Class imbalance is a pervasive challenge in real-world machine learning (ML) applications, where the minority class, often the class of interest, is significantly underrepresented. This imbalance can degrade model performance, result in misleading evaluation metrics, and complicate validation processes. Two prominent data-augmentation techniques to address class imbalance are the Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN). However, both techniques have inherent limitations, motivating the emergence of novel variants designed to overcome these challenges. While previous reviews have typically focused on specific domains, conventional methodologies, or broad strategy overviews, this review presents a unified taxonomy that outlines the causes, types, and implications of class imbalance across diverse ML tasks. It further examines emerging trends in the application of SMOTE and GAN techniques, their limitations, and hybrid adaptations. By categorising imbalance types and analysing models, metrics, datasets, and comparative approaches, this review provides actionable insights and identifies future research directions for practitioners and researchers working to address class imbalance in real-world ML tasks.

Objective: To perform a systematic review of the literature exploring magnetic resonance imaging (MRI) methods for measuring natural brain tissue pulsations (BTPs) in humans. Methods: A prospective systematic search of MEDLINE, SCOPUS and OpenGrey databases was conducted by two independent reviewers using a pre-determined strategy. The search focused on identifying reported measurements of naturally occurring BTP motion in humans. Studies involving non-human participants, MRI in combination with other modalities, MRI during invasive procedures and MRI studies involving externally applied tests were excluded. Data from the retrieved records were combined to create Forest plots comparing brain tissue displacement between Chiari-malformation type 1 (CM-I) patients and healthy controls using an independent samples t-test. Results: The search retrieved 22 eligible articles. Articles described 5 main MRI techniques for visualisation or quantification of intrinsic brain motion. MRI techniques generally agreed that the amplitude of BTPs varies regionally from 0.04 mm to ~ 0.80 mm, with larger tissue displacements occurring closer to the centre and base of the brain compared to peripheral regions. Studies of brain pathology using MRI BTP measurements are currently limited to tumour characterisation, idiopathic intracranial hypertension (IIH), and CM-I. A pooled analysis confirmed that displacement of tissue in the cerebellar tonsillar region of CM-I patients was + 0.31 mm [95% CI 0.23, 0.38, p < 0.0001] higher than in healthy controls. Discussion: MRI techniques used for measurements of brain motion are at an early stage of development with high heterogeneity across the methods used. Further work is required to provide normative data to support systematic BTPs characterisation in health and disease.

Understanding the pulsing dynamics of tissue and fluids in the intracranial environment is an evolving research theme aimed at gaining new insights into brain physiology and disease progression. This article provides an overview of related research in magnetic resonance imaging, ultrasound medical diagnostics and mathematical modelling of biological tissues and fluids. It highlights recent developments, illustrates current research goals and emphasizes the importance of collaboration between these fields.

This paper describes the design and successful implementation of a constrained model predictive controller with integral action for the control of a Twin Rotor MIMO System (TRMS). The integral action guarantees zero steady-state error in set-point tracking with robustness toward perturbations of the nominal system parameters. In addition to saturation constraints on the input variables, hard constraints are imposed on the controlled output variables, i.e., on pitch and yaw angular positions, to avoid collisions with obstacles. The model predictive controller was designed using a high-fidelity nonlinear model of the TRMS developed in previous work. As an intermediate step, exact linearized models of the TRMS are obtained and their closed-form expressions are reported. The controller was tested experimentally, also showing its effectiveness in ensuring actual collision avoidance by the TRMS when physical obstacles were present.

Hypocapnia is known to affect patients with acute stroke and plays a key role in governing cerebral autoregulation. However, the impact of hypocapnia on brain tissue pulsations (BTPs) is relatively unexplored. As BTPs are hypothesised to result from cerebrovascular resistance to the inflow of pulsatile arterial blood, it has also been hypothesised that cerebral autoregulation changes mediated by hypocapnia will alter BTP amplitude. This healthy volunteer study reports measurements of BTPs obtained using transcranial tissue Doppler (TCTD). Thirty participants underwent hyperventilation to induce mild hypocapnia. BTP amplitude, EtCO₂, blood pressure, and heart rate were then analysed to explore the impact of hypocapnia on BTP amplitude. Significant changes in BTP amplitude were noted during recovery from hypocapnia, but not during the hyperventilation manoeuvre itself. However, a significant increase in heart rate and pulse pressure and decrease in mean arterial pressure were also observed to accompany hypocapnia, which may have confounded our findings. Whilst further investigation is required, the results of this study provide a starting point for better understanding of the effects of carbon dioxide levels on BTPs. Further research in this area is needed to identify the major physiological drivers of BTPs and quantify their interactions with other aspects of cerebral haemodynamics.