检索结果-内蒙古大学图书馆

An Effective yet Fast Early Stopping Metric for Deep Image Prior in Image Denoising

IEEE Signal Processing Letters 2025年 32卷 1925-1929页

作者： Cheng, Xiaohui Xu, Shaoping Tao, Wuyong Nanchang University School of Mathematics and Computer Sciences Nanchang330036 China Nanchang Institute of Technology School of Computer Information Engineering Nanchang330044 China

The deep image prior (DIP) and its variants have demonstrated the ability to address image denoising in an unsupervised manner using only a noisy image as training data, but practical limitations arise due to overfitting in highly overparameterized models and the lack of robustness in the fixed iteration step of early stopping, which fails to adapt to varying noise levels and image contents, thereby affecting denoising effectiveness. In this work, we propose an effective yet fast early stopping metric (ESM) to overcome these limitations when applying DIP models to process synthetic or real noisy images. Specifically, our ESM measures the image quality of the output images generated by the DIP network. We split the output image from each iteration into two sub-images and calculate their distance as an ESM to evaluate image quality. When the ESM stops decreasing over several iterations, we end the training, ensuring near-optimal performance without needing the ground-truth image, thus reducing computational costs and making ESM suitable for application in the denoising of real noisy images. © 1994-2012 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Quadratic and Lagrange interpolation-based butterfly optimization algorithm for numerical optimization and engineering design problem

引用

Soft Computing 2025年第1期29卷 157-194页

作者： Sharma, Sushmita Saha, Apu Kumar Chakraborty, Sanjoy Deb, Suman Sahoo, Saroj Kumar Department of Computer Science and Engineering Indian Institute of Information Technology Tripura Agartala India Department of Computer Science and Engineering National Institute of Technology Tripura Agartala India Department of Mathematics National Institute of Technology Agartala Tripura Agartala India Department of Information Technology Bir Bikram Memorial College Tripura Agartala India

This work proposes a novel and improved Butterfly Optimization Algorithm (BOA), known as LQBOA, to solve BOA’s inherent limitations. The LQBOA uses Lagrange interpolation and simple quadratic interpolation techniques with adapted parameter settings to enhance the search strategy of BOA and to achieve a better balance of diversification and intensification. LQBOA’s performance was examined on 45 traditional benchmark issues as well as the IEEE CEC 2017 benchmark suites with 10, 30 and 50 dimensions, and the results were compared against popular state-of-the-art and modified algorithms. It was discovered that in more than 85% of cases, the proposed LQBOA outperformed the compared algorithms. The Friedman rank test and Wilcoxon rank test were used to validate the suggested LQBOA’s rank and significance. Additionally, convergence and diversity analyses were performed to investigate its convergence speed and searching behavior, respectively. Furthermore, LQBOA has been successfully deployed to solve twelve real-world issues including several engineering design problems and two multiple gravity assist spacecraft trajectory problems. The results of these problems were compared to those of a wide range of algorithms, demonstrating the superior performance of the proposed LQBOA. In conclusion, LQBOA makes a significant addition to the optimization area, and its application could greatly improve the performance of numerous optimization jobs. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Comparative Study and Analysis of Health Care System for Heart Patients: Formal Review 1

Comparative Study and Analysis of Health Care System for Hea...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Agrawal, Chanchal G. Uke, Nilesh J. Vishwakarma Institute of Information Technology Computer Engineering Pune India Indira College of Engineering and Management Computer Engineering Pune India

ISBN: (纸本)9798350355611

Nationwide in today's day to life the fundamental root causes of deaths and hospitalization is heart diseases which will put enormous economic burden on health care system and on the Human life. Prediction at early stage for this type of crucial diseases is one of the best results in morbidity which can be achieve by Clinical Data Analysis. The assessment of cardiovascular events relies on numerous risk factors. Central to effective cardiovascular disease prevention is risk evaluation. In medical systems, data mining and machine learning techniques play a crucial role in developing models to predict heart or cardiovascular disease. These techniques assist researchers in estimating the likelihood of heart disease in vulnerable patients and comparing various ML models. Researchers and practitioners have proposed multiple solutions at both data and algorithm levels over time. This study employs a formal literature review (FLR) approach to provide a comprehensive overview of existing literature and uncover challenges related to imbalanced data in heart disease predictions. Prior to writing, an extensive analysis was conducted using 100 reference papers from reputable journals published between 2017 and 2023. A thorough examination of 52 referenced papers was performed, considering factors such as heart disease type, algorithms, applications, and solutions across various scientific databases, including the Ryerson University Library and Archives (RULA) online system. The primary search databases accessed through RULA were PubMed Central, Springer, Elsevier, Multidisciplinary Digital Publishing institute (MDPI), IEEE Xplore, Web of Science, Hindawi, and Frontiers. The FLR study revealed that current approaches face several unresolved issues when handling heart disease datasets. © 2025 IEEE.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Indic Language Empowerment in E-commerce: Integrating Generative Translations and Vectorized Searches 1

Indic Language Empowerment in E-commerce: Integrating Genera...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Bhosale, Parth Gopale, Kunal Taware, Karan Bewoor, Laxmi Vishwakarma Institute Of Information Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350355611

E-commerce has revolutionized the retail landscape, offering consumers unparalleled convenience and a vast array of choices from the comfort of their homes. Enabling e-commerce in native languages is crucial for creating an inclusive shopping experience, allowing businesses to effectively reach and engage diverse linguistic communities. India is renowned for its multilingual and cultural legacy and this work is an attempt to reach a wider consumer base and increase market potential in India by providing online shopping for cultural festivals. The proposed work is an attempt to develop native language E-commerce platform for various festivals celebrated in India by using Large Language Models (LLM) to generate contextually rich and relevant contents making the user experience more intuitive and personalized. Finally, we talk about making search features better by using modern technology. By using smart algorithms and models, we help users search for products in their own language, and show them results that are most relevant to what they're looking for. Through careful testing and analysis, we show that our solution works well in improving how people interact with e-commerce websites, reaching more customers, and making more sales. Our research is important because it helps bridge the language gap online, giving businesses new opportunities to grow and making online shopping more accessible for everyone. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Secure probe-based latency measurement using NTP and PTP for optimized gateway placement in LoRaWAN

引用

International Journal of information Technology (Singapore) 2025年 1-10页

作者： Bhatnagar, Kumar Vaibhav Kushwah, Rashmi Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Uttar Pradesh Noida 201304 India

The paper presents a novel framework for optimizing LoRaWAN gateway placement to enhance network performance and reliability. By integrating Network Time Protocol (NTP) for global synchronization and Precision Time Protocol (PTP) for local precision, the approach ensures accurate and secure latency measurements. A robust hash algorithm is employed to safeguard the integrity of latency data. The Performance Efficiency Index (PEI) is introduced as a comprehensive metric to evaluate key performance indicators such as latency, throughput, energy efficiency, and packet delivery ratio (PDR). The model incorporates factors like geographical distribution, signal strength, and gateway density to achieve optimal placement. Simulation results demonstrate the framework’s effectiveness in improving network latency, coverage, energy efficiency, and security, providing actionable insights for LoRaWAN-based IoT network design. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： Gateway placement LoRaWAN Network performance NTP PTP Timestamp

来源：评论

学校读者我要写书评

暂无评论

Enhancing the efficiency of lung cancer screening: predictive models utilizing deep learning from CT scans

引用

Neural Computing and Applications 2025年 1-19页

作者： Tawfeek, Medhat A. Alrashdi, Ibrahim Alruwaili, Madallah Shaban, Warda M. Talaat, Fatma M. Department of Computer Science Faculty of Computers and Information Menoufia University Shebin Elkom32511 Egypt Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Computer Engineering and Networks College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Communication and Electronics Engineering Nile Higher Institute for Engineering and Technology Mansoura Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt

Lung cancer is the most lethal form of cancer. This paper introduces a novel framework to discern and classify pulmonary disorders such as pneumonia, tuberculosis, and lung cancer by analyzing conventional X-ray and CT scan images called lung cancer risk prediction (LCRP) model. LCRP has four modules, namely data collection and preprocessing, data augmentation module, image segmentation module, and prediction module. Actually, LCRP employs three deep learning models;sequential model, functional model, and transfer model on publicly available training datasets. Convolutional neural networks (CNNs) have emerged as a highly effective field in machine learning, particularly for image datasets in the field of biomedical applications. The primary goal is to validate these models by comparing their performance with other models in order to determine their effectiveness in addressing challenging datasets. Our research has revealed a noteworthy enhancement in the efficiency of binary and multi-class classification using mask R-CNN image segmentation. During the model training process, a combination of Adam and stochastic gradient descent dual optimizers has been used to improve performance. LCRP have outperformed current pre-trained models by minimizing training parameters, computational costs, and overhead. It introduces 98.5% accuracy, 88.7% specificity, 89% sensitivity, 89.2% precision, and 89.09% F-measure. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning models for automatic detection of driver’s facial expressions, movements, and alertness in varied lighting conditions: a comparative analysis

引用

Multimedia Tools and Applications 2025年第6期84卷 2947-2983页

作者： Das, Shiplu Pratihar, Sanjoy Pradhan, Buddhadeb Computer Science and Engineering Indian Institute of Information Technology West Bengal Kalyani India University of Engineering and Management Kolkata West Bengal New Town India

Emotion recognition is vital in understanding human behavior and improving the driving experience. We present a systematic analysis of automatic detection of driver’s facial expressions and movements while crying, feeling sad, experiencing anger, drowsiness, fear and surprise to reduce road accident using a deep learning method in varied lighting conditions. The proposed approach aims to accurately detect and analyze driver emotions in real time, it would help in advancing the growth of smart driver assistance systems. To conduct our analysis, we create a comprehensive dataset comprising annotated facial images of drivers exhibiting crying, sadness, anger, drowsiness, fear and surprise. The dataset is carefully designed to encompass diverse lighting conditions, facial orientations, and driver demographics, ensuring the generalizability and robustness of the proposed method. The CNN-BiLSTM model is compared against the CNN, LSTM, CNN-LSTM, BiLSTM, and CNN-LSTM models in the research to perform precise localization of facial expressions and movements. The trial findings show how well our technique accurately identifies and evaluates a driver’s facial expressions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

NSGT: A Plasma Position Prediction Method for the HL-2A Tokamak Device Based on Transformer

引用

IEEE Access 2025年 13卷 72875-72882页

作者： Zhou, Ling Yang, Bin Lin, Xiangcheng Zhu, Kaihao Lan, Ziran Li, Xiangwen Chengdu University of Technology The Engineering and Technology College Department of Electronic Information and Computer Engineering Leshan614000 China Southwestern Institute of Physics Chengdu610225 China

In the discharge experiments of the HL-2A Tokamak device, plasma position prediction plays a crucial role in aspects such as the closed - loop control of HL-2A and verifying the correctness of the plasma controller design. In previous studies, methods based on traditional equations and LSTM have made significant progress in plasma position prediction. However, plasma position prediction is of extremely high complexity, and these methods have difficulty in achieving further improvement on this issue. To address the problem that the performance of traditional methods is hard to enhance further, we propose a Non - Stationary - Gated Linear Unit Transformer (NSGT) model integrating multi - source data processing. In this model, we select data from historical discharge experiments as the input of the NSGT model, and use the improved Transformer structure to model the global features of the multi - source fused data. The experimental results show that the NSGT model has a significant reduction in the root - mean - square error of prediction compared with the LSTM method, effectively supporting the real - time adjustment of the closed - loop control system. This method not only improves the prediction accuracy but also provides important technical support for achieving more stable and safe operation of the Tokamak device. © 2013 IEEE.

关键词： Tokamak devices

来源：评论

学校读者我要写书评

暂无评论

Enhancing Accuracy of Handwritten Character Segmentation Using Region-Based Convolutional Neural Networks (R-CNN) 1

Enhancing Accuracy of Handwritten Character Segmentation Usi...

引用

1st International Conference on AIML-Applications for engineering and Technology, ICAET 2025

作者： Varpe, Kanchan Sakhare, Sachin Joshi, Rahul Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Department of Computer Science and Engineering Pune India

ISBN: (纸本)9798350355611

Handwritten character segmentation plays a pivotal role in the performance of Optical Character Recognition (OCR) systems. This paper introduces an innovative approach to enhancing segmentation accuracy using Region-Based Convolutional Neural Networks (R-CNN). Traditional methods often struggle with issues such as varying character sizes, overlapping, and inconsistent writing styles, leading to suboptimal recognition results. The proposed R-CNN model addresses these challenges by effectively localizing and segmenting individual characters from handwritten text images. The methodology involves training the R-CNN on a comprehensive dataset of handwritten characters, annotated to capture diverse styles and complexities. The model leverages deep learning's feature extraction capabilities and region-based localization to accurately segment characters, even in challenging scenarios like connected or touching characters. Comparative experiments show that the proposed approach outperforms conventional techniques in terms of segmentation accuracy and robustness. Results demonstrate significant improvements, with the R-CNN model achieving higher precision and recall rates across multiple handwritten datasets, including different languages and scripts. This advancement holds promise for enhancing OCR systems used in applications such as automated document processing and digital archiving. Future work will focus on integrating this segmentation method with advanced recognition models to further boost overall handwritten text recognition performance. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Emotion Detection from Facial Features Extraction and Machine Learning Models

Automatic Emotion Detection from Facial Features Extraction ...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Shankar, Raghav Singh Kirar, Bhupendra Upadhyay, Pratham Jee Mishra, Shree Govind Indian Institute of Information Technology Computer Science and Engineering Bhopal India Indian Institute of Information Technology Electronics and Communications Engineering Bhopal India Information Technology Indian Institute of Information Technology Bhopal India

ISBN: (纸本)9798331529833

In the domain of Interactive Systems (IS), machine learning (ML) emerges as a profound, user-friendly, and accurate approach to enhancing emotional intelligence in digital systems. This research work focuses on facial emotion detection, an important but often-neglected aspect of affective computing. Models used for the assessment include Multinomial Naïve Bayes (MNB), Decision Trees (DT), K-Nearest Neighbours (KNN), Random Forest (RF), Support Vector Machines (SVMs), XG Boost (XGB), and Logistic Regression (LR). By employing the FER2013 dataset and MediaPipe's (MP's) facial recognition technology, this research extracts 478 3D facial landmarks to test. The best Acc in emotion detection is found using LR with an accuracy of 65.57% followed by XGB with an accuracy of 61.24%. This study thus will help as a practical application toward making improvements in IS in matters regarding health, marketing, or even security. © 2025 IEEE.

关键词： Adversarial machine learning

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：