检索结果-内蒙古大学图书馆

Deep learning methods for noisy sperm image classification from convolutional neural network to visual transformer:a comprehensive comparative study

引用

Intelligent Medicine 2024年第2期4卷 114-127页

作者： Ao Chen Chen Li Md Mamunur Rahaman Yudong Yao Haoyuan Chen Hechen Yang Peng Zhao Weiming Hu Wanli Liu Shuojia Zou Ning Xu Marcin Grzegorzek Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information EngineeringNortheastern UniversityShenyangLiaoning 110169China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA School of Arts and Design Liaoning Petrochemical UniversityFushunLiaoning 113001China Institute of Medical Informatics University of LübeckLüebeckGermany

Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of ***,the rapid development of deep learning(DL)has led to strong results in image classification ***,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA *** purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm *** The SVIA dataset is a publicly available large-scale sperm dataset containing three *** this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity *** investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise *** This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial *** particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based

关键词： computer-assisted sperm analysis Anti-noise Robustness Deep learning .Image classification Sperm image Conventional noise Adversarial attacks Convolutional neural network Visual transformer

来源：评论

学校读者我要写书评

暂无评论

Maximum Correntropy Criterion Kalman Filter for Indoor Quadrotor Navigation under Intermittent Measurements

arXiv

引用

arXiv 2023年

作者： Hadjiloizou, Loizos Makridis, Evagoras Charalambous, Themistoklis Deliparaschos, Kyriakos M. Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Electrical and Computer Engineering and Informatics Department Cyprus University of Technology Limassol Cyprus

We present a multisensor fusion framework for the onboard real-time navigation of a quadrotor in an indoor environment. The framework integrates sensor readings from an Inertial Measurement Unit (IMU), a camera-based object detection algorithm, and an Ultra-WideBand (UWB) localisation system. Often the sensor readings are not always readily available, leading to inaccurate pose estimation and hence poor navigation performance. To effectively handle and fuse sensor readings, and accurately estimate the pose of the quadrotor for tracking a predefined trajectory, we design a Maximum Correntropy Criterion Kalman Filter (MCC-KF) that can manage intermittent observations. The MCC-KF is designed to improve the performance of the estimation process when is done with a Kalman Filter (KF), since KFs are likely to degrade dramatically in practical scenarios in which noise is non-Gaussian (especially when the noise is heavy-tailed). To evaluate the performance of the MCC-KF, we compare it with a previously designed Kalman filter by the authors. Through this comparison, we aim to demonstrate the effectiveness of the MCC-KF in handling indoor navigation missions. The simulation results show that our presented framework offers low positioning errors, while effectively handling intermittent sensor measurements. Copyright © 2023, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Auto-Handover Gateway LoRaWAN based on Autonomous Vehicles

Auto-Handover Gateway LoRaWAN based on Autonomous Vehicles

引用

Information technology International Seminar (ITIS)

作者： Iwan Purnama Rahmadani Pane Adri Gabriel Sooai Firman Edi Ahmad Abdul Chamid Puput Dani Prasetyo Adi Department of Information Technology Faculty of Science and Technology Universitas Labuhanbatu Labuhanbatu Indonesia Department of Computer Engineering Faculty of Computer Science Universitas Katolik Widya Mandira Kupang NTT Indonesia Department of Engineering Management Faculty of Industrial Technology Batam Institute of Technology Batam City Indonesia Department of Informatics Engineering Muria Kudus University Kudus Indonesia Department of Telecommunication National Research and Innovation Agency (BRIN) Bandung Indonesia

ISBN: (数字)9798331521295

ISBN: (纸本)9798331521301

This article presents a simulation study on the use of LoRaWAN technology in autonomous vehicles. The research focuses on developing an Auto-Handover Gateway for Autonomous Vehicles, utilizing LoRaWAN parameters such as bit rates, spreading factor (SF), packet loss, and received signal strength. These parameters are tested in simulations of autonomous vehicle movements, which include both regular and random motion patterns. The aim is to assess the performance of LoRaWAN in different scenarios and its impact on communication in autonomous vehicle systems. The simulation results show several key trends. As the vehicle moves further, the spreading factor (SF) increases, and bit rates tend to decrease, indicating a drop in communication performance over longer distances. The research also identifies that the gateway with the closest proximity to the vehicle is selected, both in random and non-random movement scenarios. Additionally, packet loss increases as the distance between the vehicle and the gateway grows, highlighting the challenges of maintaining reliable communication over long distances. These findings provide insights into optimizing LoRaWAN parameters for real-time communication in autonomous vehicles, contributing to the development of intelligent vehicle networks.

关键词： Seminars Simulation Bit rate LoRaWAN Packet loss Logic gates Market research Real-time systems Reliability Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Dynamics of cold random hyperbolic graphs with link persistence

引用

Physical Review E 2022年第6期106卷 064312-064312页

作者： Sofoclis Zambirinis Harrison Hartle Fragkiskos Papadopoulos Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology 3036 Limassol Cyprus Network Science Institute Northeastern University Boston Massachusetts 02115 USA

We consider and analyze a dynamic model of random hyperbolic graphs with link persistence. In the model, both connections and disconnections can be propagated from the current to the next snapshot with probability ω∈[0,1). Otherwise, with probability 1−ω, connections are reestablished according to the random hyperbolic graphs model. We show that while the persistence probability ω affects the averages of the contact and intercontact distributions, it does not affect the tails of these distributions, which decay as power laws with exponents that do not depend on ω. We also consider examples of real temporal networks, and we show that the considered model can adequately reproduce several of their dynamical properties. Our results advance our understanding of the realistic modeling of temporal networks and of the effects of link persistence on temporal network properties.

关键词： Evolving networks Random graphs

来源：评论

学校读者我要写书评

暂无评论

A neural approach for detecting inline mathematical expressions from scientific documents

A neural approach for detecting inline mathematical expressi...

引用

作者： Madisetty, Sreekanth Maurya, Kaushal Kumar Aizawa, Akiko Desarkar, Maunendra Sankar Department of Computer Science and Engineering Indian Institute of Technology Hyderabad HyderabadTelangana502285 India National Institute of Informatics The University of Tokyo Tokyo Japan

Scientific documents generally contain multiple mathematical expressions in them. Detecting inline mathematical expressions are one of the most important and challenging tasks in scientific text mining. Recent works that detect inline mathematical expressions in scientific documents have looked at the problem from an image processing perspective. There is little work that has targeted the problem from NLP perspective. Towards this, we define a few features and applied Conditional Random Fields (CRF) to detect inline mathematical expressions in scientific documents. Apart from this feature based approach, we also propose a hybrid algorithm that combines Bidirectional Long Short Term Memory networks (Bi-LSTM) and feature-based approach for this task. Experimental results suggest that this proposed hybrid method outperforms several baselines in the literature and also individual methods in the hybrid approach. © 2020 John Wiley & Sons, Ltd

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Semantic Data Representation for Explainable Windows Malware Detection Models

arXiv

引用

arXiv 2024年

作者： Švec, Peter Balogh, Štefan Homola, Martin Kľuka, Ján Bisták, Tomáš Institute of Computer Science and Mathematics Faculty of Electrical Engineering and Information Technology Slovak University of Technology Ilkovičova 3 Bratislava Slovakia Department of Applied Informatics Faculty of Mathematics Physics and Informatics Comenius University in Bratislava Mlynská dolina Bratislava Slovakia

Ontologies are a standard tool for creating semantic schemata in many knowledge intensive domains of human interest. They are becoming increasingly important also in the areas that have been until very recently dominated by subsymbolic knowledge representation and machine-learning (ML) based data processing. One such area is information security, and specifically, malware detection. We thus propose PE Malware Ontology that offers a reusable semantic schema for Portable Executable (PE – the Windows binary format) malware files. This ontology is inspired by the structure of the EMBER dataset, which focuses on the static malware analysis of PE files. With this proposal, we hope to provide a unified semantic representation for the existing and future PE-malware datasets and facilitate the application of symbolic, neuro-symbolic, or otherwise explainable approaches in the PE-malware-detection domain, which may produce interpretable results described by the terms defined in our ontology. In addition, we also publish semantically treated EMBER data, including fractional datasets, to support the reproducibility of experiments on EMBER. We supplement our work with a preliminary case study, conducted using concept learning, to show the general feasibility of our approach. While we were not able to match the precision of the state-of-the-art ML tools, the learned malware discriminators were interesting and highly interpretable. Copyright © 2024, The Authors. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Maximum Correntropy Criterion Kalman Filter for Indoor Quadrotor Navigation under Intermittent Measurements

Maximum Correntropy Criterion Kalman Filter for Indoor Quadr...

引用

Mediterranean Conference on Control and Automation (MED)

作者： Loizos Hadjiloizou Evagoras Makridis Themistoklis Charalambous Kyriakos M. Deliparaschos Department of Intelligent Systems KTH Royal Institute of Technology Stockholm Sweden Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Electrical and Computer Engineering and Informatics Department Cyprus University of Technology Limassol Cyprus

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Hospital Readmissions Using Logistic Regression and IoT Sensor Data 6

Predictive Analytics for Hospital Readmissions Using Logisti...

引用

6th International Conference on Energy, Power and Environment, ICEPE 2024

作者： Kiruthiga, B. Riazulhameed, Arshadh Ariff Mohamed Abuthahir Rajapriya, M. Sarasu, R. Mohankumar, N. Kasthuri, A. Srm Valliammai Engineering College Department of Management Studies Tamil Nadu Chennai India Blackstraw Technologies Pvt Ltd Tamil Nadu Chennai India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Management Studies Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Spatial Informatics Tamil Nadu Chennai India Maharashtra Nagpur India Vinayaka Mission's Kirupananda Variyar Engineering College Department of Computer Science and Engineering Tamil Nadu Salem India

ISBN: (纸本)9798350379297

Hospital readmissions affect healthcare systems globally, increasing costs and morbidity. Readmissions must be predicted and prevented to improve patient outcomes and save healthcare costs. This research leverages the Internet of Things (IoT) sensor data and Logistic Regression (LR) to reduce hospital readmissions using predictive analytics. Patient health data from IoT devices during and after hospitalization is used in the paper. Heart rate, blood pressure, and oxygen saturation are constantly monitored. LR is used to examine this dataset and create a prediction model. The LR algorithm trains us to recognize IoT sensor data patterns and correlations that indicate readmission risks. Our methodology provides developed risk estimates incorporating patient-specific parameters, including age, multiple illnesses, and medical history. The temporal data permits dynamic predictions, considering patient health changes over time. This research detected hospital readmission risk with promising accuracy. These predictions allow healthcare practitioners to proactively intervene and deliver targeted treatments, including prescription modifications, lifestyle advice, and follow-up consultations to decrease readmission. This proactive strategy may improve patient outcomes and save healthcare expenses. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

arXiv

引用

arXiv 2024年

作者： Pfeiffer, Kilian Balaskas, Konstantinos Siozios, Kostas Henkel, Jörg Embedded Systems Karlsruhe Institute of Technology Karlsruhe76131 Germany Department of Computer Engineering and Informatics University of Patras Patras26504 Greece Department of Physics Aristotle University of Thessaloniki Thessaloniki54124 Greece

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped from the collaborative training. However, dropping devices in FL can degrade training accuracy and introduce bias or unfairness. Several works have tackled this problem on an algorithm level, e.g., by letting constrained devices train a subset of the server neural network (NN) model. However, it has been observed that these techniques are not effective w.r.t. accuracy. Importantly, they make simplistic assumptions about devices’ resources via indirect metrics such as multiply accumulate (MAC) operations or peak memory requirements. We observe that memory access costs (that are currently not considered in simplistic metrics) have a significant impact on the energy consumption. In this work, for the first time, we consider on-device accelerator design for FL with heterogeneous devices. We utilize compressed arithmetic formats and approximate computing, targeting to satisfy limited energy budgets. Using a hardware-aware energy model, we observe that, contrary to the state of the art’s moderate energy reduction, our technique allows for lowering the energy requirements (by 4×) while maintaining higher accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Classifying Upper Extremity Motor Function Using Deep Learning and Third-Person Video Data

Classifying Upper Extremity Motor Function Using Deep Learni...

引用

IEEE International Conference on Big Data

作者： Tan Tran Lin-Ching Chang Peter Lum Department of Electrical Engineering and Computer Science The Catholic University of America Washington DC USA Department of Informatics New Jersey Institute of Technology Newark NJ USA Department of Biomedical Engineering The Catholic University of America Washington DC USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Post-stroke rehabilitation of upper extremity (UE) motor function is essential. Despite the widespread use of UE rehabilitation in clinical settings, assessing the success of these treatments is challenging. Methods for evaluating UE motor function include task performance under clinical supervision, patient self-reports, and data analysis from wearable devices equipped with accelerometers and gyroscopes. In prior research, we demonstrated that machine learning and deep learning models using data from a single wrist-worn accelerometer sensor could accurately differentiate between functional and non-functional UE movements in stroke patients. To overcome the limitations of single wrist-worn accelerometer sensors – challenges in capturing the full context of functional movements – this study presents a new deep learning (DL) based framework designed to classify functional and non-functional arm movements in videos captured from a conventional camera. The system is entirely automated and comprises two DL networks. The first network performs human pose estimation, extracting 2D pose key points of the paretic arm(s) and torso on 2-second sequences of the frames. The second network then uses these 2D pose landmarks to classify the movement sequence as functional or non-functional. This system offers two key benefits for rehabilitation. First, it can automatically generate initial annotations for video frames, significantly reducing the time needed for manual labeling. Second, analyzing the effectiveness of UE rehabilitation through third-person videos allows for objective outcome measurement of UE treatments in stroke survivors' home environments.

关键词： Deep learning Accelerometers Torso Pose estimation Manuals Stroke (medical condition) Motors Cameras Wearable devices Videos

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：