检索结果-内蒙古大学图书馆

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

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.

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

Contemporary Approach of Additive Manufacturing for Sustainable Products in the Era of Circular Economy 8th

Contemporary Approach of Additive Manufacturing for Sustaina...

引用

8th EAI International Conference on Management of Manufacturing Systems, MMS 2023

作者： Knapčíková, Lucia Behúnová, Annamária Tauberová, Rebeka Kaščak, Jakub Husár, Jozef The Technical University of Košice Faculty of Manufacturing Technologies with a seat in Prešov Department of Industrial Engineering and Informatics Prešov Slovakia Technical University of Kosice Faculty of Mining Ecology Process Control and Geotechnologies Institute of Earth Resources Kosice Slovakia The Technical University of Košice Faculty of Manufacturing Technologies with a seat in Prešov Department of Computer Aided Manufacturing Technology Prešov Slovakia

ISBN: (纸本)9783031531606

Considering the need for mass customization in Industry 4.0, it is necessary to develop non-traditional production methods. Therefore, additive manufacturing can become a key technology for the production of customized products thanks to its ability to create irregular objects or shapes. In addition to enabling new design possibilities, the additive manufacturing method holds promise for increasing social, economic, and environmental sustainability. It also has the potential to reduce energy consumption and lower polymer material consumption. Additive manufacturing contrasts with conventional processes, as it consists in applying materials layer by layer. Conventional manufacturing operations produce polymer waste that is difficult to reintroduce into manufacturing processes. The aim of the contribution is the possibility of using additive manufacturing in the design and processing of new effective use of the product with regard to the environmental aspect. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Resilient Routing Table Computation Based on Connectivity Preserving Graph Sequences

Resilient Routing Table Computation Based on Connectivity Pr...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： János Tapolcai Péter Babarczi Pin-Han Ho Lajos Rónyai Department of Telecommunications and Media Informatics Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary Deptartment of Electrical and Computer Engineering University of Waterloo Canada Eötvös Loránd Research Network and Department of Algebra Institute for Computer Science and Control Institute of Mathematics Budapest University of Technology and Economics Budapest Hungary

Fast reroute (FRR) mechanisms that can instantly handle network failures in the data plane are gaining attention in packet-switched networks. In FRR no notification messages are required as the nodes adjacent to the failure are prepared with a routing table such that the packets are re-routed only based on local information. However, designing the routing algorithm for FRR is challenging because the number of possible sets of failed network links and nodes can be extremely high, while the algorithm should keep track of which nodes are aware of the failure. In this paper, we propose a generic algorithmic framework that combines the benefits of Integer Linear Programming (ILP) and an effective approach from graph theory related to constructive graph characterization of k-connected graphs, i.e., edge splitting-off. We illustrate these benefits through arborescence design for FRR and show that (i) due to the ILP we have great flexibility in defining the routing problem, while (ii) the problem can still be solved very fast. We demonstrate through simulations that our framework outperforms state-of-the-art FRR mechanisms and provides better resilience with shorter paths in the arborescences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Feasibility of direct quantum communications between the UK and Ireland via 224 km of underwater fibre

Feasibility of direct quantum communications between the UK ...

引用

British and Irish Conference on Optics and Photonics, BICOP 2023

作者： Amies-Kin, Ben Schatz, Karolina P. Duan, Haofan Biswas, Ayan Bailey, Jack Felvinti, Adrian Winward, Jaimes Dixon, Mike Minder, Mariella Kumar, Rupesh Albosh, Sophie Lucamarini, Marco School of Physics Engineering and Technology York Centre for Quantum Technologies Institute for Safe Autonomy University of York YorkYO10 5FT United Kingdom EuNetworks Fiber UK Limited 5 Churchill Place LondonE14 5HU United Kingdom Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Limassol3036 Cyprus

Quantum key distribution is required for unconditionally secure communications against an eavesdropper with a powerful quantum computer. We present the first QKD feasibility study over long-haul submarine fibre, betwe... 详细信息

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

A Cloud-based Distributed Computing Approach for Extracting Molecular Descriptors 6

A Cloud-based Distributed Computing Approach for Extracting ...

引用

6th International Conference on Algorithms, Computing and Systems, ICACS 2022

作者： Didachos, Christos Kintos, Dionisis Panagiotis Fousteris, Manolis Gerogiannis, Vassilis C. Son, Le Hoang Kanavos, Andreas Department of Computer Engineering & Informatics University of Patras Patras Greece Department of Pharmacy Laboratory of Medicinal Chemistry University of Patras Patras Greece Department of Digital Systems University of Thessaly Larissa Greece Vnu Information Technology Institute Vietnam National University Hanoi Viet Nam Department of Informatics Ionian University Corfu Greece

ISBN: (纸本)9781450397407

Feature extraction is an initial and essential part for the development of accurate predictive machine learning classifiers. In the research field of drug discovery and development, the usage of molecular descriptors, which can be defined as mathematical representations of molecules' chemical properties, is a challenging task not only for machine learning studies but even for "classical wet lab"approaches. However, a high diversity of these descriptors is required in order to exploit all the available knowledge and, consequently, to maximize the potentially predictive power of approaches that could be applied for the discovery of new bioactive compounds against one or more molecular targets. Furthermore, the representation and normalization of these information is considered a rather time-consuming process. Herein, we present an approach that employs the power of cloud and distributing computing for the extraction, processing and representation of big datasets, leading to the generation of molecular descriptors in a reasonable time frame. © 2022 ACM.

关键词： Big data

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：