检索结果-内蒙古大学图书馆

Advancing skin cancer detection integrating a novel unsupervised classification and enhanced imaging techniques

CAAI Transactions on Intelligence technology 2025年第2期10卷 474-493页

作者： MdAbdur Rahman Nur Mohammad Fahad Mohaimenul Azam Khan Raiaan Mirjam Jonkman Friso De Boer Sami Azam Department of Computer Science and Engineering United International UniversityDhakaBangladesh Faculty of Science and Technology Charles Darwin UniversityCasuarinaNorthern TerritoryAustralia

Skin cancer,a severe health threat,can spread rapidly if ***,early detection can lead to an advanced and efficient diagnosis,thus reducing *** classification techniques analyse extensive skin image datasets,identifying patterns and anomalies without prior labelling,facilitating early detection and effective diagnosis and potentially saving *** this study,the authors aim to explore the potential of unsupervised learning methods in classifying different types of skin lesions in dermatoscopic *** authors aim to bridge the gap in dermatological research by introducing innovative techniques that enhance image quality and improve feature *** achieve this,enhanced super-resolution generative adversarial networks(ESRGAN)was fine-tuned to strengthen the resolution of skin lesion images,making critical features more *** authors extracted histogram features to capture essential colour characteristics and used the Davies-Bouldin index and silhouette score to determine optimal ***-tuned k-means clustering with Euclidean distance in the histogram feature space achieved 87.77% and 90.5% test accuracies on the ISIC2019 and HAM10000 datasets,*** unsupervised approach effectively categorises skin lesions,indicating that unsupervised learning can significantly advance dermatology by enabling early detection and classification without extensive manual annotation.

关键词： histogram feature optimal cluster skin lesion unsupervised classification

来源：评论

学校读者我要写书评

暂无评论

X-LeafNet: A Modified Xception Model for Identifying Tea Leaf Diseases with Explainable Artificial Intelligence

X-LeafNet: A Modified Xception Model for Identifying Tea Lea...

引用

2024 International Conference on Innovations in science, engineering and technology, ICISET 2024

作者： Biswas, Prithvi Ferdib-Al-Islam Das, Sumi Northern University of Business and Technology Khulna Department of Computer Science and Engineering Khulna Bangladesh

ISBN: (纸本)9798350355499

This study presents "X-LeafNet,"a novel approach for identifying tea leaf diseases using a modified Xception model integrated with Explainable Artificial Intelligence (XAI) techniques. The system aims to classify tea leaf images into six distinct classes: Algal Spot, Brown Blight, Gray Blight, Healthy, Helopeltis, and Red Spot. Utilizing transfer learning, the modified Xception model (X-LeafNet) serves as a robust multiclass image classifier. Prior to model input, images undergo a series of preprocessing steps to enhance classification accuracy. XAI approaches, including Gradient-weighted Class Activation Mapping (Grad-CAM) and Local Interpretable Model-Agnostic Explanations (LIME), are utilized to clarify the decision-making process of the modified Xception-based convolutional neural network (CNN). These strategies enable the identification of pivotal image regions that affect the model's predictions. Experimental results demonstrate the efficacy of X-LeafNet, achieving remarkable accuracies: 99.41% for Red Spot, 100% for Algal Spot, Brown Blight, Gray Blight, and Healthy leaves, and 99.82% for Helopeltis. With an average accuracy, precision, recall, and F1-score of 99.71%, X-LeafNet significantly outperforms existing methods, providing a reliable and interpretable solution for tea leaf disease classification. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning-based Fine Tuned MobileNetV2 Model with Explainable Artificial Intelligence for Identifying Dental Diseases

Transfer Learning-based Fine Tuned MobileNetV2 Model with Ex...

引用

2024 IEEE International Conference on Biomedical engineering, computer and Information technology for Health, BECITHCON 2024

作者： Taskin, Summiya Ferdib-Al-Islam Department of Computer Science and Engineering Northern University of Business and Technology Khulna Khulna9100 Bangladesh

ISBN: (纸本)9798331534356

This study presents a pioneering approach to identifying and categorizing six prevalent dental diseases—calculus, caries, gingivitis, hypodontia, mouth ulcers, and tooth discoloration using transfer learning-based deep learning models enhanced with explainable artificial intelligence (XAI). To support medical professionals and address significant diagnostic challenges, we evaluated four pre-trained models: DenseNet169, InceptionV3, MobileNetV2, and ResNet50V2. Model efficacy was assessed through various metrics, including accuracy, precision, recall, f1-score, and confusion matrix. Our findings indicate that MobileNetV2 excelled, achieving the highest accuracy rate of 89.02%, with a precision of 89.45%, recall of 89.02%, and an F1-score of 89.13%. To enhance model interpretability and trust, we employed LIME and Grad-Cam techniques, which provided valuable insights into model predictions by highlighting critical areas of focus. This comprehensive and rigorous analysis not only advances multiclass image classification for oral diseases but also strengthens the reliability of the results. The integration of XAI techniques ensures that the models are transparent and trustworthy, thereby enhancing the confidence of both dentists and patients in the diagnostic process. The proposed work significantly outperforms existing works, providing a reliable and interpretable solution for dental diseases classification. © 2024 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Role of Artificial Intelligence in Bioinformatics and Information Extraction Systems

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2025年第1期8卷 401-418页

作者： Al-Safarini, Maram Y. Baashirah, Rania A. Computer Science Department Zarqa University Jordan Software Engineering Department University of Business & Technology Saudi Arabia

Artificial Intelligence (AI) is transforming numerous domains, including bioinformatics and information extraction systems, by advancing data processing capabilities, enhancing precision, and facilitating automation. The primary aim of this research is to examine the function of AI within the realms of bioinformatics and information extraction through a combination of quantitative and qualitative approaches. The quantitative component involved a sample of 152 participants, recognised as experts in bioinformatics and data science. The survey findings underscore the prevalent integration of AI in bioinformatics, particularly through the utilisation of reinforcement learning, neural networks, and natural language processing (NLP). Furthermore, AI substantially improves the analysis of biological data;however, it encounters challenges such as limited model interpretability and the lack of data standardisation. Notwithstanding these obstacles, AI-driven innovations in disease prognosis, personalised healthcare, and pharmaceutical development are anticipated to shape the future trajectory of bioinformatics. The qualitative findings, derived through thematic analysis encompassing core themes and sub-themes, reveal that AI significantly contributes to accelerating and refining information extraction processes. Technologies such as machine learning, NLP, and neural networks are instrumental in enhancing data processing efficiency. Nonetheless, issues such as inadequate data quality, elevated computational expenses, and the intricacy of AI models remain persistent. Looking ahead, AI is projected to integrate more effectively with big data infrastructures, enable real-time information extraction, and deliver increasingly tailored solutions. The study concludes with several policy recommendations to guide future implementation strategies. © 2025 Regional Association for Security and crisis management. All rights reserved.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Stochastic Augmented-Based Dual-Teaching for Semi-Supervised Medical Image Segmentation

引用

computers, Materials & Continua 2025年第1期82卷 543-560页

作者： Hengyang Liu Yang Yuan Pengcheng Ren Chengyun Song Fen Luo School of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China College of Artificial Intelligence Chongqing Technology and Business UniversityChongqing400067China

Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution ***,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than *** design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these *** be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled *** introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in *** the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local *** this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation *** two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation *** only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.

关键词： Semi-supervised medical image segmentation contrastive learning stochastic augmented

来源：评论

学校读者我要写书评

暂无评论

Solving Sparse Reward Tasks Using Self-Balancing Exploration and Exploitation

引用

Journal of Internet technology 2025年第3期26卷 293-301页

作者： Kong, Yan Wei, Junfeng Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

A core challenge in applying deep reinforcement learning (DRL) to real-world tasks is the sparse reward problem, and shaping reward has been one effective method to solve it. However, due to the enormous state space and sparse rewards in the real world, a large number of useless samples may be generated, leading to reduced sample efficiency and potential local optima. To address this issue, this study proposes a self-balancing method of exploration and development to solve the issue of sparse rewards. Firstly, we shape the reward function according to the evaluated progress, to guide the agent’s learning of high-reward samples. Secondly, we construct a dual-trajectory exploration network, which provides intrinsic rewards based on the novelty of states and the trajectory difference of sibling agents to encourage the agent to explore and adjust the balance between exploration and exploitation. This method effectively prevents the generation of a large amount of useless training data during the interaction between the agent and the environment, resolves local optimal dilemmas through state novelty, and adjusts the strategy in a timely manner to solve sparse reward tasks. Our method outperforms basic reinforcement learning (RL) and curiosity-driven incentives in these experimental tasks. The self-balancing exploration and exploitation approach in our research provides a new perspective and effective solution for addressing the problem of sparse rewards, thereby advancing the application of DRL in real-world problems and achieving greater success. © 2025 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FaLa: feature-augmented location-aware transformer network for graph representation learning

引用

Neural Computing and Applications 2025年第19期37卷 13835-13862页

作者： Morshed, Md Golam Sultana, Tangina Lee, Young-Koo Computer Science and Engineering Kyung Hee University Yongin17104 Korea Republic of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka1230 Bangladesh Electronics and Communication Engineering Hajee Mohammad Danesh Science & Technology University Dinajpur5200 Bangladesh

Data augmentation is a technique that improves the ability of neural networks to make accurate predictions by increasing the size of the training dataset. However, it is still uncertain how to properly use data augmentation on graph data in order to boost the performance of graph neural networks (GNNs). While the majority of current graph regularizers primarily concentrate on modifying the topological structures of graphs by adding or deleting nodes and edges, we propose a technique to augment node and edge features in order to improve efficiency. More precisely, we use cosine similarity to perform cross-functions on the existing features. This allows us to generate new graph features, such as node and edge attributes, as well as new graph structures. We then merge these new features together to provide specific pairs of inputs for graph transformer networks. We next propose feature-augmented location-aware transformer (FaLa) networks that generalize well across several graph learning problems by combining the positional and structural encoding of nodes. Additionally, in order to avoid collecting duplicate data from other features, we apply a disparity restriction during training on these latent node embeddings. Experimental findings across eleven real-world datasets demonstrate that our methodology enhances node classification accuracy by a significant margin of 2.8% to 22.7%, link prediction by 1.6% to 8.5%, and graph classification by 7.0% to 39.8% compared to the state-of-the-art graph convolutional network (GCN) and graph transformer (GT) models. This clearly shows the importance of augmenting graph features and location encoding for efficient graph representation learning. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A new technology perspective of the Metaverse:Its essence,framework and challenges

引用

Digital Communications and Networks 2024年第6期10卷 1653-1665页

作者： Feifei Shi Huansheng Ning Xiaohong Zhang Rongyang Li Qiaohui Tian Shiming Zhang Yuanyuan Zheng Yudong Guo Mahmoud Daneshmand School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Jinzhong University Shanxi030619China Department of Business Intelligence and Analytics and the Department of Computer Science Stevens Institute of TechnologyHobokenNJ07030USA

The Metaverse depicts a parallel digitalized world where virtuality and reality are *** has economic and social systems like those in the real world and provides intelligent services and *** this paper,we introduce the Metaverse from a new technology perspective,including its essence,corresponding technical framework,and potential technical ***,we analyze the essence of the Metaverse from its etymology and point out breakthroughs promising to be made in time,space,and contents of the Metaverse by citing Maslow's Hierarchy of ***,we conclude four pillars of the Metaverse,named ubiquitous connections,space convergence,virtuality and reality interaction,and human-centered communication,and establish a corresponding technical ***,we envision open issues and challenges of the Metaverse in the technical *** work proposes a new technology perspective of the Metaverse and will provide further guidance for its technology development in the future.

关键词： Metaverse Technical framework Ubiquitous connections Space convergence Virtuality and reality interaction Human-centered communication

来源：评论

学校读者我要写书评

暂无评论

SkinMultiNet: Advancements in Skin Cancer Prediction Using Deep Learning with Web Interface

引用

Biomedical Materials and Devices 2025年第1期3卷 621-637页

作者： Likhon, Md Nur Hosain Rana, Sahab Uddin Akter, Sadeka Ahmed, Md. Shorup Tanha, Khadiza Akter Rahman, Md. Mahbubur Nayeem, Md Emran Hussain Department of Computer Science and Engineering Dhaka International University Dhaka Bangladesh Department of Computer Science and Engineering Dhaka University of Engineering and Technology Gazipur Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh

Cancer remains the leading cause of death worldwide, significantly impacting individuals and healthcare systems alike. In recent decades, skin cancer has surged in prevalence compared to other major cancer types. Various factors such as texture, color, morphological characteristics, and structure are employed in categorizing different forms of skin cancer. However, traditional methods of identification often prove time-consuming and costly. Skin cancer classification predominantly relies on machine learning, with the primary method being convolutional neural networks (CNNs). Our ‘SkinMultiNet’ framework, presented in this study and based on transfer learning principles, integrates the InceptionV3 and Xception CNN models for predicting skin cancer using image data. While other machine learning models such as ResNet50, NasNet, and MobileNet were explored, the 'SkinMultiNet' framework demonstrated the most promising outcomes. Utilizing a publicly available dataset comprising 6086 skin images, we trained, tested, and evaluated our models extensively. Proposed system employed a train generator to feed image data into our deep learning CNN models, followed by implementing a learning rate reducer on the datasets within the model. Through rigorous testing and validation procedures, our models successfully processed a substantial volume of skin image data. In contrast to conventional approaches, our proposed architecture offers the potential for more reliable diagnoses, achieving an optimal accuracy rate of 94% in skin cancer prediction. This advancement holds promise for early detection and improved patient outcomes following therapy. © The Author(s), under exclusive licence to Springer science+business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural network Deep learning Django Skin cancer Web interface

来源：评论

学校读者我要写书评

暂无评论

DERLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Dual Experience Replay

引用

Journal of Internet technology 2024年第1期25卷 79-86页

作者： Yang, Zhichao Kong, Yan Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

In recent years, with the increasingly severe traffic environment, most cities are facing various traffic congestion problems, and the demand for intelligent regulation of traffic signals is also increasing. In this study, we propose a new intelligent traffic light control algorithm, dual experience replay light (DERLight), which innovatively and efficiently designs a dual experience replay training mechanism based on the classic deep Q network (DQN) framework and considers the dynamic epoch function. As results show that compared with some state-of-the-art algorithms, DERLight can shorten the average travel time of vehicles, increase the throughput at intersections, and also speed up the convergence of the network. In addition, the design of this algorithm framework is not only limited to the field of intelligent transportation, but also has transferability for some other fields. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Reinforcement 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：