检索结果-内蒙古大学图书馆

4th International Conference on Signal Processing and Communication, ICSPC 2023

作者： Gladston, Anushiya Rachel Pradeep, K.V. Vellore Institute of Technology Chennai School of Computer Science Engineering Chennai India

ISBN: (纸本)9798350300772

A text-to-speech synthesis system is expected to convert any given text to highly intelligible and natural speech that sounds as human-like as possible. It finds its place in a variety of applications, like virtual assistants, speech-assistive aids, and speech-to-speech translation systems. In recent years several deep learning-based methods have been proposed for text-to-speech synthesis, which result in synthetic speech that is intelligible and very natural. However, these methods require a large amount of speech data, in the order of tens of hours, preferably recorded from a single speaker and in a quiet/studio environment. While such a large amount of data might be easily available for certain languages, like English, which are widely spoken and used globally, this is not the case with several other languages. In this regard, the current work explores state-of-the-art text-to-speech synthesis methods and strategies for handling low-resource languages. The paper ultimately aims to provide insight into developing text-to-speech systems for Indian languages and hence reviews the work done so far on Indian languages as well. Since India is a multilingual country where several languages co-exist, a multilingual synthesizer would be preferable. Further, one recurring suggestion to handle data scarcity is to make use of data from multiple languages too. Therefore, the current work focuses on exploring multilingual text-to-speech synthesis for low-resource languages. © 2023 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

Detection of Tile Surface Based on SSM-R-CNN Algorithm 5

Detection of Tile Surface Based on SSM-R-CNN Algorithm

引用

5th International Conference on Frontiers technology of Information and computer, ICFTIC 2023

作者： Wang, Jiahua Li, Lin Kong, Siman Zhou, Chenyang Sun, Jianzhi Beijing Technology and Business University School of Computer Science and Engineering Beijing China

ISBN: (纸本)9798350309034

A computer vision algorithm, SSM-R-CNN, based on feature extraction and adaptive weighting, is proposed to address the challenges of diverse tile types, complex surface areas, and varied defect morphologies, as well as low image contrast in tile surface defect detection. The algorithm extracts templates and defect images from the original images, aligns them using the SURF algorithm, and enhances the features through gray image differencing, mean, and variance normalization. By incorporating edge-preserving filters and bilateral filters, the algorithm achieves a flexible balance between image smoothing and detail preservation to meet the requirements of different application scenarios. Furthermore, the algorithm improves the Mask R-CNN model by integrating the SENet channel attention mechanism, Explore the interaction and importance of feature information between learning channels, thereby enhancing the network's expressive power and accuracy. Experimental results demonstrate the outstanding performance of the proposed algorithm in tile surface defect detection, achieving excellent accuracy, recall rate, and F1-score of 98.72%, 95.65%, and 97.18%, respectively. The algorithm exhibits stable and reliable performance in handling complex textures, non-uniform lighting, and low contrast. With its promising prospects in the field of tile surface defect detection, this method provides a new approach to adaptive weighting. © 2023 IEEE.

关键词： Adaptive weighting Bilateral filter computer vision Feature extraction SENet channel attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Feature Cross Perception Instance Segmentation Network based on 3D Point Cloud 8

Multi-scale Feature Cross Perception Instance Segmentation N...

引用

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： He, Liuqin Li, Wenju Cui, Liu Liu, Xinzhe Shanghai Institute of Technology School of Computer Science and Information Engineering Shanghai China

ISBN: (纸本)9798350369564

To address challenges in 3D point cloud instance segmentation, we propose a novel network called Multi-scale Feature Cross Perception Instance Segmentation Network (MFCPNet). MFCPNet incorporates two key enhancements to improve the performance of 3D point cloud instance segmentation. Firstly, we introduce a multi-scale semantic aggregation module that effectively captures scene features using Markov Chain Monte Carlo (MCMC) for point filtering and aggregation. This module enables the extraction of intricate semantic information across various scales. Secondly, MFCPNet integrates a feature cross perception module employing an attention mechanism to independently process features from different scales. By connecting features from diverse scales, the model achieves a comprehensive and enriched representation. Extensive experiments on the ScanNetv2 dataset demonstrate the superiority of MFCPNet. Notably, MFCPNet outperforms other methods by 2.8% in mean Average Precision (mAP) on the ScanNetv2 test set. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hand-Gesture Based Emoji Identification and Chat Integration 5

Hand-Gesture Based Emoji Identification and Chat Integration

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Tare, Sanskar S Patil, Madhav J Alam, Adnan Swarnalatha, P. School of Computer Science and Engineering Vellore Institute of Technology Vellore Vellore India

ISBN: (纸本)9798350321425

Every aspect of human life is slowly getting computerized and gradually turning electronic. This has made a rangeof tasks a lot easier and accessible for people from all walks of life. Unfortunately, this rapid computerization and the ever changing landscape of electronics has given birth to a new classof computer - illiterate individuals. Such individuals exist due to the lack of accessibility to latest electronic gadgets, or humansocial problems like old age. There is a need to make technology fun and easier to use for individuals belonging to such classes. The very primary use of internet-based networking is text-based communications namely: e-mails, texts chats, blogs, etc. The text based interaction is mainly facilitated using a keyboard which makes it the most focal human-computer interaction involved. The modern usage of this text-based communication involves extensive usage of emoticons. While most handheld devices feature a customised emoji-keyboard, the emoji keyboard is difficult to access in personal computers. This can adversely affect the interactions the aforementioned computer-illiterates partake in. This project aims to deal with this problem by creating a hand-detection based emoji detection algorithm in python through OpenCV and Mediapipe for detection of hand landmarks and implementing it in one such communication channel. The algorithm consists of two modules: a Hand-Tracking Moduleand an emoji detector capable of matching the tracked hand to existing emoji database. The resulting application is consistent, allow frequent users to use shortcuts and make the user feel more in control. The work also strives to integrate error prevention and simple error handling in existing emoji detection technologies along with managing short term memory load. © 2023 IEEE.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection Based on LSTM-GRU in SDN Environment 6

DDoS Attack Detection Based on LSTM-GRU in SDN Environment

引用

6th International Conference on computer Information science and Application technology, CISAT 2023

作者： Gao, Chenguang Yin, Mingxuan School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9781510668546

The implementation of software-defined networking (SDN) as a new network architecture brings about a variety of novel characteristics and application scenarios, decreasing network development redundancy, but it also raises serious security concerns. This study describes and develops the recurrent neural network-based LSTM-GRU detection algorithm for distributed denial-of-service attacks (DDoS) assaults in SDN, which uses LSTM and GRU as the base model and stacks them to achieve high accuracy classification of traffic. According to tests, the detection algorithm outperforms conventional detection techniques, achieving accuracy levels of 99.53% and 98.78% on the CIC-IDS 2017 and CIC-DDoS 2019 datasets, respectively. © 2023 SPIE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

A Universal Virtual Reality Training Platform for Microscale Robotic Cell Injection in Biomedical Research and Practice

引用

SN computer science 2024年第8期5卷 1-13页

作者： Hafeez, Rubab Amjad, Zohaib Waheed, Sadia Hasan, Osman Sharif, Muhammad Imran Ulhaq, Anwaar Department of Computer Science University of Wah Wah Cantt 47010 Pakistan School of Electrical Engineering and Computer Science NUST Islamabad 44320 Pakistan Department of Computer Science Kansas State University Manhattan 66506 United States Manna Institute School of Engineering and Technology Central Queensland University Brisbane QLD Australia

Micro-robotic cell injection is a widely used procedure in cell biology where a small quantity of biological material is inserted into a cell using an automated or semi-automated micro-robotic system. Given its micro-scale nature, cell injection using a semi-automated micro-robotic system requires extremely high precision, hand-eye coordination, and depth perception for maneuvering the micro-pipette. As the cell injection is a laborious work, there is a dire need of rigorous training and a great deal of experience using live specimens and high-end microscopes. To facilitate this training, we have presented a paper in the past about modular virtual reality (VR) with basic simulation modules, here, the present work deals with the modelling of advanced training modules and experimenting of VR simulator. The proposed simulator includes: (i) Advanced training modules to train users on complete injection/suction procedures;(ii) The performance evaluation of the users using three metrics, i.e., (i) time, (ii) trajectory, and (iii) positioning accuracy is also integrated within the simulator;(iii) An experimental set-up has been developed for the face, content, and construct validity of the VR simulator. Finally, the effectiveness of the proposed simulator is validated by experts from the relevant domains and can be used for various applications like drug delivery, injection procedures and in-vitro fertilization. The experimental results demonstrated that a Virtual cell injection training simulator is feasible for the training of cell injection procedures and depicted that the injection success rate is 100% after using VR simulator. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adherent cells Cell injection Collision modeling Micro-robotic Simulator validity VR simulation

来源：评论

学校读者我要写书评

暂无评论

Hybridization of Metaheuristics Based Energy Efficient Scheduling Algorithm for Multi-Core Systems

引用

computer Systems science & engineering 2023年第1期44卷 205-219页

作者： J.Jean Justus U.Sakthi K.Priyadarshini B.Thiyaneswaran Masoud Alajmi Marwa Obayya Manar Ahmed Hamza Department of Computer Science&Engineering St.Joseph’s College of EngineeringChennai600119India Department of Computer Science and Engineering Saveetha School of EngineeringSIMATSChennai602105India Department of Electronics and Communication Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Electronics and Communication Engineering Sona College of TechnologySalem636005India Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The developments of multi-core systems(MCS)have considerably improved the existing technologies in thefield of computer *** MCS comprises several processors that are heterogeneous for resource capacities,working environments,topologies,and so *** existing multi-core technology unlocks additional research opportunities for energy minimization by the use of effective task *** the same time,the task scheduling process is yet to be explored in the multi-core *** paper presents a new hybrid genetic algorithm(GA)with a krill herd(KH)based energy-efficient scheduling techni-que for multi-core systems(GAKH-SMCS).The goal of the GAKH-SMCS tech-nique is to derive scheduling tasks in such a way to achieve faster completion time and minimum energy *** GAKH-SMCS model involves a multi-objectivefitness function using four parameters such as makespan,processor utilization,speedup,and energy consumption to schedule tasks *** performance of the GAKH-SMCS model has been validated against two datasets namely random dataset and benchmark *** experimental outcome ensured the effectiveness of the GAKH-SMCS model interms of makespan,pro-cessor utilization,speedup,and energy *** overall simulation results depicted that the presented GAKH-SMCS model achieves energy effi-ciency by optimal task scheduling process in MCS.

关键词： Task scheduling energy efficiency multi-core systems fitness function makespan

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Location Sharing via LWE-based Private Information Retrieval 8

Privacy-Preserving Location Sharing via LWE-based Private In...

引用

8th International Conference on Intelligent Informatics and Biomedical sciences, ICIIBMS 2023

作者： Xue, Qingshui Cui, Tianrui Shanghai Institute of Technology School of Computer Science and Information Engineering Shanghai China

ISBN: (纸本)9798350369564

We proposes a privacy-preserving location sharing scheme based on Learning with Errors (LWE) encryption, emphasizing its ability to resist quantum computing attacks and provide a high level of security. In order for real-world usage, we focus on its efficiency, flexibility, and adaptability for streaming. Location privacy has has emerged as a critical concern in today's data-driven society, due to the widespread usage of location-based services and the growing demand for personalized information. We leverages for fast and accurate information retrieval while maintaining robust privacy guarantees, achieving peer-to-peer transmission, 128-bit security or higher and an unparalleled throughput of 10 GB/s/core Through extensive experimental evaluations conducted on real-world deployments, we demonstrate the remarkable performance of our scheme in terms of preserving privacy and retrieval speed, particularly for streaming location data. © 2023 IEEE.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

DSA-MFNet: Deep-shallow Attention based Multi-frame Fusion Network for EEG motor imagery classification

DSA-MFNet: Deep-shallow Attention based Multi-frame Fusion N...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Li, Huifu Zhang, Xun Wan, Yuchai Zhang, Xin Beijing Technology and Business University School of Computer Science and Engineering Beijing China

ISBN: (纸本)9798350337488

One of the most prevalent brain-computer interface (BCI) paradigms is the Electroencephalogram (EEG) motor imagery (MI). It has found extensive applications in numerous fields. While there have been significant strides in achieving high MI classification performance, certain challenges still persist:Effective utilization of the time-varying spatial and temporal features from multi-channel brain signals remains elusive. Fully leveraging the interactive information embedded within finite-length MI-EEG samples is still an open question. In this study, we introduce the Deep-Shallow Attention-Based Multi-Frame Fusion Network (DSA-MFNet) tailored for EEG-based motor imagery classification. The architecture of DSA-MFNet encompasses both a Deep-Shallow Attention (DSA) module and a Multi-Frame Fusion (MF) module. In detail, the DSA module integrates a deep-shallow convolution block, which extracts both intricate deep spatial-temporal features and surface-level features. Subsequently, an attention block emphasizes the most salient features in MI-EEG data. Meanwhile, the MF module delves into the interactions amongst multiple frames in the MI-EEG data, shedding light on the unique characteristics of time-varying EEG *** model sets a new benchmark by outperforming the leading techniques, achieving an accuracy of 86.6% on the BCI Competition IV-2a dataset for subject-dependent modes. For the sake of transparency and to foster further research, we will be making our code and trained models available on GitHub. © 2023 IEEE.

关键词： attention EEG fusion motor imagery

来源：评论

学校读者我要写书评

暂无评论

Research on GPU-Based Parallel Processing for the Paillier Algorithm 3

Research on GPU-Based Parallel Processing for the Paillier A...

引用

3rd International Conference on Blockchain technology and Information Security, ICBCTIS 2023

作者： Teng, Yifei Liu, Chunyuan School of Computer and Information Engineering Heilongjiang University of Science and Technology Harbin China

ISBN: (纸本)9798350340402

The homomorphic encryption algorithm Paillier is a cryptographic method that can be applied in areas such as privacy-preserving computation and federated learning. However" due to the inherent complexity and computational overhead of the algorithm, it may affect real-time requirements when dealing with a large volume of encrypted data. In this paper, we propose a method to improve the efficiency of the encryption algorithm by combining GPU parallel processing technology with homomorphic encryption. Through experiments on encrypting and decrypting plaintexts of different sizes, the results show that the introduction of GPU significantly improves the encryption and decryption speed Compared with other parallel processing methods" the acceleration effect of our proposed method is more significant. © 2023 IEEE.

关键词： Graphics processing unit

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：