检索结果-内蒙古大学图书馆

6th International Workshop on Health Recommender Systems, HealthRecSys 2024

作者： Neehal, Nafis Anand, Vibha Bennett, Kristin P. Department of Computer Science Rensselaer Polytechnic Institute TroyNY12180 United States Biomedical AI-Healthcare and Life Sciences IBM T.J. Watson Research Center CambridgeMA02141 United States Institute of Data Exploration and Applications Mathematical Sciences and Computer Science Departments Rensselaer Polytechnic Institute TroyNY12180 United States

Incorporating real-world data (RWD) into clinical trials can enhance trial efficiency, diversity, and generalizability. This paper introduces the Framework for Research in Synthetic Control Arms (FRESCA), which uses a novel Recommender System combined with Equity Adjustment strategies to design and evaluate Representative Hybrid Clinical Trials (HCTs). FRESCA employs a novel matching algorithm through its recommendation system to select suitable patients from RWD while ensuring that the selected population is representative of the target demographic. This dual approach improves both patient selection and trial outcomes by balancing statistical appropriateness and equity. Simulations based on data from two existing randomized clinical trials (RCTs) show that using FRESCA to recommend patients from RWD and apply equity adjustments enhances internal validity and generalizability. Our analysis indicates that combining matching and equity adjustments yields more accurate treatment effect estimates and fair population representation, even with reduced RCT control group sizes. In contrast, using either method alone may result in biased outcomes. The flexibility of FRESCA to simulate various HCT scenarios makes it a valuable tool for advancing equitable and efficient clinical trial designs. © 2024 Copyright for this paper by its authors.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Image-Based Distance Estimation of a Target from a Camera using Color Checker Chart 2

Image-Based Distance Estimation of a Target from a Camera us...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Kamath, Vedavyasa Kurian, Ciji Pearl Shailesh, K.R. Suprabha Padiyar, U. Sontakke, Mangalam Manipal Institute of Technology Manipal Academy of Higher Education Dept. of Electrical and Electronics Engg. Karnataka Manipal India Manipal Institute of Technology Manipal Academy of Higher Education Dept. of Data Science and Computer Applications Karnataka Manipal India

ISBN: (纸本)9798350306415

In recent years, photography-based photometry has gained popularity and is being implemented widely. Under this approach, a camera is used as a sensor to estimate photometric quantities like illuminance or luminance. The absolute distance between the target surface and the camera can be crucial for photometric analysis. The technique proposed in this article employs a fixed focal length lens mounted on a DSLR camera. The standardised classic ColorChecker chart is placed over the target surface, and the scene image with the chart is captured. The intuition is that the average pixel area of the swatches present on the chart decreases as the camera is moved away from the chart. OpenCV libraries are used to calculate the average pixel area of the chart color swatches. Distance is measured using an industry-standard laser-based distance measurement tool. Curve fitting is used to establish a mathematical relationship between camera-chart distance and the average pixel area of the swatches. Distance varies from 650 cm to 2 m during the data collection process. The influence of the tilt of the chart plane with respect to the camera sensor plane is also studied. During testing, the proposed power trendline-based mathematical model performed with an error percentage of less than 1. This approach for distance measurement enables finer tuning of the machine learning-based model and, as a result, more accurate illuminance estimation for the work plane. © 2024 IEEE.

关键词： computer vision Curve fitting Distance measurement Image analysis Image edge detection Photometry

来源：评论

学校读者我要写书评

暂无评论

Pattern Recognition Based Skin Lesion Stage Analysis Using IoT

引用

SN computer science 2024年第5期5卷 1-15页

作者： Kollu, Venkatagurunatham Naidu Sharma, Girish Kumar Kautish, Sandeep Manikandan, R. Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Computer Science and Applications Bhai Parmanand DSEU Shakarpur Campus-II Shakarpur Delhi 110092 India Dean-Academics COER University Roorkee India Professor & amp School of Computing SASTRA Deemed University Thanjavur India

Skin diseases are considered the emerging cause of high mortality throughout the world. To reduce the rate of death, that arise due to skin is minimized with early detection and cure. The lesions in the skin need to be evaluated significantly to increase the detection rate in the early stage. Nowadayscomputer-Aided Diagnosis (CAD) is considered as the effective technique to detect lesions in the skin with the use of pattern recognition technique. Through CAD system skin lesions are classified into different classes. In other hand, medical environment uses the Internet of Things (IoT) for the monitoring and detection of diseases in patients. Hence, this paper constructed a framework of Dragon Pattern Optimization Stacked Classifier (DPOSC) automated model for the early detection of skin lesions. The DPOSC automated model is interconnected with the IoT devices implanted in the patient body for the classification of lesions as malignant, benign and normal in the early stage. The DPOSC model perform the image pre-processing with PCA (Principal component analysis) followed by the segmentation. The pattern recognition approach is developed with estimation of the features in the skin images. The technique uses quantitative analysis with the coding process to extract the pattern in the skin lesion and utilized for the automated detection system. The modifier dragon optimization model is implemented for the extraction and optimization of features in the skin lesion images. Upon the extracted features classification is performed with the stacked classification model. The DPOSC model effectively detect the lesions in the skin images and linked with the IoT environment for the detection of skin cancer in the early diagnosis. The developed automated integrated with IoT is emerging innovative technique for the detection of cancer in early stages. The accuracy of the improved DPOSCis 0.5% superior to SVM and NN, 2.4% more improved than GA-NN, PSO-NN and DA-NN. The precision of the

关键词： Classification Dragon optimization Features Internet of Things (IoT) Pattern recognition Skin lesions

来源：评论

学校读者我要写书评

暂无评论

Enhanced Framework for MRI Brain Tumor Recognition with Residual Learning and Intuitive Heatmap Visualization

Enhanced Framework for MRI Brain Tumor Recognition with Resi...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Velmurugan, L. Maheswari, R.K. Janani, K. Agalya, K. Poornima, M. Gayathri, K.C. Vit Bhopal University Bhopal-Indore Highway Kothrikalan Madhya Pradesh Sehore India M.A.M College of Enginnering and Technology Artificial Intelligence and Data Science Tamilnadu Trichy India Manipal institute of Technology Manipal Academy of Higher Education Department of Data science and computer applications Manipal India Sri Eshwar College of Engineering Department of Computer Science Engineering Coimbatore India Oasys Institute of Technology Department of Information Technology Tamil Nadu Trichy India Kelambakkam Chennai India

ISBN: (纸本)9798331543617

Early detection of brain tumors is crucial for effective treatment, yet it poses a significant challenge due to the rapid nature of the disease's progression. This study explores the application of ResNet, aimed at improving the accuracy of brain tumor diagnosis in magnetic resonance imaging (MRI) scans. Our model was trained on a dataset comprising 253 MRI images, which included 155 confirmed cases of tumors. The residual learning framework of ResNet effectively captures intricate features and mitigates issues such as vanishing gradients. The results indicate that the ResNet model achieved an impressive accuracy rate of 97%, surpassing traditional detection methods. We evaluated the model's performance using metrics like accuracy and F1-score, demonstrating its robustness. To improve the interpretability of our model's predictions, we utilized Grad-CAM (Gradient-weighted Class Activation Mapping), which highlighted critical areas in the MRI scans that influenced the model's decisions. Our findings confirm ResNet' s effectiveness in medical imaging and stress the importance of model interpretability in healthcare, allowing radiologists to make informed diagnostic choices. © 2024 IEEE.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

Disguise Face Classification Using EfficientNet Deep Learning 1st

Disguise Face Classification Using EfficientNet Deep Learnin...

引用

1st International Conference on Human-Centric Smart Computing, ICHCSC 2022

作者： Padmashree, G. Wagle, Shruti G. Karunakar, A.K. Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9789811954023

With the rise in popularity of social media and intelligent gadgets, one essential biometrics for identifying people is their face. The efficiency of existing automatic face recognition systems has decreased due to factors such as face ageing, conceals, and pose variations. Face recognition algorithms must be more accurate for recognizing faces hidden behind masks and makeup, as security and surveillance requirements become more stringent. Disguise face classification acts as a standalone early warning system in such scenarios. The major goal of this research was to see how the EfficientNet family of models compares to the current state-of-the-art architecture in terms of disguise face classification. For disguise face classification, the EfficientNet deep learning architecture was proposed in this paper. The models were trained and tested using the Disguise Faces in Wild (DFW) 2018 data set. The transfer learning method was used to train EfficientNet and other deep learning models. Results obtained proved that EfficientNet-B3 has outperformed other EfficientNet architectures with 92.2% precision and 93.9% accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Image To Text Description Platform For Yakshagana Images By Detecting Crown Using CNN

Image To Text Description Platform For Yakshagana Images By ...

引用

2025 International Conference on Artificial Intelligence and data Engineering, AIDE 2025

作者： Kiranraj, M. Murthy, Anantha Manish Prathwini, Prathwini Savitha, G. Harshitha, G.M. NMAM Institute of Technology Department of Master of Computer Applications Karnataka Nitte574110 India NMAM Institute of Technology Department of Master of Computer Applications Karkala Nitte India Manipal Academy of Higher Education Manipal Institute of Technology Department of Data Science and Computer Applications Manipal India

ISBN: (纸本)9798331527518

This research called "Yakshakatha - Image to Text Platform for Yakshagana Images."It employs deep learning to classify crowns in Yakshagana Kirita using CNN classification. Yakshagana is a traditional South Indian art form, well known for its intricate costumes and headgear, posing specific challenges in identifying and classifying crowns. The system aims to classify various Kirita styles and provide detailed descriptions of the respective Yakshagana characters, or Vesha, offering valuable cultural and symbolic insights. The model was trained on a self-labelled dataset of Yakshagana images and used convolutional and pooling layers to capture fine details in crown designs. It achieved an impressive accuracy of 99%, ensuring precise identification and classification. Real-time predictions for the input images are made, which have predetermined mappings and description content for recognized characters. The system employs Google Gemini AI, in order to enrich the text description of the image by integrating cultural background. The responsive interface is provided for users on the image upload, real-time result, and enriched visual feedback using annotated output. This project combines modern image recognition with rich cultural content to preserve and promote the traditional heritage of Yakshagana. It will help the users to understand and appreciate the vibrancy of this art form. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CLEANSURVIVAL: AUTOMATED data PREPROCESSING FOR TIME-TO-EVENT MODELS USING REINFORCEMENT LEARNING

arXiv

引用

arXiv 2025年

作者： Koka, Yousef Selby, David Großmann, Gerrit Vollmer, Sebastian Media Engineering Technology Faculty German University in Cairo Cairo Egypt Data Science and its Applications DFKI GmbH Kaiserslautern67663 Germany Data Science and its Applications DFKI GmbH Department of Computer Science University of Kaiserslautern–Landau Kaiserslautern 67663 Kaiserslautern67663 Germany

data preprocessing is a critical yet frequently neglected aspect of machine learning, often paid little attention despite its potentially significant impact on model performance. While automated machine learning pipelines are starting to recognize and integrate data preprocessing into their solutions for classification and regression tasks, this integration is lacking for more specialized tasks like survival or time-to-event models. As a result, survival analysis not only faces the general challenges of data preprocessing but also suffers from the lack of tailored, automated solutions in this area. To address this gap, this paper presents CleanSurvival, a reinforcement-learning-based solution for optimizing preprocessing pipelines, extended specifically for survival analysis. The framework can handle continuous and categorical variables, using Q-learning to select which combination of data imputation, outlier detection and feature extraction techniques achieves optimal performance for a Cox, random forest, neural network or user-supplied time-to-event model. The package is available on GitHub: https://***/datasciapps/CleanSurvival. Experimental benchmarks on real-world datasets show that the Q-learning-based data preprocessing results in superior predictive performance to standard approaches, finding such a model up to 10 times faster than undirected random grid search. Furthermore, a simulation study demonstrates the effectiveness in different types and levels of missingness and noise in the data. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Tensor MIMO Perfect-Equalizer Design Using New Projection-Based Method and Approximation-Error Analysis

引用

IEEE Systems Journal 2024年第1期18卷 668-679页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Kao, Yi-Chih San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Chungli32003 Taiwan National Yang Ming Chiao Tung University Network and System Division Information Technology Service Center Hsinchu30010 Taiwan

As real environments are quite complex, multiple-input-multiple-output (MIMO) channels should be characterized by the multidimensional-multirelational models. Tensor linear algebra has been emerging as a powerful and promising tool for such MIMO channel modeling and estimation. However, to the best of our knowledge, there hardly exists any algebraic framework of MIMO channel equalization when the channel is modeled as an arbitrary-dimensional transfer tensor (a tensor whose entries are all rational z-functions). In this work, we first propose a new method based on the projection, namely, 'projection-based method,' to determine whether a given transfer tensor is a full-rank tensor or not and carry out the inversion of an invertible transfer tensor. Our idea is employing the projection subspace of the system transfer tensor to simplify the pertinent inversion process. Second, we design the finite-impulse-response (FIR) realization to approximate the inverse of an arbitrary transfer tensor such that all entries of the approximated inverse transfer tensor are finite-degree polynomials of z. Third, we also analyze the computational and memory complexities required by our proposed new projection-based method for checking the full-rank condition of a given transfer tensor and for undertaking the tensor inversion. Our developed new theories and analysis in this work can be applied to determine the FIR model-orders of an approximated inverse MIMO transfer tensor often encountered in signal processing, control, communications, etc. © 2007-2012 IEEE.

关键词： FIR filters

来源：评论

学校读者我要写书评

暂无评论

An AI-driven Approach for Tailoring Java Programming Instructions

An AI-driven Approach for Tailoring Java Programming Instruc...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Gomathi Thiyagarajan Vijayalakshmi V Department of Computer Applications CMR Institute of Technology Bengaluru Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Tamil Nadu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

AI and virtual assistants are transforming higher education by using digital tools to enhance teaching and learning in ways that go beyond traditional methods. These digital tools are not merely supplementary aids but are increasingly gaining popularity in educationalsetting offering innovative approaches that transcend conventional methods. In this research we introduce ByteBuddy a virtual assistant which assists instructors on Java instructions. ByteBuddy's framework is designed in a way to integrate easily into educational context. This study reveals the architecture of ByteBuddy, the process model that captured the behavior of students in the learning environment and the observation of its application in java instructions. By applying this study, we provide profound insights on how the effective use of ByteBuddy supplements the teaching practices and measure learning outcomes.

关键词： Java Virtual assistants Education Encoding Internet of Things data communication Artificial intelligence Programming profession

来源：评论

学校读者我要写书评

暂无评论

Patterns of Widespread Structural Abnormalities in Autism Spectrum Disorder using Diffusion Tensor Imaging

Patterns of Widespread Structural Abnormalities in Autism Sp...

引用

Communication, computer sciences and Engineering (IC3SE), International Conference on

作者： Dilip Kumar Bharti Sanjay Kumar Singh Mukesh Kumar Vishal Kumar Kanaujia Manisha Aeri Computer Science and Engineering-Data Science ABES Engineering College Ghaziabad India Department of Computer Science & Applications Kashi Institute of Technology Varanasi U.P India Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand Data Science Department Computer Science and Engineering ABES Engineering College Ghaziabad INIDA

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

Diffusion tensor imaging (DTI) is a neuroimaging approach that lets in for the visualization and quantification of the structural integrity of white depend fibers in the brain. In latest years, DTI has come to be an essential tool for investigating the underlying neurobiological mechanisms of autism spectrum sickness (ASD), a neurodevelopmental disorder characterized via problems in social communication and repetitive behaviors. Through the usage of DTI, researchers have identified good sized styles of structural abnormalities in the brains of individuals with ASD. these abnormalities encompass changes in the microstructure of white remember fibers, along with decreased fiber density, changes in fiber directionality, and decreased connectivity between mind areas. Additionally, there may be evidence of bizarre mind development in early formative years, with a few research finding that these structural variations are present even in very younger children with ASD. One constant finding in DTI studies of ASD is reduced white rely integrity inside the corpus callosum, a large fiber package deal that connects the two hemispheres of the mind. This abnormality has been connected to deficits in social communiqué and language in people with ASD, as well as difficulties in integrating records from distinctive brain areas. The results showed extensive structural abnormalities in people with ASD in comparison to TD individuals.

关键词： Neuroimaging Optical fiber sensors Autism Visualization Variable speed drives Optical fiber networks Motors

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：