检索结果-内蒙古大学图书馆

Effect of Vaccination on Stability of Wireless Sensor Network Against Malware Attack: An Epidemiological Model

SN computer science 2024年第2期5卷 1-13页

作者： Verma, Chakradhar Gupta, C.P. Department of Computer Science and Engineering Rajasthan Technical University Rajasthan Kota 324010 India

Wireless sensor network (WSN) has gained increased prominence due to fast deployment of sensors in IoT. With WSN being deployed in varying fields viz. industrial automation, surveillance, security in these networks has become important consideration. Security solutions employed in infrastructure networks are unsuitable for resource constrained WSNs. To limit power consumption within the node, implementing antivirus/ malware protection within the node is not recommended. However, WSNs are equally prone and vulnerable to such threats (malware, worm, virus etc.). Due to distributed topology and decentralized network control, malware detection and isolation of infected nodes needs to be carried out within the network. Techniques such as SIS (Susceptible–Infected–Susceptible), SIR (Susceptible–Infected–Recovered), SCIR (Susceptible–Carrier–Infectious–Recovered) have been proposed for malware detection in WSNs. However, the techniques suffer from quarantine and vaccination. In this paper, we propose an epidemiological model for immunizing the network against such attacks. In our method, the nodes are initially vaccinated and then deployed. This protects the malware infection after deployment. The model also has a quarantine state. A vaccinated node getting infected after deployment is placed in this state. Simulation results have shown lower probability of malware attack. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Basic reproduction number Coverage and connectivity Malware Points of equilibria Stability Wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Differently processed modality and appropriate model selection lead to richer representation of the multimodal input

引用

International Journal of Information Technology (Singapore) 2024年第7期16卷 4505-4516页

作者： Panda, Saroj Kumar Diwan, Tausif Kakde, Omprakash G. Department of Computer Science and Engineering Indian Institute of Information Technology Tata Consultancy Services

We aim to effectively solve and improvise the Meta Meme Challenge for the binary classification of hateful memes detection on a multimodal dataset launched by Meta. This problem has its challenges in terms of individual modality processing and its impact on the final classification of hateful memes. We focus on feature-level fusion methodologies in proposing the solutions for hateful memes detection in comparison with the decision-level fusion as feature-level fusion generates richer features’ representation for further processing. Appropriate model selection in multimodal data processing plays an important role in the downstream tasks. Moreover, inherent negativity associated with the visual modality may not be detected completely through the visual processing models, necessitating the differently processed visual data through some other techniques. Specifically, we propose two feature-level fusion-based methodologies for the aforesaid classification problem, employing VisualBERT for the effective representation of textual and visual modality. Additionally, we employ image captioning generating the textual captions from the visual modality of the multimodal input which is further fused with the actual text associated with the input through the Tensor Fusion Networks. Our proposed model considerably outperforms the state of the arts on accuracy and AuROC performance metrics. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Deep learning Hateful memes Multimodality Text tensor fusion VisualBERT

来源：评论

学校读者我要写书评

暂无评论

Dual-Recommendation Disentanglement Network for View Fuzz in Action Recognition

引用

IEEE Transactions on Image Processing 2023年 32卷 2719-2733页

作者： Liu, Wenxuan Zhong, Xian Zhou, Zhuo Jiang, Kui Wang, Zheng Lin, Chia-Wen Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China Wuhan University of Technology Hubei Key Laboratory of Transportation Internet of Things School of Computer Science and Artificial Intelligence Wuhan430070 China Peking University School of Electronics Engineering and Computer Science Beijing100091 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Wuhan University School of Computer Science Wuhan430072 China National Tsing Hua University Department of Electrical Engineering Hsinchu30013 Taiwan

Multi-view action recognition aims to identify action categories from given clues. Existing studies ignore the negative influences of fuzzy views between view and action in disentangling, commonly arising the mistaken recognition results. To this end, we regard the observed image as the composition of the view and action components, and give full play to the advantages of multiple views via the adaptive cooperative representation among these two components, forming a Dual-Recommendation Disentanglement Network (DRDN) for multi-view action recognition. Specifically, 1) For the action, we leverage a multi-level Specific Information Recommendation (SIR) to enhance the interaction among intricate activities and views. SIR offers a more comprehensive representation of activities, measuring the trade-off between global and local information. 2) For the view, we utilize a Pyramid Dynamic Recommendation (PDR) to learn a complete and detailed global representation by transferring features from different views. It is explicitly restricted to resist the fuzzy noise influence, focusing on positive knowledge from other views. Our DRDN aims for complete action and view representation, where PDR directly guides action to disentangle with view features and SIR considers mutual exclusivity of view and action clues. Extensive experiments have indicated that the multi-view action recognition method DRDN we proposed achieves state-of-the-art performance over powerful competitors on several standard benchmarks. The code will be available at https://***/51cloud/DRDN. © 1992-2012 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Realm of Medical Image Processing Under the Light of Artificial Intelligence 1

Realm of Medical Image Processing Under the Light of Artific...

引用

1st International Conference on Healthcare Innovations, Software and engineering Technologies, HISET 2024

作者： Tamboli, Asif I. Shah, Samarth Saxena, Gaurav Wagh, S.J. Prashanth, Addagatla Diallo, Mamadou Yero Department of Radio-Diagnosis Karad India Chandigarh University Department of Computer Science Mohali India Government Engineering College Department of Computer Science Karad India Institute of Aeronautical Engineering Electronics and Communication Engineering Hyderabad India Sharda University Computer Science & Engineering Gr.Noida India

ISBN: (纸本)9798350360707

Over the previous century, a fundamental breakthrough in medical imaging processing as well as storage occurred, with the switch from traditional detectors in radiography to digital detectors. As a result, medical imaging digitalization constitutes a big achievement and promises considerable breakthroughs in cancer. Thus, goal of study is to analyze the advanced imaging process in medical field using artificial intelligence (AI). AI, on the other hand, has the potential to go beyond these applications by producing picture-based biomarkers that are able to accurately predicting survival or response to therapy, thereby extracting far more information from photographic images than used to be conceivable. Such biomarkers might be incorporated into existing prognostic as well as predictive models used in clinical treatment, functioning as integrative biomarkers. So, the study helps in understanding importance of medical imaging processes and further helps in diagnosing minor diseases and eliminates it without human intervention with help of AI. © 2024 IEEE.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Optimized Extreme Learning Machine Framework for Efficient Ransomware Detection Using Seagull Optimization-Based Feature Selection 2

Optimized Extreme Learning Machine Framework for Efficient R...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Rajululi, G. Govinda Geetha, R. Bebitha, J. Basha, SK Mahaboob Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science & Engineering Chennai India R.M.K. Engineering College Department of Computer Science & Engineering Chennai India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Department of Computer Science & Engineering Chennai India TKR College of Engineering and Technology Department of Computer Science & Engineering Telangana India

ISBN: (纸本)9798331534950

Ransomware is becoming a more serious threat to cybersecurity, and conventional detection techniques frequently fail to maintain up with its changing strategies. To overcome this difficulty, this research proposes an extreme learning machine (ELM) framework enhances the system the efficiency in threat identification. The Static and dynamic feature of files is identified using ELM for analyzing their behavior patterns. The Seagull Optimization Algorithm (SGO) is employed for feature selection refining the dataset by eliminating redundant characteristics, to improve detection process. The system model trained with a Support Vector Machine (SVM) to determine which files are malicious and which are safe. The ELM-SGO-SVM framework is evaluated using performance metrics for identify ransomware threats and it has efficacy in early ransomware detection and mitigation by showing that it greatly outperforms existing techniques. However, this proposed method strengthens the cybersecurity defenses against ransomware threat and ensures better protection for important digital threats. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Crop Monitoring System Using Deep Learning Techniques for Increasing Production

Real-Time Crop Monitoring System Using Deep Learning Techniq...

引用

2024 International Conference on Smart Devices, ICSD 2024

作者： Dutta, Chiranjit Moudgil, Suveg Aluvala, Srinivas Saxena, Virat Raj Devi, K. Singh, Jagendra SRM Institute of Science and Technology Department of Computer Science and Engineering Ghaziabad India Galgotias University School of Computer Science Engineering Greater Noida India SR University School of Computer Science & Artificial Intelligence Warangal India Raj Kumar Goel Institute of Technology Department of Computer Science Engineering Ghaziabad India DAV Autonomous College Department of Commerce Titilagarh India Bennett University School of Computer Science Engineering & Technology Greater Noida India

ISBN: (纸本)9798350394412

This study applies machine learning to determine rice crop production using sensor information from temperature, humidity, and water levels. This project looks forward to providing insights to maximize agricultural practices and allow data-driven decision-making in rice cultivation. This is in line with how well these disparate machine learning models can predict rice crop production when measured against precision, accuracy, recall, and F1 score. To some extent, this is evident, as this study found that the machine learning models can predict yield quite satisfactorily, of which the model Random Forest performs very well in terms of precision and accuracy. Among them were the exactitude of sensor data and the algorithm selection, along with subsequent model assessment, refinement, and the ingression of great datasets inclusive of a broader set of environmental characteristics and crop yields - that were considered to be crucial in improving the precision of yield prediction algorithms. Additionally, the use of machine learning in farming has a number of benefits, such as enabling farmers to make decisions about crop management, irrigation, and optimization of yield. Combining machine learning methodologies with sensor technology can optimize resource allocation, save water, and improve overall agricultural productivity. Further, this study will facilitate the implementation of smart irrigation systems and set the stage for data-driven decision-making in agriculture for better farming practices and food production worldwide. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Intelligent Face Recognition System to Enhance Security in Residential Areas

Intelligent Face Recognition System to Enhance Security in R...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Santosh Reddy, P. Mamatha, A. Sreelatha, P.K. Bnm Institute of Technology Department of Computer Science & Engineering Bangalore India Ramaiah Institute of Technology Department of Computer Science & Engineering Bangalore India Presidency University Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350317060

The Rising price of security measures has been a significant concern recently. The study suggests creating a real-time facial recognition system to process images quickly to reduce monitoring costs and ensure that homes and businesses are secure. The primary objective of this research was to develop a deep learning-based facial recognition method for use in smart homes. This study aims to improve existing face recognition structures by using a hybrid of the SVM Increased and a convolutional neural network (CNN). The usefulness of the planned model is shown by comparing it to other state-of-the-art methods. The study presents a tree-based deep neural network for cloud-based face recognition that uses less data storage space without sacrificing accuracy. Multiple volumes are generated from the model's input volume, and trees are then constructed for each volume, considering their height and branching structure. Each split is represented by a layer of convolution and two non-linear functions forming a residual function together. Evaluate the proposed model on many open-source datasets and compare it to state-of-the-art deep models for face recognition. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Recognize Bangladeshi Shrimp Species 14

A Deep Learning Approach to Recognize Bangladeshi Shrimp Spe...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Hasan, Md. Mehedi Nishi, Jubiria Subrin Habib, Md. Tarek Islam, Mohammad Monirul Ahmed, Farruk Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Independent University Department of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798350335095

Shrimp, the most popular shellfish in Bangladesh, is a good source of protein, minerals, vitamin D, and iodine that promote a healthy body and balanced nutrition. In Bangladesh shrimp is referred to as white gold. It consumes about 70% of exported agricultural food. In our country, about 56 species of shrimp are found. Most people do not know all of the species very well. Ordinary people even the fisherman are sometimes confused about different species because of looking like the same. To solve the problem in this work we introduced an intelligence mahine that can help people to concede Shrimp species accurately. We expect this work also help the export sector to differentiate the shrimp species monitoring. To achieve the goal, we build a custom CNN algorithm for image processing and feature extraction. We build three different CNN architectures and differentiate them by hyperparameter and number of convolutional layers. Model 1 and Model 3 both obtain an accuracy of 99.01%, however Model 3 was chosen as the final model for computer Vision integration. Though both models generated the best accuracy why do we use model 3 as the final model? In this work, we will also describe with appropriate reason. © 2023 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

PANLS: Performance Analysis of Node Localization Scheme in WSNs 3

PANLS: Performance Analysis of Node Localization Scheme in W...

引用

3rd International Conference on Technological Advancements in Computational sciences, ICTACS 2023

作者： Mohan, Yogendra Yadav, Rajesh Kumar Manjul, Manisha Delhi Technological University Department of Computer Science and Engineering Delhi India Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350342338

Node localization (NL) in wireless sensor networks (WSN) has numerous applications, such as maritime rescue, agriculture, and hazardous environments, that heavily rely on the node position. In WSN, node localization is crucial since GPS-enabled sensors are not economical or energy-efficient. Therefore, GPS-enabled sensors are not appropriate for many WSN applications. The exact positioning of sensor nodes has a considerable impact on WSN performance. NL is the process of locating a target node (an unknown node). Gaussian noise and RSSI are practical methods for locating a target node's position. The seagull optimization algorithm and its improved versions are used in this research to improve the localization accuracy of nodes. To enhance the accuracy of NL and improve the randomness of the seagull optimization algorithm a chaotic map is employed in this work to enhance the seagull optimization algorithm (SOA). The performance evaluation of C-SOA is far better than the SOA. © 2023 IEEE.

关键词： chaotic-map Meta-heuristic Optimization Node Localization Wireless Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

MultiFlow: Leveraging Combined Time Series Algorithms for Accurate Traffic Forecasting 3

MultiFlow: Leveraging Combined Time Series Algorithms for Ac...

引用

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Naik, Archana Ushashree, P. Disha, N. Reddy, Hrushika Dheemanth, M. Kirthan, Shaun Sooda, Kavitha Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India Geethanjali College of Engineering and Technology Department of Computer Science and Engineering Hydrabad India BMS College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350340358

Anticipating website traffic is a significant issue today because it might interfere with the functioning of important websites. Research on time-series forecasting has been very active. Predicting future time series values is one of the most difficult problems in the field. This study of time series data covers a wide range of topics, from classification and forecasting to inference and analysis. The forecast is typically accurate when the time series databases are utilized with the quickest growth rates, despite the fact that it can be predicted using a variety of techniques. The work proposed is a unique deep learning-based time series hybrid model dependent on regression, which is a combination of different algorithms for predicting web traffic. © 2023 IEEE.

关键词： Time series

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：