A Hybrid Deep Learning Model Combining VGG19 and AD_Net through Feature-Level Fusion for Real-Time Skin Cancer Classification

Ali Atshan; Monji; Faiza

doi:https://doi.org/10.54216/FPA.210206

Journal of Intelligent Systems and Internet of Things | 2026

Assessing Quality Attributes of Microservices in Hadoop and Spark Clusters: A Performance Benchmarking Approach in Dockerized and Non-Dockerized Architectures

The rapid expansion of big data has accelerated the adoption of distributed computing frame- works such as Apache Hadoop and Apache Spark, enabling efficient large-scale data processing. While Spark’s in-memory computation model significantly enhances performance compared to Hadoop’s traditional MapReduce, the deployment architecture—whether Dockerized or non- Dockerized—plays a crucial role in affecting performance, scalability, and resource management. This study evaluates the impact of containerized and non-containerized multi-node cluster architectures on the performance of Hadoop and Spark, utilizing standardized workloads such as WordCount and TeraSort. Key performance metrics, including execution time, throughput, and resource utilization, are analyzed across various configurations with parameter tuning. Beyond pure performance benchmarking, the study also assesses the quality attributes of microservices in big data environments, focusing on scalability, maintainability, fault tolerance, and resource efficiency. The comparative analysis between monolithic and microservice-based architectures highlights the advantages of modularity and independent scaling inherent to microservices. Experimental findings indicate that Spark outperforms Hadoop on small to medium-scale workloads, while Hadoop exhibits superior robustness for processing extremely large datasets. Dockerized deployments offer better resource isolation and management flexibility, whereas non-Dockerized setups demonstrate reduced overhead under certain configurations. These insights contribute to optimizing deployment strategies and architectural decisions for microservices-based big data processing frameworks.

groups

Saad Hussein Abed Hamed mail -

Mondher Frikha mail -

Heni Bouhamed mail

link https://doi.org/10.54216/JISIoT.180216

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2026

Extended EWMA Scheme for Enhanced Maxwell Process Monitoring: An Application to the Industrial Sector

The neutrosophic framework offers a promising direction for modeling data affected by uncertainty. Many quality characteristics in the production industry follow the asymmetric structure of the Maxwell distribution. The neutrosophic VSQ chart serves as a novel tool for monitoring parameters of the neutrosophic Maxwell distribution. However, the existing structure of the neutrosophic VSQ chart, based on the basic Shewhart model, is generally unable to detect small shifts in the production process. In this study, a new control chart designed following the structure of the EWMA chart is developed to efficiently monitor Maxwell-distributed neutrosophic data. The run length properties of the proposed scheme are studied, and Monte Carlo simulations are performed to investigate its statistical characteristics. Numerical results indicate that the proposed chart is effective in detecting small shifts in the process. The practical utility of the proposed chart is demonstrated through a real-world industrial dataset affected by uncertainty.

groups

Fuad S. Alduais mail

link https://doi.org/10.54216/IJNS.270215

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Exploring the Relationship between Social Network Structures and Emotional Contagion using NLP and Network Science

Natural Language Processing (NLP) and&ensp;Network Science were combined to study emotional contagion dynamics in social media networks. We simulated the&ensp;diffusion of emotions through users on a synthetic interaction network using sentiment-labeled Twitter data and a graph-based model. We explored the relationship between graph metrics, including centrality and clustering coefficient, on emotion&ensp;propagation and stability. The findings show that&ensp;emotion intensity converges through the network and that both weak coupling of central nodes and moderate cluster structures dampen the spread of emotion. A community-level analysis reveals more alternative&ensp;results, such as the fact that emotions differ in polarity between communities. Our work demonstrates a better understanding of how emotional behavior in online environments can be adjusted using semantic measures, which offer a&ensp;means to characterize the relevance of information online and the interconnected relationships among emotionality.

groups

Prapti Pandey mail -

Vivek Shukla mail -

Rohit Miri mail -

Praveen Chouksey mail -

Parul Dubey mail -

Rohit Raja mail

link https://doi.org/10.54216/JISIoT.180217

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

A Two-Stage Hybrid AI Framework for Robust and Real-Time Driver Drowsiness Detection

Driver drowsiness detection is an important aspect of intelligent transportation systems that aim to reduce fatigue-related accidents. The existing schemes based on threshold-based method, or deep-learning based models often found to be associated with issues in terms of flexibility, computational efficiency, or capacity for real-time performance. This paper presents a development of two-stage hybrid framework for driver drowsy detection, where the first stage utilizes a fuzzy-logic based approach applied to physiological measures, facial feature, head position, blink duration, and eye movements to produce lightweight and adaptive analyses of sleepiness in drivers. The second stage consists of a hybrid quantum-classical neural network (HQCNN), in which convolutional neural networks (CNN) extract spatial features whereas quantum fully connected (QFC) components apply entanglement-based transformations to improve both feature characterization and classification accuracy. The experimental result validates effectiveness of the proposed hybrid method with 94% accuracy, and better than traditional CNNs with real-time capability. The proposed framework is developed to achieve a balance between computational efficiency and classification/decision quality thereby making it suitable for driver monitoring in real-time application.

groups

Gowrishankar Shiva Shankara Chari mail -

Jyothi Arcot Prashant mail

link https://doi.org/10.54216/JISIoT.180218

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Enhancing Osteoporosis Detection with Hybrid Fuzzy Logic Preprocessed Convolutional Neural Networks

  This paper applies deep learning techniques in classifying X-ray images to detect osteoporosis. Osteoporosis, a bone weakness condition, increases the risk of fractures; therefore, accurate early diagnosis is essential in management. We have designed a hybrid method called Fuzzy Logic Preprocessed Convolutional Neural Network, or FLPCNN, wherein fuzzy logic is used at the preprocessing step to handle uncertainty and imprecision of features extracted from X-ray images. This paper used a dataset of X-ray images, and the FLPCNN model was applied, classifying them into osteoporotic and non-osteoporotic with quite an accuracy of 100%. Fuzzy logic preprocessing combined with Convolutional Neural Networks (CNN) enhances the model’s classification accuracy and interpretable decisions. The proposed method would be a new way to cut down diagnostic errors and improve patient outcomes, opening ways for further research into deep learning techniques applied in healthcare.

groups

Murtadha M. Hamad mail -

Azmi Tawfeq Hussein Alrawi mail

link https://doi.org/10.54216/FPA.210201

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Barriers to E-Government Implementation in Developing Countries: A PEST Analysis of Citizens' Perceptions in Iraq

E-government implementation in developing countries faces obstacles and challenges far beyond being a simple technology., By interviewing citizens through its enhanced PEST (Political, Economic, Social, and Technological) analysis and artificial intelligence algorithms, this study systematically evaluates the experiments of Iraq to accommodate e-government service. 1,081 Iraqi citizens were surveyed using mixed methods to quantify their public acceptance and willingness of e-government services, as well as identifying the obstacles. Our investigation finds that data security (mean = 3.59-3.80), the political situation, economic distress, a lack of enthusiasm for change in society, and shortfalls of technological infrastructure are all serious challenges at present. The research used advanced statistical methods, including correlation analysis (0.634 technology-trust relationship), regression models (R ^ 2 = 0.542), factor analysis (KMO = 0.891), and Multi-Layer Perceptron (MLP) neural network algorithms achieved 89.8% prediction accuracy for e-government acceptance. The AI algorithm supported the conclusions drawn from statistical tests, with Technology Readiness and Security Perception rising up as two most significant predictors (23.4% importance for Technology Readiness and 19.8% importance for Security Perception). The findings also propose a novel methodological framework that integrates traditional statistical analysis with machine learning capabilities, rendering concrete recommendations to developing country policy makers. The study's findings imply that successful e-government implementation requires a holistic approach that factors in political, economic, social and technological aspects together. The composite PEST index score of 0.826 smells widespread resistance on the ground, although AI predictive model greatly facilitates forecasting for future e-government initiatives.

groups

Yaman Huthaifa Saeed Aldewachi mail

link https://doi.org/10.54216/FPA.210202

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Models and Algorithms for Minimizing Errors in Managing the Consumption of Fuel and Energy Resources

Managing fuel and energy resources (FER) efficiently is still a major challenge for energy-intensive industries like oil and gas. This paper presents a practical framework that combines mathematical models with easy-to-run algorithms to plan and control FER use in real time. Our twin goals are to cut costs and keep equipment dependable. We first outline the main parts of an energy-management system for an oil-and-gas operation, and then list the key tasks, factors, and decision criteria. The framework has two complementary paths: Path 1 relates FER use to production output via Lagrange optimization, while Path 2 fine-tunes forecasts with a simple least-squares correction based on metered data. Both paths are implemented as executable algorithms and tested on real electricity and fuel-gas datasets. The new method cuts monthly FER-planning errors by up to 80 %, reducing penalties and helping equipment last longer.

groups

Murodjon Sultanov mail -

Botirjon Karimov mail -

Olimjon Uralov mail -

Nodir Akbarov mail

link https://doi.org/10.54216/FPA.210203

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

Deep Sequence Modeling of Dump Truck Sensor Data for Fuel Efficiency and Engine Health Prediction

The Fourth Industrial Revolution represents a shift to a more connected, digital world across all industries, including mining. The application of smart sensors will reduce site risks and fuel consumption, reduce equipment breakdowns, improve preventative maintenance, and improve equipment efficiency, including dump truck engines. Dump truck fuel efficiency is influenced by a number of real-world factors, including driver behavior, road and weather conditions, and vehicle specifications. Additionally, potential engine failures and other aspects can impact vehicle outcomes. By using dynamic on-road data to predict fuel consumption per trip, the industry can effectively minimize the expense associated with driving evaluations. Furthermore, analysis of data provides valuable insights into identifying the underlying causes of fuel consumption by analyzing input parameters. This paper proposes and evaluates novel models for predicting dump truck fuel consumption and engine failures in open-pit mining. These models combine the power of features derived from data collected locally by dump truck sensors and their analysis. The fuel consumption prediction architecture for open-top mining trucks using an improved Long Short-Term Memory (LSTM) model and a double-layer thick Deep Neural Network (DNN) forms the basis of the model design, which consists of two separate components. Multi-delay Recurrent Neural Network (RNN) models have been found to be efficient and accurate. The RNN architecture is applied to capture the cyclic components and complex rules in engine consumption data. This research relied on essential factors (route, vehicle speed, engine revolutions, and engine load). The proposed model outperforms existing models, achieving (MAE=0.0210), (RMSE=0.0294), (MSE=0.0009), and accuracy (R²=0.9842), demonstrating that it can produce highly accurate predictions.

groups

Raed Majeed mail -

Hiyam Hatem mail

link https://doi.org/10.54216/FPA.210204

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

An Explainable AI Fusion-Based Model for Enhanced Deepfake Detection Using Vision Transformer and InceptionResNetV1

Generative AI has made significant strides over the past few years, and this progress has accelerated the development of deepfake techniques, which can unfortunately be used for harmful purposes. It is essential to stay up-to-date with this advancement. In this paper, we present an explainable weighted average fusion deepfake detection system that combines Vision Transformer (ViT) and InceptionResNetV1 to improve classification accuracy. We also employed LIME and GradCAM++ to provide interpretability for the model decision. ViT utilizes self-attention modules to extract features, whereas InceptionResNetV1 employs convolutional layers to extract spatial features. Grad-CAM++ highlights the important regions influencing classification, and LIME examines the regional contributions. Together, these tools offer a deeper understanding of the model's decision-making process. Our fusion technique combines the outputs of both models by assigning specific weights that users can adjust interactively through the user interface. The use of these tools gives a better understanding of how the model classifies, which improves transparency and reliability in the models. The performance of the fusion strategy is tested with accuracy, precision, recall, and F1-score. Our proposed model achieves a classification accuracy of 99.19%, surpassing both ViT and InceptionResNetV1 when we evaluated them individually. To the best of our knowledge, this work represents the first deepfake detection model that combines Vision Transformer (ViT) and InceptionResNetV1 using a weighted averaging fusion approach with dual explainability techniques.

groups

Yousef A. Alsamaani mail -

Murad A. Rassam mail

link https://doi.org/10.54216/FPA.210205

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new

Fusion: Practice and Applications | 2026

A Hybrid Deep Learning Model Combining VGG19 and AD_Net through Feature-Level Fusion for Real-Time Skin Cancer Classification

Automated detection (AD) techniques are essential for early recognition of skin cancer. Hybrid models using feature fusion, which combine pre-trained CNNs with customized models, have shown superiority in real-time skin cancer pathology classification. This study combines VGG19 feature maps with a novel learning network based framework called AD_Net to enhance classification accuracy. VGG19 facilitated robust low-level feature extraction, while AD_Net brilliantly extracts specialized patterns. This strategy provided a flexible and fast architecture, suitable for real-time medical applications. This work led to the classification of three of the most lethal skin cancer types. The model was trained and validated using experiments on the publicly available ISIC2019 dataset. In order to improve the interpretability of the model's predictions, interpretable artificial intelligence (XAI) techniques particularly Grad-CAM were applied. Four baseline models EfficientNetB0, MobileNetV2, Inception-v3, and VGG16, were used to assess the proposal's efficacy. The suggested model outperformed the four baseline models with 99.18% accuracy, 99.0% precision, 99.0% recall, and 99.0% F1 score. Dermatologists and other medical professionals can use this method to detect skin cancer early.

groups

Ali Atshan Abdulredah mail -

Monji kherallah mail -

Faiza Charfi mail

link https://doi.org/10.54216/FPA.210206

Volume & Issue

Vol. Volume 21 / Iss. Issue 2

Details open_in_new