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

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

Hybrid RMDL-CNN for speech recognition from unclear speech signal

引用

International Journal of Speech Technology 2025年第1期28卷 195-217页

作者： Bhargava, Raja Arivazhagan, N. Babu, Kunchala Suresh Research Scholar Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering Potti Sriramulu Chaluvadi Mallikarjuna Rao college of Engineering and Technology Andhra Pradesh Vijayawada India

ASR is an effectual approach, which converts human speech into computer actions or text format. It involves extracting and determining the noise feature, the audio model, and the language model. The extraction and determination of the noise feature is a crucial aspect of speech recognition, serving as both a process of information compression and signal deconvolution. ASR schemes are mostly employed in smart homes, smart appliances, and biometric schemes. Yet, traditional approaches offer very low performance because of a noisy environment. Moreover, local differences and accents negatively influence the ASR scheme execution during the conversion of the speech signals. This paper introduces a hybrid RMDL-CNN method to address these challenges. At first, the input of unclear speech is carried out by the dataset. Then, signal pre-processing is done by employing a Gaussian filter. After that, voice enhancement is accomplished by employing nonlinear spectral subtraction. Later, the speech word is segmented from the enhanced output based on the Attentional Encoder-Decoder approach and finally, the speech is recognized using the proposed RMDL-CNN. The RMDL-CNN method is devised by the combination of RMDL and CNN. Furthermore, the established RMDL-CNN is accessed for its efficiency based on several values of k-group value, as well as learning data. In addition, the introduced RMDL-CNN approach for speech recognition achieved better accuracy, PPV, as well as NPV of 0.909, 0.947, and 0.917 for dataset 1. Moreover, the RMDL-CNN has achieved the highest accuracy of 0.909, PPV of 0.926 and NPV of 0.888 for dataset 2. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CAML: Cryptographic-Based Cloud Security for Healthcare Data with Machine Learning Technique

引用

Recent Patents on engineering 2025年第2期19卷 26-40页

作者： M.H, Chaithra Vagdevi, S. Department of Computer Science and Engineering REVA University & Research Scholar Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of AI & ML City Engineering College Karnataka Bangalore India

Background: The Cloud model is one of the most realistic frameworks with a vast range of social networking interactions. In medical data, security is a major constraint as it incorporates information about the patients. The cloud environment subjected to mobility and openness is exposed to security issues and limits authorization levels for data transmission. Objective: This patent paper aims to propose a security model for attack prevention within the healthcare environment. Methods: The proposed Cryptographic Attribute-based Machine Learning (CAML) scheme incorporates three stages. Initially, the homomorphic encryption escrow is performed for secure data transmission in the cloud. Secondly, the information of the users is evaluated based on the consideration of users' authorization. The authorization process for the users is carried out with the attribute-based ECC technique. Finally, the ML model with the classifier is applied for the detection and classification of attacks in the medical network. Results: The detected attack is computed and processed with the CNN model. Simulation analysis is performed for the proposed CAML with conventional ANN, CNN, and RNN models. The simulation analysis of proposed CAML achieves a higher accuracy of 0.96 while conventional SVM, RF, and DT achieve an accuracy of 0.82, 0.89 and 0.93, respectively. Conclusion: With the analysis, it is concluded that the proposed CAML model achieves higher classification accuracy for attack detection and prevention in the cloud computing environment. © 2025 Bentham science Publishers.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image classification using efficientnet-B4 with search and rescue operation algorithm

引用

International Journal of Information Technology (Singapore) 2023年第3期15卷 1473-1479页

作者： Srinivasan, S. Rajakumar, K. Research Scholar School of Computer Science and Engineering VIT University Vellore India School of Computer Science and Engineering VIT University Vellore India

In recent times, a lack of discrimination power in the features produced by traditional machine learning algorithms has resulted in poor classification results. It is also a study topic to find out how to get excellent classification results with limited samples without getting overfitting issues in hyperspectral images (HSIs). These issues can be addressed by utilising a new learning network structure developed in this study. EfficientNet-B4-Based Convolutional network (EN-B4), which is why it is critical to maintain a constant ratio between the dimensions of network resolution, width, and depth in order to achieve a balance. The weight of the proposed model is optimized by Search and Rescue Operations (SRO), which is inspired by the explorations carried out by humans during search and rescue processes. Tests were conducted on two datasets to verify the efficacy of EN-B4, with Indian Pines (IP) and the University of Pavia (UP) dataset. Experiments show that EN-B4 outperforms other state-of-the-art approaches in terms of classification accuracy. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Deep Learning EfficientNet-B4 Features Learning Rate Overfitting Search and Rescue Operation

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

A systematic review of deep learning and machine learning tools for predicting and classifying pediatric genetic disorders 4th

A systematic review of deep learning and machine learning to...

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Ishdeep Gagandeep Research Scholar Computer Science and Engineering IK Gujral Punjab Technical University Punjab Kapurthala India Punjab India

ISBN: (纸本)9781032911571

There are various hurdles in the field of Genetic ailments in children, particularly in the realms of timely identification and management. Conventional diagnostic techniques often encounter obstacles such as protracted methods and resource-demanding procedures, hampering timely diagnosis and treatment. This paper investigates the Capability of advanced computing, specifically machine learning and deep learning techniques, to address these challenges. By harnessing available AI (Artificial Intelligence) technologies, scholars and scientists aim to enhance the effectiveness and precision of paediatric genetic healthcare, ultimately enhancing outcomes for children with genetic disorders. Through a comprehensive review of existing literature, this paper review investigates the state-of-the-art AI techniques employed in the prediction and classification of pediatric genetic disorders. Despite challenges such as data availability and algorithm validation, AI presents promising opportunities for revolutionizing paediatric genetic healthcare, paving the way for prompt detection, personalized therapy, and improved recipients outcomes. © 2025 the Author(s).

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach for Segmentation and Classification of Brain Tumor Cells 7th

A Machine Learning Approach for Segmentation and Classificat...

引用

7th International Conference on Intelligent Technologies, ICIT 2022

作者： Goyal, Nandita Trivedi, Munesh C. Choudhary, Chinu Mog Saluja, Sonam Research Scholar AKTU Lucknow Lucknow India Department of Computer Science and Engineering NIT Agartala Agartala India Department of Computer Science and Engineering TIT Agartala Agartala India Research Scholar NIT Agartala Agartala India

ISBN: (纸本)9789819919116

Diagnosis of any chronic disease at an early stage can improve effective response to medical intervention and increase chances of survival among patients. The greater part of the individuals neglects to recognize their disease before it becomes severe. Brain tumor is one of such disease which can be cured effectively if diagnosed early. Brain tumors are highly similar in appearance and there is a comparability among tumor shapes and typical tissues. Along these lines the extraction of tumor locales from image becomes highly complex. The medical specialist may analyze the tumors erroneously because of these distortions and complexities. Consequently, line of treatment is vital to improve the personal satisfaction of patients. By and large, different imaging strategies, for example, Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and ultrasound scans are utilized to assess the tumor in a breast, lung, liver, brain and other parts of human body. In this work we will use MRI images data. Our major focus will be brain tumor segmentation and classification using Convolutional Neural Network (CNN) from multi-contrast Magnetic Resonance Images. This work focuses on investigation of the concept and approach for applying artificial intelligence and machine learning algorithms in the field of brain tumor segmentation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Levy Flight Adopted Particle Swarm Optimization-based Resource Allocation Strategy in Fog Computing

引用

Chinese Journal of Electronics 2023年

作者： Sharmila Patil(Karpe) Brahmananda S H Research Scholar Department of Computer Science and Engineering GITAM School of Technology GITAM Deemed University Professor Department of Computer Science and Engineering GITAM Bengaluru

The prevalence of the Internet of Things(Io T) is unsteady in the context of cloud computing, it is difficult to identify fog and cloud resource scheduling policies that will satisfy users’ Qo S need. As a result, it increases the efficiency of resource usage and boosts user and resource supplier profit. This research intends to introduce a novel strategy for computing fog via emergencyoriented resource allotment, which aims and determines the effective process under different parameters. The modeling of a non-linear functionality that is subjected to an objective function and incorporates needs or factors like Service response rate, Execution efficiency, and Reboot rate allows for the resource allocation of cloud to fog computing in this work. Apart from this, the proposed system considers the resource allocation in emergency priority situations that must cope-up with the immediate resource allocation as well. Security in resource allocation is also taken into consideration with this strategy. Thus the multi-objective function considers 3 objectives such as Service response rate, Execution efficiency, and Reboot rate. All these strategies in resource allocation are fulfilled by Levy Flight adopted Particle Swarm Optimization(LF-PSO). The evaluation is performed to determine whether the developed strategy is superior to numerous traditional schemes. The cost function attained by the adopted technique is 120, which is 19.17%, 5%, and 2.5%greater than the conventional schemes like GWSO, EHO,and PSO, when the number of iterations is 50.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prevention of soil erosion, prediction soil NPK and Moisture for protecting structural deformities in Mining area using fog assisted Smart agriculture system 2

Prevention of soil erosion, prediction soil NPK and Moisture...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Mohanty, Surajit Pani, Subhendu Kumar Tripathy, Niva Rout, Raghunath Acharya, Mousumi Raut, Prakash Kumar Research Scholar Computer Science and Engineering Biju Patnaik University of Technology Odisha Rourkela India Krupajal Computer Academy Odisha India Cuttack India

A new idea called "smart agriculture" enables farms to be managed using cutting-edge technology like IoT, AI, robotics, drones, etc. The goal is to maximize the use of the resources at hand while producing more crops of higher quality and quantity. Crop output growth is mostly dependent on the fertility and moisture content of the soil. In the past, different fertilizers were added to the soil to boost its nutrients, but this process took time and labour from humans. Subsequently, as technology advanced, the data gathered from IoT devices was processed via cloud computing. Fog computing provides a solution to the significant latency associated with cloud server location that is remote. The main goal of this research is to create a fog-assisted recommendation model that can be applied to the future prediction of soil moisture content and NPK. When combined with agricultural systems, machine learning algorithms provide a proactive, data-driven method for maximizing resource management and soil health. It offers a succinct overview of how to forecast crop growth through the use of hybrid machine learning algorithms on the IFogsim platform to enhance soil quality and irrigation efficiency. Moreover, it lessens soil erosion and increases soil stability. In the mining sector, the suggested technique is helpful for protecting against structural deformities and stabilizing slopes. © 2024 Elsevier B.V.. All rights reserved.

关键词： Fog

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：