Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

System Identification I

Physics of shock waves and high-temperature hydrodynamic phenomena - Ya.B. Zeldovich and Yu.P. Raizer (translated from the Russian and then edited by Wallace D. Hayes and Ronald F. Probstein); Dover Publications, New York, 2002, 944 pp., $34.

The impact of the Internet of Things (IoT) on the advancement of the healthcare industry is immense. The ushering of the Medicine 4.0 has resulted in an increased effort to develop platforms, both at the hardware level as well as the underlying software level. This vision has led to the development of Healthcare IoT (H-IoT) systems. The basic enabling technologies include the communication systems between the sensing nodes and the processors; and the processing algorithms for generating an output from the data collected by the sensors. However, at present, these enabling technologies are also supported by several new technologies. The use of Artificial Intelligence (AI) has transformed the H-IoT systems at almost every level. The fog/edge paradigm is bringing the computing power close to the deployed network and hence mitigating many challenges in the process. While the big data allows handling an enormous amount of data. Additionally, the Software Defined Networks (SDNs) bring flexibility to the system while the blockchains are finding the most novel use cases in H-IoT systems. The Internet of Nano Things (IoNT) and Tactile Internet (TI) are driving the innovation in the H-IoT applications. This paper delves into the ways these technologies are transforming the H-IoT systems and also identifies the future course for improving the Quality of Service (QoS) using these new technologies.

The Future of Healthcare Internet of Things: A Survey of Emerging Technologies

This is the second part of a large survey paper in which we analyze recent literature on Formal Concept Analysis (FCA) and some closely related disciplines using FCA. We collected 1072 papers published between 2003 and 2011 mentioning terms related to Formal Concept Analysis in the title, abstract and keywords. We developed a knowledge browsing environment to support our literature analysis process. We use the visualization capabilities of FCA to explore the literature, to discover and conceptually represent the main research topics in the FCA community. In this second part, we zoom in on and give an extensive overview of the papers published between 2003 and 2011 which applied FCA-based methods for knowledge discovery and ontology engineering in various application domains. These domains include software mining, web analytics, medicine, biology and chemistry data.

https://publications.hse.ru/mirror/pubs/share/folder/utyhyy55j6/direct/114480266.pdf

Review: Formal concept analysis in knowledge processing: A survey on applications

We provide a generalization of one-sided (crisp-fuzzy) concept lattices, based on Galois connections. Our approach allows analysis of object-attribute models with different structures for truth values of attributes. Moreover, we prove that this method of creating one-sided concept lattices is the most general one, i.e., with respect to the set of admissible formal contexts, it produces all Galois connections between power sets and the products of complete lattices. Some possible applications of this approach are also included.

Generalization of One-Sided Concept Lattices

On equivalence of conceptual scaling and generalized one-sided concept lattices

The emergence of anti-social behaviour in online environments presents a serious issue in today’s society. Automatic detection and identification of such behaviour are becoming increasingly important. Modern machine learning and natural language processing methods can provide effective tools to detect different types of anti-social behaviour from the pieces of text. In this work, we present a comparison of various deep learning models used to identify the toxic comments in the Internet discussions. Our main goal was to explore the effect of the data preparation on the model performance. As we worked with the assumption that the use of traditional pre-processing methods may lead to the loss of characteristic traits, specific for toxic content, we compared several popular deep learning and transformer language models. We aimed to analyze the influence of different pre-processing techniques and text representations including standard TF-IDF, pre-trained word embeddings and also explored currently popular transformer models. Experiments were performed on the dataset from the Kaggle Toxic Comment Classification competition, and the best performing model was compared with the similar approaches using standard metrics used in data analysis.

Comparison of Deep Learning Models and Various Text Pre-Processing Techniques for the Toxic Comments Classification

Spreading of misinformation on the web nowadays represents a serious issue, as their influence on peoples opinions may be significant. Fake news represents a specific type of misinformation. While its detection was mostly being performed manually in the past, automated methods using machine learning and related fields became more critical. On the other hand, deep learning methods became very popular and frequently used methods in the field of data analysis in recent years. The study presented in this paper deals with the detection of fake news from the textual data using deep learning techniques. Our main idea was to train different types of neural network models using both entire texts from the articles and to use just the title text. The models were trained and evaluated on the Fake News dataset obtained from the Kaggle competition.

Deep learning methods for Fake News detection

Formal concept analysis (FCA) is one of the approaches which can be applied in process of conceptual modeling in domain of text documents. FCA can be used for formal analysis of data tables and identification of similar objects - clusters (concepts). Extension of classic FCA (binary table data) is one-sided fuzzy version that works with real values in the object-attribute table (document- term matrix in case of vector representation of textual documents). Computational complexity of creation of concept lattices from large context is considerable. This paper describes one simple approach to creation of simple hierarchy of concepts. Starting set of documents is decomposed to smaller sets of similar documents with the use of clustering algorithm. Then one concept lattice is built upon every cluster using FCA method and these FCA-based models are combined to simple hierarchy of concept lattices using agglomerative clustering algorithm. For our experiments we used GHSOM algorithm for finding of appropriate clusters, then 'upper neighbors' FCA algorithm was used for building of particular concept lattices. Finally, particular FCA models were labeled by some characteristic terms and simple agglomerative algorithm was used for clustering of local models, with the metric based on these characteristic lattices terms. We have used this approach also to extend it for Grid-based solution in which time consuming building of several local models is distributed between grid computing nodes and then it leads to speed-up of computing of final model.

Peter Butka

Papers

Generalization of One-Sided Concept Lattices

On equivalence of conceptual scaling and generalized one-sided concept lattices

Comparison of Deep Learning Models and Various Text Pre-Processing Techniques for the Toxic Comments Classification

Deep learning methods for Fake News detection

One approach to combination of FCA-based local conceptual models for text analysis — grid-based approach