检索结果-内蒙古大学图书馆

Enhancing intra-aural disease classification with attention-based deep learning models

Neural Computing and Applications 2025年第9期37卷 6601-6616页

作者： Demircan, Furkancan Ekinci, Murat Cömert, Zafer Software Engineering Faculty of Engineering and Natural Sciences Samsun University 19 Mayıs Samsun Turkey Computer Engineering Faculty of Engineering Karadeniz Technical University Trabzon Ortahisar Turkey Department of Technical Sciences of the Western Caspian University Baku Azerbaijan

Ear diseases are defined as pathological conditions that indicate dysfunction or abnormal function of the ear organ, which is part of the auditory system of living organisms that regulates hearing and balance functions. These diseases usually manifest as conditions that affect the internal components of the ear structure and can manifest themselves with symptoms such as hearing loss, ear pain, balance problems, and fluid accumulation in the ear. The accuracy of the diagnosis depends on expert knowledge and subjective opinion. This method is prone to human error. This study presents a novel computer-aided diagnosis system for otoscope images of ear diseases, utilizing a vision transformer-based feature extractor combined with machine learning classifiers to provide accurate second opinions for ENT specialists. For this purpose, a new model based on state-of-the-art vision transformer feature extractor and machine learning models is proposed. In the experimental study, the dataset, comprising 880 eardrum images categorized into four classes (CSOM, earwax, myringosclerosis, and normal), was split into training (70%), validation (10%), and testing (20%) subsets. Each image was preprocessed to 420 × 380 pixels to fit the input dimensions of the models. The vision transformer architecture was utilized for feature extraction, followed by classification using various machine learning algorithms including kNN, SVM, and random forest. As a result, the model using vision transformer feature extractor and k-nearest neighbors (kNN) algorithm achieved 99.00% accuracy. In this study, a deep learning-based and computer-aided diagnosis system, in other words, a computational model, was developed instead of the current human error-prone disease diagnosis method used by ear nose throat (ENT) specialists. The main purpose of the deep learning-based decision support system is to support the diagnosis process where expert knowledge is difficult to access and to provide an alternative opi

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Review on the Use of Smart Agriculture Systems to Protect Crops 3

A Review on the Use of Smart Agriculture Systems to Protect ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kumar, Gulshan Gourshettiwar, Palash Suman, Saurabh Kumar, Shravan Kumar, Dhiraj Raushan, Rahul Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha India Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798331509675

Smart agriculture systems leverage the possibilities offered by cutting-edge technologies such as IoT, AI, and remote sensing to revolutionize conventional farming by enhancing resource utilization, production, and crop damage mitigation. Real-time monitoring of soil and crop health, predictive analytics, pest control, and precision irrigation measures are all enabled by these systems. They are able to address major Indian agriculture issues, consequently boosting yield and profitability and promoting environmental sustainability. The largescale deployment of intelligent agriculture systems will change the agriculture landscape in India and will assure long-term food security for an ever-growing population. Challenges include adequate research and future studies in order to better install and achieve smart agricultural systems to protect crops. Intelligent agriculture involves all advanced research, including science and innovations, in national development through space technologies to enhance soil quality, conserve water, and facilitate agriculture information. Space ventures will undergo improved modernization through the introduction of crop sprayers, precision gene editors, epigenetics, big data analytics, IoT, wind and photovoltaic smart energy, AI-enabled robotic applications, and wide-scale desalination technologies. Implementing digital farming systems in developing economies will help their sectors as 85 percent of the global population is set to live in developing countries by 2030. Automation will prove to be necessary since food scarcity is on the rise along with resource wastage. Control strategies such as the IoT, aerial imagery, machine learning, and artificial intelligence will boost production and prevent soil degradation. These advanced technologies are also able to alleviate such issues as plant disease detection, pesticide management, and water application. The introduction of the Internet of Things in the agricultural research world has started

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Parameters Estimation of Modified Triple Diode Model of PSCs Considering Charge Accumulations and Electric Field Effects Using Puma Optimizer

引用

computer Modeling in engineering & Sciences 2025年第4期143卷 723-745页

作者： Amlak Abaza Ragab A.El-Sehiemy Mona Gafar Ahmed Bayoumi Electrical Engineering Department Faculty of EngineeringKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Computer Engineering and Information College of Engineering inWadi AlddawasirPrince Sattam Bin Abdulaziz UniversityKharj16278Saudi Arabia Machine Learning and Information Retrieval Department Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Electrical Department Faculty of Engineering and TechnologyBadr University in CairoBadr11829Egypt Physics and Mathematics Department Faculty of EngineeringKafrelsheikh UniversityKafrelsheikh33516Egypt College of Engineering Al-Ayen UniversityThi-Qar64001Iraq

Promoting the high penetration of renewable energies like photovoltaic(PV)systems has become an urgent issue for expanding modern power grids and has accomplished several challenges compared to existing distribution *** study measures the effectiveness of the Puma optimizer(PO)algorithm in parameter estimation of PSC(perovskite solar cells)dynamic models with hysteresis consideration considering the electric field effects on *** models used in this study will incorporate hysteresis effects to capture the time-dependent behavior of PSCs *** PO optimizes the proposed modified triple diode model(TDM)with a variable voltage capacitor and resistances(VVCARs)considering the hysteresis *** suggested PO algorithm contrasts with other wellknown optimizers from the literature to demonstrate its *** results emphasize that the PO realizes a lower RMSE(Root mean square errors),which proves its capability and efficacy in parameter extraction for the *** statistical results emphasize the efficiency and supremacy of the proposed PO compared to the other well-known competing *** convergence rates show good,fast,and stable convergence rates with lower RMSE via PO compared to the other five competitive ***,the lowermean realized via the PO optimizer is illustrated by the box plot for all optimizers.

关键词： Dynamic model of PSCs puma optimizer parameter estimation triple diode model

来源：评论

学校读者我要写书评

暂无评论

Surface Functionalized Plasmonic Sensors for Uric Acid Detection With Gold-Graphene Stacked Nanocomposites

引用

Photonic Sensors 2025年第1期15卷 122-137页

作者： Olabisi Abdullahi ONIFADE Dinie Dayana MOHAMAD AZRI Muhammad Hafiz ABU BAKAR Mohammed Thamer ALRESHEEDI Eng Khoon NG Mohd Adzir MAHDI Ahmad Shukri MUHAMMAD NOOR Department of Computer and Communication Systems Engineering Faculty of EngineeringUniversiti Putra MalaysiaSerdang 43400Malaysia Wireless and Photonics Research Centre of Excellence Faculty of EngineeringUniversiti Putra MalaysiaSerdang43400Malaysia Department of Electrical Engineering College of EngineeringKing Saud UniversityRiyadh 11421Kingdom of SaudiArabia Department of Engineering University of CambridgeCambridge CB30FAThe United Kingdom Institute of Nanoscience and Nanotechnology(ION2) Universiti Putra MalaysiaSerdang 43400Malaysia

This study presented a surface-functionalized sensor probe using 3-aminopropyltriethoxysilane(APTES)self-assembled monolayers on a Kretschmann-configured plasmonic *** probe featured stacked nanocomposites of gold(via sputtering)and graphene quantum dots(GQD,via spin-coating)for highly sensitive and accurate uric acid(UA)detection within the physiological *** encompassed the field emission scanning electron microscopy for detailed imaging,energy-dispersive X-ray spectroscopy for elemental analysis,and Fourier transform infrared spectroscopy for molecular *** functionalization increased sensor sensitivity by 60.64%,achieving 0.0221°/(mg/dL)for the gold-GQD probe and 0.0355°/(mg/dL)for the gold-APTES-GQD probe,with linear correlation coefficients of 0.8249 and 0.8509,*** highest sensitivity was 0.0706°/(mg/dL),with a linear correlation coefficient of 0.993 and a low limit of detection of 0.2 mg/***,binding affinity increased dramatically,with the Langmuir constants of 14.29μM^(-1)for the gold-GQD probe and 0.0001μM^(-1)for the gold-APTES-GQD probe,representing a 142900-fold *** probe demonstrated notable reproducibility and repeatability with relative standard deviations of 0.166%and 0.013%,respectively,and exceptional temporal stability of 99.66%.These findings represented a transformative leap in plasmonic UA sensors,characterized by enhanced precision,reliability,sensitivity,and increased surface binding capacity,synergistically fostering unprecedented practicality.

关键词： Plasmon nanocomposite gold-graphene quantum dot uric acid,functionalize sensor

来源：评论

学校读者我要写书评

暂无评论

Optimizing Stand-Alone PV Systems:A Metaheuristic-Enhanced Fuzzy Approach for Adaptive MPPT

引用

China Communications 2025年第1期22卷 61-74页

作者： Tina Samavat Mostafa Nazari Lin Fuhong Lei Yang Department of Computer Science and Engineering University of NevadaRenoNVUSA Faculty of Mechanical Engineering Shahrood University of TechnologyShahroodIran School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

This paper introduces a simple yet effective approach for developing fuzzy logic controllers(FLCs)to identify the maximum power point(MPP)and optimize the photovoltaic(PV)system to extract the maximum power in different environmental *** propose a robust FLC with low computational complexity by reducing the number of membership functions and *** optimize the performance of the FLC,metaheuristic algorithms are employed to determine the parameters of the *** evaluate the proposed FLC in various panel configurations under different environmental *** results indicate that the proposed FLC can easily adapt to various panel configurations and perform better than other benchmarks in terms of enhanced stability,responsiveness,and power transfer under various scenarios.

关键词： genetic algorithm imperialist competitive algorithm invasive weed algorithm maximum power point tracking

来源：评论

学校读者我要写书评

暂无评论

Evaluating AI-powered predictive solutions for MRI in lumbar spinal stenosis: a systematic review

引用

Artificial Intelligence Review 2025年第8期58卷 1-78页

作者： Al-antari, Mugahed A. Salem, Saied Raza, Mukhlis Elbadawy, Ahmed S. Bütün, Ertan Aydin, Ahmet Arif Aydoğan, Murat Ertuğrul, Bilal Talo, Muhammed Gu, Yeong Hyeon Department of Artificial Intelligence and Data Science College of AI Convergence Daeyang AI Center Sejong University Seoul05006 Korea Republic of Department of Artificial Intelligence College of AI Convergence Daeyang AI Center Sejong University Seoul05006 Korea Republic of Department of Computer Engineering Faculty of Engineering Fırat University Elazığ Turkey Department of Computer Engineering Faculty of Engineering Inonu University Malatya Turkey Department of Software Engineering Faculty of Technology Fırat University Elazığ Turkey Department of Neurosurgery Faculty of Medicine Fırat University Elazığ Turkey Department of Computer Science & Engineering University of North Texas DentonTX76205 United States

Lumbar spinal stenosis (LSS) involves the narrowing of the spinal canal, leading to compression of the spinal cord and nerves in the lower back. Common causes include injuries, degenerative age-related changes, congenital conditions, and tumors, all of which contribute to back pain. Early diagnosis is critical for symptom management, preventing progression, and preserving quality of life. This study systematically reviews AI-based approaches for predicting LSS using MRI axial and sagittal imaging. The review focuses on various AI tasks: detection, segmentation, classification, hybrid approaches, spinal index measurements (SIM), and explainable AI frameworks. The aim is to highlight current knowledge, identify limitations in existing models, and propose future research directions. Following PRISMA guidelines and the PICO method (Population, Intervention, Comparison, Outcome), the review collects data from databases like PubMed, Web of Science, ScienceDirect, and IEEE Xplore (2005–2024). The Rayyan AI tool is used for duplicate removal and screening. The screening process includes an initial review of titles and abstracts, followed by full-text appraisal. The Meta Quality Appraisal Tool (MetaQAT) assesses the quality of selected articles. Of 1323 records, 97 duplicates were removed. After screening, 895 records were excluded, leaving 331 for full-text review. Among these, 184 articles were excluded for lacking AI relevance. Ultimately, 95 key articles (91 technical papers and 4 reviews) were identified for their contributions to AI-based LSS prediction. This review provides a comprehensive analysis of AI techniques in LSS prediction, guiding future research and advancing understanding in areas like explainable AI and large language models (LLMs). © The Author(s) 2025.

关键词： Explainable artificial intelligence (XAI) Harmonization Large language models (LLMs) LSS prediction Lumbar spinal stenosis (LSS) Spinal LSS indices measurements

来源：评论

学校读者我要写书评

暂无评论

AE-MCDM: an autoencoder-based multi-criteria decision-making approach for unsupervised feature selection

引用

Journal of Supercomputing 2025年第7期81卷 1-44页

作者： Hashemi, Amin Dowlatshahi, Mohammad Bagher Farshidi, Siamak Moradi, Parham Department of Computer Engineering Faculty of Engineering Lorestan University Khorramabad Iran Informal Technology Group Wageningen University & Research Wageningen Netherlands School of Engineering RMIT University Melbourne Australia

Feature selection is a fundamental technique for reducing the dimensionality of high-dimensional data by identifying the most relevant features while discarding redundant or irrelevant ones. In unsupervised settings, where labeled data are unavailable and labeling is costly, effective feature selection becomes even more challenging. This paper proposes AE-MCDM, a novel unsupervised feature selection method that integrates autoencoder-based feature extraction with multi-criteria decision-making (MCDM). The autoencoder captures high-level feature representations, and the connection weights between input features and hidden neurons reflect feature importance. These weights are then processed using MCDM to rank and select the most informative features. Unlike conventional unsupervised feature selection methods, AE-MCDM leverages deep representation learning to enhance feature evaluation. To the best of our knowledge, this is the first attempt to combine autoencoders with MCDM for feature selection. Extensive experiments on various datasets demonstrate that AE-MCDM outperforms existing methods in terms of clustering performance, measured by metrics such as accuracy, precision, recall, and normalized mutual information (NMI), while also achieving competitive computational efficiency. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Review of dehazing techniques: challenges and future trends

引用

Multimedia Tools and Applications 2025年第3期84卷 1103-1131页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

The phenomenon of atmospheric haze arises due to the scattering of light by minute particles suspended in the atmosphere. This optical effect gives rise to visual degradation in images and videos. The degradation is primarily influenced by two key factors: atmospheric attenuation and scattered light. Scattered light causes an image to be veiled in a whitish veil, while attenuation diminishes the image inherent contrast. Efforts to enhance image and video quality necessitate the development of dehazing techniques capable of mitigating the adverse impact of haze. This scholarly endeavor presents a comprehensive survey of recent advancements in the domain of dehazing techniques, encompassing both conventional methodologies and those founded on machine learning principles. Traditional dehazing techniques leverage a haze model to deduce a dehazed rendition of an image or frame. In contrast, learning-based techniques employ sophisticated mechanisms such as Convolutional Neural Networks (CNNs) and different deep Generative Adversarial Networks (GANs) to create models that can discern dehazed representations by learning intricate parameters like transmission maps, atmospheric light conditions, or their combined effects. Furthermore, some learning-based approaches facilitate the direct generation of dehazed outputs from hazy inputs by assimilating the non-linear mapping between the two. This review study delves into a comprehensive examination of datasets utilized within learning-based dehazing methodologies, elucidating their characteristics and relevance. Furthermore, a systematic exposition of the merits and demerits inherent in distinct dehazing techniques is presented. The discourse culminates in the synthesis of the primary quandaries and challenges confronted by prevailing dehazing techniques. The assessment of dehazed image and frame quality is facilitated through the application of rigorous evaluation metrics, a discussion of which is incorporated. To provide empiri

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Joint Distributed Estimation and Random Gain Channel Estimation with Beta Prior

引用

IEEE Communications Letters 2025年第5期29卷 1008-1012页

作者： Zayyani, Hadi Korki, Mehdi Torkamani, Razieh Department of Electrical and Computer Engineering Qom Iran Swinburne University of Technology School of Science Computing and Engineering Technologies Melbourne Australia Bu-Ali Sina University Faculty of Engineering Department of Electrical Engineering Hamedan Iran

In this letter, we propose a joint distributed estimation and channel estimation algorithm for wireless sensor networks (WSNs). We assume a random gain channel model with a Beta prior, where the channel gain is an attenuation factor ranging between zero and one. To estimate the augmented unknown vector, which includes both the unknown vector and the channel gain vector, we employ Maximum A Posteriori (MAP) estimation. This is achieved through an iterative steepest-descent method to find the MAP estimators for both the unknown vector and the channel gain vector. We mathematically derive the optimum combination coefficients that minimize disturbance. Additionally, we propose a separate approach for channel gain estimation using Least Squares (LS) and provide the convexity analysis of the cost function along with the sufficient conditions for the convergence of the iterative channel gain estimator. Simulation results demonstrate the effectiveness of the proposed algorithm compared to some other algorithms in the literature, specially when channel gains are modeled with a Beta prior. © 1997-2012 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Enhanced Skin Cancer Diagnosis via Deep Convolutional Neural Networks with Ensemble Learning

引用

SN computer Science 2025年第2期6卷 1-14页

作者： Khan, Mohd Anas Alam, Shahzad Ahmed, Waseem Department of Computer Engineering Faculty of Engineering and Technology Jamia Millia Islamia New Delhi 110025 India

Skin cancer constitutes a third of all cancer diagnoses worldwide, with its incidence steadily increasing over recent decades. The introduction of dermoscopy has significantly improved the diagnostic accuracy for skin cancer. However, dermatologists face considerable challenges in accurately diagnosing skin cancer due to the similar appearances of different types. The diagnostic accuracy among dermatologist’s ranges between 62 and 80%. The research community has achieved significant progress in creating automated systems to aid dermatologists in decision-making. This work presents a very precise automated computer-aided diagnostic (CAD) system for multi-class skin cancer classification. Our suggested strategy improves the accuracy of both skilled dermatologist and existing deep learning techniques in MCS cancer classification. Utilizing the HAM10000 dataset, we fine-tuned models across seven skin cancer classes and conducted a comparative study to evaluate the performance of three pre-trained convolutional neural networks (CNNs) and three ensemble models. Our results demonstrated a maximum accuracy of 92.16% for the best-performing individual model and an impressive 94.17% accuracy for the ensemble model. We suggest for taking advantage of InceptionV3, which for MCS cancer classification owing to its improved architecture and enhanced accuracy. This research underscores the capability of sophisticated deep learning models to improve the diagnostic process for skin cancer, providing a significant resource to assist dermatologists in attaining more precise diagnoses. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks (CNNs) Deep Ensemble Model InceptionV3 Skin cancer

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：