检索结果-内蒙古大学图书馆

Artificial intelligence-based smart galliformes farm management system

Journal of Umm Al-Qura University for engineering and Architecture 2025年第1期16卷 64-77页

作者： Himel, Galib Muhammad Shahriar Islam, Md. Masudul Kader, Md. Nasimul Rahman, Mustafizur School of Computing and Mathematical Sciences University of Greenwich London United Kingdom Department of Computing and Information System Daffodil International Academy Dhaka Bangladesh Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Department of Computing and Information System Daffodil International University Dhaka Bangladesh

This article introduces an Artificial Intelligent-driven system for Galliformes Farm Management, consulting, and disease control. Comprising both a web-based mobile app and a website, the system integrates physical electronic devices to regulate intelligent automation. The application employs Artificial Neural Network and computer vision for the identification of breeds and the recognition of diseases in galliform birds, utilizing TensorFlow for real-time detection. It notifies local farmers about bird flu infections with an integrated infection map using Google's map Application Programming Interface. The system also controls farm temperature and humidity through microcontrollers and sensors, offering consulting features such as cost calculation, food chart generation, and drug suggestions. © The Author(s) 2025.

关键词： Artificial intelligence Breed identification Disease classification Image classification Poultry farm automation Smart farm management

来源：评论

学校读者我要写书评

暂无评论

Minecrafter: A secure and decentralized consensus protocol for blockchain-enabled vaccine supply chain

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-26页

作者： Maloth, Sreenu Hada, Nishant Singh Jatoth, Chandrashekar Gupta, Nitin Fiore, Ugo Sharma, Pradip Kumar Department of Computer Science and Engineering National Institute of Technology Hamirpur Himachal Pradesh India CVR College of Engineering Ibrahimpatnam Telangana Ranga Reddy India National Institute of Technology Raipur Chattisgarh India Department of Computer Science University of Salerno SA Fisciano Italy Department of Computing Science University of Aberdeen Scotland United Kingdom

The vaccine supply chain (VSC) is crucial for the response to pandemics, ensuring that vaccines reach those in need. However, it faces security risks, network congestion, and inefficiencies. Existing blockchain-based solutions struggle with high energy consumption, centralization, and suboptimal validator selection. To address these challenges, we propose Minecrafter, a secure, decentralized consensus protocol. It selects validators dynamically using game theory, machine learning, and randomness. DBSCAN clustering is utilized for its ability to detect anomalies and adapt to varying network conditions without requiring a predefined number of clusters, reducing centralization risks. Unlike most proof-based protocols, Minecrafter operates with low energy and computational costs. The proposed work demonstrates that Minecrafter outperforms traditional consensus protocols in terms of security, transaction rate, and block latency through experiments. This new protocol is particularly useful for VSCs because it strikes an appropriate balance between speed, safety, and expandability. The results show that the proposed work can improve the reliability and strength of vaccine distribution networks while reducing the risks associated with traditional blockchain consensus methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Blockchain Consensus protocol DBSCAN Game theory Machine learning Vaccine supply chain

来源：评论

学校读者我要写书评

暂无评论

Towards Collaborative Intelligence for Meta-Computing-Driven IIoT Based on Vertical Federated Learning With Fast Convergence

引用

IEEE Internet of Things Journal 2025年

作者： Li, Youqi Liu, Shuangji Meng, Yanchen Qi, Shenyi Qu, Zhe Li, Fan Wang, Yu Beijing Institute of Technology School of Computer Science and Technology Beijing100081 China Central South University School of Computer Science and Engineering Changsha410083 China Temple University Department of Computer and Information Sciences PhiladelphiaPA19122 United States

Industrial Internet of Things (IIoT) is an emerging technology that digitizes industrial production and realizes Industry 4.0. However, it shows that IIoT is difficult to enable sophisticated downstream applications without eliciting all devices to achieve collaborative intelligence. Existing works on IIoT either require the consolidation of various IIoT devices' data into a single centralized server which has potential privacy breach, or coordinate devices to learn a global model in privacy-preserving federated learning (FL) but assume data across devices has the sample feature space and neglect the heterogeneity of IIoT devices. In this paper, we propose Meta-computing-driven vertical FL algorithms to achieve collaborative intelligence in IIoT where heterogeneous devices have imperfect data with incomplete features. Specifically, we first provide the modeling of N devices' VFL to collectively train the sub-models and the common model. We present the computing graph to clearly indicate the gradient evaluation. To enable a fast convergence performance, we design a variance-reduced gradient estimator that can be seamlessly integrated into the basic VFL. Finally, we evaluate our proposed VFL by conducting experiments on the MNIST dataset regarding image recognition and the DAWM dataset for detecting anomalies in wafer manufacturing. The experimental results show that our VFL for IIoT is both effective and efficient. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Graph-based design of irregular metamaterials

引用

International Journal of Mechanical sciences 2025年 295卷

作者： Karimi Mahabadi, Rayehe Chen, Zhi Ogren, Alexander C. Zhang, Han Daraio, Chiara Rudin, Cynthia Brinson, L. Catherine Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States Departments of Computer Science and Electrical and Computer Engineering Duke University DurhamNC United States Division of Engineering and Applied Science California Institute of Technology PasadenaCA United States

In the field of metamaterial research, irregular structures offer a novel and less conventional approach compared to traditional periodic designs. Designing irregular metamaterials is challenging when it comes to ensuring interconnectivity, which is essential for manufacturability. This study introduces an innovative framework for generating irregular metamaterials using graph algorithms, ensuring connectivity and adaptability across various base shapes, including cylinders, triangles, pyramids, and cubes. By employing graph algorithms, our framework enhances the intuitiveness and efficiency of design representation and manipulation, streamlining the design process. The framework generates families of designs that exhibit a wide range of property magnitudes that can be adjusted intuitively by modifying the input parameters. The rapid design process allows many designs to be generated, offering the user a multitude of solutions around the target property range. The designs can be effectively implemented in various fields and subjected to diverse analytical studies, including static, dynamic, and eigenfrequency assessments. We illustrate computational results for two key properties (stiffness and acoustic impedance), showcasing the method's effectiveness through examples ranging from rod-based to cube-based designs. The framework not only advances metamaterial research but also creates new opportunities for innovation in fields requiring customized material properties. © 2025

关键词： Acoustic impedance

来源：评论

学校读者我要写书评

暂无评论

Offline Handwritten Signature Identification and Verification Using LBP Features 3rd

Offline Handwritten Signature Identification and Verificatio...

引用

3rd International Conference on Machine Intelligence and Smart Systems, MISS 2023

作者： Gupta, Chitvan Singh, Bhawna Bharti, Vandana Chauhan, Karishma Tiwari, Shivam Department of Computer Science and Engineering Noida Institute of Engineering and Technology Gr. Noida India CSE Department G.L.Bajaj Institute of Technology and Management Greater Noida India Department of Computer Science KIET Group of Institutions Delhi NCR Ghaziabad India Department of Computer Science and Engineering Sharda University Greater Noida India

ISBN: (纸本)9783031691140

Biometrics is the science and technology of automatically identifying people by their unique physical and behavioural traits. More and more people are being verified by biometric methods. In order to increase signature verification’s classification accuracy, researchers are always looking into new feature representations. As a robust feature extraction method, local binary pattern (LBP) has been proposed to capture the texture. LBP is a texture measure that works in any colour space, as it is based on a neighbourhood-level definition of texture. The LBP operator converts a 3 × 3 area’s grayscale value to binary by using it as a threshold for a binary code. You may describe the texture using the histogram of these labels. To generate a binary code for each pixel in a greyscale image, the LBP approach begins with a basic processing step. Intensity differences between surrounding pixels and the current pixel are encoded by this code. Each subject is given a set of 100 signatures, of which 10 are authentic and 3 are forgeries, to use as training data. The testing process involves determining whether or not a submitted signature is a legitimate copy of the subject’s original. In order to extract features, the LBP operator is used, which is a gray-scale invariant texture measure based on a generic definition of texture in the context of a particular neighbourhood. By thresholding a 33 area by its central grey value, the LBP operator generates a binary code. A texture description is then derived from the histograms of these labels. Tests are conducted on signature photos from the local dataset and the MCYT database. Signature verification systems have used KNN and SVM classifiers. KNN and SVM classifiers’ overall recognition accuracy and FAR are provided. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

QoE-Aware Volumetric Video Caching and Rendering for Mobile Extended Reality Services

引用

IEEE Internet of Things Journal 2025年

作者： Pei, Yingying Li, Mushu Huang, Xinyu Shen, Xuemin University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada Lehigh University Department of Computer Science and Engineering BethlehemPA18015 United States

In this paper, we propose a novel volumetric video caching and rendering approach for an edge-assisted extended reality (XR) system to enhance user quality of experience (QoE). Particularly, user QoE consists of visual quality and quality variation. Different quality of volumetric videos are required to be cached, rendered, and delivered to XR devices for different viewing distances within a time latency. Given the limited caching, computing, and communication resources on the edge server, we formulate a long-term user QoE maximization problem to jointly optimize video caching and rendering by considering user locations and viewing distances. To solve this problem, we first design an online optimization algorithm in which caching decisions are obtained using a regularization technique. We then develop a low-complexity binary search algorithm to determine optimal rendering quality. Extensive simulations are conducted to demonstrate that our proposed approach outperforms benchmark schemes by an average 46% improvement in terms of long-term user QoE. © 2014 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

QoE-Aware Offloading and Resource Allocation for MEC-Empowered AIGC Services

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wu, Jiaqi Zhuang, Xinyi Tang, Ming Gao, Lin Harbin Institute of Technology School of Electronics and Information Engineering Shenzhen China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen China

Artificial Intelligence-Generated Content (AIGC) has emerged as a transformative paradigm, enabling the autonomous creation of diverse content. By offloading model inference tasks to the network edge that is closer to mobile users (MUs), Mobile Edge Computing (MEC) has the potential to significantly enhance the performance of AIGC services. In practice, however, it is challenging to optimally manage MEC-empowered AIGC services, due to the lack of well-defined AIGC-specific metrics, as well as the dynamic workload and computation-intensive nature of AIGC services. In this paper, we first define a novel AIGC metric based on extensive real data experiments, and then study the joint task offloading and resource allocation problem in a generic MEC-empowered AIGC network, where MUs can offload model inference tasks to local or remote Base Stations (BSs), aiming at maximizing their Quality of Experience (QoE). The problem is challenging due to the fast and randomly changing of environments, as well as the necessity for real-time, asynchronous decision-making. To tackle these challenges, we propose two deep reinforcement learning algorithms based on the Proximal Policy Optimization (PPO) framework: Single-Layer PPO (SL-PPO) and Multi-Layer PPO (ML-PPO), designed for slow-changing and fast-changing environments, respectively. In the SL-PPO algorithm, both task offloading and resource allocation decisions are made simultaneously when tasks arrive. In the ML-PPO algorithm, the task offloading decision is made immediately when tasks arrive, while the resource allocation decision is deferred until tasks are scheduled for processing or transmission in the corresponding queues. Simulation results show that (i) both algorithms outperform existing methods in the literature, and can increase the average utility by up to 47% and 48.8%;(ii) both algorithms can effectively manage the trade-off between latency and energy consumption. © 2002-2012 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A privacy-enhanced framework for collaborative Big Data analysis in healthcare using adaptive federated learning aggregation

引用

Journal of Big Data 2025年第1期12卷 1-56页

作者： Haripriya, Rahul Khare, Nilay Pandey, Manish Biswas, Sreemoyee Department of Computer Science and Engineering Maulana Azad National Institute of Technology M.P. Bhopal462003 India

The exponential growth of Big Data in healthcare, particularly in AI-driven medical diagnostics, has raised critical concerns about data privacy in medical image classification. With over 30% of healthcare organizations worldwide experiencing data breaches in the past year, the demand for secure, privacy-preserving solutions is more urgent than ever. This study explores a federated learning approach combined with transfer learning to enhance privacy in medical image classification using ResNet and VGG16 architectures. Pre-trained on ImageNet and fine tuned on three specialized medical datasets TB chest X-rays, brain tumor MRI scans, and diabetic retinopathy images these models were deployed in a simulated multi-center healthcare environment. A major contribution of this work is the development of an adaptive aggregation methodology, which dynamically selects between Federated Averaging (FedAvg) and Federated Stochastic Gradient Descent (FedSGD) based on real-time data divergence observed across participating clients. Unlike conventional static aggregation methods, which uniformly apply the same update rule regardless of data heterogeneity, the proposed adaptive approach monitors gradients and data distributions at each communication round and selects the most suitable aggregation method dynamically. This adaptive strategy not only improves convergence but also optimizes resource utilization, making it suitable for multi-center healthcare networks where data heterogeneity is prevalent. The novelty of the proposed adaptive aggregation lies in its ability to maintain robust performance while minimizing computational costs, making it feasible for large-scale healthcare AI networks, such as hospital federated learning systems. Comparative analysis with baseline FL models, including FedAvg and FedSGD, shows that the adaptive aggregation method achieves comparable accuracy (up to 96.3%) while significantly reducing execution time by approximately 20% and maintaining a comp

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Emergency Vehicles in Traffic and Assign Traffic Free Path Using Deep Learning 4

Detection of Emergency Vehicles in Traffic and Assign Traffi...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Vikruthi, Sriharsha Singasani, Tejesh Reddy Ram Pavan Kumar, V.T.M. Nagendrudu, P.V.V.S.D. Raghavendra, Ch Sahith, R. B v Raju Institute of Technology Dept of Cse Telangana Medak Narsapur502313 India University of Cumberlands LouisvilleKY United States Kakaraparti Bhavanarayana College Dept of Computer Science Andhrapradesh Vijayawada India Aditya Univeristy Department of Artificial Intelligence and Machine Learning Suramplaem India Andhra Pradesh Guntur India Cvr College of Engineering Dept of Computer Science and Engineering Telangana Hyderabad501510 India

ISBN: (纸本)9798331523923

Too much of Traffic jams are in a highly populated country. Sometimes emergency vehicles such as fire-fighter and ambulance get stuck in traffic, putting lives at threat in many cases. Priority should be given to special vehicles and their way should be cleared. However, traffic police find it difficult or sometimes impossible to handle with it. Emergency vehicles have visual and audio warning devices help them to overtake traffic by demanding as little space as possible from other vehicles. Many death happen due to delay in doctors, ambulance and fire engine vehicles while reaching their destinations. The traditional systems didn't provide path free route accurately. Therefore, by using detection of emergency vehicles in traffic and assign traffic free path using deep learning system, emergency vehicles can get free path or fast route by observing the traffic cameras. So, those emergency vehicles can reach the location on time by using RNN system. Therefore, the main objective is to improve this system for better results interms of accuracy, detection rate and precision. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Near-Far Field Boundary Analysis and Transmit Covariance Optimization for Dual-Polarized XL-MIMO Communications

Near-Far Field Boundary Analysis and Transmit Covariance Opt...

引用

IEEE Conference on Wireless Communications and Networking

作者： Shuhao Zeng Boya Di Hongliang Zhang Zhu Han H. Vincent Poor School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen China Department of Electrical and Computer Engineering Princeton University USA School of Electronics Peking University Beijing China Electrical and Computer Engineering Department University of Houston USA Department of Computer Science and Engineering Kyung Hee University South Korea

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Extremely large-scale multiple-input multiple-output (XL-MIMO) is expected to play an important role in future sixth generation (6G) networks. Most existing works in this area focus on single-polarized XL-MIMO, where transceivers transmit and receive signals in only one polarization direction, leading to degraded data rates. To improve multiplexing performance, in this paper, we investigate downlink XL-MIMO networks with dual-polarized antennas. However, unlike conventional dual-polarized massive MIMO, the cross-polarization discrimination (XPD) of channels vary across base station antennas in dual-polarized XL-MIMO due to the enlarged antenna aperture, leading to following two challenges. First, conventional near-far field boundary is insufficient as it only accounts for phase differences across array elements while irrespective of XPD differences. Second, existing transmit covariance optimization methods developed for dual-polarized massive MIMO cannot be directly utilized, since they are developed based on uniform XPD and pathloss assumptions. To address these challenges, we model the variations of XPD across antennas, based on which a non-uniform XPD distance is introduced to complement existing near-far field boundary. Based on the new distance criterion, we propose an efficient scheme for optimizing the transmit covariance, which considers the non-uniform XPD and pathloss. Numerical results validate our analysis and demonstrate the effectiveness of the proposed algorithm.

关键词： 6G mobile communication Phased arrays Multiplexing Transmitting antennas Optimization methods Massive MIMO Downlink Aperture antennas Transceivers Numerical models

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：