检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wang, Wenyu Zhou, Yiquan Zhu, Jihua Ding, Hongwu Xu, Jiacheng Li, Shihao School of Software Engineering Xi’an Jiaotong University Xi’an China School of Computer Science and Technology Anhui University Hefei China School of Software Engineering East China Normal University Shanghai China Division of Music and Audio Union Wheatland Culture and Media Ltd Chengdu China

Voice conversion (VC) has made progress in feature disentanglement, but it is still difficult to balance timbre and content information. This paper evaluates the pre-trained model features commonly used in voice conversion, and proposes an innovative method for disentangling speech feature representations. Specifically, we first propose an ideal content feature, referred to as the average feature, which is calculated by averaging the features within frame-level aligned parallel speech (FAPS) data. For generating FAPS data, we utilize a technique that involves freezing the duration predictor in a Text-to-Speech system and manipulating speaker embedding. To fit the average feature on traditional VC datasets, we then design the AVENet to take features as input and generate closely matching average features. Experiments are conducted on the performance of AVENet-extracted features within a VC system. The experimental results demonstrate its superiority over multiple current speech feature disentangling methods. These findings affirm the effectiveness of our disentanglement approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Segmentation in Multimodal MRI Using U-Net Layered Structure

引用

computers, Materials & Continua 2023年第3期74卷 5267-5281页

作者： Muhammad Javaid Iqbal Muhammad Waseem Iqbal Muhammad Anwar Muhammad Murad Khan Abd Jabar Nazimi Mohammad Nazir Ahmad Department of Information Technology The Superior UniversityLahorePakistan Department of Software Engineering The Superior UniversityLahorePakistan Department of Information Sciences Division of Science and TechnologyUniversity of EducationLahorePakistan Department of Computer Science Government College UniversityFaisalabadPakistan Deptment of Oral and Maxillofacial Surgery Faculty of DentistryUniversiti Kebangsaan MalaysiaKuala LumpurMalaysia Institute of IR4.0 Universiti Kebangsaan MalaysiaBangiSelangorMalaysia

The brain tumour is the mass where some tissues become old or damaged,but they do not die or not leave their *** brain tumour masses occur due to malignant *** tissues must die so that new tissues are allowed to be born and take their *** segmentation is a complex and time-taking problem due to the tumour’s size,shape,and appearance *** finding such masses in the brain by analyzing Magnetic Resonance Images(MRI)is a crucial task for experts and *** could not work for large volume images simultaneously,and many errors occurred due to overwhelming image *** main objective of this research study is the segmentation of tumors in brain MRI images with the help of digital image processing and deep learning *** research study proposed an automatic model for tumor segmentation in MRI *** proposed model has a few significant steps,which first apply the pre-processing method for the whole dataset to convert Neuroimaging Informatics Technology Initiative(NIFTI)volumes into the 3D NumPy *** the second step,the proposed model adopts U-Net deep learning segmentation algorithm with an improved layered structure and sets the updated *** the third step,the proposed model uses state-of-the-art Medical Image Computing and computer-Assisted Intervention(MICCAI)BRATS 2018 dataset withMRI modalities such as T1,T1Gd,T2,and Fluidattenuated inversion recovery(FLAIR).Tumour types in MRI images are classified according to the tumour *** of these masses carried by state-of-the-art approaches such that the first is enhancing tumour(label 4),edema(label 2),necrotic and non-enhancing tumour core(label 1),and the remaining region is label 0 such that edema(whole tumour),necrosis and *** proposed model is evaluated and gets the Dice Coefficient(DSC)value for High-grade glioma(HGG)volumes for their test set-a,test set-b,and test set-c 0.9795, 0.9855 and 0.9793, respectively.

关键词： Brain tumour segmentation magnetic resonance images modalities dice coefficient low-grade glioma U-Net

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation for NOMA-Assisted Backscatter Communication in 6G Internet of Vehicles Networks

Optimal Resource Allocation for NOMA-Assisted Backscatter Co...

引用

International Conference on Information Networking

作者： Van Dat Tuong Dongwan Kim Eui-Jik Kim Jeongyeup Paek Sungrae Cho School of Computer Science and Engineering Chung-Ang University Seoul Republic of Korea Department of Electronic Engineering Dong-A University Busan Republic of Korea Division of Software Hallym University Chuncheon Republic of Korea

ISBN: (数字)9798350330946

ISBN: (纸本)9798350330953

Non-orthogonal multiple access (NOMA) is considered as an emerging technology to improve the spectral efficiency performance for 6G networks. Ambient backscatter communication (BackCom) is another promising solution owing to its advantages in increasing spectral and power efficiency. The investigation of integrating NOMA with BackCom is conducted to enhance the connectivity of the emerging 5G low-powered Internet-of-Vehicles (IoVs) and future 6G transportation systems. This study proposes an optimal resource allocation scheme for the NOMA-assisted BackCom IoV network. Specifically, multiple Road-Side Units (RSUs) are considered sending superimposed signals to the subscribed IoVs in the downlink NOMA. BackCom tags are considered to transmit data symbols to nearby IoVs by reflecting the signals of RSUs. Thus, we aim to maximize the total data rate performance of the NOMA-assisted BackCom IoV network. A joint problem that simultaneously optimizes the IoV clustering, IoV power allocation, and reflection coefficients of BackCom tags is formulated. To solve the problems efficiently, multiple subproblems are decomposed that can be solved using CVX optimization tool. To validate the performance of the proposed method, we compare it with those of state-of-the-art benchmark schemes. Numerical results will be provided to show the superiority of the proposed framework.

关键词： 6G mobile communication NOMA Transportation Symbols Benchmark testing Reflection coefficient Resource management

来源：评论

学校读者我要写书评

暂无评论

A Lightweight CNN-Based Pothole Detection Model for Embedded Systems Using Knowledge Distillation 21

A Lightweight CNN-Based Pothole Detection Model for Embedded...

引用

21st International Conference on New Trends in Intelligent software Methodologies, Tools and Techniques, SoMeT 2022

作者： Musa, Aminu Hassan, Mohammed Hamada, Mohamed Kakudi, Habeebah Adamu Amin, Md. Faizul Ibne Watanobe, Yutaka Department of Computer Science Federal University Dutse Nigeria Faculty of Computer Sci. & Info. Technology Bayero University Kano Nigeria Software Engineering Lab University of Aizu Japan Graduate School of Computer Science University of Aizu Japan Division of Information System University of Aizu Japan

ISBN: (纸本)9781643683164

Recent breakthroughs in computer vision have led to the invention of several intelligent systems in different sectors. In transportation, this advancement led to the possibility of proposing autonomous vehicles. This recent technology relies heavily on wireless sensors and Deep learning. For an autonomous vehicle to navigate safely on highways, the vehicle needs equipment to aid with detecting road anomalies such as potholes ahead of time. The massive improvement in computer vision models such as Deep Convolutional Neural networks (DCNN) or vision transformers (ViT) resulted in many success stories and tremendous breakthroughs in object detection tasks;this enabled the use of such models in different application areas. But many of the reported results are theoretical and unrealistic in real-life. Usually, the nature of these models is extensive;they are trained on High-performance computers or cloud computing environments with GPUs, which challenge their usage on edge devices. However, to come up with a light model that can fit into embedded devices, the model size has to be reduced significantly so that the performance will not be affected. Therefore, this paper proposes a lightweight model of pothole detection for an embedded device. The model achieved a state-of-the-art accuracy of 98%, with the number of parameters reduced to more than 70% compared with a deep CNN model;the model can be trained and deployed on embedded devices such as smartphones efficiently. © 2022 The authors and IOS Press. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

CardioNetFusion: A Deep Learning and Explainable AI Integrated System for Cardiovascular Disease Detection

CardioNetFusion: A Deep Learning and Explainable AI Integrat...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Gunasekaran Raja Selvam Essaky Surya Raj Muthu Babith Sarish Suresh Jaehyuk Cho Seohyun Yoo Sathishkumar Veerappampalayam Easwaramoorthy Department of Computer Technology NGNLab Anna University Chennai India Department of Software Engineering & Division of Electronics and Information Engineering Jeonbuk National University Jeonju-si the Republic of Korea School of Engineering and Technology Sunway University Malaysia

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

Early detection of Cardiovascular Diseases (CVD) plays a vital role in effective treatment and management. However, traditional methods for analyzing ECG signals are often limited in both accuracy and interpretability. In this work, we introduce a novel model, CardioNetFusion, designed to address these limitations by incorporating advancements in Deep Learning (DL) and Explainable AI (XAI). The model leverages the strengths of Convolutional Neural Networks (CNN), MobileNetV2, and VGG16 to improve the robustness of ECG signal interpretation. To further enhance transparency and provide healthcare professionals with actionable insights, saliency maps are utilized to visualize model predictions. Additionally, by integrating an Application Programming Interface (API) within an IoT-based sensor fusion framework, the model supports real-time cardiovascular health monitoring. Achieving a classification accuracy of 98.7% in detecting arrhythmias, CardioNetFusion surpasses existing methodologies and offers a practical, reliable solution for early CVD diagnosis and management. Traditional methods of ECG analysis often have limitations in terms of diagnostic accuracy and interpretability. This paper proposes a CardioNetFusion model to address the challenges of conventional methods of ECG data analysis by leveraging advances in Deep Learning (DL) and Explainable AI (XAI). The proposed CardioNetFusion model integrates Convolutional Neural Networks (CNN), MobileNetV2, and VGG16 models to improve the robustness of ECG signal interpretation. Additionally, we utilized saliency maps to enhance model transparency and provide clear, actionable insights for healthcare professionals. Integrating Application Programming Interface (API) in the IoT-based sensor fusion approach to our proposed model facilitates seamless real-time monitoring of cardiovascular health. With an impressive 98.7% accuracy in arrhythmia classification, CardioNetFusion outperformed existing methods and ensured reliab

关键词： Deep learning Accuracy Explainable AI Medical services Electrocardiography Sensor fusion Robustness Real-time systems Convolutional neural networks Application programming interfaces

来源：评论

学校读者我要写书评

暂无评论

Integrating Design Thinking into software Process Improvement 4

Integrating Design Thinking into Software Process Improvemen...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Khalid, Anum Hashmi, Amber Sarwar Kiani, Azaz Ahmed Muzammal, Syeda Mariam Jhanjhi, N.Z. Bibi, Ruqia Kumar, Sandeep Foundation University Department of Software Engineering Islamabad Pakistan Rawalpindi Women University Department of Software Engineering Rawalpindi Pakistan National University of Modern Languages Rawalpindi Pakistan School of Computer Science Taylor's University Faculty of Innovation and Technology Subang Jaya Malaysia University Institute of Information Technology Pir Mehr Ali Shah Arid Agriculture University Rawalpindi Pakistan Lovely Professional University Division of Research and Development Phagwara144411 India KKR and KSR institute of technology and sciences Andhra Pradesh Guntur India

ISBN: (纸本)9798350353266

The need for software improvement is growing widely due to the demand for technology development. The issues that arise by expanding the software processes in the workplace are expense, lack of understanding, time constrained, and lack user experience. This research paper focuses on proposing a framework for integrating design thinking into software process improvement. The secret to project success may lie in fusing methodological and reusable approaches with human-centric techniques. A mixed-methods research strategy is proposed to compile thorough information and reach conclusions. In addition, it incorporates components of both qualitative and quantitative research (secondary research and descriptive analysis). The assumption is that the existing model significantly affects the user satisfaction variable. This indicates a statistically significant association between the individual's experience (number of years) and design thinking integration into the software process improvement. The variables in the proposed model and the dependent variable user satisfaction accounts for 6.1 © 2024 IEEE.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Using Deep Learning for Blister Blight Identification in Sri Lankan Tea

Effectiveness of Using Deep Learning for Blister Blight Iden...

引用

2023 International Research Conference on Smart Computing and Systems engineering, SCSE 2023

作者： Hewawitharana, G.H.A.U. Nawarathne, U.M.L.A. Hassan, A.S.F. Wijerathna, Lochana M. Sinniah, G.D. Vidhanaarachchi, Samitha P. Wickramarathne, Jagath Wijekoon, Janaka L. Sri Lanka Institute of Information Technology Department of Information Technology Malabe Sri Lanka Tea Research Institute of Sri Lanka Plant Pathology Division Talawakelle Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka Military Technological College Systems Engineering Department Muscat Oman

ISBN: (纸本)9798350341454

Ceylon tea industry faces a major challenge in the form of pathogen-induced crop loss, with Blister Blight (BB) caused by Exobasidium vexans posing the greatest threat, leading to harvest losses of over 30%. This fungus attacks the tender tea shoots, resulting in a direct negative impact on the tea harvest. This paper presents a system to identify the suspicious tea leaves and BB disease at its early stages along with an assessment of severity, offering a potential solution to this critical issue. By utilizing real-time object detection, the system filters out non-tea leaves from the captured initial image of a segment of a tea plant. The identified tea leaves are then subjected to BB identification and severity assessment based on differing visual symptoms of the BB stages. This approach enables the system to accurately identify BB in the initial stage and severity stage, allowing for timely and targeted intervention to minimize crop losses. The YOLOv8 model has been able to correctly identify 98% of the objects it has detected as relevant (precision), and it has been able to correctly identify 96% of all the relevant objects present in the scene (recall). The Residual Network 50 (Resnet50) convolutional neural network (CNN) model was selected as the final model, achieving an accuracy of 89.90% during the training phase and an accuracy of 88.26% during the testing phase. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Designing a Distributed Multi-agent System for Compiler Optimization

Designing a Distributed Multi-agent System for Compiler Opti...

引用

2021 Zooming Innovation in Consumer Technologies Conference, ZINC 2021

作者： Sari, Alparslan Sahin, Cagri Butun, Ismail University of Delaware Electrical and Computer Engineering Computer Systems and Networking NewarkDE United States Gazi University Computer Engineering Software Research Group Ankara Turkey Chalmers University of Technology Computer Science and Engineering Network and Systems Division Gothenburg Sweden

ISBN: (纸本)9781665404174

This paper explores the run time performance improvements using different GCC optimization flags in program compilation. As multi-core microprocessor systems replacing legacy single-core ones, tremendous effort is needed to address to optimize the associated compilers for newly designed architectures in order to suit them for running parallel programming on multiple cores. Therefore, the aim of this paper is to address this challenge by designing an optimum distributed multi-agent system to perform compiler optimization. A multi-agent framework is adopted to utilize random and genetic algorithm-based search algorithm to find the best GCC optimization flags for a given program. The framework is highly scalable and can be extended with distributed system concept to perform code compilation in parallel to find the best-optimized code sequence in a short amount of time. The initial performance results have promising indicators which clearly show that the performance improvement is achieved. © 2021 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Multimodal Ensemble Fusion-Based Deep Learning for COVID-19 on Chest Radiographs

引用

computer Systems Science & engineering 2023年第10期47卷 873-889页

作者： Mohamed Yacin Sikkandar K.Hemalatha M.Subashree S.Srinivasan Seifedine Kadry Jungeun Kim Keejun Han Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Biomedical Engineering Bannari Amman Institute of TechnologySathyamangalam638401India Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Institute of Biomedical Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea Division of Computer Engineering Hansung UniversitySeoul02876Korea

Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its *** researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their *** of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)*** the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical ***,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest *** the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly *** study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and *** major intention of the IFFO-DLEF model is to investigate the presence or absence of *** do so,the presented IFFODLEF model applies image pre-processing at the initial *** addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature ***,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify *** parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification *** experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.

关键词： COVID-19 computer vision deep learning image classification fusion model

来源：评论

学校读者我要写书评

暂无评论

A Patient Specific Algorithm for Plasmodium Malaria Detection on Cell Images

A Patient Specific Algorithm for Plasmodium Malaria Detectio...

引用

IEEE National Conference on Aerospace and Electronics (NAECON)

作者： Barath Narayanan Narayanan Manawaduge Supun de Silva Russell C. Hardie Sensor and Software Systems Division University of Dayton Research Institute Dayton USA Department of Electrical and Computer Engineering University of Dayton Dayton USA

computer-aided detection of plasmodium malaria on cell images from digital microscopy provides an invaluable second opinion to medical experts. Traditionally, well-established deep learning algorithms are widely used to detect plasmodium, but these techniques have not been deployed due to the uninterpretable nature of the decisions made by the network. To address this, we present an ensemble method that fuses the predictions based on the class activation mapping (CAM) results from multiple networks via a novel selector network. We study the performance on a publicly available dataset of cell images by using three convolutional neural network architectures, Xception, ResNet50, and InceptionV3,to produce CAM results for the selector network and performance comparison. Our proposed approach helps enhance doctors' trust and outperforms the traditional methods by 1%.

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：