检索结果-内蒙古大学图书馆

Clinical deep model to analyse medical multivariate time-series data for health diagnosis

Cyber-Physical Systems 2025年第2期11卷 139-164页

作者： Almahadeen, Layth Vijay, Richa Shabaz, Mohammad Soni, Mukesh Singh, Pavitar Parkash Patel, Pavan Byeon, Haewon Department of Financial and Administrative Sciences Al- Balqa’Applied University Al-Salt Jordan Department of computer science Amity University UP Noida India Department of Computer Science Engineering Model Institute of Engineering and Technology Jammu Jammu and Kashmir India Department of Computer Science Engineering University Centre for Research & Development Chandigarh University Mohali India Department of Management Lovely Professional University Phagwara India Department of Computer Science Engineering Ahmedabad Institute of Technology Ahmedabad India Department of Digital Anti-Aging Healthcare Inje University Gimhae Korea Republic of

Clinical auxiliary decision-making is related to life and health of patients, so the deep model needs to extract the personalised representation of patients to ensure high analysis and prediction accuracy;and provide a basis for prediction conclusions. In this context, a clinical deep model proposed an interpretable assessment method of patient health status based on contextual learning of medical features, encoding the time-series features of each variable separately, and using a multi-head de-coordination self-attention mechanism for learning Relationships between different features;feature skip-connection encoding based on a compressed excitation mechanism is proposed to improve the sensitivity of the model. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Multi-Output and Multi-Task Regression for Supershape Reconstruction from 3D Point Clouds

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

IoT based Line of Control Monitoring System 2

IoT based Line of Control Monitoring System

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Petkar, Taniya Faculty of Engineering and Technology Department of Computer Science And Medical Engineering Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

This paper presents a novel line-of-control (LoC) monitoring system that leverages the Internet of Things (IoT) to improve border security. The system creates a strong infrastructure for real-time monitoring throughout critical border regions, especially the Line of Control, by utilizing IoT devices, sensors, and communication technologies. The coverage, timeliness, and data quality of conventional border surveillance systems are frequently compromised. As opposed to this, the suggested system makes use of a wirelessly networked network of intelligent sensors, such as infrared, acoustic, and video cameras. By utilizing sophisticated image processing algorithms and machine learning to analyze the gathered data, the system is able to differentiate between regular activities and any security risks. To help security staff make decisions quickly, real-time updates are transmitted to a centralized control center. Integration with cloud computing also makes data analysis, retrieval, and storage simpler and guarantees data accessibility for forensic investigations and trend research. © 2025 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Age Detection: The Impact of Data Augmentation and Balancing on CNN Performance 1st

Enhancing Human Age Detection: The Impact of Data Augmentati...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Alrubaye, Maryam Hameed, Alaa Ali Jamil, Akhtar Department of Artificial Intelligence Engineering Istinye University Istanbul Turkey Department of Computer Engineering Istinye University Istanbul Turkey Department of Computer Science National University of Computer and Engineering Sciences Islamabad Pakistan

ISBN: (纸本)9783031823763

Accurate age detection is a crucial aspect in various sectors including security, marketing, and demographic analysis, where understanding the age of individuals can lead to better service delivery and enhanced user experience. This study explores the enhancement of age detection algorithms using Convolutional Neural Networks (CNNs). Leveraging a unique combination of the UTKFace and Facial-age datasets, our approach introduces an advanced data augmentation and balancing technique. This methodological innovation significantly contributes to optimizing CNN performance in age detection tasks. The proposed technique not only overcomes the common challenges in age estimation but also achieves an accuracy of 90.51%, and a noteworthy F1 score of 89.82%, which demonstrates the model’s accuracy and robustness. The findings of this research hold substantial implications for improving age detection processes, offering a promising direction for future applications in various fields that require reliable age estimation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DeepLeaf: an optimized deep learning approach for automated recognition of grapevine leaf diseases

引用

Neural Computing and Applications 2025年第15期37卷 8799-8823页

作者： Talaat, Fatma M. Shams, Mahmoud Y. Gamel, Samah A. ZainEldin, Hanaa Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Faculty of Engineering Horus University Damietta Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

Plant diseases can cause severe losses in agricultural production, impacting food security and safety. Early detection of plant diseases is crucial to minimize crop damage and ensure agricultural sustainability. Manual monitoring is often impractical due to the complexity and time involved, making automated disease recognition essential. This study presents a new Plant Disease Detection Algorithm (PDDA) called DeepLeaf focused on identifying four common grapevine diseases: leaf blight, black rot, stable, and black measles. The PDDA integrates three key modules: an Image Preprocessing Module, a Feature Extraction Module, and an Optimized Convolutional Neural Network (OCNN)-based Classification Module. The OCNN forms the core of the classification system, with its hyperparameters fine-tuned using fuzzy optimization to enhance performance. Preprocessing techniques are applied to analyze diseased leaves, and a logistic regression algorithm is used to downsample the features for better analysis. The CNN is trained on images from the Plant Village dataset, allowing it to detect and classify grapevine leaf diseases accurately. The proposed model's efficiency in the automated diagnosis of grapevine diseases is demonstrated by its remarkable 99.7% accuracy rate. This high accuracy indicates that the PDDA may help with more effective and scalable plant disease monitoring, which will ultimately allow better agricultural practices. © The Author(s) 2025.

关键词： CNN Detection of leaf disease Extracting features Plant disease

来源：评论

学校读者我要写书评

暂无评论

A new family of q-Bernstein polynomials: probabilistic viewpoint

引用

Arab Journal of Basic and Applied sciences 2025年第1期32卷 42-50页

作者： Karagenc, Ayse Acikgoz, Mehmet Araci, Serkan Department of Mathematics Faculty of Science and Arts Gaziantep University Gaziantep Turkey Department of Computer Engineering Faculty of Engineering Hasan Kalyoncu University Gaziantep Turkey

In this paper, we introduce a new class of polynomials, called probabilistic q-Bernstein polynomials, alongside their generating function. Assuming (Formula presented.) is a random variable satisfying moment conditions, we use the generating function of these polynomials to establish new relations. These include connections to probabilistic Stirling numbers of the second kind and higher-order probabilistic Bernoulli polynomials associated with (Formula presented.) Additionally, we derive recurrence and differentiation properties for probabilistic q-Bernstein polynomials. Utilizing Leibniz’s formula, we give an identity for the generating function of these polynomials. In the latter part of the paper, we explore applications by choosing appropriate random variables, such as Poisson, Bernoulli, Binomial, Geometric, Negative Binomial, and Uniform distributions. This allows us to derive relationships among probabilistic q-Bernstein polynomials, Bell polynomials, Stirling numbers of the second kind, higher-order Frobenius-Euler numbers, and higher-order Bernoulli polynomials. We also present p-adic q-integral and fermionic p-adic q-integral representations for probabilistic q-Bernstein polynomials. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group on behalf of the University of Bahrain.

关键词： 05D40 11B73 11B83 distributions generating functions moment generating functions probabilistic q-Bernstein polynomials

来源：评论

学校读者我要写书评

暂无评论

Automated Classification and Segmentation of Brain Tumor Images using Backboned ResUNet Framework 6

Automated Classification and Segmentation of Brain Tumor Ima...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Prasanalakshmi, B. Anitha, Cuddapah Balamanigandan, R. Mahaveerakannan, R. Gade, N.V. Ratnakishor Adjunct Faculty Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India Department of Computer Science and Engineering School of Computing Mohan Babu University Andhra Pradesh Tirupati India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Tamil Nadu Chennai India

ISBN: (纸本)9798331522667

One of the most challenging issues in computer imaging is the automated segmentation of brain tumors using Magnetic Resonance Images (MRI). Several approaches are explored using Deep Neural Networks in image segmentation since they perform well in automated tumor segmentation using tumor scans. Due to the complexity, training deeper neural networks usually takes a long time and many processing resources. An automated approach for classifying and segmenting images of Brain tumor MRI is proposed. As a hybrid transfer learning approach, modified ResNet50 identifies the class of MRI images as Benign or malignant. After identifying the Benign images, the tumor’s location is segmented using a hybrid network involving ResUNet with the Xception network as Backbone. This combination approach is chosen after its comparative analysis with other backbones. Various combination approaches are carried out, and performance metrics like Jaccard, Dice, and Tversky coefficient are done to prove the ResUNet backboned with Xception plays a better role concerning accuracy and speed. The proposed approach was tested on the dataset Cancer Imaging Archive to validate its efficiency. The proposed model has an average dice similarity coefficient score of 0.94, outperforming the conventional transfer learning training method with all the layers. © 2025 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Non-Destructive Detection of Fillet Fish Quality Using MQ135 Gas Sensor and Neutrosophic Logic-Enhanced System

引用

Neutrosophic Sets and Systems 2025年 80卷 540-563页

作者： Shams, M.Y. Darwesh, M.R. Bhatnagar, Roheet Al-Sattary, N.S.A. Salama, A.A. Ghoname, M.S. Deptartment of Machine Learning Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheihk33516 Egypt Department of Agriculture Engineering Faculty of Agriculture Tanta University Tanta31527 Egypt Department of Food Processing Faculty of Industry and Energy Samannoud Technological University Egypt Department of Computer Science and Engineering Manipal University Rajasthan Jaipur India Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt

This paper demonstrates the feasibility of using an electronic nose to assess fish quality by analyzing air quality and examining volatile organic compounds (VOCs) alongside physical variables, with pH, protein content, and VOCs serving as chemical reference points. Artificial intelligence algorithms were employed to predict quality and calculate regression coefficients. Using the reference neural network algorithm based on chemical and physical compounds, regression coefficients (R values) achieved were 0.99, 0.98, and 0.97, respectively. Additionally, ANFIS (Adaptive Neuro-Fuzzy Inference System) produced R values of 0.99, 0.85, and 0.98. Both fuzzy logic and ANFIS proved effective for predicting fish quality. Image processing techniques, including histogram analysis, color mapping, and edge detection, were also applied to assess fish quality. To enhance the inference process, Neutrosophic Logic-Enhanced Fuzzy Logic Systems were utilized, addressing uncertainty and imprecision in fish quality assessment. Neutrosophic logic combines fuzzy logic's partial truth with indeterminacy, represented by three membership functions: truth, indeterminacy, and falsity. Neutrosophic fuzzy inference integrates steps like neutrosophication, rule evaluation, aggregation, and defuzzification, ensuring improved expressiveness and fidelity. For instance, neutrosophic fuzzy rules evaluated fish freshness and appearance to determine quality ratings such as poor, good, or excellent. This integration enhances decision-making by accurately modeling complex real-world uncertainties. These methods, combining electronic nose technology, artificial intelligence, and neutrosophic inference, provide a robust, non-destructive, and cost-effective approach to detecting spoilage in fillet fish. © 2025, University of New Mexico. All rights reserved.

关键词： Volatile organic compounds

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Detection by Using Machine Learning 1st

Enhancing Intrusion Detection by Using Machine Learning

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Khan, Andleeb Nand, Parma Bhushan, Bharat Hameed, Alaa Ali Jamil, Akhtar Department of Computer Science and Engineering Sharda University Greater Noida India Department of Computer Engineering Istinye University Istanbul34396 Turkey Department of Computer Science National University of Computer and Emerging Sciences Islamabad44000 Pakistan

ISBN: (纸本)9783031823763

With the advancing technology, the increase in threats has been exponential. These technologies have led to the production of huge amounts of network traffic data. Therefore, it is of immense importance for the companies to safeguard this sensitive data from any attack by the implementation of robust security techniques as this can cause heavy financial losses to the companies. There is need for the enhancement in the performance of existing Intrusion Detection Systems in order to detect the attacks more diligently. This is done by the integration of Machine Learning in the intrusion detection approaches as they develop models which are data driven and hence detect and prevent cyber-attacks. This study develops an ML based intrusion detection model by using Random Forest, Naïve Bayes and XGBoost classifiers on UNSW_NB15 dataset and pre-processing the dataset by applying One Hot Encoder and thereby giving an accuracy of 99.98%, 74.59% and 66.20% respectively. The performance evaluation indicates that the Random Forest model with an accuracy of 99.98% clearly outperforms the other algorithms. Hence, this framework can improve the system security to a greater extent. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Parallel Color Image Encryption Algorithm Based on a 2D Logistic-Rulkov Neuron Map

引用

IEEE Internet of Things Journal 2025年第11期12卷 18115-18124页

作者： Gao, Suo Zhang, Zheyi Ho-Ching Iu, Herbert Ding, Siqi Mou, Jun Erkan, Uğur Toktas, Abdurrahim Li, Qi Wang, Chunpeng Cao, Yinghong The School of Information Science and Engineering Dalian Polytechnic University Dalian116034 China School of Electrical Electronic and Computer Engineering The University of Western Australia Perth6009 Australia School of Mathematical Sciences Dalian University of Technology Dalian116024 China Department of Computer Engineering Faculty of Engineering Karamanoglu Mehmetbey University Karaman70200 Turkey Department of Artificial Intelligence and Data Engineering Engineering Faculty Ankara University Ankara06830 Turkey Jinan250000 China

Images are widely used in social networks, necessitating efficient and secure transmission, especially in bandwidth-constrained environments. This paper aims to develop a color image encryption algorithm that enhances security while optimizing computational efficiency. A novel parallel color image encryption algorithm based on the 2D Logistic-Rulkov neuron map (2D-LRNM) is proposed. In this approach, the three channels of the color image are first separated. Cross-channel information interaction is introduced to form three new channels, which are then processed in parallel. During the encryption process of each channel, a block-wise parallel encryption mechanism is applied, ensuring simultaneous encryption of each block. This block-wise strategy effectively leverages parallel computing resources and balances the task load. To meet the demand for a large number of keystreams during encryption, the 2D-LRNM is introduced. It combines the simplicity and chaotic properties of the Logistic map with the multi-timescale dynamics and neurodynamic behaviors of the Rulkov map. By overcoming the dimensional limitations inherent in the single Logistic map, this approach extends the system to a two-dimensional framework, significantly increasing the complexity of chaotic behavior and improving its unpredictability. Experimental results demonstrate that the proposed encryption algorithm achieves high security and reduces computation time by approximately 83.3%. © 2014 IEEE.

关键词： Encryption algorithms

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：