检索结果-内蒙古大学图书馆

Facilitating innovation and knowledge transfer between homogeneous and heterogeneous datasets: Generic incremental transfer learning approach and multidisciplinary studies

学校读者我要写书评

暂无评论

Journal of Innovation and Knowledge 2023年第2期8卷

作者： Chui, Kwok Tai Arya, Varsha Band, Shahab S. Alhalabi, Mobeen Liu, Ryan Wen Chi, Hao Ran Department of Electronic Engineering and Computer Science School of Science and Technology Hong Kong Metropolitan University Ho Man Tin Kowloon Hong Kong Insights2Techinfo India Asia University Taiwan Lebanese American University Beirut 1102 Lebanon Department of Computer Science National Yunlin University of Science and Technology Douliou Taiwan Department of Computer Science King Abdulaziz University Jeddah Saudi Arabia Hubei Key Laboratory of Inland Shipping Technology School of Navigation Wuhan University of Technology Wuhan 430063 China Instituto de Telecomunicações 3810- 193 Aveiro Portugal

Open datasets serve as facilitators for researchers to conduct research with ground truth data. Generally, datasets contain innovation and knowledge in the domains that could be transferred between homogeneous datasets and have become feasible using machine learning models with the advent of transfer learning algorithms. Research initiatives are drawn to the heterogeneous datasets if these could extract useful innovation and knowledge across datasets of different domains. A breakthrough can be achieved without the restriction requiring the similarities between datasets. A multiple incremental transfer learning is proposed to yield optimal results in the target model. A multiple rounds multiple incremental transfer learning with a negative transfer avoidance algorithm are proposed as a generic approach to transfer innovation and knowledge from the source domain to the target domain. Incremental learning has played an important role in lowering the risk of transferring unrelated information which reduces the performance of machine learning models. To evaluate the effectiveness of the proposed algorithm, multidisciplinary studies are carried out in 5 disciplines with 15 benchmark datasets. Each discipline comprises 3 datasets as studies with homogeneous datasets whereas heterogeneous datasets are formed between disciplines. The results reveal that the proposed algorithm enhances the average accuracy by 4.35% compared with existing works. Ablation studies are also conducted to analyse the contributions of the individual techniques of the proposed algorithm, namely, the multiple rounds strategy, incremental learning, and negative transfer avoidance algorithms. These techniques enhance the average accuracy of the machine learning model by 3.44%, 0.849%, and 4.26%, respectively. © 2023 The Authors

关键词： Deep learning Domain knowledge Incremental learning Innovation transfer Knowledge transfer Transfer learning

Network Traffic Co-Movement Assessment via Oriented Basis Signal Processing and Ensemble Decision Trees

学校读者我要写书评

暂无评论

Network Traffic Co-Movement Assessment via Oriented Basis Si...

International Conference on Intelligent Transportation

作者： Mohammad Reza Mohebbi Mohammad Javad Hassan Zada Majid Rostami-Shahrbabaki Mario Döller Iuliia Yamnenko Josef Ressel Center Vision2Move project University of Applied Sciences Kufstein Tirol Austria Department of Computer Science University of Passau Germany Chair of Traffic Engineering and Control Technical University of Munich Germany Department of Electronic Devices and Systems National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” Kyiv Ukraine

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Accurate short-term network-wide traffic prediction is essential to guarantee high service quality in urban traffic control systems. Nevertheless, traffic state time series represent network-scale spatiotemporal co-movement patterns and location-specific features. Therefore, hybrid statistical machine learning (ml) algorithms could be utilized to accommodate the aforementioned characteristics. In this paper, a hybrid random forest (rf) and extreme gradient boosting tree (XGBoost) model is introduced for network-wide traffic prediction. Moreover, a multi-noise oriented basis wavelet transform (OBT) filter is employed to pre-process the original time series, and improve the predictive accuracy. The RF model captures the traffic co-movements and the XGBoost extracts the local information. Comparative analysis of the hybrid algorithm and deep learning-based benchmarks indicate better performance of the proposed methodology in hourly traffic state prediction of 30 loop detectors, located in the paris city center. Hence, the hybrid decision-tree-based mechanism is a useful framework for real-time network traffic forecasting offering fewer trainable (hyper-)parameters, and thus, lower computational cost.

关键词： Wavelet transforms Radio frequency Accuracy Machine learning algorithms Urban areas Signal processing algorithms Detectors Prediction algorithms Decision trees Random forests

Quantum limit to subdiffraction incoherent optical imaging. II. A parametric-submodel approach

学校读者我要写书评

暂无评论

Physical Review A 2021年第5期104卷 052411-052411页

作者： Mankei Tsang Department of Electrical and Computer Engineering National University of Singapore 4 Engineering Drive 3 Singapore 117583 Singapore Department of Physics National University of Singapore 2 Science Drive 3 Singapore 117551 Singapore

In a previous paper [M. Tsang, Phys. Rev. A 99, 012305 (2019)], I proposed a quantum limit to the estimation of object moments in subdiffraction incoherent optical imaging. In this sequel, I prove the quantum limit rigorously by infinite-dimensional analysis. A key to the proof is the choice of an unfavorable parametric submodel to give a bound for the semiparametric problem. By generalizing the quantum limit for a larger class of moments, I also prove that the measurement method of spatial-mode demultiplexing with just one or two modes is able to achieve the quantum limit. For comparison, I derive a classical bound for direct imaging using the parametric-submodel approach, which suggests that direct imaging is substantially inferior.

关键词： Quantum metrology Quantum parameter estimation Imaging & optical processing Optical microscopy Super-resolution techniques Telescopes

Adjunctive Three-Way Concepts from Positive and Negative Concepts in Lattice-Valued Formal Contexts

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Deng, Tingquan Long, Binghan Xu, Weihua Yao, Yiyu College of Mathematical Sciences Harbin Engineering University Harbin150001 China College of Artificial Intelligence Southwest University Chongqing400715 China Department of Computer Science Regina University ReginaSKS4S 0A2 Canada

Three-way concept analysis is an integration of formal concept analysis and three-way decision, which has been found wide applications in knowledge representation, cognitive computing and decision sciences. There have been already a huge number of literature on theory and applications on such topics. Most researches on formal concept analysis focus, independently, on specific scenarios such as Boolean formal contexts and fuzzy formal contexts. In this paper, a unified framework for three-way concept analysis is built in lattice-valued formal contexts. The notions of positive concept and negative concept are given in a lattice-valued formal context based on an overlapping function, one of significant operators for information fusion. Two pairs of object induced adjunctive three-way concept operators and attribute induced adjunctive three-way concept operators are introduced. Their properties have been fully investigated. With those operators, the algebraic structures of adjunctive three-way concepts, their extensions and intensions have been explored. Specifically, the local structure within pairs of sub-concept and sup-concept has been finely characterized. The derived results provide ones a way to construct the complete lattice of a lattice valued formal context or its sublattice by determining all pairs of sub-concept and sup-concept provided that an object fuzzy set or an attribute fuzzy set is given. A case analysis on a real world dataset from UCI repository is presented to verify the rationality and significance of obtained results. © 2023, The Authors. All rights reserved.

关键词： Formal concept analysis

Predicting ionic conductivity in solids from the machine-learned potential energy landscape

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Maevskiy, Artem Carvalho, Alexandra Sataev, Emil Turchyna, Volha Noori, Keian Rodin, Aleksandr Castro Neto, A.H. Ustyuzhanin, Andrey National University of Singapore Institute for Functional Intelligent Materials NUS S9 Building 4 Science Drive 2 117544 Singapore National University of Singapore Centre for Advanced 2D Materials 6 Science Drive 2 117546 Singapore HSE University Faculty of Computer Science Pokrovsky Boulevard 11 Moscow109028 Russia Yale-NUS College 16 College Avenue West 138527 Singapore National University of Singapore Department of Materials Science Engineering 9 Engineering Drive 1 117575 Singapore National University of Singapore Department of Physics 2 Science Drive 3 Singapore117551 Singapore Constructor Knowledge Labs Campus Ring 1 Bremen28759 Germany Constructor University Campus Ring 1 Bremen28759 Germany

Discovering new superionic materials is essential for advancing solid-state batteries, which offer improved energy density and safety compared to the traditional lithium-ion batteries with liquid electrolytes. Conventional computational methods for identifying such materials are resource-intensive and not easily scalable. Recently, universal interatomic potential models have been developed using equivariant graph neural networks. These models are trained on extensive datasets of first-principles force and energy calculations. One can achieve significant computational advantages by leveraging them as the foundation for traditional methods of assessing the ionic conductivity, such as molecular dynamics or nudged elastic band techniques. However, the generalization error from model inference on diverse atomic structures arising in such calculations can compromise the reliability of the results. In this work, we propose an approach for the quick and reliable screening of ionic conductors through the analysis of a universal interatomic potential. Our method incorporates a set of heuristic structure descriptors that effectively employ the rich knowledge of the underlying model while requiring minimal generalization capabilities. Using our descriptors, we rank lithium-containing materials in the Materials Project database according to their expected ionic conductivity. Eight out of the ten highest-ranked materials are confirmed to be superionic at room temperature in first-principles calculations. Notably, our method achieves a speed-up factor of approximately 50 compared to molecular dynamics driven by a machine-learning potential, and is at least 3,000 times faster compared to first-principles molecular dynamics. © 2024, CC BY.

关键词： Lithium-ion batteries

Spatial Clustering of Citizen science Data Improves Downstream Species Distribution Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ahmed, Nahian Roth, Mark Hallman, Tyler A. Robinson, W. Douglas Hutchinson, Rebecca A. School of Electrical Engineering and Computer Science Oregon State University CorvallisOR97331 United States Department of Fisheries Wildlife and Conservation Sciences Oregon State University CorvallisOR97331 United States School of Natural Sciences Bangor University BangorLL57 2DG United Kingdom

Citizen science biodiversity data present great opportunities for ecology and conservation across vast spatial and temporal scales. However, the opportunistic nature of these data lacks the sampling structure required by modeling methodologies that address a pervasive challenge in ecological data collection: imperfect detection, i.e., the likelihood of under-observing species on field surveys. Occupancy modeling is an example of an approach that accounts for imperfect detection by explicitly modeling the observation process separately from the biological process of habitat selection. This produces species distribution models that speak to the pattern of the species on a landscape after accounting for imperfect detection in the data, rather than the pattern of species observations corrupted by errors. To achieve this benefit, occupancy models require multiple surveys of a site across which the site’s status (i.e., occupied or not) is assumed constant. Since citizen science data are not collected under the required repeated-visit protocol, observations may be grouped into sites post hoc. Existing approaches for constructing sites discard some observations and/or consider only geographic distance and not environmental similarity. In this study, we compare ten approaches for site construction in terms of their impact on downstream species distribution models for 31 bird species in Oregon, using observations recorded in the eBird database. We find that occupancy models built on sites constructed by spatial clustering algorithms perform better than existing alternatives. Copyright © 2024, The Authors. All rights reserved.

关键词：

Insights and caveats from mining local and global temporal motifs in cryptocurrency transaction networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Arnold, Naomi Zhong, Peijie Ba, Cheick Tidiane Steer, Ben Mondragon, Raul Cuadrado, Felix Lambiotte, Renaud Clegg, Richard G. Northeastern University London Network Science Institute LondonE1W 1LP United Kingdom Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom University of Milan Department of Computer Science Via Giovanni Celoria 18 MI Milano20133 Italy Pometry Ltd 69 Wilson St LondonEC2A 2BB United Kingdom Universidad Politecnica de Madrid School of Telecommunications Engineering Av. Complutense 30 Moncloa - Aravaca Madrid28040 Spain University of Oxford Mathematical Institute OxfordOX2 6GG United Kingdom

Distributed ledger technologies have opened up a wealth of fine-grained transaction data from cryptocurrencies like Bitcoin and Ethereum. This allows research into problems like anomaly detection, anti-money laundering, pattern mining and activity clustering (where data from traditional currencies is rarely available). The formalism of temporal networks offers a natural way of representing this data and offers access to a wealth of metrics and models. However, the large scale of the data presents a challenge using standard graph analysis techniques. We use temporal motifs to analyse two Bitcoin datasets and one NFT dataset, using sequences of three transactions and up to three users. We show that the commonly used technique of simply counting temporal motifs over all users and all time can give misleading conclusions. Here we also study the motifs contributed by each user and discover that the motif distribution is heavy-tailed and that the key players have diverse motif signatures. We study the motifs that occur in different time periods and find events and anomalous activity that cannot be seen just by a count on the whole dataset. Studying motif completion time reveals dynamics driven by human behaviour as well as algorithmic behaviour. Copyright © 2024, The Authors. All rights reserved.

关键词： Distributed ledger

FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jinbao Xie, Guoyang Huang, Yawen Lyu, Jiayi Zheng, Feng Zheng, Yefeng Jin, Yaochu Department of Computer Science and Engineering Southern University of Science and Technology 518055 China Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom Tencent Jarvis Lab Shenzhen518040 China School of Engineering Science University of Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen518000 China Faculty of Technology Bielefeld University Bielefeld33619 Germany

Utilizing multi-modal neuroimaging data is proven to be effective in investigating human cognitive activities and certain pathologies. However, it is not practical to obtain the full set of paired neuroimaging data centrally since the collection faces several constraints, e.g., high examination cost, long acquisition time, and image corruption. In addition, these data are dispersed into different medical institutions and thus cannot be aggregated for centralized training considering the privacy issues. There is a clear need to launch federated learning and facilitate the integration of dispersed data from different institutions. In this paper, we propose a new benchmark for federated domain translation on unsupervised brain image synthesis (FedMed-GAN) to bridge the gap between federated learning and medical GAN. FedMed-GAN mitigates the mode collapse without sacrificing the performance of generators, and is widely applied to different proportions of unpaired and paired data with variation adaptation properties. We treat the gradient penalties using the federated averaging algorithm and then leverage the differential privacy gradient descent to regularize the training dynamics. A comprehensive evaluation is provided for comparing FedMed-GAN and other centralized methods, demonstrating that the proposed algorithm outperforms the state-of-the-art. Our code is available at: https://***/M-3LAB/FedMed-GAN. © 2022, CC BY-NC-SA.

关键词： Gradient methods

Semantic Communication with Memory

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Huiqiang Qin, Zhijin Li, Geoffrey Ye The School of Electronic Engineering and Computer Science Queen Mary University of London LondonE1 4NS United Kingdom The Department of Electronic Engineering Tsinghua University Beijing China School of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom

While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. Particularly, we investigate a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer task. We exploit the universal Transformer based transceiver to extract the semantic information and introduce the memory module to process the context information. Moreover, we derive the relationship between the length of semantic signal and the channel noise to validate the possibility of dynamic transmission. Specially, we propose two dynamic transmission methods to enhance the transmission reliability as well as to reduce the communication overheads by masking some unessential elements, which are recognized through training the model with mutual information. Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics