检索结果-内蒙古大学图书馆

4th international conference on Computer, Big data and Artificial Intelligence, ICCBD+AI 2023

作者： Wang, Rui Wang, Jiong Qiyuan Lab Beijing China The 21st Research Institute of China Electronics Technology Group Corporation Robotics Engineering Center Shanghai China

ISBN: (纸本)9798350373233

The existing federated learning models have issues such as malicious central servers and malicious participants publishing false data to poison the model. Aiming at this case, this thesis proposed an improved decentralized federated learning model (IDFL), which moves the aggregation work from the central server to the local participants. In this paper, a proof-of-training consensus mechanism is proposed, which makes the election of block producers based on the quality of model training rather than the competition mechanism, thus effectively avoiding the block generation delay caused by the mining process, and also alleviating the blocking problem in the verification of model parameters in an asynchronous manner. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Design of receiver RF front end for mm-Wave 5G applications 21

Design of receiver RF front end for mm-Wave 5G applications

引用

21st international learning and Technology conference, L and T 2024

作者： Hussein, Aziza I. Alamoudi, Nora Ali, Mirna Zakaria, Ahmed Mourad Mabrook, M. Effat University College of Engineering Energy and Technology Research Center Saudi Arabia Effat University Electrical and Computer Engineering Department Jeddah Saudi Arabia Telecom Egypt Telecommunication Engineer Asyut Egypt Beni-Suef University Faculty of Navigation Science & Space Technology Space Communication Dept. Egypt

ISBN: (纸本)9798350393569

Recently, the research emphasis has shifted towards 5G due to its potential to accommodate the increasing demand for data traffic, extensive interconnectivity of devices, and the emergence of numerous novel applications. Given the inadequacy of speed provided by spectrum resources in the lower frequency bands of 5G, a novel sub-generation utilizing millimeter wave frequencies has been introduced. The new sub-generation is called mm-wave 5G and provides higher bandwidth for faster speed and higher capacity. RF system architecture, circuits, and antenna innovation will be required to provide the requisite speed and capacity. In this paper the design challenges and trade-offs in RF front-end circuits and receiver sub-systems are discussed. Moreover, the massive multiple-input multiple-output (MIMO) techniques are examined. In addition, design, and simulation of key components in 5G mm-wave receiver, including the design of linear phased array antenna receiver and an analog-to-digital converter (ADC) is presented. Sigma-Delta (ΣΔM) Converters are a type of ADC with a technique that involves oversampling and shaping quantization noise to achieve a higher resolution which make it a best choice to be used in the design of the mm wave 5G communication applications. The proposed ΣΔM uses multistage architecture to provide high-order noise shaping and high resolution. The simulation results shows that the designed Cascade 2-2 MASH ΣΔ achieve a signal to noise ratio of 110(resolution of 16 bits). © 2024 IEEE.

关键词： Antenna phased arrays

来源：评论

学校读者我要写书评

暂无评论

Does data Balancing Impact stutter Detection and Classification? 21st

Does Data Balancing Impact Stutter Detection and Classificat...

引用

21st international conference on Distributed Computing and intelligent Technology

作者： Batra, Ashita Shrivastava, Pratyush Das, Pradip K. Indian Inst Technol Guwahati Gauhati 781039 India

ISBN: (纸本)9783031814037;9783031814044

stuttering, a speech impediment that significantly impacts an individual's personality and daily life, is a critical research area requiring technological solutions. Therefore, bringing our attention, we analyzed speech utterances of people who stutter, using recordings from the publicly available Sep-28k dataset, which consists of natural conversations from podcasts. A major focus has been put on analyzing the fact that data imbalance plays a role in learning the characteristics of a speech utterance. We have used a sampling technique by considering the middle value of samples calculated from the minority and the majority class and this serves as a combination of up-sampling and down-sampling. This helps us to avoid bias in the class-wise characteristic learning of the model. The proposed approach focuses on two feature extraction techniques, specifically Mel-Frequency Cepstral Coefficients (MFCCs), del-del MFCC and a comprehensive analysis using the openSMILE toolkit, selecting only the ComParE2016 features. We conducted a comparative study between various machine learning models like random forest (RF), support vector machine (SVM) and time-delayed neural network (TDNN) using both features. Our findings indicated that the stutter class outperformed the no stutter class by a significant margin for each classifier in binary classification. This prompted us to conduct two experiments: one with all classes and another with only stutter classes. The experimental analysis revealed an average F1-score with del-del MFCC features of 85.38% with RF, 90.10% with SVM when all classes are considered. Furthermore, 93.29% with RF, 93.71% with SVM when only stutter classes are considered. On the contrary, when we use ComParE2016 features we achieve an average accuracy of 86.79% with RF and 87.77% with SVM considering all classes. Whereas, 95.10% with RF, 94.34% with SVM when only stutter classes are considered. When TDNN was used with del-del MFCC, we achieved an accuracy of 79.

关键词： stuttering Speech disorder feature extraction MFCC ComParE TDNN Sep-28k

来源：评论

学校读者我要写书评

暂无评论

A Machine learning Based Methodology for Load Profiles Clustering and Non-Residential Buildings Benchmarking

引用

IEEE TRANSACTIONS ON INDUstRY APPLICATIONS 2023年第3期59卷 2963-2973页

作者： Eiraudo, Simone Barbierato, Luca Giannantonio, Roberta Porta, Alessandro Lanzini, Andrea Borchiellini, Romano Macii, Enrico Patti, Edoardo Bottaccioli, Lorenzo Politecn Torino Dept Energy I-10129 Turin Italy Politecn Torino Control & Comp Engn I-10129 Turin Italy Politecn Torino Interuniv Dept Reg & Urban Studies & Planning I-10129 Turin Italy TIM SpA I-20123 Rome Italy

Buildings benchmarking based on their electric profiles is a fundamental step to identify, evaluate and then possibly implement energy efficiency oriented actions. Indeed, benchmarking enables comparison among peer buildings or industrial sites and the identification of reference cases, either efficient and inefficient ones. In this regard, temporal data clustering is an effective and widely applicable benchmarking tool. In this work, we propose a novel Machine learning based methodology, taking advantage of two fundamental tools, namely a decomposition algorithm and a clustering one. Several clustering algorithms have been tested to identify k-Means as the most suitable one. The proposed methodology includes the evaluation of energyKeyPerformance Indicators for effective analysis and comparison of buildings. The proposed framework has been tested on a real-world case study including around 2000 non-residential buildings. The classification of buildings based on K-Means achieved an accuracy of 99.7% with respect to their usage category. Furthermore, reference Key Performance Indicator values for each cluster are obtained and discussed to understand buildings' energy behaviour and possible reasons for inefficiencies.

关键词： Energy efficiency non-residential buildings clustering machine learning benchmarking

来源：评论

学校读者我要写书评

暂无评论

Apnea/Hypopnea Detection using Modified YOLOv8n Model on Non-EEG Signals 21

Apnea/Hypopnea Detection using Modified YOLOv8n Model on Non...

引用

21st international conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON)

作者： Aphimeteetamrong, Denphum Thiennviboon, Phunsak Intarawichian, Soraaut Sungkarat, Witaya Laothamatas, Jiraporn Kasetsart Univ Dept Elect Engn Bangkok Thailand Mahidol Univ Ramathibodi Hosp Fac Med Bangkok Thailand Chulabhorn Royal Acad Fac Hlth Sci Technol Bangkok Thailand

ISBN: (纸本)9798350381566;9798350381559

Sleep apnea is a sleep breathing disorder, causing ineffective sleep, that may lead to serious problems. Severity of sleep apnea is determined by an apnea-hypopnea index (AHI) that is usually obtained manually with both labor intensive and time consuming. Additionally, while the popularity of home sleep testing (Hst) is increasing, many Hst devices still lack EEG monitoring. Thus, our goal is to develop a machine learning model for detecting apnea and hypopnea events using 3 non-EEG signals to determine a severity level of sleep apnea for a full overnight record. We propose a modified YOLOv8n model for this task. The proposed model was trained, validated, and tested using 2 datasets including 2,056 and 23 full overnight records from the Multi-Ethnic study of Atherosclerosis (MESA) and the ***'s University Hospital/University College Dublin Sleep Apnea (UCD), respectively. Testing performances of the proposed model were evaluated using 15% record-based data splitting for MESA and 23-fold cross validation for UCD. By comparing with selected existing models, the proposed model achieves reasonably good sample-based testing performances. To assess more realistic testing performances, the severity levels of sleep apnea were predicted using the detected apnea/hypopnea events with and without groundtruth total sleep times (Tsts). The results show that the proposed model provides severity-level (event-based) performances substantially better than the existing model. The proposed model also achieves moderate to substantial agreement with the groundtruth severity levels where the Cohen's kappa coefficients are between 0.61 and 0.81.

关键词： autoscoring sleep apnea YOLO deep learning home sleep test polysomnography

来源：评论

学校读者我要写书评

暂无评论

Design of an intelligent Voice-Controlled Home System Based on Raspberry Pi 25

Design of an Intelligent Voice-Controlled Home System Based ...

引用

25th IEEE international conferences on High Performance Computing and Communications, 9th international conference on data Science and Systems, 21st IEEE international conference on Smart City and 9th IEEE international conference on Dependability in Sensor, Cloud and Big data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Wu, Kaiyi Li, Jiaying Yu, Jiabin Hua, Yuhao Xiao, Binggang Wang, Wu College of Information Engineering China Jiliang University Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province Hangzhou China School of Computer Science and Technology Xidian University Xi'an China School of Psychological and Cognitive Sciences Peking University Multisensory Integration Laboratory Beijing China

ISBN: (纸本)9798350330014

A complete intelligent voice-controlled home system should include voice capture, voice recognition, authentication, voice result processing, and other processes. Based on the intelligent voice interaction model of Raspberry Pi 3b+ and Alibaba Cloud platform, this paper realized a high recognition accurate, stable, and efficient intelligent voice-controlled home system. We used the Raspberry Pi to control the hardware interface, collected voice data through an external microphone, and performed command control with external sensors and controllable devices in the hardware part;The software was based on Alibaba Cloud intelligent voice interaction platform to realize voice data recognition. The system constructed can achieve the expected function after repeatedly testing the controlled device. The test results show that the recognition accuracy and recognition efficiency of the system's voice control instructions are both high in a relatively quiet environment. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Free Text Keystroke Dynamics-based Authentication with Continuous learning: A Case study 21

Free Text Keystroke Dynamics-based Authentication with Conti...

引用

21st IEEE international conference on Ubiquitous Computing and Communications / 5th IEEE international conference on data Science and Computational Intelligence / 21st IEEE international conference on Computer and Information Technology

作者： Trad, Fouad Hussein, Ali Chehab, Ali Amer Univ Beirut Elect & Comp Engn Beirut Lebanon

ISBN: (纸本)9781665477260

Authenticating users based on their typing patterns has always been a target for cybersecurity professionals and researchers. Although previous studies have worked on free text -based authentication on mobile devices, none of them addressed the necessity of continuous learning under these settings. In this work, we propose a variational autoencoder (VAE) model that deals with this issue. As a case study, we consider a scenario where the model is initially trained on data collected from the user in a particular language (English). Then, the model is supposed to recognize the user when typing in another language (Korean). One way to adapt to that change is to retrain the model on a subset of the Korean data when it becomes available. By then, two scenarios can arise: 1) The English data still exists and the model is trained on the combination of English and Korean data;2) The English data does not exist for security reasons or limited storage issues, and thus, we use the decoder part of our VAE to generate data based on what has been learned and then retrain the model on the mix. The average Equal Error Rate achieved among 50 participants was 3.23% and 3.55% for scenarios 1 and 2, respectively (similar to 14% less than the baseline case where the model is not retrained). These results prove the need for continuous retraining of authentication models and highlight the efficiency of the proposed model and its ability to continuously learn, even without having access to the previous training data.

关键词： Free-text Authentication Keystroke dynamics Variational Auto Encoders Continuous learning

来源：评论

学校读者我要写书评

暂无评论

THE BENEFITS OF TRANSFORMING engineering EDUCATION AND TRAINING WITH METAVERSE TECHNOLOGIES 21

THE BENEFITS OF TRANSFORMING ENGINEERING EDUCATION AND TRAIN...

引用

21st international conferences on Mobile learning, ML 2025 and 10th international conference on Educational Technologies, ICEduTech 2025

作者： Nedeva, Veselina Dineva, Snezhana Ducheva, Zlatoeli Trakia University – Stara Zagora Faculty of Technics and Technology 38 Graf Ignatiev Str. Yambol8600 Bulgaria

ISBN: (纸本)9789898704665

After analysing various publications and leveraging our direct experiences, we have identified the benefits and advantages of incorporating the metaverse. The Metaverse and related technologies such as Virtual Reality, Augmented Reality, and Artificial Intelligence offer innovative approaches to transforming engineering education. These technologies overcome the limitations of traditional methods by providing interactive and accessible learning opportunities. This study integrates insights from a comprehensive bibliometric analysis of research publications for the period 2013–2024, an extensive content analysis of selected academic articles, and the practical experiences of the Faculty of engineering and Technology. Our research is informed by professional engagements with e-learning platforms such as MOODLE and by observations from mobility exchanges at Karlsruhe Institute of Technology, where faculty members gained valuable insights into virtual and immersive education practices. The data reveals significant growth in interest and impact in recent years, with a peak in publications and citations. The analysis highlights how Metaverse and immersive technologies enhance student engagement, foster better understanding of complex concepts, and enable safe, realistic simulations. In addition to identifying opportunities for transforming traditional teaching methods, this study provides recommendations for integrating the Metaverse into engineering education. It also examines current technology trends and best practice applications, while addressing key challenges and outlining future prospects. By combining research insights with practical expertise, this paper underscores how Metaverse technologies can revolutionise engineering education and offer sustainable solutions to existing challenges. © 2025 Proceedings of the international conferences on Mobile learning 2025 and Educational Technologies 2025. All rights reserved.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

multi-GAT: Integrative Analysis of scRNA-seq and scATAC-seq data Using Graph Attention Networks for Cell Annotation 21st

multi-GAT: Integrative Analysis of scRNA-seq and scATAC-seq ...

引用

21st Pacific Rim international conference on Artificial Intelligence

作者： Jia, Shangru Tsunoda, Tatsuhiko Sharma, Alok Univ Tokyo Grad Sch Frontier Sci Dept Computat Biol & Med Sci Lab Med Sci Math Tokyo Japan Univ Tokyo Sch Sci Dept Biol Sci Lab Med Sci Math Tokyo Japan RIKEN Lab Med Sci Math Ctr Integrat Med Sci Yokohama Kanagawa Japan Griffith Univ Inst Integrated & Intelligent Syst Nathan Qld 4111 Australia Korea Univ Coll Informat Seoul South Korea

ISBN: (纸本)9789819601158;9789819601165

Single-cell RNA sequencing (scRNA-seq) and single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) provide complementary views of cellular states by capturing transcriptomic and chromatin accessibility landscapes, respectively [1]. Combining these modalities offers a comprehensive understanding of cellular functions and regulatory mechanisms. Here, we present multi-GAT, a model specifically designed for integrative analysis of scRNA-seq and scATAC-seq data using Canonical Correlation Analysis (CCA) followed by Graph Attention Network (GAT) to predict cell types. This approach leverages shared nearest neighbors and contrastive learning to enhance model performance. Multi-GAT effectively captures the complex relationships between transcriptomic and chromatin accessibility data, achieving robust cell type annotation across different single-cell modalities. The experimental results demonstrate that multi-GAT surpasses several baseline methods in accuracy, precision, and F1-score on the benchmark dataset.

关键词： Graph Attention Networks Single-cell transcriptomics Canonical Correlation Analysis Cell Annotation Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method for On-Board Interface Equipment of CTCS-3 Based on Temporal Knowledge Graph Completion 21

Fault Diagnosis Method for On-Board Interface Equipment of C...

引用

21st international conference on Networking, Sensing and Control, ICNSC 2024

作者： Zhou, Bingyan Zhang, Daqian Lv, Jidong Liu, Hongjie Zhao, Zixu Luo, Zhengwei School of Automation and Intelligence Beijing Jiaotong University Beijing China Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing China

ISBN: (纸本)9798350365221

Chinese Train Control System level 3 (CTCS-3) train control onboard equipment plays a crucial role in ensuring train safety and improving operational efficiency. And the on-board interface equipment enables the interaction between the on-board Automatic Train Protection (ATP), ground equipment, drivers, and trains. While its fault accounts for a relatively high proportion of faults, therefore, this paper proposed a fault diagnosis method for on-board interface equipment based on temporal knowledge graph completion. Firstly, this method introduces temporal series to integrate travel logs and fault statistics, which extract fault phenomena and perform entity alignment, construct the temporal knowledge graph. Secondly, on this basis, we constructed a fault diagnosis network based on knowledge graph completion, which incorporates the Temporal-Translating Embedding (T - TransE) vectorization algorithm, Bidirectional Long Short-Term Memory (Bi-LstM), and Self-Attention (SA) mechanism for temporal feature extraction. Finally, the T - TransE vectorization model was pretrained using the on-board interface equipment fault data from a railroad station in recent years for selecting the most effective temporal integration method. In order to validate the superiority of the proposed fault diagnosis method and the effectiveness of the data combination method, the diagnostic network without data combination and temporal relationship introduction, and other common fault diagnostic networks, were tested using the on -board fault data. Compared with the following fault diagnosis methods, the model proposed in this paper achieved the highest fault diagnostic accuracy of 96.8%. © 2024 IEEE.

关键词： Knowledge graph

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：