检索结果-内蒙古大学图书馆

A Blockchain-Assisted Trusted Federated Learning for Smart Agriculture

SN computer science 2025年第3期6卷 1-26页

作者： Manoj, T. Makkithaya, Krishnamoorthi Narendra, V.G. Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal 576104 India

Smart agriculture promises to alleviate the burden of climate risks on crop production by leveraging machine learning tasks. These tasks act as a decision support instrument for making well-informed choices by stakeholders in the agricultural value chain. Currently, predictive models in smart agriculture demand a centralized collection of diverse data, fragmented across multiple information systems leading to a single point of failure. The application of the Federated Learning (FL) technique restricts the movement of raw data and trains the model at the data source. However, the FL approach does not ensure trust factors like privacy, authentication, data provenance, transparency and traceability. To address this, a decentralized federated learning framework built on blockchain can be a potential solution. In this study, we introduce a blockchain-based framework called AgriFLChain for trusted federated learning in the context of smart agriculture. We focus on crop yield prediction as an illustrative use case, initially discussing centralized deep learning models (ResNet-16, ResNet-28, CNN-DNN, and CNN-LSTM). We then detail the authentication and data provenance mechanisms for federated learning participants, utilizing blockchain-based Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). We implement these models using vanilla federated learning and Differential Privacy (DP) federated learning approaches, achieving transparency and traceability through smart contracts by recording metadata of model updates into the blockchain. Finally, detailed evaluation demonstrates that AgriFLChain achieves comparable efficiency to centralized models while maintaining scalability in blockchain transactions for higher data volumes. © The Author(s) 2025.

关键词： Blockchain Crop yield prediction Deep learning Federated learning Smart agriculture Smart contracts

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Smoking Likelihood: A Machine Learning Regression Analysis 2

Predicting Student Smoking Likelihood: A Machine Learning Re...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kocher, Sheen Kumar, Horesh Jain, Tarun Kumar, Ashish Manipal University Jaipur Department of Computer Science & Engineering Jaipur India G.L. Bajaj Institute of Technology and Management Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350382952

Smoking stands as a prominent preventable hazard that contributes to untimely mortality. Smoking remains a concern for health among students as it has enduring impacts on both personal well being and society, at large. For the purpose of creating focused treatments and preventive programs, it is essential to identify the variables that affect students' propensity to start smoking. This study uses machine learning regression approaches to give a thorough analysis of predicting student smoking propensity. We acquired a variety of data from a sizable number of students who were enrolled in educational institutions. Details about their demographics, socioeconomic situation, academic accomplishments, peer influences, and various facets of their lifestyle are included in this data. We utilized this dataset to make predictions on the probability of students engaging in smoking. In our research we employed regression models such, as Linear regression, Ridge regression, Lasso regression, Decision tree regression etc. Keywords - PCOS, Machine Learning, Classification, SVM, KNN, XGBoost, Logistic Regression, Random Forest. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhancing Trajectory Tracking of Quadrotor Using Feedback Linearization with MPC-LPV and LQI-LPV under Variable Disturbances 3

Enhancing Trajectory Tracking of Quadrotor Using Feedback Li...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Chowdhury, Raian Haider Imtiaz Ferdous, Ahmed Hossain, Amreen Rahman, Kazi Arafat Bangladesh University of Engineering and Technology Department of Mechanical Engineering Dhaka Bangladesh Brac University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

The deployment of Unmanned Aerial Vehicles (UAVs) has markedly improved industrial efficiency. Optimizing control algorithms for precise path tracking is essential for enhancing the reliability and performance of these systems. This paper presents a comparative analysis of Model Predictive Controller (MPC) and Linear Quadratic Integral (LQI) controller, combined with the Linear Parameter Varying (LPV) approach, for quadrotor trajectory tracking under variable disturbances. The quadrotor is modeled using Newton-Euler equations for a six-degrees-of-freedom system. The control architecture includes an outer loop position controller using Feedback Linearization (FL) and an inner loop attitude controller implemented as either MPC-LPV or LQI-LPV. Disturbances are modeled using a custom sinusoidal model. Numerical simulations are done to evaluate controller performance for six different trajectories. The results for the helical trajectory indicate that under variable disturbances, the MPC-LPV+FL outperforms the LQI-LPV+FL. The MPC-LPV+FL achieves a steady-state error of 0.1934 m compared to 0.6611 m for the LQI-LPV+FL. Additionally, the MPC-LPV+FL reaches the minimum error in 3.1 seconds, compared to 3.8 seconds for the LQI-LPV+FL, resulting in a 22.58% faster response. Therefore, MPC-LPV+FL is the superior choice based on accuracy, stability, and speed of response under adverse conditions. © 2024 IEEE.

关键词： Feedback linearization

来源：评论

学校读者我要写书评

暂无评论

Influence of Opinion Formation on Polarization in Social Networks 14

Influence of Opinion Formation on Polarization in Social Net...

引用

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

作者： Das, Susmita Dutta, Sangita Chakraborty, Susanta Biswas, Samit Indian Institute of Engineering Science and Technology Department of Computer Science and Technology Shibpur711103 India

ISBN: (纸本)9798350335095

Online social networks have introduced diverse discussions regarding different topics. At the same time, these platforms have also garnered the idea of shaping opinions. The increase in user engagement in case of arguments has led to the issue of polarization in online social media platforms. In this paper, we have studied the influence of opinion change on homophily in social networks and the variation in polarization. Our own new method has been proposed for analysing the modification of user opinions dynamically in different timestamps. The probability of information sharing varies depending on the opinion similarity and homophily in social networks alters accordingly. Our approach portrays the opinion modification dynamics for different network features using complex networks concepts. We have observed that on social interaction networks like Twitter, opinion, information sharing and homophily perform a significant role in the determination of online polarization. Our approach has been compared with an established approach over external datasets and the results obtained are promising. © 2023 IEEE.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

ItoV: Efficiently Adapting Deep Learning-Based Image Watermarking to Video Watermarking

ItoV: Efficiently Adapting Deep Learning-Based Image Waterma...

引用

2023 International Conference on Culture-Oriented science and technology, CoST 2023

作者： Ye, Guanhui Gao, Jiashi Wang, Yuchen Song, Liyan Wei, Xuetao Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

ISBN: (纸本)9798350357998

Robust watermarking tries to conceal information within a cover imag e/video imperceptibly that is resistant to various distortions. Recently, deep learning-based approaches for image watermarking have made significant advancements in robustness and invisibility. However, few studies focused on video watermarking using deep neural networks due to the high complexity and computational costs. Our paper aims to answer this research question: Can well-designed deep learning-based image watermarking be efficiently adapted to video watermarking? Our answer is positive. First, we revisit the workflow of deep learning-based watermarking methods that leads to a critical insight: temporal information in the video may be essential for general computer vision tasks but not for specific video watermarking. Inspired by this insight, we propose a method named ITOV for efficiently adapting deep learning-based Image watermarking to Video watermarking. Specifically, ITOV merges the temporal dimension of the video with the channel dimension to enable deep neural networks to treat videos as images. We further explore the effects of different convolutional blocks in video watermarking. We find that spatial convolution is the influential primary component in video watermarking, and depthwise convolutions significantly reduce computational costs with negligible impact on performance. In addition, we propose a new frame loss to constrain that the watermark intensity in each video clip frame is consistent, significantly improving the invisibility. Extensive experiments show the superior performance of the adapted video watermarking method compared with the state-of-the-art methods on Kinetics-600 and Inter4K datasets, which demonstrates the efficacy of our method ITOV. © 2023 IEEE.

关键词： Image watermarking

来源：评论

学校读者我要写书评

暂无评论

Meta-learning with orthogonal softmax layer (MLOSL) for small sample hyperspectral image classification

引用

Multimedia Tools and Applications 2025年 1-30页

作者： Amoako, Prince Yaw Owusu Cao, Guo Shi, Hao Arthur, John Kingsley Agyenim, Yaw Oti Boateng School of Computer Science and Engineering Nanjing University of Science and Technology Xiaolingwei Nanjing City210094 China Department of Computer Science Valley View University Accra Oyibi Ghana ETSU Municipal Center East Tennessee State University Johnson CityTN United States

Recent research on Hyperspectral image classification (HSIC) has been much concerned with small sample size due to the challenges of obtaining large labeled data. Coupled with this is the challenge with optimization of the models’ structure and computational complexities. Meta-learning techniques have been proposed to improve classification accuracy on small training data samples. The existing meta-learning techniques still require several pre-collected labeled hyperspectral images (HSI) source datasets of large labeled samples for meta-training, which is undoubtedly a huge task and time-consuming. We propose a meta-learning with orthogonal softmax layer (MLOSL) for small sample HSIC. Orthogonality is introduced to address the structural and computational complexities of deep convolutional neural network (CNN) models for HSIC. An unsupervised meta-learning task construction extracts multiview spectral dimension features of different bands from the same sample, whereas the spatial dimension multiview features are extracted through data augmentation. The orthogonal softmax layer captures a wider variety of patterns in the data by promoting variation among the weight vectors, potentially improving generalization to unobserved samples and minimizing computational time. Label smoothing is added to the classification loss to lessen the impact of incorrectly classified samples and class imbalance. Experimental outcomes on four target datasets compared to existing state-of-the-art models indicate the competitiveness of the proposed model's small sample HSIC performance and its suitability in time-constraint applications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Implementation of Hector SLAM Algorithm for Mapping Indoor Environments with Obstacles 3

Implementation of Hector SLAM Algorithm for Mapping Indoor E...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Hossain, Amreen Chowdhury, Raian Haider Brac University Department of Computer Science and Engineering Dhaka Bangladesh Bangladesh University of Engineering and Technology Department of Mechanical Engineering Dhaka Bangladesh

ISBN: (纸本)9798331534400

Autonomous navigation in obstacle-rich indoor environments is crucial for both industrial and domestic robotic applications. A central aspect of this process is Simultaneous Localization and Mapping (SLAM). This paper presents a comprehensive methodology for implementing Hector SLAM, a widely used SLAM algorithm that operates without relying on external odometry and pose data from wheel encoders or Inertial Measurement Unit (IMU) sensors. The experimental setup involves a custom-built two-wheeled mobile robotic platform, equipped with essential components including a 2D Light Detection and Ranging (LiDAR) sensor, wheel encoders, IMU, motor drivers, an Arduino UNO, and a Raspberry Pi 4B, with Robot Operating System (ROS) serving as the primary software framework. The robot navigates within a predefined rectangular indoor environment, where real-time mapping results are captured at different time intervals to assess mapping accuracy. Additionally, a randomly placed object is introduced to test the obstacle detection capability during operation. Results indicate that Hector SLAM demonstrates high accuracy, achieving precision within a few centimeters, particularly in environments with distinct structural features. © 2024 IEEE.

关键词： Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Enabling Gesture-based Application Interaction on Head Mounted VR Display 7

Enabling Gesture-based Application Interaction on Head Mount...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Rishi Kalis, K. Rohith, V. Kalaiarasi, G. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397253

With the integration of smartphones, VR head-mounted displays that are affordable (HMDs) have made VR more accessible to the general public and increased its widespread use. However, due to their lack of interaction, these systems frequently have limitations. GestOnHMD, a technique for a pipeline for classifying gestures and gesture-based interaction, is presented in this study. It makes use of the gesture technique in smartphones to detect hand gestures, detecting 21 points on hand on VR headset. Initially, gesture-elicitation research is carried out using specific headset the Google Cardboard to detect the 21 hand points which detects the hand gestures and display the meaning of the hand gesture. Based on signal detectability and user choices, different kinds of gestures are selected to input the dataset. It uses the neural networks to map the hand points and the cam detects the hand gestures and recognizes it and the displays the meaning of each On the VR device's screen. Each gesture can be made specifically for the commands and its meaning by showing the hand gesture in front of the cam and storing it in the dataset. It can be used to read American Signal Language, etc. which makes people to understand hand gestures and might help in future exploring. The output is displayed on the Google Cardboard Virtual Reality device screen which is connected to the laptop. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Prediction Accuracy of Corn Leaf Diseases Using A Pre-Trained Network Model

Analyzing the Prediction Accuracy of Corn Leaf Diseases Usin...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Ashwini, C. Sellam, V. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396485

During corn's exploration and manufacturing phases, farmers have a complicated issue in accurately diagnosing corn crop infections. To solve this issue, this work provides a method for specific position three prevalent diseases of corn leaves: grey spot, leaf blight, and rusty depending on grouping and an upgraded deep learning method. Deep learning advancements paved the path for enhancing prediction accuracy as its significance is adopted over various research fields. Disease prediction and classification is time-consuming due to the lesser foreground and background intensity information. To identify three illnesses, first cluster reference images using the clustering technique, then input them into the enhanced deep network. The influences of various 'k' values on corn diagnostic techniques are investigated in this research. The trial findings show that the approach has the most significant identification impact on observations with the analytical prediction of corn disease, rust, and grey spot disease. Here, VGG-16 and ResNet18 likewise produce the best diagnostic findings, with an average diagnostic accuracy, respectively. The technique presented in this study has a diagnostic performance of 95% for the three corn diseases. It has a more substantial diagnostic impact than another four techniques and can be used to safeguard crops in the agricultural area. The simulation is done in the MATLAB 2020a environment, and various performance metrics like accuracy, precision, F1-score, recall and some other statistical measures are evaluated and compared with existing approaches. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Deep Learning's Impact on Advancing Cybersecurity in the Field of computer science 1

Deep Learning's Impact on Advancing Cybersecurity in the Fie...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Poornima, D. Sheela, A. C. Santha Ahamed, B. Shamreen Kathambari, P. Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350359756

The pervasive proliferation of digital technologies and interconnected systems has heightened the necessity for comprehensive cybersecurity measures in computer technological know-how. While deep gaining knowledge of (DL) has turn out to be a effective tool for bolstering security, its effectiveness is being examined via malicious hacking. Cybersecurity has end up an trouble of essential importance inside the cutting-edge virtual world. By making it feasible to become aware of and respond to threats in actual time, Deep Learning is a important issue of progressed security. Adversarial assaults, interpretability of models, and a lack of categorized statistics are all obstacles that want to be studied further with the intention to support DL-based totally security solutions. The protection and reliability of DL in our on-line world relies upon on being able to triumph over those boundaries. The present studies presents a unique method for strengthening DL-based totally cybersecurity, known as name dynamic adverse resilience for deep learning-based totally cybersecurity (DARDL-C). DARDL-C gives a dynamic and adaptable framework to counter antagonistic assaults by using combining adaptive neural community architectures with ensemble learning, real-time threat tracking, risk intelligence integration, explainable AI (XAI) for version interpretability, and reinforcement getting to know for adaptive defense techniques. The cause of this generation is to make DL fashions more secure and proof against the constantly transferring nature of online threats. The importance of simulation evaluation in determining DARDL-C's effectiveness in practical settings with out compromising genuine safety is important. Professionals and researchers can compare the efficacy and versatility of DARDL-C with the aid of simulating realistic threats in managed contexts. This gives precious insights into the machine's strengths and regions for improvement. © 2023 IEEE.

关键词： Cybersecurity

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：