检索结果-内蒙古大学图书馆

Using Computational Models to Detect Autistic Tendencies for Children from their Story Book Narratives

Multimedia Tools and applications 2025年第6期84卷 3175-3196页

作者： Sun, Ruihan Wong, Jasin Chen, Eva E. Chen, Arbee L. P. Department of Computer Science National Tsing Hua University Hsinchu Taiwan Department of Special Education National Tsing Hua University Hsinchu Taiwan College of Education National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering Asia University Taichung Japan

Diagnosing autism spectrum disorder (ASD) conventionally demands significant time and resources. Language deficits are key markers of ASD, particularly in constructing narratives. This study leverages computational models to analyze story book narratives from seven children with ASD and 16 typically-developing (TD) peers. By transcribing and training models on limited data using augmentation techniques, our best model achieved over 90% accuracy, sensitivity, and specificity-outperforming previous models by 20% in ASD detection. This research showcases the efficacy of our approach in efficiently assessing language abilities and identifying ASD tendencies. The method holds promise for enhancing diagnostic efficiency and providing comprehensive language evaluations to support children with ASD and their caregivers. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Diagnosis Of Cardio Vascular Diseases Using Retinal Fundus Scans Via Deep Learning

Diagnosis Of Cardio Vascular Diseases Using Retinal Fundus S...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Pryadarshne, D. Madireddy, Sai Ruthvik Vaishnnave, M.P. Paul, Mercy Sathyabama Institute Of Science And Technology Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350371567

Cardiovascular disease (CVD) remains a leading global health concern, necessitating early and accurate detection methods for effective intervention. This study presents a groundbreaking approach to CVD detection leveraging deep learning techniques applied to retinal fundus scans. Retinal fundus scans offer a non-invasive, cost-effective, and easily accessible source of information for potential CVD risk assessment. The utilization of deep learning algorithms, such as Convolution Neural Networks (CNNs), has demonstrated remarkable promise in identifying subtle pathological changes within the retinal vasculature and optic nerve. This study reviews the current state of research on CVD risk prediction and highlights the potential of retinal fundus scans as a valuable diagnostic tool. The integration of deep learning methods facilitates the automatic extraction of intricate features from retinal images, enabling the development of accurate and efficient CVD detection models. By examining retinal vasculature, microaneurysms, hemorrhages, and other relevant features, these models can aid in early risk stratification and timely intervention. Furthermore, this study delves into the challenges and future prospects of this novel approach, emphasizing the importance of large, diverse datasets, model interpretability, and the integration of clinical data to enhance predictive accuracy. As the field of deep learning continues to advance, this innovative strategy has the potential to revolutionize cardiovascular disease detection, enabling proactive healthcare measures and ultimately improving patient outcomes. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Classification of Malicious Financial applications Using Naive Bayes and K-Nearest Neighbor Algorithms Based on Android Permission 3

Classification of Malicious Financial Applications Using Nai...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Akter, Mst.Liya Moon, Iffath Tanjim Akter, Md Akash Shafa, Zhakia Tabessum Pundra University of Science & Technology Department of Computer Science & Engineering Bogura Bangladesh

ISBN: (纸本)9798350388282

In this research paper, we have worked on some of the vulnerabilities of multiple Android apps and we have explored the vulnerability of financial apps and how these apps are acting as threats in our daily lives. Nowadays in this digital technology, mobile banking is a common way for people to make transactions, through which many people have to face financial loss. we have identified the vulnerability of Financial Apps by performing permission analysis to protect the privacy, security, and financial security of these customers. Our main contribution is to find out the vulnerabilities of Android apps by permission analysis to create high-quality datasets using static analysis and learning the dataset through the K-Nearest Neighbor algorithm and Naive Bayes algorithm to show whether it is malicious or not by using the 'Permission Dataset' and the 'Appdroid' dataset. To test the developed model, we have extracted 1438 combined attributes from these two datasets and took 12050 applications samples. According to the test findings, the Naive Bayes model can improve detection by roughly 82.07% For further testing it was 88.25% that the KNN model has the highest accuracy and efficiency. Our main objective is to identify multiple Financials app vulnerabilities and create a comprehensive dataset by permission analysis and by using a machine learning model, as a result, we have been able to determine the Financial Apps vulnerability and safeguard these financial security, privacy, and safety. © 2024 IEEE.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning and Explainable AI for Brain Tumor Classification: A Study Using MRI Data from Bangladesh 6

Transfer Learning and Explainable AI for Brain Tumor Classif...

引用

6th International Conference on Sustainable Technologies for Industry 5.0, STI 2024

作者： Sarker, Shuvashis Ahsanullah University of Science and Technology Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (数字)9798331531973

ISBN: (纸本)9798331531973

Brain tumors, regardless of being benign or ma-lignant, pose considerable health risks, with malignant tumors being more perilous due to their swift and uncontrolled prolifer-ation, resulting in malignancy. Timely identification is crucial for enhancing patient outcomes, particularly in nations such as Bangladesh, where healthcare infrastructure is constrained. Manual MRI analysis is arduous and susceptible to inaccuracies, rendering it inefficient for prompt diagnosis. This research sought to tackle these problems by creating an automated brain tumor classification system utilizing MRI data obtained from many hospitals in Bangladesh. Advanced deep learning models, including VGGI6, VGGI9, and ResNet50, were utilized to classify glioma, meningioma, and various brain cancers. Explainable AI (XAI) methodologies, such as Grad-CAM and Grad-CAM++, were employed to improve model interpretability by emphasizing the critical areas in MRI scans that influenced the categorization. VGG16 achieved the most accuracy, attaining 99.17%. The integration of XAI enhanced the system's transparency and stability, rendering it more appropriate for clinical application in resource-limited environments such as Bangladesh. This study highlights the capability of deep learning models, in conjunction with explainable artificial intelligence (XAI), to enhance brain tumor detection and identification in areas with restricted access to advanced medical technologies. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

An Integrated Secure Rail System For Accident Prevention and Anti-Hijacking Measures

An Integrated Secure Rail System For Accident Prevention and...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Pradeep, Ganesula Kiran, Samineni Uday Sathyadurga, V. Hindustan Institute Of Technology & Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

India has one of the world's longest rail systems, covering an amazing distance. However, Indian railways fall short of international norms in terms of dependability and passenger safety. In order to solve this, an improved interface solution this paper has been started to improve railway safety and prevent collisions. This method uses Arduino microcontrollers in conjunction with fingerprint sensor modules. In order to maintain safe and controlled train operations, trains fitted with these specialised fingerprint devices won't start their engines until after authenticating the fingerprints of authorised users. And also the system recognises when two trains are about to collide on the same track when fingerprint modules are activated simultaneously. The GSM module quickly sends the latitude and longitude coordinates to a specified web site after detecting something. The position and seriousness of the collision risk may be quickly determined thanks to this data interchange, which is essential for further processing and analysis. In addition, the apparatus features an LCD screen that offers instantaneous visual notifications to users on potential collision scenarios. By enabling proactive steps for collision prevention and easy connection with external monitoring systems, this novel solution strengthens overall railway safety rules. It makes use of web-based connectivity and cutting-edge sensor technology to do this. © 2024 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Adaptive & Fine-Grained Domain Adaptation for Pavement Crack Segmentation using YOLOv8 Learning Framework

Adaptive & Fine-Grained Domain Adaptation for Pavement Crack...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Reddy, Devarapalli Abhilash Kumar, Kolli Sathish Rajendran, P. Selvi Hindustan Institute Of Technology And Science Department Of Computer Science &engineering Chennai India

ISBN: (纸本)9798350364828

In this study, the utilization of Roboflow's YOLOv8 architecture for crack segmentation is explored, focusing on evaluating the model's performance and readiness for real- world deployment. The methodology involves key steps such as data collection, pre processing, model training, evaluation, and deployment. Initially, a diverse dataset of images containing various types and severity of cracks is curated and annotated. The dataset undergoes pre processing to enhance image quality and standardize input dimensions for optimal training performance. Subsequently, the YOLOv8 architecture is employed for model training due to its efficiency in realtime object detection tasks and effectiveness in handling small objects like cracks. To evaluate the trained model, metrics such as precision, recall, F1score, and mean Intersection over Union (mIoU) are computed on a separate validation dataset to assess the model's ability to accurately segment cracks while minimizing false positives and false negatives. © 2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Quantum Encrypted Messaging Application: Harnessing Quantum Mechanics for Secure Communication 2

Quantum Encrypted Messaging Application: Harnessing Quantum ...

引用

2nd IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2024

作者： Gabriela Sharon, R. Kumar, Aswin Sanil Mayan, Albert Catharine, A. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372847

This research aims to develop a quantum encrypted messaging application that uses the principles of quantum mechanics to provide secure and privacy communication between users This project focuses on using quantum encryption techniques to improve messaging application security. The application will incorporate post-quantum algorithms to establish secure communication channels, ensuring that messages exchanged between users are protected from eavesdropping and unauthorized access Messaging application exit results will provide users with greater security and a quantum-resistant platform for private transactions -Will address the emerging need for quantum-secure encryption in this era of threats © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Core Tumor Prediction and Feature Segmentation by using Weber's Law in Brain Images 8

Core Tumor Prediction and Feature Segmentation by using Webe...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Punitha, M. Kumar, M. Sathish Mangayarkarasi College of Arts and Science for Women Department of Computer Science and Applications Madurai Tamilnadu Paravai India Tamilnadu Madurai India

ISBN: (纸本)9798350376425

The presented paper proposes a feature to extract the exact core tumor portions from brain images using modified weber's law. Generally, Weber's Law is mostly used to identify the background and fore ground of an image, that knowledge encourages us to implement Weber law in MRI images for core tumor detection. Usually, tumors are in high gray level in T2-weighted and FLAIR Magnetic resonance imaging (MRI) scan images. Tumors are complex structure which contains different types of tissues called substructures. The physicians diagnose the tumor stage and surgical plan based on the substructures. Hence, the proposed work focuses to locate the substructure. Subsequently, the proposed method modifies the parameters used in Weber's law corresponding to the tumor appearance in MRI images. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Detection of Traffic Violation and Vechicle Number Plate Using computer Vision 2

Detection of Traffic Violation and Vechicle Number Plate Usi...

引用

2nd IEEE International Conference on IoT, Communication and Automation Technology, ICICAT 2024

作者： Jeevan Abishek, H. Balavinodhan, R. Rajalakshmi, R. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368109

A novel approach for detecting numberplate for violation identification is introduced in this research. The main objective of this research is to create the intelligent system for vehicle detection and number plate identification. For the purpose of identifying automobiles that are present inside the video frames, the system makes use of cutting-edge object identification algorithms and SORT (Simple online real-time tracking). When objects are correctly identified, the system is able to study their behaviour and determine whether or not they follow to traffic regulations. During the categorization phase, it is determined whether or not a vehicle has done anything that is against the rules of traffic signals, such as running a red light. For the purpose of training and fine-tuning the deep learning models, the project makes use of a comprehensive dataset consisting of labelled traffic situations. This allows for the research to achieve robust performance. Another thing that we have done is teach a specialized model to recognize red, yellow, and green lights as well as pedestrian crossings. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Efficacy of Text Summarization Models: A Comparison of NLP Algorithms 8

Evaluating the Efficacy of Text Summarization Models: A Comp...

引用

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Chakraborti, Rounak Banerjee, Romit Das, Soma Institute of Engineering and Management University of Engineering and Management Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798331520762

Text Summarization is a critical tool nowadays. People do not have enough time to read big articles which take a lot of time. A short summary is no doubt an enthralling option for this case. As this demand increases numerous algorithms and methods have come up which can serve this purpose. This survey paper encompasses the different algorithms and methods used by different researchers which includes methods like TF-IDF and LSA alongside neural networks like Seq2Seq, Pegasus, and Transformer-based models like BART and T5. We analyze these on metrics like ROUGE scores. This survey paper will provide a valuable resource for researchers in the future who want to study text summarization in the news domain. © 2025 IEEE.

关键词： BART Latent Semantic Analysis (LSA) News Summarization Pegasus ROUGE Score Seq2Seq T5 Text Summarization TF-IDF Transformer Models

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

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

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：