IoT System Based on parameter optimization of Deep Learning using Genetic Algorithm

Slim, Salwa O.; Elfattah, Marwa M. A.; Atia, Ayman; Mostafa, Mostafa-Sami

doi:10.22266/ijies2021.0430.20

Cited by 11 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, Slim et al 36 focused on the parameter optimization of deep learning using GA. Their study proposed an approach leveraging GA to optimize the parameters of DL models within an IoT framework. By integrating these technologies, the paper aimed to enhance the efficiency and performance of DL algorithms, particularly in the context of IoT applications.…”

Section: Nature‐inspired Algorithmsmentioning

confidence: 99%

The applications of nature‐inspired algorithms in Internet of Things‐based healthcare service: A systematic literature review

Amiri,

Heidari,

Zavvar

et al. 2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Nature‐inspired algorithms revolve around the intersection of nature‐inspired algorithms and the IoT within the healthcare domain. This domain addresses the emerging trends and potential synergies between nature‐inspired computational approaches and IoT technologies for advancing healthcare services. Our research aims to fill gaps in addressing algorithmic integration challenges, real‐world implementation issues, and the efficacy of nature‐inspired algorithms in IoT‐based healthcare. We provide insights into the practical aspects and limitations of such applications through a systematic literature review. Specifically, we address the need for a comprehensive understanding of the applications of nature‐inspired algorithms in IoT‐based healthcare, identifying gaps such as the lack of standardized evaluation metrics and studies on integration challenges and security considerations. By bridging these gaps, our paper offers insights and directions for future research in this domain, exploring the diverse landscape of nature‐inspired algorithms in healthcare. Our chosen methodology is a Systematic Literature Review (SLR) to investigate related papers rigorously. Categorizing these algorithms into groups such as genetic algorithms, particle swarm optimization, cuckoo algorithms, ant colony optimization, other approaches, and hybrid methods, we employ meticulous classification based on critical criteria. MATLAB emerges as the predominant programming language, constituting 37.9% of cases, showcasing a prevalent choice among researchers. Our evaluation emphasizes adaptability as the paramount parameter, accounting for 18.4% of considerations. By shedding light on attributes, limitations, and potential directions for future research and development, this review aims to contribute to a comprehensive understanding of nature‐inspired algorithms in the dynamic landscape of IoT‐based healthcare services.

show abstract

Section: Nature‐inspired Algorithmsmentioning

confidence: 99%

The applications of nature‐inspired algorithms in Internet of Things‐based healthcare service: A systematic literature review

Amiri,

Heidari,

Zavvar

et al. 2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Therefore, during the training process, a four layer automatic encoder network with 794 units in the display layer and 1100-550-260-40-20 in the hidden layer can be established; Secondly, convert the original pixel intensity values between 0 and 265 to grayscale values between 0 and 2; Finally, the 65000 training samples in the database were divided into 650 small batches in groups of 120, and each training cycle processed these 650 small batches in sequence. The weights were only updated after each small batch ended [9,10].…”

Section: Handwritten Digitmentioning

confidence: 99%

“…This neighborhood is a window that matches with the authentication point as the center. Reconstruct the point cloud of industrial products, give a three-dimensional point, use a normalization function to represent the projection of product images, and perform matching and feature tracking between industrial product images [11,12].…”

Section: Handwritten Digitmentioning

confidence: 99%

Application of Deep Learning Algorithm in Visual Optimization of Industrial Design

Zhang

2024

SCPE

View full text Add to dashboard Cite

In order to understand the application of degree learning algorithms in industrial design visual optimization, the author proposes an application research based on deep learning algorithms in industrial design visual optimization. The author first starts with the basic principles of deep learning algorithms and provides a detailed explanation of the basic structure of the single-layer network of deep learning algorithms, as well as the restricted Boltzmann machine and its training process. Finally, an example of the performance improvement brought by the application of deep learning technology in handwritten digit recognition was given through an automatic encoder, and a simple summary of deep learning technology was made. Secondly, the NCI matching algorithm is used to match industrial design products and reconstruct the point cloud of industrial products to accurately detect their features. On this basis, deep learning algorithms are applied to construct a visual optimization model for industrial design, determine the output format of the model scene and the output situation of industrial design, and process the model according to the changing characteristics of the industrial design model to comprehensively edit the data of the model. Finally, targeted optimization of the industrial design visual optimization model is carried out based on the technical characteristics of deep learning algorithms, in order to complete the industrial design visual optimization. The experimental comparison results show that the industrial design visual optimization method optimized in this design has higher visual clarity than the traditional industrial design method, reaching 98%. Greatly improves the visual clarity of industrial design.

show abstract

“…Mobile DL apps combine large-scale data DL models with DL programs in a variety of software apps [5]. A security mentality must be applied to all software engineering methods in order to produce secure software [6]. Statistical fault localization is a simple technique for identifying candidates for defective code places fast [7][8].…”

Section: Related Workmentioning

confidence: 99%

Inside A Deep Learning Library, the Symptoms, Causes, and Fixes for Bugs

2022

IJIES

View full text Add to dashboard Cite

Deep learning has become a popular study area in recent years. While deep learning software generates tremendous positive results in some cases, faults in the programme can have fatal repercussions, in safety-critical applications, this is extremely significant. Researchers have conducted various empirical investigations on defects in deep learning systems to better understand the bug characteristic of deep learning software. Despite the fact that these studies are useful, none of them investigate the problem in TensorFlow, a deep learning framework. They feel that some fundamental concerns about deep learning library difficulties remain unsolved. The answers to these questions are crucial and helpful because they constitute the underlying library of many deep learning endeavours. Many deep learning initiatives are influenced by its flaws. In this paper we pre-process a dataset that is openly accessible by performing data normalization and log transformation. To prepare the data input for the deep learning model, we next undertake data modelling. Third, we send the modelled data to a deep neural network-based model that was specifically created to forecast the number of faults. We test the suggested method on two well-known datasets as well. The evaluation's findings show that the suggested strategy is reliable and can outperform cuttingedge methods. The suggested approach enhances the squared correlation coefficient by more than 8% while, on average, drastically reducing the mean square error by more than 14%.

show abstract

IoT System Based on parameter optimization of Deep Learning using Genetic Algorithm

Cited by 11 publications

References 57 publications

The applications of nature‐inspired algorithms in Internet of Things‐based healthcare service: A systematic literature review

The applications of nature‐inspired algorithms in Internet of Things‐based healthcare service: A systematic literature review

Application of Deep Learning Algorithm in Visual Optimization of Industrial Design

Inside A Deep Learning Library, the Symptoms, Causes, and Fixes for Bugs

Contact Info

Product

Resources

About