检索结果-内蒙古大学图书馆

Audio-Text Multimodal Speech Recognition via Dual-Tower Architecture for Mandarin Air Traffic Control Communications

引用

computers, Materials & Continua 2024年第3期78卷 3215-3245页

作者： Shuting Ge Jin Ren Yihua Shi Yujun Zhang Shunzhi Yang Jinfeng Yang School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic UniversityShenzhen518055China Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Industrial Training Centre Shenzhen Polytechnic UniversityShenzhen518055China

In air traffic control communications (ATCC), misunderstandings between pilots and controllers could result in fatal aviation accidents. Fortunately, advanced automatic speech recognition technology has emerged as a promising means of preventing miscommunications and enhancing aviation safety. However, most existing speech recognition methods merely incorporate external language models on the decoder side, leading to insufficient semantic alignment between speech and text modalities during the encoding phase. Furthermore, it is challenging to model acoustic context dependencies over long distances due to the longer speech sequences than text, especially for the extended ATCC data. To address these issues, we propose a speech-text multimodal dual-tower architecture for speech recognition. It employs cross-modal interactions to achieve close semantic alignment during the encoding stage and strengthen its capabilities in modeling auditory long-distance context dependencies. In addition, a two-stage training strategy is elaborately devised to derive semantics-aware acoustic representations effectively. The first stage focuses on pre-training the speech-text multimodal encoding module to enhance inter-modal semantic alignment and aural long-distance context dependencies. The second stage fine-tunes the entire network to bridge the input modality variation gap between the training and inference phases and boost generalization performance. Extensive experiments demonstrate the effectiveness of the proposed speech-text multimodal speech recognition method on the ATCC and AISHELL-1 datasets. It reduces the character error rate to 6.54% and 8.73%, respectively, and exhibits substantial performance gains of 28.76% and 23.82% compared with the best baseline model. The case studies indicate that the obtained semantics-aware acoustic representations aid in accurately recognizing terms with similar pronunciations but distinctive semantics. The research provides a novel modeling pa

关键词： Speech-text multimodal automatic speech recognition semantic alignment air traffic control communications dual-tower architecture

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling and Analysis of COVID-19 with Machine Learning Techniques 5

Predictive Modeling and Analysis of COVID-19 with Machine Le...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Pant, Garima Pant, Janmejay Kotlia, Priyanshi Singh, Devendra Khulbe, Sumit Bhatt, Jaishankar Graphic Era Hill University Department of PC/PDP Bhimtal Campus India Graphic Era Hill University Department of Computer Science and Engineering Bhimtal Campus India Amrapali group of institutes Department of Computer Applications Uttarakhand Haldwani India SSJ University Department of Information Technology Uttarakhand Almora India Graphic Era Deemed to be University Department of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350367171

For successful management of COVID-19 pandemic outbreak, case detection has to be done through Machine Learning (ML). The Machine Learning (ML) techniques can be used to process the patient's data, such as imaging and results of various tests, to detect Covid19 cases. This study aims to present a computer learning model for COVID-19 severity and course prediction using initial manifestations. As a result of training and classification, supervised learning methods are included in the proposed approach in order to detect the presence of the corona virus COVID-19 and classify it. Estimation and predication of COVID-19 infection can be accomplished by machine learning principle and statistical and computational models on how to assess negative and positive impacts of the virus. The data was analyzed using two machine learning models: Random forest (RF) and Logistic regression (LR) have been chosen as classification algorithms to build models based on the obtained data. The results found out that both LR and RF were equally accurate knowing that the overall accuracy recorded was good. The following model provides a wayof accurately categorizing patients, making it easier for health care professionals and policymakers to track the risky individuals. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of CNN and Transfer Learning Algorithms in Predicting Alzheimer’s Disease Stages Using Neuroimaging

A Comparative Analysis of CNN and Transfer Learning Algorith...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Meenakshi Sharma Bhavneet Bhagat Vandana Kumari Bhumi Naman Sharma Dipti Singh Department of Computer Science Engineering Global Group of Institutes Amritsar India Department of Computer Science Engineering Guru Nanak Dev University Amritsar India

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

Alzheimer’s disease (AD) prediction plays a critical role in early detection and intervention, allowing for better patient care and management. This paper investigates the predictive capabilities and state-of-art of Convolutional Neural Networks (CNN) and transfer learning models, including Inception V3, Resnet-18, and Resnet-50, for the progression of Alzheimer’s disease (AD). The Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset used in this study, which includes multimodal neuroimaging, clinical, genetic and demographic data, the research aims to provide accurate predictions at various stages of the EA. This dataset enables robust training and evaluation of deep learning algorithms to predict AD progression. The data undergoes preprocessing and feature engineering to prepare a robust data set. Evaluations covering accuracy, precision, recall and F1 score, using k-fold cross-validation, are performed to measure the performance of the chosen algorithms. CNN and Inception V3 demonstrate remarkable performance with an accuracy of 93.75% and 94%. Comparative analyzes include exploration of Inception V3, Resnet-18, and Resnet-50, shedding light on their individual contributions to AD prediction. This paper contributes to the development of reliable and efficient deep learning approaches for early prediction and diagnosis of AD, with the potential to improve patient outcomes. Comparing the predictive capabilities of CNNs and transfer learning models provides valuable insights into their effectiveness in modeling AD progression.

关键词： Neuroimaging Deep learning Training Accuracy Computational modeling Transfer learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Design of Variational Autoencoder for Generation of Odia Handwritten Numerals in CNN Model 2nd

Design of Variational Autoencoder for Generation of Odia Han...

引用

2nd International Conference on Innovation in Electrical Power engineering, Communication, and Computing Technology, IEPCCT 2021

作者： Das, Abhishek Mohapatra, Saumendra Kumar Mohanty, Mihir Narayan Bhubaneswar751030 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institutes of Medical and Technical Sciences Chennai India

ISBN: (纸本)9789811670756

Generative models have fascinated attention of researchers as it learns the important features from the trained data to generate the structures similar to the data provided for training. Autoencoders are the basic building components of generative models. In this work, we have designed a variational autoencoder to generate a large number of data to support the generative adversarial network model. The encoder, as well as the decoder of the proposed model, is designed using convolutional layers. The proposed method is verified on IIT Bhubaneswar Odia handwritten database. The encoder generates the feature vectors with the probability distribution of each category in latent space that follows the Gaussian distribution. It is verified that the decoder recognizes the features due to proper training. The generated images are quite similar to original data that validate the proposed VAE is well-generative. To measure the performance of the model, loss is calculated using binary cross-entropy along with Kullback–Leibler divergence loss. The proposed model is trained with Adam optimizer. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection and Localization from MRI Scan Images

Brain Tumor Detection and Localization from MRI Scan Images

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Richa Sharma Radhika Kumari Bhanu Thakur Kuldeep Kumar Computer Science and Engineering Chandigarh University Chandigarh India Computer Science and Engineering Global Group of Institutes Amritsar India Computer Science and Engineering Chandigarh University

A tumor is a tissue mass produced by an accumulation of uncontrolled cells that keeps growing. A brain cancer is a tumor that is either framed in the cerebrum or has spread there. In this research, a model is proposed that can accurately segments pictures using the PSO methods, extracts features using the PCA strategies, and classifies tumors using the CNN. A mind cancer is a growth which is either framed in the cerebrum or has relocated No essential driver has been recognized for the arrangement of growths in the cerebrum till date. However, cancers in the mind are not extremely normal (Worldwide cerebrum growths make up just 1.8% of complete detailed cancers), the death pace of threatening cerebrum cancers is exceptionally high because of the way that the growth development is in the most basic organ of the body. Subsequently, it is of most extreme significance to precisely recognize mind cancers at beginning phases to bring down the death rate. We have accordingly proposed a space variation based Deep Neural Network which will evaluate cerebrum growths from MRI checks for the administration of mind cancer conclusion. In this review, we have executed a model that identify the pictures by utilizing ResNet based profound brain network which has previously been prepared on huge picture datasets and move this preparing information into our own information. To augment the presentation, I have additionally tweaked it in light of our concern set.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of CT Scan Lung Cancer Images using Machine Learning Algorithms 6

Analysis of CT Scan Lung Cancer Images using Machine Learnin...

引用

6th International Conference on Intelligent Computing and Control Systems, ICICCS 2022

作者： Rathod, Seema Babusing Ragha, Lata Sipna College of Engineering and Technology Amravati Department of Computer Science and Engineering Amravati India Fr. C. Rodrigues Institutes Technology Department of Computer Engineering Navi Mumbai India

ISBN: (纸本)9781665410359

Inflammation of the lungs is caused by the growth of cancer cells. Men and women are more likely to die from cancer as the disease progresses. Cancer cells in the lungs develop outside of management in the context of lung cancer. While there is no proven way to prevent lung cancer, the recent technologies can be used to reduce its risk. Lung cancer can be fast detected and also quickly increase a patient's chances of survival. Patients with lung cancer equally have a higher chance of not smoking the paper, studying machine learning algorithms, and comparing the precision classification method based on this method. Classification techniques such as Naive Bayes, SVM, Decision Tree, and Logistic Regression were used to investigate lung cancer prediction. The primary goal of this research is to investigate the performance of classification algorithms in the early detection of lung cancer. In the United States, smoking causes about 80 percent of all deaths from lung cancer. Throughout this research, the lung cancer has been detected efficiently. Support equipment achieves an accuracy of 98.61% and an AUC school of 94%. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Using Weakly Supervised Machine learning Algorithms for Classification and Analysis of CT Scan Lung Cancer Images 2

Using Weakly Supervised Machine learning Algorithms for Clas...

引用

2nd IEEE International Conference on Intelligent Technologies, CONIT 2022

作者： Babusing Rathod, Seema Ragha, Lata Sipna College of Engineering and Technology Amravati Department of Computer Science and Engineering Amravati India Fr. C. Rodrigues Institutes Technology Department of Computer Engineering Navi Mumbai India

ISBN: (数字)9781665484077

ISBN: (纸本)9781665484077

At present, scientific pictures have played a more and a greater critical function in clinical remedies. Lung pics provide an important reference for medical doctors to make an analysis. specifically for surgical patients, a tumor can be efficaciously removed based on the entire cognition of its size, feature, and quantity. therefore, pc-aided analysis for the evaluation and remedy of diffusion of lung tumor images can be very critical. Aiming at the complexity and self-adaption of image segmentation in lung tumors, this paper proposed to use the machine learning algorithms to study a set of rules with supervising algorithms interest mechanism for photograph segmentation. In this paper, we have to use the SVM, Decision Tree, Logistic regression, and Naïve Bayes algorithms for the classification of CT scan lung cancer images. In this paper, we have found the accuracy using the machine learning algorithms and we are analyzing the SVM is improve the accuracy. It provides the stylish delicacy of 98.61 %, the perfection of 96.65%, a perceptivity of 100%, and particularity of 99.25%, which outperforms other machine literacy models. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Gallai Signed Graphs and Anti-Gallai Signed Graphs 14

Gallai Signed Graphs and Anti-Gallai Signed Graphs

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Madhusudhan, K.V. Reddy, Sashi Kanth Reddy, P. Siva Kota Department of Mathematics ATME College of Engineering Mysore570 028 India Department of Computer Science AIMS Institutes Bangalore India Department of Mathematics JSS Science and Technology University Mysuru570 006 India

In this paper we introduced the new notions Gallai and anti-Gallai signed graph of a signed graph and its properties are obtained. Also, we obtained the structural characterizations of these notions. Further, we prese... 详细信息

关键词： 05C12 Anti-Gallai Signed Graph Balance Gallai Signed graph Mathematics Subject Classification: 05C22 Signed graphs Switching

来源：评论

学校读者我要写书评

暂无评论

Protein Residue Contact Prediction Based on Deep Learning and Massive Statistical Features from Multi-Sequence Alignment

引用

Tsinghua science and Technology 2022年第5期27卷 843-854页

作者： Huiling Zhang Min Hao Hao Wu Hing-Fung Ting Yihong Tang Wenhui Xi Yanjie Wei Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen 518055China University of Chinese Academy of Sciences Beijing 100049China College of Electronic and Information Engineering Southwest UniversityChongqing 400715China School of Software Engineering University of Science and Technology of ChinaHefei 230051China Department of Computer Science The University of Hong KongHong Kong 999077China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Sequence-based protein tertiary structure prediction is of fundamental importance because the function of a protein ultimately depends on its 3 D *** accurate residue-residue contact map is one of the essential elements for current ab initio prediction protocols of 3 D structure ***,with the combination of deep learning and direct coupling techniques,the performance of residue contact prediction has achieved significant ***,a considerable number of current Deep-Learning(DL)-based prediction methods are usually time-consuming,mainly because they rely on different categories of data types and third-party *** this research,we transformed the complex biological problem into a pure computational problem through statistics and artificial *** have accordingly proposed a feature extraction method to obtain various categories of statistical information from only the multi-sequence alignment,followed by training a DL model for residue-residue contact prediction based on the massive statistical *** proposed method is robust in terms of different test sets,showed high reliability on model confidence score,could obtain high computational efficiency and achieve comparable prediction precisions with DL methods that relying on multi-source inputs.

关键词： multi-sequence alignment residue-residue contact prediction feature extraction statistical information Deep Learning(DL) high computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Identification Model of Economically Disadvantaged College Students Using GBDT 24

Identification Model of Economically Disadvantaged College S...

引用

2024 International Symposium on Artificial Intelligence for Education, ISAIE 2024

作者： Peng, Shuhong Qian, Jing Wang, Jing School of Computer Science and Engineering Huizhou University Guangdong Huizhou China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China School of Arts and Design Huizhou University Guangdong Huizhou China

ISBN: (纸本)9798400707100

This paper employs a logistic regression model for feature selection and utilizes Gradient Boosting Decision Trees (GBDT) to classify economically disadvantaged students and non-disadvantaged students. By analyzing the resulting confusion matrix and evaluating metrics such as accuracy, precision, recall, and F1 score, we assess the reliability and practicality of the model in real-world applications. The study indicates that household annual income, dependency ratio, and daily expenditure are significant factors affecting a family's economic status, whereas the price of mobile phones and computers have minimal impact. The prediction results based on the GBDT model demonstrate excellent performance in identifying economically disadvantaged students, effectively reducing misclassifications, and improving the efficiency and fairness of resource allocation. © 2024 Copyright held by the owner/author(s).

关键词： Logistic regression

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：