检索结果-内蒙古大学图书馆

security of Information and Networks (SIN), International Conference on

作者： Halimcan Yaşar Şerif Bahtiyar Department of Computer Engineering Cyber Security and Privacy Research Lab SPFLab Istanbul Technical University Maslak Istanbul Türkiye

ISBN: (数字)9798331509736

ISBN: (纸本)9798331509743

Manned-Unmanned Teaming (MUM-T) systems integrate manned aircraft and unmanned aerial vehicles (UAVs) to enhance mission effectiveness, allowing a single pilot to coordinate multiple UAVs for tasks like reconnaissance, communication, and targeting. However, the complexity and operational demands of MUM-T systems introduce significant security challenges, particularly for mission-critical data integrity and real-time communication. In this paper, we propose a new framework for adaptive blockchain cryptography that combines Proof of Authority (PoA)-based blockchain with XOR-based lightweight authentication. The blockchain component, with the manned aircraft that serves as the sole validator, ensures tamper-resistant logging of key mission data. Additionally, it supports accountability and traceability through an efficient PoA consensus algorithm. In parallel, XOR-based lightweight authentication secures control and telemetry signals with minimal computational overhead that enables low-latency and a real-time communication. Analyses results show that the proposed framework achieves a better transaction throughput with acceptable latency, which meets the stringent security and performance requirements of MUM-T operations. The proposed framework offers a scalable and resilient solution for secure communications in complex military environments.

关键词： Military computing Mission critical systems Authentication Reconnaissance Throughput Real-time systems Blockchains Telemetry Aircraft Low latency communication

来源：评论

学校读者我要写书评

暂无评论

Neural Sequence Modelling for Spam Classification via Bidirectional LSTM and Hierarchical Neural Networks: A Deep Learning Approach

Neural Sequence Modelling for Spam Classification via Bidire...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： Yakin Ginson E. Bijolin Edwin V. Ebenezer S. Stewart Kirubakaran M. Roshni Thanka M. Manicka Raja Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

Spam messages are a major problem in digital communication. They are a breach of privacy, facilitate financial fraud and result in unnecessary clutter in one’s inbox. Most traditional methods for spam filtering are based on the older machine learning approaches. Such approaches rely on hand-crafted features which are inadequate to detect novel and progressively complex varieties of spam. As the spam messages become more sophisticated and sophisticated, we clearly require better detection algorithms. It must be able to detect small details in the text and understand the context of the messages in order to identify and filter out the spam *** this paper a deep learning architecture for accurate classification of spam using Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) networks is introduced. The proposed method tokenizes, uses embedding layers and sequence modeling to effectively analyze SMS texts in order to distinguish between spam and non spam contents. A publicly available dataset of 5,574 SMS messages was used in this study, which included 4,827 non-spam messages and 747 spam messages. To this end, the dataset was first preprocessed through text normalization, stop word removal, and padding to ensure that the input sequences were of consistent length. In order to prevent overfitting, the model was trained with an optimum learning rate, an appropriate sample size, and dropout regularization procedures. The best performing model was the BiLSTM model which was able to process sequences in both directions and achieved an accuracy of 97.3%, precision of 95.6%, recall of 96.1% and an F1-score of 95.8%. The high recall score indicates that the model is able to correctly identify spam without many false negatives which is a critical component of an effective spam detection system. The study compares the accuracy of Bidirectional Long Short-Term Memory networks with usual classifiers such as SVM, Naïve Bayes, and Random Forest. The former techni

关键词： Deep learning Support vector machines Privacy Accuracy Text categorization Bidirectional long short term memory Message services Natural language processing security Robots

来源：评论

学校读者我要写书评

暂无评论

Prediction of Consumer Price Index (CPI) in Urban India using Statistical Methods

Prediction of Consumer Price Index (CPI) in Urban India usin...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Shravya Dasu Mohana Department of Computer Science & Engineering RV College of Engineering® Bengaluru India Department of Computer Science & Engineering (Cyber Security) RV College of Engineering® Bengaluru India

The Consumer Price Index (CPI) is an important economic indicator used to measure inflation and price changes in a basket of goods and services consumed in households. It is a crucial tool for policymakers, businesses, and individuals as it helps in policy formation, wage adjustment, investment decisions, etc. The Indian government collects information on the CPI of various categories of goods in rural and urban India. Food and beverages, cereals, milk, pulses, and their products take up a large portion of the overall CPI in Urban India. Therefore, predicting the CPI will help policymakers, businesses, and individuals make smarter choices. The work carried out in this paper focuses on predicting the CPI of food and beverages, cereals, milk, pulses, and their products in Urban India using statistical time series models such as ARIMA, SARIMA, and ETS. Univariate models were developed for each of the commodities and the best model was chosen based on least MAPE and RMSE values. The minimal MAPE and RMSE values obtained show that statistical time series models were successful in predicting the CPI of food and beverages, cereals, milk, pulses, and their products in Urban India.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Target Recognition Model Based on Small Sample Image Generation 4

Remote Sensing Target Recognition Model Based on Small Sampl...

引用

4th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2023

作者： Chen, Lei Sun, Liting Space Engineering University School of Space Information Beijing China Beijing Institute of Computer Technology and Application General Department of Network and Information Security Beijing China

ISBN: (纸本)9798350306323

In recent years, remote sensing object recognition methods based on deep learning have received extensive attention. Deep learning methods need to use a large number of labeled data to carry out network training. However, the cost of labeling remote sensing image data is very high. Therefore, how to use a small number of labeled target images to train the remote sensing target classifier with high performance is an urgent problem to be solved. In view of the above problems, this paper has carried out the following work. Firstly, based on WGAN-GP, this paper optimizes the constraint conditions of neural network and proposes a depth generation model, namely CCWGAN-GP, for remote sensing image generation. Secondly, this paper proposes a remote sensing target classification model SCLNet, which makes full use of the original one-hot label and the generated soft classification label to train the neural network. Experimental results show that the proposed model can generate highly similar images to real images, and can significantly improve the performance of the classifier under training conditions with only a few labels. © 2023 IEEE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Predictive Distributed Learning based on Stability and Complexity Measures

Predictive Distributed Learning based on Stability and Compl...

引用

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Igodan, Efosa Charles Obe, Olumide O. Thompson, A.-F. Owolafe, Otasowie Usiosefe, Linda Osarumen Katyo, Peter University of Benin Faculty of Physical Sciences Dept. of Computer Science Benin City Nigeria University of Technology School of Computing Federal Dept. of Computer Science Akure Nigeria University of Technology School of Computing Dept. of Cyber Security Akure Nigeria Nigerian Custom Service Risk and Management Unit ICT - Modernization Department Abuja Nigeria

ISBN: (纸本)9798350358155

Due to the inherent properties of high dimensional datasets, the majority of feature selection methods already in use do not scale well and eventually become inapplicable. As a result of this limitation, the performance of most classifiers are degraded. The objective of this paper is to propose an improved distributed feature selection technique by sample while maintaining class distribution towards obtaining optimal subsets using data complexity-stability measures. Whilst the Kuncheva and Jaccard were applied in obtaining stable subsets, the Fisher's Discriminant Ratio was used to discriminate good candidate features from bad candidate features. The performance of the implementation framework was demonstrated using Brain Tumor Microarray datasets (using the original and the Synthetic Minority Oversampling Technique - induced datasets). The experiments contrasted the accuracy of three machine learning classifiers (decision tree, support vector machines and naive Bayes), trained with subsets of features generated by three selectors (information gain, gain ratio, and Chi-Squared). We observed that the highest accuracy percentages (100%, 100%, and 99.5%, respectively) were obtained by SVM, decision tree and naive Bayes respectively when the distributed learning techniques combined with data-complexity-stability measures were applied compared to existing techniques. Additionally, the stability of the feature subsets generated showed significant reduction both in the runtime complexities (2.97sec, 3.94sec, and 4.54sec), and the percentage of the number of selected features (0.52%, 1.39%, and 1.43%) with an alpha value of 0.75 respectively. These results showed that our proposed method achieved maximum performance and has future prospects. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Novel Gender and Age Prediction from Real Time Facial Images using Linear Regression Algorithm 8

Novel Gender and Age Prediction from Real Time Facial Images...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Nalini, N. Shahila, D. Ferlin Deva Rosi, A. Tamilselvi, M. Giri, Jayant Sherideh, Ala'a Al Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India Saveetha University Saveetha School of Engineering Department of Ece Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Zarqa University College of Information Technology Department of Cyber Security zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (纸本)9798350367904

The proposed novel algorithm utilizes linear regression in real-time facial image analysis for predicting both gender and age. By leveraging features extracted from facial data, the model aims to provide accurate and instantaneous predictions. The emergence of social media platforms has made the automatic classification of gender and age increasingly relevant. Real-time frame processing is possible with OpenCV. The expected gender and age are provided as the output, and this frame is provided as the input. The capacity to autonomously ascertain age and gender from facial images because of its versatility in facial analysis applications. However, the current models are still behind the required accuracy level, which is required for these models to be used in real-world applications, because of the significant intraclass variance of face images (such as difference in lighting, position, scale, and occlusion). In this work, a deep learning framework uses an ensemble of residual and attentional convolutional networks to reliably determine the gender and age group of facial photographs. By employing an attention mechanism, this model can concentrate on the important and instructive aspects of the face, increasing its prediction accuracy to 90.15%. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Cold Chain Distribution Model with Blockchain for Supply Chain Management 4

Deep Learning Based Cold Chain Distribution Model with Block...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Ramkumar, M. Siva Arun, M. Gopan, Gokul Giri, Jayant Al-Qawasmi, Khaled Sns College of Technology Dept of Ece India Saveetha University Department of Mechanical Engineering Chennai602105 India YeshwantraoChavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Saveetha University Department of Vlsi Microelectronics TN Chennai602105 India Zarqa University Faculty of Information Technology Department of Cyber Security Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331529635

Transportation and storage regulations are very stringent in the pharmaceutical cold chain, a subset of the logistics sector. The primary function of an integrated product supply chain manager is distribution. The pharmaceutical business places a premium on the drug distribution process because of the importance of ensuring the safe handling, storage, and distribution of medical items. False medication circulation by affiliated parties is an issue in the pharmaceutical sector. This includes data collecting for unregistered pharmaceuticals disseminated by distributors or unauthorized or unregistered distributors. Cold chain logistics for pharmaceuticals are expensive. Hence, this paper proposes a Deep Learning based Cold Chain Distribution Model (DL-CCDM) to manage the supply chain. This study presents a DL-CCDM that utilizes blockchain technology, cloud storage, and the Internet of Things (IoT). The objective is to ensure customer safety and make the whole life cycle of pharmaceutical goods trustworthyly traceable. The next step is to help with cold chain inventory management decisions by building a deep learning method using the high-quality and large-scale data generated to reduce the cost of cold chain product warehousing. This method may help the government guarantee the public's health and safety by ensuring the medications they purchase are of good quality, which improves community health and safety and trust in pharmaceuticals. © 2024 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of IoT Powered Automated Wheel Chair Controlling Mechanism Based on Artificial Intelligence Principle

Experimental Evaluation of IoT Powered Automated Wheel Chair...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Loganathan, Arulmurugan Anjaiah, K. Laxmi Bai, P. Jhansi Rani Edlabadkar, Ajinkya P. Al-Qawasmi, Khaled Thiyaneswaran, B. Bannari Amman Institute of Technology Department of Electronics and Communication Engineering Sathyamangalam India Qis College of Engineering and Technology Department of S&h Pondur Road Vengamukkapalem Ongole Andhra Pradesh Prakasam District523272 India Qis College of Engineering and Technology Department of Mba Pondur Road Vengamukkapalem Ongole Prakasam Andhra Pradesh Prakasam District523272 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India College of Information Technology Zarqa University Department of Cyber Security Zarqa Jordan Uiversity of Business and Technology Jeddah21448 Saudi Arabia Sona College of Technology Department of Ece Salem India

ISBN: (纸本)9798331543617

This paper presents the experimental evaluation of an IoT-powered automated wheelchair control mechanism based on artificial intelligence (AI) principles. The system integrates smart features such as voice control, obstacle detection, and real-time health monitoring to improve mobility for individuals with disabilities. Key components include Arduino Nano and ESP8266 microcontrollers, 12V DC motors for movement, and various sensors for health monitoring and obstacle detection. The wheelchair can be controlled via smartphone using Bluetooth or Wi-Fi, and voice commands for hands-free operation. Results from the experiment show that the voice control system demonstrated an average recognition delay of 0.5 to 0.7 seconds, while total response times under load averaged around 1.3 seconds. Health monitoring sensors, including heart rate and temperature sensors, exhibited a high accuracy, with an error margin of less than 3% for heart rate and 0.5% for temperature measurements. Obstacle detection proved effective, with an average response time of 1.2 seconds for detecting objects at 50 cm distance. Overall, the system demonstrated reliable performance across different operational conditions, making it suitable for practical applications in healthcare and personal mobility. Future enhancements aim to integrate artificial intelligence for autonomous navigation and multilingual support in the voice recognition system. © 2024 IEEE.

关键词： Wheelchairs

来源：评论

学校读者我要写书评

暂无评论

Discovering High Utility Episodes in Sequences

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第3期4卷 473-486页

作者： Gan, Wensheng Lin, Jerry Chun-Wei Chao, Han-Chieh Yu, Philip S. Jinan University College of Cyber Security Guangzhou510632 China Pazhou Lab Guangzhou510330 China Western Norway University of Applied Sciences Department of Computing Mathematics and Physics Bergen5063 Norway National Dong Hwa University Department of Electrical Engineering Hualien974 Taiwan University of Illinois at Chicago Department of Computer Science ChicagoIL60607 United States

Sequence data are more commonly seen than other types of data (e.g., transaction data) in real-world applications. For the mining task from sequence data, several problems have been formulated, such as sequential pattern mining, episode mining, and sequential rule mining. As one of the fundamental problems, episode mining has often been studied. The common wisdom is that discovering frequent episodes is not useful enough. In this article, we propose an efficient utility mining approach, namely, UMEpi: utility mining of high-utility episodes from complex event sequences. We propose the concept of remaining utility of episodes and achieve a tighter upper bound, namely, episode-weighted utilization (EWU), which will provide better pruning. Thus, the optimized EWU-based pruning strategies can achieve better improvements in mining efficiency. The search space of UMEpi w.r.t. a prefix-based lexicographic sequence tree is spanned and determined recursively for mining high-utility episodes, by prefix-spanning in a depth-first way. Finally, extensive experiments on four real-life datasets demonstrate that UMEpi can discover the complete high-utility episodes from complex event sequences. Furthermore, the improved variants of UMEpi significantly outperform the baseline in terms of execution time, memory consumption, and scalability. © 2020 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning at the Relation and Event Level for Rumor Detection 48

Contrastive Learning at the Relation and Event Level for Rum...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Xu, Yingrui Hu, Jingyuan Ge, Jingguo Wu, Yulei Li, Tong Li, Hui Chinese Academy of Sciences Institute of Information Engineering Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China University of Exeter Faculty of Environment Science and Economy Department of Computer Science United Kingdom

ISBN: (纸本)9781728163277

Existing studies for rumor detection rely heavily on a large number of labeled data to operate in a fully-supervised manner. However, manual data annotation in realistic cases is very expensive and time-consuming. In this paper, we propose a novel self-supervised Relation-Event based Contrastive Learning (RECL) framework for rumor detection to address the above issue. Specifically, we present both the relation-level and event-level augmentation strategies to generate contrastive samples, which capture both the semantics revealed by repost relations and the structural features of rumor events. Moreover, contrastive learning tasks are devised to generate informative graph representations by utilizing self-supervision signals of unlabeled data. Extensive experimental results on real-world datasets demonstrate the effectiveness of our model, especially with limited labeled data. © 2023 IEEE.

关键词： Graph neural networks

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：