检索结果-内蒙古大学图书馆

Dynamic Multi-Layer Perceptron for Fetal Health Classification Using Cardiotocography Data

computers, Materials & Continua 2024年第8期80卷 2301-2330页

作者： Uddagiri Sirisha Parvathaneni Naga Srinivasu Panguluri Padmavathi Seongki Kim Aruna Pavate Jana Shafi Muhammad Fazal Ijaz Department of Computer Science and Engineering Prasad V Potluri Siddhartha Institute of TechnologyVijayawada520007India Amrita School of Computing Amrita Vishwa VidyapeethamAmaravatiAndhra Pradesh522503India Department of Tele informatics Engineering Federal University of CearáFortaleza60455-970Brazil Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramGunturAndhra Pradesh522302India Department of Computer Engineering Chosun UniversityGwangju61452Republic of Korea School of CSIT Symbiosis Skills and Professional UniversityPune412101India Department of Computer Engineering and Information College of Engineering inWadi AlddawasirPrince Sattam bin Abdulaziz UniversityWadi Alddawasir11991Saudi Arabia School of IT and Engineering Melbourne Institute of TechnologyMelbourne3000Australia

Fetal health care is vital in ensuring the health of pregnant women and the *** check-ups need to be taken by the mother to determine the status of the fetus’growth and identify any potential *** know the status of the fetus,doctors monitor blood reports,Ultrasounds,cardiotocography(CTG)data,***,in this research,we have considered CTG data,which provides information on heart rate and uterine contractions during *** researchers have proposed various methods for classifying the status of fetus *** processing of CTG data is time-consuming and ***,automated tools should be used to classify fetal *** study proposes a novel neural network-based architecture,the Dynamic Multi-Layer Perceptron model,evaluated from a single layer to several layers to classify fetal *** strategies were applied,including pre-processing data using techniques like Balancing,Scaling,Normalization hyperparameter tuning,batch normalization,early stopping,etc.,to enhance the model’s performance.A comparative analysis of the proposed method is done against the traditional machine learning models to showcase its accuracy(97%).An ablation study without any pre-processing techniques is also *** study easily provides valuable interpretations for healthcare professionals in the decision-making process.

关键词： Fetal health cardiotocography data deep learning dynamic multi-layer perceptron feature engineering

来源：评论

学校读者我要写书评

暂无评论

An overview of the spatiotemporal patterns of land displacements in Western Greece 15

An overview of the spatiotemporal patterns of land displacem...

引用

Earth Resources and Environmental Remote Sensing/GIS Applications XV 2024

作者： Fasoulis, Konstantinos Orfanoudakis, Michalis Hadjidoukas, Panagiotis Pappas, Christoforos Department of Civil Engineering University of Patras Patras265 04 Greece Department of Computer Engineering and Informatics University of Patras Patras265 04 Greece

ISBN: (纸本)9781510681026

Understanding and monitoring geohazards, including not only abrupt phenomena but also gradual land displacements, is of key scientific importance with socioeconomic implications. Satellite remote sensing techniques, such as Interferometric Synthetic Aperture Radar (InSAR), allow for detailed estimation of land displacements. Here, we focused on the area of Western Greece, characterized by numerous faults and high seismicity, and we quantified the spatiotemporal patterns of land displacements across the study domain from 2018 to 2022. We used the Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) technique to process Sentinel-1 InSAR data following the Stanford Method for Persistent Scatterer (StaMPS) workflow. Vertical and horizontal land displacements across the study area were estimated and compared with estimates from the European Ground Motion Service (EGMS). The magnitude of these displacements was further scrutinized at the annual and sub-annual time scale by examining the EGMS-derived time series of vertical and horizontal land motion at selected areas with critical infrastructures. The increasing availability of InSAR data, in tandem with advancements and ease in data handling and processing, facilitate the deployment of such remote sensing techniques, and, when combined with observations from ground networks, could assist towards comprehensive monitoring of land processes and infrastructures. © 2024 SPIE.

关键词： Interferometric synthetic aperture radar Deformation Satellites Bridges Data processing Synthetic aperture radar Earthquakes Remote sensing Satellite navigation systems Statistical analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection 7

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

7th International Congress on Ambient Intelligence, Software engineering, and e-Health and Mobile Health, AmITIC 2024

作者： Jiménez-Delgado, E. Quesada-López, C. Méndez-Porras, A. Lara-Petitdemange, A. Alfaro-Velasco, J. Graduate Program in Computer Science and Informatics University of Costa Rica Costa Rica Technological Institute of Costa Rica Computer Engineering Department Costa Rica School of Computer Science and Informatics University of Costa Rica Costa Rica

ISBN: (纸本)9798350364538

In this study, two deep learning models for automatic tattoo detection were analyzed;a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Model-to-Circuit Cross-Approximation for Printed Machine Learning Classifiers

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2023年第11期42卷 3532-3544页

作者： Armeniakos, Giorgos Zervakis, Georgios Soudris, Dimitrios Tahoori, Mehdi B. Henkel, Jorg Karlsruhe Institute of Technology Karlsruhe76131 Germany National Technical University of Athens School of Electrical and Computer Engineering Athens15780 Greece University of Patras Computer Engineering and Informatics Department Patras26504 Greece Karlsruhe Institute of Technology Department of Computer Science Karlsruhe76131 Germany

Printed electronics (PEs) promises on-demand fabrication, low nonrecurring engineering costs, and subcent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to improve the efficiency of emerging PE machine learning (ML) applications. Nevertheless, large feature sizes in PE prohibit the realization of complex ML models in PE, even with bespoke architectures. In this work, we present an automated, cross-layer approximation framework tailored to bespoke architectures that enable complex ML models, such as multilayer perceptrons (MLPs) and support vector machines (SVMs), in PE. Our framework adopts cooperatively a hardware-driven coefficient approximation of the ML model at algorithmic level, a netlist pruning at logic level, and a voltage overscaling at the circuit level. Extensive experimental evaluation on 12 MLPs and 12 SVMs and more than 6000 approximate and exact designs demonstrates that our model-to-circuit cross-approximation delivers power and area optimal designs that, compared to the state-of-the-art exact designs, feature on average 51% and 66% area and power reduction, respectively, for less than 5% accuracy loss. Finally, we demonstrate that our framework enables 80% of the examined classifiers to be battery-powered with almost identical accuracy with the exact designs, paving thus the way toward smart complex printed applications. © 1982-2012 IEEE.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

Factors influencing the adoption of awareness-raising activities in SMEs 10

Factors influencing the adoption of awareness-raising activi...

引用

10th International Conference on Socio-Technical Perspectives in Information Systems, STPIS 2024

作者： Bergström, Erik Kävrestad, Joakim Gustafsson, Johannes Hou Jonsson, Hannes Department of Computer Science and Informatics School of Engineering Jönköping University Jönköping Sweden

Information security incidents are most commonly caused by user behaviour, placing the user in focus. In order to mitigate information security threats and thereby protect the organisation, more and more are adopting a socio-technical viewpoint, which implies adopting the belief that information security cannot be solved with technology alone. A common way to address the user is by adopting awareness-raising activities. All types of organisations struggle to raise awareness. Several studies have pointed out small and medium-sized enterprises (SMEs) as being extra vulnerable and, in addition, having more issues adopting awareness-raising activities. There are few studies investigating factors influencing the adoption of awareness-raising activities in general, and the body of literature is even more scarce when focusing on the factors from an SME perspective. This study targets the gap by investigating what factors influence the adoption of awareness-raising activities in SMEs. We did this by conducting a semi-structured interview study in 10 organisations. Five factors with a total of seven sub-factors were found: Resources (with the sub-factors time and cost), implementation, content (with the sub-factors quality, adaptability, and comprehensibility), compliance, management (with the sub-factors management support and motivation of the employees). © 2024 Copyright for this paper by its authors.

关键词： Information hiding

来源：评论

学校读者我要写书评

暂无评论

Classification and Regression Trees (CART) Method in the Classification Process of Blood Control Candidates 9

Classification and Regression Trees (CART) Method in the Cla...

引用

9th International Conference on Wireless and Telematics, ICWT 2023

作者： Ramdania, Diena Rauda Slamet, Cepy Lutfiyah, Hasna Fairuz Irfan, Mohamad Zulfikar, Wildan Budiawan Harika, Maisevli Uin Sunan Gunung Djati Department of Informatics Bandung Indonesia Politeknik Negeri Bandung Computer Engineering and Informatics Department Bandung Indonesia

ISBN: (纸本)9798350305029

The classification of blood donor candidates is a crucial process that requires thorough health checks and assessments. Implementing a reliable and efficient classification system for blood donor candidates is essential to ensure the safety and well-being of both the donor and the recipient. This study focuses on implementing the Classification and Regression Trees (CART) method in the classification process of blood control candidates. Given the complex series of health checks involved in the process, which includes age, weight, blood pressure, pulse rate, and blood tests (hemoglobin, blood type, and rhesus), a reliable and efficient classification system is necessary. This research demonstrates the successful implementation of the CART method in developing an expert classification system for blood donor candidates. The system achieved an accuracy value of 98.03%, making it a highly effective and reliable tool for improving blood control candidate classification accuracy and efficiency. This research has significant implications for enhancing the safety and success of blood transfusions. © 2023 IEEE.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

PartSeg v2: Bioimage Segmentation Using Advanced Deep Learning Techniques 4th

PartSeg v2: Bioimage Segmentation Using Advanced Deep Learni...

引用

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

作者： Bokota, Grzegorz Basu, Subhadip Sroka, Jacek Insititute of Informatics University of Warsaw Warsaw Poland Department of Computer Science and Engineering Jadavpur University Kolkata India

ISBN: (纸本)9789819726134

In this paper, we present a new version of our bioimaging tool PartSeg. It allows integration of deep learning models from the Bioimage Model Zoo, which is a community-driven AI model repository. We also show how PartSeg’s power users can train such models, for example, to increase automatization of their data processing workflows. Then, we present further new features of PartSeg that make it easier to publish datasets in a durable and referencable way with version tracking. We also describe good practices related to data publishing and how adding metadata can allow for easier data discovery. Availability of such published datasets enables development of even better machine learning models. Publishing of the data is also a requirement for verifiable and repeatable science, leads to greater visibility of the results and enables cooperation and cross-domain exchange of ideas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Bioimaging

来源：评论

学校读者我要写书评

暂无评论

Transient events during photic driving in single-trial EEG within the second harmonics 46

Transient events during photic driving in single-trial EEG w...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Oppermann, Hannes Haueisen, Jens Technische Universität Ilmenau Insititute of Biomedical Engineering and Informatics Department of Computer Science and Automation Ilmenau Germany

ISBN: (纸本)9798350371499

Intermittent photic stimulation (IPS) is a commonly used activation method in clinical applications, e.g. epilepsy, but also used in research for investigating excitability states in the brain. Effects in the brain followed by IPS are also known as photic driving response. These effects are usually characterized using averaged data. Here, we used single-trial analysis to determine photic driving effects at the second harmonics of the stimulation *** rest and auditory-visual stimulation, 64-channel EEG data were recorded with eyes closed. The visual stimulation included eight stimulation frequencies within the alpha and beta bands. A complex Morlet wavelet was used for time-frequency (TF) analysis. Bursts within the TF representations were then detected and characterized by number, frequency, and power near the second *** observed bursts close to the second harmonic of each stimulation frequency. The number of these events increased during stimulation and the main frequencies were shifted towards the second harmonics. Similarly, the power increased at all but one *** new single-trial analysis during IPS could lead to a better understanding of the photic driving effects in the brain and, in particular, the generation mechanisms with regard to the occurrence of effects in the harmonics and sub-harmonics. © 2024 IEEE.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

Binary to Decimal Conversion and Subnetting Calculations using Augmented Reality 9

Binary to Decimal Conversion and Subnetting Calculations usi...

引用

9th IEEE International Conference on Computing, engineering and Design, ICCED 2023

作者： Ramdania, Diena Rauda Alam, Cecep Nurul Ghuswari, Afif Hani Irfan, Mohamad Atmadja, Aldy Rialdy Harika, Maisevli UIN Sunan Gunung Djati Department of Informatics Bandung Indonesia Politeknik Negeri Bandung Computer Engineering and Informatics Department Bandung Indonesia

ISBN: (纸本)9798350370126

This paper studies markerless augmented reality applications for displaying digital objects on different colored surfaces under varying lighting conditions and tracking angles. The study aimed to evaluate the application's effectiveness in accurately displaying digital objects. The testing was conducted in bright and dark light settings, with tracking angles of 45° and 90°. The results showed that surfaces with a texture in dark or bright colors, especially patterned surfaces, yielded optimal results in displaying digital objects in both lighting conditions. However, plain bright surfaces and surfaces without patterns were not practical for displaying digital objects. The angle of the tracking device and the presence of shadows significantly impacted the quality of the displayed objects. The tracking distance did not significantly affect the display quality. These findings provide valuable insights for enhancing the performance and usability of markerless augmented reality applications, guiding the selection of suitable surfaces and lighting conditions for optimal display outcomes. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

LSTM-XGBoost: An Ensemble Model for Blood Demand Distribution Forecasting – A Case Study in Zakho City, Kurdistan Region, Iraq

引用

Operations Research Forum 2025年第1期6卷 1-22页

作者： Zebari, Rizgar R. Zebari, Gheyath M. Al-zebari, Adel Mohammed, Marwan Aziz Department of Computer Science College of Science Knowledge University Erbil 44001 Iraq Department of Information Technology Technical College of Informatics Akre University for Applied Sciences Kurdistan Akre Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil 44001 Iraq

A safe and adequate blood supply is essential for healthcare systems to function effectively. Accurately forecasting blood demand plays a key role in efficient inventory management and resource allocation. Traditional forecasting methods, like moving averages and ARIMA models, often fall short due to the complexity of factors influencing blood demand. This study introduces an innovative hybrid ensemble model that combines Long Short-Term Memory (LSTM) networks with XGBoost, harnessing their combined strengths to enhance forecasting accuracy. By analyzing blood donation data from the Zakho Blood Bank (January 1, 2015—July 22, 2022), the model outperforms individual LSTM and XGBoost models, excelling in metrics such as Mean Square Error (MSE) and Mean Absolute Error (MAE). These findings underscore the potential of advanced machine learning techniques to improve healthcare supply chain management and ensure the timely availability of critical blood supplies. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Blood banking Blood demand forecasting Healthcare supply chain LSTM network Machine learning XGBoost

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：