Values Of Input Data Research Articles

PROBABILISTIC COUNTERFACTUAL CAUSAL MODEL FOR A SINGLE INPUT VARIABLE IN EXPLAINABILITY TASK

The subject of research in this article is the process of constructing explanations in intelligent systems represented as black boxes. The aim is to develop a counterfactual causal model between the values of an input variable and the output of an artificial intelligence system, considering possible alternatives for different input variable values, as well as the probabilities of these alternatives. The goal is to explain the actual outcome of the system's operation to the user, along with potential changes in this outcome according to the user's requirements based on changes in the input variable value. The intelligent system is considered as a "black box." Therefore, this causal relationship is formed using possibility theory, which allows accounting for the uncertainty arising due to the incompleteness of information about changes in the states of the intelligent system in the decision-making process. The tasks involve: structuring the properties of a counterfactual explanation in the form of a causal dependency; formulating the task of building a potential counterfactual causal model for explanation; developing a possible counterfactual causal model. The employed approaches include: the set-theoretic approach, used to describe the components of the explanation construction process in intelligent systems; the logical approach, providing the representation of causal dependencies between input data and the system's decision. The following results were obtained. The structuring of counterfactual causal dependency was executed. A comprehensive task of constructing a counterfactual causal dependency was formulated as a set of subtasks aimed at establishing connections between causes and consequences based on minimizing discrepancies in input data values and deviations in the decisions of the intelligent system under conditions of incomplete information regarding the functioning process of the system. A potential counterfactual causal model for a single input variable was developed. Conclusions. The scientific novelty of the obtained results lies in the proposal of a potential counterfactual causal model for a single input variable. This model defines a set of alternative connections between the values of the input variable and the obtained result based on estimates of the possibility and necessity of using these variables to obtain a decision from the intelligent system. The model enables the formation of a set of dependencies that explain to the user the importance of input data values for achieving an acceptable decision for the user.

Numerical simulations of temperature and stress distribution in thermal barrier coatings in the context of differences in input data values – bond coat and substrate materials

Numerical simulations of temperature and stress distribution in thermal barrier coatings in the context of differences in input data values – bond coat and substrate materials

Design of various operating devices for sorting binary data

The object of research is the process of designing hardware devices for sorting arrays of binary data using the methodology of space-time graphs. The main task that is solved in the work is the development and research of multi-cycle operating devices for sorting binary data in order to choose the optimal structure with predetermined technical characteristics for solving the sorting problem. As an example, the development of different types of structures of multi-cycle operating sorting devices by the method of «even-odd» permutation is shown and their system characteristics are determined. New structures of multi-cycle operating devices have been designed for a given sorting algorithm, and analytical expressions for calculating equipment costs and their performance have been given. A comparative analysis of the hardware and time complexity of the developed structures of devices for sorting binary numbers of various types with known implementations of algorithmic and pipeline operating devices was carried out. As a result, the proposed structures, when sorting large arrays of binary data (N>128), have an order of magnitude less hardware complexity due to sequential execution of the same type of operations. The time complexity of multi-cycle operating devices of combined and sequential types with large values of input data is 2.3 and 3.4 times less than that of known pipeline operating devices. A feature of the research results is the possibility of finding the optimal ratio between the hardware and time characteristics of the resulting structures of sorting devices. Owing to this, the designer will be able to choose the necessary type of device for the implementation of the corresponding task with optimal system characteristics. The field of application of the designed sorting devices is the tasks of digital processing of signals and images. The practical use of the developed sorting devices can be carried out in the form of their synthesis on software integrated logic circuits

Numerical simulations of temperature and stress distribution in thermal barrier coatings in the context of differences in input data values – external ceramic layer

Numerical simulations of temperature and stress distribution in thermal barrier coatings in the context of differences in input data values – external ceramic layer

A A Context-Aware Human Distress Alert System for Safety from Interpersonal Violence Using Smartphone Sensors

Interpersonal violence is one of the causes of death globally. Getting help depends on timely response from responders. Development in personal safety technologies have been improved over the years due to the increase in the use of mobile technologies and the miniaturization of electronic sensors. However, existing technologies for communicating distress usually require active user interventions in alerting emergencies. Hence, this study proposes a system for the automatic detection and alert of distress situations arising from violent attacks through smartphone sensors. A fuzzy logic approach was adopted to classify levels of distress situation using input data values from tri-axial accelerometer, gyroscope, sound and proximity sensors. A prototype of the distress detection and alert process was implemented using Java programming language. The system prototype was implemented as an android based real-time application that detects and alerts distress using values from mobile device sensors. Testing the prototype showed that the system can automatically detect and send alert to responders using smartphone.

Measuring Information System-Based Village Administration Service Performance Using Boundary Value Analysis Techniques

Application development often does not have a significant impact on users, especially various application functions that make it difficult for users to take advantage of the system optimally. System testing plays an important role in an application development. Tests are carried out to ensure that all programs run properly before an application is released. This study discusses the measurement of performance on the administration service website application with the Black Box Testing method. Functional testing is carried out using the Boundary Value Analysis technique. Boundary Value Analysis technique is one of the techniques of Black Box testing that identifies errors from the outside or inside of a system. With this technique, the success of an input data value is tested based on the upper and lower limit values. The result of the measurement of the administrative service application is the optimal system functionality and in accordance with the user's business process needs. The percentage of success rate for fields on the Register Account menu is 91.67% and Login is 75%. Meanwhile, on the Daftar Surat Izin Keramaian menu, it has a success rate of 80%.

Evaluating the failure load of high-rise reinforced concrete walls under fire loading using the yield design approach

The present contribution is addressing the investigation on the failure of high-rise reinforced concrete walls subject to fire loading. In Yang (2018), a 2D plate model has been developed for predicting the deflections and subsequent geometry changes of tall reinforced concrete panels under severe fire exposure. Such a deformed geometry of the wall is a key ingredient to its stability analysis by means of the yield design theory, which is the subject of the present paper. The practical implementation of the approach is based on shell finite elements and a generalized strength criterion accounting for reduced strength capacities of the constitutive materials. For illustrative purpose, numerical simulations based on typical values of input data (geometrical as well as material parameters), are conducted to investigate the sensitivity of the wall stability to the temperature increase on the one hand, and to its geometrical parameters and boundary conditions, on the other hand. One of the main conclusions which can be drawn from the present analysis is that the boundary conditions prescribed along the vertical lateral sides of the wall have a decisive influence on its stability.

Применение квадратичной интерполяции на примере нахождения глубины зоны возможного заражения аварийно химически опасными веществами

Introduction. When calculating the depth and angle of the zone of possible damage by emergency chemically hazardous substances distributed by air masses, the old, simplified methodology set out in the guidance document RD 52.04.253-90 is used. This technique has a number of limitations, which can significantly affect the resulting size of the affected area and the establishment of other consequences of the accident and measures necessary for its elimination. In the latest version of Building Codes and Regulations SNiP 2.01.51-90 dated 11/26/2020: in code of practice SP 165.1325800.2014, this technique is also used. The purpose of the study is to develop a method for determining the depth and angle of the zone of possible damage during the release of an emergency chemically hazardous substance using quadratic interpolation at input data values other than those provided by the methods of the currently used methodology. Methods. The research uses methods of system analysis, linear algebra, analytical geometry, mathematical statistics. Results and their discussion. The conducted research when calculating the depth of the zone of possible damage by emergency chemically hazardous substances by the proposed method showed that quadratic interpolation mainly gives an increase in the depths of the zones of possible damage, while linear approximation with the same data always reduces the size in comparison with the values taken from the reference tables. Conclusions. The proposed method will be especially useful when finding the angular dimensions of the zone of possible damage, since they are selected too inaccurately. In addition, according to the quadratic interpolation data, it is possible to find optimal (maximum and minimum) values of the depth and angle of the zone of possible damage by emergency chemically hazardous substances. The results of this study can also help in the long term when assessing risks in real time and provide support to decision makers in responding to emergencies. Keywords: emergency chemical hazardous substances; forecasting; affected area; quadratic interpolation; linear approximation.

Priority Chronological Time-Period Clustering for Generation and Transmission Expansion Planning Problems With Long-Term Dynamics

The increasing incorporation of renewable generating units into power systems has made it imperative to model variabilities during the resolution of generation and transmission expansion planning problems. This is commonly carried out by considering representative time periods, which are attained using clustering techniques, since the use of all historical data may involve computationally intractable problems. The chronological information concerning the input data should be maintained when representative time periods are used to model inter-temporal constraints. This is the case of long-term storage, which may be critical as regards mitigating the fluctuations related to renewable production. Recent clustering techniques have resolved this drawback at the cost of not ensuring the feasibility of the problem or underestimating extreme values of input data, which may influence investment decisions. This paper proposes a new clustering method that is based on previous techniques, maintains the chronological information regarding the input data throughout the entire time horizon and assigns more priority to the representation of extreme values. Numerical results show that the use of the proposed clustering method involves a reduction in the computational burden, since investment plans closer to the optimal solution are attained while considering less representative time periods than occurs with other methods.

Deep-learning-based surrogate model for fast and accurate simulation in pipeline transport

A new deep-learning-based surrogate model is developed and applied for predicting dynamic temperature, pressure, gas rate, oil rate, and water rate with different boundary conditions in pipeline flow. The surrogate model is based on the multilayer perceptron (MLP), batch normalization and Parametric Rectified Linear Unit techniques. In training, the loss function for data mismatch is considered to optimize the model parameters with means absolute error (MAE). In addition, we also use the dynamic weights, calculated by the input data value, to increase the contribution of smaller inputs and avoid errors caused by large values eating small values in total loss. Finally, the surrogate model is applied to simulate a complex pipeline flow in the eastern part of the South China Sea. We use flow and pressure boundary as the input data in the numerical experiment. A total of 215690 high-fidelity training simulations are performed in the offline stage with commercial software LeadFlow, in which 172552 simulation runs are used for training the surrogate model, which takes about 240 min on an RTX2060 graphics processing unit. Then the trained model is used to provide pipeline flow forecasts under various boundary conduction. As a result, it is consistent with those obtained from the high-fidelity simulations (e.g., the media of relative error for temperature is 0.56%, pressure is 0.79%, the gas rate is 1.02%, and oil rate is 1.85%, and water is 0.80%, respectively). The online computations from our surrogate model, about 0.008 s per run, achieve speedups of over 1,250 relative to the high-fidelity simulations, about 10 s per run. Overall, this model provides reliable and fast predictions of the dynamic flow along the pipeline.

Ефективний оптичний підхід до обробки нечітких даних на основі кольорів та світлофільстрів

Ця робота присвячена створенню ефективних оптичних логічних систем на основі використання світлового випромінювання визначеного кольору безпосередньо як нечіткої змінної — носія логічної інформації та основи побудови логічних рішень шляхом перетворення світлового випромінювання відповідними світловими фільтрами. Оптична обробка кольорової інформації, яка відображає різні значення вхідних даних (розглядається на прикладі експертних оцінок), здійснюється запропонованою структурною побудовою нечітких логічних вентилів (логічного колороїда) та значно спрощується, по відношенню до існуючих систем, за рахунок реалізації на властивостях адитивної та субтрактивної обробки кольорів з використанням достатньо простих світлових фільтрів. Сформовано нечітку базу даних на основі визначення кванта інформації, як відповідний колір, та компоненти оптичної логічної системи за допомогою адитивної та субтрактивної обробки світлового випромінювання відповідних кольорів; розроблено основи синтезу систем логічного висновку та прийняття рішень. В роботі синтезовано узагальнену структурну схему оптичного логічного колороїда як основу створення багаторівневої системи прийняття рішень для подальшого застосування в системах штучного інтелекту. Схеми оптичних логічних колороїдів можуть поєднуватися в послідовно-паралельні ієрархічно організовані схеми, колір використовуваних світлофільтрів може також, крім експертних оцінок, відображати тактильну інформацію систем сенсорів про навколишнє середовище, що необхідно для формування відповідних логічних оцінок або рішень. Використання кольору як носія логічної інформації дозволяє створити швидкодіючі технічні пристрої з продуктивністю, в основі розрахунків якої використовується швидкість світла для формування певного масиву логічних рішень.

Climate change adaptation in pavement design

Since 2011, the change in climatic characteristics has emerged as one of the three most common environmental risks today. Global warming forecasts warn that by 2100, our planet could warm by an average of 3.5 to 7.5 °C. In Europe, over the last 140 years, the average annual air temperature has risen by about 1.5 °C. In Slovakia, it was an increase of 1.7 - 1.8 °C on average. The consequences of these changes in road construction are immediate and intense and require adequate adaptation measures.Long-term measurements of climatic conditions in Slovakia were the basis for assessing changes in average daily air temperatures in individual seasons. With the design of road pavements and calculations of pavement structure models, we have also tested road construction materials - especially asphalt mixtures. The results were used to correct the values of input data, design criteria, as well as in measures to reduce the impact of changes in climatic conditions.The paper focuses on the characterization of the climatic conditions in Slovakia and the changes reflected in the design of the road constructions; also provides some insights into the solution of partial problems in the field of asphalt pavement and cement concrete pavement.

Design of decision model for sensitive crop irrigation system

AbstractAgriculture Industry is highly dependent on environmental and weather conditions. Many times, crops are spoiled because of sudden changes in weather. Therefore, we need a decision model to take care the water requirement of sensitive crops of agriculture industry. The proposed work presents a novel and proficient hybrid model for sensitive crop irrigation system (SCIS). For implementation of the model, brassica crop is taken. The duration and amount of water to be supplied is based upon the weather prediction and soil condition information. The decision model is developed using adaptive neuro‐fuzzy inference system (ANFIS) and artificial neural network (ANN) for brassica crops. In this model, if the input data values are available in range, then ANFIS model would be preferred and if the data sets are available for training, testing and validation then ANN model would be the best choice. The soil moisture, soil status in terms of temperature and leaf wetness are the input and flow control of sprinklers is the out for SCIS. The predicted outputs are analysed to assert the suitability of the proposed approach in the brassica crops. The proposed SCIS achieved an accuracy of 91% and 99% for ANFIS and ANN models respectively.

Quantification of Precipitation and Evapotranspiration Uncertainty in Rainfall-Runoff Modeling

Mountainous watersheds have always been a challenge for modelers due to large variability and insufficient ground observations, which cause forcing data, model structure, and parameter uncertainty. This study employed Differential Evolution Adaptive Metropolis (DREAM) algorithm which utilizes Markov Chain Monte Carlo (MCMC) approach to account for forcing data uncertainty. A conceptual degree day snowmelt model, MIKE 11 NAM (Nedbor Afstromnings Model), was used to simulate snowmelt runoff from Ilgaz basin, with an area of 28.4 km2 area, located in the northern part of Turkey. The mean elevation is around 1700 m and the basin is covered with broadleaf forest and has mainly brown soil with a high water holding capacity. Precipitation and evapotranspiration (ET) values were optimized in combination with model parameters conditioned on observed discharges and corrected values of input data were utilized for calibration and validation. Results showed that the observed precipitation was over-estimated by almost 10%, while evapotranspiration calculated by Penman–Monteith method was underestimated. The mean values of storm and ET multipliers were obtained as 1.14 and 0.84, respectively. When only parameter uncertainty was considered, calibration did not yield Nash–Sutcliffe Efficiency (NSE) greater than 0.64. However, when forcing data uncertainty was incorporated in the DREAM approach, an improved value of NSE (0.84) was obtained. After calibration and treatment of forcing data errors, the model yielded reasonable prediction uncertainty bounds and well-defined posterior distributions of NAM model parameters. Main objectives of the study are to assess the applicability of MIKE 11 NAM model to the selected catchment. In addition, the importance of errors in the input forcing variables to the model is demonstrated.

Способ оценки похожести программ методами машинного обучения

The problem of constructing an algorithm for comparing two executable files is considered. The algorithm is based on the construction of similarity features vector for a given pair of programs. This vector is then used to decide on the similarity or dissimilarity of programs using machine learning methods. Similarity features are built using algorithms of two types: universal and specialized. Universal algorithms do not take into account the format of the input data (values of fuzzy hash functions, values of compression ratios). Specialized algorithms work with executable files and analyze machine code (using disassemblers). A total of 15 features were built: 9 features of the first type and 6 of the second. Based on the constructed training set of similar and dissimilar program pairs, 7 different binary classifiers were trained and tested. To build the training set, coreutils programs were used. The results of the experiments showed high accuracy of models based on random forest and k nearest neighbors. It was also found that the combined use of features of both types can improve the accuracy of classification.

Performance analysis of dynamic optimization algorithms using relative error distance

Quantification of the performance of algorithms that solve dynamic optimization problems (DOPs) is challenging, since the fitness landscape changes over time. Popular performance measures for DOPs do not adequately account for ongoing fitness landscape scale changes, and often yield a confounded view of performance. Similarly, most popular measures do not allow for fair performance comparisons across multiple instances of the same problem type nor across different types of problems, since performance values are not normalized. Many measures also assume normally distributed input data values, while in reality the necessary conditions for data normality are often not satisfied. The majority of measures also fail to capture the notion of performance variance over time. This paper proposes a new performance measure for DOPs, namely the relative error distance. The measure shows how close to optimal an algorithm performs by considering the multi-dimensional distance between the vector comprising the normalized performance scores for specific algorithm iterations of interest, and the theoretical point of best possible performance. The new measure does not assume normally distributed performance data across fitness landscape changes, is resilient against fitness landscape scale changes, better incorporates performance variance across fitness landscape changes into a single scalar value, and allows easier algorithm comparisons using established nonparametric statistical methods.

Assessing the value of a diversified by-product portfolio to allow for increased production flexibility in pulp mills

Abstract This paper presents a model for design optimization of pulp mill steam utility systems subject to variations in energy prices and steam demands. A Scandinavian Kraft pulp mill is used as case study to investigate investment opportunities in lignin extraction and new turbines. The model enables solutions to be identified that are more flexible than the solutions that would have been identified with a corresponding model using, for example, annual average values for key input data. The results from the case study show that lignin extraction has a potential to contribute to flexibility in pulp mill electric power production under certain conditions provided that the mill invests in both lignin extraction and condensing turbine capacity. However, the potential electric power production flexibility will vary over time. In the studied mill, with a capacity increased to around 1.3 million tonnes/a of pulp, it is estimated to vary between 15 and 30 MW. Furthermore, investment in new condensing turbine capacity only seems to be attractive if electricity prices that are considerably higher than the spot prices of recent years are assumed. Such prices may occur if there is a clear value of tradable electricity certificates or if future electricity prices rise significantly.

An open queuing network-based tool for performance estimations in a shuttle-based storage and retrieval system

Recently, growth in e-commerce has resulted in substantially increased investment in robotic technologies in warehouses, especially for storage and retrieval devices. A shuttle-based storage and retrieval system (SBS/RS) is one of the robotic automated storage and retrieval technologies mostly used for a miniload material handling system in e-commerce warehouses. This new technology has been developed as an alternative to the traditional miniload crane-based automated storage and retrieval system. Because it has an autonomous order picker robot in each tier of the racking system, the process rate for this new technology is very high. To evaluate several design options for an SBS/RS warehouse quickly, we have developed analytical models for estimating important performance outputs of these systems. Specifically, this study presents an open queuing network-based software tool that can quickly estimate some important performance metrics for a predefined SBS/RS warehouse design. Once the user enters the required input data values in the tool (e.g., the arrival rate of transactions in the system, warehouse metrics, number of tiers, aisles, and bays, and velocity profiles of devices), the performance metric estimates can be obtained in terms of the mean cycle time of a transaction, the mean energy consumption and energy regeneration per transaction, the mean waiting time of a transaction, the mean number of transactions waiting in a server (lift/shuttle) queue, and the mean utilization of servers. The software tool developed can be downloaded for free from the Web site http//:www.sbsrscalculator.com.

Sensitivity of urban flood simulations to stormwater infrastructure and soil infiltration

Flooding from intense rainfall is a major hazard in many urban areas. One of the major challenges in urban flood simulations is lack of data about the location and properties of stormwater infrastructure and land cover. In this paper, we investigate the sensitivity of urban flood simulations to inputs of stormwater infrastructure and soil characteristics. We use a 2D hydrodynamic model (MIKE URBAN) to simulate flood events on the University of Alabama (UA) campus in Tuscaloosa U.S.A. Infiltration rate, soil moisture, and soil texture were measured in the field. Soil texture was found to be homogeneous across campus (sandy loam) but with a high degree of spatial and temporal variation in infiltration rate and soil moisture. Comparison between different storm event return periods (10, 25, 50, and 100 years) shows that the same flooding hotspots are persistent but with considerable variation in water depth and flood extent. To investigate the sensitivity of the simulations to stormwater infrastructure, simulations without the stormwater infrastructure input were conducted. The results show that stormwater infrastructure decreases flooding volume of RP 10, 25, 50, and 100 by factors of 20, 14, 12, and 8, respectively. This shows that urban flood simulation is highly sensitive to the inclusion of stormwater infrastructure, though with decreasing relative impact for larger events. To investigate the sensitivity of the simulations to soil characteristics, four land-cover simulations (actual, uniform, entirely pervious, entirely impervious) were compared. The results show flood simulation predictions are sensitive to both the value and spatial explicitness of the soil input data. We discuss challenges in urban flood simulation and their potential solutions in the context of emerging frameworks for national and global hyper-resolution flood forecasting and analysis.

Self-Structured Cortical Learning Algorithm by Dynamically Adjusting Columns and Cells

The cortical learning algorithm (CLA) is a type of time-series data prediction algorithm based on the human neocortex. CLA uses multiple columns to represent an input data value at a timestep, and each column has multiple cells to represent the time-series context of the input data. In the conventional CLA, the numbers of columns and cells are user-defined parameters. These parameters depend on the input data, which can be unknown before learning. To avoid the necessity for setting these parameters beforehand, in this work, we propose a self-structured CLA that dynamically adjusts the numbers of columns and cells according to the input data. The experimental results using the time-series test inputs of a sine wave, combined sine wave, and logistic map data demonstrate that the proposed self-structured algorithm can dynamically adjust the numbers of columns and cells depending on the input data. Moreover, the prediction accuracy is higher than those of the conventional long short-term memory and CLAs with various fixed numbers of columns and cells. Furthermore, the experimental results on a multistep prediction of real-world power consumption show that the proposed self-structured CLA achieves a higher prediction accuracy than the conventional long short-term memory.