检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Daniel M. M. da Costa Sarajane M. Peres Clodoaldo A. M. Lima Pollyana Mustaro Information Systems Program University of São Paulo São Paulo SP Brazil Graduate Program in Electrical Engineering and Computing Mackenzie Presbyterian University São Paulo SP Brazil

ISBN: (纸本)9781479919611

In recent years, human identification based on face recognition has attracted the attention of the scientific community and the general public due to its wide range of applications. A face recognition system involves three important phases: face detection, feature extraction and classification (identification and/or verification). The robustness of face recognition could be improved by treating the variations in these stages. One of the main issues in design of face recognition system is how to extract discriminative facial features. A precise extraction of a representative feature set will improve the performance of a face recognition system. Various techniques have been used to represent images efficiently, of which the most well-known and widely applied are Wavelet, Contourlet, Shearlet and Curvelet Transform. Their ability to capture localized time-frequency information of image motivates their use for feature extraction. In this paper, we conduct a systematic empirical study on these transforms as feature extractors from face images. To further reduce the feature dimensionality, we adopt Principal Component Analysis and Linear Discriminant Analysis to select the most discriminative feature sets. The performance levels delivered by each transform are contrasted in terms of the accuracy measure computed over the outputs generated by the Support Vector Machine classifier (SVM). Experimental results conducted on a publicly available database are reported whereby we observe that the Curvelet Transform followed by the Wavelet Transform significantly outperform the others according to accuracy measure calculated over the SVM classifier.

关键词： Face recognition Support vector machines Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Embeddings of Acoustic and Articulatory Features for Speaker Identification

Combining Deep Embeddings of Acoustic and Articulatory Featu...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Qian-Bei Hong Chung-Hsien Wu Hsin-Min Wang Chien-Lin Huang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan PingAn AI Lab Palo Alto CA USA

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

In this study, deep embedding of acoustic and articulatory features are combined for speaker identification. First, a convolutional neural network (CNN)-based universal background model (UBM) is constructed to generate acoustic feature (AC) embedding. In addition, as the articulatory features (AFs) represent some important phonological properties during speech production, a multilayer perceptron (MLP)-based AF embedding extraction model is also constructed for AF embedding extraction. The extracted AC and AF embeddings are concatenated as a combined feature vector for speaker identification using a fully-connected neural network. This proposed system was evaluated by three corpora consisting of King-ASR, LibriSpeech and SITW, and the experiments were conducted according to the properties of the datasets. We adopted all three corpora to evaluate the effect of AF embedding, and the results showed that combining AF embedding into the input feature vector improved the performance of speaker identification. The LibriSpeech corpus was used to evaluate the effect of the number of enrolled speakers. The proposed system achieved an EER of 7.80% outperforming the method based on x-vector with PLDA (8.25%). And we further evaluated the effect of signal mismatch using the SITW corpus. The proposed system achieved an EER of 25.19%, which outperformed the other baseline methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistics Pooling Time Delay Neural Network Based on X-Vector for Speaker Verification

Statistics Pooling Time Delay Neural Network Based on X-Vect...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

ISBN: (数字)9781509066315

ISBN: (纸本)9781509066322

This paper aims to improve speaker embedding representation based on x-vector for extracting more detailed information for speaker verification. We propose a statistics pooling time delay neural network (TDNN), in which the TDNN structure integrates statistics pooling for each layer, to consider the variation of temporal context in frame-level transformation. The proposed feature vector, named as statsvector, are compared with the baseline x-vector features on the VoxCeleb dataset and the Speakers in the Wild (SITW) dataset for speaker verification. The experimental results showed that the proposed stats-vector with score fusion achieved the best performance on VoxCeleb1 dataset. Furthermore, considering the interference from other speakers in the recordings, we found that the proposed statsvector efficiently reduced the interference and improved the speaker verification performance on the SITW dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Selection Based on Phoneme Affinity Matrix for Electrolarynx Speech Recognition

Data Selection Based on Phoneme Affinity Matrix for Electrol...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： I-Ting Hsieh Chung-Hsien Wu Shu-Wei Tsa Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Tainan Taiwan Dept. of Otolaryngology National Cheng Kung University Hospital Taiwan

Electrolarynx (EL) is a communicative aid for the patient after laryngectomy to generate communicable speech. Since EL speech exhibits low speech intelligibility and produces loud noise, understanding the content of the speech remains challenging for listeners, even if the patient is proficient in using the EL device. Accordingly, it is important to develop the tools that offer additional communication methods. Automatic speech recognition (ASR) of EL speech emerges as a method worth considering in this regard. However, the problem of under-resourced data dramatically degrades the recognition performance of EL speech. Data augmentation is one of the viable solutions for addressing the issue of under-resourced speech data. However, even with an increased health training corpus, the improvement in EL speech recognition may not be satisfactory. Because the characteristics of the EL speech still differ significantly from those of health speech. This paper proposes a data selection method using the phoneme affinity matrix to prioritize the selection of health speech that closely resembles EL speech for data augmentation. The affinity between two phonemes is defined as the similarity of the Phone Posteriorgrams(PPGs) of the two phonemes, considering the phoneme models. The experimental results demonstrate that the approach utilizing data selection based on the phoneme affinity matrix yields superior results compared to both the baseline and the method employing random sampling to select the augmented health speech corpus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic programming Algorithm using Furniture Industry 0/1 Knapsack Problem 5

Dynamic Programming Algorithm using Furniture Industry 0/1 K...

引用

5th International Conference on Cybernetics and Intelligent systems, ICORIS 2023

作者： Anditta, Mietha Amartya, Natashya Warnars, Laurens Spits Warnars, Harco Leslie Hendric Spits Ramadhan, Arief Siswanto, Teddy Mantoro, Teddy Noordin, Nurulhuda Bina Nusantara University School of Computer Science Computer Science Departement Jakarta11530 Indonesia Bina Nusantara University School of Information Systems Information Systems Departement Jakarta11530 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Departement Jakarta11530 Indonesia Telkom University Pjj Informatika Bandung40257 Indonesia Trisakti University Information Systems Department Jakarta11440 Indonesia Sampoerna University Faculty of Engineering and Technology Jakarta12760 Indonesia Universiti Teknologi Mara School of Computing Sciences College of Computing Informatics and Mathematics Selangor Malaysia

ISBN: (纸本)9798350369489

Dynamic programming is a fundamental algorithm that can be found in our daily lives easily. One of the dynamic programming algorithm implementations consists of solving the 0/1 knapsack problem. A 0/1 knapsack problem can be seen from industrial production cost. It is prevalent that a production cost has to be as efficient as possible, but the expectation is to get the proceeds of the products higher. Thus, the dynamic programming algorithm can be implemented to solve the diverse knapsack problem, one of which is the 0/1 knapsack problem, which would be the main focus of this paper. The implementation was implemented using C language. This paper was created as an early implementation algorithm using a Dynamic program algorithm applied to an Automatic Identification System (AIS) dataset. © 2023 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Multilabel Machine Learning System for Predicting Gender and Age Group from Human Gait 2

Multilabel Machine Learning System for Predicting Gender and...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Qomariyah, Nunung Nurul Nurul Fajar, Ahmad Yono, Vincent Kazakov, Dimitar Bina Nusantara University School of Computing and Creative Arts Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Information System Management Information Systems Management Department Jakarta11480 Indonesia University of York Computer Science Department YO10 5GH United Kingdom

ISBN: (纸本)9798350360523

This paper explores the development of a multilabel machine learning system for predicting both gender and age from human gait patterns. Gait analysis, a non-intrusive method of identifying subtle nuances in human movement, has proven to be a rich source of information related to demographic characteristics. The research extends beyond traditional single-label classification approaches, adopting a multilabel framework to simultaneously predict gender and age *** study evaluates various multilabel machine learning algorithms, with the Random k-labeLsets (RAKEL) algorithm demonstrating superior performance in predicting gender and age labels from human gait datasets. The accuracy of the algorithm can reach up to 87%. We also compared the multilabel approach with several multiclass algorithms such as Decision Tree, Random Forest, Gradient Boosting, K-Neighbors and XGBoost. However, when we also considering the training time, Classifier Chain algorithm showed the best trade off with the accuracy of 86% and the training time is twice faster than the RAKEL algorithm. © 2024 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Explainable and Adaptable Augmentation in Knowledge Attention Network for Multi-Agent Deep Reinforcement Learning systems

Explainable and Adaptable Augmentation in Knowledge Attentio...

引用

Artificial Intelligence and Knowledge Engineering (AIKE)

作者： Joshua Ho Chien-Min Wang Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan

ISBN: (数字)9781728187082

ISBN: (纸本)9781728187099

The scale of modem Artificial Intelligence systems has been growing and entering more research territories by incorporating Deep Learning (DL) and Deep Reinforcement Learning (DRL) methods. More specifically, multi-agent DRL methods have been widely applied to address the problems of high-dimensional computation, which interpret the conditions that real-world systems mainly encounter and the issues that require resolving. However, the current approaches of DL and DRL are often challenged for their untransparent and time-consuming modeling processes in their attempt to achieve a practical and applicable inference based on human-level perspective and acceptance. This paper presents an explainable and adaptable augmented knowledge attention network for multi-agent DRL systems, which uses game theory simulation to tackle the problem of non-stationarity at the beginning, while improving the learning exploration built upon the strategic ontology to achieve the learning convergence more efficiently for autonomous agents. We anticipate that our approach will facilitate future research studies and potential research inspections of emerging multi-agent DRL systems for increasingly complex and autonomous environments.

关键词： Knowledge engineering Adaptation models Reinforcement learning Ontologies Inspection Modems Game theory

来源：评论

学校读者我要写书评

暂无评论

Improving the Vocabulary Learning by Personalized Proficiency

Improving the Vocabulary Learning by Personalized Proficienc...

引用

IEEE International Conference on Ubi-Media computing

作者： Yi-Zhen Lin Kai-Hsiang Chen Jen-Wei Huang Department of Electrical Engineering National Cheng Kung University Tainan Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (数字)9781728128207

ISBN: (纸本)9781728128214

To improve the vocabulary ability is very important in language learning. Thus, if we can learn and remember a word very effectively, then we will be able to master a language more quickly. Therefore, many scholars began to propose related research. Due to the learning mechanism of human brain, sometimes when people learn a new knowledge they may forgot at a short time. In order to make the consideration more complete, after analyzing Hermann Ebbinghaus's forgetting curve experiment, we added two variables, one is the acceptance of each word by the same person, and the other is the ability of different people to remember vocabulary. With the above two parameters, we want to design a system to help user to review the vocabulary which may be forgetting before. The forgetting curve can be personalized, and it is more accurate to calculate the best time for each user to review the vocabulary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Model-Driven Approach for Interoperability Among SaaS and DaaS/DBaaS: The MIDAS Case

引用

SN Computer Science 2022年第4期3卷 301页

作者： Mane, Babacar Mascarenhas, Ana Patrícia F. Magalhães Quinteiro, Gustavo Maciel, Rita Suzana Pitangueira Claro, Daniela Barreiro Formalisms and Semantic Applications Research Group (FORMAS) Institute of Computing Federal University of Bahia Av. Milton Santos Ondina Bahia Salvador 40170-110 Brazil Models for Software Engineering (MAtisse) Department of Exact Sciences and Earth State University of Bahia 2555 Silveira Martins St. Cabula Bahia Salvador Brazil Post Graduate Program in Computing and Systems Salvador University 251 Dr. Jose Peroba St. Bahia Salvador Brazil Models for Software Engineering (MAtisse) Institute of Computing Federal University of Bahia Av. Milton Santos Ondina Bahia Salvador 40170-110 Brazil

Cloud Platforms are heterogeneous, and users may face interoperability issues migrating applications or exchanging data among distinct clouds due, for instance, to the lack of standards solutions. Several solutions have been proposed to overcome lock-in situations, and middleware platforms are one of them. A semantic interoperability solution named middleware for Data as a Service (DaaS)/Database as a Service (DBaaS) and Software as a Service (SaaS)—MIDAS has been developed to overcome this lock-in issue. It is an intermediate communication layer to retrieve data from DaaS or DBaaS through a Structured Query Language (SQL) or a Not Only SQL (NoSQL) created at the SaaS level. MIDAS is a platform for software execution, but software development needs support for its entire life cycle. Therefore, we propose the Model drIven Approach for MIDAS (MIAMI), which enables the specification of platform-independent middleware models and their use to generate code on different cloud platforms. MIAMI comprises a Domain-Specific Modeling Language (DSML) that enables middleware models and a transformation specification, which defines how these models can be converted to code. MIAMI offers a strategy for MIDAS specification and code generation phases to help middleware developers’ activities. MIAMI was applied to code generation specifications in Cloud Foundry, Amazon Web Services, OpenShift, and Heroku providers to evaluate our approach. This specification shows MIAMI’s feasibility and points out that MDD is a promising approach to improving cloud interoperability solutions. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Cloud computing Interoperability Metamodel Model-driven development

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Wound Reconstruction using Point Descriptors: A Comparative Study

Three-Dimensional Wound Reconstruction using Point Descripto...

引用

Annual IEEE Symposium on Computer-Based Medical systems

作者： José R. A. Souto Fellipe M. C. Barbosa Bruno M. Carvalho Graduate Program in Systems and Computing Federal University of Rio Grande do Norte Natal Brazil Department of Informatics and Applied Mathematics Federal University of Rio Grande do Norte Natal Brazil

Precise measurements of chronic wound areas are very important for measuring the efficacy of different treatments, since it provides a clear picture of the chosen treatment evolution. The most used techniques still in use for measuring the wound areas involve manual measuring, paper scales and/or acetate tracing, with each health professional possibly measuring the wounds in slightly different ways, specially when dealing with the wound's depth. Thus, it is common to observe inconsistent wound area estimations by different health workers on the same wounds. Moreover, the measuring process requires direct contact with the wound, increasing the contamination and infection risks, besides possibly causing discomfort for the patient. An alternative that has already been proved successful is the use of Structure from Motion (SfM) to recover three-dimensional representations of a wound's surface and estimate that area. In this work, we analyze the effectiveness of several widely used point descriptors (BRIEF, DRINK, FREAK, ORB, SIFT and SURF) in the SfM wound reconstruction task when applied to real images of realistic synthetic wounds made of latex placed on different areas of the body. The results showed that SIFT, SURF and DRINK produced better area estimates. Since the execution time is a factor, we selected DRINK as the standard descriptor for our system, since it is approximately 9.3 and 4.9 times faster than SIFT and SURF, respectively.

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：