Brain Tumor Classification Using Convolutional Neural Network and Feature Extraction

Ehsan; S. K.; Hussein

doi:https://doi.org/10.54216/FPA.130203

Journal of Intelligent Systems and Internet of Things | 2023

Safeguarding Digital Essence: A Sub-band DCT Neural Watermarking Paradigm Leveraging GRNN and CNN for Unyielding Image Protection and Identification

Image watermarking preserves digital content. This study introduces a new watermarking approach employing Sub-Band Discrete Cosine Transform and Deep neural networks, GRNN and CNN. The method embeds robust, invisible watermarks in greyscale photos and compares the two neural network topologies. The watermark is added using sub-band DCT. Watermark embedding in low-frequency sub-bands resists photo processing. The binary watermark modifies sub-band DCT coefficients to determine embedding intensity, resisting signal deterioration, and assaults. GRNN and CNN neural networks extract watermarks accurately. CNN extracts hierarchical features from images, enabling robust watermark recovery even under distortions, whereas non-parametric GRNN stores the whole training data to create predictions. The watermarking approach is tested on several greyscale photos. PSNR, SSIM, MSE, and NCC measure performance. The watermark tests noise addition, compression, and filtering. Compare GRNN and CNN's watermark extraction strengths and shortcomings to assess image watermarking suitability.

groups

Ashish Dixit mail -

R. P. Aggarwal mail -

B. K. Sharma mail -

Aditi Sharma mail

link https://doi.org/10.54216/JISIoT.100103

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2023

The «Climate in Weathers» Approach to Processing of Meteorological Series in Mesopotamia: Assessment of Climate Similarity and Climate Change using Data Mining

The "climate in the weather" (CW) approach, which combines the scientific and everyday sense of climate, has been proposed. The CW is based on the in-depth idea of E. E. Fedorov to classify regional climates as an ensemble of daily weather states. We have transformed this idea into a nonparametric method of processing meteorological series, where each member of the series is mapped to quantiles of corresponding distributions, and then new time series are formed, where meteorological variables are replaced by their quantiles. Next, the members of the new quantized series are combined in weather states. In this work, by using quantiles combination of monthly temperature and precipitation, we construct four CW states - "cold and dry", "cold and rainy", "warm and rainy", "warm and dry". Then we demonstrate the possibility of the CW approach to analyze space-time climate similarity and climate change in the Mesopotamian River system. The application of 16 CW states is also discussed. The climate change dynamical assessment (CCDA) showed that the Euphrates (Tigris) tributaries values varied from 13 to 19% (13-25%) with a clear increase in Greater Zab, Lesser Zab, Adhaim, and Dyala basins. The analysis of CW-altered states demonstrated that climate change is occurred due to an increase in temperature, a decrease in precipitation, and mixed changes simultaneously. In each of the basins, there were a different number of such changes. The "climate in weather" approach developed can be used for processing multidimensional meteorological time series data and outlining the general conception of the regional climate.

groups

Hussein Alkattan mail -

Sanjar Abdullaev mail -

El-Sayed M. El-Kenawy mail

link https://doi.org/10.54216/JISIoT.100104

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2023

Deep Convolutional Neural Network and Metaheuristic Optimization for Disease Detection in Plant Leaves

In this research, we employed a deep convolutional neural network, often known as a Deep CNN, to propose a novel approach to the detection of illnesses in the leaves of plants. In order to train the Deep CNN model, a dataset that is already accessible is employed. This dataset contains photographs of the leaves of 39 distinct plant species. Six different methods of data augmentation were utilized, including image inversion, gamma correction, noise injection, principal component analysis (PCA), color enhancement, rotation, and scaling. We came to the conclusion that adding more data to a model can improve its accuracy. The proposed model was trained using many epochs, batch sizes, and dropout percentages over the course of its development. When utilizing validation data, the suggested model performs better than methods of transfer learning that are commonly utilized. Extensive simulations demonstrate that the proposed model is capable of an astounding 83.12% accuracy in data classification. The proposed research is more accurate than the many machine learning technologies that are currently in use. In addition to that, we put the suggested model through our consistency and reliability testing.

groups

S. K. Towfek mail -

Nima Khodadadi mail

link https://doi.org/10.54216/JISIoT.100105

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2023

Real-time Monitoring of Activity Recognition in Smart Homes: An Intelligent IoT Framework

The rapid proliferation of the Internet of Things (IoT) has paved the way for transformative innovations, and this paper explores its profound impact on the realm of elderly care within smart homes. We present a pioneering IoT-based approach for human activity recognition, addressing the critical need for accurate and non-intrusive monitoring of elderly individuals. Our IoT-based approach begins with data preprocessing, where raw sensor data is refined using median filtering, reducing noise and ensuring high-quality inputs for our model. We apply the "series_to_supervised" transformation to convert the sensor data into a supervised learning format, which is critical for training the GRU-based activity recognition model. The heart of our approach lies in the federated distillation-based training strategy. Edge devices within the IoT network locally train their GRU models using their datasets while sharing knowledge with a central server and other edge devices. Knowledge distillation further enhances the model's performance by transferring knowledge from the global model to the edge devices. Experimental analysis demonstrated an impressive accuracy of 95% and an F1-score of 0.94, Our system excels in recognizing and classifying a wide range of human activities, from daily routines to emergencies.

groups

Ahmed Aziz mail -

Sanjar Mirzaliev mail -

Yuldashev Maqsudjon mail

link https://doi.org/10.54216/JISIoT.100106

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2023

On The Symbolic 6-Plithogenic and 7-Plithogenic Rings

Symbolic n-plithogenic algebraic structures are considered as a direct application of fuzzy generalized systems in pure algebra, where the symbolic n-plithogenic set is used to generalize algebraic structures by adding logical generators. In this paper, we study the concept of symbolic 6-plithogenic rings and 7-plithogenic rings from an algebraic point of view, where the main substructures formed by them will be presented such as AH-ideals, AHS-isomorphisms, and AH-kernels. Also, many theorems that explain their algebraic behaviors and classifications will be proved and illustrated.

groups

Khadija Ben Othman mail -

Othman Al-basheer mail -

Rama Asad Nadweh mail -

Oliver Von Shtawzen mail -

Rozina Ali mail

link https://doi.org/10.54216/GJMSA.080103

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

Galoitica: Journal of Mathematical Structures and Applications | 2023

A Computer Program For The System Of Weak Fuzzy Complex Numbers And Their Arithmetic Operations Using Python

Weak fuzzy complex number system is considered as a generalization of complex numbers by using an algebraic element with fuzzy property. It is believed that this new numerical system will play many important roles in various computer science disciplines, proceeding from this importance this paper aims to introduce for the first time the algebraic operations defined on weak fuzzy complex numbers using Python and Jupyter Notebook. Hence, by building a new class and its functions in Python for this new set, we can now use weak fuzzy complex numbers and the main arithmetic operations on them.

groups

Lama Razouk mail -

Suliman Mahmoud mail -

Mohammad Ali mail

link https://doi.org/10.54216/GJMSA.080104

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2023

Characterization of fuzzy algebraic structure based on diophantine Q-neutrosophic subbisemiring of bisemiring

We propose the concept of diophantine Q-neutrosophic subbisemiring(DioQNSBS), level sets of DioQNSBS of a bisemiring. The idea of DioQNSBS is an extension of fuzzy subbisemiring over bisemiring. Exploring the concept for DioQNSBS over bisemiring. Let H be the diophantine Q-neutrosophic subset in D, prove H = ⟨(Γ_H^T,Γ_H^I,Γ_H^F ), (ΛH, ΞH, ΦH )⟩ is a DioQNSBS of D if and only if all non empty level set H(t,s) is a subbisemiring of D for t, s ∈ [0, 1]. Let H be the DioQNSBS of a bisemiring D and M be the strongest diophantine Q-neutrosophic relation (SDioQNSR)of D, we notice H is a DioQNSBS of D if and only if M is a DioQNSBS of D × D. Let H1, H2, ..., Hn be the family of DioQNSBSs of D1, D2, ..., Dn respectively, prove H1 × H2 × ... × Hn is a DioQNSBS of D1 × D2 × ... × Dn. The homomorphic image of DioQNSBS is a DioQNSBS. The homomorphic preimage of DioQNSBS is a DioQNSBS. Illustrations are presented to demonstrate results.

groups

V. Sreelatha devi mail -

M. Palanikumar mail -

Aiyared Iampan mail

link https://doi.org/10.54216/IJNS.220207

Volume & Issue

Vol. Volume 22 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2023

Maize Plant Leaf Disease Classification Using Supervised Machine Learning Algorithms

Maize is an important staple crop all over the world, and its health is very important for food security. It is important for crop management and yield to find diseases that affect maize plants as soon as possible. In this study, we suggest a new way to classify diseases on maize plant leaves by using supervised machine learning algorithms. Our method uses the power of texture analysis with Gray-Level Co-occurrence Matrix (GLCM) and Gabor feature extraction techniques on the Plant-Village dataset, which has images of both healthy and unhealthy maize leaves. This method uses four supervised machine learning algorithms, called Decision Tree, Gradient Boosting, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), to sort the extracted features into healthy and diseased groups. By doing a lot of tests, we show that our way of finding maize leaf diseases works well. The results show that these techniques have the potential to quickly and non-invasively diagnose diseases, giving farmers important information for acting quickly. We talk about the pros and cons of each algorithm and suggest ways to make them even better. This research contributes to the advancement of automated plant disease detection systems, fostering sustainable agriculture practices and aiding in crop management decisions. The proposed approach holds promise for real-world application, enabling farmers to mitigate disease-related losses and secure global food supplies.

groups

Ashish Patel mail -

Richa Mishra mail -

Aditi Sharma mail

link https://doi.org/10.54216/FPA.130201

Volume & Issue

Vol. Volume 13 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2023

Enhancement CNN based on LSTM for vital sign classification

Monitoring vital signs is essential for tracking patient health and detecting changes in their condition. However, in aging cultures with overburdened healthcare staff, accurately and efficiently monitoring vital signs poses a challenge. To address this issue, an autonomous system for vital sign control is proposed, offering improved accuracy, real-time monitoring, alert systems, remote monitoring, and reduced staff labor costs. This paper presents a deep learning architecture using a publicly accessible dataset of 25,494 patients and five numerical characteristics to classify vital signs. A CNN-LSTM model is introduced, outperforming a traditional CNN model in terms of performance, parameter efficiency, and training time. The CNN-LSTM model effectively captures both spatial and temporal features from the input data, resulting in superior representation and improved accuracy compared to the CNN model, which only extracts spatial data. The suggested model achieved a remarkable accuracy of 98%, surpassing previous models. The findings demonstrate the potential of the CNN-LSTM model for early identification of medical issues, enabling prompt actions and enhanced patient outcomes. Overall, this research highlights the significance of implementing an autonomous system for vital sign control in healthcare organizations, offering substantial benefits in patient care and healthcare management.

groups

Mina H. Madhi mail -

Abbas M. Al-Bakry mail -

Alaa Kadhim Farhan mail -

El-Sayed M. El-Kenawy mail

link https://doi.org/10.54216/FPA.130202

Volume & Issue

Vol. Volume 13 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2023

Brain Tumor Classification Using Convolutional Neural Network and Feature Extraction

Convolutional Neural Networks (CNNs) are the most popular neural network model for the image classification problem, which has seen a surge in interest in recent years thanks to its potential to improve medical picture classification. CNN employs a number of building pieces, including convolution layers, pooling layers, and fully connected layers, to determine features in an adaptive manner via backpropagation. In this study, we aimed to create a CNN model that could identify and categorize brain cancers in T1-weighted contrast-enhanced MRI scans. There are two main phases to the proposed system. To identify images using CNN, first they must be preprocessed using a variety of image processing techniques. A total of 3064 photos of glioma, meningioma, and pituitary tumors are used in the investigation. Testing accuracy for our CNN model was 94.39%, precision was 93.33%, and recall was 93% on average. The suggested system outperformed numerous well-known current algorithms and demonstrated satisfactory accuracy on the dataset. We have performed several procedures on the data set to get it ready for usage, including standardizing the pixel sizes of the photos and dividing the dataset into 80% for train, 10% for test, and 10% for validation. The proposed classifier achieves a high level of accuracy of 95.3%.

groups

Ehsan khodadadi mail -

S. K. Towfek mail -

Hussein Alkattan mail

link https://doi.org/10.54216/FPA.130203

Volume & Issue

Vol. Volume 13 / Iss. Issue 2

Details open_in_new