Machine Learning for QoE Prediction and Anomaly Detection in Self-Organizing Mobile Networking Systems

In this chapter, a brief overview of the role and applications of machine learning (ML) algorithms in future wireless cellular networks is presented, more specifically, in the context of self-organizing networks (SONs). SON is a promising and innovative concept, in which future networks are expected to analyze and use historical data in order to improve and adapt themselves to the network conditions. For this to be possible, however, algorithms that are capable of extracting patterns from data and learn from previous actions are necessary. This chapter highlights the utilization and possible applications of ML algorithms in future cellular networks. A brief introduction of ML and SON is presented, followed by an analysis of current state of the art solutions involving ML in SON. Lastly, guidelines on the utilization of intelligent algorithms in SON and future research trends in the area are highlighted and conclusions are drawn.

The aging and multimorbid population and health personnel shortages pose a substantial burden on primary health care. While predictive machine learning (ML) algorithms have the potential to address these challenges, concerns include transparency and insufficient reporting of model validation and effectiveness of the implementation in the clinical workflow. To systematically identify predictive ML algorithms implemented in primary care from peer-reviewed literature and US Food and Drug Administration (FDA) and Conformité Européene (CE) registration databases and to ascertain the public availability of evidence, including peer-reviewed literature, gray literature, and technical reports across the artificial intelligence (AI) life cycle. PubMed, Embase, Web of Science, Cochrane Library, Emcare, Academic Search Premier, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI.org (Association for the Advancement of Artificial Intelligence), arXiv, Epistemonikos, PsycINFO, and Google Scholar were searched for studies published between January 2000 and July 2023, with search terms that were related to AI, primary care, and implementation. The search extended to CE-marked or FDA-approved predictive ML algorithms obtained from relevant registration databases. Three reviewers gathered subsequent evidence involving strategies such as product searches, exploration of references, manufacturer website visits, and direct inquiries to authors and product owners. The extent to which the evidence for each predictive ML algorithm aligned with the Dutch AI predictive algorithm (AIPA) guideline requirements was assessed per AI life cycle phase, producing evidence availability scores. The systematic search identified 43 predictive ML algorithms, of which 25 were commercially available and CE-marked or FDA-approved. The predictive ML algorithms spanned multiple clinical domains, but most (27 [63%]) focused on cardiovascular diseases and diabetes. Most (35 [81%]) were published within the past 5 years. The availability of evidence varied across different phases of the predictive ML algorithm life cycle, with evidence being reported the least for phase 1 (preparation) and phase 5 (impact assessment) (19% and 30%, respectively). Twelve (28%) predictive ML algorithms achieved approximately half of their maximum individual evidence availability score. Overall, predictive ML algorithms from peer-reviewed literature showed higher evidence availability compared with those from FDA-approved or CE-marked databases (45% vs 29%). The findings indicate an urgent need to improve the availability of evidence regarding the predictive ML algorithms' quality criteria. Adopting the Dutch AIPA guideline could facilitate transparent and consistent reporting of the quality criteria that could foster trust among end users and facilitating large-scale implementation.

Several machine learning (ML) algorithms have been increasingly utilized for cardiovascular disease prediction. We aim to assess and summarize the overall predictive ability of ML algorithms in cardiovascular diseases. A comprehensive search strategy was designed and executed within the MEDLINE, Embase, and Scopus databases from database inception through March 15, 2019. The primary outcome was a composite of the predictive ability of ML algorithms of coronary artery disease, heart failure, stroke, and cardiac arrhythmias. Of 344 total studies identified, 103 cohorts, with a total of 3,377,318 individuals, met our inclusion criteria. For the prediction of coronary artery disease, boosting algorithms had a pooled area under the curve (AUC) of 0.88 (95% CI 0.84–0.91), and custom-built algorithms had a pooled AUC of 0.93 (95% CI 0.85–0.97). For the prediction of stroke, support vector machine (SVM) algorithms had a pooled AUC of 0.92 (95% CI 0.81–0.97), boosting algorithms had a pooled AUC of 0.91 (95% CI 0.81–0.96), and convolutional neural network (CNN) algorithms had a pooled AUC of 0.90 (95% CI 0.83–0.95). Although inadequate studies for each algorithm for meta-analytic methodology for both heart failure and cardiac arrhythmias because the confidence intervals overlap between different methods, showing no difference, SVM may outperform other algorithms in these areas. The predictive ability of ML algorithms in cardiovascular diseases is promising, particularly SVM and boosting algorithms. However, there is heterogeneity among ML algorithms in terms of multiple parameters. This information may assist clinicians in how to interpret data and implement optimal algorithms for their dataset.

In mobile networks, handover (HO) is one of the most important and complex KPIs (Key Performance Indicators), which directly affect to Quality of Service (QoS), Quality of Experience (QoE), and mobility performance. Moreover, its configuration parameters such as handover thresholds and handover neighbor lists are the key factors for implementing network optimization such as load balancing and energy saving. In a study before, the authors proposed clustering and forecasting models using ML algorithms and Time Series models to cluster, forecast, and manage the HO behavior of a huge number of cells. In this study, on the other hand, the authors firstly investigated more network KPIs to analyze their relationship with HO KPIs, and then, proposed new clustering, forecasting, and abnormal detection models that are expected to make them much more comprehensive. Finally, the performances of the proposed models were evaluated by applying them to a real dataset collected from the HO KPIs and other KPIs of more than 6000 cells of a real network during the years, 2016 and 2017. The results showed that the study was successful in identifying the relationship among network KPIs and significantly improving the performance of the HO clustering, forecasting, abnormal detection models. Moreover, the study also introduced the integration of emerging technologies such as machine learning (ML), big data, software-defined network (SDN), and network functions virtualization (NFV) to establish a practical and powerful computing platform for future self-organizing networks (SON).

The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model–agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.

BackgroundDespite the interest in machine learning (ML) algorithms for analyzing real-world data (RWD) in healthcare, the use of ML in predicting time-to-event data, a common scenario in clinical practice, is less explored. ML models are capable of algorithmically learning from large, complex datasets and can offer advantages in predicting time-to-event data. We reviewed the recent applications of ML for survival analysis using RWD in healthcare.MethodsPUBMED and EMBASE were searched from database inception through March 2023 to identify peer-reviewed English-language studies of ML models for predicting time-to-event outcomes using the RWD. Two reviewers extracted information on the data source, patient population, survival outcome, ML algorithms, and the Area Under the Curve (AUC).ResultsOf 257 citations, 28 publications were included. Random survival forests (N = 16, 57%) and neural networks (N = 11, 39%) were the most popular ML algorithms. There was variability across AUC for these ML models (median 0.789, range 0.6–0.950). ML algorithms were predominately considered for predicting overall survival in oncology (N = 12, 43%). ML survival models were often used to predict disease prognosis or clinical events (N = 27, 96%) in the oncology, while less were used for treatment outcomes (N = 1, 4%).ConclusionsThe ML algorithms, random survival forests and neural networks, are mainly used for RWD to predict survival outcomes such as disease prognosis or clinical events in the oncology. This review shows that more opportunities remain to apply these ML algorithms to inform treatment decision-making in clinical practice. More methodological work is also needed to ensure the utility and applicability of ML models in survival outcomes.

The integration of machine learning (ML) algorithms into audit processes represents a significant advancement in the field of auditing, offering substantial benefits in terms of efficiency, accuracy, and risk management. This review examines the transformative potential of ML in auditing, highlighting its key benefits and the challenges that must be addressed to fully leverage its capabilities. Machine learning algorithms, with their ability to analyze large datasets and identify patterns, enhance the accuracy and thoroughness of audits. Traditional auditing methods often rely on sampling and manual checks, which can miss anomalies and fraudulent activities. In contrast, ML algorithms can process entire datasets, uncovering subtle patterns and irregularities that may indicate fraud or errors. This comprehensive analysis reduces the risk of oversight and improves the reliability of audit findings. One of the primary benefits of ML in auditing is its capacity for anomaly detection. ML models can be trained on historical data to understand normal financial behavior and flag deviations that might signify irregularities. This ability to detect anomalies in real-time enables auditors to identify potential issues promptly, reducing the time lag between occurrence and detection of fraud. Predictive analytics, powered by ML, further enhances audit processes by forecasting future risks based on historical data. This proactive approach allows auditors to anticipate and mitigate risks before they materialize, contributing to more robust risk management strategies. Despite these advantages, integrating ML into audit processes presents several challenges. Ensuring data quality and integrity is crucial, as ML algorithms are only as good as the data they analyze. Poor-quality data can lead to inaccurate predictions and conclusions. Additionally, the "black box" nature of some ML algorithms can pose transparency issues, making it difficult for auditors to explain how specific conclusions were reached, which is critical for stakeholder trust and regulatory compliance. Another significant challenge is the potential for algorithmic bias. ML models can inadvertently perpetuate existing biases in the data, leading to unfair or skewed audit outcomes. Continuous monitoring and validation of ML algorithms are necessary to detect and mitigate such biases. In conclusion, while integrating machine learning algorithms into audit processes offers substantial benefits in terms of accuracy, efficiency, and risk management, it also necessitates careful attention to data quality, transparency, and bias mitigation. Addressing these challenges is essential to fully realize the potential of ML in enhancing audit practices. Keywords: Benefits, Challenges, Audit Processes, Algorithms, ML.

In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is clinically relevant for surgeon and patient to anticipate unplanned secondary procedures, other than operations that can be readily expected such as reconstructive procedures for soft tissue defects. Therefore, the objective of this study was to develop a machine learning (ML) prediction model using the SPRINT data that can give individual patients and their care team an estimate of their particular probability of an unplanned second surgery. Patients from the SPRINT trial with unilateral TSFs were randomly divided into a training set (80%) and test set (20%). Five ML algorithms were trained in recognizing patterns associated with subsequent surgery in the training set based on a subset of variables identified by random forest algorithms. Performance of each ML algorithm was evaluated and compared based on (1) area under the ROC curve, (2) calibration slope and intercept, and (3) the Brier score. Total data set comprised 1198 patients, of whom 214 patients (18%) underwent subsequent surgery. Seven variables were used to train ML algorithms: (1) Gustilo-Anderson classification, (2) Tscherne classification, (3) fracture location, (4) fracture gap, (5) polytrauma, (6) injury mechanism, and (7) OTA/AO classification. The best-performing ML algorithm had an area under the ROC curve, calibration slope, calibration intercept, and the Brier score of 0.766, 0.954, -0.002, and 0.120 in the training set and 0.773, 0.922, 0, and 0.119 in the test set, respectively. An ML algorithm was developed to predict the probability of subsequent surgery after IMN for TSFs. This ML algorithm may assist surgeons to inform patients about the probability of subsequent surgery and might help to identify patients who need a different perioperative plan or a more intensive approach. Prognostic Level II. See Instructions for Authors for a complete description of levels of evidence.

This study presents a comparative analysis of the classification performance of facial and emotion recognition systems using Machine Learning (ML) and Deep Learning (DL) algorithms. The primary objective of this work is to evaluate the applicability of emotion recognition in fields such as psychotherapy and crime analysis, using the FER-2013 dataset.The study was conducted with ML algorithms such as Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Decision Trees, and Gradient Boosting, as well as the DL algorithm, Convolutional Neural Network (CNN). Supported by the application of feature selection, preprocessing, and feature extraction techniques, the model’s performance was measured using standard metrics such as accuracy, precision, F1-score, and AUC-ROC.The experimental results showed that the highest classification accuracy (46.61%) was achieved with the CNN model. While the ML models generally offered lower accuracy, they provided advantages in terms of computational efficiency in specific scenarios.This study aims to contribute to the literature by providing a comparative analysis of ML and DL algorithms and by highlighting the effect of data preprocessing on performance. The findings set targets for future work, such as real-time system integration and hybrid model development.

The growing implementation of aluminum alloys in industry has focused interest on studying transformation processes such as laser welding. This process generates different kinds of signals that can be monitored and used to evaluate it and make a quality analysis of the final product. Internal defects that are difficult to detect, such as porosity, are one of the most critical irregularities in laser welding. This kind of defect may result in a critical failure of the manufactured goods, affecting the final user. In this research, a porosity prediction method using a high-speed camera monitoring system and machine learning (ML) algorithms is proposed and studied to find the most performant methodology to resolve the prediction problem. The methodology includes feature extraction by high-speed X-ray analysis, feature engineering and selection, imbalance treatment, and the evaluation of the ML algorithms by metrics such as accuracy, AUC (area under the curve), and F1. As a result, it was found that the best ML algorithm for porosity prediction in the proposed setup is Random Forest with a 0.83 AUC and 75% accuracy, 0.75 in the F1 score for no porosity, and 0.76 in the F1 score for porosity. The results of the proposed model and methodology indicate that they could be implemented in industrial applications for enhancing the final product quality for welded plates, reducing process waste and product quality analysis time, and increasing the operational performance of the process.

The widespread use of encryption in the delivery of Over-The-Top video streaming services poses challenges for network operators looking to monitor service performance and detect potential customer perceived Quality of Experience (QoE) degradations. While monitoring solutions deployed on client devices provide insight into application layer KPIs (e.g., video quality levels, buffer underruns, stalling duration) which can be further mapped to user QoE, network providers commonly rely primarily on passive traffic monitoring solutions deployed within their network to obtain insight into user perceived degradations and their potential causes. In this paper we present a methodology for the estimation of end users' QoE when watching YouTube videos which is based only on statistical properties of encrypted network traffic. We have developed a system called YouQ which includes tools for monitoring and analysis of application-layer KPIs and corresponding traffic traces, and the subsequent use of this data for the development of machine learning models for QoE estimation based on traffic features. To test this approach, we have collected a dataset of 1060 different YouTube video traces using 39 different bandwidth scenarios. All video traces are annotated with application-layer KPIs and classified into one of three QoE classes. The dataset was used to test various machine learning algorithms, and results showed that up to 84\% QoE classification accuracy could be achieved using only features extracted from encrypted traffic.

Satellite-based aerosol optical property retrieval over land, especially size-related parameters, is challenging. This study proposed a novel two-stage machine learning (ML) algorithm for retrieving aerosol optical depth (AOD), Ångström exponent (AE), fine mode fraction (FMF), and fine mode AOD (FAOD)) over land using MODIS observed reflectance. The new ML algorithm consists of three steps: (1) first, all samples extracted from AERONET measurements were used to train the ML model, (2) then, to reduce the extreme estimation bias of the model, divided low-value and high-value samples were used to train low-value and high-value ML models, respectively, and (3) finally, the three ML models were integrated into the final retrieval based on the weight interpolation. Independent site network validation results show that the new ML algorithm has a Pearson correlation coefficient (R) of 0.894 (0.638, 0.661, 0.865) and root mean square error (RMSE) of 0.146 (0.258, 0.245, 0.153) for the AOD (AE, FMF, FAOD) retrieval, which significantly outperforms the validation metrics of MODIS operational products, with AOD (AE, FMF, FAOD) RMSE of 0.130-0.156 (0.536-0.569, 0.313, 0.191). The inter-comparison of aerosol products shows that the spatial patterns of AOD, AE, FMF, and FAOD of the new ML algorithm are in good agreement with those of the MODIS and POLDER products. These results illustrate that the new ML algorithm has good performance and transferability and indicate the ability of ML methods to be applied to multispectral instruments (such as MODIS) to retrieve multiple aerosol properties.

Machine learning (ML) algorithms seek to extract the most beneficial information out of the raw data. As mentioned in previous chapters, preprocess data preparation actions might be needed in order to make the data set ready to be fed into the ML algorithms. ML algorithms have gotten the attention of researchers all over the world during the last few decades. In traditional algorithms, the analyst had to define the rules, which was not always accessible or easily possible, in order to obtain the output. ML algorithms develop the models or rules based on the training data set which include input and output data points. ML algorithms try to understand more beneficial information regarding the system based on the training data set. The built model can be tested using the verification data set which does not have any overlap with the training sets. If the model acquires the acceptable performance measures, it can be applied for other cases to perform the prediction process. It should be considered that ML algorithms are not supposed to do the magic. Indeed, they are supposed to explore and analyze the training data, which the human brain is not able to handle that, to develop a predictive model in which its performance is acceptable for the verification data set. Predictive models should be generalized which means performing satisfactorily for both training and verifying data sets.

A machine learning (ML) algorithm for automatic segmentation of intravascular ultrasound was previously validated. It has the potential to improve efficiency, accuracy and precision of coronary vessel segmentation compared to manual segmentation by interventional cardiology experts. The aim of this study is to compare the performance of human readers to the machine and against the readings from a Core Laboratory. This is a post-hoc, cross-sectional analysis of the IBIS-4 study. Forty frames were randomly selected and analyzed by 10 readers of varying expertise two separate times, 1week apart. Their measurements of lumen, vessel, plaque areas, and plaque burden were performed in an offline software. Among humans, the intra-observer variability was not statistically significant. For the total 80 frames, inter-observer variability between human readers, the ML algorithm and Core Laboratory for lumen area, vessel area, plaque area and plaque burden were not statistically different. For lumen area, however, relative differences between the human readers and the Core Lab ranged from 0.26 to 12.61%. For vessel area, they ranged from 1.25 to 9.54%. Efficiency between the ML algorithm and the readers differed notably. Humans spent 47min on average to complete the analyses, while the ML algorithm took on average less than 1min. The overall lumen, vessel and plaque means analyzed by humans and the proposed ML algorithm are similar to those of the Core Lab. Machines, however, are more time efficient. It is warranted to consider use of the ML algorithm in clinical practice.

7 - Machine learning and deep learning algorithms in disease prediction: Future trends for the healthcare system