检索结果-内蒙古大学图书馆

information technology Research and Innovation (ICITRI), International Conference on

作者： Nur Aini Hilman Ferdinandus Pardede Faculty of Technology Information Graduate School of Computer Science Universitas Nusa Mandiri Depok Indonesia Research Center for AI and Cybersecurity National Research and Innovation Agency Indonesia

Emotion recognition in facial images is a topic that has attracted many interests. Research on emotion recognition in facial images continues to face challenges such as variations of human faces due to environments or situations. Of all the techniques that have been used, the Deep Convolution Neural Network (DCNN) method reports a significant improvement compared to traditional machine learning methods. In recent years, self-attachment mechanisms have increased in popularity in DCNN, especially in Natural Language Processing. In this study, we propose to add attention networks to DCNN method to improve the performance of emotion recognition. By incorporating self-attention mechanisms into the model architecture, the network is able to recognize which facial features are most relevant for each emotion, increasing the accuracy and interpretation of the model. This study reports an accuracy of 69.55% which is 11.15% higher than using the traditional DCNN model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VMD-Inspired Bidirectional LSTM for Anomaly Detection of Hyperspectral Images 3

VMD-Inspired Bidirectional LSTM for Anomaly Detection of Hyp...

引用

3rd International Conference on Geology, Mapping and Remote Sensing, ICGMRS 2022

作者： He, Zhi Xiao, Man He, Dan Lou, Anjun Li, Xinyuan School of Geography and Planning Guangzhou510275 China National Key Laboratory of Science and Technology on Automatic Target Recognition China Sun Yat-sen University School of Geography and Planning Guangzhou510275 China School of Computer and Information Dongguan City College Dongguan511700 China Macau University of Science and Technology School of Computer Science and Engineering Faculty of Innovation Engineering China

ISBN: (数字)9781665485951

ISBN: (纸本)9781665485951

Anomaly detection plays an essential role in hyperspectral remote sensing. Various widespread detectors, such as ReedXiaoli (RX), sparse representation, or deep learning-based methods, have been developed by using the original spectral or spatial-spectral features. However, most of the existing methods cannot adaptively extract spatial-spectral information by integrating traditional and deep learning methods. In this paper, we propose a variational mode decomposition (VMD)-inspired bidirectional long short-term memory (termed as VbiLSTM) for anomaly detection of hyperspectral images (HSI). The VbiLSTM consists of three main modules, i.e., noise reduction module, intrinsic feature extraction module, and anomaly detection module. First, wavelet transform is performed on the original HSI datasets to reduce the noise. Second, VMD-guided biLSTM is proposed for intrinsic feature extraction of the denoised image. Finally, a one-class support vector machine (OCSVM) is adopted for anomaly detection by feeding the extracted features and the final detection results are an ensemble of detection results over all the features. Experiments performed on two HSI datasets demonstrate that the VbiLSTM achieves superior detection results compared with current state-of-the-art methods. © 2022 IEEE.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

The Effect of Management Accounting information Systems and Decision Making on Managerial Performance 5

The Effect of Management Accounting Information Systems and ...

引用

5th International Conference on Software and e-Business, ICSEB 2021

作者： Meiryani, Meiryani Gilberta, Gisela Arshanty, Risky Lindawati, A.S.L. Liawatimena, Suryadiputra Department of Accounting Faculty of Economics and Communication Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781450385831

This purpose of this study is find empirically The effect of management accounting information systems and decision making on managerial performance. The research method used is quantitative research methods with primary data obtained from questionnaire data which is measured using a likert scale. The result found that management accounting information system and decision making influence managerial performance. The results showed that the smaller the management accounting information system and decision making owned by the company, the smaller the percentage of managerial performance carried out in the company. The higher the management accounting information system, the higher the company's managerial performance. © 2021 ACM.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

MIN-DAS: The Digital Asset System Based on MIN Architecture

MIN-DAS: The Digital Asset System Based on MIN Architecture

引用

Communication technology and information technology (ICCTIT), International Conference on

作者： Rui Chen Hui Li Wuyang Li Yimin Yu Shao Kaili Kedan Li Shenzhen Graduate School Peking University Shenzhen China Information School University of Yunnan Finance and Economics Kunming China Faculty of Engineering Huanghe Science and Technology University Zhengzhou China Department of Computer Science University of Illinois Urbana-Champaign USA

ISBN: (数字)9798331528973

ISBN: (纸本)9798331528980

In this paper, we propose an innovative digital asset system based on the MIN (MIN-DAS), which integrates PPoV consortium blockchain technology along with NFT identifiers, achieving the rights confirmation, decentralization, and high security for digital asset trading. We first deployed the MIN-DAS within the high-security MIN network and designed a built-in MIN-VPN security tunnel, enabling end-to-end communication encryption, thereby significantly bolstering transaction security. Subsequently, we adopted the PPoV consortium blockchain as the core processing engine, greatly increasing the speed of transaction processing to accommodate large-scale transaction demands. Moreover, MIN-DAS supports stablecoin transactions, effectively mitigating risks stemming from cryptocurrency market fluctuations. MIN-DAS provides a secure and efficient solution for digital asset trading. Our experimental findings reveal that, compared to existing traditional digital asset platforms, MIN-DAS demonstrates significant superiority in both performance and security.

关键词： Fluctuations Smart contracts TCPIP User interfaces Throughput Encryption Security Nonfungible tokens information technology Engines

来源：评论

学校读者我要写书评

暂无评论

The Implementation of TOGAF for Enterprise System Planning on XYZ Campus

The Implementation of TOGAF for Enterprise System Planning o...

引用

Networking, Electrical Engineering, computer science, and technology (IConNECT), International Conference on

作者： Tamsir Hasudungan Sirait Ford Lumban Gaol Suhono Harso Supangkat Benny Ranti Binus Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department Bina Nusantara University Jakarta Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Computer Science Department Universitas Indonesia Jakarta Indonesia

Universities can employ information technology as one means of achieving their goals and objectives. Universities can get advantages from information technology, such as effective resource management and information management for decision-making. However, don't forget that the campus must consider what technology is appropriate to assist them achieve their goals, particularly in the current industrial era 4.0 where technology is available with many different choices. The campus requires an enterprise architecture in order to design, manage, and coordinate information technology infrastructure, applications, and processes strategically and thoroughly. The adoption of enterprise information system architecture (EA) is also intended to improve the quality of services provided to internal and external stakeholders. In this case, Enterprise Architecture can help an organization to match its information technology resources with business processes and strategies to achieve their goals. This research was conducted using TOGAF ADM, also known as the Open Group Architecture Framework Architecture Development Method. This method offers best practices for creating enterprise architecture and emphasizes several steps that include creating an architectural vision, information systems, business architecture modeling to help XYZ campus manage all their information technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid IoT programming with Data Flow Diagrams and mruby

Hybrid IoT Programming with Data Flow Diagrams and mruby

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Kazuaki Tanaka Sota Ogura R. Krishnamoorthy Faculty of Information Engineering Kyushu Institute of Technology Iizuka Fukuoka Japan Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Fukuoka Japan Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai India

ISBN: (数字)9798331522728

ISBN: (纸本)9798331522735

IoT is increasingly being used in different areas of society. IoT is used in society by collecting values acquired by sensor devices through networks and analysing the data. IoT software is needed to use the IoT, but efficient software development methods are desired because software for an increasingly complex society tends to become more complex. This research aims to improve the efficiency of IoT software and develop an intuitive method for developing IoT *** paper proposes a development methodology that combines a data-flow-based programming approach with a procedural programming language. When the focus is on data, data flow programming is intuitive and efficient. On the other hand, when the focus is on data processing, it is better to use a procedural programming language because data is processed sequentially[1].In the hybrid IoT programming environment proposed in this paper, the code of a procedural programming language is generated from the description by data flow programming, and the program is executed by a micro *** products of this research are available as open source software[2], [3].

关键词： Hands computer languages Codes programming Data processing Hybrid power systems Open source software Software development management programming environments

来源：评论

学校读者我要写书评

暂无评论

MERNet: Multimodal Emotion Recognition in Conversation Network via Cross-Modal Knowledge Distillation and Contrastive Learning

MERNet: Multimodal Emotion Recognition in Conversation Netwo...

引用

2025 IEEE International Conference on Big Data and Smart Computing, BigComp 2025

作者： Hwang, Sooyeon Gweon, Gahgene Kwon, Eunseong Seoul National University Interdisciplinary Program in Artificial Intelligence Korea Republic of Seoul National University Graduate School of Convergence Science and Technology Korea Republic of POSTECH Dept. of Computer Science and Engineering Korea Republic of

Multimodal Emotion Recognition in Conversation (ERC) is a task of predicting the emotion of each utterance in a conversation by utilizing both verbal and non-verbal modalities. However, existing approaches often struggle to bridge cross-modal gaps, resulting in misaligned features and frequent misclassification of minority emotions into semantically similar majority emotions. To address these challenges, we propose MERNet, a framework that employs cross-modal knowledge distillation and contrastive learning to align multimodal features and effectively distinguish subtle emotions in conversations. Our framework consists of two stages: 1) guiding non-verbal modalities with the text modality to transfer knowledge and align their features, and 2) applying contrastive learning with emotion labels as anchors to distinguish subtle differences between similar emotions and address the class imbalance problem. Experiments conducted on two benchmark datasets, IEMOCAP and MELD, demonstrate that our MERNet outperforms existing state-of-the-art models. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Imperceptible and Sparse Adversarial Attacks via a Dual-Population-Based Constrained Evolutionary Algorithm

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第2期4卷 268-281页

作者： Tian, Ye Pan, Jingwen Yang, Shangshang Zhang, Xingyi He, Shuping Jin, Yaochu Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230088 China Anhui University School of Computer Science and Technology Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Hefei230601 China Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Hefei230601 China Bielefeld University Faculty of Technology Bielefeld33619 Germany

The sparse adversarial attack has attracted increasing attention due to the merit of a low attack cost via changing a small number of pixels. However, the generated adversarial examples are easily detected in vision since the perturbation to each pixel is relatively large. To achieve imperceptible and sparse adversarial attacks, this article formulates a bi-objective constrained optimization problem, simultaneously minimizing the 0 and 2 distances to the original image, and proposes a dual-population-based constrained evolutionary algorithm to solve it. The proposed method solves the optimization problem by evolving two populations, where one population is responsible for finding feasible solutions (i.e., successful attacks) and the other one is to minimize both the 0 and 2 distances. Moreover, a population initialization strategy and two genetic operators are customized to accelerate the convergence speed. Experimental results indicate that the proposed method can achieve high success rates with low attack costs, and strikes a better balance between the 0 and 2 distances than state-of-the-art methods. © 2020 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Video Steganography for Image and Text Using Deep Genetic Algorithm and LSB

引用

International Journal of Network Security 2022年第1期24卷 140-146页

作者： Selim, Nouran Mohamed Guirguis, Shawkat Kamal Hassan, Yasser Fouad Computer Science Department Faculty of Science Alexandria University Alexandria Egypt Information Technology Department Institute of Graduate Studies and Research Alexandria University Alexandria Egypt Faculty of computer science and AI Pharos University Egypt

Data security is a threat for delivering data through the internet, and it is concerned with protecting sensitive data from unauthorized access. The security threats increase with the increase of sensitive data, so security issues should be considered because hackers may use vulnerabilities over public networks to thieve the information. Video steganography is considered an efficient technique and becomes an important research area for data security. This paper aims to embed images and text into a video. The proposed algorithm selects the best frames and pixels for embedding images and the best video tags to hide text. As a result, the video’s size and visual quality are not altered even after embedding secret data. © 2022. All Rights Reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

A Slot Antenna Array With Low Cross-Polarization Level Based on a Novel Substrate Integrated Coaxial Line Feeding Structure

A Slot Antenna Array With Low Cross-Polarization Level Based...

引用

2023 IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications, IMWS-AMP 2023

作者： Shen, Shuhao Zhou, Kang Dong, Chunli School of Electrical Information and Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo315200 China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China

ISBN: (纸本)9798350308761

A slot antenna array with low cross-polarization level based on a novel substrate integrated coaxial line (SICL) feeding structure is proposed in this paper. The longitudinal slots are etched on the top layer as the radiation part, thus a broadside radiation characteristic can be achieved. Two sets of SICL are arranged on both sides to feed the quasi-substrate integrated double line (SIDL), and the length of the quasi-SIDL is adjusted to obtain the optimal slot etching scheme. A slot antenna array covering 27.1-27.6 GHz is designed and verified. The simulated results show that the peak gain is more than 8.6 dBi, while the cross-polarization level is better than 43.9 dB. The excellent radiation performance makes it a strong competitor for millimeter-wave (mm-wave) wireless applications. © 2023 IEEE.

关键词： Low cross-polarization level millimeter-wave slot antenna array substrate integrated coaxial line (SICL)

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：