检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Jhonatan Geremias Altair O. Santin Eduardo K. Viegas Alceu S. Britto Graduate Program in Computer Science - PPGIa Pontifical Catholic University of Parana Curitiba Brazil

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Convolutional neural networks have been successfully applied for video content detection in the last years. However, such cognitive models usually demand the availability of several gigabytes of memory and present a low detection throughput, as a result, they are not feasible for resource-constrained devices, especially for real-time applications like video streaming. In this paper, we address real-time video content detection in resource-constrained devices in a threefold manner. First, we improve detection throughput by means of a frame sampling technique. Then, we propose a new evaluation measure towards proper deployment of convolutional neural networks in resource-constrained devices. Finally, we address the accuracy degradation caused by the porting of the convolutional neural network, applying a lightweight classification verification technique. The evaluation results, through a real-time demanding application, show that the proposed approach can detect up to 301 frames/sec, demanding only 9 megabytes of memory while reaching up to 89.3% of accuracy. Besides, we can increase the detection throughput by up to 10 times, with no effects on accuracy, and further increase accuracy without effects on processing demands.

关键词： Streaming media Throughput Real-time systems computer architecture Task analysis Feature extraction Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

A Reliable Semi-Supervised Intrusion Detection Model: One Year of Network Traffic Anomalies

A Reliable Semi-Supervised Intrusion Detection Model: One Ye...

引用

IEEE International Conference on Communications (ICC)

作者： Eduardo K. Viegas Altair O. Santin Vinicius V. Cogo Vilmar Abreu Graduate Program in Computer Science - Pontifical Catholic University of Parana Brazil LASIGE Faculdade de Ciências Universidade de Lisboa Portugal

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Despite the promising results of machine learning for network-based intrusion detection, current techniques are not widely deployed in real-world environments. In general, proposed detection models quickly become obsolete, thus, generating unreliable classifications over time. In this paper, we propose a new reliable model for semi-supervised intrusion detection that uses a verification technique to provide reliable classifications over time, even in the absence of model updates. Additionally, we cope with this verification technique with semi-supervised learning to autonomously update the underlying machine learning models without human assistance. Our experiments consider a full year of real network traffic and demonstrate that our solution maintains the accuracy rate over time without model updates while rejecting only 10.6% of instances on average. Moreover, when autonomous (non-human-assisted) model updates are performed, the average rejection rate drops to just 3.2% without affecting the accuracy of our solution.

关键词： Reliability Training Intrusion detection Feature extraction Computational modeling Machine learning Task analysis

来源：评论

学校读者我要写书评

暂无评论

SABER: An Infrastructure-Agnostic Benchmark Tool for Elasticity Evaluation on Cloud Foundry Based Platforms

SABER: An Infrastructure-Agnostic Benchmark Tool for Elastic...

引用

International Conference on Information Networking

作者： Wagner Marques Felipe Rubin Paulo de Souza Rômulo de Oliveira Tiago Ferreto Graduate Program in Computer Science Pontifical Catholic University of Rio Grande do Sul (PUCRS) Porto Alegre Brazil

ISBN: (数字)9781728141992

ISBN: (纸本)9781728142005

Elasticity can be considered as one of the main features of cloud computing. It can be described as the ability to dynamically provision (or de-provision) resources to meet an application's demand. Cloud-native platforms support this feature, allowing applications to be vertically or horizontally scaled. However, evaluating the performance of elasticity in cloud-native platforms is not a trivial task. These platforms tend to focus on providing higher abstractions to their customers, which typically results in the absence of low-level metrics that are required for measuring and evaluating elasticity performance. Therefore, this paper presents SABER, an infrastructure-agnostic benchmark tool for elasticity evaluation of Cloud Foundry based platforms. SABER collects low-level metrics regarding elasticity typical procedures (e.g., allocation and de-allocation of resources) and can be used to evaluate elasticity on different cloud infrastructures. Furthermore, we present an evaluation of SABER running on Pivotal Application Service, a Cloud Foundry based platform provided by Pivotal Web Services.

关键词： Cloud computing Elasticity Foundries Benchmark testing Measurement Tools computer architecture

来源：评论

学校读者我要写书评

暂无评论

CrowdEst: A method for estimating (and not simulating) crowd evacuation parameters in generic environments

arXiv

引用

arXiv 2020年

作者： Testa, Estêvão Barros, Rodrigo C. Musse, Soraia Raupp Pontifical Catholic University of Rio Grande do Sul School of Technology Graduate Program in Computer Science Porto Alegre Brazil

Evacuation plans have been historically used as a safety measure for the construction of buildings. The existing crowd simulators require fully-modeled 3D environments and enough time to prepare and simulate scenarios, where the distribution and behavior of the crowd needs to be controlled. In addition, its population, routes or even doors and passages may change, so the 3D model and configurations have to be updated accordingly. This is a time-consuming task that commonly has to be addressed within the crowd simulators. With that in mind, we present a novel approach to estimate the resulting data of a given evacuation scenario without actually simulating it. For such, we divide the environment into smaller modular rooms with different configurations, in a divide-and-conquer fashion. Next, we train an artificial neural network to estimate all required data regarding the evacuation of a single room. After collecting the estimated data from each room, we develop a heuristic capable of aggregating per-room information so the full environment can be properly evaluated. Our method presents an average error of 5% when compared to evacuation time in a real-life environment. Our crowd estimator approach has several advantages, such as not requiring to model the 3D environment, nor learning how to use and configure a crowd simulator, which means any user can easily use it. Furthermore, the computational time to estimate evacuation data (inference time) is virtually zero, which is much better even when compared to the best-case scenario in a real-time crowd simulator. Copyright © 2020, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Automating News Summarization with Sentence Vectors Offset

Automating News Summarization with Sentence Vectors Offset

引用

Brazilian Conference on Intelligent Systems (BRACIS)

作者： Mauricio Steinert Roger Granada João Paulo Aires Felipe Meneguzzi Graduate Program in Computer Science Pontifical Catholic University of Rio Grande do Sul (PUCRS) Brazil Pontifical Catholic University of Rio Grande do Sul Rio Grande Brazil

Text summaries consist of short versions of texts that convey their key aspects and help readers understand the gist of such texts without reading them in full. Generating such summaries is important for users who must sift through ever-increasing volumes of the content generated on the web. However, generating high-quality summaries is time-consuming for humans and challenging for automated systems, since it involves understanding the semantics of the underlying texts in order to extract key information. In this work, we develop an extractive text summarization method using vector offsets, which we show empirically to be able to summarize texts from an Internet news corpus with an effectiveness competitive with state-of-the-art extractive techniques.

关键词： Semantics Gold Task analysis Standards Mathematical model Internet Neural networks

来源：评论

学校读者我要写书评

暂无评论

How much do you perceive this? An analysis on perceptions of geometric features, personalities and emotions in virtual humans (extended version)

arXiv

引用

arXiv 2019年

作者： Araujo, Victor Favaretto, Rodolfo Migon Knob, Paulo Musse, Soraia Raupp Vilanova, Felipe Costa, Angelo Brandelli Graduate Program in Computer Science Pontifical Catholic University of Rio Grande do Sul Porto Alegre - RS Brazil Graduate Program in Psychology Pontifical Catholic University of Rio Grande do Sul Porto Alegre - RS Brazil

This work aims to evaluate people's perception regarding geometric features, personalities and emotions characteristics in virtual humans. For this, we use as a basis, a dataset containing the tracking files of pedestrians captured from spontaneous videos and visualized them as identical virtual humans. The goal is to focus on their behavior and not being distracted by other features. In addition to tracking files containing their positions, the dataset also contains pedestrian emotions and personalities detected using computer Vision and Pattern Recognition techniques. We proceed with our analysis in order to answer the question if subjects can perceive geometric features as distances/speeds as well as emotions and personalities in video sequences when pedestrians are represented by virtual humans. Regarding the participants, an amount of 73 people volunteered for the experiment. The analysis was divided in two parts: i) evaluation on perception of geometric characteristics, such as density, angular variation, distances and speeds, and ii) evaluation on personality and emotion perceptions. Results indicate that, even without explaining to the participants the concepts of each personality or emotion and how they were calculated (considering geometric characteristics), in most of the cases, participants perceived the personality and emotion expressed by the virtual agents, in accordance with the available ground truth. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Dossier: Decentralized Trust Model Towards a Decentralized Demand

Dossier: Decentralized Trust Model Towards a Decentralized D...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Vanderson Botelho Kelvin V. Kredens Juliano V. Martins Bráulio C. Ávila Edson E. Scalabrin Graduate Program on Applied Computer Science PPGIA Pontifical Catholic University of Paraná Curitiba PR Brazil

ISBN: (纸本)9781538614839

This paper presents a trust model that aggregates multiple sources of information, such as: testimonies, context, social information, preconception, reputation, and proposes a new data structure, called Dossier. The aim is to raise the success rate that consumer agents have when contracting provider agents. To reach this objective we make two hypotheses: (i) every consumer agent is able to measure and inform the quality of a service they receive from a provider agent; (ii) the Dossier is a data structure that allows the evaluated agent himself to keep locally the history of feedbacks received without modification or omission that benefits him. The model-that uses the Dossier structure-reduces some weak points of trust models that rely on the direct interaction between provider and consumer agents (direct trust) or those that rely on testimony obtained from client agents (indirect trust). The Dossier model allows us effectively to use the agent approach to build decentralized IT solutions, where control and data-of every application encapsulated in an agent-can actually be distributed logically and physically. The comparative analysis showed that the Dossier model has a behavior equivalent to or superior to the considered models (FIRE, TRAVOS, MARSH and Central) and that such a model can make the agents more efficient in choosing their partners. The reason for this is that the reputation of a given service provider agent is based on the reputation it has among the totality of consumer agents that used its services.

关键词： History Data structures Data models Analytical models Games Multi-agent systems Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Electromagnetic Optimization Based on Gaussian Crow Search Approach

Electromagnetic Optimization Based on Gaussian Crow Search A...

引用

2018 International Symposium on Power Electronics, Electrical Drives, Automation and Motion, SPEEDAM 2018

作者： Dos Santos Coelho, Leandro Klein, Carlos Eduardo Mariani, Viviana Cocco Do Nascimento, Carlos Augusto Richter Askarzadeh, Alireza PUCPR Industrial and Systems Eng. Graduate Program PPGEPS Federal University of Parana UFPR Department of Electrical Engineering DEE/PPGEE Pontifical Catholic University of Parana Curitiba PR Brazil PUCPR Mechanical Engineering Graduate Program PPGEM Curitiba Pontifical Catholic University of Parana PR Brazil Department of Energy Management and Optimization Institute of Science and High Technology and Environmental Sciences Graduate University of Advanced Technology Kerman Iran

ISBN: (纸本)9781538649411

Metaheuristic algorithms have provided efficient tools to designers by which it became possible to determine the optimum solutions of optimization problems encountered in several fields such as engineering, finance and computation. Generally metaheuristics are based on metaphors that are taken from nature or some other processes. Recently, an optimization metaheuristic paradigm based on the social behavior of the crows, called crow search algorithm (CSA), has been proposed. The idea of CSA is motivated from the storing process of the excess food in hiding places then restoring it in the necessary time. The CSA has many favorable characteristics, such as ease of implementation, the need to adjust only a few parameters, a favorable balance between search diversification and intensification, and fast convergence and high sensitivity. However, to enhance the performance of the standard CSA approach, this paper proposes to tune the control parameters using population diversity information and normal (Gaussian) probability distribution function. Loney's solenoid benchmark and circular antenna array design problems are used to evaluate the effectiveness of the conventional CSA and the proposed variant. Simulation results and comparisons with the CSA demonstrated that the performance of the proposed MCSA approach is promising in electromagnetics optimization. © 2018 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Exploring Data Augmentation to Improve Music Genre Classification with ConvNets

Exploring Data Augmentation to Improve Music Genre Classific...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Rafael L. Aguiar Yandre M.G. Costa Carlos N. Silla Postgraduate Program in Informatics (PPGIa) Pontifical Catholic University of Paraná (PUCPR) Curitiba Brazil Graduate Program in Computer Science (PCC) State University of Maringá (UEM) Maringá Brazil

In this work we address the automatic music genre classification as a pattern recognition task. The content of the music pieces were handled in the visual domain, using spectrograms created from the audio signal. This kind of image has been successfully used in this task since 2011 by extracting handcrafted features based on texture, since it is the main visual attribute found in spectrograms. In this work, the patterns were described by representation learning obtained with the use of convolutional neural network (CNN). CNN is a deep learning architecture and it has been widely used in the pattern recognition literature. Overfitting is a recurrent problem when a classification task is addressed by using CNN, it may occur due to the lack of training samples and/or due to the high dimensionality of the space. To increase the generalization capability we propose to explore data augmentation techniques. In this work, we have carefully selected strategies of data augmentation that are suitable for this kind of application, which are: adding noise, pitch shifting, loudness variation and time stretching. Experiments were conducted on the Latin Music Database (LMD), and the best obtained accuracy overcame the state of the art considering approaches based only in CNN.

关键词： Spectrogram Music Machine learning Training Task analysis Visualization Multiple signal classification

来源：评论

学校读者我要写书评

暂无评论

Enabling Anomaly-based Intrusion Detection Through Model Generalization

Enabling Anomaly-based Intrusion Detection Through Model Gen...

引用

IEEE Symposium on computers and Communications

作者： Eduardo Viegas Altair Santin Vilmar Abreu Luiz S. Oliveira Graduate Program in Computer Science Pontifical Catholic University of Parana Curitiba Parana Brazil Informatics Department Federal University of Parana Curitiba Parana Brazil

Anomaly-based intrusion detection by the means of machine learning techniques is extensively studied in the literature mainly due to its promise to detect new attacks. However, despite the promising reported results, it is hardly deployed to real world environments. The main challenge in its adoption is the discrepancy between the accuracy rates obtained during the classifier development process and the rates obtained during its use in production environments. Such a discrepancy is mainly caused by non-representative training databases and non-generalizable (scenario-specific) classifier's model. This paper presents a method to create intrusion databases, which aims at mimicking the production environments characteristics by using well-known tools. Moreover, we present and evaluate a new validation technique, which aims at ensuring the generalization capacity of the obtained models, reached using cross-validating with different intrusion databases. The evaluation tests showed the feasibility of the proposed method. The feature selection technique ensured the model generalization capacity, improving its accuracy rate by 13%, while testing in different intrusion databases. Finally, the proposed anomaly-based approach was compared with Snort, reaching an accuracy rate of 99% against 27% of Snort for detecting DoS attacks.

关键词： Anomaly-based Intrusion Detection Model Generalization Machine Learning Genetic Algorithm

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：