检索结果-内蒙古大学图书馆

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Velvizhi R Bhooma Charitha Bala Yashwitha Kasarapu Manju C Nair Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

Heart disease continues to be a global health issue, causing much morbidity and mortality in spite of the advancement in medical science. Appropriate and timely prediction is crucial for successful clinical intervention, but conventional diagnostic measures are deficient in efficiency and accuracy to enable early-stage detection. Over the last few years, machine learning (ML) has been a high-powered tool used to predict heart disease by analyzing intricate patterns across various healthcare data sets like ECG signals and demographic data. Yet, most current ML-based systems are dependent on centralized repositories of data, which poses legitimate concerns about data privacy, security, and conformance to compliance with regulatory protocols like HIP AA and GDPR. This review looks at the state of heart disease prediction in the context of machine learning and decentralized data exchange technologies. We look at how techniques like federated learning and blockchain are being used in predictive health systems in order to overcome privacy and security constraints of the centralized approaches. The literature reports promising methods that allow collaborative training of models without sharing raw patient data, thus ensuring patient confidentiality while still enjoying high predictive accuracy. In addition, blockchain technology is emphasized to playa crucial role in ensuring data integrity, secure access management, and open auditing.

关键词： Heart Training Data privacy Accuracy Federated learning Reviews Medical services Blockchains Security Diseases

来源：评论

学校读者我要写书评

暂无评论

LANGUAGE MODELS ARE IMPLICITLY CONTINUOUS

arXiv

引用

arXiv 2025年

作者： Marro, Samuele Evangelista, Davide Huang, X. Angelo La Malfa, Emanuele Lombardi, Michele Wooldridge, Michael Department of Engineering Science University of Oxford Oxford United Kingdom Department of Computer Science University of Bologna Bologna Italy Department of Computer Science ETH Zurich Zurich Switzerland Department of Computer Science University of Oxford Oxford United Kingdom

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based language models implicitly learn to represent sentences as continuous-time functions defined over a continuous input space. This phenomenon occurs in most state-of-the-art Large Language Models (LLMs), including Llama2, Llama3, Phi3, Gemma, Gemma2, and Mistral, and suggests that LLMs reason about language in ways that fundamentally differ from humans. Our work formally extends Transformers to capture the nuances of time and space continuity in both input and output space. Our results challenge the traditional interpretation of how LLMs understand language, with several linguistic and engineering implications. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative study of cardiovascular disease detection using machine learning techniques with an extended dataset

A comparative study of cardiovascular disease detection usin...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Abdul Aziz Mohammad Rifat Ahmed Argho Deb Das Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Heart disease, also referred to as cardiovascular disease (CVD), is a broad category of illnesses that obstruct the coronary arteries, impairing the cardiovascular system’s ability to operate normally. They are in charge of blood circulation, oxygen delivery, and the delivery of vital nutrients to various bodily areas. Heart disease claims the lives of over 17.9 million people worldwide each year, or about 31% of all deaths. The alarmingly high death toll from cardiovascular disease worldwide highlights the urgent need for thorough study and creative remedies. The current research uses various cutting-edge techniques in a multi-modal manner to address the detection of cardiovascular disease in response to this pressing need. A variety of machine learning models, such as random forests, decision trees, Naïve Bayes, k-nearest neighbors (KNN), and neural networks, were employed in conjunction with a voting ensemble technique to attain an accuracy of 89.2%. Therefore, in order to lessen the severe effects of cardiovascular disease, this study offers an improved strategy. Its adoption offers better individual health results and more effective control of the societal and financial challenges associated with cardiovascular disease.

关键词： Heart Neural networks Pressing Nearest neighbor methods Nutrients Bayes methods Cardiovascular diseases Decision trees Random forests Blood

来源：评论

学校读者我要写书评

暂无评论

A Temporal Self-Attention Guided Deep Learning Approach for Prognosis of Remaining Useful Life of Aircraft Turbofan Engines

A Temporal Self-Attention Guided Deep Learning Approach for ...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Arupa Barua Ashim Dey Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

In the aviation industry, a reliable prognosis of the remaining useful life (RUL) of aircraft engines is a prerequisite for effective predictive maintenance as well as averting critical failures. But the high non-linearity of engine components and operation in complex environments make it more challenging to capture the deterioration behavior and estimate the RUL. To deal with this concern, a deep learning ensemble model with a Temporal Self-Attention Mechanism (TSAM) is presented to estimate the RUL of aircraft turbofan engines effectively. Firstly, the importance of different sensors is evaluated by applying the TSAM method to the raw sensor data. Then Temporal Convolutional Network (TCN) is applied to the weighted sensor data to extract high-dimensional features. Next, a Bi-directional LSTM network is used to acquire the long-term dependencies in the time series. To further improve the performance we used the Bayesian Optimization strategy to optimize the best hyperparameters. Finally, the efficiency of the proposed TSAM-TCN-Bi-LSTM model is verified using the Commercial Modular Aero Propulsion System Simulation (C-MAPSS) dataset obtained by NASA and evaluated against other existing methods. The study demonstrates that the presented ensemble model can prominently yield better results than other approaches for estimating the remaining useful life of aircraft turbofan engines.

关键词： Atmospheric modeling Computational modeling Predictive models Sensor phenomena and characterization Bayes methods Aircraft propulsion Aircraft Prognostics and health management Engines Optimization

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap in Bangla Healthcare: Machine Learning Based Disease Prediction Using a Symptoms-Disease Dataset

Bridging the Gap in Bangla Healthcare: Machine Learning Base...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Rowzatul Zannat Abdullah Al Shafi Abdul Muntakim Department of Computer Science and Engineering Khulna University of Engineering & Technology Khulna Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Increased access to reliable health information is essential for non-English-speaking populations, yet resources in Bangla for disease prediction remain limited. This study addresses this gap by developing a comprehensive Bangla symptoms-disease dataset containing 758 unique symptom-disease relationships spanning 85 diseases. The dataset enables the prediction of diseases based on Bangla symptom inputs, supporting healthcare accessibility for Bengali-speaking populations. Using this dataset, we evaluated multiple machine learning models to predict diseases based on symptoms provided in Bangla and analyzed their performance on our dataset. Both soft and hard voting ensemble approaches combining top-performing models achieved 98% accuracy, demonstrating superior robustness and generalization. Our work establishes a foundational resource for disease prediction in Bangla, paving the way for future advancements in localized health informatics and diagnostic tools. This contribution aims to enhance equitable access to health information for Bangla-speaking communities, particularly for early disease detection and healthcare interventions.

关键词： Surveys Machine learning algorithms Computational modeling Medical services Predictive models Prediction algorithms Robustness Medical diagnostic imaging Random forests Diseases

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Anomaly Detection in Energy Consumption Data: Assessing the Vulnerability to Adversarial Attacks

arXiv

引用

arXiv 2025年

作者： Telila, Yohannis Kifle Senevirathne, Damitha Tissera, Dumindu Narayan, Apurva Capretz, Miriam A.M. Grolinger, Katarina Department of Electrical and Computer Engineering Western University LondonON Canada Department of Computer Science Western University LondonON Canada

Anomaly detection is crucial in the energy sector to identify irregular patterns indicating equipment failures, energy theft, or other issues. Machine learning techniques for anomaly detection have achieved great success, but are typically centralized, involving sharing local data with a central server which raises privacy and security concerns. Federated Learning (FL) has been gaining popularity as it enables distributed learning without sharing local data. However, FL depends on neural networks, which are vulnerable to adversarial attacks that manipulate data, leading models to make erroneous predictions. While adversarial attacks have been explored in the image domain, they remain largely unexplored in time series problems, especially in the energy domain. Moreover, the effect of adversarial attacks in the FL setting is also mostly unknown. This paper assesses the vulnerability of FL-based anomaly detection in energy data to adversarial attacks. Specifically, two state-of-the-art models, Long Short Term Memory (LSTM) and Transformers, are used to detect anomalies in an FL setting, and two white-box attack methods, Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), are employed to perturb the data. The results show that FL is more sensitive to PGD attacks than to FGSM attacks, attributed to PGD’s iterative nature, resulting in an accuracy drop of over 10% even with naive, weaker attacks. Moreover, FL is more affected by these attacks than centralized learning, highlighting the need for defense mechanisms in *** Codes 68 Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing SMS Spam Detection with Large Language Models and Transformer Architectures

Optimizing SMS Spam Detection with Large Language Models and...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Md. Nazir Ahmed A. S. M. Shakil Ahamed Fahim Shakil Tamim Department of Computer Science & Engineering IUBAT—International University of Business Agriculture and Technology Dhaka Bangladesh Department of Computer Science & Engineering Islamic University of Technology Gazipur Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

In recent years, the Short Message Service (SMS) has become omnipresent, with most people ignoring emails while nearly all check their daily text messages. These messages may contain spam, providing useless promotions or links that could lead to the installation of malicious applications into the system. Spam detection involves identifying minute linguistic signs and patterns in text messages, with detecting disguised spam presenting a significant challenge due to the continuous evolution of techniques. It aims to develop an intelligent system for classifying messages into two different classes, namely Spam or Ham from English SMS spam messages. In order to do so, this study explores different fine-tuned machine learning (Logistic Regression-LR, Multinomial Naive Bayes-MNB, Support Vector Machine-SVM) models, deep learn- ing(Convolutional Neural Network-CNN, Bidirectional Long Short-Term Memory-BiLSTM, CNN+BiLSTM) models, transformer(M-BERT, BERT base , XLM-R base , XLNet base ) techniques and two large language models(Phi-3 and H2O-Danube). Finally, we experimented with two large language models, Phi-3 and H2O-Danube. Out of all the models we tested, H2O-Danube outperformed all other models with a macro F1-score of 0.94, proving to be the best for SMS spam detection, surpassing traditional machine learning, transformer, and LLM models.

关键词： Large language models Transfer learning Text categorization Linguistics Message services Transformers Reliability engineering Vectors Intelligent systems Logistics

来源：评论

学校读者我要写书评

暂无评论

A Secure Telemedicine Scheme Based on Distributed Database, Machine Learning and Iot for Diagnosis of Diabetes Disease

SSRN

引用

SSRN 2025年

作者： Ahmad, Md. Kawsar Abir, Md. Ashikuzzaman Akter, Farzana Hasan, Tanveer Shaha, Pabon Hossain, Muhammad Minoar Iqbal, Md. Sadiq Department of Computer Science and Engineering Bangladesh University Dhaka Dhaka1207 Bangladesh Department of Computer Science and Engineering Mawlana Bhashani Science and Technology University Santosh Tangail1902 Bangladesh

Diabetes is one of the leading causes of morbidity and mortality in the world;thus, its early diagnosis is the hallmark of prevention. In these modern times, at a time when healthcare systems head towards digitization, secure management and timely sharing of health data have become highly crucial in telemedicine. This paper proposes a secure telemedicine framework using IoT, machine learning algorithms and a distributed database system to enhance the identification, tracking, and treatment of diabetes. The proposed architecture will use advanced data encryption and authentication protocols to ensure security, confidentiality, and integrity of patient data. The proposed system will have higher accuracy and efficiency compared to the traditional approaches by monitoring through IoT devices in real time and early diagnosis through machine learning. Moreover, the automatic nature of the system eliminates physical barriers, hence making it very convenient, cost-effective, and time-effective for the patients to detect diabetes. The results will be shared securely with authenticated users, thus ensuring privacy while overcoming geographical barriers. The findings of this study confirm that strong health data protection is must essential in this digital era. It also visualized how telemedicine has completely revolutionized the process of distribution for healthcare by improving security and efficiency. The proposed scheme not only ensure the confidentiality and integrity of patient’s data by addressing the issues the conventional approaches but also enables the path for more scalable and effective healthcare solution. © 2025, The Authors. All rights reserved.

关键词： Distributed database systems

来源：评论

学校读者我要写书评

暂无评论

Drillboards: Adaptive Visualization Dashboards for Dynamic Personalization of Visualization Experiences

引用

IEEE Transactions on Visualization and computer Graphics 2025年 PP卷 PP页

作者： Shin, Sungbok Na, Inyoup Elmqvist, Niklas Inria-Saclay and Universite Paris-Saclay Saclay France Department of Computer Science and Engineering Korea University Seoul Korea Republic of Department of Computer Science Aarhus University Aarhus Denmark

We present drillboards, a technique for adaptive visualization dashboards consisting of a hierarchy of coordinated charts that the user can drill down to reach a desired level of detail depending on their expertise, interest, and desired effort. This functionality allows different users to personalize the same dashboard to their specific needs and expertise. The technique is based on a formal vocabulary of chart representations and rules for merging multiple charts of different types and data into single composite representations. The drillboard hierarchy is created by iteratively applying these rules starting from a baseline dashboard, with each consecutive operation yielding a new dashboard with fewer charts and progressively more abstract and simplified views. We also present an authoring tool for building drillboards and show how it can be applied to an agricultural dataset with hundreds of expert users. Our evaluation asked three domain experts to author drillboards for their own datasets, which we then showed to casual end-users with favorable outcomes. © 2025 IEEE.

关键词： Drills

来源：评论

学校读者我要写书评

暂无评论

Monitoring of Fire-Affected Buildings and Air-Quality Assessment: A Remote-Sensing Study Using Ground-Based interferometric Radar and Google-Earth-Engine

引用

Rangeland Ecology and Management 2025年 101卷 28-42页

作者： Zhang, Hao Zheng, Xiangtian Ghaffar, Bushra Quddoos, Abdul Naz, Iram Aslam, Rana Waqar Fatima, Zoia Abdullah-Al-Wadud, M. Zulqarnain, Rana Muhammad China Academy of Safety Science and Technology Beijing 100012 China Nanjing Institute of Technology School of Computer Engineering Nanjing 211167 China Department of Environmental Science Faculty of Sciences International Islamic University Islamabad 44000 Pakistan State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing (LIESMARS) Wuhan University Wuhan 430079 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia Department of Mathematics Saveetha School of Engineering SIMATS Thandalam Tamilnadu Chennai - 602105 India

This study investigates the environmental and structural impacts of crop and rangeland residue burning in Punjab during April and May 2023, utilizing ground-based interferometric radar alongside atmospheric and land use datasets. The radar system was employed to monitor structural deformations in buildings affected by fire, providing critical insights into the broader impacts of the fires on infrastructure. Multiple ground-based interferometric radars for distributed monitoring can effectively obtain the three-dimensional deformation components of structural targets in real fire scenes. The monitoring results conform to the displacement variation law of existing portal steel frame structures during fire deformation, and can provide effective data support for building structure collapse warning under fire. This approach offers a novel method for assessing the structural integrity of buildings during and after fire events, complementing traditional environmental monitoring. Environmental data show a marked increase in atmospheric pollutants such as NO₂, CH₄, and CO in May 2023, directly linked to the residue burning. Active fire data from FIRMS and MODIS revealed a 98% increase in fire events compared to April, while land surface temperature analysis showed a rise of 1.54%, with affected areas reaching up to 45.9°C. LULC analysis indicated a 23.3% decrease in cropland and rangeland areas, reflecting extensive land clearing. These findings highlight the urgent need for sustainable agricultural management and policies to mitigate the environmental and infrastructural damage caused by residue burning in Punjab. © 2025 The Society for Range Management

关键词： Agriculture Fire & Air Quality Distributed monitoring Google Earth Engine Ground-based interferometric radar Sentinel-2

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：