检索结果-内蒙古大学图书馆

Titania coating formation on hydrostatically extruded pure titanium by micro-arc oxidation method

Journal of Materials science & Technology 2022年第16期111卷 224-235页

作者： Ł.Maj D.Wojtas A.Jarz˛ebska M.Bieda K.Trembecka-Wójciga R.Chulist W.Kozioł A.Góral A.Trelka K.Janus J.Kawałko M.Kulczyk F.Muhaffel H.Çimeno˘glu K.Sztwiertnia Institute of Metallurgy and Materials Science Polish Academy of SciencesReymonta 25Krakow 30-059Poland Faculty of Physics and Applied Computer Science AGH University of Science and TechnologyKrakowPoland Academic Centre of Materials and Nanotechnology AGH University of Science and TechnologyKrakowPoland Institute of High Pressure Physics Polish Academy of SciencesWarsawPoland Department of Metallurgical and Materials Engineering Istanbul Technical UniversityIstanbulTurkey

In this work,the microstructure of titania coating fabricated on the surface of hydrostatically extruded titanium grade 4 with the use of the micro-arc oxidation method was *** surface topography and microstructure investigations performed with atomic force microscopy and scanning and transmission electron microscopy revealed that,by using an Na_(2)HPO_(4)electrolyte,a well-adherent porous coating is produced on the top surface and side walls of the extruded *** distribution of chemical elements was analyzed by using energy dispersive X-ray *** chemical elements dissolved in the electrolyte(Na,P and O)incorporated into the *** locates preferentially in the outer part of the coating,while phosphorus and oxygen are distributed throughout the whole *** most relevant finding shows that a grain refinement caused by a hydrostatic extrusion provoked an increase in density of high-angle grain boundaries(HAGB),which in turn secured the formation of a continuous amorphous layer close to the *** presence of this layer compensates for the effect of anisotropic substrate,producing a comparable and homogenous microstructure with a large number of micropores.

关键词： Micro-arc oxidation Titanium of commercial purity Hydrostatic extrusion Surface topography Microstructure

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiovascular Disease Analytics with Demographic and Behavioral Risk Features through Unsupervised and Ensemble Learning Techniques 12

Enhancing Cardiovascular Disease Analytics with Demographic ...

引用

12th IEEE Conference on Systems, Process and Control, ICSPC 2024

作者： Sem, Li Xiang Chua, Hui Na Jasser, Muhammed Basheer Wong, Richard T.K. Aldharhani, Ghassan Saleh Sunway University No. 5 Jalan Universiti School of Engineering and Technology Department of Computing and Information Systems Bandar Sunway Selangor Darul Ehsan47500 Malaysia Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia UKM University Faculty of Information Science and Technology Selangor Bangi Malaysia

ISBN: (纸本)9798350391398

Cardiovascular diseases (CVD) are a leading health concern, projected to affect 23.6 million people by 2030. Despite extensive research, challenges remain in conventional diagnostic accuracy and limited healthcare access in low-income communities. Current computing methods for detecting CVD rely on costly medical tests. Subsequently, prior studies have documented many inconsistent insights on the development of CVD due to variations in study design and demographics. This research addresses these gaps by studying the potential of incorporating demographics and behavioral risk factors for CVD detection and experimenting with various modeling and sampling techniques to address imbalanced target distributions and improve detection accuracy. The resampled BRFSS dataset was subjected to regression analysis to capture demographic trends in CVD development, with two cross-referenced datasets for comparison. Association rule mining identified key risk factors linked to CVD. Classifiers, including XGBoost, Random Forest, SVM, Multilayer Perceptron, and Logistic Regression, were used to establish baseline performance, and these classifiers were integrated into CatBoost as a meta-classifier using a stacking ensemble approach. Our findings indicate that demographic factors significantly influence CVD development, but effects vary by region, culture, and lifestyle. Key risk factors such as diabetes, smoking, and stroke were identified as significant contributors to CVD. Our experiment results show that leveraging full features set with fine-tuned ensemble stacking techniques increases model performance and achieves an accuracy of 96%. Our research contributes valuable insights into the consistency of demographic effects and identifies key risk factors for CVD. The proposed ensemble model demonstrates exceptional performance, highlighting its potential as a cost-effective tool for early cardiac detection and improved healthcare accessibility. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

SSANet: Side-by-Side Additive Network for Knee Osteoarthritis Severity Detection from X-Ray Images 4th

SSANet: Side-by-Side Additive Network for Knee Osteoarthrit...

引用

4th International Conference on Frontiers in computing and Systems, COMSYS 2023

作者： Tewari, Rakhi Bhattacharjee, Debotosh Roy, Hiranmoy Krejcar, Ondrej Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Department of Information Technology RCC Institute of Information Technology Canal South Road Beliaghata Kolkata700015 India Faculty of Informatics and Management Center for Basic and Applied Science University of Hradec Kralove Rokitanskeho 62 Hradec Kralove50003 Czech Republic

ISBN: (纸本)9789819726103

Knee Osteoarthritis (KOA) is becoming one of the most frequent degenerative and irreversible diseases in elderly people. Its early detection and diagnosis is also a difficult and time-intensive task. The recent advances in Machine Learning (ML) and computer Vision (CV) created new paths to automatically detect KOA in the early stages. Detecting and grading the severity of KOA requires a dedicated ML model. This paper proposes a Side-by-Side Additive Network (SSANet)-based model for detecting and grading the severity of KOA. Since KOA affects the knee joint space by narrowing the gap between the joints, we preprocess the X-ray images to detect the Region of Interest (ROI) before the training of the model. From experimental results, it is evidenced that the ROI selection is really improving the detection accuracy of the model. Unlike sequentially connected convolution layer-based deep learning models, the proposed SSANet is based on a parallel convolution layer to reduce the degradation of feature quality. Again, to enhance the edge feature maps, we apply an additive layer that couples the previous layers’ convolutional output. SSANet captures both high-level and low-level features to predict the KOA severity effectively. The presence of a smaller number of layers and fewer numbers of learnable parameters than the existing popular deep learning models, make SSANet a time and space-efficient network. Moreover, the performance of the proposed SSANet in detecting KOA severity is significantly superior to that of other popular state-of-the-art networks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Blockchain Empowered Secure Federated Learning for Consumer IoT Applications in Cloud-Edge Collaborative Environment

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Kumar, Mohit Samriya, Jitendra Kumar Walia, Guneet Kaur Verma, Prabal Wu, Huaming Gill, Sukhpal Singh National Institute of Technology Department of Information Technology Jalandhar India Indian Institute of Information Technology Computer Science and Engineering Sonepat India National Institute of Technology Department of Information Technology Srinagar India Tianjin University Center for Applied Mathematics Tianjin China Queen Mary University of London School of Electronic Engineering and Computer Science United Kingdom

The growing number of consumer Internet of Things (IoT) gadgets, including smart homes, fitness trackers, connected appliances, and home security systems, is transforming the way we live our daily lives. This has led to the emergence of a collaborative cloud-edge paradigm to leverage resources and services near the end-user, thereby providing prompt response to delay-sensitive real-time applications. Nevertheless, the tremendous amount of data generated by various IoT devices and sent over the network is always an open security challenge. The introduction of Federated Learning (FL) addresses the security and data privacy shortcomings of traditional centralised machine learning. Despite FL's use for data privacy, it must overcome a number of significant challenges, such as privacy concerns, communication overhead, stragglers, and heterogeneity. To solve these challenges, this paper proposes a novel technique for enhancing security in IoT-enabled edge cloud computing networks, utilising blockchain-driven FL and Gaussian Bayesian transfer convolutional neural network architectures for data analysis. Blockchain-driven FL ensures the security and privacy of consumer IoT applications. In comparison to state-of-the-art works, the experimental results achieved throughput of up to 89%, latency of 71%, training accuracy of 91%, validation accuracy of 96%, and network security of 92%. © 1975-2011 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Predictive Modeling of Military PTSD: SCA-Guided LSTM Analysis

Advanced Predictive Modeling of Military PTSD: SCA-Guided LS...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Sawangikar, Megha Dash, Chinmaya Surekha, S. Vuyyuru, Veera Ankalu Chopra, P.K.P. Gaitry Saravanakumar, R. Yeshwantrao Chavan College of Engineering Department of Applied Chemistry Maharashtra Nagpur India St. Claret College Autonomous Department of Computer Science Bangalore India Affiliated to JNTUH Ghatkesar Hyderabad India Koneru Lakshmaiah Education Foundation Department of CSE Andhra Pradesh Vaddeswaram India DMIHER Faculty of Engineering and Technology Department of Applied Chemistry Maharashtra Wardha India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of ECE Chennai India

ISBN: (纸本)9798331539948

Military personnel frequently suffer from posttraumatic stress disorder (PTSD), a complicated mental health illness brought on by their exposure to terrible experiences during combat operations. For prompt assistance and intervention, it is essential to anticipate and comprehend the onset of PTSD. This study suggests a unique method for combining the LSTM network with the Sine Cosine Algorithm (SCA) for enhanced predictive modelling of military PostTraumatic Stress Disorder (PTSD). PTSD is a common mental health issue that affects military people, frequently stemming from their exposure to traumatic events that occurred during war. For PTSD to be effectively managed and treated, early recognition and intervention are essential. Due to the disorder's complexity and dynamic nature, traditional predictive modelling tools frequently encounter difficulties in effectively predicting the onset of PTSD. The approach is a methodical procedure that starts with gathering data on PTSD from military members and ends with pre-processing the data using Z-score normalisation. The SCA method is then utilised to extract pertinent characteristics, which makes it possible to identify important patterns associated with PTSD. These features are utilized as input for a SCA-LSTM model, which combines the advantages of both algorithms to predict PTSD with accuracy. Experiments on a sizable dataset of military soldiers show that the suggested method is highly accurate in predicting the onset of PTSD with recall rates and precision. The increased prediction accuracy and robustness of the SCA-LSTM framework are demonstrated by comparative comparisons with baseline models. The performance and accuracy (9 7%) of the prediction model are assessed by comprehensive model evaluation, guaranteeing its dependability in diagnosing PTSD patients. This research provides possible possibilities for improving mental health outcomes within this group by highlighting the need of utilising advanced predictive

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Cancer Diagnosis with Deep Learning: A Case Study Using U-Net 7

Revolutionizing Cancer Diagnosis with Deep Learning: A Case ...

引用

7th International Conference on Contemporary computing and Informatics, IC3I 2024

作者： Goyal, Himanshu Rai Al-Farouni, Mohammed Deepak, A. Reddy, R. Akhilesh Yadav, Kanchan Revathi, V. Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India The Islamic university College of technical engineering Department of computers Techniques engineering Najaf Iraq Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Tamilnadu Chennai India Mlr Institute of Technology Department of CSE-AI&ML Telangana Hyderabad India Gla University Department of Electrical Engineering Mathura India New Horizon College of Engineering Department of Applied Sciences Bangalore India

ISBN: (纸本)9798350350067

The U-Net architecture is a convolutional neural network model that is well-known for its skills in biomedical image segmentation. This study investigates the revolutionary potential that the U-Net architecture presents in the context of cancer diagnosis. We guarantee that the input is of high quality by using sophisticated preprocessing methods, which we do by constructing a robust U-Net-based system that is specifically designed for the segmentation and classification of tumour regions in medical imaging data. An exhaustive examination that makes use of criteria such as the Dice similarity coefficient, precision, recall, and F1 score indicates that our model performs substantially better than conventional techniques when it comes to identifying and distinguishing malignant tissues. Case studies that cover a wide range of cancer types provide further validation of the flexibility and practical application of the system. These studies also highlight the significant influence that deep learning has on increasing diagnosis accuracy, lowering the risk of human error, and overall patient outcomes in the field of cancer treatment. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Multicarrier Waveform Design for Integrated Sensing and Communication

Cross-Domain Multicarrier Waveform Design for Integrated Sen...

引用

IEEE Conference on Wireless Communications and Networking

作者： Fan Zhang Tianqi Mao Ruiqi Liu Zhu Han Octavia A. Dobre Sheng Chen Zhaocheng Wang Department of Electronic Engineering Tsinghua University Beijing China Advanced Research Institute of Multidisciplinary Science Beijing Institute of Technology Beijing China Wireless and Computing Research Institute ZTE Corporation Beijing China Department of Electrical and Computer Engineering University of Houston Houston TX USA Faculty of Engineering and Applied Science Memorial University St. John's NL Canada School of Electronics and Computer Science University of Southampton Southampton U.K.

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Integrated sensing and communication (ISAC) is expected to be a promising technology in the sixth-generation (6G) wireless networks for its ability to alleviate resources shortage and excessive hardware expenses. One typical representative for ISAC waveforms is the orthogonal frequency division multiplexing (OFDM) waveform, which divides the time-frequency resources into orthogonal resource elements (REs). In order to satisfy their diverse design requirements and mitigate mutual interference, the communication and sensing subsystems can be assigned with different REs, which necessitates effective allocation strategies of different resources across time and frequency domains. In this article, a cross-domain multicarrier waveform design method-ology is proposed, which optimizes the RE assignment and power allocation strategies for the OFDM-based ISAC system. Specifically, for sensing performance enhancement, the unit cells of the ambiguity function (AF) of the sensing components are spe-cially shaped to achieve a “locally” perfect auto-correlation (AC) property within a predefined region of interest (RoI) in the Delay-Doppler domain. Afterwards, the irrelevant cells outside the RoI, which can determine the sensing power allocation strategy, are optimized alternatively with the communication power allocation strategy to maximize the throughput for the communication purpose. Numerical results demonstrate the superiority of the cross-domain multicarrier waveform design, which also provides useful guidelines for parameter settings of the proposed OFDM-based ISAC system.

关键词： Time-frequency analysis OFDM Design methodology Wireless networks Radar Interference Throughput

来源：评论

学校读者我要写书评

暂无评论

Applications of Artificial Intelligence in Solid Waste Management

Applications of Artificial Intelligence in Solid Waste Manag...

引用

Emerging Trends in engineering and Medical sciences (ICETEMS), International Conference on

作者： Gauri S. Deshmukh Praveen Kumar Derartment of Applied Chemistry Yeshwantrao Chavan College of Engineering Nagpur India Department of Computer Science and Medical Engineering Datta Meghe Institute of Higher Education and Research Wardha India

ISBN: (数字)9798331529352

ISBN: (纸本)9798331529390

researchers all over the world are exploring cutting-edge technologies to handle the issue of solid waste generation in municipal sector, which has increased significantly due to urbanization and fast population expansion. Artificial intelligence (AI) algorithms have been increasingly used to promote sustainable environmental development. The relevance of AI approaches in solid waste management (SWM) is reviewed and analyzed in this research paper, along with the benefits and downsides of several AI models. The use of AI across the whole SWM procedure, starting with waste creation to collection, transportation to ultimate disposal is also covered in this article. The paper also discusses the common AI algorithms employed for SWM along with their advantages and drawbacks. However, the development of AI techniques in this sector is constrained by the absence of trustworthy data and a defined benchmark to evaluate the effectiveness of accepted methodologies. The study also addresses the shortcomings and recommendations for future developments in AI methods for SWM, providing theoretical and practical guidance for future research.

关键词： Waste management Waste materials Solid modeling Reviews Urban areas Transportation Market research Artificial intelligence research and development Sorting

来源：评论

学校读者我要写书评

暂无评论

Quality of Experience Assessment of Online Server/Cloud Gaming 8

Quality of Experience Assessment of Online Server/Cloud Gami...

引用

8th Annual International Conference on Network and Information Systems for computers, ICNISC 2022

作者： Laghari, Asif Ali Laghari, Rashid Ali Khan, Asiya Sindh Madressatul Islam University Department of Computer Science Pakistan Harbin Institute of Technology Harbin China School of Engineering Computing and Mathematics University of Plymouth United Kingdom

ISBN: (纸本)9781665453516

Nowadays, gaming is very popular among the young generation, and game players use heterogeneous devices to play games from cloud/server and PC installation/mobile app. Better gaming can be considered as where the game runs smoothly, speedy, and quickly responds to the user's input. The game player and developer are unaware of how a better gaming experience will be achieved. In this paper, we used quality of experience (QoE) to assess the game experience of game players by using different ways of gaming such as PC installation, Mobile app, and online from server/cloud using both devices. The results show that the PC installation method provides a better QoE for both games, whereas, gaming online from server/cloud using both devices gave the worst user experience. © 2022 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Feature Correlation-Guided Knowledge Transfer for Federated Self-Supervised Learning

引用

IEEE Transactions on Neural Networks and Learning Systems 2025年第6期36卷 10544-10557页

作者： Yi Liu Song Guo Jie Zhang Yufeng Zhan Qihua Zhou Yingchun Wang Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong SAR China Beijing Institute of Technology Beijing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Huawei Technologies Company Ltd. Hangzhou China

Extensive attention has been paid to the application of self-supervised learning (SSL) approaches on federated learning (FL) to tackle the label scarcity problem. Previous works on federated SSL (FedSSL) generally fall into two categories: parameter-based model aggregation or data-based feature sharing to achieve knowledge transfer among multiple unlabeled clients. Despite the progress, they inevitably rely on some assumptions, such as homogeneous models or the existence of an additional public dataset, which hinder the universality of the training frameworks for more general scenarios (e.g., unlabeled clients with heterogeneous models). Therefore, in this article, we propose a novel and general method named federated self-supervised learning with feature-c orrelation-based aggregation (FedFoA) to tackle the above limitations. By exchanging feature correlation instead of model parameters or feature mappings, our approach reduces the discrepancies of local representations learning processes, thus promoting collaboration between heterogeneous clients. A factorization-based method is designed to extract the cross-feature relation matrix from local representations, which serves as a knowledge medium for the aggregation phase. We demonstrate that FedFoA is a heterogeneity-supportive and privacy-preserving training framework and can be easily compatible with state-of-the-art FedSSL methods. Extensive empirical experiments demonstrate our proposed approach outperforms the state-of-the-art methods by a significant margin.

关键词： Training Feature extraction Matrix decomposition Correlation Self-supervised learning Knowledge transfer Data models Vectors Electronic mail Collaboration

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：