Input Test Data Research Articles

A novel approach for the fractional SLS material model experimental identification

A multi-step, iterative technique for the local non-parametric identification of the standard linear solid (SLS) material model employing fractional order time differential operators is presented. Test input data consists of a set of identified material complex modulus values estimated at different frequency values, obtained from input–output experimental measurements made on a material specimen by means of forced harmonic excitation and from experimental measurements made on the same specimen in quasi-static relaxation conditions. The proposed technique is mainly based on an algebraic procedure leading to the solution of an overdetermined system of linear equations, in order to get the optimal value of the model unknown parameters. The procedure is non-parametric, since the SLS model order is initially unknown. The optimal model size can be found by evaluating the stability properties of the solution associated to any model size and by automatically discarding computational, non-physical contributions. The identification procedure is first validated by means of numerically simulated test data from within known model examples, and then it is applied to some experimentally obtained test data associated to different materials.

Problems on the theme "Maximum non-decreasing subsequence"

In the article, using the example of solving few problems, the methodology for studying the theme "Maximum non-decreasing subsequence" is illustrated in preparing schoolchildren for Olympiads in informatics. The study is based on the sequential solution of increasingly complex problems. For each problem, the following materials are given: the formulation of the problem, the idea of a solution, the solution in the Pascal programming language. Distance learning system (http://dl.gsu.by) is the technical base for teaching. The system allows to offer for a student a formulation of the problem; to submit the solution for review; to get a verdict from the system — a correct or incorrect solution; for incorrect solution, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, figure out what the error is in his program, correct it and send the solution again. In addition, for each problem there is a link on it to the topic in the forum at site, where you can ask a question on solving this problem and / or read the answer if the questions have already been asked before.

Research on Indoor Wireless Positioning Method based on Center-of-mass Algorithm

Indoor mobile positioning is widely used in shopping malls, energy saving in buildings, medical care and emergency rescue. Range-free algorithms typically use the connectivity of a wireless sensor network system to estimate the location of target nodes, typically through Dv-hop, the prime method, ap-proximate point-in-triangulation test, or APIT for short. -free algorithms can be obtained by changing the distribution density of reference nodes or by changing the blind node communication radius to obtain higher accuracy. Due to constraints such as complex indoor environments, current indoor positioning methods are often less accurate and more expensive. To address these issues, this paper improves on the traditional center-of-mass algorithm by using a six-point center-of-mass algorithm for indoor positioning to further improve the accuracy of the indoor positioning algorithm. To this end, the following work is accomplished in this paper: 1. introduced the algorithms currently used for indoor positioning and their shortcomings, laying the theoretical foundation for the improved approach proposed in the following paper. 2. introduced the basic working principle of the center-of-mass algorithm and proposed an improved system using the six-point center-of-mass algorithm. 3. established the best possible model through experiments, then input test data and evaluated it based on expert judgement. The experimental results show that the model proposed in this study has excellent accuracy in indoor wireless positioning.

Artificial Intelligence-Driven Interactive Learning Methods for Enhancing Art and Design Education in Higher Institutions

ABSTRACT To address the problem of the classroom practice teaching of art and design, this paper proposes an interactive learning method in universities, followed by the use of AI technology to evaluate the quality of art and design teaching. The study aims to achieve the following objectives: 1) To introduce the current research status of art and design and interactive teaching methods used in other countries; 2) To discuss the essential ideas and mechanics of Back Propagation Neural Networks (BPNN) and other standard teaching approaches based on interactive learning; and 3) To input test data into the trained model and compare the obtained results with the evaluation results of experts. The findings of this study indicate that the model used to evaluate art and design instruction is accurate. The proposed interactive learning method is beneficial for art and design majors as it allows them to improve their practical skills and learn more engagingly and effectively. The use of AI technology for evaluation purposes can also improve the quality of art and design education in universities.

Speeding up recursive solutions using memoization

In the article, using the example of solving two problems, the methodology for studying the theme "Speeding up recursive solutions using memoization" is illustrated in preparing schoolchildren for Olympiads in informatics. The study is based on the sequential solution of increasingly complex problems. For each problem the following materials are given: the formulation of the problem, the idea of a solution with a proposal to come up with an implementation on their own, the solution in the Pascal programming language. Distance learning system (http://dl.gsu.by) is the effective technical base for teaching. The system allows to offer for a student a formulation of the problem; to submit the solution for review; to get a verdict from the system — a correct or incorrect solution; for incorrect solution, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, figure out what the error is in his program, correct and send the solution again. In addition, for each problem there is a link on it to the topic in the forum at site, where you can ask a question onsolving this problem and / or read the answer if the questions have already been asked before.

Deep Fake Video Detection Using Transfer Learning Approach.

The usage of the internet as a fast medium for spreading fake news reinforces the requirement of computational utensils in order to fight for it. Fake videos also called deep fakes that create great intimidation in society in an assortment of social and political behaviour. It can also be utilized for malevolent intentions. Owing to the availability of deep fake generation algorithms at cheap computation power in cloud platforms, realistic fake videos or images are created. However, it is more critical to detect fake content because of the increased complexity of leveraging various approaches to smudge the tampering. Therefore, this work proposes a novel framework to detect fake videos through the utilization of transfer learning in autoencoders and a hybrid model of convolutional neural networks (CNN) and Recurrent neural networks (RNN). Unseen test input data are investigated to check the generalizability of the model. Also, the effect of residual image input on accuracy of the model is analyzed. Results are presented for both, with and without transfer learning to validate the effectiveness of transfer learning.

Автоматизація процесу ідентифікації динамічних сигналів тензометричних систем з використанням згорткових нейронних мереж

Purpose. Based on empirical data obtained from the system of weighing on single-platform railway scales in motion and numerical methods, create software to generate an array of input data to the wrapped neural network. Using the Python programming language, build a model of a wrapped neural network that will allow you to recognize the type of object (auto-coupling, cart) that has passed through the strain gauge platform. Generate test data of different quality, with noise overlay, and test the recognition quality of the obtained model on different test input data. Research methods. The Python programming language and keras library were used to build plot diagrams of objects through the weighing platform, create a model of a convolutional neural network and generate test plots with noise overlay. Results. Empirical data from the railway strain gauge system were approximated for all types of moving objects used by the enterprise using the algorithm of approximation to empirical data by the Heaviside function. Software for data generation based on the obtained approximation equations is developed. Using a noise generator, we managed to create a dataset for learning and testing a convolutional neural network with different levels of input signal quality. A convolutional neural network has been built and trained, the test of which shows a high level of recognition of test objects, even when simulating an incorrectly configured weighing platform. Scientific novelty. The novelty is a new method of processing dynamic signals for tensometric systems based on machine learning, which with minimal error can recognize the types of objects that have passed through the weighing system. This used algorithm for processing dynamic signals is universal and can be so in many dynamic systems. Practical meaning. The method presented in the article is a key to building an intelligent identification system for evaluating wagons in dynamics. This system allows you to increase the speed of weighing cars and reduce errors in the system as a whole.

Padding Of LFSR Seeds with Low Transition Bits for Reduced Input Test Data Volume

Padding Of LFSR Seeds with Low Transition Bits for Reduced Input Test Data Volume

Recursive solving of the Problems using the "Divide & conquer" method

The methodology for studying the theme "Recursive solving of the problem using the "divide & conquer" method" in preparing schoolchildren for Olympiads in informatics is illustrated in the article by solving the "Head on shoulders" problem. The solution of this problem includes several algorithms (subtasks) considered sequentially, namely: merge sort, counting the number of inversions in a permutation, the number of pairs of intersecting segments. The study of the method is based on the sequential solution of these subtasks. For each subtask, the following materials are given: the formulation of the subtask, the idea of a solution with a proposal to come up with an implementation on their own, the solution in the Pascal programming language. Distance learning system DL.GSU. BY is the effective technical base for teaching. The system allows to offer for a student a formulation of the task; to submit the solution for review; to get a verdict from the system — a correct or incorrect solution; for incorrect solution, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, fgure out what the error is in his program, correct and send the solution again.

Fingerprint Recognition Based on Deep Learning Pre-Train with Our Best CNN Model for Person Identification

In this article, we use pre-train VGG16, VGG19, and ResNet50 with ImageNet wights and our best CNN model to identify human fingerprint patterns. The system including pre-processing phase where the input fingerprint images first technique apply cropping and normalize for unwanted part remove of fingerprint images and normalize its dimension, second Image Enhancement for removing noise in to ridgelines, and last Canny Edge Detection technique for adjustment to smooth image with Gaussian to remove noise. Then apply one by one model on KVKR fingerprint dataset. Our best CNN model has automatically extracted features and RMSprop optimizer use for classification this features. This study performing experimental work of each pre-processed dataset and testing these three models with different dataset size of input train, test, and validation data. The VGG16 model got a better recognition accuracy than VGG19 and ResNet50 models.

스마트팜 적용 피복재의 시험을 통한 성능평가 및 냉방부하 분석

The thermal performance database of the covering material which can be used as input data for the smart farm cooling load simulation performance evaluation was analyzed through the test evaluation. Methods: The solar heat gain coefficient of the covering materials (PE, PMMA, PC double layer, woven film) was compared and analyzed through the Korean standard test method and input data was derived. Based on the thermal input data, the cooling load simulation of smart farm was conducted and the simulation performance evaluation of each case was performed to analyze how the indoor cooling load changes by covering materials. Results: The cooling load of the PC double layer was the lowest at 424 W/㎡, and the PE film was the highest at 559 W/㎡. The coefficient of heat transmission was 3.7 W/㎡ ·K~6.7 W/㎡ ·K for each covering materials, and the solar heat gain coefficient was evaluated as 54%~90% visible transmittance was 50%~88%. The cooling load of the PC double layer and PE film showed a difference of 135 W/m2(24%), indicating that the selection of the coating material greatly affects the cooling load. The cooling load was reduced by 25.3% when the cooling setpoint temperature was controlled, and the cooling load was reduced by 35.8% when the internal shading rate was applied by 60%.

Solving game problems using recursion

The article describes the methodology to game problems of Olympiads in informatics using recursive numbers generation. The study is based on the sequential solution of increasingly complex tasks. For each task, the following materials are given: the condition of the task, the idea of the solution with a proposal to come up with an independent implementation, the solution in the Pascal programming language. Distance learning system DL.GSU.BY is the effective technical base for teaching. It allows offer the student a condition of the task; send the solution for review; get a verdict from the system — a correct or incorrect solution; for incorrect solutions, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, figure out what the error is in his program, correct and send the solution again. In addition, for each problem there is a link on it to the topic in the forum at site, where you can ask a question on solving this problem and / or read the answer if the questions have already been asked before.

Dynamic Forecasting Algorithm of Inbound Ice and Snow Tourism in China Based on Improved Deep Confidence Network

Ice and snow-based tourism is getting popular around the world and it is one of the major sources of revenue for a region with required facilities. According to a report by China Daily, China was expected to witness 230 million tourist visits in 2020-2021 with a total revenue generation surpassing 390 billion yuan. In order to promote the ice and snow tourism, proper arrangements such as accommodation, transport facility, and energy provision for heating and food need to be arranged as per the demand of the visitors at a certain period of time. A tourist prediction system can help in this regard for good estimation but considering the problems of traditional ice and snow tourism systems, specifically the prediction accuracy and long forecasting time, a dynamic forecasting algorithm for ice and snow inbound tourism based on an improved deep confidence network is proposed. The system analyzes the relationship between the demand for ice and snow inbound tourism and the level of national economic development, people’s living standards, demographic characteristics, traffic conditions, and tourism supply capacity. It then takes the influencing factors of ice and snow inbound tourism demand as sample data and arranges the sample data sequence. The inbound tourism demand dynamic prediction model uses an improved deep confidence network to learn and train the prediction model, input test data into the trained model, and output the dynamic prediction value of ice and snow inbound tourism demand in the output layer to obtain the prediction result. The simulation results show that the proposed algorithm has improved accuracy in predicting the demand of inbound tourism for ice and snow, whereas the forecasting time is reduced.

An Approach for Robust System Testing the Event Data Recorder in the Context of a Passive Safety System

As long as road accidents happen, passive safety systems like the airbag control unit are an essential part of the whole automotive safety system. Within the airbag control unit, the event data recorder (EDR) is an integrated function. Recent developments in legislation show that an increasing number of EDR-related regulations are being introduced. They are mainly focusing on data recording, crash-data retrieval, and some of them define testing aspects. In the system testing of an airbag control unit with a focus on the event data recorder, the question arises of how to deal with the fact that real-world crash events are not “straightforward” but arbitrary and do not follow any rules and restrictions. The purpose of this work is to develop a robust test approach to these conditions—giving a tester the possibility to extend the test depth considering the common test design techniques and testing principles. The applied methodology is the use of optimization algorithms in an automated test environment. With this, the tester can steer the test execution in a predefined way with minimal interaction. The application of the developed test method automatically creates a set of test data which fulfill the predefined conditions by the user. The generated results show that a high number of test data are created at and close to the target condition. Consequently, this test approach provides an extension to the common test design techniques with regard to how test input data can be created, and especially how automated test data creation and test execution can be realized.

Tracing CVE Vulnerability Information to CAPEC Attack Patterns Using Natural Language Processing Techniques

For effective vulnerability management, vulnerability and attack information must be collected quickly and efficiently. A security knowledge repository can collect such information. The Common Vulnerabilities and Exposures (CVE) provides known vulnerabilities of products, while the Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of common attributes and approaches employed by adversaries to exploit known weaknesses. Due to the fact that the information in these two repositories are not linked, identifying related CAPEC attack information from CVE vulnerability information is challenging. Currently, the related CAPEC-ID can be traced from the CVE-ID using Common Weakness Enumeration (CWE) in some but not all cases. Here, we propose a method to automatically trace the related CAPEC-IDs from CVE-ID using three similarity measures: TF–IDF, Universal Sentence Encoder (USE), and Sentence-BERT (SBERT). We prepared and used 58 CVE-IDs as test input data. Then, we tested whether we could trace CAPEC-IDs related to each of the 58 CVE-IDs. Additionally, we experimentally confirm that TF–IDF is the best similarity measure, as it traced 48 of the 58 CVE-IDs to the related CAPEC-ID.

Dimensionality reduction to maximize prediction generalization capability

Generalization of time series prediction remains an important open issue in machine learning, wherein earlier methods have either large generalization error or local minima. We develop an analytically solvable, unsupervised learning scheme that extracts the most informative components for predicting future inputs, termed predictive principal component analysis (PredPCA). Our scheme can effectively remove unpredictable noise and minimize test prediction error through convex optimization. Mathematical analyses demonstrate that, provided with sufficient training samples and sufficiently high-dimensional observations, PredPCA can asymptotically identify hidden states, system parameters, and dimensionalities of canonical nonlinear generative processes, with a global convergence guarantee. We demonstrate the performance of PredPCA using sequential visual inputs comprising hand-digits, rotating 3D objects, and natural scenes. It reliably estimates distinct hidden states and predicts future outcomes of previously unseen test input data, based exclusively on noisy observations. The simple architecture and low computational cost of PredPCA are highly desirable for neuromorphic hardware.

Solution of tasks using recursive numbers generation

The article describes the methodology to solve tasks of Olympiads in informatics using recursive numbers generation. The study is based on the sequential solution of increasingly complex tasks. For each task, the following materials are given: the condition of the task, the idea of the solution with a proposal to come up with an independent implementation, the solution in the Pascal programming language. Distance learning system DL.GSU.BY is the effective technical base for teaching. It allows offer the student a condition of the task; send the solution for review; get a verdict from the system — a correct or incorrect solution; for incorrect solutions, the number of the test on which the solution did not pass is indicated. A student can take a test (input and output data), on which his solution did not pass, figure out what the error is in his program, correct and send the solution again. In addition, for each task there is a link on it to the topic in the forum, where you can ask a question on solving this problem and / or read the answer if the questions have already been asked before.

Quantifying spatial accessibility of general practitioners by applying a modified huff three-step floating catchment area (MH3SFCA) method

BackgroundIt is necessary to ensure sufficient healthcare. The use of current, precise and realistic methods to model spatial accessibility to healthcare and thus improved decision-making is helping this process. Generally, these methods—which include the family of floating catchment area (FCA) methods—incorporate a number of criteria that address topics like access, efficiency, budget, equity and the overall system utilization. How can we measure spatial accessibility? This paper investigates a sophisticated approach for quantifying the spatial accessibility of general practitioners. (GPs). Our objective is the investigation and application of a spatial accessibility index by an improved Huff three-step floating catchment area (MH3SFCA) method.MethodsWe modify and implement the huff model three-step floating catchment area (MH3SFCA) method and exemplary calculation of the spatial accessibility indices for the test study area. The method is extended to incorporate a more realistic way to model the distance decay effect. To that end, instead of a binary approach, a continuous approach is employed. Therefore, each distance between a healthcare site and the population is incorporated individually. The study area includes Swabia and the city of Augsburg, Germany. The data for analysis is obtained from following data sources: (1) Acxiom Deutschland GmbH (2020) provided a test dataset for the locations of general practitioners (GPs); (2) OpenStreetMap (OSM) data is utilized for road networks; and (3) the Statistische Ämter des Bundes und der Länder (German official census 2011) provided a population distribution dataset stemming from the 2011 Census.ResultsThe spatial accessibility indices are distributed in an inhomogeneous as well as polycentric pattern for the general practitioners (GPs). Differences in spatial accessibility are found mainly between urban and rural areas. The transitions from lower to higher values of accessibility or vice versa in general are smooth rather than abrupt. The results indicate that the MH3SFCA method is suited for comparing the spatial accessibility of GPs in different regions. The results of the MH3SFCA method can be used to indicate over- and undersupplied areas. However, the absolute values of the indices do not inherently define accessibility to be too low or too high. Instead, the indices compare the spatial relationships between each supply and demand location. As a result, the higher the value of the accessibility indices, the higher the opportunities for the respective population locations. The result for the study area are exemplary as the test input data has a high uncertainty. Depending on the objective, it might be necessary to further analyze the results of the method.ConclusionsThe application of the MH3SFCA method on small-scale data can provide an overview of accessibility for the whole study area. As many factors have to be taken into account, the outcomes are too complex for a direct and clear interpretation of why indices are low or high. The MH3SFCA method can be used to detect differences in accessibility on a small scale. In order to effectively detect over- or undersupply, further analysis must be conducted and/or different (legal) constraints must be applied. The methodology requires input data of high quality.

Design and Implementation of Computer Based Test (CBT) in vocational education

This research is motivated by an analysis of the needs of the examination system that still uses conventional methods that require considerable time, cost, and effort and have not been able to synergize with technological developments. Research on the development of Computer Based Test (CBT) Models Based on the web aims to develop a CBT model that can overcome the problems found in conventional tests. This type of research is development research (R & D) with software development procedures using the waterfall model. The stages of development consist of the needs analysis phase, the design stage, the implementation phase, and the testing phase. Research respondents were students of the Information Systems study program. The results of this study were obtained online test kits to help the process of evaluating student learning outcomes with features: input test data, display an analysis of the completeness of the report, and print reports made for the completion of the learning assessment. By using a database system, this online exam makes it easier for the exam system to display questions and assessments, making it easier for users to use it and for administrators to manage questions.

An Ontology-Based Approach to Automated Test Case Generation

Software testing is as old as software itself. However, the techniques, tools, and processes used by researchers to ensure product quality are constantly evolving. Application of knowledge management technologies in automated test case generation is one of them. This paper addressed the issue of ontology-based automated test case generation in the case of black box testing. In this context, several challenges are present in existing literature. The prime challenges among are (1) major approaches are confined to a specific domain, (2) least consideration about modified domain knowledge, (3) lack of methodology for auto-identification of pre-conditions and different combinations among test input data and (4) poor requirements and domain coverage. The proposed methodology, in this paper, is aimed to resolve these issues by devising a rule-based reasoner that can auto generate the test cases. The proposed method takes an ontology-based requirements specification as an input. The novelty of the proposed method is the specification of domain independent inference rules based on which the devised reasoner can generate test cases for different domains and systems automatically. This contribution of the proposed work facilitates in improving both user’s requirements coverage and domain coverage. The devised reasoned, in this paper, is implemented in Apache Jena (Apache Jena, https://jena.apache.org ., Accessed 2020/09/04). In addition, the usability of the proposed work is illustrated using a suitable case study.