检索结果-内蒙古大学图书馆

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Shanto, Salauddin Haque, Nazmul Department of Computer Science & Engineering Rajshahi University of Engineering & Technology Rajshahi6204 Bangladesh

ISBN: (纸本)9798331508227

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder that affects memory, thinking, and behavior, gradually leading to mild to severe dementia. Over the past decade, researchers have leveraged deep learning models, such as Convolutional Neural Networks (CNN) and transfer learning, for the early detection and classification of AD. In this paper, we propose a simple and computationally cost-effective CNN architecture for the early diagnosis and classification of AD. The model was trained using ADNI T1-weighted 2D MRI scans, encompassing cognitively normal (CN) individuals, stable mild cognitive impairment (sMCI) cases, and Alzheimer’s dementia (AD) patients. Experimental results demonstrate the superiority of our model, achieving an accuracy of 98.97%, thereby surpassing most previous studies while utilizing a low-cost custom CNN architecture. ©2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CUET_Binary_Hackers@DravidianLangTech EACL2024: Fake News Detection in Malayalam Language Leveraging Fine-tuned MuRIL BERT 4

CUET_Binary_Hackers@DravidianLangTech EACL2024: Fake News De...

引用

4th Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, DravidianLangTech 2024

作者： Farsi, Salman Eusha, Asrarul Hoque Islam, Ariful Taher, Hasan Mesbaul Ali Hossain, Jawad Ahsan, Shawly Das, Avishek Hoque, Mohammed Moshiul Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chattogram4349 Bangladesh

ISBN: (纸本)9798891760783

Due to technological advancements, various methods have emerged for disseminating news to the masses. The pervasive reach of news, however, has given rise to a significant concern: the proliferation of fake news. In response to this challenge, a shared task in DravidianLangTech EACL2024 was initiated to detect fake news and classify its types in the Malayalam language. The shared task consisted of two sub-tasks. Task 1 focused on a binary classification problem, determining whether a piece of news is fake or not. Whereas task 2 delved into a multi-class classification problem, categorizing news into five distinct levels. Our approach involved the exploration of various machine learning (RF, SVM, XGBoost, Ensemble), deep learning (BiLSTM, CNN), and transformer-based models (MuRIL, Indic-SBERT, m-BERT, XLM-R, Distil-BERT) by emphasizing parameter tuning to enhance overall model performance. As a result, we introduce a fine-tuned MuRIL model that leverages parameter tuning, achieving notable success with an F1-score of 0.86 in task 1 and 0.5191 in task 2. This successful implementation led to our system securing the 3rd position in task 1 and the 1st position in task 2. The source code will be found in the GitHub repository at this link: https://***/Salman1804102/ DravidianLangTech-EACL-2024-FakeNews. © 2024 Association for Computational Linguistics.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Statistical approaches to assess the performance of domestic air-to-water heat pumps

引用

International Journal of Ambient Energy 2023年第1期44卷 1316-1328页

作者： Tangwe, Stephen Kusakana, Kanzumba Department of Electrical Electronic and Computer Engineering Central University of Technology Bloemfontein South Africa

Air-to-water heat pump (AWHP) is a renewable and efficient technology used in sanitary water heating. This study focused on the employment of statistical methods to compare the coefficient of performance (COP) and electrical energies consumed using 1.2 kW, 150 L split type AWHP and 0.9 kW, 150 L integrated type AWHP, with 0.5 kW as auxiliary electric heater. The COPs and the electrical energies consumed were determined from the controlled volumes of hot water drawn from each tank at different use periods. The average month-day COPs of the specific volumes of hot water from either system were above two. The p-values from the one-way ANOVA (analysis of variance) and the Kruskal–Wallis tests of the groups’ COPs were smaller than 0.01 and showed significant differences at 99% confidence level. The study can assist energy service companies and researchers, to test for statistical differences in the performance among different AWHPs. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Analysis of variance (ANOVA)

来源：评论

学校读者我要写书评

暂无评论

Cryptonite: A Framework for Flexible Time-Series Secure Aggregation with Non-interactive Fault Recovery

引用

SN computer Science 2025年第3期6卷 1-18页

作者： Karl, Ryan Koirala, Nirajan Januszewicz, Tasha Takeshita, Jonathan Jung, Taeho Department of Computer Science and Engineering University of Notre Dame Notre Dame IN United States

In many real-world applications, an untrusted aggregator (server) is required to collect privacy-sensitive data from the users (clients) to compute aggregate statistics on that data periodically. In Private Stream Aggregation (PSA), multiple data producers encrypt their data for a central party, which can then retrieve only the aggregate sum of the encrypted values, without access to any individual values. PSA enables untrusted aggregators to execute aggregation operations over privacy-critical data from multiple data sources. Traditionally, existing PSA schemes require the aggregator to interact with a trusted third party to achieve fault tolerance. However, this kind of interactive recovery poses many security and practical vulnerabilities to achieve fault tolerance in real-world applications. This paper introduces a new formal PSA framework that ensures rigorous privacy guarantees for individual user inputs and achieves fault tolerance with non-interactive recovery. Existing definitions for fault tolerance do not account for the impact of faults on security and cannot defend against residual function attacks. We define a new level of security for a non-interactive fault tolerance model with malicious adversaries that guarantees defense for such attacks during fault recovery. We present the first PSA protocol that provably achieves this new level of security. Our techniques are versatile and can be used to enhance any existing PSA scheme to safely recover from faults in a non-interactive manner. We employ our proposed framework and use trusted hardware, cryptographic hashing, and p-ary trees to develop a protocol that achieves significant improvements in scalability and communication efficiency. Our proposed protocol is about 3× faster than existing PSA protocols for cases when faults do not occur. During cases when faults occur, our protocol provides faster execution by about 1–2 orders of magnitude compared to existing works. © The Author(s) 2025.

关键词： Fault tolerance Secure aggregation Trusted hardware

来源：评论

学校读者我要写书评

暂无评论

White Blood Cell Segmentation Using DeepLabv3+ for Improved Hematological Disease Detection

White Blood Cell Segmentation Using DeepLabv3+ for Improved ...

引用

2023 IEEE Region 10 Symposium, TENSYMP 2023

作者： Joshi, Vivek C. Mehta, Mayuri A. Gujarat Technological University Department of Computer/IT Engineering Ahmedabad India Sarvajanik College of Engineering and Technology Department of Computer Engineering Surat India

ISBN: (纸本)9781665482585

The morphological analysis of the White Blood Cell (WBC) plays a crucial role in disease diagnosis using medical image analysis, particularly in treating haematological disorders like leukemia, lymphoma, anemia, and sickle cell disease. Clinical medical image analysis is manual and susceptible to subjectivity and human error. Therefore, deep learning-based methods are used to segment WBCs from microscopic blood smear images. This paper introduces a new DeepLabv3+-based WBC segmentation approach. The performance of the proposed approach is evaluated using the science bowl challenge dataset. The dataset is augmented using traditional techniques such as centre cropping, rotation, grid distortion, horizontal flipping, and vertical flipping. The performance of the proposed approach is measured using the parameters such as dice coefficient, Intersection of Union (IoU), precision, and recall. The results are compared with the results of traditional U-Net-based WBC segmentation. The experimental results show that training loss, training dice coefficient, validation dice coefficient, training IoU, validation IoU, precision and recall of the proposed approach are increased by 23.78%, 2.32%, 0.43%, 4.29%, 0.78%, 0.96%, 1.01%, respectively compared to U-Net-based WBC segmentation. Thus, DeepLabv3+-based WBC segmentation outperforms U-Net-based WBC segmentation. © 2023 IEEE.

关键词： Blood

来源：评论

学校读者我要写书评

暂无评论

Investigation Emotion Dynamics in Bangla Social Media Text for Improved Emotion Detection

Investigation Emotion Dynamics in Bangla Social Media Text f...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Ahmed, Mostak Sobhan, Abdus Hossen Sajib, Md. Sahadat Masud, Nasrullah Green University of Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh Varendra University Department of Computer Science and Engineering Rajshahi Bangladesh Varendra University Department of Electrical and Electronic Engineering Rajshahi Bangladesh

ISBN: (纸本)9798331529765

Recognizing emotion from text is fundamental to machine learning and influences our understanding of human interaction. While English sentiment analysis has been well-researched, Bengali (Bangla) is still under-researched. Our study bridges this gap by investigating the emotional dynamics in Bengali social media posts using extensive user-generated content. We use a modified dataset defined by seven emotions: Happy, Surprise, Fearful, Angry, Neutral, Disgust, and Sad. Using machine learning techniques such as support vector classifiers, decision trees, logistic regression, and random forest, we found that the Random Forest model achieved the highest accuracy of 84%. This study advances our understanding of Bengali emotional expression and demonstrates its application in social media sentiment analysis, psychoanalysis, and communication technologies. By addressing the complexities of Bengali language and culture, our work contributes to a broader definition of emotion and lays the foundation for future research in different contexts. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Performance of Sentiment Analysis using Enhanced Preprocessing Technique with Agriculture Review Score Calculation

Enhancing the Performance of Sentiment Analysis using Enhanc...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Hubert, Arokiaraj Christian St Madhusudanan, J. Department of Computer Science and Engineering Sri Manakula Vinayagar Engineering College Puducherry India

ISBN: (纸本)9798350374933

The discipline of natural language processing is now placing the highest level of research focus on sentiment analysis. Nevertheless, despite its significant capabilities, the use of this technology remains limited in the agricultural industry. The objective of this research is to analyse the online review characteristics, review length, and review sentiment score across different food products. Furthermore, the analysis examines the differences in customer sentiment ratings based on the length of the reviews. This study proposes an enhanced preprocess method, which can adjust the selection and weighting of features or attributes of the parsed tree structures dynamically, based on the specific context or target sentiment being analyzed. This technique aims to improve the accuracy and relevance of sentiment analysis by tailoring the feature selection process to better capture the sentiment expression in different contexts. Furthermore, it uses the Valence Aware Dictionary and Sentiment Reasoner (VADER) lexicon-based categorisation approach to assess consumer sentiment across many domains. The approach entails creating a specialised vocabulary for the agricultural domain using the VADER lexicon. The reviews are then classified using this dictionary. The variations in sentiment ratings across the different farm evaluations provide a thorough feedback to the companies. Additionally, it conveys a brand's assessment by customers and provides performance feedback for expanding into other areas. By evaluating various reviews, the VADER Lexicon classifier with Treebank dynamic filtering (VADER_TDF) method achieves 98% of accuracy, 93% of precision, 91% of recall and 90% of F1-score. © 2024 IEEE.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Advancing Sentiment Understanding in social media through Dynamic Contextual Embedding 3

Advancing Sentiment Understanding in social media through Dy...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Yadav, Aditi Chaudhary, Anu Gupta, Avdhesh Ajay Kumar Garg Engineering College Department of Computer Science & Engineering Ghaziabad India

ISBN: (纸本)9798350381931

In the current landscape of social media communication, believing sentiment expression is crucial for diverse applications, including brand management and public opinion analysis. The study explores ways to improvise sentiment analysis, in media by using contextual embeddings. It places its emphasis on well-settled models such as BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pre-trained Transformer). By tackling the force of these dynamic inserting, the study looks to beat the impediments of conventional feeling examination strategies in catching the nuanced and context-dependent nature of language prevalent in social media disclosure. Through a comprehensive examination of existing literature and recent developments, the paper systematically evaluates the impact of dynamic contextual embedding, emphasizing prominent models such as BERT and GPT. The main goal is to provide an in-depth overview of how these techniques have subsidized to the enhancement of sentiment analysis in the ever-evolving landscape of social media platforms. The research involves a comprehensive investigation into the fine-tuning and pre-training of these models on social media datasets. This paper provides an outline based on previous studies in the field of understanding sentiments in social media posts using algorithms like BERT and GPT. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

The Modern Approaches for Identifying Foreign Object Debris (FOD) in Aviation 2

The Modern Approaches for Identifying Foreign Object Debris ...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Ashmi, G.V. Priyadharsini, R. Sri Sivasubramaniya Nadar College of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350317558

In recent days, the Federal Aviation Administration (FAA) put forward various technologies to detect the Foreign Object Debris (FOD). The FAA's proactive approach to addressing FOD issues underscores the commitment to maintaining high safety standards in aviation operations. Foreign Object Debris (FOD) is rising as a common risk factor in the aviation industry which damages aircraft and external FODs such as bird strikes, sand storms, and foggy clouds on their runways and radar. The internal FOD is associated with flight safety which includes sorting out electrical connections, control cables, and so on. Moreover, the rise of air traffic results in the landing and takeoff of planes in a frequent manner. So, their runways should be well maintained and cleaned to make them free from the presence of foreign objects, but it is very complex to identify them through visual inspection. So, this paper particulate the effectiveness of automated detection techniques which ensure safety, and efficiency, and reduce the risks associated with foreign object debris. © 2024 IEEE.

关键词： Federal Aviation Administration Foreign Object Debris radar runways

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Phishing Website Detection 18

Machine Learning based Phishing Website Detection

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Kawale, Manav Maru, Bhavik Dagu, Sakshi Varghese, Maya Gupta, Vikas Vidyavardhini's College of Engineering & Technology Department of Computer Science and Engineering Mumbai India

ISBN: (纸本)9789380544519

Phishing websites are those where a person can imitate a legitimate website and trick an innocent user into thinking he is visiting a legitimate website while stealing sensitive information. Statistics from the Anti-Phishing Website Group (APWG) show that in the second quarter of 2023, 1,286,208 phishing attacks were recorded. This was the APWG's third-highest quarterly total ever. To address this issue, a Phishing website detection system was made that automatically detects and notifies the user of any phishing website. The system will be based on supervised learning wherein machine learning models such as k-nearest Neighbors, Logistic Regression, Support Vector Classifier, Naive Bayes, Decision Tree, and Random Forest are selected for training. Random Forest was found to have the highest accuracy among them. As a result, Randomforest was chosen with an accuracy of 96.7 and a combination of 32 features, among which features like status bar customizing, website forwarding, stats report, pop windows, server form handler were uniquely identified and implemented to the proposed system to improve the overall accuracy of the model. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning technique Phishing phishing feature extraction Random Forest

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：