Temporomandibular disorders (TMDs) refer to a group of conditions that affect the temporomandibular joint, causing pain and dysfunction in the jaw joint and related muscles. The diagnosis of TMDs typically involves clinical assessment through operator-based physical examination, a self-reported questionnaire and imaging studies. To objectivize the measurement of TMD, this study aims at investigating the feasibility of using machine-learning algorithms fed with data gathered from low-cost and portable instruments to identify the presence of TMD in adult subjects. Through this aim, the experimental protocol involved fifty participants, equally distributed between TMD and healthy subjects, acting as a control group. The diagnosis of TMD was performed by a skilled operator through the typical clinical scale. Participants underwent a baropodometric analysis by using a pressure matrix and the evaluation of the cervical mobility through inertial sensors. Nine machine-learning algorithms belonging to support vector machine, k-nearest neighbours and decision tree algorithms were compared. The k-nearest neighbours algorithm based on cosine distance was found to be the best performing, achieving performances of 0.94, 0.94 and 0.08 for the accuracy, F1-score and G-index, respectively. These findings open the possibility of using such methodology to support the diagnosis of TMDs in clinical environments.

• Klíčová slova
• clinical assessment, inertial sensors, machine learning, pressure platform, temporomandibular disorder,
• MeSH
• algoritmy * MeSH
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mladý dospělý MeSH
• nemoci temporomandibulárního kloubu * diagnóza   patofyziologie   MeSH
• rozhodovací stromy MeSH
• strojové učení * MeSH
• support vector machine MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mladý dospělý MeSH
• mužské pohlaví MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• srovnávací studie MeSH

This study tested whether machine learning (ML) methods can effectively separate individual plants from complex 3D canopy laser scans as a prerequisite to analyzing particular plant features. For this, we scanned mung bean and chickpea crops with PlantEye (R) laser scanners. Firstly, we segmented the crop canopies from the background in 3D space using the Region Growing Segmentation algorithm. Then, Convolutional Neural Network (CNN) based ML algorithms were fine-tuned for plant counting. Application of the CNN-based (Convolutional Neural Network) processing architecture was possible only after we reduced the dimensionality of the data to 2D. This allowed for the identification of individual plants and their counting with an accuracy of 93.18% and 92.87% for mung bean and chickpea plants, respectively. These steps were connected to the phenotyping pipeline, which can now replace manual counting operations that are inefficient, costly, and error-prone. The use of CNN in this study was innovatively solved with dimensionality reduction, addition of height information as color, and consequent application of a 2D CNN-based approach. We found there to be a wide gap in the use of ML on 3D information. This gap will have to be addressed, especially for more complex plant feature extractions, which we intend to implement through further research.

• Klíčová slova
• 3D point clouds, computer vision, machine learning, phenotyping, plant detection,
• MeSH
• algoritmy * MeSH
• neuronové sítě MeSH
• strojové učení * MeSH
• Publikační typ
• časopisecké články MeSH

In most biomedical research paper corpus, document classification is a crucial task. Even due to the global epidemic, it is a crucial task for researchers across a variety of fields to figure out the relevant scientific research papers accurately and quickly from a flood of biomedical research papers. It can also assist learners or researchers in assigning a research paper to an appropriate category and also help to find the relevant research paper within a very short time. A biomedical document classifier needs to be designed differently to go beyond a "general" text classifier because it's not dependent only on the text itself (i.e. on titles and abstracts) but can also utilize other information like entities extracted using some medical taxonomies or bibliometric data. The main objective of this research was to find out the type of information or features and representation method creates influence the biomedical document classification task. For this reason, we run several experiments on conventional text classification methods with different kinds of features extracted from the titles, abstracts, and bibliometric data. These procedures include data cleaning, feature engineering, and multi-class classification. Eleven different variants of input data tables were created and analyzed using ten machine learning algorithms. We also evaluate the data efficiency and interpretability of these models as essential features of any biomedical research paper classification system for handling specifically the COVID-19 related health crisis. Our major findings are that TF-IDF representations outperform the entity extraction methods and the abstract itself provides sufficient information for correct classification. Out of the used machine learning algorithms, the best performance over various forms of document representation was achieved by Random Forest and Neural Network (BERT). Our results lead to a concrete guideline for practitioners on biomedical document classification.

• Klíčová slova
• COVID-19, Machine learning algorithms, Multi-class classification, Text mining,
• Publikační typ
• časopisecké články MeSH

The fingerprinting technique is a popular approach to reveal location of persons, instruments or devices in an indoor environment. Typically based on signal strength measurement, a power level map is created first in the learning phase to align with measured values in the inference. Second, the location is determined by taking the point for which the recorded received power level is closest to the power level actually measured. The biggest limit of this technique is the reliability of power measurements, which may lack accuracy in many wireless systems. To this end, this work extends the power level measurement by using multiple anchors and multiple radio channels and, consequently, considers different approaches to aligning the actual measurements with the recorded values. The dataset is available online. This article focuses on the very popular radio technology Bluetooth Low Energy to explore the possible improvement of the system accuracy through different machine learning approaches. It shows how the accuracy-complexity trade-off influences the possible candidate algorithms on an example of three-channel Bluetooth received signal strength based fingerprinting in a one dimensional environment with four static anchors and in a two dimensional environment with the same set of anchors. We provide a literature survey to identify the machine learning algorithms applied in the literature to show that the studies available can not be compared directly. Then, we implement and analyze the performance of four most popular supervised learning techniques, namely k Nearest Neighbors, Support Vector Machines, Random Forest, and Artificial Neural Network. In our scenario, the most promising machine learning technique being the Random Forest with classification accuracy over 99%.

• Klíčová slova
• Bluetooth, fingerprinting, indoor navigation, machine learning,
• MeSH
• algoritmy MeSH
• neuronové sítě * MeSH
• reprodukovatelnost výsledků MeSH
• strojové učení * MeSH
• support vector machine MeSH
• Publikační typ
• časopisecké články MeSH

BACKGROUND: Keratoconus is a disorder characterized by progressive thinning and distortion of the cornea. If detected at an early stage, corneal collagen cross-linking can prevent disease progression and further visual loss. Although advanced forms are easily detected, reliable identification of subclinical disease can be problematic. Several different machine learning algorithms have been used to improve the detection of subclinical keratoconus based on the analysis of multiple types of clinical measures, such as corneal imaging, aberrometry, or biomechanical measurements. OBJECTIVE: The aim of this study is to survey and critically evaluate the literature on the algorithmic detection of subclinical keratoconus and equivalent definitions. METHODS: For this systematic review, we performed a structured search of the following databases: MEDLINE, Embase, and Web of Science and Cochrane Library from January 1, 2010, to October 31, 2020. We included all full-text studies that have used algorithms for the detection of subclinical keratoconus and excluded studies that did not perform validation. This systematic review followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. RESULTS: We compared the measured parameters and the design of the machine learning algorithms reported in 26 papers that met the inclusion criteria. All salient information required for detailed comparison, including diagnostic criteria, demographic data, sample size, acquisition system, validation details, parameter inputs, machine learning algorithm, and key results are reported in this study. CONCLUSIONS: Machine learning has the potential to improve the detection of subclinical keratoconus or early keratoconus in routine ophthalmic practice. Currently, there is no consensus regarding the corneal parameters that should be included for assessment and the optimal design for the machine learning algorithm. We have identified avenues for further research to improve early detection and stratification of patients for early treatment to prevent disease progression.

• Klíčová slova
• artificial intelligence, cornea, corneal disease, corneal imaging, corneal tomography, decision support systems, keratoconus, keratometry, machine learning, subclinical,
• Publikační typ
• časopisecké články MeSH
• přehledy MeSH

Additive friction stir deposition (AFSD) is a novel solid-state additive manufacturing technique that circumvents issues of porosity, cracking, and properties anisotropy that plague traditional powder bed fusion and directed energy deposition approaches. However, correlations between process parameters, thermal profiles, and resulting microstructure in AFSD still need to be better understood. This hinders process optimization for properties. This work employs a framework combining supervised machine learning (SML) and physics-informed neural networks (PINNs) to predict peak temperature distribution in AFSD from process parameters. Eight regression algorithms were implemented for SML modeling, while four PINNs leveraged governing equations for transport, wave propagation, heat transfer, and quantum mechanics. Across multiple statistical measures, ensemble techniques like gradient boosting proved superior for SML, with the lowest MSE of 165.78. The integrated ML approach was also applied to classify deposition quality from process factors, with logistic regression delivering robust accuracy. By fusing data-driven learning and fundamental physics, this dual methodology provides comprehensive insights into tailoring microstructure through thermal management in AFSD. The work demonstrates the power of bridging statistical and physics-based modeling for elucidating AM process-property relationships.

• MeSH
• algoritmy MeSH
• hliník * chemie   MeSH
• neuronové sítě MeSH
• řízené strojové učení * MeSH
• slitiny * chemie   MeSH
• strojové učení MeSH
• teplota MeSH
• tření MeSH
• Publikační typ
• časopisecké články MeSH
• Názvy látek
• hliník * MeSH
• slitiny * MeSH

Classification problems in the small data regime (with small data statistic T and relatively large feature space dimension D) impose challenges for the common machine learning (ML) and deep learning (DL) tools. The standard learning methods from these areas tend to show a lack of robustness when applied to data sets with significantly fewer data points than dimensions and quickly reach the overfitting bound, thus leading to poor performance beyond the training set. To tackle this issue, we propose eSPA+, a significant extension of the recently formulated entropy-optimal scalable probabilistic approximation algorithm (eSPA). Specifically, we propose to change the order of the optimization steps and replace the most computationally expensive subproblem of eSPA with its closed-form solution. We prove that with these two enhancements, eSPA+ moves from the polynomial to the linear class of complexity scaling algorithms. On several small data learning benchmarks, we show that the eSPA+ algorithm achieves a many-fold speed-up with respect to eSPA and even better performance results when compared to a wide array of ML and DL tools. In particular, we benchmark eSPA+ against the standard eSPA and the main classes of common learning algorithms in the small data regime: various forms of support vector machines, random forests, and long short-term memory algorithms. In all the considered applications, the common learning methods and eSPA are markedly outperformed by eSPA+, which achieves significantly higher prediction accuracy with an orders-of-magnitude lower computational cost.

• MeSH
• algoritmy * MeSH
• entropie MeSH
• strojové učení * MeSH
• support vector machine MeSH
• Publikační typ
• časopisecké články MeSH

During the lockdown of universities and the COVID-Pandemic most students were restricted to their homes. Novel and instigating teaching methods were required to improve the learning experience and so recent implementations of the annual PhysioNet/Computing in Cardiology (CinC) Challenges posed as a reference. For over 20 years, the challenges have proven repeatedly to be of immense educational value, besides leading to technological advances for specific problems. In this paper, we report results from the class 'Artificial Intelligence in Medicine Challenge', which was implemented as an online project seminar at Technical University Darmstadt, Germany, and which was heavily inspired by the PhysioNet/CinC Challenge 2017 'AF Classification from a Short Single Lead ECG Recording'. Atrial fibrillation is a common cardiac disease and often remains undetected. Therefore, we selected the two most promising models of the course and give an insight into the Transformer-based DualNet architecture as well as into the CNN-LSTM-based model and finally a detailed analysis for both. In particular, we show the model performance results of our internal scoring process for all submitted models and the near state-of-the-art model performance for the two named models on the official 2017 challenge test set. Several teams were able to achieve F1scores above/close to 90% on a hidden test-set of Holter recordings. We highlight themes commonly observed among participants, and report the results from the self-assessed student evaluation. Finally, the self-assessment of the students reported a notable increase in machine learning knowledge.

• Klíčová slova
• atrial fibrillation, deep learning, electrocardiogram, gamification,
• MeSH
• algoritmy MeSH
• COVID-19 * diagnóza   MeSH
• elektrokardiografie metody   MeSH
• fibrilace síní * diagnóza   MeSH
• kontrola infekčních nemocí MeSH
• lidé MeSH
• strojové učení MeSH
• umělá inteligence MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

With the increased number of Software-Defined Networking (SDN) installations, the data centers of large service providers are becoming more and more agile in terms of network performance efficiency and flexibility. While SDN is an active and obvious trend in a modern data center design, the implications and possibilities it carries for effective and efficient network management are not yet fully explored and utilized. With most of the modern Internet traffic consisting of multimedia services and media-rich content sharing, the quality of multimedia communications is at the center of attention of many companies and research groups. Since SDN-enabled switches have an inherent feature of monitoring the flow statistics in terms of packets and bytes transmitted/lost, these devices can be utilized to monitor the essential statistics of the multimedia communications, allowing the provider to act in case of network failing to deliver the required service quality. The internal packet processing in the SDN switch enables the SDN controller to fetch the statistical information of the particular packet flow using the PacketIn and Multipart messages. This information, if preprocessed properly, can be used to estimate higher layer interpretation of the link quality and thus allowing to relate the provided quality of service (QoS) to the quality of user experience (QoE). This article discusses the experimental setup that can be used to estimate the quality of speech communication based on the information provided by the SDN controller. To achieve higher accuracy of the result, latency characteristics are added based on the exploiting of the dummy packet injection into the packet stream and/or RTCP packet analysis. The results of the experiment show that this innovative approach calculates the statistics of each individual RTP stream, and thus, we obtain a method for dynamic measurement of speech quality, where when quality decreases, it is possible to respond quickly by changing routing at the network level for each individual call. To improve the quality of call measurements, a Convolutional Neural Network (CNN) was also implemented. This model is based on two standard approaches to measuring the speech quality: PESQ and E-model. However, unlike PESQ/POLQA, the CNN-based model can take delay into account, and unlike the E-model, the resulting accuracy is much higher.

• Klíčová slova
• OpenFlow, artificial neural networks, software defined networks, speech analysis,
• MeSH
• algoritmy MeSH
• počítačové komunikační sítě * MeSH
• řeč * MeSH
• software MeSH
• strojové učení MeSH
• Publikační typ
• časopisecké články MeSH

Fragmented QRS (fQRS) is an electrocardiographic (ECG) marker of myocardial conduction abnormality, characterized by additional notches in the QRS complex. The presence of fQRS has been associated with an increased risk of all-cause mortality and arrhythmia in patients with cardiovascular disease. However, current binary visual analysis is prone to intra- and inter-observer variability and different definitions are problematic in clinical practice. Therefore, objective quantification of fQRS is needed and could further improve risk stratification of these patients. We present an automated method for fQRS detection and quantification. First, a novel robust QRS complex segmentation strategy is proposed, which combines multi-lead information and excludes abnormal heartbeats automatically. Afterwards extracted features, based on variational mode decomposition (VMD), phase-rectified signal averaging (PRSA) and the number of baseline-crossings of the ECG, were used to train a machine learning classifier (Support Vector Machine) to discriminate fragmented from non-fragmented ECG-traces using multi-center data and combining different fQRS criteria used in clinical settings. The best model was trained on the combination of two independent previously annotated datasets and, compared to these visual fQRS annotations, achieved Kappa scores of 0.68 and 0.44, respectively. We also show that the algorithm might be used in both regular sinus rhythm and irregular beats during atrial fibrillation. These results demonstrate that the proposed approach could be relevant for clinical practice by objectively assessing and quantifying fQRS. The study sets the path for further clinical application of the developed automated fQRS algorithm.

• MeSH
• algoritmy MeSH
• elektrokardiografie * metody   MeSH
• fibrilace síní * diagnóza   MeSH
• lidé MeSH
• strojové učení MeSH
• support vector machine MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH