检索结果-内蒙古大学图书馆

10th Biennial international conference on Pattern Recognition and machine Intelligence (PReMI)

作者： Mohanta, Anindita Roy, Sourav Dey Nath, Niharika Bhowmik, Mrinal Kanti Tripura Univ Comp Sci & Engn Dept Agartala 799022 Tripura India New York Inst Technol Biol & Chem Sci Dept New York NY 10023 USA

ISBN: (纸本)9783031451690;9783031451706

The inaccessibility of high numbers of annotated data and imbalance dataset's classes is a common phenomenon in medicalmicroscopic image datasets. Also, collecting data from the same domain is a challenging task in microscopic imaging (e.g. same magnification factor, staining method, cancer type, imaging modality). A Conventional Deep learning model with lack of labeled training data and domain shift could result in a misdiagnosis for such datasets. To overcome this problem, we formulated a domain adaptive few-shot learning (DA-FSL) problem and measured the perception capability of DA-FSL benchmark for medical histopathological image classification (especially for breast histopathological imaging). DA-FSL model overcomes a few-shot learning problem with domain shift by training the network on available source domain data but being able to test on target domain data with less number of available samples. DA-FSL models are validated on two publicly available breast cancer histopathological image datasets i.e., BreakHis and BreastCancer_IDC_Grade (BCIG). The presented DA-FSL framework has shown promising outcomes on both datasets. For performance evaluation we compared DA-FSL framework with other transfer learning and few-shot learning methods with different settings.

关键词： Breast Cancer Histopathological Images Few-Shot learning Domain Adaptation Classification

来源：评论

学校读者我要写书评

暂无评论

machine learning-assisted tri-objective optimization inspired by grey wolf behavior of an enhanced SOFC-based system for power and freshwater production

引用

international JOURNAL OF HYDROGEN ENERGY 2023年第66期48卷 25869-25883页

作者： Hai, Tao Alizadeh, As'ad Ali, Masood Ashraf Dhahad, Hayder A. Goyal, Vishal Metwally, Ahmed Sayed Mohammed Ullah, Mirzat Qiannan Normal Univ Nationalities Sch Comp & Informat Duyun 558000 Guizhou Peoples R China Guizhou Univ State Key Lab Publ Big Data Guizhou 550025 Guiyang Peoples R China Univ Teknol MARA Inst Big Data Analyt & Artificial Intelligence IBD Shah Alam 40450 Selangor Malaysia Cihan Univ Erbil Coll Engn Dept Civil Engn Erbil Iraq Prince Sattam Bin Abdulaziz Univ Coll Engn Dept Ind Engn Alkharj 16273 Saudi Arabia Univ Technol Baghdad Mech Engn Dept Baghdad Iraq GLA Univ Dept Elect & Commun Engn Mathura India King Saud Univ Coll Sci Dept Math Riyadh 11451 Saudi Arabia Ural Fed Univ Grad Sch Econ & Management Ekaterinburg 620002 Russia

In recent years paying attention to the generation of clean and sustainable power and fresh water along with having lower cost and emission has increased. In the present research, a novel scheme for generating efficient power using the flame-assisted fuel cell is introduced, which has higher efficiency than ordinary fuel cells due to increased hydrogen concentration in the flame-rich combustion chamber. The waste heat is then introduced to a multi-effect desalination unit through a heat recovery steam generation unit to generate fresh, drinkable water. In order to make the system have higher efficiency, lower cost, and lower emission, the machine learning techniques are applied to optimize the operational conditions of the system, and find out the best solution point based on the cutting-edge algorithm of the grey wolf. Also, a complete techno-economic analysis and a parametric study are necessary to figure out the best solution point based on the TOPSIS method. The results indicate that the maximum value of exergy efficiency and drinkable water generation is 67.5% and 3.4 kg/s, respectively, while the minimum energy cost is 90.1 $/MWh. Moreover, results show that for the second optimization scenario considering the drinkable water production, energy cost, and pollution index as the objectives, the net produced power, energy efficiency, exergy efficiency, and water mass flowrate improve by around 1059 kW, 5.1%, 1.3%, and 1.6 kg/s than the design condition. Besides, energy cost and emission index are reduced by about 22 $/MWh and 51.9 kg/MWh, respectively.& COPY;2023 Published by Elsevier Ltd on behalf of Hydrogen Energy Publications LLC.

关键词： machine learning Optimization Reduced environmental impact MED Sustainability

来源：评论

学校读者我要写书评

暂无评论

A Review on Automated Cancer Detection in Medical Images using machine learning and Deep learning based Computational Techniques: Challenges and Opportunities

引用

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 2022年第5期29卷 2893-2933页

作者： Manhas, Jatinder Gupta, Rachit Kumar Roy, Partha Pratim Univ Jammu Dept Comp Sci & IT BC Jammu India IIT Roorkee Dept Comp Sci & Engn Roorkee Uttar Pradesh India

Cancer is one of the most deadly diseases diagnosed among the population across the globe so far. The number of cases is increasing at a high pace each year that subsequently leads to the advancement in different diagnosis tools and technologies to handle this pandemic. Significant increase in the mortality rate worldwide leads tremendous scope to device and implement latest computer aided diagnostic systems for its early detection. The one among such techniques is machine learning coupled with medical imaging modalities. This combination has proven to be efficient in diagnosing various medical conditions in cancer diagnosis. Current study presents a review of different machine learning techniques applied on imaging modalities for cancer diagnosis from 2008 to 2019. This study focuses on diagnosis of five most prevalent and deadly cancers i.e., cervical cancer, oral cancer, breast cancer, brain cancer and skin cancer. Extensive and exhaustive review was carried out after going through different research papers, research articles and book chapters published by reputed international and national publishers such as Springer Link, science Direct, IEEE Xplore Digital library and PubMed. A number of conference proceedings have also been included subject to the fulfilling of our quality evaluation criteria. This review article provides a comprehensive overview of machine learning approaches using image modalities for cancer detection and diagnosis with main focus on challenges being faced during their research. Majority of the challenges are identified based on the use of potential machine learning based approaches, image modalities, features and evaluation metrics. This review not only identified challenges but also ear mark and present the new research opportunities for researchers working in this field. It has been widely observed that traditional machine learning algorithms Like SVM, GMM performed excellent in classification whereas the deep learning has dominated the

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Study on Factors Affecting Carbon Emissions in Ship Navigation and Prediction of EEDI 9th

Study on Factors Affecting Carbon Emissions in Ship Navigati...

引用

9th international conference on Advances in Energy Resources and Environment Engineering, ICAESEE 2023

作者： Zhang, Jingwen Peng, Zitong Liu, Jiaying Yang, Boxin Harbin Engineering University Harbin China University of Southampton Southampton United Kingdom

ISBN: (纸本)9783031665042

In the context of green shipping, this paper analyzes factors influencing carbon emissions during vessel navigation, including wind speed, wind direction, wave conditions, and ocean currents. Through qualitative analysis and data collection from various sources, the study identifies key factors with operational significance that impact vessel navigation speed. A predictive model for shaft power is proposed, outputting Energy Efficiency Existing Ship Index (EEDI) predictions. The research aligns with the trend of low-carbon green shipping, providing insights for reducing operational costs and emission expenses. The study holds significance in the field of artificial intelligence, particularly in machine learning and deep learning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Maritime Anomaly Detection: A Decadal Bibliometric Analysis (2014–2024)

引用

Journal of The Institution of Engineers (India): Series C 2025年第2期106卷 665-689页

作者： Thakur, Aman Singh Alex, T. Lawrence Nighojkar, Amrita Department of Mechanical Engineering National Institute of Technology Raipur Raipur India R & D Management and AI Analytics Research Group Defence Institute of Advanced Technology Pune India

This investigation builds upon scholarly research on AI-integrated anomaly detection in maritime safety operations from 2014 to 2024. The bibliometric analysis analyzes key Countries, Journals, Research themes, Keyword frequency, Co-citation analysis, Impactful authors, and significant collaborations among researchers and relevant institutes for Maritime Anomaly Detection Research. Our findings highlight substantial contributors, including China, France, Italy, and the USA, emphasizing essential collaboration networks and influential journals such as IEEE Transactions on Intelligent Transportation Systems and the international Journal of Approximate Reasoning. We scrutinize the application of various AI and machine learning models, such as LSTM, CNN, and SVM, across different anomaly types. These models are frequently implemented to detect environmental, navigation, cybersecurity, sensor, operational, communication, and behavioural anomalies. For navigation anomalies like unexpected course changes and speed variations, LSTM is utilized due to its capability to handle sequential data. CNN is employed for spatial-temporal pattern recognition in navigation routes, while SVM is applied to classify navigation patterns and detect deviations. Similarly, LSTM effectively identifies security anomalies, including unauthorized boardings and suspicious activities, through sequence modelling, and CNN proves helpful for spatial analysis. This study provides comprehensive insights into the current state of maritime anomaly detection research. It proposes future research areas, emphasizing model accuracy and efficiency enhancements, developing hybrid models, and addressing emerging challenges. Our analysis aims to guide researchers and practitioners by identifying critical areas for advancement and fostering potential collaborative efforts in this field. © The Institution of Engineers (India) 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Prototype-guided Knowledge Transfer for Federated Unsupervised Cross-modal Hashing 23

Prototype-guided Knowledge Transfer for Federated Unsupervis...

引用

31st ACM international conference on Multimedia (MM)

作者： Li, Jingzhi Li, Fengling Zhu, Lei Cui, Hui Li, Jingjing Shandong Normal Univ Jinan Peoples R China Univ Technol Sydney Sydney NSW Australia Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9798400701085

Although deep cross-modal hashing methods have shown superiorities for cross-modal retrieval recently, there is a concern about potential data privacy leakage when training the models. Federated learning adopts a distributed machine learning strategy, which can collaboratively train models without leaking local private data. It is a promising technique to support privacy-preserving cross-modal hashing. However, existing federated learning-based cross-modal retrieval methods usually rely on a large number of semantic annotations, which limits the scalability of the retrieval models. Furthermore, they mostly update the global models by aggregating local model parameters, ignoring the differences in the quantity and category of multi-modal data from multiple clients. To address these issues, we propose a Prototype Transfer-based Federated Unsupervised Cross-modal Hashing (PT-FUCH) method for solving the privacy leakage problem in cross-modal retrieval model learning. PT-FUCH protects local private data by exploring unified global prototypes for different clients, without relying on any semantic annotations. Global prototypes are used to guide the local cross-modal hash learning and promote the alignment of the feature space, thereby alleviating the model bias caused by the difference in the distribution of local multi-modal data and improving the retrieval accuracy. Additionally, we design an adaptive cross-modal knowledge distillation to transfer valuable semantic knowledge from modal-specific global models to local prototype learning processes, reducing the risk of overfitting. Experimental results on three benchmark cross-modal retrieval datasets validate that our PT-FUCH method can achieve outstanding retrieval performance when trained under distributed privacy-preserving mode. The source codes of our method are available at https://***/exquisite1210/PT-FUCH_P.

关键词： Federated learning Unsupervised learning Cross-modal Retrieval Unsupervised Cross-modal Hashing Prototype learning

来源：评论

学校读者我要写书评

暂无评论

Impact of data Preprocessing on Wind Forecasting Using machine learning Techniques 4

Impact of Data Preprocessing on Wind Forecasting Using Machi...

引用

4th international conference on Power, Control and Computing Technologies, ICPC2T 2025

作者： Gaikwad, Nidhi Haribhau Mitra, Arghya Payal, Jangilwar Das, Soumyabrata Keshri, Ritesh kumar Department of Electrical Engineering VNIT Nagpur India

ISBN: (纸本)9798331530402

There is a high demand for renewable energy sources as non renewable energy sources are harmful to the environment due to its effects such as global warming. Among non renewable energy source, the wind energy is unpredictable in nature, making Its integration with the grid a concern. By accurately forecasting wind energy, the stability of the grid can be ensured. The aforementioned can be achieved with the help of machine learning (ML) techniques. This paper investigate four ML techniques Multiple Linear Regression, Support Vector Regression, Random Forest Regression, and Decision Trees which are utilized and compared based on the metrics such as root mean square error, mean square error, mean absolute error, and R2 for three different cases. Initially errors are calculated without data preprocessing and later with data preprocessing. It is observed that preprocessing reduces error. This paper also investigates the effect of different seasons on the errors generated by these ML techniques. For this research, data is taken from National Solar Radiance database (NSRD) over two year period from January 2018 to December 2019. © 2025 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

A New Federated learning Model for Host Intrusion Detection System Under Non-IID data

A New Federated Learning Model for Host Intrusion Detection ...

引用

2023 IEEE international conference on Systems, Man, and Cybernetics, SMC 2023

作者： Guo, Wei Yao, Zhiwei Liu, Yongfei Zhang, Lanxue Li, Liangxiong Li, Tong Wu, Bingzhen Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350337020

Host Intrusion Detection System (HIDS) is an important research topic in the field of cyberspace security. With the explosion in the number of malicious attacks in recent years, machine learning-based detection method is now the most common and efficient approach. While traditional centralized machine learning needs to transmit data to the central server for training, which not only requires the central server to have large computing resources, but also causes problems such as sensitive data leakage and communication overhead. As a distributed machine learning paradigm, Federated learning (FL) can achieve multi-party collaborative training and aggregate a unified global model without data sharing, which can well alleviate these problems. It is worth noting that existing studies on the use of FL in HIDS are all conducted in the scenario where the data is independent and identically distributed (IID). However, due to the different context of hosts, the data generated by hosts is usually non-independent and identically distributed (Non-IID) in reality. Therefore, We investigate the impact of Non-IID data with different skew levels on FL in HIDS. On this basis, we propose a data augmentation FL algorithm based on Synthetic Minority Over-Sampling Technique (SMOTE) to reduce the impact of Non-IID data. We also develop a data collection module using extended Berkeley Packet Filter (eBPF) technology to collect a dataset for experiments. Experimental results show that our proposed FL algorithm can effectively improve the performance of HIDS under Non-IID data. © 2023 IEEE.

关键词： eBPF Federated learning HIDS Non-IID data SMOTE

来源：评论

学校读者我要写书评

暂无评论

GoPlace: chip placement like playing go 3

GoPlace: chip placement like playing go

引用

3rd international conference on Algorithms, Microchips, and Network Applications, AMNA 2024

作者： Hu, Jianguo Shen, Shengzhi Ding, Yanyu Wang, Yuhe Pan, Jiakai Huang, Wenjun Wang, Deming School of Microelectronics Science and Technology Sun Yat-sen University Zhuhai519082 China School of Electronics and Information Engineering South China Normal University Foshan528225 China Dongguan University of Technology Dongguan China Shenzhen Research Institute of Sun Yat-Sen University Shenzhen China

ISBN: (纸本)9781510680098

As a critical stage in modern Very-Large-Scale Integrated (VLSI) design, placement plays a crucial role in positioning numerous circuit modules of varying sizes onto a 2D chip canvas to achieve optimal performance. In recent years, applying machine learning methods to placement has emerged as a promising solution for significantly enhancing efficiency and achieving superior results. However, machine learning-driven methods are still in their early stages, facing challenges such as exploration and convergence difficulties. In addition, it is challenging to integrate netlist data with the placement information. This paper proposes a novel approach leveraging deep reinforcement learning to address these challenges. First, a multi-layer chip canvas state representation method is proposed to tackle the challenges of storing and using the placement information. Additionally, a graph neural network is used to assist in generating placement information. Second, this paper proposed a semi-shared policy and value network, and to accommodate the scale and complexity of chip placement, a residual-like neural network is proposed. Third, extensive experiments on eight circuits of public benchmarks show that GoPlace achieves 10% ~ 25% wirelength reduction compared to other reinforcement learning-based methods, lowest congestion, and guarantees zero overlap. © 2024 SPIE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Survey of Edge Computing Resource Allocation Strategies Based on Federated learning

A Survey of Edge Computing Resource Allocation Strategies Ba...

引用

2023 international conference on Networking and Network Applications, NaNA 2023

作者： Ni, Siyuan He, Yuanhang Chen, Lei Wang, Yuyao Yu, Fei Science and Technology on Communication Security Laboratory Chengdu610041 China No.30 Research Institute of China Electronics Technology Group Corporation Chengdu China

ISBN: (纸本)9798350327380

In the edge computing environment, the data on edge computing is at risk of leakage due to the variety and wide distribution of nodes. As a new distributed machine learning framework, federated learning can effectively solve the privacy and security problems of users' information data in different fields. However, in federated learning, with the continuous landing of AI applications and the growing demand for model reasoning services, the resources consumed by federated learning will exceed the computing power of edge computing, so it is necessary to study the resource allocation strategy of edge computing for federated learning. This paper first introduces the concepts of federated learning and edge computing, and resource allocation strategies based on edge computing;Then it introduces the challenges faced by federated learning and the operating system framework of edge computing based on federated learning;Secondly, it combs the resource allocation strategy of edge computing based on federated learning;Finally, the paper summarizes the work of the full text and analyzes the future development trend of resource allocation under Federated learning. © 2023 IEEE.

关键词： Resource allocation

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：