Emerging Technologies and Engineering Journal

Averaging-Based Hybrid Ensemble of DenseNet-121 and ResNet-50 for Computer-Aided Brain Tumour Diagnosis: A Step Towards Early Detection

2025-12-19T22:12:24-07:00

One of the deadliest diseases that can affect children and adults is a brain tumour. A brain tumour is the abnormal growth of cells in the brain or near it. Commonly, there are two types of tumours: malignant (cancerous) and benign (non-cancerous). The importance of early detection of brain tumours cannot be overstated, as tumours progress rapidly and decrease survival rates. Due to the complexity of brain tumour structure and classification, manual inspection can lead to false-positive or false-negative results. The complexity of tumour detection can be reduced by using deep learning segmentation and classification models. This paper proposes an AI-driven solution for screening brain tumours using MRI images, emphasising improving the model’s sensitivity to reduce missed tumour cases. A deep hybrid ensemble model is developed by combining two CNN models using an averaging ensemble learning technique. The models were trained and evaluated on a publicly available MRI dataset consisting of 4,845 images. Four state-of-the-art deep learning architectures were trained and evaluated, and the best-performing models were combined through the ensemble technique. Our final model achieves 98.49% accuracy and 97.58% sensitivity. Compared with a recent ensemble-based baseline, the proposed approach reduces error rate and false negative cases, improving robustness and clinical reliability.

From Proof of Concept to Industrial Deployment: Application of Multi-Level FBS, TRIZ and Lean Six Sigma to Wave Energy Conversion

2026-03-18T05:57:25-06:00

This study presents a structured, integrated methodology that combines Lean Six Sigma and TRIZ to support the transition of a wave energy converter from a laboratory proof-of-concept to an industrializable system. It addresses key techno-economic challenges, including high cost, limited efficiency, maintenance constraints, and scalability limitations, by systematically resolving underlying technical contradictions through the DMAIC framework. In the Define phase, industrial requirements were established, focusing on robustness, maintainability, and performance under irregular wave conditions. A laboratory-scale prototype based on a point absorber coupled to a linear generator was developed to validate the wave-to-wire conversion concept. The Measure phase quantified system performance, recording peak voltages up to 3.7 mV and demonstrating a correlation (R² = 0.75) between experimental and theoretical results. The analyze phase integrated performance data with Function-Behaviour-Structure analysis to identify root causes and key contradictions in system scaling. In the Improve phase, TRIZ tools were used to generate optimised design solutions, including coil redesign, hydrodynamic improvements, and a segmented generator architecture. Finally, the Control phase outlines a roadmap for a Generation 2 prototype under real sea conditions. Overall, the study contributes a systematic, need-driven framework that bridges the gap between conceptual validation and industrial deployment, while proposed design solutions require further experimental validation.

Application of an Integral-PID-Like-SMC (IPS) for Cruise Control

2026-01-23T22:56:11-07:00

This study presents the application of an enhanced Proportional–Integral–Derivative (PID)-like Sliding Mode Controller (SMC), referred to as the Integral PID-like Sliding Mode (IPS) controller, for cruise control systems. Robustness remains a critical requirement in cruise control applications, particularly with the increasing use of automation and intelligent vehicle systems. During operation, cruise controllers must compensate for various uncertainties and disturbances, including changes in fuel weight due to consumption, variations in passenger and luggage loads, aerodynamic effects, frictional changes caused by road conditions, and variations in road inclination. As autonomous vehicle technologies continue to advance, improved control strategies are required to ensure smoother and more reliable system performance. Several control approaches have been proposed for cruise control systems. Although nonlinear control methods provide strong robustness and high precision, their implementation often involves significant computational complexity. The proposed IPS approach addresses this limitation by combining the robustness of sliding mode control with a PID-like structure and an additional integral component. The performance of the IPS controller was evaluated and compared with conventional PID control and standard SMC under disturbance conditions. The IPS control law contains fewer components than the standard SMC while maintaining comparable or improved performance. Simulation results demonstrate that the IPS controller achieves enhanced precision and robustness with reduced computational complexity, making it suitable for real-time implementation.

Simplified Sliding Mode Control of a Single-Link Planar Robot

2026-02-14T19:41:38-07:00

Robotic technologies are becoming more advanced and are becoming more popular. Requirements are high levels of accuracy and operational speed, such as in surgery and manufacturing. These targets were highly challenging and could be enhanced by employing suitable control systems. Nonlinear control schemes were characterised by high accuracy and robustness, but by high computational time. Hence, the study simplified the Sliding Mode Control (SMC) scheme for a single link planar robot and was referred to as the Simplified Sliding Mode Control (RSMC), which was compared with the normal version referred to as Normal Sliding Mode Control (NSMC) and the gain scheduling based Proportional Derivative Control (GPDC). The effect considered was friction, and it was limited to simulation studies conducted using the SIMULINK/MATLAB software. Results showed that the proposed controller, RSMC, has an algorithm length that is at least 50% shorter than that of the NSMC, with a simplicity similar to that of the GPDC. Results also indicated achieving a settling time of 1.5s, a rise time of 0.8s, 0% overshoot, and a cumulative error of about 250, maintaining the same results with disturbance. The system with the NSMC showed the corresponding parameters as 2.0s, 1.8s, 0% and 260, respectively, without disturbance, and as 3s, 3s, 0% and 310, respectively, with disturbance. It therefore implied that a shorter RSMC algorithm means lower execution time. The RSMC showed superior performance, indicating higher accuracy, operational speed and robustness.

Design of Anaerobic Co-Digestion and Integrated Fuzzy Logic Method for Optimization of Biogas Production from Mixed Livestock Waste

2026-03-18T05:58:46-06:00

Anaerobic co-digestion of livestock waste presents a viable approach for addressing environmental challenges and reducing greenhouse gas emissions in semi-urban and rural contexts. This study focuses on the development of an optimised anaerobic digestion system for treating cow, sheep, and goat manure in the small Bnaslawa village, located in the Erbil Governorate of Iraq. Quantitative assessments of daily manure production were conducted to evaluate feedstock availability and guide the design parameters of the digester. The resulting system was engineered with a total volume of 836.96 m³ and an organic loading rate of 4.42 kg volatile solids (VS) per cubic meter per day. To improve operational performance and enhance predictive reliability, a fuzzy-logic-based modelling framework was implemented in MATLAB R2023a. This computational model facilitated the identification of optimal process conditions and projected a daily biogas yield of approximately 2436.25 m³, of which methane constituted 1461.75 m³. The integration of systematic engineering design with intelligent modelling techniques underscores the potential of this approach for renewable energy production and sustainable waste management. The fuzzy logic model improves methane output estimation, supporting informed decision-making in waste-to-energy applications.