China
Africa
Explore chapters and articles related to this topic
Software Quality Management
Published in Jong S. Lim, Quality Management in Engineering, 2019
Clean code is easy to read, analyze, and manage. For example, in the case of C-language programming, each instruction should be in a new line with a proper indent for easy reading. For example, Figure 10.21 shows an example for a loop routine in C-language—all three programs work, but we know “A” coding is the easiest to read.34
A Comprehensive Artificial Intelligence Based User Intention Assessment Model from Online Reviews and Social Media
Published in Applied Artificial Intelligence, 2022
Archika Sharma, M. Omair Shafiq
In the data preparation block, we clean and prepare the collected reviews by categorizing and tagging part-of-speech for each review with the NLTK library in the Python programming language (NLTK.tag package 2020). Next, we feed the pre-processed data to the feature extraction and selection block, which calculates the pointwise mutual information for the tagged words. It is then used to construct the neighborhoods by assessing word bigrams. Following that, we customize the cost function for the classifiers to be applied for the prediction. We employ the machine learning and deep learning models that utilize overlapping neighborhood construction of words and variant parameters of the cost function. In our earlier work (Sharma and Shafiq 2020), we built an ensemble model by utilizing different machine learning and deep learning techniques with historical data to carry out purchase prediction. This helped us in selecting the machine learning and deep learning models for building the solution in this work.
Quantifying and modelling the game speed outputs of English Championship soccer players
Published in Research in Sports Medicine, 2022
Mark Connor, Dylan Mernagh, Marco Beato
In order to model game-speed data, the protocol previously presented by Delaney et al., 2018 was utilized. Briefly, this involved exporting raw GNSS data at a sampling rate of 10 Hz for each player across all matches. A custom computer program written in the Python programming language (Version 3.6.5, Anaconda Inc, New York, USA) was then used to clean the raw data, removing dead time (half time, extra time) and excluding any match files where a player had less than 60 minutes of data. Moving average calculations were then applied to the GNSS Doppler speed data of each player using 10 different moving average window durations (1, 2, 3, … 10). The maximum value across each of the moving average window durations was then extracted and converted to units of metres per minute (m.min−1) for further statistical analysis (Delaney et al., 2018; Zinoubi et al., 2017).