检索结果-内蒙古大学图书馆

A novel approach for image retrieval in remote sensing using vision-language-based image caption generation

Multimedia Tools and Applications 2025年第6期84卷 2985-3014页

作者： Yadav, Prem Shanker Tyagi, Dinesh Kumar Vipparthi, Santosh Kumar Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India School of Artificial Intelligence and Data Engineering Indian Institute of Technology Ropar Punjab Rupnagar140001 India

Recent advancements in satellite technologies have resulted in the emergence of Remote Sensing (RS) images. Hence, the primary imperative research domain is designing a precise retrieval model for retrieving the most pertinent images based on the query. Present Remote Sensing Image Retrieval (RSIR) systems use visual descriptors to characterize the primitives (such as various land-cover types) that are visible in the images. However, the visual descriptors are inadequate for defining the complicated content of RS images. To solve this problem, a new model is devised for image retrieval based on image captions. The goal is to generate textual illustrations with captions to define relations amongst objects precisely. Here, image captioning is attained based on the vision-language pre-training model. The image captions are utilized for generating features like term frequency-inverse document frequency (TF-IDF), length of text, and Bag of Words. Meanwhile, query text is utilized wherein features like TF-IDF, text length, and Bag of Words are obtained. The similarity between query text features and the image captions features has been computed on the basis of a hybrid similarity measure wherein weights are tuned with the proposed Honey Badger Political Optimizer (HBPO) to retrieve the image. The proposed HBPO provided enhanced efficiency with elevated precision of 93.3%, recall of 93.7%, F1-score of 93.5%, and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) of 0.441. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

PDNet: A Novel Approach to Plant Disease Detection using CNN and Keras 6

PDNet: A Novel Approach to Plant Disease Detection using CNN...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Jain, Garima Shukla, Amita Chaudhary, Anamika Sharma, Nidhi Bisht, Sovers Singh Jain, Ankush Department of Computer Science and Buisness Systems Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Greater Noida India Department of Data Science Noida Institute of Engineering and Technology Delhi India Department of Computer Science and Engineering Netaji Subhas University of Technology Delhi India

ISBN: (纸本)9798331522667

This research addresses the pressing global demand for food by leveraging cutting-edge deep learning techniques for automating plant disease detection. Focusing on tomato and potato leaf diseases, the study utilized the PlantVillage dataset to compare classical machine learning methods, such as Local Binary Patterns (LBP) combined with classifiers like kNN, SVM, and Extreme Learning Machines, against modern Convolutional Neural Network (CNN) architectures. These included MobileNet, DenseNet201, ResNet50, Inception V3, and VGG16/19. A custom-designed CNN model was developed with unique configurations implemented using Keras and TensorFlow. The model was tested for binary, 6-class, and 10-class classifications, achieving remarkable accuracy rates of 99.6%, 98.4%, and 97.2%, respectively. Notably, after 50 training epochs, the model achieved a peak accuracy of 99.78% for plant disease classification. A practical web-based application was also developed, integrating the best-performing model to facilitate real-time leaf disease detection and notify farmers via email. This approach demonstrates a significant advancement in sustainable agriculture by providing an efficient, accurate, and scalable solution for early disease detection, which is critical for improving crop yield and productivity. © 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

Advancing Sentiment Analysis for Low-Resource Languages Using Fine-Tuned LLMs: A Case Study of Customer Reviews in Turkish Language

引用

IEEE Access 2025年 13卷 77382-77394页

作者： Kiziltepe, Rukiye Savran Ezin, Ercan Yentür, Ömer Basbrain, Arwa M. Karakus, Murat Ankara University Department of Software Engineering Ankara06100 Turkey Harran University Department of Computer Engineering Şanlıurfa63200 Turkey Software Solutions-Data Security and Data Management Kron Technology İstanbul34467 Turkey King Abdulaziz University Department of Computer Science Jeddah21589 Saudi Arabia

This study investigates the application of advanced fine-tuned Large Language Models (LLMs) for Turkish Sentiment Analysis (SA), focusing on e-commerce product reviews. Our research utilizes four open-source Turkish SA datasets: Turkish Sentiment Analysis version 1 (TRSAv1), Vitamins and Supplements Customer Review (VSCR), Turkish Sentiment Analysis dataset (TSAD), and TR Customer Review (TRCR). While these datasets were initially labeled based on star ratings, we implemented a comprehensive relabeling process using state-of-the-art LLMs to enhance data quality. To ensure reliable annotations, we first conducted a comparative analysis of different LLMs using the Cohen’s Kappa agreement metric, which led to the selection of ChatGPT-4o-mini as the best-performing model for dataset annotation. Our methodology then focuses on evaluating the SA capabilities of leading instruction-tuned LLMs through a comparative analysis of zero-shot models and Low-Rank Adaptation (LoRA) fine-tuned LlaMA-3.2-1B-IT and Gemma-2-2B-IT models. Evaluations were conducted on both in-domain and out-domain test sets derived from the original star-ratings-based labels and the newly generated GPT labels. The results demonstrate that our fine-tuned models outperformed leading commercial LLMs by 6% in both in-domain and out-domain evaluations. Notably, models fine-tuned on GPT-generated labels achieved superior performance, with in-domain and out-domain F1-scores reaching 0.912 and 0.9184, respectively. These findings underscore the transformative potential of combining LLM relabeling with LoRA fine-tuning for optimizing SA, demonstrating robust performance across diverse datasets and domains. © 2013 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Evaluation of convolutional neural network models’ performance for estimating mango crop yield

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2025年第1期9卷 1-18页

作者： Neethi, M.V. Raviraj, P. Department of Computer Science and Engineering-Data Science ATME College of Engineering Affiliated to Visvesvaraya Technological University (VTU) Belagavi India Department of Computer Science and Engineering GSSS Institute of Engineering and Technology for Women Affiliated to Visvesvaraya Technological University (VTU) Belagavi India

In agriculture, crop yield estimation is essential;producers, industrialists, and consumers all benefit from knowing the early yield. Manual mango counting typically involves the utilization of human labor. Experts visually examine each sample to complete the process, which is time-consuming, difficult, and lacks precision. For commercial mango production to produce high-quality fruits from the orchard to the consumer, a quick, non-destructive, and accurate variety classification is required. Because of its effectiveness in computer vision, a convolutional neural network—one of the deep learning techniques—was chosen for this investigation. For yield prediction, a total of eight popular mango cultivars were utilized. A comparison with previously trained models was used to assess the proposed model. The performance of the classifiers was evaluated using evaluation metrics such as accuracy, loss, area under the receiver operating characteristic curve score, precision, recall, F1-score, sensitivity, specificity, positive predictive value, negative predictive value, and Cohen’s Kappa performance measure. In terms of performance evaluation criteria, it was found that the proposed approach outperformed the pre-trained models. The suggested model achieved 98.85% accuracy in the test set, which had 800 images. This outcome demonstrates the tangible applicability of the proposed methodology for mango crop estimation. © (2025), (Society of Sytematic Innovation). All rights reserved.

关键词： Convolutional Neural Networks Deep Learning Early Detection Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Guitar Chord Recognition Using Spectrogram-Based Feature Extraction and AlexNet Architecture for Categorization

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 758-767页

作者： Korade, Nilesh B. Salunke, Mahendra B. Bhosle, Amol A. Sangve, Sunil M. Joshi, Dhanashri M. Asalkar, Gayatri G. Kadu, Sujata R. Sarwade, Jayesh M. Department of Computer Engineering JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India Department of Computer Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune412101 India Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Bibwewadi Pune411037 India Department of Computer Engineering Terna Engineering College Maharashtra Mumbai India Department of Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Chord prediction plays a key role in the advancement of musical technological innovations, such as automatic music transcription, real-time music tutoring, and intelligent composition tools. Accurate chord prediction can assist musicians, educators, and developers in constructing tools that help in learning, playing, and composing music. Background noise and audio distortions may have an impact on chord prediction accuracy, particularly in real-world situations. Chords can have distinct voicings or finger positions on the guitar, resulting in slight variations in audio representation. This study focuses on the classification of guitar chords using techniques of deep learning. There are eight major and minor guitar chords in the dataset. They have been turned into spectrograms, chromagrams, and Mel Frequency Cepstral Coefficients (MFCC) so that features can be extracted. Various deep learning architectures, including CNN, ResNet50, AlexNet, and VGG, were employed to classify the chords. Experimental results demonstrated that the spectrogram-based AlexNet model outperforms others, achieving good accuracy and robustness in chord classification. The proposed study demonstrates the efficiency of spectrograms and advanced deep learning models for audio signal processing in music applications. By automating chord detection, this study provides beneficial resources for music learners as well as educators, enabling more efficient learning and real-time feedback during practice sessions. © (2025), (Science and Information Organization). 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

Deep ensemble optimal classifier-based software defect prediction for early detection and quality assurance

引用

Journal of Umm Al-Qura University for engineering and Architecture 2025年 1-12页

作者： Srinivas, Kalyanapu Janapati, Krishna Chaithanya Sai Kiran, Mungalched Sudheer Reddy, Davu Vinay, Thota Vamshi Yashwanth, Choula Department of Computer Science and Engineering Dhanekula Institute of Engineering and Technology Andhra Pradesh Vijayawada India Department of Electronics and Communication Engineering Vardhaman College of Engineering Telangana Hyderabad India Department of Computer Science and Engineering (Data Science) Malla Reddy Engineering College and Management Sciences Medchal Telangana Kistapur India

Software Defect Prediction (SDP) is critical in identifying fault-prone modules during the software development life cycle, enhancing software quality, and reducing maintenance costs. However, existing SDP models face significant challenges, including high false positive rates and severe class imbalance between defect-prone and non-defect modules, which hinder practical model training and accurate defect detection. To overcome these challenges, this study proposes a robust and efficient SDP architecture that integrates several advanced techniques to enhance predictive accuracy and model reliability. The methodology begins with comprehensive data preprocessing, incorporating normalization to standardize feature scales and outlier detection to eliminate noise and improve data quality. To address the inherent class imbalance in the dataset, the minority oversampling by synthetic data (MOSD) technique is employed to generate synthetic samples for the minority class, thus achieving a more balanced distribution. Following this, an Adaptive sequential K-best (ASKB) feature selection strategy is implemented to identify and retain the most relevant features, effectively reducing dimensionality while preserving critical information. Finally, the weighted random forest (WRF) classifier is utilized, which assigns appropriate weights to training instances, enabling improved classification performance, especially for minority class instances. The proposed methodology achieved an accuracy of 99.119%, a precision of 99.431%, a recall of 99.122%, and an F1-score of 99.333%. © The Author(s) 2025.

关键词： Adaptive sequential K-best Class imbalance data preprocessing Feature selection Minority oversampling Predictive modeling Software defect prediction Synthetic data Weighted random forest

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Deep Learning Based Method for Abnormality Detection in Videos 1

Semi-Supervised Deep Learning Based Method for Abnormality D...

引用

1st International Conference on Advances in computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Chaudhary, Deevesh Kumar, Sunil Dhaka, Vijaypal Singh Manipal University Jaipur Department of Data Science and Engineering Jaipur India Manipal University Jaipur Department of Computer Communication and Engineering Jaipur India

ISBN: (纸本)9798331518578

Anomaly detection refers to recognition of events different from normal ones for example road accident, fight, robbery, arsenal etc. Anomaly identification in real world surveillance videos is an important application of computer vision. The work proposed in the paper detects anomalous events in surveillance videos dataset and is based upon semi supervised deep learning model. We trained the model using UCF Crime dataset that consists of 950 normal videos and 950 anomalous videos. The anomaly videos in the dataset consists of 13 different types of anomalies such as Abuse, arrest, explosion, fight etc. that generally occur in real life. The anomaly in the dataset is labelled at video level and not at a specific frame in a video to define the semi supervised nature of learning paradigm. The extracted 3D features from dataset are fed into the multilayered deep learning model. Experimental results show that our approach has significant improvement over state-of-the-art approaches for anomaly detection in surveillance videos. The accuracy of model comes out to be 83.96 percent, that is improvement over other methods. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

data Orchestration Platform for AI Workflows Execution Across Computing Continuum 15

Data Orchestration Platform for AI Workflows Execution Acros...

引用

15th International Conference on Cloud Computing and Services Science, CLOSER 2025

作者： Arcas, Gabriel Ioan Cioara, Tudor Engineering and Data Solutions Department Bosch Engineering Center Cluj-Napoca Romania Computer Science Department Technical University of Cluj Napoca Romania

ISBN: (纸本)9789897587474

Cloud AI technologies have emerged to exploit the vast amount of data produced by digitized activities. However, despite these advancements, they still face challenges in several areas, including data processing, achieving fast response times, and reducing latency. This paper proposes a data orchestration platform for AI workflows, considering the computing continuum setup. The edge layer of the platform focuses on immediate data collection, the fog layer provides intermediate processing, and the cloud layer manages long-term storage and complex data analysis. The orchestration platform incorporates the Lambda Architecture principles for flexibility in managing batch processing and real-time data streams, enabling effective management of large data volumes for AI workflows. The platform was used to manage an AI workflow dealing with the prediction of household energy consumption, showcasing how each layer supports different stages of the machine learning pipeline. The results are promising the models are being trained, validated, and deployed effectively, with reduced latency and use of computational resources. Copyright © 2025 by SCITEPRESS - Science and Technology Publications, Lda.

关键词： data streams

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Xi’an710049 China Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China Peking University School of Computer Science Beijing100871 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University Xi'an710049 China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports 3.12x more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

A Hybrid EKF/WUFIR Filter for Indoor Localization Integrating INS and UWB data

引用

IEEE Transactions on Network Science and engineering 2025年第3期12卷 2266-2276页

作者： Cheng, Long Song, Jiahe Zhao, Wenhao Northeastern University Department of Computer and Communication Engineering Qinhuangdao066004 China Northeastern University Hebei Key Laboratory of Marine Perception Network and Data Processing Qinhuangdao066004 China

Due to the complex and variable indoor environment, ultra-wideband (UWB) signal transmission is often obstructed by walls and obstacles, resulting in non-line-of-sight (NLOS), which reduces localization accuracy. Inertial navigation system (INS) is an autonomous navigation system that does not rely on external information and is not affected by NLOS. Therefore, a hybrid EKF/WUFIR filter indoor localization algorithm that integrates INS and UWB data is proposed. The proposed algorithm is composed of three parts: INS localization, UWB localization and data fusion. In the INS localization part, the motion model is used to determine the state of the target in real time using measurement data obtained from the inertial measurement unit (IMU). In the UWB localization part, a resettable residual weighted particle filter algorithm is proposed to mitigate the effect of NLOS on the localization results. In the data fusion part, a hybrid filtering algorithm combining extended Kalman filter (EKF) and weighted unbiased finite impulse response (WUFIR) filtering is proposed to fuse the INS and UWB localization data. Simulation and experimental results show that the proposed algorithm outperforms other comparative algorithms in terms of robustness and localization accuracy. © 2013 IEEE.

关键词： Inertial navigation systems

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：