Showing papers by "Tallinn University of Technology published in 2020"

Microbiome definition re-visited: old concepts and new challenges

Abstract: The field of microbiome research has evolved rapidly over the past few decades and has become a topic of great scientific and public interest. As a result of this rapid growth in interest covering different fields, we are lacking a clear commonly agreed definition of the term “microbiome.” Moreover, a consensus on best practices in microbiome research is missing. Recently, a panel of international experts discussed the current gaps in the frame of the European-funded MicrobiomeSupport project. The meeting brought together about 40 leaders from diverse microbiome areas, while more than a hundred experts from all over the world took part in an online survey accompanying the workshop. This article excerpts the outcomes of the workshop and the corresponding online survey embedded in a short historical introduction and future outlook. We propose a definition of microbiome based on the compact, clear, and comprehensive description of the term provided by Whipps et al. in 1988, amended with a set of novel recommendations considering the latest technological developments and research findings. We clearly separate the terms microbiome and microbiota and provide a comprehensive discussion considering the composition of microbiota, the heterogeneity and dynamics of microbiomes in time and space, the stability and resilience of microbial networks, the definition of core microbiomes, and functionally relevant keystone species as well as co-evolutionary principles of microbe-host and inter-species interactions within the microbiome. These broad definitions together with the suggested unifying concepts will help to improve standardization of microbiome studies in the future, and could be the starting point for an integrated assessment of data resulting in a more rapid transfer of knowledge from basic science into practice. Furthermore, microbiome standards are important for solving new challenges associated with anthropogenic-driven changes in the field of planetary health, for which the understanding of microbiomes might play a key role.

Transmission of SARS-CoV-2 by inhalation of respiratory aerosol in the Skagit Valley Chorale superspreading event

Abstract: During the 2020 COVID-19 pandemic, an outbreak occurred following attendance of a symptomatic index case at a regular weekly rehearsal on 10 March of the Skagit Valley Chorale (SVC) After that rehearsal, 53 members of the SVC among 61 in attendance were confirmed or strongly suspected to have contracted COVID-19 and two died Transmission by the airborne route is likely It is vital to identify features of cases such as this so as to better understand the factors that promote superspreading events Based on a conditional assumption that transmission during this outbreak was by inhalation of respiratory aerosol, we use the available evidence to infer the emission rate of airborne infectious quanta from the primary source We also explore how the risk of infection would vary with several influential factors: the rates of removal of respiratory aerosol by ventilation; deposition onto surfaces; and viral decay The results indicate an emission rate of the order of a thousand quanta per hour (mean [interquartile range] for this event = 970 [680-1190] quanta per hour) and demonstrate that the risk of infection is modulated by ventilation conditions, occupant density, and duration of shared presence with an infectious individual Practical Implications During respiratory disease pandemics, group singing indoors should be discouraged or at a minimum carefully managed as singing can generate large amounts of airborne virus (quanta) if any of the singers is infected Ventilation requirements for spaces that are used for singing (eg, buildings for religious services and rehearsal/performance) should be reconsidered in light of the potential for airborne transmission of infectious diseases Meetings of choirs and other kinds of singing groups during pandemics should only be in spaces that are equipped with a warning system of insufficient ventilation which may be detected with CO2 “traffic light” monitors Systems that combine the functions heating and ventilation (or cooling and ventilation) should be provided with a disclaimer saying “do not shut this system off when people are using the room; turning off the system will also shut down fresh air supply, which can lead to the spread of airborne infections”

CREB Family Transcription Factors Are Major Mediators of BDNF Transcriptional Autoregulation in Cortical Neurons

Abstract: BDNF signaling via its transmembrane receptor TrkB has an important role in neuronal survival, differentiation, and synaptic plasticity. Remarkably, BDNF is capable of modulating its own expression levels in neurons, forming a transcriptional positive feedback loop. In the current study, we have investigated this phenomenon in primary cultures of rat cortical neurons using overexpression of dominant-negative forms of several transcription factors, including CREB, ATF2, C/EBP, USF, and NFAT. We show that CREB family transcription factors, together with the coactivator CBP/p300, but not the CRTC family, are the main regulators of rat BDNF gene expression after TrkB signaling. CREB family transcription factors are required for the early induction of all the major BDNF transcripts, whereas CREB itself directly binds only to BDNF promoter IV, is phosphorylated in response to BDNF-TrkB signaling, and activates transcription from BDNF promoter IV by recruiting CBP. Our complementary reporter assays with BDNF promoter constructs indicate that the regulation of BDNF by CREB family after BDNF-TrkB signaling is generally conserved between rat and human. However, we demonstrate that a nonconserved functional cAMP-responsive element in BDNF promoter IXa in humans renders the human promoter responsive to BDNF-TrkB-CREB signaling, whereas the rat ortholog is unresponsive. Finally, we show that extensive BDNF transcriptional autoregulation, encompassing all major BDNF transcripts, occurs also in vivo in the adult rat hippocampus during BDNF-induced LTP. Collectively, these results improve the understanding of the intricate mechanism of BDNF transcriptional autoregulation.SIGNIFICANCE STATEMENT Deeper understanding of stimulus-specific regulation of BDNF gene expression is essential to precisely adjust BDNF levels that are dysregulated in various neurological disorders. Here, we have elucidated the molecular mechanisms behind TrkB signaling-dependent BDNF mRNA induction and show that CREB family transcription factors are the main regulators of BDNF gene expression after TrkB signaling. Our results suggest that BDNF-TrkB signaling may induce BDNF gene expression in a distinct manner compared with neuronal activity. Moreover, our data suggest the existence of a stimulus-specific distal enhancer modulating BDNF gene expression.

Macrovascular Complications of Type 2 Diabetes Mellitus.

Abstract: Background Type 2 diabetes mellitus (T2DM) has emerged as a pandemic. It has different complications, both microvascular and macrovascular. Objective The purpose of this review is to summarize the different types of macrovascular complications associated with T2DM. Methods A comprehensive review of the literature was performed to identify clinical studies, which determine the macrovascular complications associated with T2DM. Results Macrovascular complications of T2DM include coronary heart disease, cardiomyopathy, arrhythmias and sudden death, cerebrovascular disease and peripheral artery disease. Cardiovascular disease is the primary cause of death in diabetic patients. Many clinical studies have shown a connection between T2DM and vascular disease, but almost always other risk factors are present in diabetic patients, such as hypertension, obesity and dyslipidaemia. Conclusion T2DM causes a variety of macrovascular complications through different pathogenetic pathways that include hyperglycaemia and insulin resistance. The association between T2DM and cardiovascular disease is clear, but we need more clinical studies in order to identify the pure effect of T2DM.

COVID-19 Mobile Positioning Data Contact Tracing and Patient Privacy Regulations: Exploratory Search of Global Response Strategies and the Use of Digital Tools in Nigeria.

Abstract: Background: The coronavirus disease (COVID-19) pandemic is the biggest global economic and health challenge of the century. Its effect and impact are still evolving, with deaths estimated to reach 40 million if unchecked. One effective and complementary strategy to slow the spread and reduce the impact is to trace the primary and secondary contacts of confirmed COVID-19 cases using contact tracing technology. Objective: The objective of this paper is to survey strategies for digital contact tracing for the COVID-19 pandemic and to present how using mobile positioning data conforms with Nigeria’s data privacy regulations. Methods: We conducted an exploratory review of current measures for COVID-19 contact tracing implemented around the world. We then analyzed how countries are using mobile positioning data technology to reduce the spread of COVID-19. We made recommendations on how Nigeria can adopt this approach while adhering to the guidelines provided by the National Data Protection Regulation (NDPR). Results: Despite the potential of digital contact tracing, it always conflicts with patient data privacy regulations. We found that Nigeria’s response complies with the NDPR, and that it is possible to leverage call detail records to complement current strategies within the NDPR. Conclusions: Our study shows that mobile position data contact tracing is important for epidemic control as long as it conforms to relevant data privacy regulations. Implementation guidelines will limit data misuse.

Selective laser manufacturing of Ti-based alloys and composites: impact of process parameters, application trends, and future prospects

Abstract: Aviation and automobile industries demand high strength, fatigue resistant, and wear-resistant materials in combination with lightweight, especially for structural applications. On the other hand, biomedical applications demand materials with low modulus and stiffness for optimized implants better matching the modulus of human bone combined with enhanced strength and wear resistance. For all the aforementioned applications in various fields, the fabrication of parts with desired size and shape without the need for joining or welding operations is desired while simultaneously reaching improved mechanical properties and more resistance to environmental attack, which are stringent requirements for almost all the applications. To achieve all these demands, both material developments, as well as modification of process conditions and parameters, are essential. Along these lines, a lot of research work focusses on advanced or even disruptive manufacturing routes and proper alloy development (e.g. Ti, Al, steels, and so on) applying additive manufacturing (AM) techniques for various applications. Among different AM methods, selective laser melting (SLM) is in high demand and preferred for achieving fully dense products in the required dimensions. Titanium alloys designed for AM have replaced a variety of other alloys due to their superior properties such as lightweight or good fatigue and corrosion resistance, achievable through modified microstructures gained by the faster heating and cooling rates realized upon laser printing. Ti alloys with a single (α) or dual (α+β) microstructure are mostly implemented in the aviation and automobile industries, whereas β alloys with exceptionally low modulus close to that of human bone are intensively studied for bio and dental implants but have not been commercialized yet. The modification of microstructure and properties in Ti-based materials with the addition of suitable reinforcement is also a reliable method. In this article, critical aspects for the optimization of processing parameters affecting the properties of SLM manufactured Ti alloys and titanium matrix composites (TMCs) will be presented, and future prospects of such materials will be critically assessed. This work is expected to be helpful for future studies on Ti alloys and composites with enhanced properties processed by laser manufacturing.

Globally consistent climate sensitivity of natural disturbances across boreal and temperate forest ecosystems

Abstract: Disturbance regimes are changing in forests across the world in response to global climate change. Despite the profound impacts of disturbances on ecosystem services and biodiversity, assessments of disturbances at the global scale remain scarce. Here, we analyzed natural disturbances in boreal and temperate forest ecosystems for the period 2001-2014, aiming to 1) quantify their within- and between-biome variation and 2) compare the climate sensitivity of disturbances across biomes. We studied 103 unmanaged forest landscapes with a total land area of 28.2 x 10(6) ha, distributed across five continents. A consistent and comprehensive quantification of disturbances was derived by combining satellite-based disturbance maps with local expert knowledge of disturbance agents. We used Gaussian finite mixture models to identify clusters of landscapes with similar disturbance activity as indicated by the percent forest area disturbed as well as the size, edge density and perimeter-area-ratio of disturbed patches. The climate sensitivity of disturbances was analyzed using Bayesian generalized linear mixed effect models and a globally consistent climate dataset. Within-biome variation in natural disturbances was high in both boreal and temperate biomes, and disturbance patterns did not vary systematically with latitude or biome. The emergent clusters of disturbance activity in the boreal zone were similar to those in the temperate zone, but boreal landscapes were more likely to experience high disturbance activity than their temperate counterparts. Across both biomes high disturbance activity was particularly associated with wildfire, and was consistently linked to years with warmer and drier than average conditions. Natural disturbances are a key driver of variability in boreal and temperate forest ecosystems, with high similarity in the disturbance patterns between both biomes. The universally high climate sensitivity of disturbances across boreal and temperate ecosystems indicates that future climate change could substantially increase disturbance activity.

A survey on artificial intelligence approaches in supporting frontline workers and decision makers for the COVID-19 pandemic.

Abstract: While the world has experience with many different types of infectious diseases, the current crisis related to the spread of COVID-19 has challenged epidemiologists and public health experts alike, leading to a rapid search for, and development of, new and innovative solutions to combat its spread. The transmission of this virus has infected more than 18.92 million people as of August 6, 2020, with over half a million deaths across the globe; the World Health Organization (WHO) has declared this a global pandemic. A multidisciplinary approach needs to be followed for diagnosis, treatment and tracking, especially between medical and computer sciences, so, a common ground is available to facilitate the research work at a faster pace. With this in mind, this survey paper aimed to explore and understand how and which different technological tools and techniques have been used within the context of COVID-19. The primary contribution of this paper is in its collation of the current state-of-the-art technological approaches applied to the context of COVID-19, and doing this in a holistic way, covering multiple disciplines and different perspectives. The analysis is widened by investigating Artificial Intelligence (AI) approaches for the diagnosis, anticipate infection and mortality rate by tracing contacts and targeted drug designing. Moreover, the impact of different kinds of medical data used in diagnosis, prognosis and pandemic analysis is also provided. This review paper covers both medical and technological perspectives to facilitate the virologists, AI researchers and policymakers while in combating the COVID-19 outbreak.

FESDA: Fog-Enabled Secure Data Aggregation in Smart Grid IoT Network

Abstract: With advances in fog and edge computing, various problems such as data processing for large Internet of Things (IoT) systems can be solved in an efficient manner. One such problem for the next generation smart grid (SG) IoT system comprising of millions of smart devices is the data aggregation problem. Traditional data aggregation schemes for SGs incur high computation and communication costs, and in recent years, there have been efforts to leverage fog computing with SGs to overcome these limitations. In this article, a new fog-enabled privacy-preserving data aggregation scheme (FESDA) is proposed. Unlike existing schemes, the proposed scheme is resilient to false data injection attacks by filtering out the inserted values from external attackers. To achieve privacy, a modified version of the Paillier cryptosystem is used to encrypt the consumption data of the smart meter (SM) users. In addition, FESDA is fault-tolerant, which means, the collection of data from other devices will not be affected even if some of the SMs malfunction. We evaluate its performance along with three other competing schemes in terms of aggregation, decryption, and communication costs. The findings demonstrate that FESDA reduces the communication cost by 50%, when compared with the privacy-preserving fog-enabled data aggregation scheme.

Robust Design Optimization and Emerging Technologies for Electrical Machines: Challenges and Open Problems

Abstract: The bio-inspired algorithms are novel, modern, and efficient tools for the design of electrical machines. However, from the mathematical point of view, these problems belong to the most general branch of non-linear optimization problems, where these tools cannot guarantee that a global minimum is found. The numerical cost and the accuracy of these algorithms depend on the initialization of their internal parameters, which may themselves be the subject of parameter tuning according to the application. In practice, these optimization problems are even more challenging, because engineers are looking for robust designs, which are not sensitive to the tolerances and the manufacturing uncertainties. These criteria further increase these computationally expensive problems due to the additional evaluations of the goal function. The goal of this paper is to give an overview of the widely used optimization techniques in electrical machinery and to summarize the challenges and open problems in the applications of the robust design optimization and the prospects in the case of the newly emerging technologies.

Premature failure of an additively manufactured material

Abstract: Additively manufactured metallic materials exhibit excellent mechanical strength. However, they often fail prematurely owing to external defects (pores and unmelted particles) that act as sites for crack initiation. Cracks then propagate through grain boundaries and/or cellular boundaries that contain continuous brittle second phases. In this work, the premature failure mechanisms in selective laser melted (SLM) materials were studied. A submicron structure was introduced in a SLM Ag–Cu–Ge alloy that showed semicoherent precipitates distributed in a discontinuous but periodic fashion along the cellular boundaries. This structure led to a remarkable strength of 410 ± 3 MPa with 16 ± 0.5% uniform elongation, well surpassing the strength-ductility combination of their cast and annealed counterparts. The hierarchical SLM microstructure with a periodic arrangement of precipitates and a high density of internal defects led to a high strain hardening rate and strong strengthening, as evidenced by the fact that the precipitates were twinned and encircled by a high density of internal defects, such as dislocations, stacking faults and twins. However, the samples fractured before necking owing to the crack acceleration along the external defects. This work provides an approach for additively manufacturing materials with an ultrahigh strength combined with a high ductility provided that premature failure is alleviated. An analysis of metallic alloys fabricated through layer-by-layer deposition processes has revealed critical factors in preventing these materials from unexpectedly breaking. In selective laser melting (SLM) technology, thin layers of metal powders are assembled into three-dimensional objects using rapid heating and cooling steps. Zhi Wang from the South China University of Technology in Guangzhou and colleagues now show that the microstructure of a silver-copper-germanium alloy formed through SLM can affect the material’s strength. Using optical and X-ray microscopy, the team found that regularly spaced precipitates formed inside the 3D-printed alloy prevented abrupt atomic sliding movements, giving the material a higher natural strength and good ductility. Fractures that occurred at lower than expected stress levels were identified as arising from errors in the printing process, such as pores and unmelted powder particles. A submicron structure strategy was introduced in a selective laser melted (SLM) Ag-Cu-Ge alloy, showing semi-coherent precipitates distributed in a discontinuous but periodic fashion along the cellular boundaries. It leads to a remarkable strength of ~410 MPa with ~16% ductility, well surpassing the strength-ductility combination of their cast counterparts. The hierarchal SLM microstructure and high density of internal defects leading to a high strain hardening rate and strong strengthening. Premature failure occurred due to the external defects, such as pores and unmelted particles. This work paves a way for additively manufacturing materials towards high strength–ductility synergy.

VoxLingua107: a Dataset for Spoken Language Recognition

Abstract: This paper investigates the use of automatically collected web audio data for the task of spoken language recognition. We generate semi-random search phrases from language-specific Wikipedia data that are then used to retrieve videos from YouTube for 107 languages. Speech activity detection and speaker diarization are used to extract segments from the videos that contain speech. Post-filtering is used to remove segments from the database that are likely not in the given language, increasing the proportion of correctly labeled segments to 98%, based on crowd-sourced verification. The size of the resulting training set (VoxLingua107) is 6628 hours (62 hours per language on the average) and it is accompanied by an evaluation set of 1609 verified utterances. We use the data to build language recognition models for several spoken language identification tasks. Experiments show that using the automatically retrieved training data gives competitive results to using hand-labeled proprietary datasets. The dataset is publicly available.

Understanding How Microorganisms Respond to Acid pH Is Central to Their Control and Successful Exploitation

Abstract: Microbes from the three domains of life, Bacteria, Archaea, and Eukarya, share the need to sense and respond to changes in the external and internal concentrations of protons. When the proton concentration is high, acidic conditions prevail and cells must respond appropriately to ensure that macromolecules and metabolic processes are sufficiently protected to sustain life. While, we have learned much in recent decades about the mechanisms that microbes use to cope with acid, including the unique challenges presented by organic acids, there is still much to be gained from developing a deeper understanding of the effects and responses to acid in microbes. In this perspective article, we survey the key molecular mechanisms known to be important for microbial survival during acid stress and discuss how this knowledge might be relevant to microbe-based applications and processes that are consequential for humans. We discuss the research approaches that have been taken to investigate the problem and highlight promising new avenues. We discuss the influence of acid on pathogens during the course of infections and highlight the potential of using organic acids in treatments for some types of infection. We explore the influence of acid stress on photosynthetic microbes, and on biotechnological and industrial processes, including those needed to produce organic acids. We highlight the importance of understanding acid stress in controlling spoilage and pathogenic microbes in the food chain. Finally, we invite colleagues with an interest in microbial responses to low pH to participate in the EU-funded COST Action network called EuroMicropH and contribute to a comprehensive database of literature on this topic that we are making publicly available.

DOME: Recommendations for supervised machine learning validation in biology

Abstract: Modern biology frequently relies on machine learning to provide predictions and improve decision processes. There have been recent calls for more scrutiny on machine learning performance and possible limitations. Here we present a set of community-wide recommendations aiming to help establish standards of supervised machine learning validation in biology. Adopting a structured methods description for machine learning based on data, optimization, model, evaluation (DOME) will aim to help both reviewers and readers to better understand and assess the performance and limitations of a method or outcome. The recommendations are formulated as questions to anyone wishing to pursue implementation of a machine learning algorithm. Answers to these questions can be easily included in the supplementary material of published papers.

Tackling COVID-19 pandemic through nanocoatings: Confront and exactitude

Abstract: After the eruption of the most deadly influenza flu pandemic in 1918, also known as Spanish flu, infected about 500 million people with a death toll of approximately 50 million globally, the second most devastating pandemic flu emerged in December 2019 ​at Wuhan (Hubei Province) of China. This viral disease caused by a novel coronavirus SARS-COV-2 was named COVID-19 by World Health Organization (WHO). The COVID-19 virus affected 213 countries globally with 5.6 million cases and 353,373 deaths as of May 28, 2020 [1] Fig. 1. Still, there is no promising solution known to tackle this severe epidemic disease worldwide. For protecting the global population from COVID-19, we must follow three steps – early detection, monitoring, and treatment. At the same time, it is important to follow WHO guidelines on preventive measures. Many countries have restricted the movement of people completely and lockdown was enforced to maintain social distancing. But lockdown alone is insufficient to prevent resurgence, can upend economies and roil society. People need to step out to perform essential tasks and may get exposed to this deadly virus. Learnings from previous outbreaks suggest the usage of nanotechnology as an important avenue to develop antiviral drugs and materials. So, to effectively minimize the acquired infection of COVID-19 in public places like hospitals, transport, schools, worship places, stores, malls, etc. Antimicrobial nanocoatings at these places and development of targeted antiviral drugs through capped nanoparticles will be a major effective option to tackle the spread of this disease.

Physicochemical and Sensorial Evaluation of Meat Analogues Produced from Dry-Fractionated Pea and Oat Proteins

Abstract: Pea protein dry-fractionated (PDF), pea protein isolated (PIs), soy protein isolated (SIs) and oat protein (OP) were combined in four mixes (PDF_OP, PIs_OP, PDF_PIs_OP, SIs_OP) and extruded to produce meat analogues. The ingredients strongly influenced the process conditions and the use of PDF required higher specific mechanical energy and screw speed to create fibrous texture compared to PIs and SIs. PDF can be conveniently used to produce meat analogues with a protein content of 55 g 100 g−1, which is exploitable in meat-alternatives formulation. PDF-based meat analogues showed lower hardness (13.55–18.33 N) than those produced from PIs and SIs (nearly 27 N), probably due to a more porous structure given by the natural presence of carbohydrates in the dry-fractionated ingredient. PDF_OP and PIs_PDF_OP showed a significantly lower water absorption capacity than PIs OP and SIs_OP, whereas pea-based extrudates showed high oil absorption capacity, which could be convenient to facilitate the inclusion of oil and fat in the final formulation. The sensory evaluation highlighted an intense odor and taste profile of PDF_OP, whereas the extrudates produced by protein isolates had more neutral sensory characteristics. Overall, the use of dry-fractionated protein supports the strategies to efficiently produce clean-labeled and sustainable plant-based meat analogues.

Microbial inoculation in rice regulates antioxidative reactions and defense related genes to mitigate drought stress.

Abstract: Microbial inoculation in drought challenged rice triggered multipronged steps at enzymatic, non-enzymatic and gene expression level. These multifarious modulations in plants were related to stress tolerance mechanisms. Drought suppressed growth of rice plants but inoculation with Trichoderma, Pseudomonas and their combination minimized the impact of watering regime. Induced PAL gene expression and enzyme activity due to microbial inoculation led to increased accumulation of polyphenolics in plants. Enhanced antioxidant concentration of polyphenolics from microbe inoculated and drought challenged plants showed substantially high values of DPPH, ABTS, Fe-ion reducing power and Fe-ion chelation activity, which established the role of polyphenolic extract as free radical scavengers. Activation of superoxide dismutase that catalyzes superoxide (O2−) and leads to the accumulation of H2O2 was linked with the hypersensitive cell death response in leaves. Microbial inoculation in plants enhanced activity of peroxidase, ascorbate peroxidase, glutathione peroxidase and glutathione reductase enzymes. This has further contributed in reducing ROS burden in plants. Genes of key metabolic pathways including phenylpropanoid (PAL), superoxide dismutation (SODs), H2O2 peroxidation (APX, PO) and oxidative defense response (CAT) were over-expressed due to microbial inoculation. Enhanced expression of OSPiP linked to less-water permeability, drought-adaptation gene DHN and dehydration related stress inducible DREB gene in rice inoculated with microbial inoculants after drought challenge was also reported. The impact of Pseudomonas on gene expression was consistently remained the most prominent. These findings suggested that microbial inoculation directly caused over-expression of genes linked with defense processes in plants challenged with drought stress. Enhanced enzymatic and non-enzymatic antioxidant reactions that helped in minimizing antioxidative load, were the repercussions of enhanced gene expression in microbe inoculated plants. These mechanisms contributed strongly towards stress mitigation. The study demonstrated that microbial inoculants were successful in improving intrinsic biochemical and molecular capabilities of rice plants under stress. Results encouraged us to advocate that the practice of growing plants with microbial inoculants may find strategic place in raising crops under abiotic stressed environments.

Machine Learning Meets Communication Networks: Current Trends and Future Challenges

Abstract: The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future communicating devices and services. In this article, we provide a detailed account of current research on the application of ML in communication networks and shed light on future research challenges. Research on the application of ML in communication networks is described in: i) the three layers, i.e., physical, access, and network layers; and ii) novel computing and networking concepts such as Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Functions Virtualization (NFV), and a brief overview of ML-based network security. Important future research challenges are identified and presented to help stir further research in key areas in this direction.