Fusion of Brain Imaging Data with Artificial Intelligence to detect Autism Spectrum Disorder

Monalin; Rubini

doi:https://doi.org/10.54216/FPA.140207

Journal of Sustainable Development and Green Technology | 2024

Enhancing Business Sustainability through Stock Analysis: A Machine Learning Approach

This study explores the integration of machine learning methodologies in stock analysis to enhance the understanding of the relationship between sustainable business practices and financial performance. Against the backdrop of a shifting investment landscape that emphasizes responsible and informed decision-making, our research addresses the need for innovative approaches in evaluating stocks within a sustainability framework. Leveraging a combination of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and linear regression, we systematically analyze a dataset comprising sustainability metrics and stock performance. The DBSCAN clustering identifies distinct groups of stocks based on sustainability profiles, offering novel insights into market segmentation. Concurrently, linear regression models quantitatively reveal the impact of sustainability metrics on stock outcomes. The results affirm the significance of sustainability considerations in investment decisions, presenting a compelling case for the adoption of machine learning techniques in responsible investing strategies.

groups

Noura Metawa mail -

Saad Metawa mail

link https://doi.org/10.54216/JSDGT.040104

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Journal of Sustainable Development and Green Technology | 2024

Enhancing Business Sustainability through an Intelligent Framework for Unveiling Financial Frauds

The aim of this research is to examine the convergence of intelligent frameworks and financial fraud detection as a strategic approach for strengthening business sustainability in the banking industry. A rigorous preprocessing regimen, which includes data cleansing, normalization, and SMOTE algorithm application for class rebalancing, sets the stage for a refined dataset. Our proposed framework employs Logistic Regression, Decision Trees, and Gradient Boosting models to conduct a multifaceted analysis that accommodates both linear and non-linear relationships within the data. The results are presented through visual representations such as distribution plots and RoC curves that confirm the effectiveness of the framework in detecting potentially fraudulent activities. The comparative analysis offers detailed insights into how versatile the framework is. This study contributes to the broader discourse on intelligent systems in financial fraud detection with practical implications for businesses seeking to enhance their sustainability through advanced risk management strategies.

groups

Rhada Boujlil mail -

Saad Alsunbul mail

link https://doi.org/10.54216/JSDGT.040105

Volume & Issue

Vol. Volume 4 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2023

Enhancing Business Sustainability through Strategic Approach for ESG Integration and Risk Score Analysis

In response to the evolving dynamics of corporate responsibility, this research explores the integration of Environmental, Social, and Governance (ESG) factors in sustainable business modeling. The study addresses the pressing need for a strategic framework by delving into the complex interplay between ESG considerations and risk score analysis. Leveraging a comprehensive dataset from S&P500 ESG Scores, our methodology employs the CATBoost algorithm, a categorical boosting technique, for predictive modeling. CATBoost's unique ability to handle categorical variables seamlessly is particularly advantageous for datasets with diverse data types, commonly encountered in ESG analysis. Additionally, we apply SHAP (Shapley additive explanations) methods to shed light on the influential factors shaping our model's predictions, enhancing interpretability. The results, presented through sector-wise ESG analyses, pairwise scatter plots, and distribution analyses, offer a granular understanding of ESG performance across various industries. Furthermore, the SHAP explanation methods provide insights into the relative impact of individual ESG factors on predictive outcomes. The findings not only contribute to the empirical understanding of sustainable business practices within the S&P500 but also offer practical insights for businesses seeking to enhance their ESG integration strategies.

groups

Noura Metawa mail -

Saad Metawa mail

link https://doi.org/10.54216/FinTech-I.030103

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2023

Towards Financial Sustainability: Integrating Business Intelligence in Fintech Operations

This study explores the integration of Business Intelligence (BI) techniques to foster sustainability within the Financial Technology (Fintech) sector. The background elucidates the transformative evolution of the Fintech industry and the increasing imperative to align its practices with sustainable principles. The problem statement addresses the gap in understanding the intricate relationship between BI strategies and sustainability within Fintech enterprises. Employing a mixed-methods approach, including literature review synthesis and the application of the Autoregressive Integrated Moving Average (ARIMA) model, our methodology seeks to provide a systematic and replicable framework for empirical investigation. The results encompass additive and multiplicative summaries, detrended and deseasonalized analyses, and partial and autocorrelation plots, shedding light on critical temporal dynamics and patterns within the Fintech domain.

groups

Rhada Boujlil mail -

Saad Alsunbul mail

link https://doi.org/10.54216/FinTech-I.030104

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2023

WASPAS Multi-Criteria Decision-Making Method for Assessment Effectiveness and Performance Intelligent Transportation Systems Alternatives

The assessment of Intelligent Transportation Systems (ITS) plays a vital role in understanding their effectiveness, efficiency, and impact on transportation networks. This abstract provides an overview of the criteria for assessing ITS and highlights the importance of a comprehensive and multidimensional approach. The requirements discussed include safety, efficiency, mobility, environmental impact, user satisfaction, cost-effectiveness, scalability and interoperability, data security and privacy, technological reliability and resilience, regulatory and policy compliance, equity and accessibility, system integration, innovation and future-readiness, stakeholder engagement, performance monitoring and evaluation, resilience and disaster preparedness, social and economic impact, and continuous improvement and adaptation. By considering these criteria, stakeholders can gain valuable insights into the performance and benefits of ITS, aiding in decision-making, policy development, and future planning for transportation systems. This study uses multi-criteria decision-making (MCDM) methodologies, such as the assessing attractiveness method and the weighted aggregated sum product assessment (WASPAS) method. The WASPAS method is used to rank the alternatives. We used 18 criteria and 8 alternatives to be organised. The sensitivity analysis is conducted to check the stability of the results.

groups

Abedallah Z. Abualkishik mail -

Rasha Almajed mail

link https://doi.org/10.54216/FinTech-I.030105

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2023

Enhancing Malware Detection in Cybersecurity through Optimized Machine Learning Technique

This research is about the increasing cybersecurity challenges posed by modern malware threats and argues for an improved approach through optimized machine learning algorithms. We apply a Tree-structured Parzen Estimator (TPE) for hyperparameter tuning, focusing on the optimization of tree-based models such as Random Forest and Gradient Boosting. Our methodology includes careful correlation analysis, variable distribution examination, and feature importance assessment to make our models more robust and transparent. We present comprehensive visualizations that demonstrate the results of our optimized approach, which show improved accuracy, precision, and recall in malware detection. Our findings highlight the significance of feature engineering and model tuning, revealing subtle patterns indicative of malicious behavior. The findings indicate that our model provides a method that not only improves detection capabilities but also emphasizes the need for continuous improvement and innovation in addressing the ever-changing nature of malware threats.

groups

Ahmed Aziz mail -

Sanjar Mirzaliev mail -

Yuldashev Maqsudjon mail

link https://doi.org/10.54216/IJAACI.040203

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2023

Enhancing Information Fusion from UAV-Captured High-Altitude Infrared Imagery through Machine Learning

Unmanned aerial vehicles (UAVs) equipped with high-altitude infrared imaging have revolutionized data collection, providing better spatial and temperature resolutions. However, an effective way to fuse and interpret this multidimensional data remains a challenge. Therefore, this research tackles this issue by incorporating machine learning specifically the YOLO object detector to fuse and analyze information from UAV-captured high-altitude infrared images. The process entails a careful fusion of data, feature extraction, and model configuration that is tailored to the unique qualities of infrared imagery. Furthermore, the confabulated YOLO model performs exceptionally well in detecting and localizing objects within the thermal spectrum. Results showed precise identification of objects as well as their localization thus indicating potential for advanced aerial surveillance and monitoring. This research represents a significant advancement in situation awareness across environmental monitoring, infrastructure inspection, and disaster response among other areas hence demonstrating the transformative ability of machine learning in aerial imaging analysis.

groups

Mustafa El-Taie mail -

Aaras Y. Kraidi mail

link https://doi.org/10.54216/IJAACI.040204

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2024

Securing the Skies: A Study of Cybersecurity Measures in Unmanned Aerial Vehicles

This study examines the importance of cybersecurity in Unmanned Aerial Vehicles (UAVs) due to the increasing technological advancements and subsequent vulnerabilities in these aerial systems. The rapid integration of UAVs across various sectors has led to a pervasive threat of cyber attacks, which necessitates comprehensive defenses to mitigate potential risks. This research outlines the complex landscape of UAV cybersecurity challenges through an in-depth analysis of attack scenarios and data features within the ECU-IoFT dataset. Using the XGBoost algorithm’s robustness, this study presents a proactive approach to classifying and mitigating cyber threats targeting UAV systems. Our findings demonstrate that XGBoost is effective at identifying different attack vectors, making it a possible key defense mechanism. The insights from this study not only highlight the changing nature of UAV cybersecurity but also provide practical steps for strengthening these aerial systems against imminent cyber threats to ensure their safe and resilient operation across multiple domains.

groups

Ahmed Mohamed Zaki mail -

Abdelaziz A. Abdelhamid mail -

Abdelhameed Ibrahim mail -

Marwa M. Eid mail -

El-Sayed M. El-Kenawy mail

link https://doi.org/10.54216/IJWAC.080106

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2024

Internet of Things Enabled Based Arrhythmia Classification using Dandelion Optimization Algorithm with Ensemble Learning

Internet of Things (IoT) based Arrhythmia Classification is a cutting-edge algorithm that amalgamates the abilities of the IoT and advanced medical diagnosis to revolutionize the detection and classification of arrhythmias—irregular heartbeats that may indicate fundamental cardiovascular issues. This technique leverages IoT devices, namely connected health monitors and wearable sensors, to continuously gather electrocardiogram (ECG) information from individuals. This information, streamed in real-time, provides a great opportunity for timely and remote monitoring of cardiac health. Leveraging the abilities of deep learning and IoT, this technique provides an automated and more sophisticated means of classifying and detecting arrhythmias, improving the efficiency and accuracy of diagnoses. This article presents an Internet of Things Enabled Based Arrhythmia Classification using the Dandelion Optimization Algorithm with Ensemble Learning (AC-DOAEL) method. The presented AC-DOAEL technique utilizes IoT-based data collection with an ensemble learning-based classification process. For the arrhythmia detection and classification process, the AC-DOAEL technique follows an ensemble learning algorithm such as long short-term memory (LSTM), autoencoder (AE), and bidirectional LSTM (BiLSTM) models. To improve the recognition rate of the ensemble models, the AC-DOAEL technique uses DOA as a hyperparameter optimizer. The simulation outcomes of the AC-DOAEL method are well-studied on benchmark ECG data. The experimental result analysis inferred the greater performance of the AC-DOAEL algorithm with other techniques.

groups

T. Vivekanandan mail -

J. Jegan mail -

D. Jagadeesan mail -

Y. Sreeraman mail -

N. Ch. S. N. Iyengar mail -

E. Purushotham mail

link https://doi.org/10.54216/JISIoT.110206

Volume & Issue

Vol. Volume 11 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2024

Fusion of Brain Imaging Data with Artificial Intelligence to detect Autism Spectrum Disorder

Autism, a developmental and neurological disorder, impacts communication, interaction, and behavior, setting individuals with it apart from those without. This spectrum disorder affects various aspects of an individual's life, including social, cognitive, emotional, and physical health. Early detection and intervention are crucial for symptom reduction and facilitating learning and development. Recent advancements in machine learning and deep learning have facilitated the diagnosis of Autism by analyzing brain signals. This current study introduces an approach for Autism detection utilizing functional Magnetic Resonance Imaging (fMRI) data. The Autism Brain Imaging Data Exchange (ABIDE) dataset serves as the foundation, employing hierarchical graph pooling to abstract brain images into a graph structure. Graph Convolutional Networks are then used to learn node embeddings derived from sparse feature vectors. The model attains an accuracy of 87% on the 10-fold cross-validation dataset. This study proves to be cost-effective and efficient in identifying Autism through fMRI, making it suitable for near real-time applications.

groups

Monalin Pal mail -

Rubini P. mail

link https://doi.org/10.54216/FPA.140207

Volume & Issue

Vol. Volume 14 / Iss. Issue 2

Details open_in_new