检索结果-内蒙古大学图书馆

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Chio, KaKit Zhu, Wenhao He, Lihua Zhang, Dian Yang, Xu Luo, Wuman Macao Polytechnic University Faculty of Applied Sciences S.A.R Macao China School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Province China Shenzhen University Department of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350337020

Personalized patient representation learning (PPRL) is a critical element in clinical risk prediction. It aims to obtain a complete portrait of each patient based on Electronic Health Records (EHR). Although existing works have achieved remarkable progress in healthcare prediction, there are still three major issues. First, feature correlation is crucial for risk prediction, but it has not yet been fully exploited by existing works. Second, variation pattern of dynamic feature contains useful information about patient's physical status, but adaptive pattern recognition is still a challenge. Third, existing works usually adopt a two-stage embedding process to process each dimension of the EHR data. However, some useful low-level information for PPRL will be lost. To address these issues, in this paper, we propose a fine-grained PPRL architecture named FG RL- N et for clinical risk prediction based on EHR. Specifically, we propose a Medical Feature Correlation Detection Module (FCM) to effectively learn the feature correlations for each patient and a Temporal Variation Pattern Recognition Module (TVM) to effectively detect the variation patterns of each dynamic feature. Moreover, we design a Fine-Grained Representation Mechanism (FGRM) to preserve the low-level information (from both feature and visit dimensions) useful for risk prediction. In addition, in the stage of data preprocessing, We utilize generic medical classification knowledge to classify numerical dynamic data. We conduct the in-hospital mortality experiment and the decompensation experiment on a real-world dataset. The experiment results show that the FGRL-Net outperforms state-of-the-art approaches. The source code is provided in github https://***/JackyChio/FGRL-Net. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Alzheimer's Disease Classification Approach Using MRI Imaging

Alzheimer's Disease Classification Approach Using MRI Imagin...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Eman Khaled Farah Amr Farah Essam Maryam Nouh Youssef Sherif Zyad Yakan Ziad El Gayar Ashraf AbdelRaouf Department of Computer Engineering and Software Systems Faculty of Engineering Ain Shams University Cairo Egypt Faculty of Computer Scinece Misr International University Cairo Egypt

Alzheimer's disease (AD) is a slowly progressing, irreversible brain condition that weakens memory and negatively affects the patient's quality of life. Alzheimer's disease (AD) can be identified using Magnetic Resonance Imaging (MRI) data. For an early diagnosis of the disease, various medical and diagnostic approaches are being investigated. Even while MRI is a useful tool for locating AD-related brain symptoms, the acquisition process is time-consuming, largely because workflow bottlenecks must be manually evaluated. In order to find the best effective method for detecting the disease, this research examines the basic technique for analyzing MRI images. To carry out our study to slow progression of the disease by the use of Alzheimer's disease (AD) prognosis, a dataset from The Alzheimer's Disease Neuroimaging Initiative (ADNI) will be imported and fitted. The outcomes highlight the tremendous potential of integrating imaging data for automated categorization of Alzheimer's disease (AD) using multidisciplinary AI techniques. With a deep three-dimensional convolutional network (3D CNN) being used to handle the three-dimensional MRI input and a Transformer encoder being applied to manage the genetic sequence input, the suggested solution merges machine learning, bioinformatics, and other image processing techniques. After various experiments by checking the results accuracy, it is stated that the CNN model is never enough to provide us with the desired accuracy either by training on both skull stripped data or the GM tissue segmented data. Although, it is relatively better at the skull stripped dataset training, but the results accuracy and predicted classes show that inferring some classifiers after extracting the features from the CNN would increase the accuracy and results. After applying Support Vector Machine SVM-RBF, SVM-POLY, and XGBoost, it is concluded that the training of the Skull Stripped Dataset with features extracted from the CNN model we provided an

关键词：

来源：评论

学校读者我要写书评

暂无评论

Symbiotic Organisms Search with Deep Learning Driven Biomedical Osteosarcoma Detection and Classification

引用

computers, Materials & Continua 2023年第4期75卷 133-148页

作者： Abdullah M.Basahel Mohammad Yamin Sulafah M.Basahel Mona M.Abusurrah K.Vijaya Kumar E.Laxmi Lydia Faculty of Economics and Administration King Abdulaziz UniversityJeddahSaudi Arabia E-Commerce Department College of Administrative and Financial SciencesSaudi Electronic UniversityJeddahSaudi Arabia Department of Management Information Systems College of Business AdministrationTaibah UniversityAl-MadinahSaudi Arabia Department of Computer Science and Engineering GITAM School of TechnologyVisakhapatnam CampusGITAM(Deemed to be a University)India Department of Computer Science and Engineering GMR Institute of TechnologyAndhra PradeshRajamIndia

Osteosarcoma is one of the rare bone cancers that affect the individualsaged between 10 and 30 and it incurs high death rate. Early diagnosisof osteosarcoma is essential to improve the survivability rate and treatmentprotocols. Traditional physical examination procedure is not only a timeconsumingprocess, but it also primarily relies upon the expert’s *** this background, the recently developed Deep Learning (DL) models canbe applied to perform decision making. At the same time, hyperparameteroptimization of DL models also plays an important role in influencing overallclassification performance. The current study introduces a novel SymbioticOrganisms Search with Deep Learning-driven Osteosarcoma Detection andClassification (SOSDL-ODC) model. The presented SOSDL-ODC techniqueprimarily focuses on recognition and classification of osteosarcoma usinghistopathological images. In order to achieve this, the presented SOSDL-ODCtechnique initially applies image pre-processing approach to enhance the qualityof image. Also, MobileNetv2 model is applied to generate a suitable groupof feature vectors whereas hyperparameter tuning of MobileNetv2 modelis performed using SOS algorithm. At last, Gated Recurrent Unit (GRU)technique is applied as a classification model to determine proper class *** order to validate the enhanced osteosarcoma classification performance ofthe proposed SOSDL-ODC technique, a comprehensive comparative analysiswas conducted. The obtained outcomes confirmed the betterment of SOSDLODCapproach than the existing approaches as the former achieved a maximumaccuracy of 97.73%.

关键词： Osteosarcoma medical imaging deep learning feature vectors computer aided diagnosis image classification

来源：评论

学校读者我要写书评

暂无评论

Enhancing Stock Price Prediction: A Hybrid Approach Leveraging Large Language Models and Deep Learning

Enhancing Stock Price Prediction: A Hybrid Approach Leveragi...

引用

International Conference on computer and Applications (ICCA)

作者： Mohamed Erfan Ahmed Gamal A. Ebrahim Marwa A. Abdelaal Computer and Systems Engineering Department Faculty of Engineering Ain Shams University Cairo Egypt Computer Science Department Faculty of Computers and Information Sadat Academy for Management Sciences Cairo Egypt

ISBN: (数字)9798350367560

ISBN: (纸本)9798350367577

Accurate stock price prediction is a challenging yet crucial goal in finance, with significant implications for investment decisions and risk management. This paper presents a comprehensive review of machine learning techniques for stock price prediction, examining traditional methods such as regression and ensemble models, as well as advanced approaches that integrate sentiment analysis and textual data sources. With the emergence of powerful Large Language Models (LLMs) such as ChatGPT, Llama and Gemini, we explore their potential for enhancing predictive accuracy using historical stock data. Key challenges are discussed, including data quality, model interpretability, and adapting to dynamic market conditions. Additionally, this paper proposes a trustworthy stock price prediction model based on LLMs enabling informed investment decision-making. Experimental results demonstrate that ChatGPT-4o model achieved a prediction accuracy of approximately 97%, which can be improved by tuning model parameters. Consequently, the paper highlights the potential of LLMs in improving stock price forecasting.

关键词： Adaptation models Accuracy Biological system modeling Large language models Semantics Predictive models Data models Forecasting Tuning Investment

来源：评论

学校读者我要写书评

暂无评论

Moving from the Developer Machine to IoT Devices: An Empirical Study

Moving from the Developer Machine to IoT Devices: An Empiric...

引用

IEEE Cybersecurity Development (SecDev)

作者： Md Rabbi Alam Jinpeng Wei Md Sajidul Islam Sajid Qingyang Wang Chenglong Fu Department of Software and Information Systems University of North Carolina at Charlotte USA Department of Computer and Information Sciences Towson University USA Department of Computer Science and Engineering Louisiana State University USA

ISBN: (数字)9798350391930

ISBN: (纸本)9798350391947

With the growing prevalence of Internet of Things (IoT) devices, IoT cloud platforms have become increasingly vital in the ecosystem that allows heterogeneous IoT devices to be accessed and managed by a wide range of IoT applications. IoT applications are typically hosted on dedicated application servers within the cloud platforms and offer intelligent automation, control, and management features for all connected IoT devices. However, we found that IoT devices can be attacked if the development environment is compromised. In this paper, we conduct the first systematic study on the security risks of IoT cloud platforms that are introduced by compromised development environments. We discover three novel attacks that can invoke commands on the IoT devices, initiate malicious IoT firmware update, and get access to the IoT devices through secure tunneling. We confirm the feasibility of these attacks on mainstream commercial IoT cloud platforms, including Azure IoT Hub, AWS IoT Core, Samsung SmartThings, IBM Watson IoT, and Google IoT, demonstrating their potential to impact a large number of devices. Our work leads to the creation of CVE-2023-38372 by IBM.

关键词： Resistance Intelligent automation Cloud computing Systematics Tunneling Internet of Things Security Servers Protection Microprogramming

来源：评论

学校读者我要写书评

暂无评论

Smart Diagnostic System for Early Detection and Prediction of Polycystic Ovary Syndrome

Smart Diagnostic System for Early Detection and Prediction o...

引用

2023 International Conference on computer Communication and Informatics, ICCCI 2023

作者： Harish, K.P. Dhivyanchali, M.N. Devi, K.Nirmala Krishnamoorthy, N. Dhana Sree, R. Dharanidharan, R. Kongu Engineering College Department of Computer Science & Engineering Erode India Swamy Vivekanandha Medical College Hospital and Research Institute Elayampalayam Tamilnadu Tiruchengode637 205 India Vellore Institute of Technology Vellore Campus School of Information Technology and Engineering Department of Software Systems and Engineering Tamilnadu 632014 India

ISBN: (纸本)9798350348217

PCOS are the serious condition which affects female ovaries during their reproductive age of 15 to 45. This disease affects 5 to 10% of reproductive-age females. Although it is difficult to fully resolve this issue,the PCOS affected women can be mitigated through proper exercise, by taking proper nutritious diet and maintaining the healthy BMI. Until they take a pregnancy test, the majority of women are unaware of the disease. The clinical dataset has the 541 instances and 45 attributes of unbalanced classes of 0 and 1 (no and yes) which has 364 instances of 0 (no) class and 177 instances of 1 (yes) class. Preprocessing is done for the unbalanced dataset by filling the null values and changing the datatype of all attributes to numeric datatypes. The unbalanced dataset is balanced by the balancing techniques of SMOTE and Random Over Sampling. Comparing the both balanced techniques through the accuracy the random oversampling gives the *** supervised learning algorithms are Decision tree, KNN,Random Forest,AdaBoost, Logistic regression,Gradient boosting, cat boosting, XGBoosting, Linear SVM, Radial SVM, Linear discriminant analysis and Quadratic discriminant analysis are *** supervised learning algorithms are trained and tested by splitting the dataset to 70% for training and 30% for testing. The ensemble stacking techniques are used by implementing the all models at the cross validation of *** xgboost gives the accuracy of 96% for the balanced dataset. © 2023 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Naïve Bayes classifier assisted automated detection of cerebral microbleeds in susceptibility-weighted imaging brain images

引用

Biochemistry and Cell Biology 2023年第6期101卷 562-573页

作者： Ateeq, Tayyab Faheem, Zaid Bin Ghoneimy, Mohamed Ali, Jehad Li, Yang Baz, Abdullah Department of Computer Engineering The University of Lahore Lahore 54000 Pakistan Department of Computer Science & IT The Islamia University of Bahawalpur Punjab Bahawalpur 63100 Pakistan Faculty of Computer Science Modern Science & Arts (MSA) University Giza Egypt Department of AI Convergence Network Ajou University Suwon South Korea College of Mechanical and Electrical Engineering Shihezi University Shihezi China Department of Computer Engineering College of Computer and Information Systems Umm Al-Qura University Makkah Saudi Arabia

Cerebral microbleeds (CMBs) in the brain are the essential indicators of critical brain disorders such as dementia and ischemic stroke. Generally, CMBs are detected manually by experts, which is an exhaustive task with limited productivity. Since CMBs have complex morphological nature, manual detection is prone to errors. This paper presents a machine learning-based automated CMB detection technique in the brain susceptibility-weighted imaging (SWI) scans based on statistical feature extraction and classification. The proposed method consists of three steps: (1) removal of the skull and extraction of the brain;(2) thresholding for the extraction of initial candidates;and (3) extracting features and applying classification models such as random forest and naïve Bayes classifiers for the detection of true positive CMBs. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data that consist of 14 subjects with 104 microbleeds and testing data that consist of 6 subjects with 63 microbleeds. We were able to achieve 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB, and the naïve Bayes classifier achieved 90.5% sensitivity with 5.5 false positives per CMB. The proposed technique outperformed many state-of-the-art methods proposed in previous studies. © 2023 The Author(s).

关键词： brain bleeds cerebral microbleeds hemosiderin deposits naïve Bayes classifier random forest classifier

来源：评论

学校读者我要写书评

暂无评论

Formal Verification Based Synthesis for Behavior Trees 9th

Formal Verification Based Synthesis for Behavior Trees

引用

9th International Symposium on Dependable software engineering: Theories, Tools and Applications, SETTA 2023

作者： Hong, Weijiang Chen, Zhenbang Li, Minglong Li, Yuhan Huang, Peishan Wang, Ji College of Computer National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology Changsha China Institute for Quantum Information & State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China

ISBN: (纸本)9789819986637

Behavior trees (BTs) have been extensively applied in the area of both computer games and robotics, as the control architectures. However, the construction of BTs is labor-expensive, time-consuming, and even impossible as the complexity of task increases. In this work, we propose a formal verification based synthesis method to automatically construct BTs whose behaviors satisfy the given Linear Temporal Logic (LTL) specifications. Our method first explores candidate BTs by a grammar-based Monte Carlo Tree Search (MCTS), then the explored BTs are transformed into Communicating Sequential Processes (CSP) models. After that, we invoke the verifier to check the models’ correctness w.r.t. specifications, and provide feedback based on the verification result for guiding the search process. The application of our method on several representative robotic missions indicates its promising. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Behavior Trees CSP MCTS Synthesis

来源：评论

学校读者我要写书评

暂无评论

ThyroidNet:A Deep Learning Network for Localization and Classification of Thyroid Nodules

引用

computer Modeling in engineering & Sciences 2024年第4期139卷 361-382页

作者： Lu Chen Huaqiang Chen Zhikai Pan Sheng Xu Guangsheng Lai Shuwen Chen Shuihua Wang Xiaodong Gu Yudong Zhang Ultrasonic Department Zhongda Hospital Affiliated to Southeast UniversityNanjing210009China School of Physics and Information Engineering Jiangsu Second Normal UniversityNanjing211200China School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia State Key Laboratory of MillimeterWaves Southeast UniversityNanjing210096China Jiangsu Province Engineering Research Center of Basic Education Big Data Application Jiangsu Second Normal UniversityNanjing211200China School of Software Engineering Quanzhou Normal UniversityQuanzhou362000China Department of Biological Sciences Xi’an Jiaotong-Liverpool UniversitySuzhou215123China

Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques ***:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid ***,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask ***,we propose the DualLoss function,tailored to the thyroid nodule localization and classification *** balances the learning of the localization and classification tasks to help improve the model’s generalization ***,we introduce strategies for augmenting the ***,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid ***:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and *** results show that ThyroidNet outperformed these methods in localizing and classifying thyroid *** achieved improved accuracy of 3.9%and 1.5%,***:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis *** research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.

关键词： ThyroidNet deep learning TransUnet multitask learning medical image analysis

来源：评论

学校读者我要写书评

暂无评论

Prediction of Solar Energy Production Using Low-Cost Data Logger and ANN Algorithm 9th

Prediction of Solar Energy Production Using Low-Cost Data L...

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Raif, Mourad Ledmaoui, Younes El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada KingstonONK7K 7B4 Canada

ISBN: (纸本)9783031886522

This article introduces a novel method for predicting solar energy production using an affordable data logger and the Artificial Neural Network (ANN) algorithm. The main goal of this research is to create a precise predictive model for solar energy output, addressing the critical need for accurate forecasting in the renewable energy industry. The study capitalizes on the accessibility and cost-efficiency of a low-cost data logger to collect detailed environmental and solar irradiance data. The ANN algorithm is utilized to analyze the collected dataset, providing a robust and effective approach for forecasting solar energy production. Extensive experiments demonstrate that the developed model achieves an impressive R2 score of 0.95, indicating a high degree of accuracy and reliability in predicting solar energy output. This significant R2 score highlights the proposed methodology’s effectiveness, demonstrating its potential for practical applications in solar energy planning and management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： data logger Machine learning Photovoltaic prediction Renewable energy

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：