检索结果-内蒙古大学图书馆

Local Periodicity-Based Beat Tracking for Expressive Classical Piano Music

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 2824-2835页

作者： Chiu, Ching-Yu Muller, Meinard Davies, Matthew E. P. Su, Alvin Wen-Yu Yang, Yi-Hsuan National Cheng Kung University Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701401 Taiwan International Audio Laboratories Erlangen Erlangen91058 Germany University of Coimbra Department of Informatics Engineering Centre for Informatics and Systems Coimbra3004-531 Portugal National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Taiwan AI Labs Yating Music Team Taipei103622 Taiwan Academia Sinica Research Center for IT Innovation Taipei11529 Taiwan

To model the periodicity of beats, state-of-the-art beat tracking systems use 'post-processing trackers' (PPTs) that rely on several empirically determined global assumptions for tempo transition, which work well for music with a steady tempo. For expressive classical music, however, these assumptions can be too rigid. With two large datasets of Western classical piano music, namely the Aligned Scores and Performances (ASAP) dataset and a dataset of Chopin's Mazurkas (Maz-5), we report on experiments showing the failure of existing PPTs to cope with local tempo changes, thus calling for new methods. In this paper, we propose a new local periodicity-based PPT, called predominant local pulse-based dynamic programming (PLPDP) tracking, that allows for more flexible tempo transitions. Specifically, the new PPT incorporates a method called 'predominant local pulses' (PLP) in combination with a dynamic programming (DP) component to jointly consider the locally detected periodicity and beat activation strength at each time instant. Accordingly, PLPDP accounts for the local periodicity, rather than relying on a global tempo assumption. Compared to existing PPTs, PLPDP particularly enhances the recall values at the cost of a lower precision, resulting in an overall improvement of F1-score for beat tracking in ASAP (from 0.473 to 0.493) and Maz-5 (from 0.595 to 0.838). © 2014 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

A novel One-vs-Next approach for multiclass classification

A novel One-vs-Next approach for multiclass classification

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： V. Hurbungs V. Bassoo T. P. Fowdur Software and Information Systems Department Faculty of Information Communication & Digital Technologies University of Mauritius Electrical and Electronic Department Faculty of Engineering University of Mauritius

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

In machine learning, multiclass classification is the process of classifying data that contains three or more classes. One-vs-Rest and One-vs-One are two popular binary transformation approaches that reduce the multiclass problem into several binary problems. One-vs-Rest is usually faster and less complex than One-vs-One and is therefore the most commonly used strategy. The main contribution of this paper is the formulation of a novel One-vs-Next method for multiclass classification. The proposed approach consists in fitting one classifier per next class pair. This technique reduces the number of binary combinations and is expected to be faster since it requires to fit less number of classifiers compared to the One-vs-Rest approach. As a proof of concept, One-vs-Next was evaluated with the improved Scalable, Efficient, and Fast classifieR (iSEFR) designed for embedded machine learning on the Edge. In addition to its computational efficiency, experiments demonstrate that the proposed approach combined with the iSEFR decision threshold gives an average increase of ~20% in accuracy for a multiclass dataset with equal number of class instances.

关键词： Performance evaluation Training Computers Accuracy Microcontrollers Fitting Machine learning Computational efficiency Time complexity Testing

来源：评论

学校读者我要写书评

暂无评论

Simulative Investigations of Crowd Evacuation by Incorporating Reinforcement Learning Scheme 6

Simulative Investigations of Crowd Evacuation by Incorporati...

引用

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

作者： Sinpan, Nitinun Sasithong, Pruk Chaudhary, Sushank Poomrittigul, Suvit Leelawat, Natt Wuttisittikulkij, Lunchakorn Department of Electrical Engineering Chulalongkorn University Thailand Wireless Communication Ecosystem Research Unit Thailand Department of Software Engineering and Information System Pathumwan Institute of Technology Thailand Disaster and Risk Management Information Systems Research Unit Department of Industrial Engineering Chulalongkorn University Thailand

ISBN: (纸本)9781450397407

Safe and effective evacuation is very essential to decrease casualties in an emergency event. The social force model is used to simulate the movement of evacuee and leader crowd evacuation with leader in an experimental area. The a-star algorithm is used to find the evacuation routes of each evacuee from the initial location to the exit. In this paper, we proposed the application of reinforcement learning to train the agent to become an evacuation leader via the Unity ML-Agents Toolkit. This model is tested in three scenarios: an evacuation without a leader, an evacuation with a leader, and an evacuation with randomly located agent. They are considered for comparison purposes to show the impact of an agent that tries to tell an exit to all evacuees in the experimental area. The experimental results show that the proposed crowd evacuation agent could effectively evacuate all evacuees in the experimental area. © 2022 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Discussion Manipulation, Language and Domain Dependent Models: An Overview

Discussion Manipulation, Language and Domain Dependent Model...

引用

Zooming Innovation in Consumer Electronics International Conference (ZINC)

作者： Filip Chalás Igor Stupavský Valentino Vranić Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava

The amount of antisocial online behavior (AOB) in the political field has been on the rise in recent years. In the research, we are dealing with the reason for confusing AOB with other forms of antisocial behavior. We specifically dealt with NLP in the political field in the Slovak language, with a specific number of prefixes and suffixes. In this paper, we focus on the area of detection of manipulation of political discussions. The data source consisted of previously collected data in the period from April 2018 with an update until November 19, 2022 realized within this research from the site ***, which we supplemented with new claims. We trained several classification models on preprocessed data and evaluated them. For multi-class classification, the best results were achieved using logistic regression and a support vector machine trained on the resampled dataset—both achieving an accuracy of 0.56 and a macro F1 score of 0.39. In the case of binary classification, the best results were achieved by logistic regression—accuracy 0.7 and macro F1 score 0.56. These models could help detect manipulation in online political discussions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDANet: Reject Domain Attention Network For Confused Facial Expression Recognition

RDANet: Reject Domain Attention Network For Confused Facial ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jintao Luo Juan Li Tonglin Cheng Faculty of Information Technology Beijing University of Technology Beijing Engineering Researeh Center for loT Software and Systems Beijing China

Due to the significant intra-class differences and inter-class similarities inherent in facial expressions, distinguishing certain highly similar facial expressions such as disgust, fear, and sadness has become one of the main challenges in facial expression recognition (FER).To address this challenge, we propose a novel Rejected Domain Attention Network (RDANet), specifically designed to distinguish these easily confusing facial expressions. We aggregate and embed the correlations of regional features and facial expressions generated by convolutional neural networks into a compact interval. Adaptive weight adjustment is performed on the features in the interval, and a strict penalty mechanism is added. We identify anti correlated regions by correlation scores and classify them as rejected domains and the rest as supported domains. We select important rejected feature elements via RDANet and give them higher weight than supported domain features. An optimized contrastive loss is used to achieve a dynamic balance between intra-class clustering and inter-class separation, combined with regularization constraints to make the model converge faster. Through experimental verification, our method has superior performance in recognizing confused facial expressions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Weapons in Surveillance Cameras Using Efficient-Net

引用

Computers, Materials & Continua 2022年第9期72卷 4615-4630页

作者： Erssa Arif Syed Khuram Shahzad Muhammad Waseem Iqbal Muhammad Arfan Jaffar Abdullah S.Alshahrani Ahmed Alghamdi Department of Computer Science Superior UniversityLahore54000Pakistan Department of Informatics&Systems University of Management&TechnologyLahore54000Pakistan Department of Software Engineering Superior UniversityLahore54000Pakistan Faculty of Computer Science&Information Technology Superior UniversityLahore54000Pakistan Department of Computer Science&Artificial Intelligence College of Computer Science&EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia

The conventional Close circuit television(CCTV)cameras-based surveillance and control systems require human resource *** all the criminal activities take place using weapons mostly a handheld gun,revolver,pistol,swords ***,automatic weapons detection is a vital requirement now a *** current research is concerned about the real-time detection of weapons for the surveillance cameras with an implementation of weapon detection using Efficient–*** time datasets,from local surveillance department’s test sessions are used for model training and *** consist of local environment images and videos from different type and resolution cameras that minimize the *** research also contributes in the making of Efficient-Net that is experimented and results in a positive *** results are also been represented in graphs and in calculations for the representation of results during training and results after training are also shown to represent our research ***-Net algorithm gives better results than existing *** using Efficient-Net algorithms the accuracy achieved 98.12%when epochs increase as compared to other algorithms.

关键词： Detection algorithms machine learning machine vision video surveillance

来源：评论

学校读者我要写书评

暂无评论

Query-Based External information Leakage Attacks on Face Recognition Models

Query-Based External Information Leakage Attacks on Face Rec...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Edita Grolman Amit Giloni Ryuta Kremer Hiroo Saito Tomoyuki Shibata Tsukasa Omino Misaki Komatsu Yoshikazu Hanatani Asaf Shabtai Yuval Elovici Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Corporate Research & Development Center Toshiba Corporation

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Recent studies have demonstrated external information leakage (EIL) attacks which allow an attacker to infer various sensitive implicit properties related to a machine learning (ML) model’s training data. Most of those attacks assumed 1) a white-box scenario in which the attacker has complete access to the ML model, its structure, and its parameters, or 2) a black-box (alternatively gray-box) scenario with non-realistic requirements such as a high query budget or high computational resources for the attacker. In this paper, we propose two practical query-based (i.e., black-box) EIL attacks that target face recognition ML models and allow an attacker to infer sensitive implicit properties, such as the facial characteristics, gender, ethnicity, income level, and average age of the individuals in the training data, with a limited number of queries. The first proposed attack, referred to as the random noise injection (RNI) attack, exploits the effect of injecting random noise into input samples on the target model’s predictions. The second proposed attack, referred to as the property substitute model (PSM) attack, creates a substitute model for each property value examined, whose predictions are compared to the target model’s predictions. Our comprehensive evaluation (a total of 730 experiments) performed on the CelebA dataset shows that the proposed attacks outperform existing EIL attacks and successfully infer private information, posing a threat to the privacy and security of the face recognition models.

关键词： Privacy Face recognition Computational modeling Noise Training data Closed box Predictive models

来源：评论

学校读者我要写书评

暂无评论

Observability and Incident Response in Managed Serverless Environments Using Ontology-Based Log Monitoring

arXiv

引用

arXiv 2024年

作者： Ben-Shimol, Lavi Grolman, Edita Elyashar, Aviad Maimon, Inbar Mimran, Dudu Brodt, Oleg Strassmann, Martin Lehmann, Heiko Elovici, Yuval Shabtai, Asaf Department of Software and Information Systems Engineering Ben-Gurion University of the Negev Israel Deutsche Telekom AG. Germany

In a fully managed serverless environment, the cloud service provider is responsible for securing the cloud infrastructure, thereby reducing the operational and maintenance efforts of application developers. However, this environment limits the use of existing cybersecurity frameworks and tools, which reduces observability and situational awareness capabilities (e.g., risk assessment, incident response). In addition, existing security frameworks for serverless applications do not generalize well to all application architectures and usually require adaptation, specialized expertise, etc. for use in fully managed serverless environments. In this paper, we introduce a three-layer security scheme for applications deployed in fully managed serverless environments. The first two layers involve a unique ontology based solely on serverless logs which is used to transform them into a unified application activity knowledge graph. In the third layer, we address the need for observability and situational awareness capabilities by implementing two situational awareness tools that utilizes the graph-based representation: 1) An incident response dashboard that leverages the ontology to visualize and examine application activity logs in the context of cybersecurity alerts. Our user study showed that the dashboard enabled participants to respond more accurately and quickly to new security alerts than the baseline tool. 2) A criticality of asset (CoA) risk assessment framework that enables efficient expert-based prioritization in cybersecurity contexts. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Recurring Structures of Subcontract Management in System Outsourcing 22

Recurring Structures of Subcontract Management in System Out...

引用

Proceedings of the 29th Conference on Pattern Languages of Programs

作者： Haji Gul Wahaj Valentino Vranić Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology in Bratislava

ISBN: (纸本)9781941652183

Despite numerous efforts to address system outsourcing problems in the subcontract management system, the existing available solutions do not appear to be sufficient. They are fragmented into individual patterns, neither composing legible pattern languages to address the subcontract management systems nor being integrated into comprehensive pattern languages for managing system outsourcing in general. Communication among stakeholders is another issue that takes a long time because of their naturally hierarchical or multi-layered structure. And usually, false information reaches the sub-contractor at the bottom of the chain, which affects a project, and causes delays in deliverables. We attempt to overcome these problems by providing a set of four organizational patterns for the subcontract management system. Using them in combination with other available patterns and practices, we demonstrate a pattern language for better communication among different involved organizations. This paper focuses on better relationships between stakeholders. The relationships contain an inter-organizational communication and coordination among the stakeholders. A pattern story of a real case illustrates the overall use of this pattern language.

关键词： multi-sourcing organizational patterns patterns software engineering subcontract management system outsourcing

来源：评论

学校读者我要写书评

暂无评论

A Combined Method for Face Recognition

A Combined Method for Face Recognition

引用

International Conference on information and Computer Technologies (ICICT)

作者： Laura Mukhamadiyeva Aiman Moldagulova Information Systems International University of Information Technologies Almaty Kazakhstan Software Engineering Satbayev University Almaty Kazakhstan

Nowadays face recognition methods are in great interest of computer vision area. The development of a face recognition method that provides a high level of reliability of the solution in the absence of restrictions on the source image is a very crucial task. The paper deals with analysis of existing algorithms for recognizing the geometric characteristics of the face. As a result a combined method for identifying the face was developed. The main goal of this paper is to develop methods for recognizing and detecting faces that increase the reliability of identification of objects of analysis, reduce the level of false recognition, reduce the training time of the classifier and the time of preliminary processing and recognition of the image.

关键词：

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：