The research proposed in this article presents a novel improved version of the widely adopted firefly algorithm and its application for tuning and optimising XGBoost classifier hyper-parameters for network intrusion detection. One of the greatest issues in the domain of network intrusion detection systems are relatively high false positives and false negatives rates. In the proposed study, by using XGBoost classifier optimised with improved firefly algorithm, this challenge is addressed. Based on the established practice from the modern literature, the proposed improved firefly algorithm was first validated on 28 well-known CEC2013 benchmark instances a comparative analysis with the original firefly algorithm and other state-of-the-art metaheuristics was conducted. Afterwards, the devised method was adopted and tested for XGBoost hyper-parameters optimisation and the tuned classifier was tested on the widely used benchmarking NSL-KDD dataset and more recent USNW-NB15 dataset for network intrusion detection. Obtained experimental results prove that the proposed metaheuristics has significant potential in tackling machine learning hyper-parameters optimisation challenge and that it can be used for improving classification accuracy and average precision of network intrusion detection systems.

• Klíčová slova
• Benchmark, Firefly algorithm, Intrusion detection, Machine learning, Optimisation,
• Publikační typ
• časopisecké články MeSH

BACKGROUND: High frequency oscillations (HFOs) are emerging as potentially clinically important biomarkers for localizing seizure generating regions in epileptic brain. These events, however, are too frequent, and occur on too small a time scale to be identified quickly or reliably by human reviewers. Many of the deficiencies of the HFO detection algorithms published to date are addressed by the CS algorithm presented here. NEW METHOD: The algorithm employs novel methods for: 1) normalization; 2) storage of parameters to model human expertise; 3) differentiating highly localized oscillations from filtering phenomena; and 4) defining temporal extents of detected events. RESULTS: Receiver-operator characteristic curves demonstrate very low false positive rates with concomitantly high true positive rates over a large range of detector thresholds. The temporal resolution is shown to be +/-∼5ms for event boundaries. Computational efficiency is sufficient for use in a clinical setting. COMPARISON WITH EXISTING METHODS: The algorithm performance is directly compared to two established algorithms by Staba (2002) and Gardner (2007). Comparison with all published algorithms is beyond the scope of this work, but the features of all are discussed. All code and example data sets are freely available. CONCLUSIONS: The algorithm is shown to have high sensitivity and specificity for HFOs, be robust to common forms of artifact in EEG, and have performance adequate for use in a clinical setting.

• Klíčová slova
• Detection algorithm, Frequency dominance, HFO, High frequency oscillations, Ripples,
• MeSH
• algoritmy * MeSH
• artefakty MeSH
• časové faktory MeSH
• elektroencefalografie metody   MeSH
• epilepsie diagnóza   patofyziologie   MeSH
• falešně pozitivní reakce MeSH
• hlodavci MeSH
• lidé MeSH
• mozek fyziologie   patofyziologie   MeSH
• počítačové zpracování signálu MeSH
• psi MeSH
• ROC křivka MeSH
• zvířata MeSH
• Check Tag
• lidé MeSH
• psi MeSH
• zvířata MeSH
• Publikační typ
• časopisecké články MeSH

DeepFake is a forged image or video created using deep learning techniques. The present fake content of the detection technique can detect trivial images such as barefaced fake faces. Moreover, the capability of current methods to detect fake faces is minimal. Many recent types of research have made the fake detection algorithm from rule-based to machine-learning models. However, the emergence of deep learning technology with intelligent improvement motivates this specified research to use deep learning techniques. Thus, it is proposed to have VIOLA Jones's (VJ) algorithm for selecting the best features with Capsule Graph Neural Network (CN). The graph neural network is improved by capsule-based node feature extraction to improve the results of the graph neural network. The experiment is evaluated with CelebDF-FaceForencics++ (c23) datasets, which combines FaceForencies++ (c23) and Celeb-DF. In the end, it is proved that the accuracy of the proposed model has achieved 94.

• Klíčová slova
• Capsule graph network, Deep fake, Deep learning, Fake face detection, Machine learning, VIOLA Jones,
• Publikační typ
• časopisecké články MeSH

BACKGROUND: Statistical analysis, which has become an integral part of evidence-based medicine, relies heavily on data quality that is of critical importance in modern clinical research. Input data are not only at risk of being falsified or fabricated, but also at risk of being mishandled by investigators. OBJECTIVE: The urgent need to assure the highest data quality possible has led to the implementation of various auditing strategies designed to monitor clinical trials and detect errors of different origin that frequently occur in the field. The objective of this study was to describe a machine learning-based algorithm to detect anomalous patterns in data created as a consequence of carelessness, systematic error, or intentionally by entering fabricated values. METHODS: A particular electronic data capture (EDC) system, which is used for data management in clinical registries, is presented including its architecture and data structure. This EDC system features an algorithm based on machine learning designed to detect anomalous patterns in quantitative data. The detection algorithm combines clustering with a series of 7 distance metrics that serve to determine the strength of an anomaly. For the detection process, the thresholds and combinations of the metrics were used and the detection performance was evaluated and validated in the experiments involving simulated anomalous data and real-world data. RESULTS: Five different clinical registries related to neuroscience were presented-all of them running in the given EDC system. Two of the registries were selected for the evaluation experiments and served also to validate the detection performance on an independent data set. The best performing combination of the distance metrics was that of Canberra, Manhattan, and Mahalanobis, whereas Cosine and Chebyshev metrics had been excluded from further analysis due to the lowest performance when used as single distance metric-based classifiers. CONCLUSIONS: The experimental results demonstrate that the algorithm is universal in nature, and as such may be implemented in other EDC systems, and is capable of anomalous data detection with a sensitivity exceeding 85%.

• Klíčová slova
• EDC system, anomaly detection, clinical research data, data quality, real-world evidence, registry database,
• Publikační typ
• časopisecké články MeSH

OBJECTIVE: The early, simple and reliable detection of pulmonary arterial hypertension (PAH) in SSc (DETECT) study described a new algorithm for early detection of PAH in patients with SSc. The aim of this retrospective, single-centre, cross-sectional study was to apply a modified DETECT calculator in patients with SSc in the East Bohemian region, Czech Republic, to assess the risk of PAH and to compare these results with PAH screening based on the European Society of Cardiology/European Respiratory Society (ESC/ERS) 2009 guidelines. METHODS: Sixty patients were recruited with a diagnosis of SSc (according to ACR criteria), aged 27-78 years. A modified DETECT algorithm using the modified parameter of (1.4 × right ventricle diameter)(2) in place of right atrium area was applied to all patients. Right heart catheterization (RHC) was performed in all patients with an estimated (by echocardiography) increased systolic pulmonary artery pressure ≥50 mm Hg in accordance with the ESC/ERS guidelines; however, RHC was not performed in patients solely recommended for RHC using the modified DETECT algorithm. RESULTS: Using the modified DETECT calculator, 24/58 (41.4%) patients were recommended for RHC, compared with 14/58 (24.1%) when applying the ESC/ERS 2009 guidelines. PAH was diagnosed in 7/58 (12.1%) patients. During follow-up, PAH was diagnosed in six patients. Of these, four were modified DETECT score-positive for 2 years and all for 1 year before PAH diagnosis. CONCLUSION: The modified DETECT algorithm detects all patients with PAH diagnosed according to ECS/ERS 2009 guidelines and RHC. Data of the 2-year follow-up indicate a possible positive predictive role for the modified DETECT calculator.

• Klíčová slova
• cardiovascular, clinical trials and methods, epidemiology, respiratory, scleroderma and related disorders,
• MeSH
• algoritmy * MeSH
• časná diagnóza * MeSH
• centra terciární péče * MeSH
• dospělí MeSH
• echokardiografie MeSH
• incidence MeSH
• lidé středního věku MeSH
• lidé MeSH
• následné studie MeSH
• plicní hypertenze diagnóza   epidemiologie   etiologie   MeSH
• průřezové studie MeSH
• retrospektivní studie MeSH
• senioři MeSH
• srdeční katetrizace MeSH
• systémová sklerodermie komplikace   diagnóza   MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Geografické názvy
• Česká republika epidemiologie   MeSH

AIM: The aim of this study was to develop an algorithm to prompt early clinical suspicion of mucopolysaccharidosis type I (MPS I). METHODS: An international working group was established in 2016 that comprised 11 experts in paediatrics, rare diseases and inherited metabolic diseases. They reviewed real-world clinical cases, selected key signs or symptoms based on their prevalence and specificity and reached consensus about the algorithm. The algorithm was retrospectively tested. RESULTS: An algorithm was developed. In patients under two years of age, kyphosis or gibbus deformity were the key symptoms that raised clinical suspicion of MPS I and in those over two years they were kyphosis or gibbus deformity, or joint stiffness or contractures without inflammation. The algorithm was tested on 35 cases, comprising 16 Hurler, 10 Hurler-Scheie, and nine Scheie patients. Of these 35 cases, 32 (91%) - 16 Hurler, nine Hurler-Scheie and seven Scheie patients - would have been referred earlier if the algorithm had been used. CONCLUSION: The expert panel developed and tested an algorithm that helps raise clinical suspicion of MPS I and would lead to a more prompt final diagnosis and allow earlier treatment.

• Klíčová slova
• Algorithm, Diagnosis, Kyphosis, Mucopolysaccharidosis, Symptoms,
• MeSH
• algoritmy * MeSH
• časná diagnóza * MeSH
• dítě MeSH
• hodnocení rizik MeSH
• internacionalita MeSH
• konsensus MeSH
• lidé MeSH
• mukopolysacharidóza I diagnóza   terapie   MeSH
• multimorbidita MeSH
• novorozenec MeSH
• novorozenecký screening metody   MeSH
• předškolní dítě MeSH
• prognóza MeSH
• progrese nemoci MeSH
• retrospektivní studie MeSH
• sexuální faktory MeSH
• stupeň závažnosti nemoci MeSH
• věkové faktory MeSH
• Check Tag
• dítě MeSH
• lidé MeSH
• mužské pohlaví MeSH
• novorozenec MeSH
• předškolní dítě MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

The classification of bioimages plays an important role in several biological studies, such as subcellular localisation, phenotype identification and other types of histopathological examinations. The objective of the present study was to develop a computer-aided bioimage classification method for the classification of bioimages across nine diverse benchmark datasets. A novel algorithm was developed, which systematically fused the features extracted from nine different convolution neural network architectures. A systematic fusion of features boosts the performance of a classifier but at the cost of the high dimensionality of the fused feature set. Therefore, non-discriminatory and redundant features need to be removed from a high-dimensional fused feature set to improve the classification performance and reduce the time complexity. To achieve this aim, a method based on analysis of variance and evolutionary feature selection was developed to select an optimal set of discriminatory features from the fused feature set. The proposed method was evaluated on nine different benchmark datasets. The experimental results showed that the proposed method achieved superior performance, with a significant reduction in the dimensionality of the fused feature set for most bioimage datasets. The performance of the proposed feature selection method was better than that of some of the most recent and classical methods used for feature selection. Thus, the proposed method was desirable because of its superior performance and high compression ratio, which significantly reduced the computational complexity.

• Klíčová slova
• Bioimage classification, Convolutional neural networks, Evolutionary algorithms, Feature fusion, Pre-trained CNNs, Transfer learning,
• MeSH
• algoritmy * MeSH
• neuronové sítě * MeSH
• Publikační typ
• časopisecké články MeSH

BACKGROUND: Breath detection, i.e. its precise delineation in time is a crucial step in lung function data analysis as obtaining any clinically relevant index is based on the proper localization of breath ends. Current threshold or smoothing algorithms suffer from severe inaccuracy in cases of suboptimal data quality. Especially in infants, the precise analysis is of utmost importance. The key objective of our work is to design an algorithm for accurate breath detection in severely distorted data. METHODS: Flow and gas concentration data from multiple breath washout test were the input information. Based on universal physiological characteristics of the respiratory tract we designed an algorithm for breath detection. Its accuracy was tested on severely distorted data from 19 patients with different types of breathing disorders. Its performance was compared to the performance of currently used algorithms and to the breath counts estimated by human experts. RESULTS: The novel algorithm outperformed the threshold algorithms with respect to their accuracy and had similar performance to human experts. It proved to be a highly robust and efficient approach in severely distorted data. This was demonstrated on patients with different pulmonary disorders. CONCLUSION: Our newly proposed algorithm is highly robust and universal. It works accurately even on severely distorted data, where the other tested algorithms failed. It does not require any pre-set thresholds or other patient-specific inputs. Consequently, it may be used with a broad spectrum of patients. It has the potential to replace current approaches to the breath detection in pulmonary function diagnostics.

• Klíčová slova
• Automated breath detection, Breath end, Lung function testing, Medical algorithm design, Multiple breath washout test, Tidal breathing,
• MeSH
• algoritmy * MeSH
• diagnóza počítačová metody   MeSH
• dítě MeSH
• kojenec MeSH
• lidé MeSH
• mladiství MeSH
• počítačové zpracování signálu * MeSH
• předškolní dítě MeSH
• respirační funkční testy MeSH
• Check Tag
• dítě MeSH
• kojenec MeSH
• lidé MeSH
• mladiství MeSH
• mužské pohlaví MeSH
• předškolní dítě MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

Any engineering system involves transitions that reduce the performance of the system and lower its comfort. In the field of automotive engineering, the combination of multiple motors and multiple power sources is a trend that is being used to enhance hybrid electric vehicle (HEV) propulsion and autonomy. However, HEV riding comfort is significantly reduced because of high peaks that occur during the transition from a single power source to a multisource powering mode or from a single motor to a multiple motor traction mode. In this study, a novel model-based soft transition algorithm (STA) is used for the suppression of large transient ripples that occur during HEV drivetrain commutations and power source switches. In contrast to classical abrupt switching, the STA detects transitions, measures their rates, generates corresponding transition periods, and uses adequate transition functions to join the actual and the targeted operating points of a given HEV system variable. As a case study, the STA was applied to minimize the transition ripples that occur in a fuel cell-supercapacitor HEV. The transitions that occurred within the HEV were handled using two proposed transition functions which were: a linear-based transition function and a stair-based transition function. The simulation results show that, in addition to its ability to improve driving comfort by minimizing transient torque ripples and DC bus voltage fluctuations, the STA helps to increase the lifetime of the motor and power sources by reducing the currents drawn during the transitions. It is worth noting that the considered HEV runs on four-wheel drive when the load torque applied on it exceeds a specified torque threshold; otherwise, it operates in rear-wheel drive.

• Klíčová slova
• fuel cell (FC), hybrid electric vehicle, operating point, soft transition algorithm, supercapacitor (SC), transition function,
• MeSH
• algoritmy * MeSH
• elektřina MeSH
• motorová vozidla MeSH
• počítačová simulace MeSH
• řízení motorových vozidel * MeSH
• zdroje elektrické energie MeSH
• Publikační typ
• časopisecké články MeSH

This study introduces an innovative approach to enhance fault detection in XLPE-covered conductors used for power distribution systems. These covered conductors are widely utilized in forested areas (natural parks) to decrease the buffer zone and increase the reliability of the distribution network. Recognizing the imperative need for precise fault detection in this context, this research employs an antenna-based method to detect a particular type of fault. The present research contains the classification of fault type detection, which was previously accomplished using a very expensive and challenging-to-install galvanic contact method, and only to a limited extent, which did not provide information about the fault type. Additionally, differentiating between types of faults in the contact method is much easier because information for each phase is available. The proposed method uses antennas and a classifier to effectively differentiate between fault types, ranging from single-phase to three-phase faults, as well as among different types of faults. This has never been done before. To bolster the accuracy, a stacking ensemble method involving the logistic regression is implemented. This approach not only advances precise fault detection but also encourages the broader adoption of covered conductors. This promises benefits such as a reduced buffer zone, improved distribution network reliability, and positive environmental outcomes through accident prevention and safe covered conductor utilization. Additionally, it is suggested that the fault type detection could lead to a decrease in false positives.

• Klíčová slova
• covered conductors, fault diagnosis, frequency domain analysis, partial discharge, radio antenna,
• Publikační typ
• časopisecké články MeSH