检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zaidi, Syed Aun Muhammad Latif, Siddique Qadir, Junaid USQ Australia Distributed Sensing Systems Group Data61 CSIRO Australia Computer Science and Engineering Department College of Engineering Qatar University Doha Qatar

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Transformer (MDAT) model to improve cross-language SER. Our model utilises pretrained models for multimodal feature extraction and is equipped with a dual attention mechanism including graph attention and co-attention to capture complex dependencies across different modalities and achieve improved cross-language SER results using minimal target language data. In addition, our model also exploits a transformer encoder layer for high-level feature representation to improve emotion classification accuracy. In this way, MDAT performs refinement of feature representation at various stages and provides emotional salient features to the classification layer. This novel approach also ensures the preservation of modality-specific emotional information while enhancing cross-modality and cross-language interactions. We assess our model's performance on four publicly available SER datasets and establish its superior effectiveness compared to recent approaches and baseline models. Copyright © 2023, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Unearthing Undiscovered Interests: Knowledge Enhanced Representation Aggregation for Long-Tail Recommendation 1

引用

10th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making, IUKM 2023

作者： Zhang, Zhipeng Zhang, Yuhang Hao, Tianyang Li, Zuoqing Zhang, Yao Inuiguchi, Masahiro School of Computer Science and Artificial Intelligence Liaoning Normal University Dalian China Dalian Gona Technology Group Co. Ltd. Dalian China School of Mechanical Engineering and Automation Dalian Polytechnic University Dalian China Department of Systems Innovation Osaka University Osaka Japan

ISBN: (数字)9783031467813

ISBN: (纸本)9783031467806

Graph neural networks have achieved remarkable performance in the field of recommender systems. However, existing graph-based recommendation approaches predominantly focus on suggesting popular items, disregarding the significance of long-tail recommendation and consequently falling short of meeting users’ personalized needs. To this end, we propose a novel approach called Knowledge-enhanced Representation Aggregation for Long-tail Recommendation (KRALR). Firstly, KRALR employs a user long-tail interests representation aggregation procedure to merge historical interaction information with rich semantic data extracted from knowledge graph (KG). By utilizing random walks on the KG and incorporating item popularity constraints, KRALR effectively captures the long-tail interests specific to the target user. Furthermore, KRALR introduces a long-tail item representation aggregation procedure by constructing a co-occurrence graph and integrating it with the KG. This integration enhances the quality of the representation for long-tail items, thereby enabling KRALR to provide more accurate recommendations. Finally, KRALR predicts rating scores for items that users have not interacted with and recommends the top N un-interacted items with the highest rating scores. Experimental results on the real-world dataset demonstrate that KRALR can improve recommendation accuracy and diversity simultaneously, and provide a wider array of satisfactory long-tail items for target users. Code is available at https://***/ZZP-RS/KRALR. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Study on Effects of Synthetic Data for Predicting the Remaining Useful Life of Aluminium Electrolytic Capacitors Using Bagging-Based Ensemble Learning 2nd

A Study on Effects of Synthetic Data for Predicting the Rema...

引用

2nd International Conference on Advances in Data-driven Computing and Intelligent systems, ADCIS 2023

作者： Bhattacharyya, Anindya Srijith, K. Behera, R.P. Dasgupta, Arup Chakraborty, R.S. Real Time Systems Division Electronics & Instrumentation Group Indira Gandhi Centre for Atomic Research Tamil Nadu Kalpakkam603102 India Birla Institute of Technology and Science Hyderabad Campus Telangana Secunderabad500078 India Physical Metallurgy Division Materials Characterization Group Metallurgy and Materials Group Indira Gandhi Centre for Atomic Research Tamil Nadu Kalpakkam603102 India Homi Bhabha National Institute Training School Complex Anushaktinagar Mumbai400094 India Department of Computer Science and Engineering IIT Kharagpur Kharagpur721302 India

ISBN: (纸本)9789819995172

Aluminium electrolytic capacitors (AECs) are crucial components used in power supplies, computer motherboards, and variable frequency drives for ripple filtering and energy storage. Their performance is affected by factors like temperature, frequency, ripple current, and ageing. Despite design advancements, AECs remain reliability weak points, demanding thorough analysis. This research proposes a method to predict the Remaining Useful Life (RUL) of AECs under combined temperature and voltage stress. We develop an RUL prediction model using bagged decision trees by ageing 24 AEC samples and tracking degradation via capacitance and ESR changes. Synthetic data strengthens the model due to limited training data. We assess the impact of different minority oversampling methods like SMOTE, SMOTER, and SMOGN on prediction accuracy, using ANOVA to compare outcomes within and between algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Analysis of variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

Joint Hybrid Beamforming and RIS Phase Shift Design for RIS-Enabled Mmwave ISAC System

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Lu Abanto-Leon, Luis F. Asadi, Arash Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum Germany Technical University of Darmstadt Department of Computer Science Darmstadt64289 Germany TU Delft Embedded Systems Group DelftCD 2628 Netherlands

Empowering cellular networks with augmented sensing capabilities is a key research area in sixth generation (6 G) communication systems. Recently, we have witnessed a plethora of efforts to devise solutions that integrate sensing capabilities into communication systems, i.e., integrated sensing and communication (ISAC), especially at millimeter-wave (mmWave) frequencies with large bandwidths. Despite the challenges posed by severe path loss and blockage at mmWave bands, this work incorporates reconfigurable intelligent surfaces (RISs) into ISAC systems to enhance both sensing and communication. To comply with the waveform utilized in current cellular systems, this paper studies mmWave orthogonal frequency-division multiplexing (OFDM) ISAC systems in the presence of RISs. Specifically, we jointly design the hybrid beamforming and RIS phase shifts to guarantee the sensing functionalities via minimizing the beampattern mean squared error at RIS, subject to signal-to-interference-plus-noise (SINR) and power constraints. The non-convexity of the investigated problem poses a challenge which we address by proposing a solution based on the penalty method and manifold-based alternating direction method of multipliers (ADMM). Simulation results demonstrate that both sensing and communication capabilities improve when the RIS is adequately designed. In addition, we discuss the tradeoff between sensing and communication. © 2025 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

An Intriguing Relation Between the Power Consumption and Number of Antenna Elements in Multi-Beam Phased Arrays

An Intriguing Relation Between the Power Consumption and Num...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Natasha Birari Yanki Aslan Alexander Yarovoy Department of Microelectronics Faculty of Electrical Engineering Mathematics and Computer Science Microwave Sensing Signals and Systems Group Delft University of Technology Delft The Netherlands

An improved system-level power consumption model (PCM) for 5G base station multi-beam phased-array transmit architectures is developed. Using this model, it is shown that an optimum number of antenna elements of the array exists with respect to the total power consumption. The proposed model is benchmarked against a recent study which is shown to underestimate the total power consumed in analog and digital antenna systems by 37% and 126% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transformer Health Monitoring via Synchrophasors

Transformer Health Monitoring via Synchrophasors

引用

International Conference on Environment and Electrical engineering (EEEIC)

作者： Gian Paramo Arturo Bretas Electrical and Computer Engineering University of Florida Gainesville FL USA Distributed Systems Group Pacifc Northwest National Laboratory Richland WA USA

Traditional transformer protection schemes such as differential protection operate once the transformer is in a critical state. Proactive means of transformer health evaluation such as Sweep Frequency Response Analysis, can only be performed periodically with the transformer out-of-service. This work presents a framework where the health and structural integrity of transformers is monitored via synchrophasors in real-time. Synchrophasors and subspace estimation techniques are used to build reduced-order models which are then analyzed across multiple domains. A diagnostics algorithm is developed and tested via Matlab simulations. Test results are promising, opening up new prospects in transformer protection research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Impedance Non-Linear Fault Detection via Eigenvalue Analysis with low PMU Sampling Rates

High-Impedance Non-Linear Fault Detection via Eigenvalue Ana...

引用

Innovative Smart Grid Technologies (ISGT)

作者： Gian Paramo Arturo Bretas Sean Meyn Electrical and Computer Engineering University of Florida Gainesville FL USA Distributed Systems Group Pacifc Northwest National Laboratory Richland WA USA

This work presents a hybrid data-driven and physics-based framework for high-impedance fault detection in power systems. An innovative method based on eigenvalue analysis is expanded and validated. Phasor Measurement Unit data is used to estimate eigenvalues corresponding to the powerlines being monitored. Eigenvalue statistics are then tracked and evaluated. Faults are detected as they drive eigenvalues outside of their normal zones. This technique holds several advantages over contemporary techniques: It utilizes technology that is already deployed in the field, it offers a significant degree of generality, and so far it has displayed a very high-level of sensitivity without sacrificing accuracy. Validation is performed in the form of simulations based in the IEEE 13 Node System and non-linear fault models. Test results are encouraging, indicating potential for real-life applications.

关键词： Sensitivity Measurement units Impedance measurement Fault detection Energy measurement Eigenvalues and eigenfunctions Phasor measurement units

来源：评论

学校读者我要写书评

暂无评论

Shaped-Beam Subarrays for Equi-Power Urban Area Coverage With Modularity and Low Cost

Shaped-Beam Subarrays for Equi-Power Urban Area Coverage Wit...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Changxu Zhao Alexander Yarovoy Antoine Roederer Yanki Aslan Department of Microelectronics Aculty of Electrical Engineering Mathematics and Computer Science Microwave Sensing Signals and Systems Group Delft University of Technology Delft The Netherlands

Design of millimeter-wave arrays for base stations operating in dense urban environment is investigated. Innovative designs for linear subarrays with shaped beam patterns for hybrid beamforming are proposed. The number of elements and element spacings in the subarrays are optimally selected based on a pattern matching technique. The subarrays are designed and verified in series edge-fed slotted substrate integrated waveguide technology at 26 GHz. A novel phase shifter unit is proposed to reduce the subarray width for grating lobe-free beam steering in the plane orthogonal to the sub-array axis. Infinite array simulations are performed to observe the coupling effects on the subarrays.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digitization and Secure Process of Forensic Data Management Using Blockchain

Digitization and Secure Process of Forensic Data Management ...

引用

IEEE International Conference on System, Computation, Automation and Networking (ICSCAN)

作者： R. Indhumathi P. Mathivanan K. Mahalakshmi K. Subha Nanda S. Krishna Department of Computer Science and Engineering Manakula Vinayagar Institute of Technology Puducherry India Department of Computer Science and Business Systems KIT - Kalaignarkarunanidhi Institute of Technology Coimbatore India Department of Computer Science and Engineering Surya Group of Institutions Villuppuram India

Cyber threats and data manipulation are the main concerns in this technological society. The investigator finds it challenging to submit evidence to the court because of the information breach as continuity documentation of records is very critical for safeguarding against criminal events. Blockchain-based digital forensic data management systems have been developed to deal with this issue of Privacy preservation for evidence items. Blockchain technology provides authentication, immutability, traceability, resilience, and distributed trust for forensic data. In order to ensure security and ease of use, the system utilizes onion architecture. Data can be stored and analysed whenever required. They provide trust between the examiners and the system. The system is a multi-platform system that provides effective usage where it can be accessed and used from anywhere. The honest information is make sure to follow the crime investigator of the steps. if we use the propose system of block chain, it is can't be altered the evidence during the submission of court. The storing data of each block is verify and added to the blockchian. The creation of safe database was implemented by a decentralised network with bitcoin and networks of cryptocurrency. In proposed system, the blockchain technology helps in can't able to access and altered the data during the investigation periods. This system is used to implements the easily accessed and used in anywhere.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Embedded Element Pattern Prediction via Machine Learning: A Case Study with Planar Non-Uniform Sub-Arrays

Efficient Embedded Element Pattern Prediction via Machine Le...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Nehir Berk Onat Ignacio Roldan Francesco Fioranelli Alexander Yarovoy Yanki Aslan Department of Microelectronics Faculty of Electrical Engineering Mathematics and Computer Science Microwave Sensing Signals and Systems Group Delft University of Technology Delft The Netherlands

Efficient prediction of embedded element patterns (EEPs) is including the mutual coupling (MC) effects in the optimization of irregular planar arrays is studied for the first time in the literature. An ANN-based methodology is used to predict the pattern of each element in the whole visible space for a flexible planar array topology in milliseconds. The technique is proposed is validated on a 4-element planar non-uniform sub-array structure. Excellent accuracy on the EEP prediction while providing great efficiency in computational time and load in comparison to the full-wave simulations is demonstrated.

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：