检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Circuits and communication Systems, ICICACS 2024

作者： Rao, K Rama Swapna Kumari, Manthena Eklarker, Ravindra Shaker Reddy, Pundru Chandra Muley, Kirti Burugari, Vijay Kumar Geethanjali College of Engineering and Technology Electronics and Communication Engineering Telangana Hyderabad India Hyderabad India Vardhaman College of Engineering Department of Ai &ds Telangana Hyderabad India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal India Bharati Vidyapeeth's Institute of Management and Information Technology Master of Computer Applications Navi Mumbai India Koneru Lakshmaiah Education Foundation Computer Science and Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798350317558

Agriculture and its large yields are vital to human survival. Recently, machine learning and deep learning have been applied to determine agricultural output. This study estimated apple production utilizing a unique deep-learning(DL)-based technique. A study-designed convolutional neural network (CNN) classified golden and royal gala apple photos. Classifying CNN-extracted pictures with traditional machine-learning(ML) methods was a hybrid application. Datasets A is used to evaluate the performance of the proposed model. Based on Dataset A accuracy findings, the CNN-SVM hybrid model performed best. CNN-SVM and CNN-Gradient Boosting hybrid models performed best and accurately for Dataset A. The more balanced distribution of train, test, and validation sizes, the suggested hybrid CNN model, and the model's assessment made dataset C the best choice. The hybrid model was 99.70% accurate for Dataset A. Precision, recall, f-measure, and Cohen kappa were 99%. The study found that hybrid models could accurately predict apple fruit yield using golden and royal gala photos. © 2024 IEEE.

关键词： DL Ensemble-Methods ML Smart-farms Yield-Prediction

来源：评论

学校读者我要写书评

暂无评论

BER Improvement of Cooperative Spectrum Sharing of NOMA in 5G Network 3

BER Improvement of Cooperative Spectrum Sharing of NOMA in 5...

引用

3rd IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Hassan, Mohamed Saeed, Rashid A. Mokhtar, Rania A. Hamid, Khalid Ali, Elmustafa Sayed Odeh, Nidhal Singh, Manwinder Khalifa, Othman O. Islam, Shayla Lovely Professional University Department of Wireless Communication Punjab Phagwara144001 India Taif University Department of Computer Engineering College of Computers and Information Technology Taif21944 Saudi Arabia University of Science & Technology Department of Communication Systems Engineering Omdurman Sudan Department of Electronics Engineering Khartoum Sudan University of Wollongong School of Electrical Computer and Telecommunications Engineering Australia International Islamic University Malaysia Department of Electrical and Computer Engineering Gombak Malaysia Libyan Center for Engineering Resarch and Information Technology Bani Waleed Libya Institute of Computer Science and Digital Innovation Ucsi University Malaysia Department of Computer Science Kuala Lumpur56000 Malaysia

ISBN: (纸本)9798350319897

Non-orthogonal multiple access is one of the best methods for addressing the needs of 5G wireless services (NOMA). The proliferation of mobile devices in recent years has increased the importance of cooperative spectrum sharing and utilization in wireless communication due to increases in the bit error rate (BER) brought on by collisions and interference. In this study, MIMO and Massive MIMO (M-MIMO) in the downlink (DL) NOMA power domain (PD) in conjunction with the Cooperative Cognitive Radio Network are proposed as two new ways for improving and evaluating BER in the 5G network (CCRN). Customers of NOMA compete for available channels on the CCRN in this first strategy. The second approach creates a dedicated channel for NOMA users. Three scenarios with varying distances, power location coefficients, and transmission power are used to evaluate the proposed methods in the MATLAB software program. It is assumed that four users will share a 90 MHz BW using QPSK modulation in all three scenarios. When evaluating the performance of the suggested system under the presumption of frequency-selective Rayleigh fading, concurrent interference cancellation (SIC) and unstable channel conditions are also considered. © 2023 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Network Security Algorithm Using Machine Learning 10

Enhancing Network Security Algorithm Using Machine Learning

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, electronics and computer engineering, UPCON 2023

作者： Satav, Sandip D Patel, Hiteshkumar Gunvantbhai Walke, Suchita Megala, R. Patel, Charushila Axay Pavithra, G. Information Technology JSPM's Jayawantrao Sawant Coe Pune411028 India Quality Engineering - Data Tiger Analytics Tamil Nadu Chennai India Mumbai University Pillaicollege of Engineering and Technology Department of Computer Engineering India Sri Eshwar College of Engineering Department of Computer and Communication Engineering Tamilnadu Coimbatore641202 India Department of Electrical Engineering Gujarat Surat India Dayananda Sagar College of Engineering Electronics & Communication Engineering Karnataka Bangalore560111 India

ISBN: (纸本)9798350382471

In light of the increasing sophistication of cyber threats in today's linked world, network security is of paramount importance. Monitoring network traffic and detecting suspicious activity is where intrusion detection systems (IDS) shine, playing a crucial role in identifying and managing these threats. There has been a rise in the use of machine learning methods to improve IDS performance. In order to improve network safety, a new hybrid method is proposed in this study, which combines Random Forest (RF) with Support Vector Machine (SVM) to perform intrusion detection. The proposed hybrid RF and SVM approach draws on the best features of both models to enhance intrusion detection precision and reliability. As an ensemble learning technique, Random Forest excels at both feature selection and handling big datasets. Conversely, Support Vector Machine has earned acclaim for its prowess in binary classification problems and its ability to locate complicated decision boundaries. We want to improve upon intrusion detection by integrating these two techniques, which have complimentary characteristics. The first step in this study is to compile a large dataset of legitimate and malicious network traffic. A preprocessing pipeline is built up to guarantee the quality of the data, and feature engineering techniques are used to extract useful information from the dataset. This preprocessed dataset is then used to train a hybrid RF and SVM algorithm using labelled data containing known intrusion cases. Extensive tests and comparisons to other intrusion detection methods are used to assess the performance of the proposed algorithm. The efficiency of the hybrid RF and SVM algorithm in identifying network intrusions is evaluated using performance measures like as accuracy, precision, recall, F1-score, and area under the Receiver Operating Characteristic (ROC-AUC) curve. This research shows that a system that combines RF and SVM for intrusion detection may beat both conventional me

关键词： etc Hybrid Algorithm i Intrusion Detection System (IDS) Machine Learning Network Security Random Forest (RF) Support Vector Machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Implementation of Optimal Classification Algorithms for Credit Card Fraud Detection 2

Evaluation and Implementation of Optimal Classification Algo...

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Sampath Kini, K. Pushpakumar, R. Senthamil Selvan, R. Praveenkumar, G.D. Basi Reddy, A. Nitte Deemed To be University Department of Computer Science and Engineering Karkala India Vel Tech Rangarajan Dr.Sangunthala R&d Institute of Science and Technology Department of Information Technology Avadi India Annamacharya Institute of Technology and Sciences Department of Electronics and Communication Engineering Tirupati India Kongu Engineering College Department of Computer Technology Erode India School of Computing Mohan Babu University Department of Computer Science and Engineering Tirupati India

ISBN: (纸本)9798350364699

Nowadays, the credit card industry is more concerned about credit card fraud than any other problem. The main idea is to examine optional techniques used for fraud detection and to identify the different types of credit card fraud. Numerous strategies exist for lowering the prevalence of credit card fraud, each tailored to the specific threats faced by banks and the credit card industry. Credit card fraud prevention is the primary goal of implementing these measures. Existing methods have several unresolved issues that cause legitimate credit card customers to be mistakenly labelled as fraudulent. The amount of fraud in the financial sphere may be inferred from this paper's emphasis on integrating the best classification algorithm out of four distinct methods. © 2024 IEEE.

关键词： Credit card fraud faced by bank Financial sphere mistakenly labelled Primary Goal

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Security of 6G Vehicular Networks with UAV Systems:First Order Secrecy Metrics,Optimization,and Bounds

引用

computers, Materials & Continua 2024年第9期80卷 3685-3711页

作者： Sagar Kavaiya Hiren Mewada Sagarkumar Patel Dharmendra Chauhan Faris A.Almalki Hana Mohammed Mujlid Smt.Chandaben Mohanbhai Patel Institute of Computer Applications Charotar University of Science and TechnologyChangaAnand388421India Electrical Engineering Department Prince Mohammad Bin Fahad UniversityP.O.Box 1664Al Khobar31952Kingdom of Saudi Arabia Department of Electronics and Communication Engineering Chandubhai S.Patel Institute of TechnologyCharotar University of Science and TechnologyChangaAnand388421India Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Kingdom of Saudi Arabia

The mobility and connective capabilities of unmanned aerial vehicles(UAVs)are becoming more and more important in defense,commercial,and research ***,their open communication makes UAVs susceptible toundesirablepassive attacks suchas eavesdroppingor ***,the inefficiencyof traditional cryptography-based techniques has led to the addition of Physical Layer Security(PLS).This study focuses on the advanced PLS method for passive eavesdropping in UAV-aided vehicular environments,proposing a solution to complement the conventional cryptography ***,we present a performance analysis of first-order secrecy metrics in 6G-enabled UAV systems,namely hybrid outage probability(HOP)and secrecy outage probability(SOP)over 2×2 Nakagami-m ***,we propose a novel technique for mitigating passive eavesdropping,which considers first-order secrecy metrics as an optimization problem and determines their lower and upper ***,we conduct an analysis of bounded HOP and SOP using the interactive Nakagami-m channel,considering the multiple-input-multiple-output configuration of the UAV *** findings indicate that 2×2 Nakagami-mis a suitable fadingmodel under constant velocity for trustworthy receivers and *** results indicate that UAV mobility has some influence on an eavesdropper’s intrusion during line-of-sight-enabled communication and can play an important role in improving security against passive eavesdroppers.

关键词： Physical layer security 3D positioning 6G communications UAV systems

来源：评论

学校读者我要写书评

暂无评论

Creating Realities: An In-Depth Study of AI-Driven Image Generation with Generative Adversarial Networks 15

Creating Realities: An In-Depth Study of AI-Driven Image Gen...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Dhand, Raman Sidana, Sagar Sinha, Anurag Kumar, Biresh Kumari, Shreya Madhukar Rao, G. Raj, Petheru Al-Khayyat, Ahmed Maheswaran, S. Guru Tegh Bahadur Institute of Technology Department of computer science and engineering India Maharshi Dayanand University Department of computer science and engineering Haryana Rohtak India IGNOU India School of Computing and information Science New Delhi India Amity University Department of computer science and It Jharkhand India Koneru Lakshmaiah Education Foundation Department of computer science and engineering India Reliance Jio Platforms Ltd Bangalore India Islamic University Department of computer science and engineering Iraq Kongu Engineering College Department of Electronics and Communication Engineering Erode Perundurai638060 India

ISBN: (纸本)9798350370249

The field of artificial intelligence has witnessed significant advancements with the advent of Generative Adversarial Networks, revolutionizing image generation techniques. The literature review covers seminal works and recent advancements, highlighting the evolution of image generation techniques. Taxonomy is developed to classify methods based on their underlying principles and applications across various domains including art, fashion, healthcare, and entertainment. Comparative analysis evaluates the effectiveness, efficiency, and applicability of different models, utilizing metrics corresponding Inception Score and Frechet Inception Distance. By conducting a thorough review of existing literature and technologies, we explore the evolution of GAN architectures, from their inception to the latest innovations. We examine various GAN models, including DCGAN, StyleGAN, and CycleGAN, assessing their effectiveness in generating high-fidelity images across diverse applications. In addition to this comprehensive analysis, we present our own implementation of a GAN model tailored for specific image generation tasks. Our model is tested on multiple datasets to evaluate its performance, highlighting improvements in training stability and image quality. We discuss the architectural choices, optimization techniques, and training procedures employed in our implementation. Furthermore, we address the challenges faced in the field, such as mode collapse, training instability, and the need for largescale datasets. Our findings offer valuable insights into optimizing GAN performance and propose potential directions for future research. This comprehensive analysis serves as a foundational reference for researchers and practitioners aiming to leverage GANs for advanced image generation tasks, pushing the boundaries of what is visually conceivable through artificial intelligence. © 2024 IEEE.

关键词： AI computer vision Deep Learning GANs Image generation ML

来源：评论

学校读者我要写书评

暂无评论

Balancing And Risks: Managing Machine Learning In Mental Health Applications 15

Balancing And Risks: Managing Machine Learning In Mental Hea...

引用

15th International Conference on Computing communication and Networking Technologies, ICCCNT 2024

作者： Upendra, Sheela Verma, Pushpendra Kumar Gupta, Prerana Kulanthaivel, M. Karthigaikumar, P. Maral, Vikas B. Department of Symbiosis College of Nursing Pune India Iimt University School of Computer Science and Applications Meerut India Tmu Department of Psychitary India Karpagam Academy of Higher Education Department of Microbiology Tamil Nadu Coimbatore India Karpagam College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Vishwakarma Institute of Information Technology Computer Engineering Pune India

ISBN: (纸本)9798350370249

The Evaluation Technique, which uses AI, has the potential to completely change the way mental health services are provided. An overview of artificially intelligent technology (AI) and its most recent developments in the medical industry is provided in this article. It also reviews current research on mental health, emphasizing how AI may help with diagnosis and therapy while taking into account its present drawbacks, unexplored territory, and ethical ramifications. New Developments: We have taken a look at psychological wellbeing analyses and evaluations that classify or split psychological problems like discomfort, extreme personality disorder, and various mental illnesses, such suicide ideas and attempts, into different categories. These evaluations make use of medical records, scales for measuring mood, neuroimaging data, cutting-edge monitoring systems, and information from social media sites. The promise of statistical machine learning to treat issues with mental health is shown by these study findings, but it is crucial to identify the methods that provide the greatest outcomes. Together, these investigations add to the expanding corpus of research that shows how AI may be used in psychiatric treatments. As AI methods develop, they hold the potential to help mental health professionals define psychotic symptoms accurately, recognize chronic illnesses at an earlier, asymptomatic stage when measures can be more effective, and customize treatment plans based on unique patient characteristics. However, care must be taken to avoid extrapolating too soon from preliminary results. To close the gap between clinical therapy and behavioral health research, further study is necessary. © 2024 IEEE.

关键词： AI in healthcare and therapy computational intelligence data mining Diagnosis emotional wellness Innovative monitoring systems Mental health Neuroimaging data Personalized therapy

来源：评论

学校读者我要写书评

暂无评论

Enhanced Food Classification System Using YOLO Models For Object Detection Algorithm 14

Enhanced Food Classification System Using YOLO Models For Ob...

引用

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

作者： Sudharson, S. Kokil, Priyanka Annamalai, R. Sai Manoj, N.V. Computer Science and Engineering Vellore Institute of Technology Chennai India Electronics and Communication Engineering Indian Institute of Information Technology Design and Manufacturing Kancheepuram Chennai600127 India Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai601103 India

ISBN: (纸本)9798350335095

Food classification is crucial for the food industry and has a significant impact on public health and nutrition. Deep learning techniques such as YOLOv5 and YOLOv7 have recently shown significant improvement in food categorization accuracy. The results of this study's analysis of both models is evaluated on a manually labeled dataset, evaluating their accuracy, recall, and mAP at the different intersections over union (IoU) criteria. The accuracy, recall, and mAP of both YOLOv5 and YOLOv7 were evaluated at various IoU criteria, and the results showed that YOLOv5 outperformed YOLOv7 in all three metrics. Specifically, YOLOv5 achieved an accuracy score of 0.851 and a recall score of 0.836, whereas YOLOv7 scored 0.67 and 0.675, respectively. Furthermore, YOLOv5's mAP score at the 0.5 IoU threshold was 0.892, while YOLOv7 scored 0.669. At the 0.5-0.95 IoU threshold, YOLOv5's mAP was 0.644 and YOLOv7's was 0.426. This study demonstrates that YOLOv5 is a superior deep learning model for food categorization tasks, with potential implications for improving consumer nutrition and food safety in the food industry. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Multi-Horizon Forecasting of Average Daily PM 2.5Concentration: A Case Study of Air Pollution in Singapore 3

Multi-Horizon Forecasting of Average Daily PM 2.5Concentrati...

引用

3rd International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2023

作者： Tripathi, Anjali Hari, Manoj Tikkiwal, Vinay Anand Tyagi, Bhishma Kumar, Arun National Institute of Technology Department of Earth and Atmospheric Sciences Odisha Rourkela India Jaypee Institute of Information Technology Department of Electronics and Communication Engineering Noida India National Institute of Technology Rourkela Department of Computer Science and Engineering Odisha India

ISBN: (纸本)9798350300604

Understanding the spatial and temporal dynamics of surface concentrations of particulate matter ($\mathbf{PM}_{2.5}$ and PM10) is essential in air quality modelling and climate research. Forecasting of air pollutants is necessary to understand the variation of pollutants and to plan and implement air pollution control measures. This work proposes a methodology for forecasting $\mathbf{PM}_{2.5}$ concentration using various meteorological parameters over multiple time horizons. The proposed deep learning-based models forecast the daily average values concentration for $\mathbf{PM}_{2.5}$ in Singapore. The performance metrics indicate the efficacy of the proposed model in forecasting $\mathbf{PM}_{2.5}$ concentrations over different horizons. The analysis shows that $\mathbf{PM}_{2.5}$ concentrations are best forecasted for the 3-days ahead scenario, with RMSE and MAPE being 3.767 $\mu \mathrm{g}/\mathrm{m}3$ and 6.82%, respectively. © 2023 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Automatic Road Extraction using Scale Invariant Feature Transform-based Random Forest in Satellite Images 1

Automatic Road Extraction using Scale Invariant Feature Tran...

引用

1st International Conference on Software, Systems and information Technology, SSITCON 2024

作者： Rajesh, N. Alzubaidi, Laith H. Shivaprasad Yadav, S.G. Chembian, W.T. Prameela, Boddepalli Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India The Islamic University of Babylon Department of Computers Techniques Babylon Iraq Ramaiah Institute of Technology Department of Electronics and Telecommunication Engineering Bengaluru India Department of Computer Science and Engineering Chennai India Vignan's Institute of Information and Technology Department of Artificial Intelligence and Data Science Andhra Pradesh India

ISBN: (纸本)9798350352931

Road Extraction from High-Resolution Satellite Images (HRSI) plays a significant role in the analysis of the remote sensor image field. The extraction of road automatically labels a road's pixels in a satellite image with semantic features depending on topographical meaningful features. However, manual road extraction inaccurately extracts road networks from satellite images which has significant difficulties like complex urban environments, varying road types, and diverse image conditions. Therefore, the Scale Invariant Feature Transform-based Random Forest(SIFT-RF) is proposed for automatic road extraction in satellite images. First, the image is obtained from DeepGlobe dataset and Z-score normalization is employed to maximize model performance. Then, SIFT is established to extract the road network in satellite images. Finally, the RF is utilized to extract and classify roads as road or non-road using Machine Learning (ML). The SIFT-RF achieves a greater f1-score of 98.24% compared to existing methods like Dual-Attention Road extraction Network (DA-RoadNet), High-Resolution U-Net architecture (HRU-Net), and Global Context-aware and Batch-independent Network (GCBNet) respectively. © 2024 IEEE.

关键词： Random forests

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：