检索结果-内蒙古大学图书馆

Advanced Implementation of Convolutional Neural Networks for Alzheimer's Diseases Diagnosis

SN computer Science 2025年第4期6卷 1-12页

作者： Gondalia, Vivek Popat, Kalpesh Faculty of Computer Applications (FCA) Marwadi University Gujarat Rajkot India

Alzheimer's Disease (AD) is a serious medical issue because of its progressive nature and the problem in diagnosis. One of the latest developments in artificial intelligence, the Convolutional Neural Networks(CNN), opens up great new possibilities in the development of methods that are being widely used for obtaining high performance in the diagnosis of AD. The new implementation of CNN with enhanced performance for the diagnosis of AD is proposed on brain Magnetic Resonance Imaging (MRI) copies. Pooling layers rectified linear unit (ReLU) activation functions and convolutional layers(Conv2D) comprise its fundamental architecture. The model here proposed is focused on the role of the activation function and convolution processes in feature extraction and nonlinear transforms but emphasizes the simplicity and efficiency of the *** this paper, the model was processed and evaluated with a dataset of MRI pictures classified into various stages of AD to assess the effectiveness of the technique. The model's ability to categorize was assessed using performance metrics like recall, accuracy, precision, and F1-score. The results are promising, showing the efficient design of CNN for the analysis of medical images, considering that although simple, the performance of the architecture is competitive for distinguishing the stages of AD. This work presents the basic CNN components for medical diagnosis, thus opening a venue toward more complex and hybrid neural network architectures. This study evaluates that the advanced implementation of CNN, with 99.06% validation accuracy and 93.82% balanced accuracy, is less complex and is good for real-world uses in early diagnosis. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Alzheimer's disease Brain MRI CNN Degenerative neuro disease Hybrid neural network Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Model to Predict Students’ Sentiments in Higher Educational Institutions

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第1期19卷 46-61页

作者： Ananthi, Claral Mary T. Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chengalpattu India

Sentiment analysis has been widely used in various fields of social media, education, and business. Specifically, in the education domain, the usage of sentiment analysis is difficult due to the huge amount of information, the nature of language, and processing the diverse perceptions of students. Deep learning emerges as an advanced concept in the realm of machine learning that learns features automatically from raw text data, making them well-suited for sentiment analysis tasks. In recent years, deep learning has been used in analyzing the sentiments. Deep learning architectures have surpassed other machine learning paradigms for performing sentiment analysis. The ability to analyze automatically the students’ sentiments enables HEI to process huge amounts of unstructured data quickly, efficiently, and cost-effectively. The paper aims to predict the sentiments of students’ reviews posted in VLE regarding online learning that enables the educators to optimize their teaching methods for the best results. This study paper explores the usage of CNN, LSTM, and hybrid CNN-LSTM for the prediction of sentiments. The proposed hybrid CNN-LSTM architecture achieves superior performance compared to other baseline algorithms with respect to accuracy, precision, recall, and F1 score. According to outcomes, the recommended technique achieves remarkable accuracy of 97%. The findings facilitate the progress of a more efficient deep learning sentiment prediction system that gives valuable insights from a huge volume of students’ textual data. © 2025 by the authors of this article.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Usage of Tesseract OCR Engine with Vernacular Indian Languages 5th

A Review of Usage of Tesseract OCR Engine with Vernacular In...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Joshi, Kartik Arolkar, Harshal Faculty of Computer Applications and Information Technology GLS University Ahmedabad India

ISBN: (纸本)9783031770807

Optical Character Recognition, or OCR, is a tool that could apprehend textual content in photographs or scanned documents and convert it into system-readable textual content. To recognize and extract information from snap shots, optical character popularity (OCR) software program uses exclusive codes and codes to research the form, sample and grouping of characters. In 2005, Hewlett-Packard (HP) created the open supply software program Tesseract OCR (Optical person reputation). Its reason is to extract text from images and convert it into gadget-readable text. Tesseract can manage a couple of fonts, sizes and languages, making it clean to apply for OCR. In this newsletter, the authors provide an in-intensity evaluate of the usage of the Tesseract OCR engine in Indian languages. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Combined deep convolutional neural networks for abnormality classification in wireless capsule endoscopy images

引用

Multimedia Tools and applications 2025年 1-29页

作者： Garbaz, Anass Lafraxo, Samira Charfi, Said El Ansari, Mohamed Koutti, Lahcen Salihoun, Mouna LabSIV Department of Computer Science Faculty of Sciences Ibn Zohr University Agadir Morocco Informatics and Applications Laboratory Department of Computer Science Faculty of Sciences My Ismail University Meknes Morocco Faculty of Medicine and Pharmacy of Rabat Mohammed V University Rabat Morocco

A digestive disease is a condition that affects the gastrointestinal (GI) tract, ranging from mild to severe. Common issues include heartburn, cancer, irritable bowel syndrome, and lactose intolerance. Additionally, other intestinal concerns such as bleeding, polyps, celiac disease, Crohn’s disease, ulcers, diverticulitis, small bowel syndrome, and intestinal ischemia represent further digestive illnesses. Wireless capsule endoscopy (WCE) is a device designed for endoscopic exploration that employs a compact camera to capture images of the GI tract as it passes through. WCE significantly aids in the identification of GI tract disorders. However, due to the capsule’s rapid transit and the potential for blurry, ambiguous images, abnormalities in certain regions of the intestine may be overlooked. Moreover, frames can become hazy if obstructed by food or stool waste. In this research, we propose a method for detecting abnormalities in WCE images to address these limitations. To achieve high classification performance through the extraction of both high-level and low-level features, we employ a deep CNN that integrates the DenseNet121 model with a residual block. Experimental studies demonstrate that our proposed method outperforms state-of-the-art techniques on two publicly available WCE datasets, one focused on bleeding and the other on various abnormalities. The accuracy of the proposed architecture is 96.96% for the Kvasir-Capsule Dataset and 99.50% for the MICCAI 2017 dataset. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

R2A-UNET: double attention mechanisms with residual blocks for enhanced MRI image segmentation

引用

Multimedia Tools and applications 2025年 1-31页

作者： Bentaher, Noura Lafraxo, Samira Kabbadj, Younes Ben Salah, Mohamed El Ansari, Mohamed Wakrim, Soukaina Department of Computer Science Faculty of Sciences Ibn Zohr University Agadir Morocco Informatics and Applications Laboratory Department of Computer Science Faculty of Sciences Moulay Ismail University Meknes Morocco Department of Radiology University Hospital of Agadir Faculty of Medicine and Pharmacy of Agadir Ibnou Zohr University Agadir Morocco

Gliomas, a highly aggressive and malignant category of brain tumors, continue to pose a significant global health challenge. Originating from the abnormal and uncontrolled growth of glial cells within the brain, these tumors often result in severe neurological impairments and high mortality rates, underscoring the urgency for improved diagnostic and therapeutic strategies. Early diagnosis can significantly improve outcomes and survival. Consequently, precise segmentation of tumor tissue in medical images is critical for accurate brain tumor diagnosis and effective treatment. However, achieving high-precision segmentation remains challenging due to the complex and variable nature of tumor structures in medical images. To address this problem, we developed R2A-UNET, a U-shaped architecture that leverages the power of residual blocks and attention mechanisms. To enhance the model’s ability to capture critical and relevant information, we incorporated two advanced attention mechanisms. These mechanisms are designed to prioritize important features while suppressing irrelevant or redundant details, thereby significantly improving the efficiency and accuracy of feature extraction across varying datasets. Normalized Channel Attention (NCA) was integrated in each encoder stage, generating a squeezed vector with relevant features at the end of the contracting path. Normalized Spatial Attention (NSA) was included in the skip connection in the middle of the encoder and decoder, generating more concentrated feature maps before concatenation on the decoder side. These mechanisms enable the model to focus on specific pixel values that more accurately localize abnormalities. In our study, we evaluated the performance of our model using two MRI image datasets: the LGG (Lower-Grade Glioma) segmentation database and the BraTS 2018 dataset. Our method achieved a DSC of 92% and an IoU of 86% on the LGG dataset. On the BraTS dataset, it achieved a DSC of 94.79% and an IoU of 90.12%, dem

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid deep learning framework for pedestrian detection based on thermal infrared and visible spectrum images

引用

Multimedia Tools and applications 2025年 1-27页

作者： Defaoui, Mahassine Koutti, Lahcen El Ansari, Mohamed Lahmyed, Redouan Masmoudi, Lhoussaine LabSIV Department of Computer Science Faculty of Science Ibn Zohr University Agadir80000 Morocco Informatics and Applications Laboratory Faculty of Science My Ismail University Meknes Morocco Conception and Systems Laboratory Faculty of Sciences Mohamed V University Rabat Morocco

For many intelligent systems, designing accurate pedestrian detection approaches is a fundamental task. This paper describes a novel hybrid system to detect pedestrians using both visible and thermal infrared sensors. The proposed method is achieved in two primary stages. The first stage, hypotheses generation (HG), aims to extract the regions that represent suspected pedestrians from the image. It is performed using both thermal and visible images of the same scene. Here, an improved deep learning-based solution with a convolutional neural network named PedTherm-U-net is proposed. It segments the thermal images and maps the segmentation results into the corresponding visible image to extract the ROIs (candidate pedestrians). The second stage, hypotheses verification (HV), classifies the ROIs extracted from the first stage into pedestrians and non-pedestrians. In the HV step, a novel PedVis-ResNet framework to classify the extracted ROIs is introduced. It is a modified version of ResNet model dedicated to classify the visible pedestrian samples. The proposed method has been tested on the publicly accessible OSU Color-Thermal dataset, and the obtained results demonstrate the effectiveness of the proposed method when compared to the recent state of the art pedestrian detection approaches. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-inspired comprehensive framework for desertification prediction

International Journal of Cognitive Computing in Engineering

引用

International Journal of Cognitive Computing in Engineering 2025年 6卷 462-476页

作者： Alsubai, Shtwai Mosleh, Mogeeb A.A. Al-Hadhrami, Suheer A. Bhatia, Munish College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Alkharj Saudi Arabia Faculty of Engineering & Computing University of Science & Technology Aden Yemen Faculty of Engineering and Information Technology Taiz Univeristy Taiz Yemen Department of Computer Engineering College of Engineering Al Mukalla Hadhramout Yemen Department of Computer Applications National Institute of Technology Kurukshetra India

Desertification greatly affects land deterioration, farming efficiency, economic growth, and health, especially in Gulf nations. Climate change has worsened desertification, making developmental issues in the area even more difficult. This research presents an enhanced framework utilizing the Internet of Things (IoT) for ongoing monitoring, data gathering, and analysis to evaluate desertification patterns. The framework utilizes Bayesian Belief Networks (BBN) to categorize IoT data, while a low-latency processing method on edge computing platforms enables effective detection of desertification trends. The classified data is subsequently analyzed using an Artificial Neural Network (ANN) optimized with a Genetic Algorithm (GA) for forecasting decisions. Using cloud computing infrastructure, the ANN-GA model examines intricate data connections to forecast desertification risk elements. Moreover, the Autoregressive Integrated Moving Average (ARIMA) model is employed to predict desertification over varied time intervals. Experimental simulations illustrate the effectiveness of the suggested framework, attaining enhanced performance in essential metrics: Temporal Delay (103.68 s), Classification Efficacy—Sensitivity (96.44 %), Precision (95.56 %), Specificity (96.97 %), and F-Measure (96.69 %)—Predictive Efficiency—Accuracy (97.76 %) and Root Mean Square Error (RMSE) (1.95 %)—along with Reliability (93.73 %) and Stability (75 %). The results of classification effectiveness and prediction performance emphasize the framework's ability to detect high-risk zones and predict the severity of desertification. This innovative method improves the comprehension of desertification processes and encourages sustainable land management practices, reducing the socio-economic impacts of desertification and bolstering at-risk ecosystems. The results of the study hold considerable importance for enhancing regional efforts in combating desertification, ensuring food security, and formulatin

关键词： Life on land Climate action Desertification Internet of things Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Smart AI Tool for Accident Damage Detection 6th

Smart AI Tool for Accident Damage Detection

引用

6th International conference on communication and computational technologies, ICCCT 2024

作者： Saseekala, M. Thomas, Atulya Faculty of Computer Applications Business Analytics Specialization School of Business and Management Christ University Bangalore India Christ University Bangalore India

ISBN: (纸本)9789819774258

Accidents and fatalities from motor vehicle accidents are major concerns despite substantial advancements in safety technology. Because of this, the industry has made significant investments in creating new safety features, like cutting-edge driver assistance systems, and raising public awareness of safe driving habits. In general, car accidents can result in severe damage to the vehicles involved, and assessing and repairing that damage can be time-consuming and expensive. Manual inspection of vehicles is prone to errors and often requires trained professionals to identify the extent and location of the damage. Therefore, there is a need to develop an automated system that can detect and assess the damage caused to vehicles using AI and deep learning techniques. An image-based processing technique, YOLOv3, is proposed in this work to automate damage detection on automobiles. In the work, we used CNN to create a Mask R-convolutional neural Networks model to identify the location of damage on a car. The damaged area is precisely marked in the images. The base weights from the Mask R-CNN COCO dataset are used to train the model. 21 epochs are used to process the images. The surface of the damage is highlighted in the final image using a color splash technique after processing. Auto insurance firms, vehicle rental companies, and repair shops would all benefit from this automated method of determining the degree of exterior vehicle damage and then calculating the severity of that damage. The value of fraudulent auto insurance claims can also be reduced. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Backstepping Method For Stabilizing Fuzzy Parabolic Equation Using Difference Method

Journal of Applied Science and Engineering

引用

Journal of Applied Science and Engineering 2025年第11期28卷 2161-2171页

作者： John, Zainab Ying, Teh Yuan Fadhel, Fadhel Subhi Jameel, Ali F. Malaysia Department of Mathematics College of Science Mustansiriyah University Baghdad Iraq Department of Mathematics and Computer Applications College of Science Al-Nahrain University Jadriya Baghdad Iraq Faculty of Education and Arts Sohar University Oman

In this work, a set of laws has been proposed as a group of feedback control stabilizing a boundary law for a linear fuzzy reaction-advection-diffusion equation. Stabilization is achieved by designing coordinate transformations that form recursive relationships;by using the fuzzy finite difference method, we can convert coordinates into other coordinates. This design process is unlimited to any specific kinds of boundary actuation and can handle systems with an arbitrarily finite number of eigenvalues for the unstable open-loop system. We noticed that there is another problem when converting coordinates, which is that the equation includes lower and upper functions, so we wrote the equations in the form of matrices and then converted them into ordinary differential equations. The problem of feedback, which becomes increasingly unbounded as the grid gets infinitely fine, is solved by carefully selecting the target system to which the original system is transformed. Then we stabilize the closed loop system and the regularity of control and solutions to the fuzzy reaction-advection-diffusion equation. © The Author(’s).

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Confluence of Machine Learning and Internet of Things for E-Healthcare Security 8th

Confluence of Machine Learning and Internet of Things for E-...

引用

8th International Conference on Microelectronics Electromagnetics and Telecommunications, ICMEET 2023

作者： Pattnayak, Parthasarathi Das, Tulip Mohanty, Arpeeta Patnaik, Sanghamitra School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India Faculty of Emerging Technologies SRI SRI University Odisha Cuttack India School of Computer Applications KIIT Deemed to be University Odisha Bhubaneswar India School of Law KIIT Deemed to be University Odisha Bhubaneswar India

ISBN: (纸本)9789819784219

In the current era, the e-communication technology is developing swiftly and has made a remarkable transformation in e-healthcare sector by facilitating efficient and secure transmission of patient’s data. Internet of Things (IoT) is developing drastically in the e-healthcare sector and the intelligent devices are also improving with many new innovative enhancements. The confluence of IoT and ML is manifested in many sectors but its implementation in e-healthcare sector provides real-time surveillance and monitoring of patient’s data and health status through prediction, anticipation and the capability of taking decisions intelligently. Nowadays, cryptographic and biometric systems, anomaly detection and machine learning (ML) approaches for authentication are being widely used for ensuring the security and functioning of healthcare systems. The present study aims to know how the convergence of IoT e-healthcare management system (EHMS) and ML techniques helps to design automated systems for proper monitoring and intelligent decision making. It also focuses to present an innovative architecture to safeguard the real-time healthcare from outside threats with the consumption of less possible resources of low-powered devices. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Electronic health record

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：