检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Zihao Ma, Le Feng, Yongsheng Pan, Xin Jin, Yuhang Zhang, Kejun Department of Computer Science Zhejiang University Hangzhou China Department of AI Music and Music Information Technology Central Conservatory of Music Beijing China Institute of Remote Sensing and Applications Beijing University of Civil Engineering and Architecture Beijing China Department of Computer Science Zhejiang University Hangzhou310027 China Department of Computer Science Zhejiang Key Laboratory of Intelligent Systems and Equipment for Digital Creativity Innovation Center of Yangtze River Delta Zhejiang University Hangzhou China

Singing voice conversion (SVC) aims to convert a singer’s voice to another singer’s from a reference audio while keeping the original semantics. However, existing SVC methods can hardly perform zero-shot due to incomplete feature disentanglement or dependence on the speaker look-up table. We propose the first open-source high-quality zero-shot SVC model SaMoye that can convert singing to human and non-human timbre. SaMoye disentangles the singing voice’s features into content, timbre, and pitch features, where we combine multiple ASR models and compress the content features to reduce timbre leakages. Besides, we enhance the timbre features by unfreezing the speaker encoder and mixing the speaker embedding with top-3 similar speakers. We also establish an unparalleled large-scale dataset to guarantee zero-shot performance, which comprises more than 1,815 hours of pure singing voice and 6,367 speakers. We conduct objective and subjective experiments to find that SaMoye outperforms other models in zero-shot SVC tasks even under extreme conditions like converting singing to animals’ timbre. The weights, code, dataset, and documents of SaMoye are publicly available on https://***/CarlWangChina/*** Codes 68Txx(Primary)14F05, 91Fxx(Secondary) Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A multimodal approach for enhanced disease management in cauliflower crops:integration of spectral sensors, machine learning models and targeted spraying technology

引用

Frontiers of Agricultural Science and engineering 2025年第2期 261-273页

作者： Rohit ANAND Roaf Ahmad PARRAY Indra MANI Tapan Kumar KHURA Harilal KUSHWAHA Brij Bihari SHARMA Susheel SARKAR Samarth GODARA Shideh MOJERLOU Hasan MIRZAKHANINAFCHI Division of Agricultural Engineering ICAR-IARI Vasantrao Naik Marathwada Krishi Vidyapeeth Central Arid Zone Research Institute Division of Vegetable Sciences ICAR-IARI Division of Design of Experiments ICAR-IASRI Division of Computer Applications ICAR-IASRI Department of Agroecology-Entomology and Plant Pathology Aarhus University Electrical Engineering and Computer Science Daktronics Engineering Hall South Dakota State University

This research explored a novel multimodal approach for disease management in cauliflower crops. With the rising challenges in sustainable agriculture, the research focused on a patch spraying method to control disease and reduce crop losses and environmental impact. For non-destructive disease assessment, a spectral sensor was used to collect spectral information from diseased and healthy cauliflower parts. The spectral data sets were analyzed using decision tree and support vector machine（SVM） algorithms to identify the most accurate model for distinguishing diseased and healthy plants. The chosen model was integrated with a low-volume sprayer(50-150 L·ha-1),equipped with an electronic control unit for targeted spraying based on sensor-detected regions. The decision tree model achieved 89.9% testing accuracy, while the SVM model achieved 96.7% accuracy using hyperparameters: cost of 10.0 and tolerance of 0.001. The research successfully demonstrated the integration of spectral sensors, machine learning, and targeted spraying technology for precise input ***, the optimized sprayer achieved a 72.5% reduction in chemical usage and a significant time-saving of 21.0% compared to a standard sprayer for black rot-infested crops. These findings highlight the potential efficiency and resource conservation benefits of innovative sprayer technology in precision agriculture and disease management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Based Personal Health Records Sharing Using Rail Fence Data Encryption (RFDE) for Secure Cloud Environment 1

Privacy Preserving Based Personal Health Records Sharing Usi...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Bhardwaj, Shashank Baskar, S. Marakala, Vijaya Prasannan, D. Gangodkar, Durgaprasad Dhole, Sumedh Vithalrao Dr. A.P.J. Abdul Kalam Technical University Department of Computer Applications Lucknow India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Department of EEE Tamilnadu Chennai India College of Medicine University of Bisha Saudi Arabia Civil Engineering Karpagam College of Engineering Tamilnadu Coimbatore India Graphic Era Deemed to Be University Department of CSE Uttarakhand Dehradun India College of Engineering Maharashtra Pune India Department of ECE India

ISBN: (纸本)9781665456876

The development of cloud technology is a fundamental idea for offering unfettered access to many different sources in the planning of the networking, memory, infrastructure, and software. computers are becoming more and more widespread across a wide range of industries due to their numerous advantages, notably in the healthcare industry. Typically, it is essential to the interchange of health information. In light of the ongoing issues with password security, sending private medical information via the internet still raises serious privacy concerns. Whether or whether they have complete permission, patients are not forced to divulge any of their private or personal information. This article examines several noteworthy recent studies that address the problems of password security and data privacy for cloud-based health services. These compare the benefits and drawbacks of different physical access preservation techniques. The paper also proposes a combined authentication procedure based on RFDE models. Cloud security is usually greatly hampered by the necessity for information privacy in an effort to protect sensitive and non-sensitive data for decision-making and to solve the problem of information leakage. One of the most challenging parts of the transfer of personal health records (PHRs) to the cloud is the reuse and exchange of accurate, complete medical evidence. When PHRs are outsourced to third-party businesses, such as cloud services, they are often used as patient-centered, private ways of exchanging health information. Data about a particular PHR doctor is coded for protection before being sent to the cloud. However, there are still substantial barriers due to issues with security, things that can be improved, lawful consumer privacy portfolio management, efficiency, and regulation over sensitive and non-sensitive data kept in the cloud. The PHR file may be encrypted using the Rail Fence Data Encryption (RFDE) technique to provide strong confidentiality rul

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Nature-Inspired Level Set Segmentation Model for 3D-MRI Brain Tumor Detection

引用

computers, Materials & Continua 2021年第7期68卷 961-981页

作者： Oday Ali Hassen Sarmad Omar Abter Ansam A.Abdulhussein Saad M.Darwish Yasmine M.Ibrahim Walaa Sheta Department of Computer Techniques Engineering Imam Al-Kadhum College(IKC)WasitIraq University of Information Technology and Communications Media Technology Engineering DepartmentIraq University of Information Technology and Communications Baghdad10081Iraq Department of Information Technology Institute of Graduate Studies and ResearchAlexandria University63 Horreya AvenueEl–ShatbyAlexandria21526Egypt Informatics Research Institute City of Scientific Research and Technology ApplicationsBorg EL Arab21934Egypt

Medical image segmentation has consistently been a significant topic of research and a prominent goal,particularly in computer *** tumor research plays a major role in medical imaging applications by providing a tremendous amount of anatomical and functional knowledge that enhances and allows easy diagnosis and disease therapy *** prevent or minimize manual segmentation error,automated tumor segmentation,and detection became the most demanding process for radiologists and physicians as the tumor often has complex *** methods for detection and segmentation presently exist,but all lack high *** paper’s key contribution focuses on evaluating machine learning techniques that are supposed to reduce the effect of frequently found issues in brain tumor ***,attention concentrated on the challenges related to level set *** study proposed in this paper uses the Population-based Artificial Bee Colony Clustering(P-ABCC)methodology to reliably collect initial contour points,which helps minimize the number of iterations and segmentation errors of the level-set *** proposed model measures cluster centroids(ABC populations)and uses a level-set approach to resolve contour differences as brain tumors vary as they have irregular form,structure,and *** suggested model comprises of three major steps:first,pre-processing to separate the brain from the head and improves contrast ***,P-ABCC is used to obtain tumor edges that are utilized as an initial MRI sequence *** level-set segmentation is then used to detect tumor regions from all volume slices with fewer *** suggest improved model efficiency compared to state-of-the-art methods for both datasets BRATS 2019 and BRATS *** BRATS 2019,dice progress was achieved for Entire Tumor(WT),Tumor Center(TC),and Improved Tumor(ET)by 0.03%,0.03%,and 0.01%*** BRATS 2017,an increase in precision for WT was reac

关键词： 3D-MRI tumor diagnosis bio-inspired clustering ABC optimization multimodal detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Neural Network for Intracranial Haemorrhage Detection and Classification

引用

computers, Materials & Continua 2021年第9期68卷 2877-2893页

作者： D.Venugopal T.Jayasankar Mohamed Yacin Sikkandar Mohamed Ibrahim Waly Irina V.Pustokhina Denis A.Pustokhin K.Shankar Department of ECE KPR Institute of Engineering and TechnologyCoimbatore641407India Department of Electronics and Communication Engineering University College of EngineeringBIT CampusAnna UniversityTiruchirappalli620024India Department of Medical Equipment Technology College of Applied Medical SciencesMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Entrepreneurship and Logistics Plekhanov Russian University of EconomicsMoscow117997Russia Department of Logistics State University of ManagementMoscow109542Russia Department of Computer Applications Alagappa UniversityKaraikudi630001India

Data fusion is one of the challenging issues,the healthcare sector is facing in the recent *** diagnosis from digital imagery and treatment are deemed to be the right *** Haemorrhage(ICH),a condition characterized by injury of blood vessels in brain tissues,is one of the important reasons for *** generated by X-rays and Computed Tomography(CT)are widely used for estimating the size and location of *** use manual planimetry,a time-consuming process for segmenting CT scan *** Learning(DL)is the most preferred method to increase the efficiency of diagnosing *** this paper,the researcher presents a unique multi-modal data fusion-based feature extraction technique with Deep Learning(DL)model,abbreviated as FFE-DL for Intracranial Haemorrhage Detection and Classification,also known as *** proposed FFEDL-ICH model has four stages namely,preprocessing,image segmentation,feature extraction,and *** input image is first preprocessed using the Gaussian Filtering(GF)technique to remove ***,the Density-based Fuzzy C-Means(DFCM)algorithm is used to segment the ***,the Fusion-based Feature Extraction model is implemented with handcrafted feature(Local Binary Patterns)and deep features(Residual Network-152)to extract useful ***,Deep Neural Network(DNN)is implemented as a classification technique to differentiate multiple classes of *** researchers,in the current study,used benchmark Intracranial Haemorrhage dataset and simulated the FFEDL-ICH model to assess its diagnostic *** findings of the study revealed that the proposed FFEDL-ICH model has the ability to outperform existing models as there is a significant improvement in its *** future researches,the researcher recommends the performance improvement of FFEDL-ICH model using learning rate scheduling techniques for DNN.

关键词： Intracerebral hemorrhage fusion model feature extraction deep features classification

来源：评论

学校读者我要写书评

暂无评论

Critical Analysis and Evaluation of Current Digital Healthcare Solutions 23

Critical Analysis and Evaluation of Current Digital Healthca...

引用

23rd International Conference on Control Systems and computer Science Technologies, CSCS 2021

作者： Ianculescu, Marilena Alexandru, Adriana Pop, Florin Systems and Applications for Society Department National Institute for RandD in Informatics Bucharest Romania Doctoral School of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Department of Computer Science and Engineering University Politehnica of Bucharest Bucharest Romania

ISBN: (纸本)9781665439398

Digitalization of health, healthcare and healthcare delivery unequivocal have positive consequences contributing to health system goals, but they also might have some negative ones which have to be avoided or mitigated. The scope of this paper is to introduce the necessity of the assessment of Health Technology Assessment (HTA) and to identify the most appropriate and important criteria needed for the evaluation and comparison of functional digital healthcare solutions. It aims to outline consistent criteria against which digital health technologies and services can be evaluated during the prototyping phase, but also during long-term operation. © 2021 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Copy-deterrence scheme for Secure Image Outsourcing in Cloud

An Enhanced Copy-deterrence scheme for Secure Image Outsourc...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： J. Anju R. Shreelekshmi Department of Computer Science and Engineering College of Engineering Trivandrum Affiliated to A. P. J. Abdul Kalam Technological University Thiruvananthapuram Kerala India Department of Computer Applications College of Engineering Trivandrum Affiliated to A. P. J. Abdul Kalam Technological University Thiruvananthapuram Kerala India

ISBN: (纸本)9781665462013

In this paper, we propose a novel watermarking-based copy deterrence scheme for identifying data leaks through authorized query users in secure image outsourcing systems. The scheme generates watermarks unique to each query user, which are embedded in the retrieved encrypted images. During unauthorized distribution, the watermark embedded in the image is extracted to determine the untrustworthy query user. Experimental results show that the proposed scheme achieves minimal information loss, faster embedding and better resistance to JPEG compression attacks compared with the state-of-the-art schemes.

关键词： Image coding Biometrics (access control) Forensics Transform coding Watermarking Outsourcing Cryptography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Traffic engineering Policy in SDN Addressing TCAM limitations using Bloom Filters

Enhancing Traffic Engineering Policy in SDN Addressing TCAM ...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Akash Ghosh Lalbihari Barik Suchismita Rout Bhupender Singh Rawat Prakash Chandra Jena Sudhansu Shekhar Patra School of Computer Applications KIIT Deemed To be University Bhubaneswar India Department of Information Systems Faculty of Computing and Information Technology in Rabigh King Abdul Aziz University Kingdom of Saudi Arabia College of Smart Computing COER University Roorkee India Department of Computer Sc and Engg Hi-Tech College of Engineering Bhubaneswar India

With the increasing demand for new technologies, the speed of delivering a packet is becoming the major focus of various industries. The generation of huge traffic is becoming the bottleneck of the current scenario. By segregating the control plane from the data plane, Software Defined Networking (SDN) is able to many such issues to certain extent. But the traffic engineering problem still remains as an important topic to focus on. Ternary Content Addressable Memory (TCAM) is capable of solving many such issues with the cost of its cost and power issues. For the effective use of TCAM, various algorithms and mechanisms have been proposed by many researchers. Bloom filter is one of the popular ways which is able to provide effective solutions after collaborating with TCAM. An algorithm has been proposed which is able to find the exact match of the entry in TCAM. The use of a CRC generator and multiple hashing tables makes it effective at finding the presence of a flow rule in TCAM, in very little time. The major focus is on the fast search procedure for finding the exact match of the flow rule. The number of false positives (FPs) is reduced to a lower percentage value as compared to the existing approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Orbital Angular Momentum Channels in Bent Inverse Raised Cosine fiber 3

Analysis of Orbital Angular Momentum Channels in Bent Invers...

引用

3rd IEEE International Conference on Design and Test of Integrated Micro and Nano-Systems, DTS 2021

作者： Rjeb, Alaaeddine Fathallah, Habib MacHhout, Mohsen University of Monastir Laboratory of Electronics and Microelectronics Department of Physics Faculty of Sciences of Monastir Monastir5019 Tunisia University of Carthage Laboratory of Artificial Intelligence and Data Engineering Applications Computer Department Faculty of Sciences of Bizerte Tunis1054 Tunisia

ISBN: (纸本)9780738132631

Orbital angular momentum (OAM) has gained a widespread interest in diverse areas especially in telecommunication due to its capability to elevate the capacity transmission and substantially improving the spectral efficiency of optical communication in optical fibers. In this work, we numerically investigate the bending impacts on OAM channels transmitted through inverse raised cosine few mode fiber (IRC-FMF). The obtained results show that the investigated OAM-Fiber supports 8 OAM data carriers, already presented in straight case, even under tight bend (i.e. at bending radius Rb=4 mm) with maximum loss of 0.0001 dB/m. This confirms the great tolerance of IRC-FMF to bending condition and confirms the capability of such fiber to handle robust OAM channels even under realistic environment. © 2021 IEEE.

关键词： Space division multiple access

来源：评论

学校读者我要写书评

暂无评论

SETA: Semantic-Aware Token Augmentation for Domain Generalization

arXiv

引用

arXiv 2024年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Nanjing211189 China

Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation, which focuses on generating virtual samples to simulate domain shifts. However, existing augmentation techniques in DG are mainly tailored for convolutional neural networks (CNNs), with limited exploration in token-based architectures, i.e., vision transformer (ViT) and multi-layer perceptrons (MLP) models. In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information. To tackle the issue, we propose the Semantic-aware Edge-guided Token Augmentation (SETA) method. SETA transforms token features by perturbing local edge cues while preserving global shape features, thereby enhancing the model learning of shape information. To further enhance the generalization ability of the model, we introduce two stylized variants of our method combined with two state-of-the-art (SOTA) style augmentation methods in DG. We provide a theoretical insight into our method, demonstrating its effectiveness in reducing the generalization risk bound. Comprehensive experiments on five benchmarks prove that our method achieves SOTA performances across various ViT and MLP architectures. Our code is available at https://***/lingeringlight/SETA. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：