holistic understanding of segmentation effectiveness, encompassing both the extent of overlap and the precision of boundary delineation. © Grenze Scientific Society, 2024.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An Advanced Encryption Algorithm for Enhancing Data Security in Cloud Computing

引用

Recent Advances in Electrical and Electronic engineering 2025年第5期18卷 623-636页

作者： Anandh, R. Swaminathan, A. Jadhav, Swati Dhondiram Valarmathi, P. Gopinath, N. Tiwari, Kanchan S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Computer Science and Business Systems Panimalar Engineering College Poonamallee Chennai India Department of Computer Engineering Keystone School of Engineering Maharashtra Pune India Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Department of Electronics and Telecommunication Modern Education Society’s Wadia College of Engineering Pune India

Aim: Cloud computing (CC) is a revolutionary new archetype in which users pool their computing resources to provide greater efficiency for everyone. Data become increasingly vulnerable to diverse security threats from attackers when millions of users circulate the same network for data transmission. Protecting these reports has shifted to the vanguard of priorities. The existing data security approach prioritizes protecting data at rest in cloud storage but gives less thought to protecting data in transit. During transmission, the data are vulnerable to intrusion attempts. Methods: The third-party auditor is provided access to data during the transfer phase, which is also the current pattern. As the attacker can now pose as a trusted third party, it makes the data more susceptible to unauthorized access. However, growing concerns regarding data privacy and security have made outsourcing sensitive information to faraway data centers difficult. As a result, new security concerns in the cloud necessitate an improved version of the tried-and-true advanced encryption standard (AES) algorithm. Key aspects presented in this study include a secure and private framework for owner data. It improves upon the 128 AES technique by adding a second round of encryption using a different key, allowing for a throughput of 1000 blocks per second. However, the standard method uses a single round key and only 800 blocks per second. The suggested approach reduces energy consumption, improves load distribution, and optimizes network trust and resource management. Results: The proposed architecture allows for the use of AES with cipher lengths of 16, 32, 64, and 128 bytes. The effectiveness of the algorithm in terms of attaining target quality metrics is illustrated graphically via simulation results. This strategy reduces power consumption by 13.23%, network utilization by 12.43%, and delay by 16.53%, according to the outcomes. Conclusion: As a result, the recommended architecture enhance

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Routing Protocol in Flying Ad Hoc Networks: A Review

引用

computers, Materials & Continua 2025年第2期82卷 1615-1643页

作者： Priyanka Manjit Kaur Deepak Prashar Leo Mrsic Arfat Ahmad Khan Department of Computer Science and Engineering(CSE) Lovely Professional UniversityPhagwara144411India Department for Program Engineering Algebra UniversityGradiscanska 24Zagreb10000Croatia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand

“Flying Ad Hoc Networks(FANETs)”,which use“Unmanned Aerial Vehicles(UAVs)”,are developing as a critical mechanism for numerous applications,such as military operations and civilian *** dynamic nature of FANETs,with high mobility,quick node migration,and frequent topology changes,presents substantial hurdles for routing protocol *** the preceding few years,researchers have found that machine learning gives productive solutions in routing while preserving the nature of FANET,which is topology change and high *** paper reviews current research on routing protocols and Machine Learning(ML)approaches applied to FANETs,emphasizing developments between 2021 and *** research uses the PRISMA approach to sift through the literature,filtering results from the SCOPUS database to find 82 relevant *** research study uses machine learning-based routing algorithms to beat the issues of high mobility,dynamic topologies,and intermittent connection in *** compared with conventional routing,it gives an energy-efficient and fast decision-making solution in a real-time environment,with greater fault tolerance *** protocols aim to increase routing efficiency,flexibility,and network stability using ML’s predictive and adaptive *** comprehensive review seeks to integrate existing information,offer novel integration approaches,and recommend future research topics for improving routing efficiency and flexibility in ***,the study highlights emerging trends in ML integration,discusses challenges faced during the review,and discusses overcoming these hurdles in future research.

关键词： FANET protocol machine learning

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：