An Approach to Risk Assessment and Threat Prediction for Complex Object Security Based on a Predicative Self-Configuring Neural System

We identified a set of methods for solving risk assessment problems by forecasting an incident of complex object security based on incident monitoring. The solving problem approach includes the following steps: building and training a classification model using the C4.5 algorithm, a decision tree creation, risk assessment system development, and incident prediction. The last system is a predicative self-configuring neural system that includes a SCNN (self-configuring neural network), an RNN (recurrent neural network), and a predicative model that allows for determining the risk and forecasting the probability of an incident for an object. We proposed and developed: a mathematical model of a neural system; a SCNN architecture, where, for the first time, the fundamental problem of teaching a perceptron SCNN was solved without a teacher by adapting thresholds of activation functions of RNN neurons and a special learning algorithm; and a predicative model that includes a fuzzy output system with a membership function of current incidents of the considered object, which belongs to three fuzzy sets, namely “low risk”, “medium risk”, and “high risk”. For the first time, we gave the definition of the base class of an object’s prediction and SCNN, and the fundamental problem of teaching a perceptron SCNN was solved without a teacher. We propose an approach to neural system implementation for multiple incidents of complex object security. The results of experimental studies of the forecasting error at the level of 2.41% were obtained.

Speech, Language and Cognitive Profile of Mild Cognitive Impairment: A single Case Study

Heterogeneity of symptoms within and among mild cognitive impairment individuals often makes it challenging to document case reports clinically. Additionally, data on the Indian population is also limited. Therefore, our study includes a case study of a 56-year-old male with mild cognitive impairment from our Institute. A patient had symptoms of mild cognitive impairment following a stroke that occurred 23 years back (vascular in origin). Both formal and informal assessments were carried out. Formal testing was done using the Montreal Cognitive Assessment. On assessment of memory, mild deficits in working memory, episodic memory, and procedural memory were noticed. Attention span and Word-finding difficulties with reduced use of words were observed in language assessment. Problems in reasoning, problem-solving, and decision-making skills, indicating deficits in executive functioning were evident. Linguistic deficits presenting secondary to cognitive deficits in our client could have led to communication breakdowns in speech, affecting his overall quality of life.

Classification and action rules in identification and self-care assessment problems

BACKGROUND: Disability, especially in children, is a very important and current problem. Lack of proper diagnosis and care increases the difficulty for children to adapt to disabilities. Disabled children have many problems with basic activities of daily living. Therefore, it is very important to support diagnosticians and physiotherapists in recognizing self-care problems in children. OBJECTIVE: The aim of this paper is to extract classification and action rules, useful for those who work with children with disabilities. METHODS: First, features and their impact on the accuracy of classification are determined. Then, two models are built: one with all features and one with selected ones. For these models the classification rules are extracted. Finally, action rules are mined and the next step in treatment process is predicted. RESULTS: Seventeen features with the greatest impact on classifying a child into a particular group of self-care problems were identified. Based on the implemented algorithms, decision and action rules were obtained. CONCLUSIONS: The obtained model, selected attributes and extracted classification and action rules can support the work of therapists and direct their work to those areas of disability where even a minimal reduction of features would be of great benefit to the children.

Intelligent Recognition of Safety Risk in Metro Engineering Construction Based on BP Neural Network

With the rapid development of urban economy, the development of urban rail transit is becoming more and more rapid. As an energy-saving, land-saving, and environment-friendly green travel mode, the subway provides realistic and feasible solutions to the increasingly prominent traffic environment and other urban diseases in our country and brings a booming development in the subway construction industry with efforts to promote and build in many large cities. For a large number of subway constructions, it is particularly important to judge the construction safety status in time during the entire safety management process. Regularly conducting safety risk assessments on subway construction status can accurately predict and judge the types of accidents that occur. In order to solve the current safety risk assessment problems in the process of subway construction in our country, this paper is based on the BP neural network to intelligently identify the safety risks of subway construction, choosing from three aspects: human factors, management factors, and risk factors. We evaluate the construction safety of subway projects under construction through the model, predict the types of accidents that may occur, so that the construction unit can take corresponding preventive and improvement measures, improve the relevant safety technology of subway construction in a targeted manner, and propose corresponding reductions. We provide suggestions and measures for risk probability, to ensure that the construction unit discovers the danger in time and takes safety measures. The rectification measures provided theoretical basis and guidance.

Generalized Read-Across prediction using genra-py

Motivation Generalized Read-Across (GenRA) is a data-driven approach to estimate physico-chemical, biological or eco-toxicological properties of chemicals by inference from analogues. GenRA attempts to mimic a human expert’s manual read-across reasoning for filling data gaps about new chemicals from known chemicals with an interpretable and automated approach based on nearest-neighbors. A key objective of GenRA is to systematically explore different choices of input data selection and neighborhood definition to objectively evaluate predictive performance of automated read-across estimates of chemical properties. Results We have implemented genra-py as a python package that can be freely used for chemical safety analysis and risk assessment applications. Automated read-across prediction in genra-py conforms to the scikit-learn machine learning library's estimator design pattern, making it easy to use and integrate in computational pipelines. We demonstrate the data-driven application of genra-py to address two key human health risk assessment problems namely: hazard identification and point of departure estimation. Availability and implementation The package is available from github.com/i-shah/genra-py.

NEW PROBLEMS AND APPROACHES TO THE EVALUATION OF LEARNING OUTCOMES BY COMBINING TRADITIONAL AND DISTANCE MODES OF WORK IN SCHOOL GEOGRAPHY

Цель исследования - разработка методических рекомендаций для оценивания результатов обучения в режиме «онлайн-офлайн» (на примере школьной географии). Новизна исследования заключается в выявлении новых проблем оценивания при активном использовании дистанционных и традиционных форм обучения. The purpose of the study is to develop guidelines for assessing learning outcomes online-offline (using the example of school geography). The novelty of the research lies in the identification of new assessment problems with the active use of distance and traditional forms of education.