检索结果-内蒙古大学图书馆

LightDD: A lightweight model for disaster detection from aerial imagery

Multimedia Tools and Applications 2025年 1-25页

作者： Gaur, Samta Kumar, J. Sathish Department of Computer Science and Engineering MNNIT Allahabad UP Prayagraj211004 India

Natural disasters disrupt both human habitats and vital infrastructures, leading to significant damage and sometimes permanent alterations to the environment. Such disasters can arise from diverse natural phenomena, such as earthquakes, cyclones, floods and wildfires. Despite various efforts by researchers to use Deep Learning (DL) for disaster identification and classification, the complexity and imbalance of image data present ongoing challenges. In response to these challenges, a new LightDD (Lightweight Deep Disaster Detection) model is proposed to streamlined deep Convolutional Neural Network (CNN) tailored for disaster detection. Notably, the proposed LightDD model is lightweight, comprising just 0.11 million parameters. The model is divided into two main segments: the first employs three convolutional modules for feature extraction, with filters sizes in descending order (128, 64, and 32), capped by average global pooling. This configuration allows the model to extract complex features using high-level filters and efficiently condense them in subsequent layers, preserving a rich feature representation while reducing the overall number of parameters. The second segment is dedicated to disaster classification and consists of a singular module of fully connected layers. The LightDD model was evaluated on a disaster dataset, achieving an accuracy rate of 91.44%. © 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

Explainable AI for Pancreatic Cancer Prediction and Survival Prognosis: An Interpretable Deep Learning and Machine Learning Approach

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第4期48卷 623-640页

作者： Srinidhi, B. Bhargavi, M.S. Department of Computer Science and Engineering Bangalore Institute of Technology Bengaluru India

Pancreatic cancer's devastating impact and low survival rates call for improved detection methods. While Artificial Intelligence has shown remarkable progress, its increasing complexity has led to "black box" models, hindering their acceptance in critical fields like healthcare. To address this, Explainable Artificial Intelligence (XAI) has gained traction, aiming to create transparent AI systems. In this study, we propose a comprehensive approach that combines the power of Deep Learning for pancreatic cancer detection using Computed Tomography (CT) images and Machine Learning (ML) for survival prognosis based on clinical data. By leveraging CT images with Deep learning models such as Convolutional Neural Networks, VGG-16 and DenseNet-201, effective diagnosis of Pancreatic Cancer is achieved and comprehensive insights into the tumor's spatial characteristics are obtained. DenseNet-201 outperformed the other models in terms of accuracy and interpretability with a predictive accuracy of 95%. The integration of ML techniques such as Stochastic Gradient Descent, Naïve Bayes and Extra Tree classifiers with clinical data predicts the chances of survival, providing vital information for treatment planning and personalized care. To validate the model's accuracy and interpretability, a comprehensive XAI validation is conducted using state-of-the-art techniques like Local Interpretable Model-agnostic Explanations and Shapley Additive Explanations. These methods provide localized explanations for predictions, allowing clinicians to understand risk and survival chances. This study holds immense potential to aid healthcare professionals in diagnosis, prognosis, and personalized treatment strategies, contributing to enhanced patient outcomes in the fight against pancreatic cancer. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A novel cluster based reliable security enhancement in FANET directed by game theory

引用

Soft Computing 2025年第2期29卷 1091-1106页

作者： Gupta, Shikha Sharma, Neetu Department of Computer Science Engineering College Ajmer Rajasthan Ajmer305001 India

The emergence of interconnected UAVs has given rise to the creation of flying ad hoc networks (FANETs) aimed at efficiently facilitating network-dependent services. However, FANET encountered considerable challenges in achieving reliability due to security issues influenced by the existence of malicious nodes. These nodes continuously engage in communication and present a significant threat. These issues are precisely addressed in this article by introducing a novel methodology enhancing network security through a game theory-driven decision tree approach. The proposed strategy involves the implementation of a cluster mechanism based on path similarity techniques. Additionally, an optimized strategy put forth to minimize cluster overhead. Comparing with state-of-the-art protocols in identifying malicious nodes within the network, the results indicate a notable enhancement averaging at 52.84%. Moreover, in aspects such as delay reduction, precision rate increase, and message drop minimization, the experimental outcomes exhibit average improvements of 42.17%, 65.24%, and 46.63%, respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

ImageNet Classification Using WordNet Hierarchy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1718-1727页

作者： Chatterjee, Ankita Mukherjee, Jayanta Das, Partha Pratim Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India Ashoka University Department of Computer Science Sonipat131029 India

Convolutional neural networks (ConvNets) have become increasingly popular for image classification tasks. All contemporary computer vision problems are being dominated by ConvNets. Conventional training methods using cross-entropy loss for training have constantly outperformed the state-of-the-art technique to set a new standard in the ImageNet classification challenge. However, growing accuracy come at the cost of enormous number of parameters and computations. Further, classical learning algorithms do not utilize the semantic relationship between the classes present in the dataset. Thus, interpreting the behavior of the model become difficult even though the results may be desirable. Hence, we demonstrate a classification method by leveraging the WordNet hierarchy on the ImageNet dataset to establish class relationships and label embedding. The model is trained using cross entropy with soft labels based on the semantic similarity between the generated output and the ground truth. Unlike categorical cross entropy, it does not treat every predicted label as equally erroneous. The method generates meaningful neighboring classes in the feature space of the true label. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Autism spectrum disorder based on squeezenet with fractional tasmanian rat swarm optimization

引用

Multimedia Tools and Applications 2024年第41期83卷 89029-89054页

作者： Muppidi, Satish Anuradha, G. Valarmathi, K. Department of Computer Science and Engineering GMR Institute of Technology Andhra Pradesh Rajam India Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Vijayawada Kanuru India Department of Computer Science and Engineering Panimalar Engineering College Bangalore Trunk Road Chennai Pooñamallee600123 India

A complicated neuro-developmental disorder called Autism Spectrum Disorder (ASD) is abnormal activities related to brain development. ASD generally affects the physical impression of the face as well as the growth of the brain in children. An early and proper medical diagnosis is essential for ASD affected children to enhance their quality of life. However, the clinical detection of ASD is a difficult task and time-consuming, hence it is essential to design an ASD detection approach for precise diagnosis of ASD children. In this research, an algorithmic approach called Fractional Tasmanian Rat Swarm Optimization driven SqueezeNet (FTRSO-SqueezeNet) is designed for the detection of ASD. The median filter and Region of Interest (RoI) extraction are used to de-noise the input image initially and extract a particular region from the filtered image. Later, the nub regions are extracted by choosing the optimal grid from the pre-processed image and using different feature extractors the features from the input images are determined. Finally, the detection of ASD is done by using SqueezeNet, which is trained using the FTRSO approach. The performance of the method is estimated, where the designed model achieved higher performance with an accuracy of 94.55%, sensitivity of 92.53%, and specificity of 95.22% than other prevailing approaches. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Efficacy of Ensemble Learning Method over Individual Classifier for Rainfall Forecasting in Eastern India

引用

Journal of The Institution of Engineers (India): Series B 2024年第4期105卷 929-939页

作者： Karmakar, Rahul Kundu, Saranagta Biswas, Saroj Kumar Tripathi, Deeksha Department of Computer Science The University of Burdwan West Bengal Bardhaman India Department of Computer Science and Engineering National Institute of Technology Assam Silchar India

Severe rainfall has seriously threatened human health and survival. Natural catastrophes such as floods, droughts, and many other natural disasters are caused by heavy rains, which people worldwide have to deal with throughout the year. Accurate rainfall forecasting is essential in nations like India where cultivation is the main occupation. Machine learning (ML) techniques are more effective than many other strategies because of the unpredictable nature of rainfall. Ensemble learning (EL) methods yield higher accuracy than ML specific classifiers. Therefore, this paper proposes an EL-based prediction model for not only a specific state of India but for the entire eastern India region, which includes ten states: West Bengal, Jharkhand, Bihar, Odisha, Assam, Tripura, Mizoram, Manipur, Nagaland and Meghalaya. We acquired the rainfall data for eastern India using NASA’s power data access view for 22 years (2000–2021). In this model, apart from classification feature selection is done using Pearson correlation and ANOVA. This study looks at the accuracy of several different classifiers, including DT, LR, and SVM. The acceptable accuracy of 96.53% for rainfall prediction in eastern India was determined using an ensemble model that includes the XGBoost ensemble technique and the classifiers DT, LR, and SVM. The findings of our experiment reveal that EL-based prediction model outperforms the individual classifiers utilized in the experiment. © The Institution of Engineers (India) 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Content Caching Algorithms in Drone-Aided Ad Hoc Networks

引用

computers, Materials & Continua 2024年第12期81卷 4727-4742页

作者： Yong Beom Park Jian Kim Beom Kyu Suh Ismatov Akobir Ki-Il Kim Department of Computer Science and Engineering Chungnam National UniversityDaejeon34134Republic of Korea

Content delivery networks(CDNs)lead to fast content distribution through content caching at specific CDN servers near end ***,existing CDNs based on infrastructure cannot be employed in special cases,such as military ***,a temporary CDN without an existing infrastructure is *** achieve this goal,we introduce a new CDN for drone-aided ad hoc networks,whereby multiple drones form ad hoc networks and quickly store specific content according to new caching *** the typical CDN server,the content-caching algorithm in the proposed architecture considers the limited storage capacity of the *** present three content distribution algorithms that consider the constraints and mobility of *** main contribution of content caching for drone-aided ad hoc networks is to keep partial segments rather than whole content as well as move the drone near to area with a high volume of *** proposed scheme is evaluated to demonstrate its feasibility in terms of content acquisition time and utilization in several practical scenarios through ***,acquisition time in CDN to support drone movement is improved by approximately 50%and 40%rather than one in the proposed naive greedy approach as a function of content request interval and size,respectively.

关键词： Content delivery networks content caching unmanned aerial networks Ad hoc networks partial segment duplicated contents drone

来源：评论

学校读者我要写书评

暂无评论

L3Buddy: a location-aware academic content-recommendation system through machine learning based cache techniques

引用

Multimedia Tools and Applications 2025年第5期84卷 2633-2649页

作者： Guddadmani, Ashwini Chougale, Supriya Gokanvi, Megha Tapale, Manisha Pattar, Santosh Department of Computer Science and Engineering KLE Technological University Belagavi Campus India

At present, recommendation systems have become pivotal in personalized education learning management systems, where there is a growing need for location-based suggestions. Our problem addresses the inefficiency of current systems in integrating real-time location data, leading to latency and irrelevant content delivery. We propose L3Buddy, a context-aware system leveraging machine learning for location-specific video recommendations. This approach enhances accuracy and reduces latency, improving the user experience by delivering timely, relevant content. Our results demonstrate significant improvements in both recommendation precision and system responsiveness. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep feature-support vector machine based hybrid model for multi-crop leaf disease identification in Corn, Rice, and Wheat

引用

Multimedia Tools and Applications 2025年第8期84卷 4751-4771页

作者： Bhola, Amit Kumar, Prabhat Department of Computer Science and Engineering National Institute of Technology Patna Bihar India

Corn, Rice, and Wheat serve as primary staple foods globally, playing a pivotal role in the economies of numerous countries. Despite their paramount importance, these cereal crops face susceptibility to various diseases, posing a significant threat to production. Timely and accurate disease diagnosis is imperative to mitigate these risks. In response, a range of Machine Learning (ML) and Deep Learning (DL) models have been devised to automate the identification of diseases impacting cereal crops. While DL excels with abundant data, traditional ML may outperform DL with limited data. This study proposes a hybrid model integrating deep transfer learning and ML techniques for identifying crop diseases. The model utilizes pre-trained DenseNet201 weights to extract features, which are subsequently fed into a Support Vector Machine (SVM) for identification. Experimental results show that the hybrid model outperforms several benchmark counterparts. The DenseNet201 deep feature combined with SVM exhibits superior performance, achieving an impressive accuracy score of 87.23% with just 20.2M parameters. The model underwent comprehensive performance assessment using precision, recall, F1 score, and overall accuracy metrics. It effectively classifies healthy and diseased categories for each crop, achieving accuracies of 99.82%, 98.75%, and 84.15% for Corn, Wheat, and Rice, respectively. Moreover, the model’s remarkable performance and lightweight nature make it a practical and efficient real-time crop disease detection solution, emphasizing its relevance and significance for farmers and researchers in the agricultural community. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Comprehensive overview of Alzheimer's disease utilizing Machine Learning approaches

引用

Multimedia Tools and Applications 2024年第37期83卷 85277-85329页

作者： Kumar, Rahul Azad, Chandrashekhar Department of Computer Science and Engineering National Institute of Technology Jamshedpur India

Alzheimer's disease is a common and complex brain disorder that primarily affects the elderly. Because it is progressing and has few effective therapies, it requires a thorough understanding of the condition;our study offers a comprehensive analysis of AD with a dual approach that combines both bibliometric and experimental analyses. The bibliometric analysis applies statistical and mathematical techniques to figure out the states of AD research, including publishing trends, prestigious journals, and collaborative networks. Concurrently, the experimental examination explores current advancements, focusing on Machine Learning, Deep Learning, and Metaheuristic approaches, tackling complex issues resulting from varied datasets. The experimental work is fascinating because it uses twenty classifiers and two datasets, initially without feature selection and then with seven feature selection techniques. This thorough investigation focuses on developments in disease processes, therapeutic approaches, and diagnostic tool development. This research offers a multidimensional overview of Alzheimer's disease by combining bibliometric and experimental methods, addressing problems and highlighting the shortcomings of earlier studies. By helping academics, policymakers, and healthcare professionals navigate the complexities of AD, this novel methodology advances a more thorough understanding of the Alzheimer's disease domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Speech processing

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：