检索结果-内蒙古大学图书馆

Advanced UAV - based leaf disease detection: Deep Radial Basis Function Networks with multidimensional mixed attention

引用

Multimedia Tools and Applications 2024年 1-29页

作者： Das, Bappaditya Raghuvanshi, C.S. Research Scholar Department of Computer Science and Engineering FET Rama University Kanpur India Professor Department of Computer Science and Engineering FET Rama University Kanpur India

Plant disease causes a highly significant impact on production due to its destructive characteristics. A variety of chemical techniques should be applied to agriculture at different stages of disease infestation to enable precise plant protection. The integration of unmanned aerial vehicles (UAVs) for obtaining high-resolution images has become necessary due to the growing demand for precision agriculture, making crop health monitoring more efficient. In this study, we developed an innovative approach that combines the Deep Radial Basis Function Network (DRBFN) with the Multidimensional Mixed Attention (MMA) method. Since DRBFNs use radial basis functions as effective feature extractors, the model can detect even the smallest changes in the composition, color, and texture of leaves. This capability is particularly helpful when dealing with a diversity of plant species and pathogens exhibiting different symptoms. By deliberately considering pertinent spatial and spectral attributes, MMA is applied to enhance the discriminatory abilities of the network. By integrating spatial and spectral attention, the network can efficiently acquire information from both local and global sources, thereby enhancing the overall resilience and precision of the detection system. Our proposed model leverages UAV-captured images to achieve a classification accuracy of 96.95% in identifying leaf diseases across two different plant species. The integration of mixed attention mechanisms improved feature representation, leading to a 47.63% reduction in Root Mean Square Error (RMSE) compared to traditional methods. Furthermore, our model demonstrates significant efficiency by processing 2000 images, making it suitable for real-time applications. These results underscore the potential of UAV-based systems combined with advanced deep learning techniques for precision agriculture, offering scalable solutions for early disease detection and management. © The Author(s), under exclusive licence to S

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Twitter sentiment analysis using conditional generative adversarial network

引用

International Journal of Cognitive Computing in Engineering 2024年第1期5卷 161-169页

作者： Mahalakshmi, V. Shenbagavalli, P. Raguvaran, S. Rajakumareswaran, V. Sivaraman, E. Department of Information Technology Sengunthar College of Engineering Tiruchengode Tiruchengode637205 India Assistant Professor Karunya Institute of Technology and Sciences Coimbatore India Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Kanchipuram Chennai Tamil Nadu 603203 India Assistant Professor Department of Computer Science and Design Erode Sengunthar Engineering College Tamil Nadu Thuduppathi India Department of Electrical and Computer Engineering Curtin University Miri Malaysia

Sentiment analysis, which aims to extract information from textual data indicating people's ideas or attitudes about a particular problem, has developed into one of the most exciting study issues in natural language processing (NLP) with the development of social media. Twitter is a social network with an extensive audience that expresses their thoughts and opinions clearly and readily. Due to the prevalence of slang phrases and incorrect spellings in short phrase styles, Twitter data analysis is more challenging than data analysis from other social networks. Automated feature selection still has several limitations, such as higher computing costs that rise with the number of characteristics. Deep learning, which is self-learned and more accurate at processing vast amounts of data, is utilized to overcome these challenges. This paper introduces a conditional generative adversarial network (GAN) for Twitter sentiment analysis, whereas a convolutional neural network (CNN) has been used to extract traits from Twitter data. Compared to existing works, the proposed work has outperformed in accuracy, recall, precision, and F1 score. The suggested method is the most accurate, with a classification accuracy of 93.33 %. © 2024

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Analyzing and predicting banking share dataset using data mining approaches

引用

Multimedia Tools and Applications 2024年 1-16页

作者： Vijayakanth, M. Veeramanikandan, V. Assistant Professor Department Computer Science Thiru Kolanjiappar Govt. Arts College Virdhachalam Tamil Nadu 606 001 India

Data mining is a process of finding and extracting hidden information from a larger dataset. It is used to analyse data patterns in volume of data using one or more data mining techniques. Data mining has applications in multiple fields, like science, engineering, banking, share marketing, and various research fields. A stock market is similarly called a share market. The stock market helps you trade financial instruments and shares of companies and allows trading of shares. Machine learning, within the realm of artificial intelligence (AI), is dedicated to crafting algorithms and models that empower computers to acquire knowledge from data and subsequently make predictions. In this paper, analysis and prediction consider State Bank of India (SBI) shares using different parameters, namely trading date, price, high, low, volume, and changes in share. The analysis and suitable parameters for prediction using supervised machine learning approaches, namely linear regression, random forest, random tree, and REP tree. Numerical illustrations also prove the results and discussions using different parameters. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Iris biometric template identification and recognition scheme using a novel parallel fused encoder

引用

Multimedia Tools and Applications 2024年 1-19页

作者： Vasuki, R. Singh, K. Ranjith Research Scholar Department of Computer Science Karpagam Academy of Higher Education Tamilnadu Coimbatore India Associate Professor Department of Computer Science Karpagam Academy of Higher Education Tamilnadu Coimbatore India

An iris recognition system is considered as an effective biometric model for human authentication. This study proposes an efficient algorithm for recognizing iris regions using a parallel fused encoder. The eye images are first pre-processed using a median filter to remove unwanted noises. Then, Daugman’s algorithm is applied to these pre-processed images to localize and segment the iris portion alone. A novel parallel fused encoder technique is applied over these segmented iris portions to extract unique textural features. The output features are converted into a single vector and processed using sigmoid activation to identify whether the iris images are matched with the dataset or not. The predicted labels from this technique are compared with the original labels for performing an evaluation using Accuracy, F1-Score, Precision, and Recall. The proposed model has been experimented on three different datasets: the Multimedia University Iris Dataset (MMU), the Indian Institute of Technology Dataset (IITD), and the CASIA-IrisV4-Interval datasets. This proposed novel biometric technique showed desirable recognition accuracies of 96.00%, 93.00%, and 98.50% on MMU, IITD, and CASIA-IrisV4-Interval datasets, respectively. The obtained performances are comparatively greater than the existing classifiers used in the published literature. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Possibilities of using nano particles in human urine for transient biometrics

引用

Materials Today: Proceedings 2023年 80卷 2765-2768页

作者： Ambiga, N. Nagarajan, A. Research Scholar Department of Computer Applications Alagappa University Tamilnadu Karaikudi India Assistant Professor Department of Computer Applications Alagappa University Tamilnadu Karaikudi India

The major aspect of this research paper is to investigate the data of Nano particles that exists in human urine The important aspect of this research paper is to study and investigate the Nano Particles present in the human urine to identify or recognise the human .The major use of nanoparticles is its presence in human biological fluid, urine and Blood. It is widely used in cosmetics, personal care, medicine, agriculture, food safety, and pharmacy. The level of the concentration of Nano particles present in human urine is analysed for defining Biometrics. It has raised a growing concern when excess or deficient may cause toxicity because of these Nano particles emerged due to the human beings and Environment. The assessment of Nano particles (size distribution and determination) is becoming a very big challenge to the human beings because of the need of the new and updated analytical instrumentation. The concentration of Nano particles is different to each and every individual. The results obtained from this investigation provides Biometric Authentication which is helpful in identifying a person and also it provides ancillary information to the primary biometrics as soft biometrics and even it can be considered for disease analysis. © 2021

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Statistical assessment of Indian classical music’s role in diabetes, thyroid, hypertension management

引用

International Journal of Information Technology (Singapore) 2025年第1期17卷 423-429页

作者： Pingle, Yogesh Prabhakar Ragha, Lakshmappa K. Research Scholar at Department of Computer Engineering Terna Engineering College Assistant Professor at Department of Computer Science and Engineering (Data Science) Vidyavardhinis College of Engineering and Technology University of Mumbai Maharashtra Mumbai India Department of Computer Engineering Terna Engineering College University of Mumbai Maharashtra Mumbai India

This multi-center randomized controlled trial explores the therapeutic benefits of Indian classical music, specifically “Raga Therapy,” for managing diabetes, thyroid disorders, and hypertension—prevalent global health issues. The study examines how specific Ragas can enhance traditional treatments: Bhimpalas and Chhanayat for hypertension, Malkauns and Bhupal Todi for diabetes, and Shyam Kalyan and Yaman for thyroid disorders. Results show significant health improvements in patients integrating Raga Therapy into their care, highlighting its holistic benefits. The study underscores the profound connection between music and healing, positioning Indian classical music as a valuable complementary therapy. By addressing a critical gap in the literature, it advocates for further research to understand the mechanisms involved and refine Raga selection for optimal therapeutic outcomes. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Paired t-test Patient satisfaction survey Raga Therapy Wilcoxon signed-rank test

来源：评论

学校读者我要写书评

暂无评论

Development and Effectiveness of Dietary Self-care Promotion Program Using Online Community for Hemodialysis Patients: A Pilot Randomized Controlled Trial

引用

Asian Nursing research 2025年第2期19卷 126-135页

作者： Kim, Hana Cho, Mi-Kyoung Assistant Professor/Department of Nursing Science College of Life & Health Sciences Hoseo University South Korea Professor/Department of Nursing Science College of Nursing Research Institute of Nursing Science Chungbuk National University South Korea

Purpose: This study aimed to develop and evaluate a dietary self-care promotion program for hemodialysis patients based on Hurley's self-efficacy model, utilizing an online community to enhance the dietary self-care behavior of patients undergoing hemodialysis. Methods: The needs of hemodialysis patients were identified, and an online community-based dietary self-care promotion program was developed with expert evaluations. Forty-four hemodialysis patients were randomly assigned to an experimental group (n = 22) and a control group (n = 22). The program was applied to the experimental group for four weeks. Before and after the intervention, as well as four weeks after the intervention, dietary self-efficacy, dietary self-care behavior, interdialytic weight gain, serum phosphorus, and serum potassium were assessed in both groups. Results: Significant differences over time and between groups were observed in dietary self-efficacy, interdialytic weight gain, serum phosphorus, and serum potassium. The interaction between time and group was also significant. While no significant differences were found over time in dietary self-care behavior, significant group differences, and interaction effects between time and group were identified. Conclusions: The results indicate that the dietary self-care promotion program using an online community for hemodialysis patients is more effective in enhancing dietary self-efficacy and dietary self-care behavior compared to conventional treatment. This suggests the clinical applicability of the proposed dietary self-care promotion program. Trial registration: This study was registered in the Clinical research Information Service system (No: KCT0007920). © 2025

关键词： diet therapy internet-based intervention renal dialysis self-care self-efficacy

来源：评论

学校读者我要写书评

暂无评论

Selective Text Encryption Using RSA for E-governance Applications for Pdf Document

Selective Text Encryption Using RSA for E-governance Applic...

引用

International Conference on Network Security and Blockchain Technology, ICNSBT 2023

作者： Adhikari, Subhajit Karforma, Sunil Assistant Professor BSH Department Institute of Engineering and Management University of Engineering and Management Kolkata India Research Scholar Department of Computer Science University of Burdwan Burdwan India Faculty Department of Computer Science The University of Burdwan Burdwan India

ISBN: (纸本)9789819944323

When data travels through an insecure medium, security must be enforced. The confidentiality of the exchanged data must be guaranteed with the help of encryption techniques. Selective encryption is a very powerful tool for encrypting textual data in a resource constrained environment. In the context of e-governance, textual data is very important and must be protected from any kind of security threat using selective text encryption. In this paper, a fast and efficient selective encryption technique based on an RSA asymmetric key encoding approach is presented. After fetching the whole textual information in the encryption phase, the user will search for a particular word or phrase using regular expression. After that, the selected data will be encrypted using the RSA-1024-bit algorithm and written to a new encoded document with the remaining text data. In the phase of decoding the data, only the encoded text of the document is considered. The experimental result confirms that the encrypting method is secure in terms of statistical security tests and fast in terms of computation time. Our encoding method can be implemented to encrypt any multimedia data like images, audio, and videos. This proposed technique can be used in IOT devices where resources are limited. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

A hybrid blended stacking disease prediction system based on symptoms

引用

Multimedia Tools and Applications 2025年第7期84卷 3439-3457页

作者： Indupalli, Manjula Rani Pradeepini, G. Research Scholar Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh522 302 India Professor Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh522 302 India

Traditional disease diagnosis methods often struggle with symptoms-based datasets containing categorical data, leading researchers to favor boosting algorithms like CatBoost for their computational efficiency;despite potential limitations in accuracy. To overcome these challenges, this study proposes a novel approach integrating ensemble boosting with traditional naive Bayesian techniques. Recognizing the risk of overfitting with pure ensemble methods, the model strategically blends non-linear models, including XGBoost, to assign weights to symptoms based on disease impact. The blending process, guided by XGBoost decision-making, significantly improves model accuracy compared to single-boost strategies. Preprocessing involves handling categorical data and missing values, enhancing the model's robustness. During the process of blending, the decision of XGBOOST plays an important role. The proposed model's accuracy of "97.2%" is significantly higher than the single-boost strategy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Accuracy Blended stacking CATegorical Boost Ensemble Multi classification Naive Bayesian

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Methodology to Validate Fuzzy Clusters of Big Data 4th

A Novel Ensemble Methodology to Validate Fuzzy Clusters of B...

引用

4th International Conference on Trends in Cognitive Computation Engineering, TCCE 2022

作者： Sardar, Tanvir Habib Sarkar, Rashel Ahmed, Sheik Jamil Bandyopadhyay, Anjan Assistant Professor Department of CSE GITAM School of Technology GITAM University Bangalore India Associate Professor Department of Computer Science University of Science and Technology Meghalaya Ri-Bhoi India Assistant Professor School of Computer Science and Engineering & Information Science Presidency University Bangalore India Assistant Professor Kalinga Institute of Industrial Technology Odisha Bhubaneswar India

ISBN: (纸本)9789811994821

The clustering of datasets is a widely used technique in unsupervised machine learning. The cluster quality evaluation is a tricky problem because external validation is usually not possible for clustering. This happens due to the unavailability of external proof. Although there are many methods developed and experimented with to validate the results obtained from clustering, it is always preferred to use more than a few cluster validity measures. The big data usually contain a high percentage of noise in it, making it necessary to use some additional techniques to incorporate while clustering big data. In this work, we have clustered document big data using fuzzy logic-based enhancement of traditional K-Means and K-Medoids. This work has suggested the Ensembling of seven different cluster quality validity measures to determine the best quality of fuzzy clusters. The Reuters standard document dataset is clustered using different cluster numbers, and the proposed ensemble methodology is proven to determine optimal numbers of clusters. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 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：