检索结果-内蒙古大学图书馆

Fuzzy deep learning architecture for cucumber plant disease detection and classification

Journal of Big Data 2025年第1期12卷 1-21页

作者： Bilal, Anas Khan, Junaid Ali Alzahrani, Abdulkareem Almohammadi, Khalid Alamri, Maha Liu, Xiaowen College of Information Science and Technology Hainan Normal University Haikou571158 China Department of Computer Science HITEC University Taxila Taxila47080 Pakistan Computer Science Department Faculty of Computing and Information Al-Baha University Al-Baha65779 Saudi Arabia Computer Science Department Applied College University of Tabuk Tabuk Saudi Arabia Software Engineering Department Faculty of Computing and Information Al-Baha University Al-Baha65779 Saudi Arabia

This paper introduces a novel fuzzy deep convolutional neural network architecture for cucumber plant disease detection, contributing to precision farming in Industry 5.0. The proposed architecture incorporates 40 convolutional layers, 4 pooling layers, 4 inverted bottleneck blocks, 4 bottleneck blocks, 5 fuzzy layers, and a fully connected layer designed to enhance accuracy and stability when analyzing remotely sensed data. The fuzzy optimistic formula is used for activation in four blocks, enabling effective information fusion. At the same time, the ReLU transfer function ensures robustness, mainly when dealing with noisy or incomplete image segments. Feature vector optimization is performed using a chaotic particle swarm algorithm, enhancing the model’s overall accuracy, reliability, and ease of implementation. The architecture achieves 98% classification accuracy, outperforming leading models like VGG-19, DarkNet-19, and ResNet-50. Moreover, the computational time per run (40–90 s) is significantly lower than these models, which use higher learnable parameters (5.7 million). The proposed approach is efficient and feasible, offering a more stable and accurate disease detection system while utilizing fewer resources. This work demonstrates the potential of AI-driven solutions in agriculture, particularly in improving disease detection and crop yield through advanced machine learning techniques. © The Author(s) 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

VisioSLR: A Vision Data-Driven Framework for Sign Language Video Recognition and Performance Evaluation on Fine-Tuned YOLO Models

引用

Procedia Computer Science 2025年 257卷 85-92页

作者： Leila Ismail Nada Shahin Henok Tesfaye Alain Hennebelle Intelligent Distributed Computing and Systems (INDUCE) Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Independent Researcher

With the emergence of AI for good, there has been an increasing interest in building computer vision data-driven deep learning inclusive AI solutions. Sign language Recognition (SLR) has gained attention recently. It is an essential component of a sign-to-text translation system to support the deaf and hard-of-hearing population. This paper presents a computer VISIOn data-driven deep learning framework for Sign Language video Recognition (VisoSLR). VisioSLR provides a precise measurement of translating signs for developing an end-to-end computational translation system. Considering the scarcity of sign language datasets, which hinders the development of an accurate recognition model, we evaluate the performance of our framework by fine-tuning the very well-known YOLO models, which are built from a signs-unrelated collection of images and videos, using a small-sized sign language dataset. Gathering a sign language dataset for signs training would involve an enormous amount of time to collect and annotate videos in different environmental setups and multiple signers, in addition to the training time of a model. Numerical evaluations of VisioSLR show that our framework recognizes signs with a mean average precision of 97.4%, 97.1%, and 95.5% and 11, 12, and 12 milliseconds of recognition time on YOLOv8m, YOLOv9m, and YOLOv11m, respectively.

关键词： Artificial intelligence Computer vision Deep learning Fine-tuning Machine translation Neural machine translation Sign language Sign language recognition Transfer learning YOLO

来源：评论

学校读者我要写书评

暂无评论

CESFusion: Cross-Frequency Enhanced Spatial—Spectral Fusion Network for Hyperspectral and Multispectral Image Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Haozheng Yang, Yanhong Li, Chaoyang Lu, Yanjie Zhang, Guodao Chen, Shengyong Tianjin University of Technology School of Computer Science and Engineering Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China School of Computer Science and Engineering Tianjin300384 China Hangzhou Dianzi University Institute of Intelligent Media Computing Hangzhou310018 China

The fusion of hyperspectral and multispectral images (MSIs) involves integrating a high spectral resolution hyperspectral image (HSI) and a high spatial resolution MSI to generate an HSI with high-resolution HSI (HR-HSI). Existing HSI-MSI fusion methods primarily focus on information fusion within the spatial domain;however, few solutions have explored the employment of frequency analysis to enhance spatial resolution, limiting their capability for global perception. In this article, we propose an efficient and novel paradigm for HSI-MSI fusion through the cross-frequency enhanced spatial-spectral fusion network, named CESFusion, exploring the complementary fusion of information between the spatial and frequency domains. Specifically, we first present the cross-frequency fusion module (CFFM) to perform global analysis through the Fourier transform (FT) and effectively integrate and enhance the frequency domain information from both HSI and MSI. Subsequently, we propose the spectral modeling module (SpeMM) based on a state space model (SMM) to capture long-range spectral dependencies with linear complexity, and integrate it with the spatial residual block-based module (SRM) for joint spatial-spectral feature extraction. Finally, to enable sufficient interaction between the spatial and frequency domains, we adopt the cross-domain interaction module (CDIM), capturing and integrating complementary information from both domains. Moreover, a frequency-based loss function is purposely designed to further improve the restoration of global information. Extensive experiments conducted on both synthetic and real datasets demonstrate the superiority of our CESFusion, as evidenced by both quantitative and qualitative evaluation results. © 1980-2012 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

multiPI-TransBTS: A multi-path learning framework for brain tumor image segmentation based on multi-physical information

引用

Computers in Biology and Medicine 2025年 191卷 110148-110148页

作者： Zhu, Hongjun Huang, Jiaohang Chen, Kuo Ying, Xuehui Qian, Ying School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Engineering Research Center of Software Quality Assurance Testing and Assessment Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Brain Tumor Segmentation (BraTS) plays a critical role in clinical diagnosis, treatment planning, and monitoring the progression of brain tumors. However, due to the variability in tumor appearance, size, and intensity across different MRI modalities, automated segmentation remains a challenging task. In this study, we propose a novel Transformer-based framework, multiPI-TransBTS, which integrates multi-physical information to enhance segmentation accuracy. The model leverages spatial information, semantic information, and multi-modal imaging data, addressing the inherent heterogeneity in brain tumor characteristics. The multiPI-TransBTS framework consists of an encoder, an Adaptive Feature Fusion (AFF) module, and a multi-source, multi-scale feature decoder. The encoder incorporates a multi-branch architecture to separately extract modality-specific features from different MRI sequences. The AFF module fuses information from multiple sources using channel-wise and element-wise attention, ensuring effective feature recalibration. The decoder combines both common and task-specific features through a Task-Specific Feature Introduction (TSFI) strategy, producing accurate segmentation outputs for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET) regions. Comprehensive evaluations on the BraTS2019 and BraTS2020 datasets demonstrate the superiority of multiPI-TransBTS over the state-of-the-art methods. The model consistently achieves better Dice coefficients, Hausdorff distances, and Sensitivity scores, highlighting its effectiveness in addressing the BraTS challenges. Our results also indicate the need for further exploration of the balance between precision and recall in the ET segmentation task. The proposed framework represents a significant advancement in BraTS, with potential implications for improving clinical outcomes for brain tumor patients. © 2025

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A drug recommendation system based on response prediction: Integrating gene expression and K-mer fragmentation of drug SMILES using LightGBM

引用

Intelligence-Based Medicine 2025年 11卷 100206-100206页

作者： Naveed, Sajid Husnain, Mujtaba Department of Computer Science Faculty of Computing The Islamia University of Bahawalpur 63100 Pakistan Department of Software Engineering Faculty of Computing The Islamia University of Bahawalpur 63100 Pakistan

Medical experts and physicians examine the gene expression abnormality in glioblastoma (GBM) cancer patients to identify the drug response. The main objective of this research is to build a machine learning (ML) based model for improve the outcome of cancer medication to save the time and effort of medical practitioners. Developing a drug response recommendation system is our goal that uses the gene expression data of cancer cell lines to predict the response of anticancer drugs in terms of half-maximal inhibitory concentration (IC50). Genetic data from a GBM cancer patient is used as input into a system to predict and recommend the response of multiple anticancer drugs in a particular cancer sample. In this research, we used K-mer molecular fragmentation to process drug SMILES in a novel way, which enabled us to build a competent model that provides drug response. We used the Light Gradient Boosting Machine (LightGBM) regression algorithm and Genomics of Drug Sensitivity of Cancer (GDSC) data for this proposed recommendation system. The results showed that all predicted IC50 values are fall within the range of the real values when examining GBM data. Two drugs, temozolomide and carmustine, were predicted with a Mean Squared Error (MSE) of 0.10 and 0.11 respectively, and 0.41 in unseen test samples. These recommended responses were then verified by expert doctors, who confirmed that the responses to these drugs were very close to the actual response. These recommendation are also effective in slowing the growth of these tumors and improving patients quality of life by monitoring medication effects. © 2025 The Authors

关键词： Drug response recommendation system Drug SMILES Gene expression Glioblastoma K-mer fragmentation LightGBM

来源：评论

学校读者我要写书评

暂无评论

Retrieval-Augmented Generation for Multiple-Choice Questions and Answers Generation

引用

Procedia Computer Science 2025年 259卷 504-511页

作者： Pradeesh N Remya T MG Thushara K Arun Krishna Pranav V Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Omnex Software Solutions Pvt. Ltd Thoraipakkam Chennai India Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

Generating a large volume of diverse questions for educational purposes can be a challenging and time-consuming task for educators. Traditional methods like manually writing questions or using templates often fall short when it comes to variety and relevance. In order to cope with these di ffi culties, we have examined a di ff erent approach adopting Retrieval-Augmented Generation ( RAG). RAG is an enhancement technique that allows retrieving independent documents and combines it with artificial intelligence that is able to qualitatively generate contextually adequate questions. In this research, RAG was employed through the Ample LMS platform in which PDF documents were the source of generating MCQ questions. The results of the research indicate that with this method, the process of formulating the questions is relatively faster and the questions generated are of better and diverse in nature. With RAG, the burden of constructing questions is lessened for teachers and the students are provided with better interactive learning opportunities. This approach presents a better alternative that is flexible and suitable for various educational requirements, demonstrating the e ff ectiveness of AI in the improvement of the learning and teaching processes.

关键词： RAG Education Question Generation LLM

来源：评论

学校读者我要写书评

暂无评论

RAHN: A Reputation Based Hourglass Network for Web Service QoS Prediction

arXiv

引用

arXiv 2025年

作者： Chen, Xia Du, Yugen Tang, Guoxing Luo, Yingwei Ma, Benchi Software Engineering Institute East China Normal University Shanghai200062 China Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China

As the homogenization of Web services becomes more and more common, the difficulty of service recommendation is gradually increasing. How to predict Quality of Service (QoS) more efficiently and accurately becomes an important challenge for service recommendation. Considering the excellent role of reputation and deep learning (DL) techniques in the field of QoS prediction, we propose a reputation and DL based QoS prediction network, RAHN, which contains the Reputation Calculation Module (RCM), the Latent Feature Extraction Module (LFEM), and the QoS Prediction Hourglass Network (QPHN). RCM obtains the user reputation and the service reputation by using a clustering algorithm and a Logit model. LFEM extracts latent features from known information to form an initial latent feature vector. QPHN aggregates latent feature vectors with different scales by using Attention Mechanism, and can be stacked multiple times to obtain the final latent feature vector for prediction. We evaluate RAHN on a real QoS dataset. The experimental results show that the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of RAHN are smaller than the six baseline methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Attention-guided CenterNet deep learning approach for lung cancer detection

引用

Computers in Biology and Medicine 2025年 186卷 109613-109613页

作者： Dawood, Hussain Nawaz, Marriam Ilyas, Muhammad U. Nazir, Tahira Javed, Ali School of Computing Skyline University College Sharjah United Arab Emirates Department of Software Engineering University of Engineering and Technology-Taxila Punjab 47050 Pakistan School of Computer Science University of Birmingham Dubai United Arab Emirates Department of Software Engineering and Computer Science Riphah International University Gulberg Green Campus Islamabad Pakistan

Lung cancer remains a significant health concern worldwide, prompting ongoing research efforts to enhance early detection and diagnosis. Prior studies have identified key challenges in existing approaches, including limitations in feature extraction, interpretability, and computational efficiency. In response, this study introduces a novel deep learning (DL) framework, termed the Improved CenterNet approach, tailored specifically for lung cancer detection. The primary importance of this work lies in its innovative integration of ResNet-34 with an attention mechanism within the CenterNet architecture, addressing critical limitations identified in previous studies. By augmenting the base network with an attention mechanism, our framework offers improved feature extraction capabilities, enabling the model to learn relevant patterns associated with lung cancer amidst complex backgrounds and varying environmental conditions. This enhancement facilitates more accurate and interpretable predictions while reducing computational complexity and inference times. Through extensive experimental evaluations conducted on standard datasets, our proposed approach demonstrates promising results, highlighting its potential to advance the field of lung cancer detection and diagnosis. Specifically, we have acquired the precision, recall, and F1-Score of 99.89 %, 99.82 %, and 99.85 % on the LUNA-16 dataset, and 98.33 %, 98.02 %, and 98.17 % for the Kaggle data sample, respectively which is showing the efficacy of our approach. One limitation of the work is that it cannot effectively locate the samples with intense light variations. Therefore, future research work is focused on overcoming this challenge. © 2024 Elsevier Ltd

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

DRESSING UP LLM: EFFICIENT STYLIZED QUESTION-ANSWERING VIA STYLE SUBSPACE EDITING

arXiv

引用

arXiv 2025年

作者： Ma, Xinyu Xu, Yifeng Lin, Yang Wang, Tianlong Chu, Xu Gao, Xin Zhao, Junfeng Wang, Yasha School of Computer Science Peking University China Center on Frontiers of Computing Studies Peking University China National Research and Engineering Center of Software Engineering Peking University China

We introduce DRESS, a novel approach for generating stylized large language model (LLM) responses through representation editing. Existing methods like prompting and fine-tuning are either insufficient for complex style adaptation or computationally expensive, particularly in tasks like NPC creation or character role-playing. Our approach leverages the over-parameterized nature of LLMs to disentangle a style-relevant subspace within the model’s representation space to conduct representation editing, ensuring a minimal impact on the original semantics. By applying adaptive editing strengths, we dynamically adjust the steering vectors in the style subspace to maintain both stylistic fidelity and semantic integrity. We develop two stylized QA benchmark datasets to validate the effectiveness of DRESS, and the results demonstrate significant improvements compared to baseline methods such as prompting and ITI. In short, DRESS is a lightweight, train-free solution for enhancing LLMs with flexible and effective style control, making it particularly useful for developing stylized conversational agents. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Differential-Trust-Mechanism Based Trade-off Method Between Privacy and Accuracy in Recommender Systems

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 5054-5068页

作者： Xu, Guangquan Feng, Shicheng Xi, Hao Yan, Qingyang Li, Wenshan Wang, Cong Wang, Wei Liu, Shaoying Tian, Zhihong Zheng, Xi Qingdao Huanghai University School of Big Data Qingdao China Tianjin University College of Intelligence and Computing Tianjin300350 China KLISS and School of Software Beijing100084 China Sichuan University School of Cyber Science and Engineering Chengdu610207 China Xi’an Jiaotong University School of Cyber Science and Engineering Xi’an710049 China East China Normal University Shanghai200062 China Hiroshima University School of Informatics and Data Science Higashihiroshima739-8511 Japan Guangzhou University Cyberspace Institute of Advanced Technology Guangdong Key Laboratory of Industrial Control System Security Huangpu Research School of Guangzhou University China Macquarie University School of Computing SydneyNSW2109 Australia

In the era where Web3.0 values data security and privacy, adopting groundbreaking methods to enhance privacy in recommender systems is crucial. Recommender systems need to balance privacy and accuracy, while also having the ability to overcome cold start problems. The Differential Trust Mechanism (DTM) introduced in this paper is such an approach. The DTM provides a unique use of Gaussian distributions in modeling trust relationships within data, offering a novel way to balance recommendation accuracy with user privacy. This mechanism innovatively applies differential privacy principles, using Gaussian noise addition to protect individual user data from inference attacks, while maintaining the integrity and utility of the overall dataset. Unlike traditional anonymization techniques that often compromise data utility or vulnerability to reverse engineering, DTM provides a robust solution by dynamically adjusting privacy levels based on the trustworthiness of data requests. By combining DTM with existing mainstream recommendation algorithms, the prediction accuracy of MAE and RMSE increases by at least 6.60% and 2.69%, respectively. This dual benefit positions DTM as a significant advancement in secure data processing, especially relevant for online businesses and platforms where personalized recommendations are crucial yet privacy concerns are paramount. © 2005-2012 IEEE.

关键词： Sensitive data

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：