检索结果-内蒙古大学图书馆

2nd International Conference on Next-Generation Computing and Information Systems, ICNGCIS 2023

作者： Digra, Monia Rajput, Preeti Sharma, Pooja Model Institute of Engineering and Technology J&K Jammu India School of Computer Science and Engineering Shri Mata Vaishno Devi University J&K Katra India

ISBN: (纸本)9781032738659

Agricultural development is crucial to ending poverty and boosting economic growth in emerging nations. The global population is expected to reach 9.7 billion by 2050. Smart and precise agriculture must enhance agricultural productivity without compromising quality, nutrition, or natural resources. IoT and AI/ML have significant uses in agriculture due to internet technologies. Although IoT has many benefits, the enormous number of networked devices may raise carbon emissions and e-waste due to energy consumption. Inspired by the goal of sustainable smart agriculture, this article addresses major results and research gaps in IoT-based smart agriculture and provides solutions for energy-saving Green-IoT (G-IoT) applications in agriculture. We start with G-IoT’s evolution and smart agriculture applications. We also examine how green architecture may efficiently apply AI/ML in smart agriculture. We propose an AI/ML G-IoT framework for smart agriculture with green sensor cloud and green AI. This unique G-IoT paradigm provides sustainable and energy-efficient agricultural architecture. We investigate statistical and experimental data and emphasise the limitations of adopting G-IoT and AI/ML architecture in agriculture. In conclusion, G-IoT and AI/ML architecture can enable sustainable, energy-efficient, smart precision agriculture. © 2025 The Author(s).

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Structural and Semantic Enrichment of Models for the Interactive Discovery of Clinical Processes

Structural and Semantic Enrichment of Models for the Interac...

引用

International Workshops which were held in conjunction with the 6th International Conference on Process Mining, ICPM 2024

作者： Bayo-Montón, Jose Luis Martínez-Salvador, Begoña Fernández-Llatas, Carlos Marcos, Mar Department of Computer Engineering and Science Universitat Jaume I Castelló Spain SABIEN-ITACA Universitat Politècnica de València Valencia Spain

ISBN: (纸本)9783031822247

Process Mining (PM) is a relatively new field which provides techniques to analyze business processes in different areas. In the field of Medicine, PM seeks to infer clinical processes from the data routinely collected during healthcare activities. In most frameworks, workflows are used to represent the results obtained by PM techniques. A problem with these workflows is that their structure is complex and not always easy to understand and hence to exploit by the clinician. A different problem, related to Clinical Practice Guidelines (CPGs), is that their development is mostly manual. We posit that workflows inferred by PM techniques could be improved and enriched by providing interactive tools to support their structuring and semantic annotation by clinicians. We also postulate that these improved and enriched models can be used to facilitate the development of CPGs. In this paper we describe our approach to the interactive discovery of clinical processes as well as an implementation to support it within the PMApp PM tool. © The Author(s) 2025.

关键词： Clinical Process Models Interactive Process Discovery Model Enrichment

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Optimization Framework for Adaptive Node Deployment in Wireless Sensor Networks 14

A Bayesian Optimization Framework for Adaptive Node Deployme...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Priyadarshi, Rahul Rout, Jayant Kumar Vishwakarma, Anish Kumar Dhengre, Nikhil Ranjan, Rakesh Verma, Amit Faculty of Engineering and Technology ITER SOA Bhubaneswar India School of Computer Application KIIT Bhubaneswar India School of Computer Science UPES Uttarakhand Dehradun India Department of ECE IIIT Maharashtra Nagpur India

ISBN: (纸本)9798331531935

Wireless Sensor Networks (WSNs) require efficient node deployment strategies to optimize network longevity, energy consumption, and coverage. This paper introduces a novel approach for strategic node deployment in WSNs using Bayesian Optimization (BO). A BO-based framework that iteratively modifies node positions to maximize network performance metrics, such as energy efficiency and coverage ratio, while minimizing execution time is proposed. Through extensive simulations across diverse deployment scenarios, the proposed method is evaluated and demonstrates superior performance compared to both traditional and machine learning (ML)-based techniques. The results indicate significant improvements in coverage and energy efficiency, alongside competitive execution times. These findings highlight the potential of BO to enhance WSN deployment strategies, offering a scalable and adaptive solution for real-world applications. Future research will focus on integrating BO with other optimization techniques and extending the approach to dynamic environments and varied network configurations. © 2025 IEEE.

关键词： Bayesian Optimization Coverage Ratio Energy Efficiency Node Deployment Wireless Sensor Networks

来源：评论

学校读者我要写书评

暂无评论

RetNet: A Two-Stage Deep Neural Network for Clinically Traceable Retinal Disease Classification 5th

RetNet: A Two-Stage Deep Neural Network for Clinically Trac...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Banerjee, Rohan Kumar Saha, Sanjoy Chakraborti, Tapabrata Department of Computer Science and Engineering Jadavpur University Kolkata India Turing-Roche Partnership Alan Turing Institute and University College London United Kingdom

ISBN: (纸本)9789819638628

Given that many globally leading diseases like diabetes and hypertension have early manifestation in the retina, development of AI enabled low-cost non-invasive pre-diagnostic tools is of great potential benefit for mass screening especially in low and middle income countries. Despite a substantial amount of existing work in this area, very few methods have been translated into the clinic because of two reasons. First, the list of diseases detectable from retinal fundus imaging is ever increasing with new medical research, and hence the AI pipelines need to be designed in a staged semi-supervised fashion to ensure scalability and generalisation. Second, it is crucial for such models to transparently align with established clinical features in order to be adopted as clinical decision support systems (CDSS). We present RetNet, a two-stage deep neural network that addresses both issues simultaneously, by providing a computationally scalable as well as clinically traceable system. In the first stage, we use autencoders to learn the healthy class in a semi-supervised manner and then do a binary classification to identify abnormal images in an anomaly detection setting. In the second stage, we use a convolutional neural network (CNN) based classifier for the disease categorization. Instead of using the whole retinal image as input in a domain agnostic way, we use clinically relevant RoIs as inputs in parallel learning channels to ensure interpretability and trustworthiness. Results show that RetNet produces competitive results on benchmark datasets like JSIEC and RFMiD across a range of diseases. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Advanced AI & ML Applications in Satellite Image Processing & Industry

Advanced AI & ML Applications in Satellite Image Processing ...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Raj Kishor Verma Ayush Chaudhary Harsh Bhati Gagan Bisht School of computer science & Engineering Galgotias University Gr. Noida Computer Science & Engineering Data Science ABES Institute of Technology Ghaziabad India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

By integrating advanced artificial intelligence (AI) and machine learning (ML) into satellite image processing, a number of industries standard to benefit in kinds of artificial intelligence and machine learning used for geoanalysis. Decades-old image processing processes are beginning to be invaded by robots. Using ML and AI to process satellite images provides a lot of new AI powered imaginations that can monitor environmental change, support disaster response and plan city layouts. Such development in the precision of techniques such as object classification, object detection and pixel detection make the analysis of image sequences from satellites possible and rapid. Enhancement of task accuracy and observability. Widely used in fields like greenhouse gas surveillance, changes in land use trends and the natural habitats of animals. In addition to introducing AI methodologies into high resolved satellite data, obvious advantages are brought to both decision making and environmental sustainability in many fields. As countries put satellites in orbit and their images become more readily accessible to the public, the opportunities for AI-driven applications of satellite image data are expected to increase, offering significant advancements in such fields as global development and resource management. This paper discusses such earth-moving applications and looks at how the future of artificial intelligence (AI) is being impacted by all this.

关键词： Industries Satellites PSNR Image resolution Accuracy Surveillance Urban planning Machine learning Satellite images Standards

来源：评论

学校读者我要写书评

暂无评论

Sustainable Energy-Driven P2P Blockchain System for Tracking EV Performance and Maintenance 1

Sustainable Energy-Driven P2P Blockchain System for Tracking...

引用

1st International Conference on Sustainable Energy Technologies and Computational Intelligence, SETCOM 2025

作者： Odnala, Srinivas Pradhan, Nihar Ranjan Nanda, Sambhu Dutta VIT-AP University School of Computer Science and Engineering Andhra Pradesh Amaravati522237 India VIT-AP University School of Electronics Engineering Andhra Pradesh Amaravathi522237 India

ISBN: (纸本)9798331520540

Electric vehicles (EVs) are the foundation of sustainable mobility, yet effective maintenance tracking and performance monitoring is still difficult, particularly in decentralized ecosystems. To fill these gaps, this study suggests a Sustainable Energy-Driven Peer-to-Peer (P2P) Blockchain System that combines blockchain technology, IoT-enabled EV systems, and renewable energy sources. The system lowers operating costs and minimizes the greenhouse effect by using sustainable energy sources like wind and solar to power blockchain nodes, EV charging stations, manufacturing, distributors and, service centers. The decentralized P2P blockchain network guaranteed transparent, immutable tracking of EV performance indicators and maintenance logs. The Istanbul Byzantine Fault Tolerance (IBFT) consensus method provides safe, effective, and energy-efficient transaction validation. EVs' IoT sensors continually gather performance data, including mileage and battery health, which is then stored on the blockchain for computationally intelligent predictive maintenance. The Ethereum Smart contracts improve dependability and reduce administrative burdens by automating warranty monitoring, maintenance schedules, insuring renewal and, service provider communications. Furthermore, by offering verified service records, the blockchain makes ownership transfers easier and increases market trust for used EVs. In line with the objectives of smart cities and green technology, this integrated strategy promotes adopting sustainable energy and improves the lifetime, efficiency, and accountability of EVs. © 2025 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

MIRIAMS: Models Integration for Reliable Identification and Accurate Multiple Sclerosis Segmentation

MIRIAMS: Models Integration for Reliable Identification and...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Pani, Alessandro Loddo, Andrea Putzu, Lorenzo Zedda, Luca Di Ruberto, Cecilia Department of Mathematics and Computer Science University of Cagliari Cagliari Italy Department of Electrical and Electronic Engineering University of Cagliari Cagliari Italy

ISBN: (纸本)9783031876592

Multiple sclerosis lesion segmentation is a critical task in medical imaging since it aims to identify and delineate brain lesions. In this study, we propose a new method called Models Integration for Reliable Identification and Accurate Multiple Sclerosis Segmentation (MIRIAMS), which is a robust ensemble approach that integrates three distinct neural network architectures to enhance segmentation performance in 3D volumes, setting it apart from the majority of existing methods which operate in 2D. MIRIAMS consists of three different 3D networks: a traditional 3D U-Net, a 3D UNETR that leverages Vision Transformers, and a 3D Swin-UNETR, which employs Swin Vision Transformers. This combination allows the model to capture features with varying receptive fields, improving the overall lesion segmentation. Unlike previous studies, we conduct a per-patient evaluation, ensuring a more individualised and clinically relevant assessment of the segmentation performance. Our results demonstrate that the ensemble approach outperforms individual models, providing a promising, reliable and effective tool for multiple sclerosis lesion segmentation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Sustainable Drone Surveillance System Using Eternal Vertex Cover and Periodic Charging 17

Sustainable Drone Surveillance System Using Eternal Vertex C...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Dhawde, Navya Chakraborty, Nilotpal Husain Baig, Mirza Galib Anwarul Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India Indian Institute of Technology School of Mathematical and Statistical Sciences Mandi India

ISBN: (纸本)9798331531195

Unmanned aerial vehicles (UAVs), or drones, are transforming surveillance strategies in various fields, including border security and wildlife conservation. Their ability to monitor large, challenging areas in real time has established them as a valuable tool, particularly in scenarios where traditional surveillance methods face operational and logistical limitations. This research focuses on optimizing drone-based surveillance along the International borders, and in wildlife conservation areas, where challenges like illegal crossings, cattle smuggling, and poaching present serious security and economic threats. Leveraging UAVs provides a cost-effective, flexible, and highly deployable solution that overcomes the limitations of static surveillance systems and limited human patrols. We propose an optimized drone-based system designed to enhance operational efficiency, coverage, and adaptability in these complex environments, with potential applications in various sectors requiring comprehensive, real-time surveillance. We propose modeling the problem using the Eternal Vertex Cover problem, a dynamic extension of the classical Vertex Cover problem. Given the NP-hard nature of determining this cover number, our research explores heuristic and algorithmic approaches to achieve an efficient and scalable solution. We also propose an intelligent charging mechanism for the drones for their continuous operation. All proposed approaches are evaluated using randomly generated datasets as long as benchmark datasets. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement in Terms of BER and Data Rate of Next Generation Optical Networking System using Raman Amplifier 3

Performance Enhancement in Terms of BER and Data Rate of Nex...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Khant, Shailesh Makwana, Mayur Patel, Atul Patel, Dip Faculty of Computer Science and Applications Charusat Changa Anand India Faculty of Electronics and Communication Engineering Charusat Changa Anand India

ISBN: (纸本)9798331508456

This study explores the integration of Raman optical amplifiers in a Wavelength Division Multiplexing Passive Optical Network (WDM-PON) system to enhance high-speed data transmission. Traditional amplifiers like Erbium doped fiber amplifier (EDFA) and Semiconductor amplifier (SOA) face limitations in noise performance and gain efficiency over long distances. To address these challenges, a four-channel WDM-PON system was designed and simulated over a 50 km fiber link. Performance metrics, including Bit Error Rate (BER), Quality Factor (Q-Factor), and eye diagram characteristics, were analyzed. The results demonstrate that Raman amplification significantly reduces BER, improves Q-Factor, and enhances signal integrity, making it a robust solution for long-reach optical networks. This study contributes to the advancement of optical communication by showcasing the effectiveness of Raman amplifiers in supporting high-capacity, high-speed transmission. The main findings are Raman amplification is used for improving signal quality and network efficiency in next-generation optical systems and is better compared to other optical amplifiers. © 2025 IEEE.

关键词： Erbium doped fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Review of AI & XAI-based breast cancer diagnosis methods using various imaging modalities

引用

Multimedia Tools and Applications 2025年第5期84卷 2209-2260页

作者： Karthiga, R. Narasimhan, K. Thanikaiselvan, V. Hemalatha, M. Amirtharajan, Rengarajan Department of ECE SRM Institute of Science and Technology Ramapuram Chennai600089 India School of Electrical & Electronics Engineering SASTRA Deemed University Thanjavur613 401 India School of Electronics Engineering Vellore Institute of Technology Vellore India Department of Electrical and Computer Engineering King Abdulaziz University Jeddah Saudi Arabia

Breast cancer is a significant health concern;early detection and treatment are critical to improving patient outcomes. Artificial Intelligence has the potential to assist healthcare professionals in the diagnosis and treatment of breast cancer, and clinical decision support systems using AI algorithms can help to improve the accuracy and speed of breast cancer detection and diagnosis. By analysing large amounts of data from various imaging modalities, AI algorithms can help identify breast cancer early, increasing the chances of successful treatment. This survey aims to briefly overview the most prevalent breast cancer types, their staging, and the methods and modalities for their diagnosis to address these problems. Our investigation showed that, when compared to ML, DL techniques achieved the highest accuracy, with an approximate 2% improvement in accuracy. This review article mainly focuses on four commonly used imaging modalities: Mammogram, Thermogram, Ultrasound imaging and histopathology images. This survey critically analyzes breast cancer detection approaches and modalities, as well as a cost-to-accuracy comparison. Explainable AI (XAI) techniques and their application for breast cancer diagnosis are critically examined, as well as their advantages and limitations. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Lung cancer

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：