检索结果-内蒙古大学图书馆

A hybrid blockchain and AI-based approach for attack protection to secure internet of medical things networks

Alexandria engineering Journal 2025年 128卷 223-230页

作者： Hadeel Alsolai Fahd N. Al-Wesabi Ali M. Al-Sharafi Asma Alshuhail Abdulbasit A. Darem Bandar M. Alghamdi Fouad Shoie Alallah Abdulrahman Alzahrani Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information Technology University of Bisha Bisha 67714 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Department of Computer Science and Engineering College of Computer Science and Engineering University of Hafr Al Batin Saudi Arabia

The Internet of Medical Things (IoMT) has revolutionized healthcare by enabling real-time monitoring, remote diagnosis, and seamless data exchange among medical devices and providers. However, the interconnected and distributed nature of IoMT systems exposes them to significant cybersecurity threats, including data breaches and unauthorized access. This study aims to develop a secure and scalable framework to safeguard IoMT environments using blockchain technology, federated learning, and dynamic consensus algorithms. The proposed approach integrates artificial intelligence to detect threats and employs federated learning to maintain patient privacy while training models collaboratively. Experimental evaluation of the framework shows improved data security, reduced response times, and enhanced system trustworthiness. The results suggest that the integration of blockchain and AI-driven mechanisms offers a robust solution to IoMT cybersecurity challenges, paving the way for more reliable and efficient healthcare systems.

关键词： Internet of medical things (IoMT) Blockchain security Federated learning AI-driven anomaly detection Cyber threat mitigation

来源：评论

学校读者我要写书评

暂无评论

A Design of Hybrid Model and Bayesian Neural Networks for Smart Grid Stability Prediction 1

A Design of Hybrid Model and Bayesian Neural Networks for Sm...

引用

1st IEEE International Conference on Smart and Sustainable Developments in Electrical engineering, SSDEE 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Salotagi, Shreekant Challagundla, Yagnesh Mungara, Sudeep Sriramkumar, R. Dayananda Sagar University AI & ML Bangalore India Stevens Institute of Technology Department of Data Science HobokenNJ07030 United States Dayananda Sagar University Computer Science & Engineering Bagalore India Herbert Wertheim College of Engineering University of Florida Department of Computer Science GainesvilleFL32611 United States Stevens Institute of Technology Masters in Information Systems HobokenNJ07030 United States

ISBN: (纸本)9798331542108

The latest evolution in power systems, is 'smart grids'that offers real time monitoring, control features as well as effective management of renewable energy sources. Nonetheless, with the increase in the system complexity, the chances for insta- bility also increase and thus it is crucial to forecast the stability accurately for the safety of the grid. Weather it is in terms of Gradient Boosting Tree Algorithm or any other traditional algorithm, these machine learning models are successful in achieving the objectives of the task but they lack a forthcoming metric to assist in high stake situations, uncertainty quantification. The paper is devoted to the analysis of the reliability of smart grid systems based on Bayesian Neural Networks (BNN) taking into account both the reliability of predictive modeling and forecasting uncertainty. The smart grid stability augmented dataset was used to benchmark the efficacy of using BNNs or BNNs combined hybrid models, one with XGBoost, for feature extraction and the other with LightGBM. The present study shows that the BNN used with the above mentioned smart grid system achieved an accuracy of 92% with precision of 0.89, recall of 0.91 and F1 of 0.90. These metrics are appending with the help of the additional features of BNN where they are capable of addressing the key questions around uncertainty and thus the metrics confirming the predictions are quite strong in terms of real-time grid stability evaluation. This article encapsulates a detailed study of BNN architecture, the role of uncertainty in machine learning models and the natural application of such models in the design of dependable and fault-tolerant smart grids. © 2025 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Leveraging Safe and Secure AI for Predictive Maintenance of Mechanical Devices Using Incremental Learning and Drift Detection

引用

Computers, Materials and Continua 2025年第3期83卷 4979-4998页

作者： Prashanth B. S Manoj Kumar M. V. Nasser Almuraqab Puneetha B. H Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Visvesvaraya Technological University Belagavi 590018 India Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bangalore 560064 India Dubai Business School University of Dubai Academic City Dubai P.O. Box 14143 United Arab Emirates Department of Computer Science and Business Systems Bapuji Institute of Engineering and Technology Davangere 577004 India

Ever since the research in machine learning gained traction in recent years, it has been employed to address challenges in a wide variety of domains, including mechanical devices. Most of the machine learning models are built on the assumption of a static learning environment, but in practical situations, the data generated by the process is dynamic. This evolution of the data is termed concept drift. This research paper presents an approach for predicting mechanical failure in real-time using incremental learning based on the statistically calculated parameters of mechanical equipment. The method proposed here is applicable to all mechanical devices that are susceptible to failure or operational degradation. The proposed method in this paper is equipped with the capacity to detect the drift in data generation and adaptation. The proposed approach evaluates the machine learning and deep learning models for their efficacy in handling the errors related to industrial machines due to their dynamic nature. It is observed that, in the settings without concept drift in the data, methods like SVM and Random Forest performed better compared to deep neural networks. However, this resulted in poor sensitivity for the smallest drift in the machine data reported as a drift. In this perspective, DNN generated the stable drift detection method; it reported an accuracy of 84 % and an AUC of 0.87 while detecting only a single drift point, indicating the stability to perform better in detecting and adapting to new data in the drifting environments under industrial measurement settings.

关键词： Incremental learning drift detection real-time failure prediction deep neural network proactive machine health monitoring

来源：评论

学校读者我要写书评

暂无评论

The influence of food bloggers toward consumer’s attitude in restaurant selection: a multi-objective metaheuristic approach

引用

Soft Computing 2025年 1-27页

作者： Tunga, Harinandan Pal, Surjendu Kar, Samarjit Giri, Debasis Bausys, Romualdas Department of Computer Science and Engineering RCC Institute of Information Technology Kolkata India Department of Mathematics National Institute of Technology Durgapur India Department of Information Technology Maulana Abul Kalamazad University of Technology Kolkata India Department of Graphical Systems Vilnius Gediminas Technical University Vilnius Lithuania

Restaurant selection by a consumer is a challenging task. The main problem is the proper optimization of ratings by food bloggers and the cost of food in the restaurant. In this paper, we propose an approach for a restaurant recommendation system that uses food blogger ratings and the cost of food items in the restaurant. The aim is to maximize the restaurant rating with minimization of overall cost. For this, we construct a multi-objective optimization problem to get restaurant recommendations that are appropriate for the customer's budget and desired rating. Three evolutionary optimization algorithms, namely Nondominated Sorting Genetic Algorithm II (NSGA II), Strength Pareto Evolutionary Algorithm 2 (SPEA 2), and Indicator-Based Evolution Algorithm (IBEA) have been used to identify approximated Pareto solutions for our proposed model. The effectiveness of the three evolutionary algorithms under consideration is given and evaluated against several performance indicators. Using Zomato restaurant data, we compare the results in terms of convergence and diversity, which confirms our suggestion for standardization. The suggested work contributes to an analytical approach based on evolutionary algorithm solutions to create a multi-objective restaurant recommendation system, which goes beyond the scope of previous works. We also present a comparative result analysis with the existing Zomato rating and proposed approach using statistical tools. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Multi-objective evolutionary algorithms Pareto front error Restaurant rating Restaurant recommendation

来源：评论

学校读者我要写书评

暂无评论

label-Free organelle image prediction using deep learning and large-scale hyperspectral stimulated Raman imaging

Label-Free organelle image prediction using deep learning an...

引用

Advanced Chemical Microscopy for Life science and Translational Medicine 2025

作者： Ma, Yang Mizuguchi, Takaha Spratt, Spencer John Ozeki, Yasuyuki Department of Electrical Engineering and Information Systems The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Research Center for Advanced Science and Technology The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo153-8904 Japan

ISBN: (纸本)9781510684126

Stimulated Raman scattering (SRS) microscopy is regarded as a powerful technique of vibrational spectroscopic imaging. Nevertheless, it is still challenging to discriminate various organelles only with spectroscopic signatures. Recently, a deep learning model was employed to predict molecular-specific fluorescence images from SRS images, paving the way for label-free organelle imaging. Here we demonstrate fluorescence prediction with an SRS/fluorescence image dataset with a larger data size (∼300 image pairs) and a larger number of hyperspectral points compared to the previous report. Taking advantage of the larger dataset, we realize accurate fluorescence prediction. © 2025 SPIE.

关键词： Fluorescence imaging

来源：评论

学校读者我要写书评

暂无评论

Current Trends on Limited View CT Reconstruction Techniques

Current Trends on Limited View CT Reconstruction Techniques

引用

International Conference on Electronics, Materials engineering and Nano-technology (IEMENTech)

作者： Sudipta Talukder Anamika Singh Soumalya Bose Anindya Sen Electronics and Communication Engineering Heritage Institute of Technology Kolkata India Chair of Electronic Systems and Sensors Institute of Electrical Engineering and Information Science Brandenburg University of Technology Cottbus-Senftenberg

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

Image reconstruction is at the core of improving Computed Tomography (CT), enabling high-quality imaging while addressing challenges like noise, limited data, and radiation exposure. Recent innovations have introduced adaptive algorithms that enhance reconstruction efficiency, clarity, and safety, making CT more effective in diverse applications. The Parameter-extended Expectation-Maximization (PXEM) algorithm dynamically adjusts reconstruction parameters during iterations, demonstrating superior noise resilience and faster convergence, especially in high-noise environments. Similarly, the Simultaneous Algebraic Reconstruction Technique with Guided Filtering (SART-G) uses prior guidance images to retain structural details and outperform traditional methods, such as Filtered Back Projection (FBP) and standard SART, in low-exposure and limited-projection scenarios. Muon Computed Tomography (MCT) presents a novel, non-invasive approach that utilizes cosmic-ray muons for imaging dense and complex materials. MCT has significant potential in nuclear safety and industrial applications where conventional CT faces limitations. Meanwhile, the Simultaneous Algebraic Reconstruction Technique with Total Variation (SART-TV) mitigates noise accumulation in sparse-angle imaging by applying total variation regularization, ensuring enhanced image quality while minimizing radiation exposure. These advancements illustrate the transformative impact of modern image reconstruction algorithms on CT technology. By integrating adaptive noise reduction, efficient data utilization, and safety-oriented approaches, these methods pave the way for more precise and versatile CT applications in clinical, research, and industrial settings. This article presents an overview of some of the CT reconstruction iterative techniques that are commonly used in CT reconstruction from limited views.

关键词： Technological innovation Mesons Computed tomography Noise Noise reduction Minimization Real-time systems Safety Image reconstruction Resilience

来源：评论

学校读者我要写书评

暂无评论

Development of an Anomaly Detection System for Rugby Match Based on Majority Rule Using Deep Neural Networks

引用

IEEJ Transactions on Industry Applications 2025年第4期145卷 238-246页

作者： Tamaki, Kanta Uza, Hirotomo Kudoh, Reo Hirose, Kiyoshi Nojiri, Shuko Nakajima, Kenji Kawasaki, Takayuki Ishijima, Muneaki Nagayama, Itaru Department of Information Engineering University of the Ryukyus 1 Senbaru Okinawa Nishihara903-0213 Japan Graduate School of Science and Engineering University of the Ryukyus 1 Senbaru Okinawa Nishihara903-0213 Japan Department of Production Systems Engineering and Science Komatsu University 4-1-3 Ishikawa Komatsu923-8511 Japan Medical Technology Innovation Center Juntendo University 2-1-1 Hongo Bunkyo-ku Tokyo113-8421 Japan National Institute of Technology Sasebo College 1-1 Okishinmachi Nagasaki Sasebo857-1193 Japan Juntendo University School of Medicine 3-1-3 Hongo Bunkyo-ku Tokyo113-8431 Japan

This paper describes the development of an anomaly detection system for players in a rugby match to provide appropriate aid and avoiding severe injury. In the developed system, deep neural networks with fine tuning and its combination of different types of construction are key techniques for anomaly detection in rugby match footage. Certain appearance-based characteristics are captured from movie streams, and the system uses deep neural networks to automatically classify concerned scenes, especially, lying down scenes. The proposed system performs very well by recognizing many types of appearances of players within occlusion from a free viewpoint. Experimental results show that the system can effectively detect concerned players with high accuracy. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Open-set Mixed Domain Adaptation via Visual-Linguistic Focal Evolving

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Liu, Bangzhen Xu, Yangyang Xu, Cheng Xu, Xuemiao He, Shengfeng South China University of Technology Guangzhou China School of Intelligence Science and Engineering China Guangdong Engineering Center for Large Model and GenAI Technology China Singapore Management University School of Computing and Information Systems Singapore

We introduce a new task, Open-set Mixed Domain Adaptation (OSMDA), which considers the potential mixture of multiple distributions in the target domains, thereby better simulating real-world scenarios. To tackle the semantic ambiguity arising from multiple domains, our key idea is that the linguistic representation can serve as a universal descriptor for samples of the same category across various domains. We thus propose a more practical framework for cross-domain recognition via visual-linguistic guidance. On the other hand, the presence of multiple domains also poses a new challenge in classifying both known and unknown categories. To combat this issue, we further introduce a visual-linguistic focal evolving approach to gradually enhance the classification ability of a known/unknown binary classifier from two aspects. Specifically, we start with identifying highly confident focal samples to expand the pool of known samples by incorporating those from different domains. Then, we amplify the feature discrepancy between known and unknown samples through dynamic entropy evolving via an adaptive entropies min/max game, enabling us to accurately identify possible unknown samples in a gradual manner. Extensive experiments demonstrate our method’s superiority against the state-of-the-arts in both open-set and open-set mixed domain adaptation. © 2025 IEEE. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

I Want to Break Free: Enabling User-Applied Active Locomotion in In-Car VR through Contextual Cues 25

I Want to Break Free: Enabling User-Applied Active Locomotio...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing systems

作者： Bocheon Gim Seokhyun Hwang Seongjun Kang Gwangbin Kim Dohyeon Yeo SeungJun Kim Human-Centered Intelligent Systems Lab Gwangju Institute of Science and Technology Gwangju Republic of Korea Information School University of Washington Seattle Washington USA and Human-Centered Intelligent Systems Lab Gwangju Institute of Science and Technology Gwangju Republic of Korea

来源：评论

学校读者我要写书评

暂无评论

CASCAIN: Cascaded Attention Infused Networks for Named Entity Recognition in Code-Mixed Setting 6th

CASCAIN: Cascaded Attention Infused Networks for Named Entit...

引用

6th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2024

作者： Kaoshik, Jay Vyas, Pranav Tripathy, B.K. Swarnalatha, P. Nagaraja, G. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9783031813351

Named Entity Recognition (NER), sometimes also referred to as Entity Extraction has been an integral part of Natural Language Understanding systems. To date, there have been continuous myriad efforts in linguistics and sequential modelling which have led to the development of reliable and highly efficient NER architectures. One frequent occurrence, however, is that most work done constitutes an inclination towards resource rich corpora. To bridge the grey space for real time code-mixed expressions, we present CASCAIN (Cascaded Attention Infused Network), which leverages attention for capturing sentence level context. We also experiment with multiple architectures involving varying number of recurrent units, attention types and stacking arrangements. To provide a comprehensive performance benchmark, we train and test our models on an extended set generated from two popular Hinglish datasets. Our best performing architecture incorporates Stacked Bi-Directional LSTM Units, each of which are paired with Attention Mechanisms for generating representations from Context Vector. CASCAIN achieves an accuracy of 94.31% on the Validation Set. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Long short-term memory

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：