检索结果-内蒙古大学图书馆

Conference on Speech Technology and Human-computer Dialogue, SpeD

作者： Seyed Reza Shahamiri Krishnendu Mandal Sudeshna Sarkar Department of Electrical Computer and Software Engineering Faulty of Engineering The University of Auckland Auckland New Zealand Computer Science & Engineering Department Indian Institute of Technology Kharagpur India

As a neurological disability that affects muscles involved in articulation, dysarthria is a speech impairment that leads to reduced speech intelligibility. In severe cases, these individuals could also be handicapped and unable to interact with digital devices. For such individuals, Automatic Speech Recognition (ASR) technologies could be life changing by enabling them to communicate with others as well as computing devices via voice commands. Nonetheless, ASR systems designed to recognize healthy speech have shown very poor performance to transcribe dysarthric speech, signaling the need to design ASR specifically tailored for dysarthria. Dysarthric Speech Recognition (DRS) research has progressed gradually because of the challenges the research community faces such as the scarcity of dysarthric speech that does not allow the researchers to design deeper acoustic models needed to better learn dysarthric speech variations. In this paper we report on our preliminary findings to improve our previous DSR called Speech Vision and study the effects of Separable Convolutional neurons to improve its acoustic model. Speech Vision is a novel Dysarthric Speech Recognition system that learns to recognize the shape of the words uttered by dysarthric speakers instead of recognizing phone sequences and then mapping them to words. Experiments conducted on the utterances provided by all UA-Speech dysarthric speakers indicate the proposed Depthwise separable architecture provided better word recognition accuracies compared to the original Speech Vision’s architecture across all dysarthric speech intelligibility classes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio Based Machine Fault Diagnosis using Hybrid Feature Extraction and Ensemble Learning 15

Audio Based Machine Fault Diagnosis using Hybrid Feature Ext...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Singhal, Shashvat Goel, Bhavya Agrawal, Kshitij Sethi, Rithwick Sah, Shashi Jain, Rachit Vishwakarma, Dinesh K. Delhi Technological University Department of Computer Science Delhi India Delhi Technological University Department of Mechanical Engineering Delhi India Delhi Technological University Department of Ece Delhi India Delhi Technological University Department of Software Engineering Delhi India Delhi Technological University Department of Information Technology Delhi India

ISBN: (纸本)9798350370249

Over the last decade, proliferation of mechanical machines has surged exponentially, amplifying the challenge of monitoring their operational health due to the inevitability of wear and tear. Consequently, the conventional human centric approach to tracking machine conditions has become impractical. This underscores the demand for an innovative and efficient strategy. This research involves machine generated audio signals to detect and analyze faults or irregularities. Analyzing the acoustic patterns generated during machine operation makes detecting abnormal sounds associated with specific faults possible. This paper examines various techniques and algorithms for achieving this goal and compares them to recommend the most effective method. Initially, Short Time Fourier transform was performed on the preprocessed audio data. Then, various techniques to perform feature extraction on the transformed audio, such as spectral kurtosis, spectral centroid, zero crossing rate, and Mel spectrogram. Subsequently, the aggregate feature vector was input into various algorithms, including XGBoost, Support Vector Classifier, Random Forest Classifier and Ensemble Learning. The MIMII dataset was trained on these models. The evaluation showed that XGBoost Classifier performed the best as compared to the other models, achieving a total accuracy rate of 98 percent upon incorporating features extraction Melspectrogram, Spectral Kurtosis and Spectral Centroid. © 2024 IEEE.

关键词： Audio Classification Ensemble Learning Mel spectogram Random Forest Classifier Short time Fourier transform Spectral Centroid Spectral Kurtosis Support Vector Classifier XGBoost Zero Crossing Rate

来源：评论

学校读者我要写书评

暂无评论

A Survey on Scheduling the Task in Fog Computing Environment

arXiv

引用

arXiv 2023年

作者： Ishaq, Faiza Ashraf, Humaira Jhanjhi, Nz Department of computer and software Engineering International Islamic University Pakistan School of Computer Science SCS Taylors University Malaysia

With the rapid increase in the Internet of Things (IoT), the amount of data produced and *** processed is also increased. Cloud Computing facilitates to handle storage, processing, and analysis of data as needed. However cloud computing devices are located far away from the IoT devices. Fog computing has emerged as a small cloud computing paradigm that is near to the edge devices and handles the task very efficiently. Fog nodes have a small storage capability than the cloud node but it is designed and deployed near to the edge device so that request must be accessed efficiently and executes in time. In this survey paper we have investigated and analysed the main challenges and issues raised in scheduling the task in fog computing environment. To the best of our knowledge there is no comprehensive survey paper on challenges in task scheduling of fog computing paradigm. In this survey paper research is conducted from 2018 to 2021 and most of the paper selection is done from 2020-2021. Moreover this survey paper organizes the task scheduling approaches and technically plans the identified challenges and issues. Based on the identified issues, we have highlighted the future work directions in the field of task scheduling in fog computing environment. © 2023, CC BY.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements

arXiv

引用

arXiv 2025年

作者： Xie, Haiyang Shen, Xi Huang, Shihua Wang, Qirui Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Intellindust AI Lab China

Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing. This enables improved detection accuracy and more efficient hardware designs by bypassing the ISP. However, RAW object detection is challenging due to limited training data, unbalanced pixel distributions, and sensor noise. To address this, we propose SimROD, a lightweight and effective approach for RAW object detection. We introduce a Global Gamma Enhancement (GGE) module, which applies a learnable global gamma transformation with only four parameters, improving feature representation while keeping the model efficient. Additionally, we leverage the green channel’s richer signal to enhance local details, aligning with the human eye’s sensitivity and Bayer filter design. Extensive experiments on multiple RAW object detection datasets and detectors demonstrate that SimROD outperforms state-of-the-art methods like RAW-Adapter and DIAP while maintaining efficiency. Our work highlights the potential of RAW data for real-world object detection, and we will release the code upon publication. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

RDPI: A Refine Diffusion Probability Generation Method for Spatiotemporal Data Imputation 39

RDPI: A Refine Diffusion Probability Generation Method for S...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Zijin Zhao, Xiang Song, You School of Computer Science and Engineering Beihang University Beijing 100191 China School of Software Beihang University Beijing 100191 China

ISBN: (纸本)157735897X

Spatiotemporal data imputation plays a crucial role in various fields such as traffic flow monitoring, air quality assessment, and climate prediction. However, spatiotemporal data collected by sensors often suffer from temporal incompleteness, and the sparse and uneven distribution of sensors leads to missing data in the spatial dimension. Among existing methods, autoregressive approaches are prone to error accumulation, while simple conditional diffusion models fail to adequately capture the spatiotemporal relationships between observed and missing data. To address these issues, we propose a novel two-stage Refined Diffusion Probability Impuation (RDPI) framework based on an initial network and a conditional diffusion model. In the initial stage, deterministic imputation methods are used to generate preliminary estimates of the missing data. In the refinement stage, residuals are treated as the diffusion target, and observed values are innovatively incorporated into the forward process. This results in a conditional diffusion model better suited for spatiotemporal data imputation, bridging the gap between the preliminary estimates and the true values. Experiments on multiple datasets demonstrate that RDPI not only achieves state-of-the-art imputation performance but also significantly reduces sampling computational costs. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

WP2-GAN: Wavelet-based Multi-level GAN for Progressive Facial Expression Translation with Parallel Generators 32

WP2-GAN: Wavelet-based Multi-level GAN for Progressive Facia...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Shao, Jun Bui, Tien D. Computer Science and Software Engineering Concordia University MontréalQC Canada

Expression translation has received increasing attention from the computer vision community due to its wide applications in the real world. However, expression synthesis is hard because of the non-linear properties of facial skin and muscle caused by different expressions. A recent study showed that the practice of using the same generator for both forward prediction and backward reconstruction as in current conditional GANs would force the generator to leave a potential "noise" in the generated images, therefore hindering the use of the images for further tasks. To eliminate the interference and break the unwanted link between the first and second translation, we design a parallel training mechanism with two generators that perform the same first translation but work as a reconstruction model for each other. Additionally, inspired by the successful application of wavelet-based multi-level Generative Adversarial Networks(GANs) in face aging and progressive training in geometric conversion, we further design a novel wavelet-based multi-level Generative Adversarial Network (WP2-GAN) for expression translation with a large gap based on a progressive and parallel training strategy. Extensive experiments show the effectiveness of our approach for expression translation compared with the state-of-the-art models by synthesizing photo-realistic images with high fidelity and vivid expression effect. © 2021. The copyright of this document resides with its authors.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Utilizing Machine Learning to Enhance Infrastructure Resilience in Cold Regions 20

Utilizing Machine Learning to Enhance Infrastructure Resilie...

引用

20th International Conference on Cold Regions engineering: Sustainable and Resilient engineering Solutions for Changing Cold Regions, ICCRE 2024

作者： Shohel Rana, Md Gudla, Charan Ahmed, Feroz Nobi, Mohammad Nur Dept. of Computing and Software Engineering Florida Gulf Coast Univ. Fort MyersFL United States Dept. of Computer Science and Engineering Mississippi State Univ. StarkvilleMS United States Prediction 3D Technologies BiloxiMS United States Dept. of Computer Science Univ. of Texas at San Antonio San AntonioTX United States

ISBN: (纸本)9780784485460

In the challenging domain of engineering, where cold regions present formidable challenges, we confront the relentless forces of nature. From sub-zero temperatures to the unpredictable dance of snowfall and the silent buildup of ice, these regions demand innovative solutions to fortify the resilience of critical infrastructure. This initiative harnesses the potential of cutting-edge technology and leverages the extensive historical weather data tapestry. It introduces a pioneering strategy by integrating machine learning algorithms with extensive weather data, steering cold region engineering into an era defined by foresight and adaptability. This paper studies a transformative approach designed to forecast, prevent, and ultimately enhance infrastructure resilience in the face of rigid cold. Addressing the distinct challenges of cold region engineering, arising from harsh winter conditions such as extreme cold temperature, snowfall, and ice accumulation, we offer a comprehensive study using machine learning algorithms applied to historical weather data to construct a deeper analysis model capable of highlighting adverse weather effects. This, in turn, covers the way for optimized resource allocation, streamlined maintenance planning, and design enhancements. Our proposed study follows a systematic process, encompassing meticulous data collection, appropriate feature selection, and aiming seamless integration of the model into existing infrastructure management systems. Additionally, it facilitates the implementation of efficient and proactive measures to mitigate the impact of severe weather conditions on infrastructure. The paper also conducts three different hypotheses testing: temperature impact hypothesis, precipitation influence hypothesis, and ice accumulation and infrastructure resilience hypothesis, propelling engineering practices to new heights, particularly in the face of challenging cold environments. © ASCE.

关键词： Snow

来源：评论

学校读者我要写书评

暂无评论

Efficient Modeling of the Routing and Spectrum Allocation Problem for Flexgrid Optical Networks 25

Efficient Modeling of the Routing and Spectrum Allocation Pr...

引用

25th International Conference on Optical Network Design and Modelling, ONDM 2021

作者： Jaumard, Brigitte Nguyen, Quang Anh Concordia University Department of Computer Science and Software Engineering MontrealQC Canada

ISBN: (纸本)9783903176331

While the problem of Routing and Spectrum Allocation (RSA) has been widely studied, very few studies attempt to solve realistic sized instances. Indeed, the state of the art is always below the standard transport capacity of a fiber link with 384 frequency slots, regardless of what the authors consider, heuristics or exact methods with a few exceptions. In this paper, we are interested in reducing the gap between realistic data sets and testbed instances that are often considered, using exact methods. Even if exact methods may fail to solve in reasonable time very large instances, they can, however, output solutions with a very good and proven accuracy. The novelty of this paper is to exploit the observations that optimal solutions contain a very large number of lightpaths associated with shortest paths or k-shortest paths with a small k. We propose an original efficient large-scale optimization model and decomposition algorithm to solve the RSA problem for flexgrid optical networks. It allows the exact or near optimal solution of much larger instances than in the literature. © 2021 IFIP TC6 WG6.10.

关键词： Optimal systems

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection: Emerging Techniques and Evolving Challenges

Deepfake Detection: Emerging Techniques and Evolving Challen...

引用

Annual Information Technology, Electromechanical engineering and Microelectronics Conference (IEMECON)

作者： Krishnaraj Natarajan Abeer Mathur Kshitiz Bhargava Manvendra Singh Moulik Tejpal Department of Database Systems School of Computer Science & Engineering Vellore Institute of Technology Vellore India Department of Software Systems School of Computer Science & Engineering Vellore Institute of Technology Vellore India

ISBN: (数字)9798350387315

ISBN: (纸本)9798350387322

Several newly developed techniques and tools for manipulating images, audio, and videos have been introduced as an outcome of the recent and rapid breakthroughs in AI, machine learning, and deep learning. While most applications for these techniques or tools are in the fields of entertainment and education, some individuals with unlawful intent have also been benefited from them. These individuals use such techniques for various purposes, including the spread of misleading information and unnecessary propaganda, the incitement of political instability, hate and unrest, as well as for purposes of torture and blackmail. These high-quality and convincing manipulated images, audio, or videos are commonly referred to as ‘Deepfakes’.Since then, various solutions to the problems raised by Deepfakes have been proposed in academic studies. This literature review contains relevant publications that offered a variety of approaches to give an updated summary of the research activities in different types of Deepfake attacks, their detection, and countermeasures. It also assesses the effectiveness of the detection capabilities of different techniques with various datasets and algorithms applied in Deepfake detection, while also outlining the various benefits and drawbacks of various methodologies.

关键词： Deep learning Deepfakes Smart contracts Microwave communication Media Forgery Blockchains Internet of Things Systematic literature review Microwave imaging

来源：评论

学校读者我要写书评

暂无评论

EHG Signal Analysis for Prediction of Term and Preterm using Variational Mode Decomposition and Artificial Neural Networks

EHG Signal Analysis for Prediction of Term and Preterm using...

引用

2022 International Conference on Frontiers of Information Technology, FIT 2022

作者： Umar Khan, Muhammad Aziz, Sumair Iqtidar, Khushbakht Fernandez Rojas, Raul University of Engineering and Technology Taxila Department of Electronics Engineering Taxila Pakistan National University of Sciences and Technology Department of Computer Software Engineering Islamabad Pakistan University of Canberra Faculty of Science & Technology Canberra Australia

ISBN: (纸本)9798350345933

Preterm deliveries are an important cause of mortality and morbidity in newborns. Accurate and early prediction of a premature delivery can prove helpful in providing proper medication and treatment. Recording of electrical activity known as Electrohysterogram (EHG) from the abdominal surface of pregnant women corresponds to the uterus contractions. A new direction is open using EHG signals for the diagnosis of preterm births. In this research, we present a new method for the accurate classification of preterm and term EHG signals. The proposed method first filters a three-channel EHG signal using bandpass filters. Next, we combined the filtered three-channel EHG into one signal using an accumulation operation. The accumulated EHG signal was post-processed through variational mode decomposition (VMD). VMD algorithm splits the input signal into finite modes using center frequencies known as intrinsic mode functions (IMFs). An energy-based intelligent signal reconstruction approach is designed to combine IMFs having an energy level above the computed threshold. Next, the reconstructed EHG signals were split into continuous windows, and time, frequency, and Hjorth features were extracted. These features were fused to construct a distinct feature representation and were reduced using the ReliefF algorithm. We trained an artificial neural network (ANN) to obtain 98.8 % average accuracy using 10-fold cross-validation. © 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

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：