检索结果-内蒙古大学图书馆

P-GELU: A Novel Activation Function to Optimize Whisper for Darija Speech Translation

IEEE Access 2025年 13卷 100198-100218页

作者： Labied, Maria Belangour, Abdessamad Banane, Mouad Laboratory of Information Technology and Modeling LTIM Hassan II University Ben M'sik Faculty of Sciences Casablanca Morocco Laboratory of Artificial Intelligence & Complex Systems Engineering Hassan II University Faculty of Legal Economic and Social Sciences Casablanca Morocco

Activation functions play a critical role in optimizing deep learning models, directly influencing gradient flow, convergence stability, and overall translation accuracy. In this work, we investigate their impact within the Whisper-Turbo model, a speech-to-text Transformer trained from scratch on the Darija-C dataset for Moroccan Darija speech translation. Our study begins by evaluating baseline activation functions - GELU, Swish, and Mish - demonstrating that while GELU is widely used in Transformer-based architectures, it may not be optimal for dialectal speech translation, particularly in low-resource settings. To address this limitation, we introduce Parameterized GELU (P-GELU), a novel activation function that extends GELU by incorporating trainable parameters (α, β), allowing the model to dynamically adjust its non-linearity across layers and training phases. Through extensive experiments, we demonstrate that P-GELU outperforms standard GELU, with superior convergence speed and generalization. Furthermore, P-GELU reduces training loss, improves feature retention, and enhances linguistic adaptability, making it a more effective alternative for speech translation tasks involving phonetic variability, code-switching, and limited training data. The proposed P-GELU offers a promising balance between computational efficiency and performance gains, presenting a viable solution for enhancing Transformer-based speech models in low-resource language scenarios. © 2013 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Machine Learning Algorithms for Smart Healthcare systems 1

引用

International Conference on Cyber Security, Privacy and Networking, ICSPN 2022

作者： Alduailij, Mai Mishra, Anupama Zamzami, Ikhlas Fuad Psannis, Konstantinos Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science and Engineering Himalayan School of Science and Technology Swami Rama Himalayan University Dehradun India Faculty of Business King Abdulaziz University Rabigh Saudi Arabia University of Macedonia Thessaloniki Greece

ISBN: (数字)9783031220180

ISBN: (纸本)9783031220173

The epidemic taught us to keep digital health records. It also showed us how wearable observing gear, video conferences, and AI-powered chatbots may give good treatment remotely. Real-time data from health care devices across the globe helped attack and track the infection. Biomedical imaging, sensors, and machine learning have improved health in recent years. Medical care and biomedical sciences are now information science sectors that demand enhanced data mining approaches. Biomedical data have high dimensionality, class irregularity, and few tests. AI uses information and computations to imitate how people learn, continually improving its accuracy. ML is an important part of information science. Calculations utilising measurable methods reveal essential information about information mining operations. This paper explains and compares ML algorithms that can detect diseases sooner. We summarise ML’s algorithms and processes to extract information for a data-driven society. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Federated Graph Learning for Cross-Domain Recommendation 38

Federated Graph Learning for Cross-Domain Recommendation

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Yang, Ziqi Peng, Zhaopeng Wang, Zihui Qi, Jianzhong Chen, Chaochao Pan, Weike Wen, Chenglu Wang, Cheng Fan, Xiaoliang Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen University China Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University China School of Computing and Information Systems The University of Melbourne Australia College of Computer Science and Technology Zhejiang University Hangzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Cross-domain recommendation (CDR) offers a promising solution to the data sparsity problem by enabling knowledge transfer between source and target domains. However, many recent CDR models overlook crucial issues such as privacy as well as the risk of negative transfer (which negatively impact model performance), especially in multi-domain settings. To address these challenges, we propose FedGCDR, a novel federated graph learning framework that securely and effectively leverages positive knowledge from multiple source domains. First, we design a positive knowledge transfer module that ensures privacy during inter-domain knowledge transmission. This module employs differential privacy-based knowledge extraction combined with a feature mapping mechanism, transforming source domain embeddings from federated graph attention networks into reliable domain knowledge. Second, we design a knowledge activation module to filter out potential harmful or conflicting knowledge from source domains, addressing the issues of negative transfer. This module enhances target domain training by expanding the graph of the target domain to generate reliable domain attentions and fine-tunes the target model for improved negative knowledge filtering and more accurate predictions. We conduct extensive experiments on 16 popular domains of the Amazon dataset, demonstrating that FedGCDR significantly outperforms state-of-the-art methods. We open source the code at https://***/LafinHana/FedGCDR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remote Patient Monitoring systems Network Adaptation Scenarios

Remote Patient Monitoring Systems Network Adaptation Scenari...

引用

2022 IEEE International Conference on Current Development in engineering and technology, CCET 2022

作者： Khujamatov, Halimjon Akhmedov, Nurshod Lazarev, Amir Arsheen, Sobiya Tashkent University of Information Technologies Dean of the Faculty of Computer Engineering Tashkent Uzbekistan Tashkent University of Information Technologies Data Transmission Networks and Systems Department Tashkent Uzbekistan Maulana Azad National Urdu University Department of Computer Science and Information Technology India

ISBN: (纸本)9781665454155

This article is devoted to the actual topic of studying scenarios for adapting a network infrastructure to a network of remote patient monitoring systems (PCMS). The paper presents an overview and analysis of scenarios for adapting the network infrastructure of monitoring systems. The stages of scenario execution have been studied and simulation models of the RPMS network infrastructure have been developed that implement various adaptation scenarios. A comparative analysis of adaptation scenarios was carried out according to several criteria, such as the speed of request delivery, delivery time, and network load. Simulation models built in the Anylogic environment, a powerful simulator of mass service system, showed the effectiveness of the mesh topology in relation to the ad-hoc topology according to several criteria. The theoretical significance of the work lies in carrying out analytical work on scenarios for adapting the network infrastructure of the RPMS, as well as in studying the network architecture. The practical significance of the work lies in the development of a simulation model that allows you to explore scenarios for adapting the network architecture. © 2022 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Time Series Classification Using Deep Learning for HAR Based on Smart Wearable Sensors 26

Time Series Classification Using Deep Learning for HAR Based...

引用

26th International computer Science and engineering Conference, ICSEC 2022

作者： Jantawong, Ponnipa Hnoohom, Narit Jitpattanakul, Anuchit Mekruksavanich, Sakorn University of Phayao School of Information and Communication Technology Department of Computer Engineering Thailand Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9781665491983

In the last decades, time series classification (TSC) has emerged as one of the most challenging issues in data mining, and extensive studies have been done on various methods, including algorithm-based and learning-based techniques. Sensor-based human activity recognition (HAR) is a TSC issue that has become one of the most sought-after fields among business and academia specialists because of the proliferation of smartphone technology and wearable movement sensors. Conventional approaches to feature extraction provide a significant challenge in feature selection. Deep learning is an efficient strategy in the HAR scientific field and has solved the issue of feature selection. Nevertheless, several obstacles remain to study topics, including classifier interpretation. This article integrates well-known deep learning methods, namely convolutional neural networks and RNN-based models. The new approach proved to be more effective than the existing state-of-the-art approach. We assessed our network on the multivariant time-series benchmark (UCI-HAR) and revealed that our model surpasses other models in terms of training time and overall accuracy. © 2022 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces 38

Taming "data-hungry" reinforcement learning? Stability in co...

引用

38th Conference on Neural information Processing systems, NeurIPS 2024

作者： Duan, Yaqi Wainwright, Martin J. Department of Technology Operations and Statistics Stern School of Business New York University New YorkNY10012 United States Laboratory for Information and Decision Systems Statistics and Data Science Center Department of Electrical Engineering and Computer Science Department of Mathematics Massachusetts Institute of Technology CambridgeMA02139 United States

We introduce a novel framework for analyzing reinforcement learning (RL) in continuous state-action spaces, and use it to prove fast rates of convergence in both off-line and on-line settings. Our analysis highlights two key stability properties, relating to how changes in value functions and/or policies affect the Bellman operator and occupation measures. We argue that these properties are satisfied in many continuous state-action Markov decision processes. Our analysis also offers fresh perspectives on the roles of pessimism and optimism in off-line and on-line RL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chest Radiographs Based Pneumothorax Detection Using Federated Learning

引用

computer systems Science & engineering 2023年第11期47卷 1775-1791页

作者： Ahmad Almadhor Arfat Ahmad Khan Chitapong Wechtaisong Iqra Yousaf Natalia Kryvinska Usman Tariq Haithem Ben Chikha Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand School of Telecommunication Engineering Suranaree University of TechnologyNakhon Ratchasima30000Thailand Department of Computer Science and Software Engineering International Islamic UniversityIslamabadPakistan Information Systems Department Faculty of ManagementComenius University in BratislavaOdbojárovBratislava440Slovakia Prince Sattam bin Abdulaziz University AlKharjSaudi Arabia

Pneumothorax is a thoracic condition that occurs when a person’s lungs collapse,causing air to enter the pleural cavity,the area close to the lungs and chest *** most persistent disease,as well as one that necessitates particular patient care and the privacy of their health *** radiologists find it challenging to diagnose pneumothorax due to the variations in *** learning-based techniques are commonly employed to solve image categorization and segmentation ***,it is challenging to employ it in the medical field due to privacy issues and a lack of *** address this issue,a federated learning framework based on an Xception neural network model is proposed in this *** pneumothorax medical image dataset is obtained from the Kaggle *** preprocessing is performed on the used dataset to convert unstructured data into structured information to improve the model’s ***-max normalization technique is used to normalize the data,and the features are extracted from chest Xray *** dataset converts into two windows to make two clients for local model *** neural network model is trained on the dataset individually and aggregates model updates from two clients on the server *** decrease the over-fitting effect,every client analyses the results three *** 1 performed better in round 2 with a 79.0%accuracy,and client 2 performed better in round 2 with a 77.0%*** experimental result shows the effectiveness of the federated learning-based technique on a deep neural network,reaching a 79.28%accuracy while also providing privacy to the patient’s data.

关键词： Privacy preserving pneumothorax disease federated learning chest x-ray images healthcare machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

Modeling and Analysis of UAV-Assisted Mobile Network with Imperfect Beam Alignment

引用

computers, Materials & Continua 2023年第1期74卷 453-467页

作者： Mohamed Amine Ouamri Reem Alkanhel Cedric Gueguen Manal Abdullah Alohali Sherif S.M.Ghoneim University of Rennes 1/ADOPNET team at IRISA laboratory Rennes35000France Facultéde Technologie Laboratoire d’Informatique Médicale(LIMED)Universitéde BejaiaBejaia06000Algérie Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Electrical engineering department College of EngineeringTaif University P.O.Box 11099Taif21944Saudi Arabia

With the rapid development of emerging 5G and beyond(B5G),Unmanned Aerial Vehicles(UAVs)are increasingly important to improve the performance of dense cellular *** a conventional metric,coverage probability has been widely studied in communication systems due to the increasing density of users and complexity of the heterogeneous *** recent years,stochastic geometry has attracted more attention as a mathematical tool for modeling mobile network *** this paper,an analytical approach to the coverage probability analysis of UAV-assisted cellular networks with imperfect beam alignment has been *** assumption was considered that all users are distributed according to Poisson Cluster Process(PCP)around base stations,in particular,Thomas Cluster Process(TCP).Using thismodel,the impact of beam alignment errors on the coverage probabilitywas ***,the ProbabilityDensity Function(PDF)of directional antenna gain between the user and its serving base station was ***,association probability with each tier was achieved.A tractable expression was derived for coverage probability in both Line-of-Sight(LoS)andNon-Line-of-Sight(NLoS)condition *** results demonstrated that at low UAVs altitude,beam alignment errors significantly degrade coverage ***,for a small cluster size,alignment errors do not necessarily affect the coverage performance.

关键词： Unmanned aerial vehicles coverage analysis stochastic geometry millimeter wave imperfect beam alignment

来源：评论

学校读者我要写书评

暂无评论

Teeth and Jaw Segmentation from CBCT images Using 3D Deep Learning Models 18

Teeth and Jaw Segmentation from CBCT images Using 3D Deep Le...

引用

18th International computer engineering Conference, ICENCO 2022

作者： Abdo, Yassmina Mohamed, Nader Alsawaf, Maryam Elsaeed, Mohamed Ain Shams University Faculty of Computers and Information Sciences Scientific Computing Department Cairo Egypt Higher Institute of Engineering and Technology Mechatronics Engineering Department Cairo Egypt Kafr Elshiekh University Faculty of Engineering Computer and Systems Engineering Cairo Egypt

ISBN: (纸本)9781665458955

The outcome of oral surgery is dependent on precise preoperative planning. In order to properly plan for dental surgery or suitable implant placement, it is necessary for accurate segmentation of the jaw tissues: the teeth, the cortical bone, the trabecular core, and overall, the inferior alveolar nerve. Achieving 3D virtual surgical planning is very hard and is a major drawback because most of the existing jaw segmentation methods require a large amount of expert knowledge for manual or partially automatic segmentation. What is more, due to the lack of experienced doctors and experts, high-quality expert knowledge is hard to achieve in practice. Furthermore, metal artifacts and large variations in their shape and size among individuals influence the segmentation of the jaw in CBCT scans seriously. Therefore, this paper presents a new automatic jaw segmentation in CBCT scans dataset. This approach is divided into two main phases;the first phase adopts the use of image processing techniques to extract the region of interest (ROI) which is the area containing the jaws. It is an important phase as it prepares the 3D image data before using it in the second phase as it makes the training more efficient rather than training the model overall 3D head of CBCT scans. In the second phase, we use several models to segment each jaw separately and then gets a 3D segmentation view of both jaws. We implement such a segmentation approach on head CBCT scans given as Dicom Numpy files datasets and then evaluate the performance. Our proposed approach has been tested in a validation set that has been evaluated using Dice's coefficient and the Attention Unet model achieved promising results with a 91 © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Wavelet Based Generative Model for Time Series Prediction

A Novel Wavelet Based Generative Model for Time Series Predi...

引用

International Conference on Big Data and information Analytics (BigDIA)

作者： Chaofan Dai Xiaoguang Yuan Zongkai Tian Xinyue Hu Zhen Luan Youchen Wang National Key Laboratory of Information Systems Engineering National University of Defense Technology Changsha China Beijing Institute of Computer Technology and Application Beijing China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

Generative models have become an exciting area of research in recent years. Generative Adversarial Networks (GANs) and Denoising Diffusion Probabilistic Models (DDPMs) have been utilized in various data augmentation applications. However, generative models can learn high-dimensional features of data through adversarial learning, making them suitable for nonlinear and nonstationary time series analysis, such as stock market prediction, high-frequency trading, and ocean current forecasting. In this paper, the researchers focus on using a wavelet-based GAN to predict stock market prices by generating synthetic stock market price trends. Historical stock price data from 2014 to 2024 is used for our experiments, and the results show that the wavelet-based GAN outperforms deep learning baseline models..

关键词： Wavelet transforms Analytical models Oceans Time series analysis Noise reduction Predictive models Generative adversarial networks Wavelet analysis Data models Stock markets

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：