Search

The aviation industry is one of the fastest-growing sectors and is crucial for both passenger transport and logistics. However, the high costs associated with maintenance, refurbishment, and overhaul (MRO) constitute one of the biggest challenges facing this industry. Motivated by the significant role that remaining useful life (RUL) prognostics can play in optimising MRO operations and saving lives, this paper proposes a novel data-driven RUL prognosis model based on counter propagation network principles. The proposed model introduces the recursive growing hierarchical self-organisation map (ReGHSOM) as a variant of SOM that can cluster multivariate time series with high correlations and hierarchical dependencies typically found in RUL datasets. Moreover, ReGHSOM is designed to allow this clustering to evolve dynamically at runtime without imposing constraints or prior assumptions on the hypothesis spaces of the architectures. The output of ReGHSOM is fed into the supervised learning layers of Grossberg to make the RUL prediction. The performance of the proposed model is comprehensively evaluated by measuring its learnability, evolution, and comparison with related work using standard statistical metrics. The results of this evaluation show that the model can achieve an average mean square error of 5.24 and an average score of 293 for the C-MPASS dataset, which are better results than most of the comparable works. [ABSTRACT FROM AUTHOR]

An unsupervised spoken term discovery task aims to capture the pattern similarities among spoken terms in the absence of annotation. Such an approach is useful for the untranscribed spoken content from low-resource or zero-resource languages. A challenge in the discovery task is to compute the similarities among spoken terms without annotation. Dynamic time warping (DTW) is one of the techniques that computes temporal alignment between two acoustic feature representations of the speech signal without annotation. However, the speech variabilities that arise in natural speech introduce a challenge to the DTW approach. As a result, the performance of the spoken term discovery task was degraded. In this study, we overcome the challenges and improve the performance of the discovery task in three stages. At first, the speaker-independent acoustic feature representation was obtained from the Self Organising Map (SOM) to reduce the variabilities. In the second stage, non-segmental pseudo-labels were generated for the spoken content using context-free grammar. Finally, the spoken term similarities were obtained by grouping the similar sequences using proposed Label Sequence Similarity Mapping and Language modelling algorithms. The performance of the proposed system was measured using the Zero-Speech challenge corpus in terms of matching, clustering and parsing qualities. The experimental results reveal that the proposed approach improves the performance by 34.2% and 22.4% in English and Xitsonga, respectively, across multiple speakers. In addition, the clustering performance of the spoken terms at the word level was improved by 4.2% in English. [ABSTRACT FROM AUTHOR]

Introduction: Oxford Nanopore Technologies (ONT) is a third generation sequencing approach that allows the analysis of individual, full-length nucleic acids. ONT records the alterations of an ionic current flowing across a nano-scaled pore while a DNA or RNA strand is threading through the pore. Basecalling methods are then leveraged to translate the recorded signal back to the nucleic acid sequence. However, basecall generally introduces errors that hinder the process of barcode demultiplexing, a pivotal task in single-cell RNA sequencing that allows for separating the sequenced transcripts on the basis of their cell of origin.Methods: To solve this issue, we present a novel framework, called UNPLEX, designed to tackle the barcode demultiplexing problem by operating directly on the recorded signals. UNPLEX combines two unsupervised machine learning methods: autoencoders and self-organizing maps (SOM). The autoencoders extract compact, latent representations of the recorded signals that are then clustered by the SOM.Results and Discussion: Our results, obtained on two datasets composed of in silico generated ONT-like signals, show that UNPLEX represents a promising starting point for the development of effective tools to cluster the signals corresponding to the same cell.

Medical professionals need help finding tumours in the ground truth image of the brain because the tumours’ location, contrast, intensity, size, and shape vary between images because of different acquisition methods, modalities, and the patient’s age. The medical examiner has difficulty manually separating a tumour from other parts of a Magnetic Resonance Imaging (MRI) image. Many semi- and fully automated brain tumour detection systems have been written about in the literature, and they keep improving. The segmentation literature has seen several transformations throughout the years. An in-depth examination of these methods will be the focus of this investigation. We look at the most recent soft computing technologies used in MRI brain analysis through several review papers. This study looks at Self-Organising maps (SOM) with K-means and the kernel Fuzzy c-means (KFCM) method for segmenting them. The suggested SOM networks were first compared to K-means analysis in an experiment based on datasets with well-known cluster solutions. Later, the SOM is combined with KFCM, reducing time complexity and producing more accurate results than other methods. Experiments show that skewed data improves networks’ performance with more SOMs. Finally, performance measures in real-time datasets are analysed using machine learning approaches. The results show that the proposed algorithm has good sensitivity and better accuracy than k-means and other state-of-art methods. [ABSTRACT FROM AUTHOR]

The aviation industry is one of the fastest-growing sectors and is crucial for both passenger transport and logistics. However, the high costs associated with maintenance, refurbishment, and overhaul (MRO) constitute one of the biggest challenges facing this industry. Motivated by the significant role that remaining useful life (RUL) prognostics can play in optimising MRO operations and saving lives, this paper proposes a novel data-driven RUL prognosis model based on counter propagation network principles. The proposed model introduces the recursive growing hierarchical self-organisation map (ReGHSOM) as a variant of SOM that can cluster multivariate time series with high correlations and hierarchical dependencies typically found in RUL datasets. Moreover, ReGHSOM is designed to allow this clustering to evolve dynamically at runtime without imposing constraints or prior assumptions on the hypothesis spaces of the architectures. The output of ReGHSOM is fed into the supervised learning layers of Grossberg to make the RUL prediction. The performance of the proposed model is comprehensively evaluated by measuring its learnability, evolution, and comparison with related work using standard statistical metrics. The results of this evaluation show that the model can achieve an average mean square error of 5.24 and an average score of 293 for the C-MPASS dataset, which are better results than most of the comparable works.

This study was aimed to analyse the lower limb kinematics during the change of direction (COD) performance with the dominant (DL) and non-dominant (NDL) leg using linear (traditional kinematics) and nonlinear (Self Organising Map-based cluster analysis) approaches. Three 5-0-5 COD performances with the DL and three with the NDL were performed by 23 (aged 21.6 ± 2.3 years) collegiate athletes. No significant difference was observed between the COD duration, and approach speed of DL and NDL. Significantly greater ankle abductions, knee and hip external rotations were identified in COD with DL, compared to NDL (p < .001, d > 0.8). Self Organising Maps portrayed a completely different coordination pattern profile during change of direction performance with the DL and NDL. The cluster analysis illustrated similar inter-individual coordination patterning when participants turned with their DL or NDL. No visible relationship was observed in the cluster analysis of the lower limb joint angles and angular velocities. Outcomes of this study portrayed that coordination patterning (combination of joint angles and the rate of change of angles) could portray the movement patterning differences in different tasks, while a sole investigation on the joint angles or angular velocities may not reveal the underlying mechanisms of movement patterning. [ABSTRACT FROM AUTHOR]

Geotechnical complexity in mining often leads to geotechnical uncertainty which impacts both safety and productivity. However, as mining progresses, particularly for strip mining operations, a body of knowledge is acquired which reduces this uncertainty and can potentially be used by mining engineers to improve the prediction of future mining conditions. In this paper, we describe a new method to support this approach based on modelling and neural networks. A high-level causal model of the mining operations based on historical data for a number of parameters was constructed which accounted for parameter interactions, including hydrogeological conditions, weather, and prior operations. An artificial neural network was then trained on this historical data, including production data. The network can then be used to predict future production based on presently observed mining conditions as mining proceeds and compared with the model predictions. Agreement with the predictions indicates confidence that the neural network predictions are properly supported by the newly available data. The efficacy of this approach is demonstrated using semi-synthetic data based on an actual mine.

The ability to score from placekicks discriminates winning from losing Rugby Union teams. We aimed to identify which biomechanical variables related to successful placekicking in professional Rugby Union players, and use self-organising maps (SOM) to determine whether meaningful sub-groups existed. Three professional placekickers performed 10 kicks outdoors. Placekicks were categorised into best, worst, and typical performances based on outcomes and coach and player perceptions. Seven 3D biomechanical variables consistently and meaningfully (moderate Cohen's effect size) discriminated best from worst placekicks in all players. The three-cluster solution from SOM on these seven variables highlighted differences between players rather than best, worst, and typical attempts. Within-clusters, however, the best and worst placekicks tended to be represented in separate map regions. The seven variables identified using standardised effect sizes can be useful for group-level coaching of placekicking skills in absence of individual data, and translated in an applied setting using verbal and visual cues to promote overall placekicking performance. However, players' idiosyncrasies formed the main SOM boundaries, indicating that optimising placekicking success would benefit from an individualised approach and numerous effective movement templates may exist. [ABSTRACT FROM AUTHOR]

Salinity levels above the drinking water standard (>250 mg/l Cl–) are observed at shallow depth in a Maastrichtian chalk aquifer on the island of Falster, south-eastern Denmark. To understand the source of the salt, 63 samples from 12 individual, 1 m, screened intervals between 14 and 26 m b.s. were collected from 1 May to 4 June 2018. The samples were collected during a tracer test to estimate the dual porosity properties of the chalk and were analysed for a wide range of elements. Furthermore, samples from the Baltic Sea and from deeper saline aquifers in the area (40 and 85 m b.s.) were analysed for comparison. The geochemical data were analysed using an unsupervised machine-learning algorithm, self-organising maps, to fingerprint water sources. The water composition in the screened intervals at various stratigraphic levels has specific geochemical fingerprints that are maintained for the first days of pumping and are distinct amongst the different levels. This suggests an evolution in water composition because of reaction with the chalk. Water composition is distinct from both seawater from the nearby Baltic Sea and salty water from deeper levels of the reservoir. Thus, neither up-coning of salty water nor intrusion of seawater caused the elevated salinity levels in the area. The slightly saline composition of groundwater in the shallow aquifer (14–26 m b.s.) is more likely because of incomplete refreshing of the salty connate water in the chalk during the Pleistocene and Holocene. Furthermore, the geochemical fingerprint of salty water from the deeper aquifer at 40 m was similar to water from the Baltic Sea, suggesting a Baltic Sea source for salt in the aquifer at 40 m b.s., c. 100 m from the coast. Statistical analysis based on self-organising maps is an effective tool for interpreting a large number of variables to understand the compositional variation in an aquifer and a useful alternative to linear dimensionality-reduction methods such as principal component analysis. The approach using the multi-element analysis combined with the analysis of self-organising maps may be useful in future studies of groundwater quality.

Structural and multidisciplinary design under uncertainty for high reliability or equivalently small probability of failure is a challenging task owing to the high computational cost associated with generating the samples at the extreme (tail) of the underlying distribution. Among other approaches, statistics of extremes based techniques are usually suitable for small probability estimation. However, typically only 10% of the samples generated that correspond to the tail of the distribution are used for probability estimation. If apriori information about regions in the design space that corresponds to the tail is available, additional samples in the identified region permit better tail fit and hence better probability estimation. In the current work, we propose iSOM (interpretable Self-Organising Map) to identify region/s in the design space, that corresponds to the extremes. An initial sample is used to map (visualize) the limit state function and random/design variables using iSOM which permits the designer to identify the region(s) that corresponds to the tail of the response. Adaptive sampling is performed in the identified region of interest to obtain additional samples. Next, the cumulative distribution function (CDF) of the response using initial as well as adaptive samples is evaluated for probability estimation. The effectiveness of the proposed approach is evident from its successful implementation on benchmark examples, real-world engineering examples, and a multi-objective reliability-based design optimization (MORBDO) case. The proposed method showcases the capability of iSOM to perform adaptive sampling for limit-state functions characterized by non-linearity and multiple modes. iSOM-enabled sampling in conjunction with log-TPNT provides better estimates of small failure probabilities than log-TPNT alone. The results from the proposed approach is compared with results from state-of-the-art (SOTA) sampling and surrogate-based techniques. For a given number of limit state evaluations, the proposed approach estimates probabilities of the order 1e−4, with lesser variance, compared to other SOTA approaches. Hence, the proposed approach is likely to encourage further research into employing iSOM-assisted sampling for other reliability estimation methods as well. • Identification of region/s contributing to small failure probability using iSOM. • Adaptive sampling in identified region/s in the design space. • Proposed approach of log-TPNT-iSOM for small failure probability estimation. • Comparison and performance evaluation of the proposed approach. • iSOM-aided multi-objective reliability-based design optimization. [Display omitted] [ABSTRACT FROM AUTHOR]

Renewable energy is a sustainable solution for reducing environmental impacts resulted from total energy production and consumption. The offshore wind energy as a clean energy choice of electricity production has been growing fast. There is a large amount of literature on the cost reduction strategies of offshore wind energy. In this study, the key cost drivers of offshore wind farms development are identified according to the content analysis of the literature. A segmentation approach to offshore wind farms is then proposed based on multiple factors including costs, spatial information, foundation type, the length of inter-array cables and the turbine manufacturers. This study focuses on 35 offshore wind farms located in the North Sea.

A protein’s structure is the key to its function. As protein structure can vary with environment, it is important to be able to determine it over a wide range of concentrations, temperatures, formulation vehicles, and states. Robust reproducible validated methods are required for applications including batch-batch comparisons of biopharmaceutical products. Circular dichroism is widely used for this purpose, but an alternative is required for concentrations above 10 mg/mL or for solutions with chiral buffer components that absorb far UV light. Infrared (IR) protein absorbance spectra of the Amide I region (1,600–1700 cm−1) contain information about secondary structure and require higher concentrations than circular dichroism often with complementary spectral windows. In this paper, we consider a number of approaches to extract structural information from a protein infrared spectrum and determine their reliability for regulatory and research purpose. In particular, we compare direct and second derivative band-fitting with a self-organising map (SOM) approach applied to a number of different reference sets. The self-organising map (SOM) approach proved significantly more accurate than the band-fitting approaches for solution spectra. As there is no validated benchmark method available for infrared structure fitting, SOMSpec was implemented in a leave-one-out validation (LOOV) approach for solid-state transmission and thin-film attenuated total reflectance (ATR) reference sets. We then tested SOMSpec and the thin-film ATR reference set against 68 solution spectra and found the average prediction error for helix (α + 310) and β-sheet was less than 6% for proteins with less than 40% helix. This is quantitatively better than other available approaches. The visual output format of SOMSpec aids identification of poor predictions. We also demonstrated how to convert aqueous ATR spectra to and from transmission spectra for structure fitting. Fourier self-deconvolution did not improve the average structure predictions.

The detailed analysis of individual rain event characteristics is an important step for improving our understanding of variations in precipitation over different topographies. In this study, the homogeneity among rain gauges was investigated using the concept of 'rain event properties'. Thirty-one properties of 23,176 rain events recorded at 47 meteorological stations in Mumbai, India, were analysed utilising seasonal (June–September) rainfall records over 2006–2016. The random forest model was used to evaluate the importance of rain event variables, thus leading to an optimum subset of variables. As a result, 12 signature variables portraying various aspects of rain event behaviour at each station were obtained. The high similarities among the variables indicated similarities among the rain gauges. Furthermore, similar rain gauges were distinguished, investigated, and characterised by cluster analysis using self-organising maps. The cluster analysis results show six clusters of similarly behaving rain gauges, where each cluster addresses one isolated class of variables for the rain gauge. Additionally, the clusters confirm the spatial variation in rainfall caused by the complex topography of Mumbai, comprising the flatland near the Arabian Sea, high-rise buildings (urban areas), and mountain and hill areas (Sanjay Gandhi National Park located in the northern part of Mumbai). [ABSTRACT FROM AUTHOR]

The analysis of change processes in relation to spatial patterns is gaining increasing attention in landscape ecology. Forest spatial pattern change is a critical process in landscape dynamics, and has a significant impact on the biodiversity, habitat quality, and ultimately, variation in the overall function of a forest ecosystem. The purpose of this study is to characterise the forest spatial pattern evolution over a 1 × 1 km2 landscape units covering Shanxi, which is a major coal-energy province in northern China. Four landscape metrics, i.e., aggregation index (AI), largest patch index (LPI), patch density (PD), and shape index (SI), were derived based upon annual forest distribution maps (1987–2018). These metrics were used to identify three spatially heterogeneous pattern types: severely fragmentised pattern (SFP), incompletely fragmentised pattern (IFP), and relatively intact pattern (RIP), based on the integration of the self-organising map (SOM) with k-means algorithms. Post-classification change detection was conducted to analyse the change process of the forest spatial patterns. Results indicate that:(i) the average proportion of forest area with the RIP was approximately 50%, making it the dominant spatial pattern type; whereas forest areas with the SFP and IFP gradually approached each other in value; (ii) 80.7% landscape units experienced a pattern change, wherein the area with the SFP was always more likely to disappear during transition; (iii) Therein, the change times primarily concentrated between 2 and 4 for 66% of these units and the change duration was primarily in the range of 7–17 years. A relatively high proportion of pattern change occurred for sequential periods (2002–2005), and that the IFP interacts with the other pattern types most frequently. We concluded that the evaluation of multiple landscape metrics is effective in identifying spatial patterns through the combined use of the SOM with the k-means cluster. The spatial pattern and landscape change processes are mutually restricted, and the forest spatial pattern has its own internal dynamics that has a different effect on the change processes.

Biometric systems are widely used in applications such as forensics and military. Biometric authentication is a challenging and complex task. These biometric systems must be accurate for practical applications. In this era of artificial intelligence, artificial neural network‐based classifiers are widely used in biometric‐based systems. However, most of the artificial neural network‐based classifiers are less accurate and computationally complex. In this work, two modified self‐organising map (SOM) networks are proposed for iris image classification to improve the performance measures. Particle swarm optimization technique is used in the training process of conventional SOM. The experiments are carried out with conventional and modified classifiers. The proposed modified classifiers provide better performance than the conventional SOM classifier. [ABSTRACT FROM AUTHOR]

This research study is intended to deliver effective magnetic resonance (MR) brain image segmentation, which is an ambiguous process in the domain of medical image analysis. In general, MR brain image comprises various tissue structures; and an accurate representation of the above‐mentioned regions is essential to have a perfect identification of different grades of tumours, and obtaining effective demarcation of different areas in which the oedema portion is widespread. The accurate representation and identification of the abnormal regions in the MR images can be a vital tool for the radiologists and oncologists to proceed further with the treatment processes. This study aims in developing a novel automated approach that combines self‐organising map and interval type‐2 fuzzy logic clustering, providing ample knowledge to the clinicians in identifying the aberrant regions present in the patient brain. A non‐invasive analysis blended with quicker segmentation results are proffered by the proposed methodology and its functioning abilities have been assessed using comparison metrics such as mean‐squared error (MSE), peak signal‐to‐noise ratio (PSNR), processing time duration, and few other standard metrics. The proposed methodology has offered commendable MSE and PSNR values, which are 0.234778 and 54.847 dB, and it can be undeniably utilised for analysing the patient diseases. [ABSTRACT FROM AUTHOR]

Purpose: Data envelopment analysis (DEA) and analytical hierarchy process (AHP) are two widely applied methods to evaluate and rank suppliers in terms of sustainability. In this study, to investigate the extent to which potential differences in the outcomes of these two methods influence the benchmarking strategies, a comparative analysis based on a common set of data gathered from 19 logistics service providers is implemented. Design/methodology/approach: As suppliers' sustainability cannot be improved in a single-step process due to several limitations, improvement needs to proceed gradually. Therefore, using the self-organising map method, the suppliers were classified into clusters within a novel framework for gradually improving their sustainability. Then, the two processes of gradual improvement based on the outcomes of DEA and AHP were compared. Findings: The findings show that although the rankings of suppliers guided by the methods correlated to a high degree, the benchmarking strategies provided by the methods for gradually improving the sustainability of suppliers differed considerably. In particular, whereas AHP suggests a benchmarking policy better suited for unsustainable or less sustainable suppliers with limited access to resources, DEA proposes one for suppliers able to dramatically boost their sustainability with few quick, significant leaps in performance. Originality/value: First, this study revealed a novel gradual improvement framework using the self-organising map method. Second, it clarified the extent to which the benchmarking policies are influenced by the type of evaluation method. [ABSTRACT FROM AUTHOR]

Renewable energy is a sustainable solution for reducing environmental impacts resulted from total energy production and consumption. The offshore wind energy as a clean energy choice of electricity production has been growing fast. There is a large amount of literature on the cost reduction strategies of offshore wind energy. In this study, the key cost drivers of offshore wind farms development are identified according to the content analysis of the literature. A segmentation approach to offshore wind farms is then proposed based on multiple factors including costs, spatial information, foundation type, the length of inter-array cables and the turbine manufacturers. This study focuses on 35 offshore wind farms located in the North Sea. [ABSTRACT FROM AUTHOR]

In recent years, data-enabled technologies have intensified the rate and scale at which organisations collect and analyse data. Data mining techniques are applied to realise the full potential of large-scale data analysis. These techniques are highly efficient in sifting through big data to extract hidden knowledge and assist evidence-based decisions, offering significant benefits to their adopters. However, this capability is constrained by important legal, ethical and reputational concerns. These concerns arise because they can be exploited to allow inferences to be made on sensitive data, thus posing severe threats to individuals’ privacy. Studies have shown Privacy-Preserving Data Mining (PPDM) can adequately address this privacy risk and permit knowledge extraction in mining processes. Several published works in this area have utilised clustering techniques to enforce anonymisation models on private data, which work by grouping the data into clusters using a quality measure and generalising the data in each group separately to achieve an anonymisation threshold. However, existing approaches do not work well with high-dimensional data, since it is difficult to develop good groupings without incurring excessive information loss. Our work aims to complement this balancing act by optimising utility in PPDM processes. To illustrate this, we propose a hybrid approach, that combines self-organising maps with conventional privacy-based clustering algorithms. We demonstrate through experimental evaluation, that results from our approach produce more utility for data mining tasks and outperforms conventional privacy-based clustering algorithms. This approach can significantly enable large-scale analysis of data in a privacy-preserving and trustworthy manner.

The spatial pixel resolution of common multispectral and hyperspectral sensors is generally not sufficient to avoid that multiple elementary materials contribute to the observed spectrum of a single pixel. To alleviate this limitation, spectral unmixing is a by‐pass procedure which consists in decomposing the observed spectra associated with these mixed pixels into a set of component spectra, or endmembers, and a set of corresponding proportions, or abundances, that represent the proportion of each endmember in these pixels. In this study, a spectral unmixing technique is proposed to handle the challenging scenario of non‐linear mixtures. This algorithm relies on a dedicated implementation of multiple‐kernel learning using self‐organising map proposed as a solver for the non‐linear unmixing problem. Based on a priori knowledge of the endmember spectra, it aims at estimating their relative abundances without specifying the non‐linear model under consideration. It is compared to state‐of‐the‐art algorithms using synthetic yet realistic and real hyperspectral images. Results obtained from experiments conducted on synthetic and real hyperspectral images assess the potential and the effectiveness of this unmixing strategy. Finally, the relevance and potential parallel implementation of the proposed method is demonstrated. [ABSTRACT FROM AUTHOR]

Highlights • Comparison of prognostics methods on instantaneous failure mode. • Benchmarking of prognostics methods on industrial reciprocating compressor. • Use of actual, non-uniformly sampled valve failure measurements. • Proposal SOM as prognostics tool, and RUL estimation variation based on SOM or KNNR. • Proposal Hotelling T 2 and Q residuals metrics as health indicators and RUL predictors. Abstract One of the major targets in industry is minimisation of downtime and cost, and maximisation of availability and safety, with maintenance considered a key aspect in achieving this objective. The concept of Condition Based Maintenance and Prognostics and Health Management (CBM/PHM), which is founded on the principles of diagnostics, and prognostics, is a step towards this direction as it offers a proactive means for scheduling maintenance. Reciprocating compressors are vital components in oil and gas industry, though their maintenance cost is known to be relatively high. Compressor valves are the weakest part, being the most frequent failing component, accounting for almost half maintenance cost. To date, there has been limited information on estimating Remaining Useful Life (RUL) of reciprocating compressor in the open literature. This paper compares the prognostic performance of several methods (multiple linear regression, polynomial regression, Self-Organising Map (SOM), K-Nearest Neighbours Regression (KNNR)), in relation to their accuracy and precision, using actual valve failure data captured from an operating industrial compressor. The SOM technique is employed for the first time as a standalone tool for RUL estimation. Furthermore, two variations on estimating RUL based on SOM and KNNR respectively are proposed. Finally, an ensemble method by combining the output of all aforementioned algorithms is proposed and tested. Principal components analysis and statistical process control were implemented to create T 2 and Q metrics, which were proposed to be used as health indicators reflecting degradation processes and were employed for direct RUL estimation for the first time. It was shown that even when RUL is relatively short due to instantaneous nature of failure mode, it is feasible to perform good RUL estimates using the proposed techniques. [ABSTRACT FROM AUTHOR]

Late glacial and Holocene environmental history of Lake Łukie and its catchment is reconstructed from the lake sediments. This shallow lake is situated in the marshy Polesie region in eastern Poland. Sediments began to accumulate in the lake in the Older Dryas. On the basis of macrofossils, pollen, and Oribatida remains, and with the use of Kohonen’s artificial neural network (self-organising map, SOM), six stages (corresponding to subclusters X 1 , X 2 , X 3 in cluster X, and Y 1 , Y 2 , Y 3 in cluster Y) of the lake history were distinguished, and indicator taxa of each stage were identified from the indicator value (IndVal) index. During the transition period corresponding to the border between X and Y, the ecosystem transformed in the broad sense from the protocratic to mesocratic phase in a 5-point scale transformation of the landscape in the glacial–interglacial cycle. All the steps involved in post-glacial history succession during interglacial cycles include changes in climate, soil, and biotic interactions. Indicator taxa for the subsequent SOM subclusters X 1 , X 2 , and X 3 are associated with the first phase of the protocratic glacial–interglacial cycle. The transformation that occurs on the level of cluster Y (subcluster Y 1 ) is the mesocratic phase (ca. 9000–5000 14 C age BP), which is characterised by high temperatures and development of closed forest (climax forest). Subcluster Y 2 corresponds to the transformation of forest cover during the oligocratic phase (ca. 5000–3000 14 C age BP), which is associated with decreasing forest share and deteriorating soils. Finally, subcluster Y 3 can be associated with the telocratic phase, characterised by the influence of a more oceanic climate (from ca. 2500 14 C age BP) with declining temperatures, higher humidity, and milder seasonal contrasts, which contributed to the development of more open vegetation and infertile soils. This stage also corresponds to an increased human activity and landscape transformation, such as from forests to cornfields and from wetlands to meadows. Interestingly, the currently strictly protected brittle naiad ( Najas minor ) was present in the lake during the Atlantic, Subboreal, and Subatlantic periods; however, this species is not listed as being part of the present vegetation and may have become extinct relatively recently. [ABSTRACT FROM AUTHOR]

Presently, there is an increasing interest in the deployment of unmanned surface vehicles (USVs) to support complex ocean operations. In order to carry out these missions in a more efficient way, an intelligent hybrid multi-task allocation and path planning algorithm is required and has been proposed in this paper. In terms of the multi-task allocation, a novel algorithm based upon a self-organising map (SOM) has been designed and developed. The main contribution is that an adaptive artificial repulsive force field has been constructed and integrated into the SOM to achieve collision avoidance capability. The new algorithm is able to fast and effectively generate a sequence for executing multiple tasks in a cluttered maritime environment involving numerous obstacles. After generating an optimised task execution sequence, a path planning algorithm based upon fast marching square (FMS) is utilised to calculate the trajectories. Because of the introduction of a safety parameter, the FMS is able to adaptively adjust the dimensional influence of an obstacle and accordingly generate the paths to ensure the safety of the USV. The algorithms have been verified and evaluated through a number of computer based simulations and has been proven to work effectively in both simulated and practical maritime environments. [ABSTRACT FROM AUTHOR]

In this paper, a speaker verification algorithm, which is inspired by the physiology of hearing in the human auditory system, is proposed. The algorithm uses a modified self-organising map composed of spiking neurons. The architecture of the algorithm imitates the biomechanical mechanism of the human auditory system, which converts the speech signal from sound vibration waves into electrical spikes inside the cochlea. The paper also suggests a spike-based rank order coding input feature vector, which is designed to be representative of the real biological spike trains found within the human auditory nerve. During the training phase, the winner neuron in the proposed Spiking Self-Organising Map is updated only when its activity exceeds a specified threshold. The algorithm is evaluated using 50 speakers from the Centre for Spoken Language Understanding (CSLU2002) speaker verification database and shows a speaker verification performance of 90.1%. This compares favourably with previous non-spiking self-organising map that used Discrete Fourier Transform-based input feature vector with the same dataset. [ABSTRACT FROM AUTHOR]

Aims/hypothesis: Previously, we proposed that data-driven metabolic subtypes predict mortality in type 1 diabetes. Here, we analysed new clinical endpoints and revisited the subtypes after 7 years of additional follow-up. Methods: Finnish individuals with type 1 diabetes (2059 men and 1924 women, insulin treatment before 35 years of age) were recruited by the national multicentre FinnDiane Study Group. The participants were assigned one of six metabolic subtypes according to a previously published self-organising map from 2008. Subtype-specific all-cause and cardiovascular mortality rates in the FinnDiane cohort were compared with registry data from the entire Finnish population. The rates of incident diabetic kidney disease and cardiovascular endpoints were estimated based on hospital records. Results: The advanced kidney disease subtype was associated with the highest incidence of kidney disease progression (67.5% per decade, p < 0.001), ischaemic heart disease (26.4% per decade, p < 0.001) and all-cause mortality (41.5% per decade, p < 0.001). Across all subtypes, mortality rates were lower in women compared with men, but standardised mortality ratios (SMRs) were higher in women. SMRs were indistinguishable between the original study period (1994-2007) and the new period (2008-2014). The metabolic syndrome subtype predicted cardiovascular deaths (SMR 11.0 for men, SMR 23.4 for women, p < 0.001), and women with the high HDL-cholesterol subtype were also at high cardiovascular risk (SMR 16.3, p < 0.001). Men with the low-cholesterol or good glycaemic control subtype showed no excess mortality. Conclusions/interpretation: Data-driven multivariable metabolic subtypes predicted the divergence of complication burden across multiple clinical endpoints simultaneously. In particular, men with the metabolic syndrome and women with high HDL-cholesterol should be recognised as important subgroups in interventional studies and public health guidelines on type 1 diabetes. [ABSTRACT FROM AUTHOR]

ABSTRACT Ozone and particle pollution are of concern for the Sydney basin, in particular during warm months (November to March) when pollution levels can exceed national standards. Previous studies on the relationship between synoptic circulation and air quality focused on high pollution days or aggregated air quality conditions over the region as a whole. This study provides both temporal and spatial analyses of the synoptic processes affecting warm-month ozone and particle pollution in Sydney. A warm-month synoptic catalogue was developed by applying the self-organising map method to the NCEP/NCAR geopotential height reanalysis for south-east Australia. The catalogue was linked to mesoscale meteorological features such as drainage flows and sea breezes, and subsequently to the spatial variability in air quality across the Sydney basin. The typical synoptic types commonly associated with high or low ozone and PM10 levels, as well as variations in visibility, were identified. The results suggest that, due to Sydney's subtropical coastal-basin environment, the interaction between meso- and synoptic-scale features determine local air quality conditions in the region, rather than the synoptic conditions alone. Emissions from bushfires appear to have considerable impacts on the synoptic modulation to visibility and PM10 levels, with such impacts tending to be more at a local scale. In contrast, no comparable impacts were found for ozone pollution. For ozone and visibility, the probability for an exceedance day under some synoptic types varied considerably over time, implying that there might have been a shift in the role of synoptic modulation to local air quality associated with changes in air emissions profiles. This study provides a leap in our understanding of the relationship between synoptic circulation and air quality in a coastal-basin environment. The results are useful for improving air quality forecasting in Sydney, with the methodology developed readily applicable to similar regions elsewhere. [ABSTRACT FROM AUTHOR]

Qualification analysis and reliability testing of electronic components represent a major activity in the process of development of electronic equipment. Electronics manufacturers have to adopt often costly test programmes to ensure qualification standards and reliability requirements are met. This paper details a novel similarity-based qualification approach for assessing expected reliability of electronic components, and in general electronic products, as an alternative to conventional physical testing. The originality of this work is in the proposed approach which introduces a new way of qualifying electronic components based on similarity with previously assessed and qualified components. This novel approach has the potential to transform in a major way the current operational practices in the industry, demanding at present substantial physical testing, by offering a complementary, “virtual qualification” route for addressing the cost and time challenges associated with qualification tests. A major achievement is the comprehensive and detailed demonstration of the proposed reliability qualification approach. Case studies on qualifying electronic components to the thermal loads induced by a particular post-manufacturing process widely adopted by high-reliability electronics sectors – the robotic hot solder dip (refinishing) process, and associated risks of thermo-mechanical damage are presented and discussed. [ABSTRACT FROM AUTHOR]

Trading on major financial markets is typically conducted via electronic order books whose state is visible to market participants in real-time. A significant research literature has emerged concerning order book evolution, focussing on characteristics of the order book such as the time series of trade prices, movements in the bid-ask spread and changes in the depth of the order book at each price point. The latter two items can be characterised as order book shape where the book is viewed as a histogram with the size of the bar at each price point corresponding to the volume of shares demanded or offered for sale at that price. Order book shape is of interest to market participants as it provides insight as to current, and potentially future, market liquidity. Questions such as what shapes are commonly observed in order books and whether order books transition between certain shape patterns over time are of evident interest from both a theoretical and practical standpoint. In this study, using high-frequency equity data from the London Stock Exchange, we apply an unsupervised clustering methodology to determine clusters of common order book shapes, and also attempt to assess the transition probabilities between these clusters. Findings indicate that order books for individual stocks display intraday seasonality, exhibit some common patterns, and that transitions between order book patterns over sequential time periods is not random. [ABSTRACT FROM AUTHOR]

We use a new method based on point correlation maps and self-organising maps (SOMs) to identify teleconnection patterns in 60 yr of National Centres for Environmental Prediction/National Centre for Atmospheric Research (NCEP/NCAR) sea level pressure (SLP) re-analysis data. The most prevalent patterns are the El Nino Southern Oscillation (ENSO), the North Atlantic Oscillation (NAO) and the Southern Annular Mode (SAM). Asymmetries are found between base points in opposite centres of action of the NAO and the Pacific North America pattern (PNA). The SOM-based method is a powerful tool that allows us to efficiently assess how realistically teleconnections are reproduced in any climate model. The degree of agreement between modelled and re-analysis-based teleconnections (or between different models) can be summarised in a single plot. Here, we illustrate this by assessing the skill of the medium complexity climate model FORTE (Fast Ocean Rapid Troposphere Experiment). FORTE reproduces some realistic teleconnections, such as the Arctic Oscillation (AO), the NAO, the PNA, the SAM, the African Monsoon and ENSO, along with several other teleconnections, which resemble to varying degrees the corresponding NCEP patterns. However, FORTE tends to underestimate the strength of the correlation patterns and the patterns tend to be slightly too zonal. The accuracy of frequency of occurrence is variable between patterns. The Indian Ocean is a region where FORTE performs poorly, as it does not reproduce the teleconnection patterns linked to the Indian Monsoon. In contrast, the North and equatorial Pacific and North Atlantic are reasonably well reproduced.

The study presents a general overview of the healthcare facility system of the Slovak Republic, especially in a field of the innovation process of the management information system, with a purpose of analysing the consistency and a unity of the system. The data applied in this analysis is collected as a part of the Gesiti research project. This project is developed for mapping out the management of an information system and information technology in healthcare facilities around the whole world. The main goal of the project is to identify the needs and the demands of the healthcare facilities and to create an integrated research report with a focus on a report research roadmap. The information and communication technologies that are applied are partially unsuitable in the healthcare facilities in the Slovak Republic. Information systems are used without exact plans of their future development. This makes it almost impossible to develop them according to the modern needs and to join them with the other systems that are currently used. The big issues also lie in financing these systems and the personnel responsible for them. The outcome of the analysis should create a direction for financial decision making support and for better management of the healthcare facilities, both in the public and the private sector.

Introduction: Oxford Nanopore Technologies (ONT) is a third generation sequencing approach that allows the analysis of individual, full-length nucleic acids. ONT records the alterations of an ionic current flowing across a nano-scaled pore while a DNA or RNA strand is threading through the pore. Basecalling methods are then leveraged to translate the recorded signal back to the nucleic acid sequence. However, basecall generally introduces errors that hinder the process of barcode demultiplexing, a pivotal task in single-cell RNA sequencing that allows for separating the sequenced transcripts on the basis of their cell of origin. Methods: To solve this issue, we present a novel framework, called UNPLEX, designed to tackle the barcode demultiplexing problem by operating directly on the recorded signals. UNPLEX combines two unsupervised machine learning methods: autoencoders and self-organizing maps (SOM). The autoencoders extract compact, latent representations of the recorded signals that are then clustered by the SOM. Results and Discussion: Our results, obtained on two datasets composed of in silico generated ONT-like signals, show that UNPLEX represents a promising starting point for the development of effective tools to cluster the signals corresponding to the same cell., Competing Interests: TL received reimbursement of expenses from ONT to speak at an event. The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2023 Papetti, Spolaor, Nazari, Tirelli, Leonardi, Caprioli, Besozzi, Vlachou, Pelicci, Cazzaniga and Nobile.)