检索结果-内蒙古大学图书馆

Practical Evaluation of Human-Computer Interaction and Artificial Intelligence deep learning algorithm in Innovation and Entrepreneurship Teaching Evaluation

引用

INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION 2025年第3期41卷 1742-1750页

作者： Wang, Dongxuan Han, Lu Cong, Lin Zhu, Hongwei Liu, Yu Hebei Agr Univ Coll Sci & Technol Huanghua Hebei Peoples R China Hebei Agr Univ Coll Econ & Management Baoding 071000 Hebei Peoples R China Hebei Agr Univ Coll Humanities & Social Sci Baoding Hebei Peoples R China Hebei Finance Univ Coll Financial Technol Baoding Hebei Peoples R China

The rise of knowledge economy has drawn much attention to Innovation and Entrepreneurship Education (IEE). IEE is conducive to helping graduates relieve employment pressure, and also to cultivating students' innovation ability and entrepreneurial willingness, which is also of great significance for promoting high-quality quantitative and sustainable development of social economy. However, the current IEE still has some limitations, such as the students' insufficient entrepreneurial willingness, low innovation practice ability, and unreasonable evaluation methods of innovation and entrepreneurship teaching, which hinder the further development of IEE. Therefore, for the purpose of further promoting the development of IEE, this article studied the evaluation of innovation and entrepreneurship teaching, and proposed an innovation and entrepreneurship teaching evaluation system combining Human-Computer Interaction (HCI) and deep learning (DL). The evaluation system was used to evaluate the innovation and entrepreneurship teaching of Class A and Class B. The evaluation result showed that Class A's innovation and entrepreneurship teaching evaluation score was 7;Class B's innovation and entrepreneurship teaching evaluation score was 7.1. The evaluation of innovation and entrepreneurship teaching in Class A and Class B was still not high enough, and the teaching quality and effect still needed to be improved;the innovation and entrepreneurship teaching evaluation system combined with HCI and DL had strong operability.

关键词： Innovation and entrepreneurship education deep learning algorithm human-computer interaction teaching quality evaluation teaching effect evaluation

来源：评论

学校读者我要写书评

暂无评论

Prediction of high-temperature mechanical properties of filled rubber based on the deep learning algorithm

引用

POLYMER COMPOSITES 2025年第6期46卷 5453-5462页

作者： Wang, Junpu Zuo, Yanjiang Yue, Xiaozhuang Wang, Yuxuan Di, Liupeng Li, Minghui Shaanxi Univ Sci & Technol Coll Mech & Elect Engn Xian Peoples R China

Filled rubber has wide applications in industries due to its high temperature and corrosion resistance. Therefore, it is crucial to accurately depict the high-temperature mechanical behavior of the filled rubber. With the expansion of machine learning, the deep learning (DL) algorithm provides a new method to investigate the stress-strain relation of filled rubber. In this paper, the carbon nanotube-filled fluororubber was used as an example to train various DL models, such as convolutional neural network (CNN), long short-term memory (LSTM) network, and CNN-LSTM hybrid models. These models were trained using test data at relatively lower temperatures to predict the relation between stress and strain at higher temperatures. Comparing the test results, it was found that all the predicted results closely matched the experimental data. However, the CNN-LSTM hybrid model exhibited the lowest error and the most stable calculation process. The results indicated that the DL model not only reduces the time and resources needed to develop new constitutive relationships for filled rubber but also offers greater advantages in predicting the high-temperature mechanical properties of filled *** DL models predict the high-temperature mechanical behavior of filled rubber. Higher temperature results got by extrapolation from lower temperature data. More test data at various temperatures improve the prediction accuracy. The prediction accuracy at 200 degrees C surpasses at 220 degrees C. CNN-LSTM model has the highest calculation efficiency and accuracy.

关键词： deep learning algorithm filled rubber high temperature mechanical properties neural network

来源：评论

学校读者我要写书评

暂无评论

Application of medical thermal radiation image diagnosis based on deep learning algorithm in the adjustment of type 2 diabetes exercise prescription

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2025年 59卷

作者： Zhang, Nan Xi, Maolong Wuxi Inst Technol Sch Control Engn Wuxi 214121 Peoples R China

The traditional exercise prescription adjustment mainly relies on the doctors experience judgment and the patients subjective feeling, and lacks objective quantitative evaluation tools. The purpose of this study was to explore the application potential of medical thermal radiation image diagnosis technology based on deep learning algorithm in exercise prescription adjustment of type 2 diabetes patients. The study collected medical thermal radiation image data of patients with type 2 diabetes. These images were obtained by high-precision thermal imaging equipment, which can reflect the thermal radiation distribution of patients under different exercise loads. A set of image analysis algorithms based on deep learning was then developed. By training deep convolutional neural networks, the algorithm was able to identify and analyze key thermal radiation patterns in the images and correlate them with patients motor responses and blood glucose control effects. On the training set, the algorithm optimizes the model parameters through iterative learning, while on the test set, the diagnostic performance of the model is evaluated. The research also compares the accuracy, sensitivity and specificity of diagnosis between deep learning algorithm and traditional image analysis method. The results show that the deep learning-based medical thermal radiation image diagnosis method has significant application value in the adjustment of exercise prescription in type 2 diabetes patients. The algorithm was able to accurately identify the thermal radiation patterns associated with the exercise response and predict the patients glycemic control effect. Compared with traditional methods, deep learning algorithm has significantly improved diagnostic accuracy, sensitivity and specificity. This shows that deep learning algorithms have obvious advantages in processing complex medical image data.

关键词： deep learning algorithm Medical heat radiation Image diagnosis Type 2 diabetes Exercise prescription

来源：评论

学校读者我要写书评

暂无评论

Evaluating the reproducibility of a deep learning algorithm for the prediction of retinal age

引用

GEROSCIENCE 2025年第2期47卷 2541-2554页

作者： Zoellin, Jay Rodney Toby Turgut, Ferhat Chen, Ruiye Saad, Amr Giesser, Samuel D. Sommer, Chiara Guignard, Viviane Ihle, Jonas Mono, Marie-Louise Becker, Matthias D. Zhu, Zhuoting Somfai, Gabor Mark Stadtspital Triemli Stadtspital Zurich Triemli Dept Ophthalmol Birmensdorferstr 497 CH-8063 Zurich Switzerland Spross Res Inst Zurich Switzerland Royal Victorian Eye & Ear Hosp Ctr Eye Res Australia Melbourne Australia Stadtspital Triemli Stadtspital Zurich Triemli Dept Neurol Zurich Switzerland Heidelberg Univ Dept Ophthalmol Heidelberg Germany Semmelweis Univ Dept Ophthalmol Budapest Hungary Gutblick Res Pfaffikon Switzerland

Recently, a deep learning algorithm (DLA) has been developed to predict the chronological age from retinal images. The Retinal Age Gap (RAG), a deviation between predicted age from retinal images (Retinal Age, RA) and chronological age, correlates with mortality and age-related diseases. This study evaluated the reliability and accuracy of RA predictions and analyzed various factors that may influence them. We analyzed two groups of participants: Intravisit and Intervisit, both imaged by color fundus photography. RA was predicted using an established algorithm. The Intervisit group comprised 26 subjects, imaged in two sessions. The Intravisit group had 41 subjects, of whom each eye was photographed twice in one session. The mean absolute test-retest difference in predicted RA was 2.39 years for Intervisit and 2.13 years for Intravisit, with the latter showing higher prediction variability. The chronological age was predicted accurately from fundus photographs. Subsetting image pairs based on differential image quality reduced test-retest discrepancies by up to 50%, but mean image quality was not correlated with retest outcomes. Marked diurnal oscillations in RA predictions were observed, with a significant overestimation in the afternoon compared to the morning in the Intravisit cohort. The order of image acquisition across imaging sessions did not influence RA prediction and subjective age perception did not predict RAG. Inter-eye consistency exceeded 3 years. Our study is the first to explore the reliability of RA predictions. Consistent image quality enhances retest outcomes. The observed diurnal variations in RA predictions highlight the need for standardized imaging protocols, but RAG could soon be a reliable metric in clinical investigations.

关键词： Retinal age gap deep learning algorithm Retinal imaging

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of a deep learning algorithm to Differentiate Between Membranes Attached to the Optic Disc on Ultrasonography

引用

CLINICAL OPHTHALMOLOGY 2025年 19卷 939-947页

作者： Bhatt, Vaidehi D. Shah, Nikhil Bhatt, deepak C. Dabir, Supriya Sheth, Jay Berendschot, Tos T. J. M. Erckens, Roel J. Webers, Carroll A. B. UBM Inst Mumbai 400019 India Stevens Inst Technol Comp Sci Jersey City NJ USA Rajan Eye Care Pvt Ltd Dept Retina Chennai India Shantilal Shanghvi Eye Inst Mumbai India Univ Eye Clin Maastricht Maastricht Netherlands

Purpose: The purpose of this study was to create and test a deep learning algorithm that could identify and distinguish between membranes attached to optic disc [OD;retinal detachment (RD)/posterior vitreous detachment (PVD)] based on ocular ultrasonography (USG). Patients and Methods: We obtained a database of B-scan ultrasonography from a high-volume imaging center. A transformer-based Vision Transformer (ViT) model was employed, pre-trained on ImageNet21K, to classify ultrasound B-scan images into healthy, RD, and PVD. Images were pre-processed using Hugging Face's AutoImage Processor for standardization. Labels were mapped to numerical values, and the dataset was split into training and validation (505 samples), and testing (212 samples) subsets to evaluate model performance. Alternate methods, such as ensemble strategies and object detection pipelines, were explored but showed limited improvement in classification accuracy. Results: The AI model demonstrated high classification performance, achieving an accuracy of 98.21% for PVD, 97.22% for RD, and 95.83% for normal cases. Sensitivity was 98.21% for PVD, 96.55% for RD, and 92.86% for normal cases, while specificity reached 95.16%, 100%, and 95.42%, respectively. Despite the overall strong performance, some misclassification occurred, with seven instances of RD being incorrectly labeled as PVD. Conclusion: We developed a transformer-based deep learning algorithm for ocular ultrasonography that accurately identifies membranes attached to the optic disc, distinguishing between RD (97.22% accuracy) and PVD (98.21% accuracy). Despite seven misclassifications, our model demonstrates robust performance and enhances diagnostic efficiency in high-volume imaging settings, thereby facilitating timely referrals and ultimately improving patient outcomes in urgent care scenarios. Overall, this promising innovation shows potential for clinical adoption.

关键词： retinal detachment posterior vitreous detachment ultrasonography artificial intelligence deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Self-Trained Robust Adaptive Network Communication (STRANC) Optimization Model Based on deep learning algorithm

Self-Trained Robust Adaptive Network Communication (STRANC) ...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Lang, Weiwei Beijing Information Technology College Department of Electronic Information Beijing100070 China

ISBN: (纸本)9798331509828

With the advent of the information age and the continuous development and application of network communications, some nodes or links may be overloaded in high-frequency and high-concurrency network communications, resulting in increased latency, increased packet loss, and other problems. To face with this challenge, this study proposes the novel self-trained robust adaptive network communication optimization model based on the deep learning algorithm. The proposed model is a 3-step approach, and the first step is link communication quality detection model. In order to effectively detect the communication quality of network links, a deep learning algorithm is introduced to establish the network link communication model. Then, network communication error data repair optimization is studied. This model improves the output stability and environmental adaptability of the network communication by adaptively repairing and estimating communication error data. Finally, dynamic network communication resource allocation optimization is proposed. Communication Resource Allocation (CRA) optimization is studied from the perspective of the communication load adaptive balancing. Experiments show that compared with traditional neural network and FCM models, the proposed model has an improved repair accuracy of about 15%. At the same time, the proposed model can effectively reduce communication delay in a test environment with 500 nodes and 200 communication links. © 2025 IEEE.

关键词： Adaptive Network Communication deep learning algorithm Optimization Model Self-trained Model

来源：评论

学校读者我要写书评

暂无评论

deep learning algorithm for breast masses classification in mammograms

引用

IET IMAGE PROCESSING 2020年第12期14卷 2860-2868页

作者： Gnanasekaran, Vaira Suganthi Joypaul, Sutha Meenakshi Sundaram, Parvathy Chairman, Durga Devi Sethu Inst Technol Kariapatti Tamil Nadu India AAA Coll Engn & Technol Sivakasi Tamil Nadu India Madurai Med Coll Madurai Tamil Nadu India

A mammogram is an image of a breast used to detect and diagnose breast cancer. This paper emphases a Computer-Aided Detection system based on convolutional neural network (CNN) that uses the concept of deep learning to classify the mammogram images into benign, malignant and normal. The proposed CNN model consists of eight convolutional, four max-pooling and two fully connected layers and achieved better results compared to the pre-trained nets, AlexNet and VGG16. The proposed model demonstrates the feasibility of using CNNs on medical image processing techniques for the classification of breast masses. The results are also compared with the state-of-the-art machine learning algorithm like kNN classifier. Experimentation is done with three datasets. Among them, two are publicly available, Mammographic Image Analysis Society (MIAS), digital database for screening mammography (DDSM) and an internally collected dataset. The proposed model achieved accuracies of 92.54, 96.47 and 95 and the Area under the ROC curve (AUC) score of 0.85, 0.96 and 0.94 for MIAS, DDSM and the internally collected dataset respectively. Furthermore, the images of the three datasets are merged to build one large set and used to fine tune the proposed CNN model and produced accuracy of 98.32 and AUC of 0.98.

关键词： mammography neural nets image classification cancer learning (artificial intelligence) medical image processing max-pooling fully connected layers pre-trained nets medical image processing techniques kNN classifier Mammographic Image Analysis Society internally collected dataset CNN model deep learning algorithm breast masses classification breast cancer Computer-Aided Detection system convolutional neural network mammogram images automatic classification

来源：评论

学校读者我要写书评

暂无评论

deep learning algorithm for Minimum Constraint Removal (MCR) Problem 2020

Deep Learning Algorithm for Minimum Constraint Removal (MCR)...

引用

12th International Conference on Machine learning and Computing (ICMLC)

作者： Xu, Bo Chen, Liangwei Xu, Kewen Guangdong Univ Finance & Econ Sch Informat Sci Guangzhou 510320 Guangdong Peoples R China

ISBN: (纸本)9781450376426

This paper investigated the path planning problem and the feasibility of a deep learning algorithm to search a solution. In this paper, the structural model and mathematical model of the robotic path problem were constructed, and a radial basis function (RBF) neural network, which is based on the deep learning algorithm, was proposed. This algorithm extends three sets of neural networks in the direction of deep learning;the deep learning process was progressively advanced using a "reachable" network, a "least barrier" network, and a "shortest path" network. The proposed deep learning algorithm was experimentally compared with the ACO algorithm. The results indicated that the proposed algorithm can plan a path with fewer barriers and shorter distances and is suitable for solving path planning problems.

关键词： Minimum constraint removal minimum constraint set path planning deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of intelligent recommendation system based on deep learning algorithm in university library talent training

引用

SOFT COMPUTING 2023年 1-11页

作者： Liu, Dongmei Changchun Normal Univ Changchun 130041 Jilin Peoples R China

Intelligent recommendation system can greatly save users' time and energy by asking for relevant information and providing powerful guidance and help to users. deep learning algorithm has become the most popular research direction in the past decade due to its powerful expression ability, whether it is the ability to fit data patterns or the ability to mine data feature combinations. This paper takes the university library as the main research data. The data come from the original data of a university library for five years, including the collection of book information, the reader information of borrowing books, the book-borrowing records, and the book-related information with research, and experimental data are selected. At the same time, in order to alleviate the start-up problem of new users, college library, as a new form of traditional library, combined with the resources of traditional library, analyzes the role of college library in college talent training in the intelligent recommendation system of college library, thinks about the driving force of college library service innovation, and discusses some measures of library service innovation under the background of talent training. Through the study of the existing book recommendation system, the shortcomings of the existing recommendation service are found, and a new service architecture of the recommendation system is proposed. The artificial intelligence recommendation algorithm is applied to achieve the purpose of intelligent book recommendation and provide the best service for teachers and students.

关键词： deep learning algorithm Intelligent recommendation system University library Personnel training

来源：评论

学校读者我要写书评

暂无评论

Power System Resiliency and Wide Area Control Employing deep learning algorithm

引用

Computers, Materials & Continua 2021年第7期68卷 553-567页

作者： Pandia Rajan Jeyaraj Aravind Chellachi Kathiresan Siva Prakash Asokan Edward Rajan Samuel Nadar Hegazy Rezk Thanikanti Sudhakar Babu Mepco Schlenk Engineering College(Autonomous) SivakasiTamil NaduIndia College of Engineering at Wadi Addawaser Prince Sattam Bin Abdulaziz UniversityWadi Addawaser11991Saudi Arabia Department of Electrical Engineering Faculty of EngineeringMinia UniversityMinia61517Egypt Department of Electrical and Electronics Engineering Chaitanya Bharathi Institute of TechnologyHyderabad500075India

The power transfer capability of the smart transmission gridconnected networks needs to be reduced by inter-area *** to the fact that inter-area modes of oscillations detain and make instability of power transmission *** fact is more noticeable in smart grid-connected *** smart grid infrastructure has more renewable energy resources installed for its *** overcome this problem,a deep learning widearea controller is proposed for real-time parameter control and smart power grid resilience on oscillations inter-area *** proposed deep Wide Area Controller(DWAC)uses the deep Belief Network(DBN).The network weights are updated based on real-time data from Phasor measurement *** assessment based on failure probability,financial impact,and time-series data in grid failure management determine the norm *** demonstrate the effectiveness of the proposed framework,a time-domain simulation case study based on the IEEE-39 bus system was *** a one-channel attack on the test system,the resiliency index increased to 0.962,and inter-area dampingξwas reduced to *** obtained results validate the proposed deep learning algorithm’s efficiency on damping inter-area and local oscillation on the 2-channel attack as *** also offer robust management of power system resilience and timely control of the operating conditions.

关键词： Neural network deep learning algorithm low-frequency oscillation resiliency assessment smart grid wide-area control

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：