检索结果-内蒙古大学图书馆

Building a neural speech recognizer for quranic recitations

International Journal of Speech technology 2023年第4期26卷 1131-1151页

作者： Al-Issa, Suhad Al-Ayyoub, Mahmoud Al-Khaleel, Osama Elmitwally, Nouh Department of Computer Engineering Jordan University of Science and Technology Irbid22110 Jordan Department of Computer Science Jordan University of Science and Technology Irbid22110 Jordan School of Computing and Digital Technology Birmingham City University BirminghamB4 7XG United Kingdom Department of Computer Science Faculty of Computers and Artificial Intelligence Cairo University Giza12613 Egypt

This work is an effort towards building Neural Speech Recognizers system for Quranic recitations that can be effectively used by anyone regardless of their gender and age. Despite having a lot of recitations available online, most of them are recorded by professional male adult reciters, which means that an ASR system trained on such datasets would not work for female/child reciters. We address this gap by adopting a benchmark dataset of audio records of Quranic recitations that consists of recitations by both genders from different ages. Using this dataset, we build several speaker-independent NSR systems based on the DeepSpeech model and use word error rate (WER) for evaluating them. The goal is to show how an NSR system trained and tuned on a dataset of a certain gender would perform on a test set from the other gender. Unfortunately, the number of female recitations in our dataset is rather small while the number of male recitations is much larger. In the first set of experiments, we avoid the imbalance issue between the two genders and down-sample the male part to match the female part. For this small subset of our dataset, the results are interesting with 0.968 WER when the system is trained on male recitations and tested on female recitations. The same system gives 0.406 WER when tested on male recitations. On the other hand, training the system on female recitations and testing it on male recitation gives 0.966 WER while testing it on female recitations gives 0.608 WER. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

DigiFarmer: Precision Agriculture Empowered by Machine Learning for Sustainable Crop Management

DigiFarmer: Precision Agriculture Empowered by Machine Learn...

引用

Networking and Communications (ICNWC), International Conference on

作者： Karan Devanand Patra Arya Adesh Bhosle Deepali Mukesh Kothari Tatwadarshi P. Nagarhalli Dept. Artificial Intelligence and Data Science Vidyavardhini’s College of Engineering and Technology Mumbai India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

In agriculture, the sector grapples with pressing challenges arising from climate change, water shortages, and pest infestations. Particularly affecting farmers in developing nations, these challenges amplify issues of food insecurity and poverty, necessitating innovative solutions for sustainable global agricultural progress. Addressing the complexities of climate variability, water scarcity, and pest outbreaks requires comprehensive tools and information. The absence of predictive insights intensifies crop losses and hampers overall profitability. In response, this research introduces DigiFarmer, an innovative solution employing advanced machine learning models. DigiFarmer adopts a holistic approach, encompassing crop disease detection, weed classification using Convolutional Neural Networks (CNNs), and crop quality analysis with a Light Gradient Boosting Machine (LGBM) classifier. Yield prediction is facilitated by the Random Forest algorithm, with real-time weather data integration enhancing efficacy. DigiFarmer stands out for empowering farmers with tools for sustainable and resilient agriculture. Leveraging cutting-edge technologies, DigiFarmer not only addresses immediate challenges but equips farmers with foresight to mitigate future risks. The ultimate goal is to contribute to the welfare of global farming communities by enabling informed decisions that enhance productivity, profitability, and sustainability in agriculture.

关键词： Productivity Adaptation models Machine learning algorithms Profitability Crops Boosting Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-head Hashing with Orthogonal Decomposition for Cross-modal Retrieval 1

引用

30th International Conference on MultiMedia Modeling, MMM 2024

作者： Liu, Wei Li, Jun Wu, Zhijian Xu, Jianhua Yang, Bo School of Computer and Electronic Information Nanjing Normal University Nanjing210023 China School of Data Science and Engineering East China Normal University Shanghai200062 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing210044 China

ISBN: (数字)9783031533082

ISBN: (纸本)9783031533075

Recently, cross-modal hashing has become a promising line of research in cross-modal retrieval. It not only takes advantage of complementary multiple heterogeneous data modalities for improved retrieval accuracy, but also enjoys reduced memory footprint and fast query speed due to efficient binary feature embedding. With the boom of deep learning, convolutional neural network (CNN) has become the de facto method for advanced cross-model hashing algorithm. Recent research demonstrates that dominant role of CNN is challenged by increasingly effective Transformer architectures due to their advantages of long-range modeling by relaxing local inductive bias. However, the absence of inductive bias shatters the inherent geometric structure, which inevitably leads to compromised neighborhood correlation. To alleviate this problem, in this paper, we propose a novel cross-modal hashing method termed Multi-head Hashing with Orthogonal Decomposition (MHOD) for cross-modal retrieval. More specifically, with the multi-modal Transformers used as the backbones, MHOD leverages orthogonal decomposition for decoupling local cues and global features, and further captures their intrinsic correlations through our designed multi-head hash layer. In this way, the global and local representations are simultaneously embedded into the resulting binary code, leading to a comprehensive and robust representation. Extensive experiments on popular cross-modal retrieval benchmarking datasets demonstrate the proposed MHOD method achieves advantageous performance against the other state-of-the-art cross-modal hashing approaches. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A System for Real-Time Shoulder Angle Measurement Using Computer Vision

A System for Real-Time Shoulder Angle Measurement Using Comp...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Meher Langote Saniya Saratkar Chetan Puri Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Higher Education and Research Wardha Maharashtra India Department of Computer Science Design Faculty of Engineering and Technology Datta Meghe Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Recently, angle measurements have been performed using a goniometer, but the complex motion of shoulder movement has made these measurements intricate. The angle of rotation of the shoulder is particularly difficult to measure from an upright position because of the complicated base and moving axes. This article presents a real-time shoulder angle measurement system utilizing computer vision and machine learning techniques, specifically designed for the rehabilitation of frozen shoulder and related conditions. The system leverages MediaPipe, an open-source framework, to capture and analyze shoulder movements accurately. With its modular architecture, the system processes video feeds in real time, detecting key body points and calculating shoulder angles, thereby providing immediate feedback to patients and therapists. The study evaluates the system's effectiveness in clinical and home-based environments, highlighting its potential to enhance physiotherapy by enabling precise, data-driven treatment plans. This research study also identifies current research gaps, proposes solutions, and explores future enhancements, including environmental adaptation, mobile integration, and the extension to other joints. This study has attempted to estimate the shoulder joint internal/external rotation angle using the combination of pose estimation artificial intelligence (AI), Computer vision, and a machine learning mode.

关键词： Computer vision Machine learning algorithms Shoulder Medical treatment Machine learning Streaming media Ubiquitous computing Real-time systems Motion measurement Smart phones

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Identity Management: Enhancing Privacy and Security in Digital Identity System 7

Blockchain-Based Identity Management: Enhancing Privacy and ...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Saranya, S. Monika Manikandan, K. Nagaraju, Jangam Nagendiran, S. Geetha, B.T. Dr. N.G.P. Institute of Technology Computer Science and Engineering Coimbatore India Mangalmay Institute of Management and Technology Greater Noida India Tamilnadu Vellore632014 India Mlr Institute of Technology Department of Data Science Dundigal Hyderabad India R. M. K. Engineering College Department of Artificial Intelligence and Data Science India Department of Ece Tamil Nadu India

ISBN: (纸本)9798350350067

Privacy and security are major concerns when it comes to digital identities, particularly in centralized systems where data can be easily hacked or where people engage in identity fraud. These issues can be addressed using blockchain technology since it allows for the creation of a decentralized digital identity that is both secure and tamper-proof. This study employs Kaggle dataset to document the transactions and the devices involved to make the distinctions on how blockchain can boost privacy and security. Predominantly, various machine learning algorithms are used to analyze blockchain applications, and the results emphasize the fact blockchain systems greatly enhance transaction viability and diminish fraudulent actions. Therefore, the study argues that blockchain-based identity management systems offset the shortcomings of the centralized model by enhancing data ownership and combating fraud. Subsequent analysis expanded on the discussion of elaborating the scalability, interoperability, and application of algorithms to blockchains as well as how it can fundamentally change the way that certain industries, particularly identity management, would work with consumers at the center of reliable and secure blockchain solutions. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Optimization of Agriculture Using data science and Machine Learning

Optimization of Agriculture Using Data Science and Machine L...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： P.Josephin Shermila Syed Atheequr Rahaman Nithosh Balaji.R Sai Manoj Department of Artificial Intelligence and Data Science R.M.K. College of Engineering and Technology India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

The research aims to optimize agriculture using data science techniques. Agriculture is a critical sector for sustaining life on earth, and optimizing it can enhance food security and increase the profitability of farmers. data science techniques such as machine learning, data analysis, and modeling to analyze agricultural data and derive insights are the key areas in this work. The project will focus on enhancing crop productivity, reducing wastage, and improving resource utilization. The findings of the project can help policymakers, farmers, and stakeholders to make informed decisions and take appropriate actions. The project aims to support the sustainable agriculture practices and promote the efficient use of resources for the benefit of both farmers and consumers.

关键词： Temperature measurement Productivity Temperature Crops Machine learning Soil data science

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Harvesting from Biodegradable Waste Using Wireless Sensor Networks and Machine Learning Techniques 4

Intelligent Energy Harvesting from Biodegradable Waste Using...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kannan, K. Jackulin Asha, G.S. Shobana, G. Sharanya, C. Beulah David, D. Sheeba Rani, S. R.M.K. College of Engineering and Technology Department of Electronics and Communication Engineering Puduvoyal Chennai India St.Joseph College of Engineering Department of Artificial Intelligence and Data Science Sriperumbudhur Chennai India Sri Krishna College of Engineering and Technology Department of Information Technology Coimbatore India Sathyabama Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Quantum Intelligence Chennai India Sri Eshwar Engineering College Department of Electronics and Communication Engineering Coimbatore India

ISBN: (纸本)9798331523923

Lack of electricity and the management of waste continue to be challenges in developing countries such as India. This project aims to provide a sustainable solution by utilizing food waste to generate electricity. The goal of the project is to maximize the energy generation from the waste by optimizing the arrangements and electrode combinations. After the electricity has been generated, it will be stored in the batteries. The monitoring system, which is called the node microcontroller, will also send data to the Think speak platform for analysis. This project's design considers the various factors that affect the quality of life in developing countries. It includes safety, scalability, and cost-effectiveness. By waste, the system can provide electricity to those who need it most. It is also contributing to the reduction of greenhouse gas emissions. © 2025 IEEE.

关键词： Things Speak

来源：评论

学校读者我要写书评

暂无评论

Decoding the News: An Integrated Approach for News Text Classification and Expert System Recommendations

Decoding the News: An Integrated Approach for News Text Clas...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Vivek Prajapati Arpit Mishra Prathmesh Shinde Neha Raut Dept. of Artificial Intelligence and Data Science Vidyavardhini’s College of Engineering and Technology Mumbai India

In the era of information overload on online platforms, efficient access to news content has become crucial for individuals leading busy lives. This paper addresses the need for categorizing vast amounts of online news data into specific sections like sports, entertainment, business, finance, etc., catering to users’ personalized interests. Leveraging Machine Learning and Deep Learning algorithms, the study utilized a BBC News dataset from Kaggle and supplemented it with an additional dataset generated through web scraping using BeautifulSoup. With up to 20,000 rows covering sports, business, entertainment, politics, and technology categories, the research applied Random Forest, Support Vector Machine (SVM), Gaussian Naive Bayes (NB), and Multi-Head Attention Transformer algorithms. The findings and recommendations extend to technologies suitable for both news text classification and user-specific content recommendation in this evolving digital landscape.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scrutinizing Domain-Specific Integrated Web Query Interfaces for Enhanced Security and Reliability in Storage Systems

Scrutinizing Domain-Specific Integrated Web Query Interfaces...

引用

2024 International Conference on Decision Aid sciences and Applications, DASA 2024

作者： Kumar, Rajeev Kumar, Pradeep Elngar, Ahmed A. Moradabad Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Moradabad India Kuala Lumpur Malaysia Beni-Suef University Faculty of Computers and Artificial Intelligence Beni-Suef City62511 Egypt

ISBN: (纸本)9798350369106

In this paper, the module is designed to possess an assortment of unique and meticulously retrieved query interfaces from multiple representative domains like travel, entertainment, and living. Using Integrated Web Query Interfaces (IWQI), which are entirely built on VDIS (View-based data Integration System) and related to data from various data sources, we have presented a novel approach to online form integration. The essential processing of the proposed model starts from the wrapper module. This module is responsible for collecting data from various sources, extracting meaningful information from them, and identifying multiple web query interfaces. The proposed model follows and applies the rules that have been given and tested by researchers even before. In the given model two major mapping tasks have been done in the wrapper module. The organizational structure of all these elements in WQI along with the positional elements are also described and defined. © 2024 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A Few-Shot Learning-Based Domain-Adaptive Lightweight CNN for Robust Hand Gesture Recognition in Real-Time Applications 2

A Few-Shot Learning-Based Domain-Adaptive Lightweight CNN fo...

引用

2nd IEEE International Conference on Integrated intelligence and Communication Systems, ICIICS 2024

作者： Shobana, K.B. Kaladeep Yalagi, Pratibha C. Ammu, V. Aldo Stalin, J.L. Kumar, Prashant Richard, Titus Department of Artificial Intelligence and Data Science Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Walchand Institute of Technology Solapur India Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Information Technology Sona College of Technology Salem India Department of Information Technology Project Circle BSNL Lalkuthi Kolkata India Department of English Vels Institute of Science Technology & Advance Studies Pallavaram Chennai India

ISBN: (纸本)9798331504960

Surface electromyogram-based hand gesture recognition (sEMG) has promising prospects in human-machine interaction applications, including the neural rehabilitation and assistive technologies. However, this technique also has several disadvantages, such as poor generalization across subjects and days, demanding a large amount of data for calibration, and computational complexity that does not enable the real-time deployment of the system. The proposed work incorporates a novel few-shot learning-based domain-adaptive lightweight CNN that is specifically designed to be used in robust and efficient hand gesture recognition. This minimizes the dependency on the labeled data of other new subjects or days, hence allowing better adaptability in real-world scenarios. The proposed lightweight CNN architecture adapts well to wearable devices with real-time performance but high accuracy. Another would be adding domain-adaptive feature learning to account for variations between inter-subject and inter-day domains while preserving the accuracy of classification and improving model generalization. The proposed framework is able to achieve competitive accuracy using a small calibration set in gesture-based human-machine interfaces continuously and broadly. Results on high-density sEMG datasets have shown that our model achieves a good balance between the accuracy (95.5%) and efficiency on experimental results and holds promise for providing a reliable solution for real-time cross-domain hand gesture recognition applications. © 2024 IEEE.

关键词： Calibration

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：