Method for forecasting the level of software quality based on quality attributes

Hovorushchenko, Tetiana; Medzatyi, Dmytro; Voichur, Yurii; Lebiga, Mykyta

doi:10.3233/jifs-222394

Cited by 3 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Time series forecasting is an important tool in many businesses, ranging from more efficient resource allocation for web traffic, electricity demand [1], mortality rates [2], biomedical data [3], predicting patient needs for staffing requirements, to forecasting a company's product sales [4]. One specific use case, known as "cold start" forecasting, involves making predictions for time series without any historical data, such as a new product just released into the retail market.…”

Section: Introductionmentioning

confidence: 99%

Time Series Forecasting Model for Solving Cold Start Problem via Temporal Fusion Transformer

YEMETS

2024

CSIT

View full text Add to dashboard Cite

Time series forecasting is an important tool in many businesses. It can range from efficiently allocating resources for web traffic, predicting patient needs for staffing requirements, to forecasting a company's product sales. A particular use case, known as "cold start" forecasting, involves making predictions for time series that have little or no historical data, like a new product just entering the retail market. The key assumption of cold start forecasting is that products with similar characteristics should have similar time series trajectories. In such scenarios, traditional forecasting models that heavily rely on past observations may face challenges, necessitating the development of innovative approaches that can effectively make predictions in the absence of a substantial historical dataset. In this paper, Temporal fusion transformer neural network architecture was applied for solving cold start time series forecasting task. Modeling of the method was based on the use of a dataset contained in an open repository. After the preprocessing procedures, the dataset has about 370 time series, each of which has different length of series and has one categorical feature. Categorical feature have only 4 types of different values. For model training was performed to search for optimal hyperparameters across such parameters as: number of attention heads, learning rate, dropout percentage and hidden size.Model performed pretty well on this task. For model comparison were chosen metrics: MAE, RMSE, SMAPE. As can be seen from comparison with such popular models as DeepAR and LSTM, the proposed approach demonstrated the smallest forecasting error. Only one downside is that it can have more problems with anomalies in time series than DeepAR. But at the same time still provide interpretability of results.

show abstract

Section: Introductionmentioning

confidence: 99%

Time Series Forecasting Model for Solving Cold Start Problem via Temporal Fusion Transformer

YEMETS

2024

CSIT

View full text Add to dashboard Cite

show abstract

“…This is one of the research gaps. Moreover, the presence of numerical values of individual quality attributes allows using software quality prediction methods, as shown in Hovorushchenko et al [10]. Traditional testing approaches are manual testing [11] and automated unit testing [12].…”

Section: Introductionmentioning

confidence: 99%

Software Quality Assessment Technique for the Autonomous Power Plants Automated Control Systems

Al-suod,

Ushkarenko,

Dorohan

et al. 2023

JESA

View full text Add to dashboard Cite

The paper proposes further development of formal method for obtaining the values of software quality attributes and assessing the quality of software used for controlling and parameters monitoring of autonomous electric power systems. For this purpose, dynamic software testing was used with the involvement of a group of experts. The results of the conducted expert assessment were used as initial data. The attributes of software quality indicators, such as functionality, practicality, maintainability, reliability, were calculated using the method of summarizing and grouping the results of statistical observation that allowed to check the software compliance with quality standards. Additional weighting coefficients that describe the importance of individual software quality attributes were introduced, and additive convolution is used to calculate the values of various software quality indicators. Minimax criterion was used to find the best solution that maximizes the quality of the software and minimizes possible losses due to errors. The technique proposed in the paper makes it possible to obtain quantitative assessments of software quality based on statistical processing of testing results and expert assessments. This allows to select specific software characteristics for improvement without affecting others, to predict software failureless time and to minimize the subjective factor during testing.

show abstract

Research on AI music creation based on neural network artificial intelligence technology

2024

AIP Conference Proceedings

View full text Add to dashboard Cite

Method for forecasting the level of software quality based on quality attributes

Cited by 3 publications

References 21 publications

Time Series Forecasting Model for Solving Cold Start Problem via Temporal Fusion Transformer

Time Series Forecasting Model for Solving Cold Start Problem via Temporal Fusion Transformer

Software Quality Assessment Technique for the Autonomous Power Plants Automated Control Systems

Research on AI music creation based on neural network artificial intelligence technology

Contact Info

Product

Resources

About