Search

The Multiclass Classification Performance (MCP) curve is an innovative method to visualize the performance of a classifier for multiclass datasets. On the other hand, the Imbalanced Multiclass Classification Performance (IMCP) curve is a novel approach to visualizing classifier performance on multiclass datasets that exhibit class imbalance, i.e. the proportions of (two or more) class labels are unequal. We have developed an open-source Python package that encompasses the functionality required to calculate and visualize these two novel classification performance measures, along with providing the calculation of the area under the curves. The MCP and IMCP curves offer advantages over the traditional ROC (Receiver Operating Characteristic) curve when dealing with multiclass and imbalanced datasets, respectively. They provide more informative insights into classifier behavior, especially in scenarios involving multiple classes or uneven class distribution.

Abstract The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or F $$_\beta$$ β -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction—an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

A bicluster consists of a subset of rows and columns of a given matrix, whose intersection defines the region (bicluster) of values of precisely defined condition. Through the decades, a variety of biclustering techniques have been successfully developed. Recently, it was proved that many possible patterns defined in two-dimensional data could be found with the application of Boolean reasoning. The provided theorems showed that any existing pattern in the data could be unequivocally encoded as an implicant of a proper Boolean function. Moreover, a prime implicant of that function encoded the inclusion-maximal (non-extendable) pattern. On the other hand, the definition of some two-dimensional patterns may be easily extended to three-dimensional patterns (triclusters) as well as to any number of dimensions (n-clusters). This paper presents a new approach for searching for three- and higher-dimensional simple patterns in continuous data with Boolean reasoning. Providing the definition of the Boolean function for this tasks, it is shown that the similar correspondence—implicants encode patterns, and prime implicants encode inclusion-maximal patterns—has a strong mathematical background: the proofs of appropriate theorems are also presented in this paper.

This paper presents a generic component for Analytic Hierarchy Process (AHP)-based decision support in risk management. The component was originally dedicated to railway transportation issues; however, its generality enabled it to extend its functionality for other domains too. To show the generality of the module and possibility of its application in other domains, an environmental case was run. Its goal was to select methods for planning the post-mining heap revitalization process, especially decision-making focusing on the selection of the most advantageous revitalization option on the basis of the Analytic Hierarchy Process and different, non-financial factors, e.g., social, environmental, technological, political, etc. Taking into account expert responses, the suggested solution was related to energy production.

There are several goals of the two-dimensional data analysis: one may be interested in searching for groups of similar objects (clustering), another one may be focused on searching for some dependencies between a specified one and other variables (classification, regression, associate rules induction), and finally, some may be interested in serching for well-defined patterns in the data called biclusters. It was already proved that there exists a mathematically proven symmetry between some patterns in the matrix and implicants of data-defined Boolean function. This paper provides the new look for a specific pattern search—the pattern named the δ-shifting pattern. The shifting pattern is interesting, as it accounts for constant fluctuations in data, i.e., it captures situations in which all the values in the pattern move up or down for one dimension, maintaining the range amplitude for all the dimensions. Such a behavior is very common in real data, e.g., in the analysis of gene expression data. In such a domain, a subset of genes might go up or down for a subset of patients or experimental conditions, identifying functionally coherent categories. A δ-shifting pattern meets the necessity of shifting pattern induction together with the bias of the real values acquisition where the original shifts may be disturbed with some outer conditions. Experiments with a real dataset show the potential of our approach at finding biclusters with δ-shifting patterns, providing excellent performance. It was possible to find the 12×9 pattern in the 112×9 input data with MSR=0.00653. The experiments also revealed that δ-shifting patterns are quite difficult to be found by some well-known methods of biclustering, as these are not designed to focus on shifting patterns—results comparable due to MSR had much more variability (in terms of δ) than patterns found with Boolean reasoning.

Abstract Background Most plants encounter water stress at one or more different stages of their life cycle. The maintenance of genetic stability is the integral component of desiccation tolerance that defines the storage ability and long-term survival of seeds. Embryonic axes of desiccation-sensitive recalcitrant seeds of Acer pseudoplatnus L. were used to investigate the genotoxic effect of desiccation. Alkaline single-cell gel electrophoresis (comet assay) methodology was optimized and used to provide unique insights into the onset and repair of DNA strand breaks and 8-oxo-7,8-dihydroguanine (8-oxoG) formation during progressive steps of desiccation and rehydration. Results The loss of DNA integrity and impairment of damage repair were significant predictors of the viability of embryonic axes. In contrast to the comet assay, automated electrophoresis failed to detect changes in DNA integrity resulting from desiccation. Notably, no significant correlation was observed between hydroxyl radical (٠OH) production and 8-oxoG formation, although the former is regarded to play a major role in guanine oxidation. Conclusions The high-throughput comet assay represents a sensitive tool for monitoring discrete changes in DNA integrity and assessing the viability status in plant germplasm processed for long-term storage.

Quality of predictive models is a critical factor. Many evaluation measures have been proposed for binary and multi–class datasets. However, less attention has been paid to graphical representation of the classification performance, where the ROC curve is extensively used for binary datasets but there is no standard method accepted by the scientific community for multi–class datasets. In this work, a multi–class classification performance (MCP) curve based on the Hellinger distance between true and prediction probabilities of the classifier is introduced. The MCP curve shows the classification performance, contributes to highlight the low or high confidence on correct predictions, and quantifies the quality by means of the area under the curve.

The liability of Member States for damages caused by the issuance of a judicial decision in breach of EU law has been shaped in the jurisprudence of the CJEU, as a mechanism to ensure effective legal protection of EU citizens. Its primary purpose is to ensure that in a situation where a court of a Member State causes damage to a citizen by violating EU laws by its ruling, the citizen has a legal remedy to obtain compensation for such a violation. Based on the principle of procedural autonomy of the Member States, such claims can be asserted on the grounds of national procedural rules under the substantive legal grounds laid down by the CJEU in its case law. Research conducted by the authors of the article indicates that despite more than 18 years of Poland’s presence in the European Union, it is extremely difficult to find rulings on liability for damages for breach of EU law by Polish courts. It seems that such a state of affairs may be caused by ambiguities and interpretative doubts that arise on the grounds of Polish procedure in the case of claims for damages for breach of EU law by the courts. Both in the doctrine and case law there are far-reaching divergences as to whether the pre-judgment provided for in the Polish Civil Code should apply to claims for breach of EU law, and if so, when it should be applied. These doubts are reflected in the scant judicial case law on the issue in question. It seems that the indicated procedural doubts and lack of clarity as to the proper procedure in pursuing such claims may deter parties from more frequent initiation of proceedings to obtain compensation for breach of EU law by a national courts in the Polish context.

To date, the use of liquid nitrogen (LN) in plant gene banks is relatively limited. Globally, in 2021, approximately 10,000 accessions were cryopreserved, and their explants were derived from in vitro plants. In Europe, out of 500 banks, only 20 use cryogenic temperatures to store plant germplasms. The implementation of seven conservation projects in Poland starting in the 1990s meant that the gene banking system in this country began to gradually develop. Plant gene bank is mainly based on the collection of seeds and makes little use of plant tissues, including those from in vitro culture. From the point of view of systematics, plant material belonging to spermatophytes dominates in Polish gene banks, while spore plants are rarely represented. This review represents the first summary of gene cryobank activities and resources in Poland. It contains a brief overview of the ex situ plant protection programs aimed at the use of LN and presents the characteristics of four existing gene cryobanks in this country. Special attention is devoted to the presentation of studies on the cryopreservation of seeds, as well as of plant tissues, such as embryonic axes and plumules of trees, and fern gametophytes, that make a permanent contribution to gene bank resources.

This Special Issue contains 2 reviews and 17 research papers related to the following topics:Time series forecasting [1,2,3,4,5];Image analysis [6];Medical applications [7,8];Knowledge graph analysis [9,10];Cybersecurity [11,12,13];Traffic analysis [14,15];Agriculture [16];Environmental data analysis [...]

The conservation of the genetic resources of old trees is crucial to their ecological role but is extremely difficult, especially for oak species (Quercus spp.) displaying recalcitrance in seed and vegetative propagation methods. Our study aimed to assess the regenerative potential of Quercus robur trees of different ages (up to 800 years) during micropropagation. We also aimed to determine how in vitro conditions can influence in vitro regeneration responses. Lignified branches collected from 67 selected trees were cultivated ex vitro in culture pots at 25 °C to obtain epicormic shoots (explant sources). The explants were cultivated on an agar medium supplemented with 0.8 mg L−1 6-benzylaminopurine (BAP) for at least 21 months. In a second experiment, two different shoot multiplication conditions (temporary immersion—RITA® bioreactor and agar medium) and two culture medium formulations (Woody Plant Medium and modified Quoirin and Lepoivre medium) were tested. The results showed that the mean length of the epicormic shoots obtained in a pot culture was a function of donor age and was similar among the group of younger trees (ca. 20–200 years), and varied between older trees (ca. 300–800 years). The efficiency of in vitro shoot multiplication strictly depended on the genotype. A sustainable in vitro culture (defined as survival after 6 months) was only possible for half of the tested old donor trees, even when they survived the first month of in vitro growth. A continuous monthly increase in the number of in vitro cultured shoots was reported in younger oaks and in some old oaks. We found a significant effect of the culture system and the macro- and micronutrient composition on in vitro shoot growth. This is the first report demonstrating that the in vitro culture can be successfully applied to the propagation of even 800-year-old pedunculate oak trees.

It seems to be a truism to say that we should pay more and more attention to network traffic safety. Such a goal may be achieved with many different approaches. In this paper, we put our attention on the increase in network traffic safety based on the continuous monitoring of network traffic statistics and detecting possible anomalies in the network traffic description. The developed solution, called the anomaly detection module, is mostly dedicated to public institutions as the additional component of the network security services. Despite the use of well-known anomaly detection methods, the novelty of the module is based on providing an exhaustive strategy of selecting the best combination of models as well as tuning the models in a much faster offline mode. It is worth emphasizing that combined models were able to achieve 100% balanced accuracy level of specific attack detection.

Seeds are the most commonly used source of storage material to preserve the genetic diversity of plants. However, prior to the deposition of seeds in gene banks, several questions need to be addressed. Here, we illustrate the scheme that can be used to ensure that the most optimal conditions are identified to enable the long-term storage of seeds. The main questions that need to be answered pertain to the production of viable seeds by plants, the availability of proper protocols for dormancy alleviation and germination, seed tolerance to desiccation and cold storage at −20 °C. Finally, it is very important to fully understand the capability or lack thereof for seeds or their explants to tolerate cryogenic conditions. The proper storage regimes for orthodox, intermediate and recalcitrant seeds are discussed.

Ex situ preservation of genetic resources is an essential strategy for the conservation of plant biodiversity. In this regard, seed storage is the most convenient and efficient way of preserving germplasm for future plant breeding efforts. A better understanding of the molecular changes that occur during seed desiccation and aging is necessary to improve conservation protocols, as well as real-time methods for monitoring seed quality. In the present study, we assessed changes in the level of genomic 5-methylcytosine (5mC) in seeds of Populus nigra L. by 2D-TLC. Epigenetic changes were characterized in response to several seed storage regimes. Our results demonstrate that P. nigra seeds represent an intermediate type of post-harvest behavior, falling between recalcitrant and orthodox seeds. This was also true for the epigenetic response of P. nigra seeds to external factors. A crucial question is whether aging in seeds is initiated by a decline in the level of 5mC, or if epigenetic changes induce a process that leads to deterioration. In our study, we demonstrate for the first time that 5mC levels decrease during storage and that the decline can be detected before any changes in seed germination are evident. Once P. nigra seeds reached an 8–10% reduction in the level of 5mC, a substantial decrease in germination occurred. The decline in the level of 5mC appears to be a critical parameter underlying the rapid deterioration of intermediate seeds. Thus, the measurement of 5mC can be a fast, real-time method for assessing asymptomatic aging in stored seeds.

Modifications of DNA nucleobases are present in all forms of life. The purpose of these modifications in eukaryotic cells, however, is not always clear. Although the role of 5-methylcytosine (m5C) in epigenetic regulation and the maintenance of stability in plant genomes is becoming better understood, knowledge pertaining to the origin and function of oxidized nucleobases is still scarce. The formation of 5-hydroxymetylcytosine (hm5C) in plant genomes is especially debatable. DNA modifications, functioning as regulatory factors or serving as DNA injury markers, may have an effect on DNA structure and the interaction of genomic DNA with proteins. Thus, these modifications can influence plant development and adaptation to environmental stress. Here, for the first time, the changes in DNA global levels of m5C, hm5C, and 8-oxo-7,8-dihydroguanine (8-oxoG) measured by ELISA have been documented in recalcitrant embryonic axes subjected to desiccation and accelerated aging. We demonstrated that tissue desiccation induces a similar trend in changes in the global level of hm5C and 8-oxoG, which may suggest that they both originate from the activity of reactive oxygen species (ROS). Our study supports the premise that m5C can serve as a marker of plant tissue viability whereas oxidized nucleobases, although indicating a cellular redox state, cannot.

In this paper, the problem of the identification of undesirable events is discussed. Such events can be poorly represented in the historical data, and it is predominantly impossible to learn from past examples. The discussed issue is considered in the work in the context of two use cases in which vibration and temperature measurements collected by wireless sensors are analysed. These use cases include crushers at a coal-fired power plant and gantries in a steelworks converter. The awareness, resulting from the cooperation with industry, of the need for a system that works in cold start conditions and does not flood the machine operator with alarms was the motivation for proposing a new predictive maintenance method. The proposed solution is based on the methods of outlier identification. These methods are applied to the collected data that was transformed into a multidimensional feature vector. The novelty of the proposed solution stems from the creation of a methodology for the reduction of false positive alarms, which was applied to a system identifying undesirable events. This methodology is based on the adaptation of the system to the analysed data, the interaction with the dispatcher, and the use of the XAI (eXplainable Artificial Intelligence) method. The experiments performed on several data sets showed that the proposed method reduced false alarms by 90.25% on average in relation to the performance of the stand-alone outlier detection method. The obtained results allowed for the implementation of the developed method to a system operating in a real industrial facility. The conducted research may be valuable for systems with a cold start problem where frequent alarms can lead to discouragement and disregard for the system by the user.