Enhancing Mushroom Detection Using One-Dimensional Convolutional Neural Networks

Jabbar Abed; Mustafa Muslih; Ahmed Mubdir; Ahmed Adil; Aythem Khairi; Mustafa Nadhim

doi:https://doi.org/10.54216/FPA.200201

Galoitica: Journal of Mathematical Structures and Applications | 2023

Deep Learning for Super Resolution and Applications

High-resolution technologies are aimed at obtaining a high-resolution image from a low-resolution image, and the importance of this field has increased due to the emergence of the need to have high-resolution images in many important applications such as medical, security, and other images. Methods for obtaining ultra-high-resolution images have developed after the advent of Deep Learning Technologies, which have shown good results in this task, Due to the importance of the field of ultra-high-resolution images and deep learning, In this article we will explain one of the deep learning models used to obtain a high-resolution image from a low-resolution image and how to build and train it based on one of the famous deep learning offices and using one of the google platforms used in training, namely Google Laboratory

groups

Zahraa Hasan mail

link https://doi.org/10.54216/GJMSA.080204

Volume & Issue

Vol. Volume 8 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Monthly Solar Prediction Using Machine Learning: Diyala Governorate, Iraq as a Case Study

Solar radiation constitutes the Earth’s primary energy source and is critical in regulating surface radiation equilibrium, vegetation photosynthesis, hydrological cycles, and extreme atmospheric. On the other hand, the depletion of global fossil fuel reserves mandates the power sector to adopt renewable energy-based sources, including photovoltaic and wind energy conversion systems. Therefore, the precise solar radiation prediction is imperative for climate research and the solar industry. This paper illustrates the use of two machine-learning approaches: random forest (RF) and support vector machine (SVM), to predict surface solar radiation in the Diyala governorate of Iraq for one step ahead, utilizing only lagged monthly time series data of the factor as input predictors. The findings were evaluated using three performance measures: coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The results showed that using 10 monthly lags time series as input predictors leads to the best prediction performance. Furthermore, in terms of the RMSE, the prediction performance of the RF algorithm was better than that of the SVM algorithm (RF's RMSE, MAE, and R2 were 181.398, 129.522, and 0.979, while for SVM were 240.149, 184.802, and 0.978, respectively).

groups

Noor Razzaq Abbas mail -

Hussein Alkattan mail -

Hamidreza Rabiei-Dastjerdi mail -

Mohamed Saber mail -

Marwa M. Eid mail

link https://doi.org/10.54216/JAIM.050204

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Medical Image Classification for Monkeypox Case using Deep Learning Algorithms: A Survey

Due to the importance of maintaining public health and preventing the spread of diseases, nowadays, new diseases have spread at a lot of countries called Monkeypox after the world get rid of covid-19.it is crucial to diagnose Monkeypox and stop the spread of this disease. so that we make this review to give a point of view to Monkeypox spread nowadays. We have recently done nine research to overlay it with different artificial intelligence deep learning methods to diagnose Monkeypox from digital skin images due primarily to AI's success in COVID-19 identification. The VGG16, VGG19, ResNet50, ResNet101, DenseNet201, and AlexNet models were used in our proposed method to classify patients with monkeypox symptoms with other diseases of a similar kind (chickenpox, measles, and normal)., Due to the importance of facing this disease and summarizing these researches according to: methodology and results of detection accuracy, precision.

groups

Ahmed Islam mail -

Mohamed G. Abdelfattah mail -

El-Sayed M. El-Kenawy mail -

Hossam El-Din Moustafa mail

link https://doi.org/10.54216/JAIM.050205

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

American Journal of Business and Operations Research | 2023

An Optimized Ensemble Model for Inflation Prediction in Egypt

Inflation, an omnipresent economic phenomenon, is marked by a continual upsurge in the overall price levels of commodities and services within an economy. Accurately predicting inflation within a data-abundant setting poses a formidable challenge and remains a dynamic area of research encompassing several unresolved methodological inquiries. Among these, a significant query pertains to the identification and extraction of data offering the highest predictive capability for a targeted variable, particularly in scenarios characterized by numerous closely interconnected predictors, as encountered in the context of inflation prediction. Recently, the application of machine learning (ML) models has gained traction in predicting inflation parameters. The predictive accuracy of such models hinges significantly on the selection of an appropriate framework. Ensemble models, designed to amalgamate multiple base models, have emerged as a compelling strategy to yield superior predictive outcomes. In this study, we introduce a novel weighted average ensemble model tailored for the prognostication of inflation prediction. The proposed approach leverages three foundational base models: Linear Regression (LR), Polynomial Regression (PR), and Moving Average (MA) regression. The critical aspect of this ensemble lies in optimizing the weights assigned to each base model, thereby accentuating their individual strengths. To achieve this, we employ the Waterwheel Plant Optimization Algorithm (WWPA), a proficient optimization algorithm, to discern the optimal weight distribution for the base models. Comparative evaluations are conducted, pitting the proposed model against three another base models. Empirical findings conclusively demonstrate the superiority of the proposed weighted average ensemble model, underscoring its capacity to predict inflation with exceptional efficiency.

groups

Ahmed M. Elshewey mail

link https://doi.org/10.54216/AJBOR.100207

Volume & Issue

Vol. Volume 10 / Iss. Issue 2

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Solving Initial Value Problem in Composite Materials for Heat Equation

In this paper, we display the definition and arrangement of the beginning esteem issue in composite materials for warm condition. The issue includes finding the starting temperature conveyance when as it were the temperature spreading at time t=T>0 is given. Typically, a challenging issue since it has a place to a course of numerically unsteady issues that are ill-posed. To characterize this issue, we have to be present work spaces and unravel the coordinate issue to decide them. The method of division of factors is commonly utilized to fathom the coordinate issue, but it isn't reasonable for the due to the expansive blunders and disparate arrangement it produces. Ivanov V.K. proposed a strategy to get a steady inexact arrangement by supplanting the coming about arrangement with a fractional whole that depends on δ, N=N(δ). Another approach is the Picard strategy that employments a family of administrators  to map the space  into itself and get a regularized inexact arrangement. We show the comes about of computational tests and assess the viability of the Picard strategy.

groups

Al-Mahdawi H. K. mail -

Alhumaima Ali Subhi mail -

Hussein Alkattan mail -

Mohamed Saber mail -

Marwa M. Eid mail -

Anfal A. Sabti Al-Mahdawi mail -

Jinan A. M. Al-Saddaee mail

link https://doi.org/10.54216/JAIM.060101

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2023

On Neutrosophic D –Topological Spaces

In this paper, we redefine the dense neutrosophic set operations and, by using them, we introduce new definition for topological space in neutrosophic topological space and also gives the basic specifications for the new definitions of neutrosophic topological space in neutrosophic topological space, we also obtained some properties that show the relationship between neutrosophic topological space and neutrosophic semi-open sets in the neutrosophic topological space, we also studied image characterization and preimages of neutrosophic    topological  space .

groups

Amer Khrija Abed mail -

Ekram Abd Ali mail -

Ahmed Salam Razzaq mail -

Qays Hatem Imran mail -

Said Broumi mail

link https://doi.org/10.54216/IJNS.220301

Volume & Issue

Vol. Volume 22 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2023

Selection of Agricultural Aircraft in Bipolar Neutrosophic Environment using Bipolar - TOPSIS method

The neutrosophic set has numerous uses in a variety of industries. There are more advantages to use the Bipolar Neutrosophic set than other sets for elucidating a multi-criteria decision-making problem. The bipolar-neutrosophic set addresses both the positive and negative facets of the issue, improving the probability of a successful resolution. By implementing the removal area method, the de-bipolarization of the bipolar neutrosophic number with eleven parameters is formulated. The proposed Neutrosophic number is used to solve the selection of agricultural aircraft using given criteria and the linguistic variables by the TOPSIS approach. A comparative study has been conducted to determine its robustness. Also, the multi-criteria decision-making problem (MCDM) is solved using the TOPSIS approach with MATLAB programming.

groups

Abraham D. Egan L mail -

B. Shoba mail -

Rajkumar A. mail -

broumi said mail

link https://doi.org/10.54216/IJNS.220302

Volume & Issue

Vol. Volume 22 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2023

On Radical of Neutrosophic Primary Submodule

In this paper, we introduce and study the concept of neutrosophic submodules and neutrosophic primary submodule with the help of the definition of a radical submodule, and we also study the properties of these submodules. Furthermore, homomorphic image and preimage of neutrosophic primary submodule are investigated.

groups

M. Vasuki mail -

P. Senthil Kumar mail -

Said Broumi mail -

N. Rajesh mail

link https://doi.org/10.54216/IJNS.220303

Volume & Issue

Vol. Volume 22 / Iss. Issue 3

Details open_in_new

International Journal of Neutrosophic Science | 2023

The Symbolic Plithogenic Complex Numbers

In this paper, we presented symbolic plithogenic complex numbers, and studied the arithmetic operations: addition, subtraction, multiplication and division. Also, we defined the conjugate, inverted and the absolute value of symbolic plithogenic complex numbers, the theories related to the conjugate of symbolic plithogenic complex numbers are proved.

groups

Yaser Ahmad Alhasan mail -

Raja Abdullah Abdulfatah mail

link https://doi.org/10.54216/IJNS.220211

Volume & Issue

Vol. Volume 22 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2025

Enhancing Mushroom Detection Using One-Dimensional Convolutional Neural Networks

The classification of mushrooms as either deadly or edible stays a important challenge due to their similar appearances, which can lead to fatal poisonings. The primary difficulty lies in identifying complex patterns in mushroom appearances, such as cap shape, color, and gill structure, which complicate accurate classification. Traditional approaches and even some machine learning (ML) models fail to capture these subtle but important distinctions, leading to misclassifications. To address this issue, this paper proposed a One-Dimensional Convolutional Neural Network (1D-CNN) approach aimed at improving the accurate of mushroom classification. By effectively recognizing complex patterns in the mushroom data set, the proposed approach greatly improves classification accuracy. The model performance evaluated utilizing Precision, Accuracy, Recall, and F1-Score that achieved high scores of 100% across all metrics. These results highlight the strength of deep learning (DL) method, specifically 1D-CNNs, in recognizing with learning complex data patterns. This shows a clear advancement over traditional ML methods and ensemble techniques, establishing the 1D-CNN as a highly reliable tool for mushroom classification that can help reduce mushroom poisoning incidents.

groups

Jabbar Abed Eleiwy mail -

Mustafa Muslih Shwaysh mail -

Ahmed Mubdir Kadhim mail -

Ahmed Adil Nafea mail -

Aythem Khairi Kareem mail -

Mustafa Nadhim Owaid mail

link https://doi.org/10.54216/FPA.200201

Volume & Issue

Vol. Volume 20 / Iss. Issue 2

Details open_in_new