检索结果-内蒙古大学图书馆

Refractive Index Biosensor–Based Detection of Mycobacterium Tuberculosis Using Sea Lion Political Optimizer and Deep Learning

引用

Plasmonics 2025年 1-19页

作者： Ragavan, V. K. Senthil Nithya, N.S. Vengala, Anantharamaiah Subramanian, Balambigai Ambhika, C. Sri Shanmugha College of Engineering and Technology Tamil Nadu Sankari Salem (D.T.) 637 304 India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of C S E K L E F Andhra Pradesh Vaddeswaram Guntur 522502 India Dept of ECE Karpagam College of Engineering Tamil Nadu Coimbatore India Department of AIML R.M.D Engineering College RSM Nagar Tamil Nadu Kavarapetai India

Mycobacterium tuberculosis (MTB) detection is a major global health concern, requiring accurate and reliable diagnostic tools. According to the World Health Organization (WHO), the global burden of TB is staggering, with approximately 10 million new cases reported annually, leading to a devastating 1.5 million fatalities worldwide every year. The timely detection and treatment of TB are critical components in the fight against this disease, as they play a vital role in preventing its transmission, minimizing the risk of complications and deaths, and enhancing the overall quality of life for affected individuals. Hence, this study presents a novel Sea Lion Political Optimizer_Deep Maxout Network (SLnPO_DMN) for detecting MTB, leveraging a robust processing pipeline to achieve exceptional accuracy. The proposed pipeline involves a series of meticulous steps, including data pre-processing by Min–Max normalization to scale the data to a common range. To enhance model generalizability, data augmentation is carried out by Bootstrap, generating additional training samples by resampling the original data with replacement. The augmented data is then fed into a DMN, optimized by the SLnPO, a hybrid algorithm combining the strengths of sea lion optimization (SLnO) and political optimizer (PO). The SLnPO_DMN model is trained to identify and learn intricate patterns within the data, ultimately attaining optimal performance and demonstrating exceptional capability in detecting Mycobacterium tuberculosis with high accuracy and reliability. The SLnPO_DMN is evaluated using a comprehensive set of metrics, including accuracy, sensitivity, and specificity. The results demonstrate the effectiveness of the SLnPO_DMN model achieving an accuracy (99.12%), sensitivity of (98.74%), and specificity of (98%). © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep maxout network Min–Max normalization Mycobacterium tuberculosis Political optimizer Sea lion optimization

来源：评论

学校读者我要写书评

暂无评论

Adaptive Control for Shunt Active Power Filter under Stochastic Solar Photovoltaics Behavior

引用

IEEE Journal of Emerging and Selected Topics in Power Electronics 2025年

作者： Prakash, Surya Alkhatib, Mohamed Sindi, Hatem F. Alghamdi, Sultan Behera, Ranjan Kumar Muduli, Utkal Ranjan Nit Jamshedpur Dept. of Electrical Engg Jharkhand Jamshedpur India Uae University Al Ain Dept. of Electrical and Communication Engg Coe Abu Dhabi15551 United Arab Emirates King Abdulaziz University Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering Jeddah21589 Saudi Arabia Indian Institute of Technology Patna Dept. of Electrical Engineering Bihta801103 India Khalifa University Apec Dept. of Electrical Engineering and Computer Science Abu Dhabi127788 United Arab Emirates

The paper discusses the challenges in controlling a two-stage photovoltaic (PV)-based shunt active power filter (SAPF) under distorted grid conditions and stochastic PV system behavior. To address this, the paper proposes an adaptive proportional integral (API) regulator to regulate the DC-link voltage, which adapts its parameters based on the DC-link error voltage to provide low bandwidth for disturbance rejection and high bandwidth for dynamic performance enhancement. The paper also proposes an estimation method for the reference current using the sliding discrete Fourier transform and the instantaneous symmetrical component theory, which is suitable for non-ideal grid or load conditions. The accuracy of the proposed reference current estimation method is analyzed using time- and frequency-domain analysis. The performance of the PV-SAPF system with the proposed control algorithms is illustrated through simulation and real-time hardware validation under various grid conditions. Despite distorted grid conditions, the total harmonic distortion of the grid current is substantially within IEEE Std 519-2014. The proposed API regulator and reference current estimation method show promising results in improving the performance of the PV-SAPF system in the presence of internal and external disturbances. © 2013 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Co-Design of Network Topology and Qubit Allocation for Distributed Quantum Computing

Co-Design of Network Topology and Qubit Allocation for Distr...

引用

Quantum Communications, Networking, and Computing (QCNC), International Conference on

作者： Jiyao Liu Lei Fan Yuanxiong Guo Zhu Han Yu Wang Department of Computer and Information Sciences Temple University Philadelphia USA Dept. of Engineering Technology University of Houston Houston USA Dept. of Electrical and Computer Engineering University of Houston Houston USA Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio USA

ISBN: (数字)9798331531591

ISBN: (纸本)9798331531607

Distributed Quantum Computing (DQC) enables the execution of quantum circuits across multiple interconnected quantum processing units (QPUs), but requiring efficient qubit allocation and network topology design to optimize computational performance. Proper qubit allocation minimizes entanglement costs across QPUs, balances computational workload, and ensures efficient execution of quantum computing tasks. Meanwhile, network topology plays a crucial role in reducing entanglement routing complexity and communication overhead for remote quantum gate operations. In this paper, we propose a joint optimization framework for network topology design and qubit allocation in DQC to minimize the communication overhead. We formulate the problem as a tractable integer nonlinear programming model that explicitly incorporates entanglement routing, thereby ensuring a more tractable optimization process. To further improve computational efficiency, we present a partially linearized version of the problem, making it solvable using any classical optimization solver. Extensive simulations on both random and real-world quantum circuits validate the effectiveness of our proposed approach, demonstrating its capability to handle complex quantum circuits while reducing communication costs in DQC.

关键词： Costs Network topology Computational modeling Qubit Topology Computational efficiency Resource management Quantum circuit Integrated circuit modeling Optimization

来源：评论

学校读者我要写书评

暂无评论

Multispectral Images and IoT Based Tea Plantation Monitoring: A Proposed System Architecture

Multispectral Images and IoT Based Tea Plantation Monitoring...

引用

Advanced Research in Computing (ICARC), International Conference on

作者： K. P. W. D. V. Kariyawasam P. N. Kahandagamage M. R. R. Fernando J. M. Fernandopulle Vishan Jayasinghearachchi Kapila Dissanayaka Dept. of Software Engineering Sri Lanka Institute of Information Technology (SLIIT) Sri Lanka Dept. of Information Technology Sri Lanka Institute of Information Technology (SLIIT) Sri Lanka Dept. of Computer Science Sri Lanka Institute of Information Technology (SLIIT) Sri Lanka

ISBN: (数字)9798331530983

ISBN: (纸本)9798331530990

In recent years, the Sri Lankan tea industry has fallen behind its competitors in the global tea market. This decline is caused by the challenges in productivity and resource management due to the limitations of traditional crop monitoring methods. This study presents a prototype system architecture that integrates multispectral imagery and IoT technologies to enhance plantation monitoring. The proposed system uses drones to capture high-resolution multispectral images and IoT devices to collect real-time environmental data, providing a comprehensive approach to assessing plant yield and detecting stress. Built on a hexagonal architecture, the system emphasizes modularity, reliability, and scalability by ensuring a clear separation of core functionalities from external components. This design facilitates easy adaptation to various crop types and agricultural contexts, enabling flexibility in deployment and use. This flexible framework can serve as a blueprint for improving decision-making and management practices across diverse plantation environments.

关键词： Scalability Plantations systems architecture Crops Real-time systems Internet of Things Resource management Reliability Monitoring Stress

来源：评论

学校读者我要写书评

暂无评论

AutoMediVision:A Deep Learning System for Accurate Pharmaceutical pill identification

AutoMediVision:A Deep Learning System for Accurate Pharmaceu...

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： G Rajeswarappa B. Venkata Sivaiah M. Navya Y. Lasya Shaik Mohammad Sameer V. Varun Kumar Department of CSE G Pulla Reddy Engineering College Kurnool Dept. of Data Science School of Computing Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India Dept. of Computer Science and Systems Engineering(CSSE) Sree Vidyanikethan Engineering College Tirupati India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The goal of this project is to build a high performance system that offers prediction of pill information from images, the pill name, medical use and recommended dosage by using MobileNet which is a lightweight and efficient deep learning model. This system serves as an important tool for healthcare professionals and patients as it offers a means of reducing risk because of the large number of medications out there. For this task, MobileNet was chosen for its high accuracy and good balance between computational efficiency and high accuracy, and hence can be deployed on mobile devices. Having trained the model on a wide variety of pills with class wise annotations, it generalized well for diverse pills. The output of the system is the pill name, primary medical indications and common dosage instructions that help in safer medication management by supporting healthcare providers in providing better care and patient safety.

关键词： Deep learning Accuracy Computational modeling Medical services Mobile handsets Safety Standards Research and development Biomedical imaging Pharmaceuticals

来源：评论

学校读者我要写书评

暂无评论

Laser-assisted Multidimensional Imaging Modalities for Early Detection of Tumours in Bio Tissues: An In Vitro Study

引用

Lasers in engineering 2025年第4-6期59卷 199-215页

作者： Akhtar, M. Ullah, H. Aslam, K. Siddique, M.A. Akram, A. Majid, M.A. Abdullah-Al-Wadud, M. Aleem, A. Farhan, M. Batool, Z. Biophotonics Imaging Techniques Laboratory Institute of Physics The Islamia University of Bahawalpur 63100 Pakistan Dept. of Software Engineering College of Computer and Information Sciences King Saud University Riyadh11543 Saudi Arabia School of Earth Sciences and Engineering Hohai University Nanjing China

The idea, upon which this research work depends, is the early detection of tumours in different biological soft tissues like bladder, respiratory and thigh tissues. Imaging and spectroscopic technique that were used to study healthy and cancerous tissues were white light microscopy and Fourier-transform infrared radiation (FTIR) spectroscopy. The observation and calculations collected through all these imaging techniques prove as helping tools to differentiate healthy and cancerous body tissues. Soft tissues from patients who had been diagnosed with bladder, respiratory, and thigh cancer were gathered from the Bahawalpur Victoria Hospital, Pakistan while keeping in mind the ethical research perspective. Two-dimensional (2-D) white light microscopy images showed that healthy and cancerous tissues have a different kind of shapes, sizes and structure arrangements. Normal tissues images show a regular pattern of structure arrangement, but cancerous tissues show an irregular shapes, sizes, and structures. Similarly, FTIR spectroscopy graphs represents different peaks of stretching vibrations of C-H, O-H, C-C, N-H, CH2 double and triple bonding of different biological tissues like bladder, respiratory and thigh tissues. This research work will help in the medical field for early detection of tumour which helps to diagnose the tumour and also helpful for better treatment planning in early stage. ©2025 Old City Publishing, Inc.

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Optimizing Spot Instance Reliability and Security Using Cloud-Native Data and Tools

arXiv

引用

arXiv 2025年

作者： Saqib, Muhammad Malhotra, Shubham Mehta, Dipkumar Jangid, Jagdish Yashu, Fnu Dixit, Sachin Texas Tech University Dept. of Computer Science United States Rochester Institute of Technology Dept. of Software Engineering United States C.K.Pithawalla College of Eng. and Tech India Infinera Corp United States Stony Brook University Dept. of Computer Science United States Stripe Inc United States

This paper presents "Cloudlab," a comprehensive, cloud-native laboratory designed to support network security research and training. Built on Google Cloud and adhering to GitOps methodologies, Cloudlab facilitates the creation, testing, and deployment of secure, containerized workloads using Kubernetes and serverless architectures. The lab integrates tools like Palo Alto Networks firewalls, Bridgecrew for "Security as Code," and automated GitHub workflows to establish a robust Continuous Integration/Continuous Machine Learning pipeline. By providing an adaptive and scalable environment, Cloudlab supports advanced security concepts such as role-based access control, Policy as Code, and container security. This initiative enables data scientists and engineers to explore cutting-edge practices in a dynamic cloud-native ecosystem, fostering innovation and improving operational resilience in modern IT infrastructures. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEARNING EFFICIENT POSITIONAL ENCODINGS WITH GRAPH NEURAL NETWORKS

arXiv

引用

arXiv 2025年

作者： Kanatsoulis, Charilaos I. Choi, Evelyn Jegelka, Stephanie Leskovec, Jure Ribeiro, Alejandro Dept. of Computer Science Stanford University United States School of Computation Information and Technology Technical University of Munich Computer Science & Artificial Intelligence Laboratory Massachusetts Institute of Technology United States Dept. of Electrical and Systems Engineering University of Pennsylvania United States

Positional encodings (PEs) are essential for effective graph representation learning because they provide position awareness in inherently position-agnostic transformer architectures and increase the expressive capacity of Graph Neural Networks (GNNs). However, designing powerful and efficient PEs for graphs poses significant challenges due to the absence of canonical node ordering and the scale of the graph. In this work, we identify four key properties that graph PEs should satisfy: stability, expressive power, scalability, and genericness. We find that existing eigenvector-based PE methods often fall short of jointly satisfying these criteria. To address this gap, we introduce PEARL, a novel framework of learnable PEs for graphs. Our primary insight is that message-passing GNNs function as nonlinear mappings of eigenvectors, enabling the design of GNN architectures for generating powerful and efficient PEs. A crucial challenge lies in initializing node attributes in a manner that is both expressive and permutation equivariant. We tackle this by initializing GNNs with random node inputs or standard basis vectors, thereby unlocking the expressive power of message-passing operations, while employing statistical pooling functions to maintain permutation equivariance. Our analysis demonstrates that PEARL approximates equivariant functions of eigenvectors with linear complexity, while rigorously establishing its stability and high expressive power. Experimental evaluations show that PEARL outperforms lightweight versions of eigenvector-based PEs and achieves comparable performance to full eigenvector-based PEs, but with one or two orders of magnitude lower complexity. Our code is available at https://***/ehejin/Pearl-PE. Copyright © 2025, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Evaluating Fault Tolerance and Scalability in Distributed File systems: A Case Study of GFS, HDFS, and MinIO

arXiv

引用

arXiv 2025年

作者： Malhotra, Shubham Yashu, Fnu Saqib, Muhammad Mehta, Dipkumar Jangid, Jagdish Dixit, Sachin Rochester Institute of Technology Dept. of Software Engineering United States Stony Brook University Dept. of Computer Science United States Texas Tech University Dept. of Computer Science United States C.K.Pithawalla College of Eng. and Tech India Infinera Corp United States Stripe Inc United States

Distributed File systems (DFS) are essential for managing vast datasets across multiple servers, offering benefits in scalability, fault tolerance, and data accessibility. This paper presents a comprehensive evaluation of three prominent DFSs—Google File System (GFS), Hadoop Distributed File System (HDFS), and MinIO—focusing on their fault tolerance mechanisms and scalability under varying data loads and client demands. Through detailed analysis, how these systems handle data redundancy, server failures, and client access protocols, ensuring reliability in dynamic, large-scale environments is assessed. In addition, the impact of system design on performance, particularly in distributed cloud and computing architectures is assessed. By comparing the strengths and limitations of each DFS, the paper provides practical insights for selecting the most appropriate system for different enterprise needs, from high-availability storage to big data analytics. Copyright © 2025, The Authors. All rights reserved.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

A Big Data Analytic and IoT-Based Approach for Addressing Water Scarcity in Jordan

A Big Data Analytic and IoT-Based Approach for Addressing Wa...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Abdelraouf Ishtaiwi Nuha El-Khalili May Alnashashibi Mohammad Abu Arqoub Dept. of Data Science and Artificial Intelligence University of Petra Amman Jordan Department of Software Engineering University of Petra Amman Jordan Department of Computer Science University of Petra Amman Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Water scarcity critically threatens agricultural sus-tainability in Jordan, necessitating innovative technological solutions. This study presents a comprehensive framework that integrates Internet of Things (IoT) sensors with Big Data Analytics to optimize water usage in agriculture. Employing a multi-stage approach, we conducted real-time data acquisition from diverse farms, processed the data using clustering algorithms, and implemented intelligent decision-making systems. Our analysis focused on key parameters such as soil moisture, temperature, rainfall, and wind speed across various farming locations. The methodology encompassed extensive field data collection, advanced analytics, and the deployment of smart irrigation systems. Results demonstrated a significant 25 % reduction in water consumption while maintaining optimal crop yields. Additionally, clustering identified three distinct farm categories, each requiring tailored water management strategies. This research contributes to the field of smart agriculture by providing practical, scalable solutions for regions facing severe water scarcity. The findings highlight the potential of advanced technologies to enhance agricultural sustainability and address critical water management challenges.

关键词： Temperature sensors Smart agriculture Irrigation Wind speed Soil moisture Big Data Real-time systems Internet of Things Sustainable development Water resources

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：