检索结果-内蒙古大学图书馆

The STIRData Approach to Interoperability of European Company High-Value Datasets

SN computer Science 2024年第4期5卷 387页

作者： Klímek, Jakub Chortaras, Alexandros Míšek, Jakub Yang, Jim J. Skagemo, Steinar Tzouvaras, Vassilis Department of Software Engineering Faculty of Mathematics and Physics Charles University Malostranské nám. 25 Prague 118 00 Czech Republic School of Electrical and Computer Engineering National Technical University of Athens 9 Iroon Polytechniou St Athens 157 80 Greece Institute of Law and Technology Masaryk University Faculty of Law Veveří 70 Brno 60200 Czech Republic Norwegian Digitalisation Agency Postboks 1382 Vika Oslo 0114 Norway Brønnøysund Register Centre Postboks 900 Brønnøysund 8910 Norway

The European Commission has published a list of high-value datasets (HVDs) that public sector bodies must make available as open data as part of the Open Data Directive. One of the HVD topics is company data. Although the HVD description contains items that must be included in these datasets, it does not prescribe any technical means of how the data should be published. This is a major obstacle to the interoperability of the datasets once they are published. In this extended paper, we elaborate on the results of STIRData, a project co-financed by the Connecting Europe Facility Programme of the European Union, focusing on various aspects of data interoperability of open data from business registries, covering the company data HVDs topic. These aspects include the semantic, technical, and legal interoperability of this data. The results include a data architecture and a data specification to make the published data technically and semantically interoperable. In addition, we present basic legal interoperability guidelines to ensure legal interoperability of the published data, which is a topic often neglected by technically focused data experts. The project results include proof-of-concept transformations of data from selected European business registries using open source tools and in accordance with the data specification. Moreover, a user-orientated platform for browsing and analysing the data is presented as an example of the possibilities of using the data published in an interoperable way. Finally, we present an example of how compliant data can be processed by data experts for further analysis. © The Author(s) 2024.

关键词： Company data Data spaces High-value datasets (HVDs) Interoperability Linked data Open data

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Human Knee Abnormality Detection Based on Surface EMG Signals

Deep Learning Networks for Human Knee Abnormality Detection ...

引用

International Conference on Telecommunications and Signal Processing (TSP)

作者： Sakorn Mekruksavanich Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350365597

ISBN: (纸本)9798350365603

Early knee problem management relies on precise identification and classification of abnormalities. Surface electromyography (sEMG) and goniometer signals offer non-invasive screening for muscle activity and joint angle patterns, yet their complexity poses challenges in extracting critical diagnostic information. This paper proposes a novel deep-learning method using sEMG and goniometer data for knee abnormality diagnosis. The proposed ResNeXt model, employing CNNs and multi-kernel modules, is evaluated on the UCIEMG dataset. Experimental results demonstrate ResNeXt's superior accuracy, precision, recall, and F1-score compared to baseline models (CNN and LSTM). Res NeXt achieves the best performance with combined EMG and goniometer data, reaching 96.37% accuracy and 93.77% F1-score, with fewer trainable parameters, indicating computational efficiency. The findings indicate ResNeXt's effectiveness in identifying knee abnormalities using biosensor data, particularly sEM G and goniometer signals, aiding early disease detection and treatment.

关键词： Deep learning Accuracy Goniometers Signal processing Muscles Electromyography Telecommunications Surface treatment Long short term memory Diseases

来源：评论

学校读者我要写书评

暂无评论

PARTITIONS AND ELEMENTARY SYMMETRIC POLYNOMIALS - AN EXPERIMENTAL APPROACH

arXiv

引用

arXiv 2024年

作者： Ballantine, Cristina Beck, George Merca, Mircea Department of Mathematics and Computer Science College of the Holy Cross WorcesterMA01610 United States Department of Mathematics and Statistics Dalhousie University HalifaxNSB3H 4R2 Canada Department of Mathematical Methods and Models Fundamental Sciences Applied in Engineering Research Center University Politehnica of Bucharest BucharestRO-060042 Romania

Given a partition λ, we write ej(λ) for the jth elementary symmetric polynomial ej evaluated at the parts of λ and ejpA(n) for the sum of ej(λ) as λ ranges over the set of partitions of n with parts in A. For ejpA(n), we prove analogs of the classical formula for the partition function, (formula presented), where σ1 is the sum of divisors function. We prove several congruences for e2p4(n), the sum of e2 over the set of partitions of n into four parts. Define the function prej(λ) to be the multiset of monomials in ej(λ), which is itself a partition. If A is a set of partitions, we define prej(A) to be the set of partitions prej(λ) as λ ranges over A. If P(n) is the set of all partitions of n, we conjecture that the number of odd partitions in pre2(P(n)) is at least the number of distinct partitions. We prove some results about pre2(B(n)), where B(n) is the set of binary partitions of n. We conclude with conjectures on the log-concavity of functions related to ejp(n), the sum of ej(λ) for all λ ∈ P(n).MSC Codes 05E05, 11P81 © 2024, CC BY.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

On "Inconsistencies of metalens performance and comparison with conventional diffractive optics"

arXiv

引用

arXiv 2024年

作者： Arbabi, Amir Faraon, Andrei Department of Electrical and Computer Engineering University of Massachusetts Amherst AmherstMA United States T. J. Watson Laboratory of Applied Physics Kavli Nanoscience Institute California Institute of Technology PasadenaCA United States

It was recently claimed1 that reported focusing efficiency values of high numerical aperture metalenses are inconsistent with a theoretical bound, and their measurement results are incorrectly interpreted. We review t... 详细信息

关键词： Diffractive optics

来源：评论

学校读者我要写书评

暂无评论

Design of a Temperature Controller for an Oven

Design of a Temperature Controller for an Oven

引用

International Symposium for Design and Technology of Electronics Packages (SIITME)

作者： Cristian Farcas Ionuţ Ciocan Adrian Tulbure Violeta Olar Adrian Szoke Department of Applied Electronics Technical University of Cluj-Napoca Cluj-Napoca Romania Department of Informatics Mathematics and Electronics ”1 Decembrie 1918” University of Alba Iulia Alba Iulia Romania Department of Electrical Engineering University of Oradea Oradea Romania

This paper describes the design and implementation of an automatic temperature control system. The developed temperature controller is designed to control temperature in an oven. The temperature can be controlled manually or automatically with a temperature profile imposed by the user. A bi-positional controller is implemented for temperature control. In manual mode, the user will select the set-point and the upper and lower limits. The control system will maintain the temperature within the prescribed limits. In automatic mode, the user can select a temperature profile, and the control system will impose that the temperature follows the prescribed temperature profile.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Singular Value Perturbation and Deep Network Optimization

arXiv

引用

arXiv 2022年

作者： Riedi, Rudolf H. Balestriero, Randall Baraniuk, Richard G. Mathematics Department HES-SO The University of Applied Sciences of Western Switzerland Fribourg Switzerland Meta AI FAIR NYC United States Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States

We develop new theoretical results on matrix perturbation to shed light on the impact of architecture on the performance of a deep network. In particular, we explain analytically what deep learning practitioners have long observed empirically: the parameters of some deep architectures (e.g., residual networks, ResNets, and Dense networks, DenseNets) are easier to optimize than others (e.g., convolutional networks, ConvNets). Building on our earlier work connecting deep networks with continuous piecewise-affine splines, we develop an exact local linear representation of a deep network layer for a family of modern deep networks that includes ConvNets at one end of a spectrum and ResNets, DenseNets, and other networks with skip connections at the other. For regression and classification tasks that optimize the squared-error loss, we show that the optimization loss surface of a modern deep network is piecewise quadratic in the parameters, with local shape governed by the singular values of a matrix that is a function of the local linear representation. We develop new perturbation results for how the singular values of matrices of this sort behave as we add a fraction of the identity and multiply by certain diagonal matrices. A direct application of our perturbation results explains analytically why a network with skip connections (such as a ResNet or DenseNet) is easier to optimize than a ConvNet: thanks to its more stable singular values and smaller condition number, the local loss surface of such a network is less erratic, less eccentric, and features local minima that are more accommodating to gradient-based optimization. Our results also shed new light on the impact of different nonlinear activation functions on a deep network's singular values, regardless of its architecture. © 2022, CC BY-NC-SA.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Hybrid Attention with CNN-BiLSTM and CBAM for Efficient Wearable Activity Recognition

Hybrid Attention with CNN-BiLSTM and CBAM for Efficient Wear...

引用

International ECTI Northern Section Conference on electrical, Electronics, computer and Telecommunications engineering (ECTI-NCON)

作者： Sakorn Mekruksavanich Ponnipa Jantawong Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Applied Statistics Faculty of Applied Science Research Group in Statistical Learning and Inference King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut’s University of Technology North Bangkok Bangkok Thailand

The use of widespread sensors for automatic activity recognition has become a dynamic area of research due to its broad applications in healthcare, fitness monitoring, and assisted living. To efficiently identify daily and sports activities from sensor data, this study suggests a hybrid deep learning model that integrates convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM) networks, and convolutional block attention modules (CBAM). The model starts by extracting spatial features from the sensor data using CNN layers. These spatial features are then employed to offer temporal context information to the BiLSTM network. To conclude, the CBAM attention mechanism is applied to guide the model’s focus to the most informative segments of the BiLSTM feature maps. This approach enables the accurate recognition of patterns in both complex and daily sports activities. The effectiveness of the proposed hybrid model is evaluated using the UCI-DSA, a publicly available benchmark dataset that includes sports and daily activities collected through wearable motion sensors. In contrast to existing approaches, the outcomes reveal that a unified framework involving CNN, BiLSTM, and CBAM achieves outstanding performance in activity recognition, exceeding $99 \%$ in both accuracy and F1-score while maintaining computational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Drug Discovery: Unravelling the Potential of Generative Adversarial Networks (GANs) in Pharmaceutical Research

AI-Driven Drug Discovery: Unravelling the Potential of Gener...

引用

Technological Advancements in Computational Sciences (ICTACS), International Conference on

作者： Srinivasa Rao Burri Mamadou Yero Diallo Lakshay Sharma Vishal Dutt Western Union Denver CO USA Computer Science & Engineering Sharda University Greater Noida India Computer Science & Applied Mathematics Indraprastha Institute of Information Technology Delhi India Department of CSE Chandigarh University Mohali Punjab India

This paper examines how AI has revolutionised drug development and medical research using the ChEMBL dataset. The primary study areas are AI-driven therapeutic target identification., computational approaches in drug development., drug repurposing for COVID-19 therapies., and AI methods for natural leather flaw detection. Target selection must balance novelty and confidence., and AI-driven therapeutic target identification is considered. Structure-based virtual screening and profound learning predictions of ligand properties and target activities are considered for application in scaling up to broader chemical spaces. AI is used to discover new links between drugs., targets., and diseases and treat COVID-19. The paper also highlights this field's enforcement challenges and offers solutions. A Generative Adversarial Network (GAN)-based automatic flaw identification system for natural leather is another topic of study. The results show that the suggested strategy is economical and accurate., despite limitations and biases. AI has revolutionised medical diagnostics., medication development., and precision medicine., making this work meaningful. This paper”s findings offer a cross-disciplinary perspective on artificial intelligence's potential in healthcare., revealing knowledge gaps and suggesting further research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Face-Touching Gestures with Smartwatches and Deep Learning Networks

Detecting Face-Touching Gestures with Smartwatches and Deep ...

引用

International Conference on Telecommunications and Signal Processing (TSP)

作者： Sakorn Mekruksavanich Wikanda Phaphan Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Applied Statistics Research Group in Statistical Learning and Inference Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Mathematics Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350365597

ISBN: (纸本)9798350365603

Everyday actions like scratching one's nose or resting the chin on one's hand may facilitate the spread of germs and diseases. Detecting these gestures holds the potential for innovative health monitoring and disease prevention applications. However, the identification of face-touching poses challenges due to the variety of human gestures and the limitations in accuracy associated with wearable sensors. This study introduces an original deep-learning system to identify face-touching gestures using standard smartwatches' inertial measurement unit sensors. The system on the smartwatch captures and pre-processes multi-channel time-series data from the accelerometer to generate robust input features. We utilize a benchmark, the Face Touching dataset, to evaluate the recognition performance of deep learning networks, including our proposed network. Our approach proposes a hybrid deep residual network architecture tailored for sequence-based gesture classification using signals from the smartwatch sensors. In our experiments, the developed deep learning framework achieves an impressive F1-score of 97.53% in detecting face-touch gestures. The suggested system takes a step forward in advancing the practical applications of face-touch gesture detection to smartwatch-based health sensing and disease prevention.

关键词： Deep learning Measurement units Prevention and mitigation Face recognition Signal processing Sensor systems Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient

arXiv

引用

arXiv 2022年

作者： Yin, Ming Wang, Mengdi Wang, Yu-Xiang Department of Computer Science UC Santa Barbara United States Department of Statistics and Applied Probability UC Santa Barbara United States Department of Electrical and Computer Engineering Princeton United States

Offline reinforcement learning, which aims at optimizing sequential decision-making strategies with historical data, has been extensively applied in real-life applications. State-Of-The-Art algorithms usually leverage powerful function approximators (e.g. neural networks) to alleviate the sample complexity hurdle for better empirical performances. Despite the successes, a more systematic understanding of the statistical complexity for function approximation remains lacking. Towards bridging the gap, we take a step by considering offline reinforcement learning with differentiable function class approximation (DFA). This function class naturally incorporates a wide range of models with nonlinear/nonconvex structures. Most importantly, we show offline RL with differentiable function approximation is provably efficient by analyzing the pessimistic fitted Q-learning (PFQL) algorithm, and our results provide the theoretical basis for understanding a variety of practical heuristics that rely on Fitted Q-Iteration style design. In addition, we further improve our guarantee with a tighter instance-dependent characterization. We hope our work could draw interest in studying reinforcement learning with differentiable function approximation beyond the scope of current research. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

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：