检索结果-内蒙古大学图书馆

Joint Rain Streaks & Haze Removal Network for Object Detection

computers, Materials & Continua 2024年第6期79卷 4683-4702页

作者： Ragini Thatikonda Prakash Kodali Ramalingaswamy Cheruku Eswaramoorthy K.V Department of Electronics and Communication Engineering National Institute of TechnologyWarangal506004India Department of Computer Science and Engineering National Institute of TechnologyWarangal506004India Department of Electronics and Communication Engineering Indian Institute of Information TechnologyDesign and ManufacturingKurnool518008India

In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant *** emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior ***,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational *** response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature *** methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map *** the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.

关键词： Image deraining Selective Dense Residual Module(SDRM) Selective Kernel Fusion Module(SKFM) Selective KernelDense Residual M-Shaped Network(SKDRMNet)

来源：评论

学校读者我要写书评

暂无评论

LesionAid: vision transformers-based skin lesion generation and classification – A practical review

引用

Multimedia Tools and Applications 2025年 1-22页

作者： K, Mallikharjuna Rao Krishna, Ghanta Sai Supriya, Kundrapu Sorgile, Meetiksha Data Science and Artificial Intelligence International Institute of Information Technology Naya Raipur India Computer Science and Engineering International Institute of Information Technology Naya Raipur India

Skin cancer is one of the most prevalent forms of human cancer. It is recognized mainly visually, beginning with clinical screening and continuing with the dermoscopic examination, histological assessment, and specimen collection. Deep convolutional neural networks (CNNs) perform highly segregated and potentially universal tasks against a classified fine-grained object. This study suggests a novel multi-class prediction framework that uses ViT and ViTGAN to categories skin lesions. To address the class disparity, GANs (Generative Adversarial Networks) based on vision transformers are used. The framework comprises four main phases: ViTGANs, Image processing, and explainable AI. Phase 1 consists of generating synthetic images using ViTGAN to balance all the classes in the dataset. To enhance the amount of the data, the second phase involves using various morphological processes and data augmentation techniques. In phases three and four, a ViT model for edge computing systems that can recognize patterns and classify skin lesions from the user's skin that is visible in the picture is developed. In phase 3, after classifying the lesions into the desired class with ViT, we will use explainable AI (XAI) that leads to more explainable results (using activation maps, etc.) while ensuring high predictive accuracy. The results demonstrate that the model used for generating synthetic images has achieved an FID score of 13.32 and the ViT model has achieved 99.2% as its training accuracy and 97.4% as its validation accuracy. The whole framework is compared with the existing frameworks for skin lesion detection. And explainable AI (XAI) is used in the proposed framework in order to increase model transparency and boost trust among users by illustrating the main factors affecting predictions. This interpretability helps physicians in making more informed decisions by providing clear insights into the model's reasoning. © The Author(s), under exclusive licence to Springer science+Bu

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A verifiable threshold secret image sharing (SIS) scheme with combiner verification and cheater identification

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第8期14卷 10631-10655页

作者： Soreng, Aswini Vinay Kandar, Shyamalendu Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur India

Image transmission is gaining importance with the advancement of information communication technology. Transmission of sensitive images in diverse applications like military, diplomatic, and medical sector requires special attention so that those are not placed in the wrong hands. Secret sharing is a technique in information security applicable for group use of a secret. In secret sharing, all the actors are considered to be trusted but in a real scenario, there is the possibility of cheating. In this current research, a verifiable secret image sharing (VSIS) is proposed which is a threshold scheme and can identify a cheater. The sharing is done by bitwise OR and verifiability is added using XOR and hash operation. The participants are provided only shadow shares not the original and combiner authentication is done by the participants before submitting information. Experimental results and security analysis provides acceptability and comparison analysis with some existing schemes provides it a strong base. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Maximizing Profit of the Service Providers through Efficient Content Placement and Retrieval in an IoT-enabled Edge-Cloud Platform 18

Maximizing Profit of the Service Providers through Efficient...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Gandhi, Preet Mahanta, Abhishriya Ghose, Manojit Sahu, Aryabartta Indian Institute of Technology Department of Computer Science and Engineering Guwahati India Indian Institute of Technology School of Computing and Electrical Engineering Mandi India Indian Institute of Information Technology Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350391725

In today's 5G era, the amount of data generated by the Internet of Things (IoT) devices is enormous. Data is processed and stored in the cloud under a traditional cloud computing architecture, and real-time processing and retrieval of these data is time-consuming. Therefore, an edge-cloud framework comes in handy where the content generated is placed on the edge nodes of the network, and it can reach the endusers in a time-bound manner. A majority of the previous research works on content placement under the edge-cloud architecture primarily aimed at improving the latency of the system. However, the approach proposed in this paper aims to maximize the profit of the service provider by effectively placing the content in a hierarchically organized edge-cloud network. We propose two strategies and compare them with random and greedy approaches for both synthetic and real data sets. The experimental results demonstrate the effectiveness of the proposed strategies, and the profit of the service providers increases by 38.81% (maximum) and 10.51% (on average) for the synthetic dataset and by 65.74% (maximum) and 22.83% (on average) for the real-world dataset when compared with the greedy approach. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Modern Machine Learning Solution for Electricity Consumption Management in Smart Buildings

引用

IEEE engineering Management Review 2025年第1期53卷 54-62页

作者： Gautam, Sandeep Kumar Shrivastava, Vinayak Udmale, Sandeep S. Singh, Amit Kumar Singh, Sanjay Kumar Department of Computer Science and Engineering Varanasi221005 India Department of Computer Engineering and Information Technology Mumbai400019 India National Institute of Technology Department of Computer Science and Engineering Patna800005 India

Effective management of electricity consumption (EC) in smart buildings (SBs) is crucial for optimizing operational efficiency, cost savings, and ensuring sustainable resource utilization. Accurate EC prediction enables proactive decision-making, ensuring that resources are allocated efficiently to meet actual demand levels while maintaining occupant comfort. Population growth, building expansion, and technology usage swiftly escalate electricity demand, thus necessitating economical EC management strategies and assist consumers to better understand and strategically plan their EC. To address these challenges, this article proposes a novel approach based on a hybrid prediction model combining temporal convolutional networks (TCNs) and gated recurrent units (GRU). This approach capitalizes on the strengths of both TCN and GRU. TCN is adept at efficiently identifying diverse patterns, particularly within the complex working environments of SBs, by effectively capturing high- and low-frequency information. Subsequently, GRU is leveraged to address the long-term dependencies within the data, enhancing the accuracy of EC prediction. In this article, the results demonstrate the effectiveness of the proposed hybrid model, outperforming competitive methods with an impressive mean absolute error score. This underscores the potential of this approach to improve energy management practices significantly within SB environments, ultimately enhancing both operational efficiency and occupant satisfaction. © 1973-2011 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Ensemble activation enabled deep classifier for Alzheimer's disease detection in the blockchain-enabled distributed edge environment

引用

International Journal of information technology (Singapore) 2024年 1-18页

作者： Mandawkar, Umakant Diwan, Tausif Department of Computer Science and Engineering Indian Institute of Information Technology Nagpur India Department of Computer Engineering SVKM’s Institute of Technology Maharashtra Dhule India

Alzheimer's disease (AD) is the most well-known cause of dementia that affects memory. Alzheimer's patients have a neurodegenerative disorder that results in the loss of many brain functions. Today’s researchers have determined that the key to enhancing patient care and treatment is early disease diagnosis. Traditional techniques for diagnosing AD are difficult ineffective, and take a lot of time to learn and execute. In this research, a disease detection system is developed using the proposed tawny flamingo-based federated deep CNN (Convolutional Neural Networks) (TF based-deep CNN) which can manage accurate patient diagnosis in dispersed contexts with blockchain support. The collected data is maintained and structured in a blockchain-based database, which upholds a high level of data security and increases the detection accuracy. After the medical professional receives the data, disease detection is done using the proposed federated learning framework, which makes it feasible to manage remote data effectively. The features are then extracted from the segments created by the CUF-GW (Cuttlefish-GreyWolf) algorithm. The detection is then carried out by the proposed ensemble activation-based deep CNN classifier, with the ensemble process being assisted by the TF (Tawny Flamingo) approach. According to AD accomplishments, at TP (Training Percentage) 80, acc (Accuracy), sen (Sensitivity), and spe (Specificity) are respectively 99.19%, 99.99%, and 98.87%;similarly, based on the k-fold 10, acc, sen, and spe are respectively 99.45%, 99.99%, and 98.45%. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Alzheimer's disease CUF-GW algorithm Deep CNN Federated learning TF

来源：评论

学校读者我要写书评

暂无评论

An Empirical Survey on the Classification Strategies for Automated Alzheimer’s Disease

引用

SN computer science 2024年第8期5卷 1140页

The early Alzheimer’s disease (AD) classification is highly important as this neuro-degenerative disease causes severe problems particularly, loss of memory among the patients. In addition, classifying Normal Control (NC), Mild Cognitive Impairment (MCI) and AD in time assists the patient to undergo treatments in the initial period of the disease. Hence, it is necessary to develop a trust worthy categorization model to classify the patients with or without AD. One of principal modalities commonly used for AD classification is the magnetic resonance imaging (MRI), the analysis of which achieved improved classification performance in categorizing the stages of AD. Hence, this review paper presents the detailed survey of 55 research articles showing different strategies to classify AD. The two important categories of the research papers are the methods using machine learning strategies, and the methods using deep learning strategies. The papers are classified based on various modalities, datasets, performance indices, and the software tools used for implementation. In addition to this, various research gaps and the challenges associated with the existing works of AD classification are discussed. In addition, this review provides the future scope for researchers with the analysis of research issues seen in the literary works. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Alzheimer’s disease Deep learning and machine learning Magnetic resonance imaging Mild cognitive impairment

来源：评论

学校读者我要写书评

暂无评论

Optimized Power Allocation in Downlink NOMA with Imperfect Successive Interference Cancellation

Optimized Power Allocation in Downlink NOMA with Imperfect S...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Biswas, Soumik Bera, Debasish Indian Institute of Information Technology Department of Electronics and Communication Engineering Kalyani India Indian Institute of Information Technology Department of Computer Science and Engineering Kalyani India

ISBN: (纸本)9798350350821

It is expected that physical-layer security will finally thrive to provide an extra layer of defence for a variety of devices in next-generation 6G wireless communication. In this work, physical-layer security using non-orthogonal multiple access (NOMA) with single-input-single-output (SISO) assumptions are considered where the users and eavesdroppers are spatially uniformly deployed. The channels between the transmitter (base station (BS)) and the NOMA users and eavesdroppers are considered to be independent Nakagami-m. We analyse the secrecy sum rate (SSR) of the NOMA system in the case of imperfect successive interfere cancellation (SIC) and propose an optimised power allocation scheme with minimised transmit power requirement to satisfy the Quality of Service (QoS) for all legitimate users. Closed-form solutions for the SSR are also derived. The performance of the proposed schemes has been evaluated both by analysis and by simulations. Results are evaluated for a wide range of the signal-to-noise ratio (SNR). © 2024 IEEE.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Graphical Causal Structure and Machine Learning Models in the Study of Infant Health and Mortality

引用

Journal of The Institution of Engineers (India): Series B 2024年 1-10页

作者： Kamei, Gaidinlung Banerjee, Indrajit Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur West Bengal Howrah711103 India

The rise of medical and health data in digitized database storage allows computer scientists and researchers to design highly accurate predictive models using machine learning. However, the dependency of models on correlation fails to establish explainable causal effects, and models show lower performance on never-before-seen data despite their high predictive and inferential accuracy on the training–testing data and the likeness. There is a lack of causal explanation among the features and target of the data. These issues give rise to challenges of adaptability and cause-effect explainability. This paper proposes a model that analyses the effect of health policies, considering health policy and observations on infants as features, whereas infant death is the target. The structural causal model (SCM) establishes the cause-effect relationship between the features and the target. The causal features are highly emphasized and considered in feature selection with proper justification. The infant deaths are predicted using the machine learning models after the causal model establishes and validates the graphical causal structure. The model articulates the graphical relationship between the features and the target in terms of the causal graph (Directed Acyclic Graph) and fitness of the model, along with the prediction performances of the machine learning models. © The Institution of Engineers (India) 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Smoke detection in foggy surveillance environment using parallel vision transformer network

引用

Neural Computing and Applications 2024年第31期36卷 19499-19514页

作者： Chaturvedi, Shubhangi Thakur, Poornima Singh Khanna, Pritee Ojha, Aparajita Computer Science and Engineering Department PDPM Indian Institute of Information Technology Design and Manufacturing Dumna Road Madhya Pradesh Jabalpur482005 India

Recent years have seen an unprecedented increase in fire incidents, resulting in severe damage to forest regions, loss of human and animal lives, and unwarranted displacement of people. Owing to these issues, artificial intelligence-based fire detection systems have been developed. These systems mostly work with camera-based inputs for fire detection and alarm generation. As fire-smoke can be seen from a distance, methods for smoke detection have also been deployed for identifying fire incidents. But detecting smoke in an outdoor environment can be challenging due to weather conditions such as haze, fog, or clouds. These challenges have led to advancements in the field, and various deep learning architectures have been suggested over the years for fire-smoke detection in normal and foggy or cloudy weather conditions. Many existing methods are either computationally expensive and demand high memory, or if they are lightweight, they suffer from lower smoke detection accuracy and high false alarms. In the present paper, a dual-channel vision transformer model ‘SmokeViT’ is proposed for detecting fire-smoke in an outdoor environment. These channels are interlaced with a convolutional neural network to improve the feature learning capability of the model. ‘SmokeViT’ shows a remarkable accuracy of more than 99% and false alarm rate below 0.20% on two publicly available smoke datasets, outperforming six state-of-the-art methods. The model architecture has only 0.4 million parameters and 0.17 giga floating-point operations, making it suitable for deployment on resource-constrained surveillance devices. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Smoke

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：