A Review of Machine Learning Models for Predicting Air Quality in Urban Areas

El-Sayed M.

doi:https://doi.org/10.54216/MOR.030204

International Journal of Advances in Applied Computational Intelligence | 2025

Knowledge-Based Decision Support System for Selecting Optimal Web Services Based on QoS Attributes for Business Process Composition

Web services are a crucial part of large-scale software development and cross-organizational collaboration. This chapter discusses the challenges of selecting the finest internet services among the vast array of possibilities available, with an emphasis on quality of service (QoS) features. Web services must fulfil every requirement needed to provide optimal user experience and the efficient execution of corporate operations. In order to find the best services, we look at important quality of service characteristics including response speed, reliability, accessibility, and efficiency. In what follows, you will find a detailed method for selecting services. The approach consists of three steps: finding services, improving them according to QoS constraints, and grading those using weighted normalized techniques. At each stage, methods are provided to ensure an accurate and successful selection that meets the customer's needs. The proposed method seems to work, according to the results of the trials. The rating of services for several customers with varying limits, achieved using real-life data sets, demonstrates the approach of filtering and assessing to acquire optimal results. This method boosts the efficiency and usefulness of the selected services by combining functional and non-functional aspects. Finally, this part concludes by stressing the importance of quality of service in guaranteeing customer satisfaction and optimizing the delivery of services in competitive and fast-changing environments. Service 3 has the highest accuracy rate at 96.5%. Due to their low reaction times and high availability, Services 2 and 6 are in close second place. Services 4 and 7 have good availability ratings; however, they take longer to respond. Services 1 and 8 have moderate availability and high response times; hence, they get the lowest scores. When it comes to reliability and accuracy, Service 3 remains your most effective choice.

groups

Stipan Podobnic mail -

Barbara Charchekhandra mail

link https://doi.org/10.54216/IJAACI.070103

Volume & Issue

Vol. Volume 7 / Iss. Issue 1

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2025

Automated Insect Detection and Classification using Pelican Optimization Algorithm with Deep Learning on Internet of Enabled Agricultural Sector

Recently, the combination of Deep Learning (DL) methods within the Internet of Things (IoTs) has developed in the agricultural field, especially in the domain of pest management. This study considers the implementation and development of an innovative method for Insect Detection and Classification using DL within the environment of the IoTs in agriculture. The developed system advantages advanced DL approaches for analysing images captured by IoT-enabled devices, enabling real-time identification and categorization of insect pests. By continuously incorporating these technologies, these research goals to increase the efficiency and precision of pest monitoring, finally providing to sustainable agricultural technologies and increased crop yield. This study presents an Automated Insect Detection and Classification using Pelican Optimization Algorithm with Deep Learning (AIDC-POADL) technique on Internet of Enabled Agricultural Sector. The main objective of the AIDC-POADL system is to identify and categorize various types of insects exist in the agricultural field. In the primary stage, the AIDC-POADL technique involves DenseNet-121 model to learn complex features in the input images. Also, the hyperparameter choice of the DenseNet-121 algorithm developed by the POA. At last, multilayer perceptron (MLP) model can be applied to discriminate the insects into various classes. To validate the enhanced performance of the AIDC-POADL algorithm, a series of simulations are involved. The experimental outcomes stated that the AIDC-POADL technique offers enhanced recognition results over other approaches.

groups

Karla Zayood mail -

Rama Asad Nadweh mail

link https://doi.org/10.54216/IJAACI.070104

Volume & Issue

Vol. Volume 7 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Optimize Decision-Making in the Industrial Sector under Uncertainty: A Neutrosophic Inverse Exponential Distribution Approach

The most widely used distribution for risk management data for modeling longevity is the one-parameter inverse exponential distribution. Among alternative models, we suggest the neutrosophic inverse exponential (NIE) model, which generalizes the extended inverse exponential distributions and the classical structure. For the suggested model, we derive explicit formulations for the quantile functions, median, mode, cumulative distribution function, and probability density function. Data generating process of the proposed model under neutrosophic environment is discussed. To estimate the model parameters, we use the maximum likelihood approach. Using the proposed model, we run the simulation setup for randomly generated data. A genuine data set is also used to support the proposed model applicability.

groups

Mansour F. Yassen mail

link https://doi.org/10.54216/IJNS.250425

Volume & Issue

Vol. Volume 25 / Iss. Issue 4

Details open_in_new

Metaheuristic Optimization Review | 2025

Optimization Algorithms for Deep Learning Prediction of Liver cirrhosis: A Survey

Today, new Artificial Intelligence (AI) techniques are utilized to help doctors forecast the occurrence of diseases because of the necessity of sustaining public health and early disease diagnosis. One significant kind of liver damage is liver cirrhosis, which typically results from long-term liver damage brought on by a variety of liver conditions and diseases, including hepatitis, persistent alcoholism, or heredity. We created this review to provide an overview of liver cirrhosis since it is essential to identify it early and prevent the damage from spreading throughout the liver tissues. In order to identify liver cirrhosis from biomedical markers rather than images, this study has recently conducted nine studies overlaying it with various artificial intelligence deep learning techniques. Our suggested approach used various Machine Learning (ML) models to predict the signs of cirrhosis in conjunction with other illnesses. Because this condition is so important, it is important to summarize these studies based on the methodology and findings of detection accuracy and precision.

groups

Aya Ebrahim mail -

Asmaa H. Rabie mail -

El-Sayed M. El-Kenawy mail -

Hossam El-Din Moustafa mail

link https://doi.org/10.54216/MOR.030101

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

Artificial Intelligence in Drug Discovery: A Review of AI Approaches for Target Identification

Artificial Intelligence (AI) has become a revolutionary solution in drug discovery and development in aspects including high costs, long times, and high failure rates. This review describes the development and focuses on areas where AI has been used for target identification, lead optimization, design of new drugs from scratch and drug repurposing. Deep learning frameworks such as generative adversarial networks (GANs), variational autoencoders (VAEs), and explainable AI (XAI) approaches have been instrumental and comparative progress in enhancing the efficacy and specificity of drug discovery processes. AI has made advances in clinical trials, trial conduct, and participant selection, as well as enhanced patient-tailored therapies for personalized medicine. Issues such as data credibility, model explainability, and algorithmic biases are still present, and logical and social sciences' cooperation and code of conduct are needed. As such, this review aligns current developments with these challenges to demonstrate the possibilities of AI in revolutionizing pharma research and enhancing health solutions worldwide.

groups

Faustino D. Reyes mail

link https://doi.org/10.54216/MOR.030102

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review of Machine Learning for Predicting Supply Chain Demand in Retail

This review aims to demonstrate the effectiveness of the ML and DL approaches to demand forecasting in the retail supply chain, proving the superiority of the approaches over conventional statistical methods. Traditional models suit themselves poorly in the face of nonlinear dependencies, outside influences and fluctuating settings, especially in retail. At the same time, Machine Learning methodologies like RandomForest, SVMs, LSTM, and CNN provide astonishing accuracy once the temporal and spatial complexity characteristics of sales information are discovered. The review underlines the consideration of data fusion and feature construction, including macroeconomic indexes, weather, and promotions, in extending the forecasts. Issues like data quality, scalability and interpretability of the model are deliberated upon along with the solutions related to incorporating IoT and blockchain. These innovations imply real-time data capture, high-reliability levels and greater process transparency. On the same note, using enhanced value assessment indicators, usually MAE, RMSE, and MAPE, highlights that model engineering requires careful, distinct selection methods. Thus, this systematic review has put together and analyzed the most recent developments, issues, and trends in applying ML and DL in enhancing inventory management, pricing, and customer satisfaction in the retail industry to stimulate better performance and competitiveness in today's fast-growing market environment.

groups

Mostafa Abotaleb mail

link https://doi.org/10.54216/MOR.030104

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

Artificial Intelligence for Face Recognition in Security Systems: A Review of Algorithms and Challenges

FRT is acknowledged as one of the successful advancements of biometric applications in security, surveillance, health care and innovative solutions. More so, the past decade has seen improvements in deep learning, pre-trained Neural Network Convolutional Neural Networks (CNNs), and combining methods such as ensembles, which have highly improved the FRT's Accuracy and efficiency. Nonetheless, several issues remain – facial expression, illumination, demographic biases or adversarial and backdoor threats. Such limitations require new approaches and tools to enhance FRT's reliability and ethical use. The current review also presents ethical concerns and the social consequences of using FRT.

groups

El-Sayed M. El-kenawy mail -

Anis Ben Ghorbal mail

link https://doi.org/10.54216/MOR.030105

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review of Metaheuristic Optimization for Network Traffic Management in Telecommunications

This review aims to identify metaheuristic optimization and machine learning in the context of network management in the current era and some graphs of real network applications, such as traffic prediction, resource assignment, and network protection. Bio-inspired meta-functions, which model heuristic approaches to problem-solving in nature, have been shown to provide the best solutions to the OP problem and possess properties that make them ideal for optimizing dynamic networks. In the same vein, neural networks and reinforcement learning models have also performed significantly better in optimizing network performance by providing precise forecasts and decision-making adaptabilities. Incorporating these methodologies into folded working models has facilitated the development of solutions for the more complicated new networks such as SDNs, MANETs and IoTs. This review consolidates the most recent work in this field while identifying new advances as revolutionary technologies for refining the next-generation networks; it discusses possible paths for future research to overcome the existing drawbacks.

groups

Sherif. S. M. Ghoneim mail

link https://doi.org/10.54216/MOR.030201

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Metaheuristic Optimization Review | 2025

Metaheuristic Algorithms in Optimizing Structural Design of Bridges: A Review

Metaheuristic optimization algorithms become essential to solving structural design problems because they can handle nonlinear, multiple-mode, large-scale, and other difficulties. This review focuses on how MOAs have been developed and utilized and how they have compared efficiency in structural engineering design optimization. It describes some of the main milestones, such as hybrid and ensemble algorithms, as well as quantum annealing and finite elements, to improve the accuracy of the results. The study organizes and assesses modern approaches scientifically and accentuates their benefits and pitfalls in practical applications. Hypotheses derived from benchmarking and statistical exercises show that enhanced MOAs are reliable and fast in yielding almost ideal structures within a manageable computational frontier. Finally, the review outlines the limitations of the current research and suggests research foci for the future advancement of metaheuristic methods and their use in structural engineering optimization.

groups

Sekar Kidambi Raju mail

link https://doi.org/10.54216/MOR.030202

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Metaheuristic Optimization Review | 2025

A Review of Machine Learning Models for Predicting Air Quality in Urban Areas

Air pollution is a critical environmental issue that threatens almost the world, and public health, ecosystems, and the sustainability of cities are affected by the severe impacts of air pollution. Urbanization and industrialization have been on the run, with escalating pollution levels. Hence, air monitoring and air quality prediction are necessary for such challenges. This review discusses advanced machine learning (ML), deep learning (DL) techniques, and IoT-based study hybrid frameworks for air-quality prediction in urban settings. Integration of different data sets such as meteorological parameters, concentrations of pollutants, and data from satellite imagery, these technologies provide strong and scalable solutions for real-time monitoring and forecasting. Some of the advancements include the use of IoT-enabled sensors, the use of convolutional and recurrent neural networks, and the development of location-specific predictive models. Despite significant evolution, several challenges of data sparsity, computational requirements, and model adaptability remain. This paper casts the technologies as transforming cities into smart and green cities and advancing the cause for continuous innovation and interdisciplinary collaboration to strengthen their effectiveness. These findings add to the advancement of knowledge on air quality prediction methodologies and their crucial role in sustainable urban development.

groups

El-Sayed M. El-kenawy mail

link https://doi.org/10.54216/MOR.030204

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new