检索结果-内蒙古大学图书馆

Fusion of speech and handwritten signatures biometrics for person identification

International Journal of Speech Technology 2023年第4期26卷 833-850页

作者： Abushariah, Ahmad A. M. Abushariah, Mohammad A. M. Gunawan, Teddy Surya Chebil, J. Alqudah, Assal A. M. Ting, Hua-Nong Mustafa, Mumtaz Begum Peer Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia Department of Computer Information Systems King Abdullah II School of Information Technology The University of Jordan Amman Jordan ECE Department Faculty of Engineering International Islamic University Malaysia Kuala Lumpur53100 Malaysia Department of Computer Science Faculty of Science and Information Technology Al-Zaytoonah University of Jordan Amman Jordan Department of Biomedical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

Automatic person identification (API) using human biometrics is essential and highly demanded compared to traditional API methods, where a person is automatically identified using his/her distinct characteristics including speech, fingerprint, iris, handwritten signatures, and others. The fusion of more than one human biometric produces bimodal and multimodal API systems that normally outperform single modality systems. This paper presents our work towards fusing speech and handwritten signatures for developing a bimodal API system, where fusion was conducted at the decision level due to the differences in the type and format of the features extracted. A data set is created that contains recordings of usernames and handwritten signatures of 100 persons (50 males and 50 females), where each person recorded his/her username 30 times and provided his/her handwritten signature 30 times. Consequently, a total of 3000 utterances and 3000 handwritten signatures were collected. The speech API used Mel-Frequency Cepstral Coefficients (MFCC) technique for features extraction and Vector Quantization (VQ) for features training and classification. On the other hand, the handwritten signatures API used global features for reflecting the structure of the hand signature image such as image area, pure height, pure width and signature height and the Multi-Layer Perceptron (MLP) architecture of Artificial Neural Network for features training and classification. Once the best matches for both the speech and the handwritten signatures API are produced, the fusion process takes place at decision level. It computes the difference between the two best matches for each modality and selects the modality of the maximum difference. Based on our experimental results, the bimodal API obtained an average recognition rate of 96.40%, whereas the speech API and the handwritten signatures API obtained average recognition rates of 92.60% and 75.20%, respectively. Therefore, the bimodal API system is a

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Improved Ingredients-based Recipe Recommendation software using Machine Learning 11

Improved Ingredients-based Recipe Recommendation Software us...

引用

11th IEEE International Conference on Intelligent Computing and Information Systems, ICICIS 2023

作者： Ashraf, Mariam Tarek, Khadija Fathy, Naglaa Mahmoud, Mariam Emad, Rana Khaled, Khadija Amr, Noran Ain Shams University Faculty of Computer and Information Science Software Engineering Department Cairo Egypt Ain Shams University Faculty of Computer and Information Science Information Systems Department Cairo Egypt

ISBN: (纸本)9798350322101

In this paper we propose an improved recipe recommendation system that employs image recognition of food ingredients. The system is currently a mobile application that performs image recognition on uploaded or camera-captured images and recommends recipes containing the recognized ingredients. We used the ResNet-V2 architecture to build a convolutional neural network model for image recognition, which was able to identify 33 different food ingredients with an accuracy rate of 89%. The recommendation system uses the identified ingredient labels, as well as user preferences and restrictions, to display a list of recipes containing the identified ingredients. This feature allows users to discover new and exciting recipes based on the ingredients they currently have at home, without having to worry about dietary restrictions or other preferences. Overall, our system provides a convenient and personalized way for users to discover and prepare delicious meals based on their unique needs and preferences. © 2023 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin Based Framework for Real-Time Machine Condition Monitoring 19

A Digital Twin Based Framework for Real-Time Machine Conditi...

引用

19th IEEE International Conference on Automation science and engineering, CASE 2023

作者： Chen, Zixiao Choudhury, Madhurjya Dev Blincoe, Kelly Dhupia, Jaspreet Singh University of Auckland Department of Mechanical and Mechatronics Engineering New Zealand School of Engineering and Computer Science Victoria University of Wellington New Zealand University of Auckland Department of Electrical Computer and Software Engineering New Zealand

ISBN: (纸本)9798350320695

Condition Monitoring (CM) is an important approach to extending the life of complex equipment by forecasting the outcome of an event before catastrophic failure occurs. Recent advancements in digital twins (DT) offer additional benefits to machine condition monitoring. In this study, a framework based on DT for real-time condition monitoring of industrial machines is proposed. The multi-layer DT framework consists of a physical entity (PE), virtual equipment (VE), edge device, fidelity service and digital twin services. The virtual equipment is a replica of the physical entity or the monitored machine. It also contains a cloud platform to store data online and an application to interface with the cloud enabling users to check the data remotely. The fidelity service ensures conformity between the PE and the VE. The digital service provides optimal operation and maintenance schedules based on the data from both physical and virtual spaces. The integration of the edge layer enables real-time handling of high-frequency machine data for effective health monitoring. The validity of the proposed framework is demonstrated with a case study based on monitoring a critical component of an industrial drivetrain test rig. The features of the framework allow end-users to visualize the component's real-time health status remotely. © 2023 IEEE.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference 30

RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Mul...

引用

30th IEEE Real-Time and Embedded Technology and Applications Symposium, RTAS 2024

作者： Kang, Woosung Lee, Jinkyu Lee, Youngmoon Oh, Sangeun Lee, Kilho Chwa, Hoon Sung DGIST Dept. of Electrical Engineering and Computer Science Korea Republic of Dept. of Computer Science and Engineering Korea Republic of Hanyang University Dept. of Robotics Korea Republic of Ajou University Department of Software and Computer Engineering Korea Republic of School of AI Convergence Soongsil University Korea Republic of

ISBN: (纸本)9798350358414

The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-Time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-Time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU's physical capacity. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Contextual defeasible reasoning framework for heterogeneous knowledge sources

Contextual defeasible reasoning framework for heterogeneous ...

引用

作者： Mahfooz ul Haque, Hafiz Muhammad Akhtar, Salwa Uddin, Ijaz Department of Software Engineering University of Lahore Lahore Pakistan Department of Computer Science University of Lahore Lahore Pakistan Department of Computer Science City University of Science and Information Technology Peshawar Pakistan University of Lahore Lahore Pakistan

Recent years have witnessed the rapid advances of smart computing paradigms in a ubiquitous environment. These paradigms make human life much easier, comfortable, secure and hassle free. In a smart computing environment, it is a fact that human users interact with the systems dynamically with or without human intervention using different modalities. The core emphasize is given on the intelligent systems that run in a highly decentralized environment with different communication mechanism. Literature highlighted numerous formalisms to bridge the communication modalities for different knowledge sources. Among others, Multi-context System (MCS) has been advocated as one of the most suitable formalism to interlink different contexts (domains) dynamically in the distributed environment. However, interaction of these knowledge sources sometime may produce inconsistent and conflicting results. In this work, we presents a contextual defeasible reasoning based multi-agent formalism to handle the inconsistency issues. This framework relies on the semantic knowledge sources which allow us to model context-aware non-monotonic reasoning agents to infer the desired goals using the extracted rules from the ontologies and handles inconsistencies using conflicting contextual information. We illustrate the validity and correctness of the proposed formalism using a simple case study of a smart healthcare system with the prototypal implementation of the system. © 2021 John Wiley & Sons Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Faithfulness Measurable Masked Language Models 41

Faithfulness Measurable Masked Language Models

引用

41st International Conference on Machine Learning, ICML 2024

作者： Madsen, Andreas Reddy, Siva Chandar, Sarath Mila Montreal Canada Computer Engineering and Software Engineering Department Polytechnique Montreal Montreal Canada Computer Science and Linguistics McGill University Montreal Canada Facebook CIFAR AI Canada Canada CIFAR AI Canada

A common approach to explaining NLP models is to use importance measures that express which tokens are important for a prediction. Unfortunately, such explanations are often wrong despite being persuasive. Therefore, it is essential to measure their faithfulness. One such metric is if tokens are truly important, then masking them should result in worse model performance. However, token masking introduces out-of-distribution issues, and existing solutions that address this are computationally expensive and employ proxy models. Furthermore, other metrics are very limited in scope. This work proposes an inherently faithfulness measurable model that addresses these challenges. This is achieved using a novel fine-tuning method that incorporates masking, such that masking tokens become in-distribution by design. This differs from existing approaches, which are completely model-agnostic but are inapplicable in practice. We demonstrate the generality of our approach by applying it to 16 different datasets and validate it using statistical in-distribution tests. The faithfulness is then measured with 9 different importance measures. Because masking is in-distribution, importance measures that themselves use masking become consistently more faithful. Additionally, because the model makes faithfulness cheap to measure, we can optimize explanations towards maximal faithfulness;thus, our model becomes indirectly inherently explainable. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Semantic and Attentive Network for Unsupervised Video Summarization

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2022年第2期18卷 1-21页

作者： Zhong, Sheng-Hua Lin, Jingxu Lu, Jianglin Fares, Ahmed Ren, Tongwei College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Electrical Engineering Computer Systems Engineering Program Faculty of Engineering at Shoubra Benha University Cairo Egypt State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China

With the rapid growth of video data, video summarization is a promising approach to shorten a lengthy video into a compact version. Although supervised summarization approaches have achieved state-of-the-art performance, they require frame-level annotated labels. Such an annotation process is time-consuming and tedious. In this article, we propose a novel deep summarization framework named Deep Semantic and Attentive Network for Video Summarization (DSAVS) that can select the most semantically representative summary by minimizing the distance between video representation and text representation without any frame-level labels. Another challenge associated with video summarization tasks mainly originates from the difficulty of considering temporal information over a long time. Long Short-Term Memory (LSTM) performs well for temporal dependencies modeling but does not work well with long video clips. Therefore, we introduce a self-attention mechanism into our summarization framework to capture the long-range temporal dependencies among the frames. Extensive experiments on two popular benchmark datasets, i.e., SumMe and TVSum, show that our proposed framework outperforms other state-of-the-art unsupervised approaches and even most supervised methods. © 2022 Association for Computing Machinery.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction using CuDNNLSTM and multiple CNN layers

Stock Price Prediction using CuDNNLSTM and multiple CNN laye...

引用

2023 IEEE International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2023

作者： Kanwal, Anika Chandrasekaran, Siva Akhunzada, Adnan Swinburne University of Technology Department of Computer Science and Software Engineering Melbourne Australia University of Doha for Science and Technology Department of Computing and Information Technology Doha Qatar

ISBN: (纸本)9798350322347

Academic and financial sectors are interested in research areas that focus on understanding the patterns of financial activities and predicting their future changes. The daily movement of financial data involves complex, insufficient, and ambiguous information, making its prediction an extremely difficult endeavour. The issues of forecasting and analysing financial data is therefore complex and time-dependent. Deep neural networks (DNNs) can be used to solve nonlinear problems more effectively than conventional machine learning techniques. This study proposes an intelligent and optimal model CuDNNLSTM-Multi(1dCNN) for stock market price prediction using a hybrid of CUDA based Long Short Term Memory (LSTM) and Multiple One Dimensional Convolution Neural Networks (CNNs). A variety of models, including Multiple CuDNNLSTM-CNN, Multi-CuDNNLSTM, Multi (1dCNN), are used to compare the prediction performance of the proposed model. In terms of RMSE, MAE, and MAPE, the results show that the suggested model outperforms all hybrid and individual models. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Provably Secure Lightweight Key Agreement Protocol for Wireless Body Area Networks in Healthcare System

引用

IEEE Transactions on Industrial Informatics 2023年第2期19卷 1683-1690页

作者： Zia, Maryam Obaidat, Mohammad S. Mahmood, Khalid Shamshad, Salman Saleem, Muhammad Asad Chaudhry, Shehzad Ashraf Comsats University Islamabad Department of Computer Science Sahiwal57000 Pakistan University of Jordan King Abdullah Ii School of Information Technology Amman11942 Jordan University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Amity University UP Noida201301 India National Yunlin University of Science and Technology Future Technology Research Center Yunlin64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan Abu Dhabi University Department of Computer Science and Information Technology College of Engineering Abu Dhabi United Arab Emirates Nisantasi University Department of Computer Engineering Faculty of Engineering and Architecture Istanbul34398 Turkey

Wireless Body Area Network (WBAN) is a vital application of the Internet of Things (IoT) that plays a significant role in gathering a patient's healthcare information. This collected data helps special professionals like doctors or physicians analyze patients' health status to cure different diseases. However, collecting such information from an insecure channel can be threatening due to the potential security threats. Therefore, it is crucial to secure this sensitive information. This article proposes a secure and lightweight authentication protocol for WBAN. The devised protocol is scalable, secure, and lightweight compared to various relevant competing protocols. The informal security analysis shows that the designed protocol is lightweight, secure, and efficient in resisting various major attacks. The performance analysis demonstrates our protocol's supremacy over various competing protocols in terms of computation and communication costs, inducing efficiency of 20.3% and 12.3%, respectively. Moreover, the practical performance of the designed protocol from the network point of view is measured using the widely recognized NS3 simulation tool. © 2005-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Speech Signal for COVID-19 Diagnostics 6

Artificial Intelligence-based Speech Signal for COVID-19 Dia...

引用

6th International Conference on Future Networks and Distributed Systems, ICFNDS 2022

作者： Alfaidi, Aseel Alshahrani, Abdullah Aljohani, Maha Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Saudi Arabia Department of Software Engineering College of Computer Science and Engineering University of Jeddah Saudi Arabia

ISBN: (纸本)9781450399050

The speech signal has numerous features that represent the characteristics of a specific language and recognize emotions. It also contains information that can be used to identify the mental, psychological, and physical states of the speaker. Recently, the acoustic analysis of speech signals offers a practical, automated, and scalable method for medical diagnosis and monitoring symptoms of many diseases. In this paper, we explore the deep acoustic features from confirmed positive and negative cases of COVID-19 and compare the performance of the acoustic features and COVID-19 symptoms in terms of their ability to diagnose COVID-19. The proposed methodology consists of the pre-trained Visual Geometry Group (VGG-16) model based on Mel spectrogram images to extract deep audio features. In addition to the K-means algorithm that determines effective features, followed by a Genetic Algorithm-Support Vector Machine (GA-SVM) classifier to classify cases. The experimental findings indicate the proposed methodology's capability to classify COVID-19 and NOT COVID-19 from acoustic features compared to COVID-19 symptoms, achieving an accuracy of 97%. The experimental results show that the proposed method remarkably improves the accuracy of COVID-19 detection over the handcrafted features used in previous studies. © 2022 ACM.

关键词： COVID-19

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：