Biological pathways underlying major depressive disorder (MDD) can be viewed as systems biology networks. The psycho-immune-neuroendocrine (PINE) network comprises central nervous, immune, endocrine and autonomic systems, integrating biological mechanisms of MDD. Such networks exhibit recurrent motifs with specific functions, including positive and negative feedback loops, and are subject to critical transitions, influenced by feedback loop transitions (FLTs). We aim to identify critical feedback loops and their FLTs, as well sentinel network nodes (SNNs), key network nodes that drive FLTs, within the PINE network. Examples of biomarkers are provided which may reflect early warning signs of impending critical transition to MDD. Disruption of homeostatic feedback loops reflects the physiological transition to MDD. Putative FLTs are identified within hypothalamic-pituitary-adrenal (HPA) and sympathetic-parasympathetic axes, the kynurenine pathway, gut function and dysbiosis. Progression from health to disease is driven by FLTs in the PINE network, which is likely to undergo changes characteristic of system instability. Biomarkers of system instability may effectively predict the critical transition to MDD.

In recent years, cryptocurrencies have received substantial attention from investors, researchers and the media due to their volatile behaviour and potential for high returns. This interest has led to an expanding body of research aimed at predicting cryptocurrency prices, which are notably influenced by a wide array of technical, sentimental, and legal factors. This paper reviews scholarly content from 2014 to 2024, employing a systematic approach to explore advanced quantitative methods for cryptocurrency price prediction. It encompasses a broad spectrum of predictive models, from early statistical analyses to sophisticated machine and deep learning algorithms. Notably, this review identifies and discusses the integration of emerging technologies such as Transformers and hybrid deep learning models, which offer new avenues for enhancing prediction accuracy and practical applicability in real-world scenarios. By thoroughly investigating various methodologies and parameters influencing cryptocurrency price predictions, including market sentiment, technical indicators, and blockchain features, this review highlights the field’s complexity and rapid evolution. The analysis identifies significant research gaps and under-explored areas, providing a foundational guideline for future studies. These guidelines aim to connect theoretical advancements with practical, profit-driven applications in cryptocurrency trading, ensuring that future research is both innovative and applicable.

Electricity has become an indispensable source of energy, and power lines play a crucial role in the functioning of modern societies. It is essential to inspect power lines promptly and precisely in order to ensure the safe and secure delivery of electricity. In steep and mountainous terrain, traditional surveying methods cannot inspect power lines precisely due to their nature. Remote sensing platforms, such as satellite and aerial images, thermal images, and light detection and ranging (LiDAR) points, were utilised for the detection and inspection of power lines. Nevertheless, with the advancements of remote sensing technologies, in recent years, LiDAR surveying has been favoured for power line corridor (PLC) inspection due to active and weather-independent nature of laser scanning. Laser ranging data and the precise location of the LiDAR can be used to generate a three-dimensional (3D) image of the PLC. The resulting 3D point cloud enables accurate extraction of power lines and measurement of their distances from the forest below. In the literature, there have been many proposals for power line extraction and reconstruction for PLC modelling. This article examines the pros and cons of each domain method, providing researchers involved in three-dimensional modelling of power lines using innovative LiDAR scanning systems with useful guidelines. To achieve these objectives, research papers were analysed, focusing primarily on geoscience-related journals and conferences for the extraction and reconstruction of power lines. There has been a growing interest in examining the extraction and reconstruction of power line spans with single and multi-conductor configurations using different image and point-based techniques. Our study provides a comprehensive overview of the methodologies offered by various approaches using laser scanning data from the perspective of power line extraction applications, as well as to discuss the benefits and drawbacks of each approach. The comparison revealed that, despite the tremendous potential of aerial and mobile laser scanning systems, human intervention and post-processing actions are still required to achieve the desired results. In addition, the majority of the methods have been evaluated on the small datasets, and very few methods have been focused on multi-conductor extraction and reconstruction for power lines modelling. These barriers hinder the automated extraction and reconstruction of power line using LiDAR data and point to unexplored areas for further research and serve as useful guidelines for future research directions. Several promising directions for future LiDAR experiments using deep learning methods are outlined in the hope that they will pave the way for applications of PLC modelling and assessment at a finer scale and on a larger scale.

Existing approaches that extract buildings from point cloud data do not select the appropriate neighbourhood for estimation of normals on individual points. However, the success of these approaches depends on correct estimation of the normal vector. In most cases, a fixed neighbourhood is selected without considering the geometric structure of the object and the distribution of the input point cloud. Thus, considering the object structure and the heterogeneous distribution of the point cloud, this paper proposes a new effective approach for selecting a minimal neighbourhood, which can vary for each input point. For each point, a minimal number of neighbouring points are iteratively selected. At each iteration, based on the calculated standard deviation from a fitted 3D line to the selected points, a decision is made adaptively about the neighbourhood. The selected minimal neighbouring points make the calculation of the normal vector accurate. The direction of the normal vector is then used to calculate the inside fold feature points. In addition, the Euclidean distance from a point to the calculated mean of its neighbouring points is used to make a decision about the boundary point. In the context of the accuracy evaluation, the experimental results confirm the competitive performance of the proposed approach of neighbourhood selection over the state-of-the-art methods. Based on our generated ground truth data, the proposed fold and boundary point extraction techniques show more than 90% F1-scores.