检索结果-内蒙古大学图书馆

Iteration Complexity of a Fixed-Stepsize SQP Method for Nonconvex Optimization with Convex Constraints 5th

学校读者我要写书评

暂无评论

Iteration Complexity of a Fixed-Stepsize SQP Method for Nonc...

5th International Conference on Numerical Analysis and Optimization: Theory, Methods, Applications and Technology Transfer, NAOV 2020

作者： Facchinei, Francisco Kungurtsev, Vyacheslav Lampariello, Lorenzo Scutari, Gesualdo Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy Department of Computer Science Faculty of Electrical Engineering Czech Technical University in Prague Prague Czech Republic Department of Business Studies Roma Tre University Rome Italy School of Industrial Engineering Purdue University West-LafayetteIN United States

ISBN: (纸本)9783030720391

We consider an SQP method for solving nonconvex optimization problems whose feasible set is convex and with an objective function that is the sum of a smooth nonconvex term and a nonsmooth, convex one. In the proposed method, at each iteration, a direction is generated by solving a strongly convex approximation to the original problem and then a fixed-stepsize is taken in that direction. The complexity result we establish is, as far as we are aware, the best available for the rather general setting we consider. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fixed-stepsize Iteration complexity SQP methods

An Approach for Improving Automatic Mouth Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Biondi, Giulio Franzoni, Valentina Gervasi, Osvaldo Perri, Damiano University of Florence Dept. of Mathematics and Computer Science Florence Italy University of Perugia Dept. of Mathematics and Computer Science Perugia Italy Sapienza University of Rome Department of Computer Control and Management Engineering "Antonio Ruberti" Rome Italy

The study proposes and tests a technique for automated emotion recognition through mouth detection via Convolutional Neural Networks (CNN), meant to be applied for supporting people with health disorders with communication skills issues (e.g. muscle wasting, stroke, autism, or, more simply, pain) in order to recognize emotions and generate real-time feedback, or data feeding supporting systems. The software system starts the computation identifying if a face is present on the acquired image, then it looks for the mouth location and extracts the corresponding features. Both tasks are carried out using Haar Feature-based Classifiers, which guarantee fast execution and promising performance. If our previous works focused on visual micro-expressions for personalized training on a single user, this strategy aims to train the system also on generalized faces data sets. © 2022, CC BY-NC-ND.

关键词： Emotion Recognition

Software Architectures for Mobile Robots

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Andreasson, Henrik Grisetti, Giorgio Stoyanov, Todor Pretto, Alberto School of Science and Technology Orebro University OrebroS-701 82 Sweden Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Department of Information Engineering University of Padova Italy

A software architecture defines the blueprints of a large computationalsystem, and is thus a crucial part of the design and development effort. Thistask has been explored extensively in the context of mobile robots, resultingin a plethora of reference designs and implementations. As the softwarearchitecture defines the framework in which all components are implemented, itis naturally a very important aspect of a mobile robot system. In this chapter,we overview the requirements that the particular problem domain (a mobile robotsystem) imposes on the software framework. We discuss some of the currentdesign solutions, provide a historical perspective on common frameworks, andoutline directions for future development. Copyright © 2022, The Authors. All rights reserved.

关键词： Software architecture

Sensors for Mobile Robots

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Andreasson, Henrik Grisetti, Giorgio Stoyanov, Todor Pretto, Alberto School of Science and Technology Örebro University ÖrebroS-701 82 Sweden Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome Italy Department of Information Engineering University of Padova Italy

A sensor is a device that converts a physical parameter or an environmental characteristic (e.g., temperature, distance, speed, etc.) into a signal that can be digitally measured and processed to perform specific tasks. Mobile robots need sensors to measure properties of their environment, thus allowing for safe navigation, complex perception and corresponding actions, and effective interactions with other agents that populate it. Copyright © 2022, The Authors. All rights reserved.

关键词： Mobile robots

Sharing Linkable Learning Objects with the use of Metadata and a Taxonomy Assistant for Categorization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Franzoni, Valentina Tasso, Sergio Pallottelli, Simonetta Perri, Damiano Department of Mathematics and Computer Science University of Perugia via Vanvitelli 1 PerugiaI-06123 Italy Department of Computer Control and Management Engineering "Antonio Ruberti" Sapienza University of Rome via Ariosto 25 Roma00185 Italy

In this work, a re-design of the Moodledata module functionalities is presented to share learning objects between e-learning content platforms, e.g., Moodle and G-Lorep, in a linkable object format. The e-learning courses content of the Drupal-based Content Management system G-Lorep for academic learning is exchanged designing an object incorporating metadata to support the reuse and the classification in its context. In such an Artificial Intelligence environment, the exchange of Linkable Learning Objects can be used for dialogue between Learning systems to obtain information, especially with the use of semantic or structural similarity measures to enhance the existent Taxonomy Assistant for advanced automated classification. © 2022, CC BY-NC-ND.

关键词： Taxonomies

Newron: A new generalization of the artificial neuron to enhance the interpretability of neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Siciliano, Federico Bucarelli, Maria Sofia Tolomei, Gabriele Silvestri, Fabrizio Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Italy Department of Computer Science Sapienza University of Rome Italy

In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neurons. We show that some specializations of NEWRON allow the network to be interpretable with no change in their expressiveness. By just inspecting the models produced by our NEWRON-based networks, we can understand the rules governing the task. Extensive experiments show that the quality of the generated models is better than traditional interpretable models and in line or better than standard neural networks. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural networks

Shape and Style GAN-based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fawakherji, Mulham Suriani, Vincenzo Nardi, Daniele Bloisi, Domenico Daniele Department of Built Environment College of Science and Technology North Carolina A&T University 1601 E Market St Greensboro27411 United States Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Via Ariosto 25 Roma00185 Italy Faculty of Political Science and Sociopsychological Dynamics UNINT University Via Cristoforo Colombo 200 Roma00147 Italy

The use of deep learning methods for precision farming is gaining increasing interest. However, collecting training data in this application field is particularly challenging and costly due to the need of acquiring information during the different growing stages of the cultivation of interest. In this paper, we present a method for data augmentation that uses two GANs to create artificial images to augment the training data. To obtain a higher image quality, instead of re-creating the entire scene, we take original images and replace only the patches containing objects of interest with artificial ones containing new objects with different shapes and styles. In doing this, we take into account both the foreground (i.e., crop samples) and the background (i.e., the soil) of the patches. Quantitative experiments, conducted on publicly available datasets, demonstrate the effectiveness of the proposed approach. The source code and data discussed in this work are available as open source. © 2024, CC BY-NC-ND.

关键词： Crops

Shape and Style Gan-Based Multispectral Data Augmentation for Crop/Weed Segmentation in Precision Farming

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Fawakherji, Mulham Suriani, Vincenzo Bloisi, Domenico D. Nardi, Daniele Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome via Ariosto 25 Rome00185 Italy Department of Mathematics Computer Science and Economics University of Basilicata viale dell’Ateneo Lucano 10 Potenza85100 Italy

The use of deep learning methods for precision farming is gaining increasing interest. However, collecting training data in this application field is particularly challenging and costly due to the need of acquiring information during the different growing stages of the cultivation of interest. In this paper, we present a method for data augmentation that uses two GANs to create artificial images to augment the training data. To obtain a higher image quality, instead of re-creating the entire scene, we take original images and replace only the patches containing objects of interest with artificial ones containing new objects with different shapes and styles. In doing this, we take into account both the foreground (i.e., crop samples) and the background (i.e., the soil) of the patches. Quantitative experiments, conducted on publicly available datasets, demonstrate the effectiveness of the proposed approach. Source code and data discussed in this work are available as open source. © 2022, The Authors. All rights reserved.

关键词： Crops

Finding single-source shortest p-disjoint paths: Fast computation and sparse preservers

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bilò, Davide D'Angelo, Gianlorenzo Gualà, Luciano Leucci, Stefano Proietti, Guido Rossi, Mirko Department of Humanities and Social Sciences University of Sassari Italy Gran Sasso Science Institute L'Aquila Italy Department of Enterprise Engineering University of Rome Tor Vergata Italy Department of Information Engineering Computer Science and Mathematics University of l'Aquila Italy Institute for System Analysis and Computer Science Antonio Ruberti Italy

Let G be a directed graph with n vertices, m edges, and non-negative edge costs. Given G, a fixed source vertex s, and a positive integer p, we consider the problem of computing, for each vertex t ≠ s, p edge-disjoint paths of minimum total cost from s to t in G. Suurballe and Tarjan [Networks, 1984] solved the above problem for p = 2 by designing a O(m + n log n) time algorithm which also computes a sparse single-source 2-multipath preserver, i.e., a subgraph containing 2 edge-disjoint paths of minimum total cost from s to every other vertex of G. The case p ≥ 3 was left as an open problem. We study the general problem (p ≥ 2) and prove that any graph admits a sparse single-source p-multipath preserver with p(n - 1) edges. This size is optimal since the in-degree of each non-root vertex v must be at least p. Moreover, we design an algorithm that requires O(pn2(p + log n)) time to compute both p edge-disjoint paths of minimum total cost from the source to all other vertices and an optimal-size single-source p-multipath preserver. The running time of our algorithm outperforms that of a natural approach that solves n - 1 single-pair instances using the well-known successive shortest paths algorithm by a factor of θ(m/np) and is asymptotically near optimal if p = O(1) and m = θ(n2). Our results extend naturally to the case of p vertex-disjoint paths. Copyright © 2021, The Authors. All rights reserved.

关键词： Directed graphs