JOSS: Update paper based on #25

Fixed typo on l.40: studyng -> studying
Use The abbreviation PdM
Add c iting for scikit-learn, tensorflow

paper/paper.bib

@@ -121,4 +121,64 @@ @article{CHEN2022104969
 author = {Yongyi Chen and Dan Zhang and Wen-an Zhang},
 keywords = {Rolling bearing, Remaining useful life estimation, Deep learning, Long-term recurrent convolutional network, Attentional mechanism},
 abstract = {Rolling bearings are important components of industrial rotating machinery and equipment. The prediction of the remaining useful life (RUL) of rolling bearings is of great significance for improving the safety of the machine, reducing the economic and property losses caused by the failure of the bearings. However, for the task of predicting the RUL of rolling bearings, the information of the past time and the future time are as important as the information of the current time. In order to make better use of the extracted features for RUL prediction of rolling bearings, this paper has proposed a novel deep learning framework of multi-scale long-term recurrent convolutional network with wide first layer kernels and residual shrinkage building unit (MSWR-LRCN). The major difference from the previous deep neural network is that our new network organically combines the attention mechanism with multi-scale feature fusion strategy, and improves the anti-noise ability of the entire network. In addition, moving average (MA) method and a polynomial fitting model are also used, which help predict the RUL of rolling bearings effectively. The results show that this method has improved the prediction accuracy compared with the existing methods.}
+}
+
+@article{scikit-learn,
+ title={Scikit-learn: Machine Learning in {P}ython},
+ author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
+         and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
+         and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
+         Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
+ journal={Journal of Machine Learning Research},
+ volume={12},
+ pages={2825--2830},
+ year={2011}
+}
+
+@misc{tensorflow2015-whitepaper,
+title={ {TensorFlow}: Large-Scale Machine Learning on Heterogeneous Systems},
+url={https://www.tensorflow.org/},
+note={Software available from tensorflow.org},
+author={
+    Mart\'{i}n~Abadi and
+    Ashish~Agarwal and
+    Paul~Barham and
+    Eugene~Brevdo and
+    Zhifeng~Chen and
+    Craig~Citro and
+    Greg~S.~Corrado and
+    Andy~Davis and
+    Jeffrey~Dean and
+    Matthieu~Devin and
+    Sanjay~Ghemawat and
+    Ian~Goodfellow and
+    Andrew~Harp and
+    Geoffrey~Irving and
+    Michael~Isard and
+    Yangqing Jia and
+    Rafal~Jozefowicz and
+    Lukasz~Kaiser and
+    Manjunath~Kudlur and
+    Josh~Levenberg and
+    Dandelion~Man\'{e} and
+    Rajat~Monga and
+    Sherry~Moore and
+    Derek~Murray and
+    Chris~Olah and
+    Mike~Schuster and
+    Jonathon~Shlens and
+    Benoit~Steiner and
+    Ilya~Sutskever and
+    Kunal~Talwar and
+    Paul~Tucker and
+    Vincent~Vanhoucke and
+    Vijay~Vasudevan and
+    Fernanda~Vi\'{e}gas and
+    Oriol~Vinyals and
+    Pete~Warden and
+    Martin~Wattenberg and
+    Martin~Wicke and
+    Yuan~Yu and
+    Xiaoqiang~Zheng},
+  year={2015},
 }

paper/paper.md

@@ -31,16 +31,16 @@ technology of Predictive Maintenance (PdM) [@heimes2008recurrent; @li2018remaini
 
 Effective maintenance management helps reduce costs related to defective products and equipment downtime. A well-planned maintenance strategy improves reliability, prevents unexpected outages, and lowers operating costs. In Industry 4.0, data from the manufacturing process can enhance decision-making. RUL estimation uses prediction techniques to forecast a machine's future performance based on historical data and determine its remaining useful life, enabling early identification of potential failures and prompt pre-failure interventions. In this context, `CeRULEo` provides a comprehensive set of utilities designed to train and evaluate regression models for predicting remaining useful life of equipment. 
 
-In order to achieve good performance, RUL regression requires data preparation and feature engineering. Typically, machinery data is provided as time series data from various sensors during operation. The first step in data preparation is often to create a dataset based on run-to-failure cycles. This involves dividing the time series into segments where the equipment starts in a healthy state and ends in a failure state, or is close to failure. The second step of data preparation is preprocessing. While predictive maintenance models can be used in a variety of contexts with different data sources and errors, there are some general techniques that can be applied [@serradilla2022deep], such as time-series validation, imputing missing values, handling homogeneous or non-homogeneous sampling rates, addressing values, range and behaviour differences across difference machines and the creation of run-to-failure-cycle-based data. 
+In order to achieve good performance, RUL regression requires data preparation and feature engineering. Typically, machinery data is provided as time series data from various sensors during operation. The first step in data preparation is often to create a dataset based on run-to-failure cycles. This involves dividing the time series into segments where the equipment starts in a healthy state and ends in a failure state, or is close to failure. The second step of data preparation is preprocessing. While PdM models can be used in a variety of contexts with different data sources and errors, there are some general techniques that can be applied [@serradilla2022deep], such as time-series validation, imputing missing values, handling homogeneous or non-homogeneous sampling rates, addressing values, range and behaviour differences across difference machines and the creation of run-to-failure-cycle-based data. 
 
 
-`CeRULEo` addresses these issues by providing a comprehensive toolkit for preprocessing time series data for use in predictive maintenance models, with a focus on run-to-failure cycles. The preprocessing includes sensor data validation methods, for studyng not only missing and corrupted values but also distribution drift among different pieces of equipment. 
+`CeRULEo` addresses these issues by providing a comprehensive toolkit for preprocessing time series data for use in PdM models, with a focus on run-to-failure cycles. The preprocessing includes sensor data validation methods, for studying not only missing and corrupted values but also distribution drift among different pieces of equipment. 
 
-In addition to preprocessing, it enables the iteration of machine data for use in both mini-batch and full-batch regression models, and is compatible with popular machine learning frameworks such as scikit-learn and tensorflow. The library also includes a catalog of successful deep learning models [@jayasinghe2019temporal; @li2020remaining; @CHEN2022104969] from the literature and a collection of commonly used remaining useful life datasets for quick model evaluation.
+In addition to preprocessing, it enables the iteration of machine data for use in both mini-batch and full-batch regression models, and is compatible with popular machine learning frameworks such as scikit-learn [@scikit-learn] and tensorflow [@tensorflow2015-whitepaper]. The library also includes a catalog of successful deep learning models [@jayasinghe2019temporal; @li2020remaining; @CHEN2022104969] from the literature and a collection of commonly used remaining useful life datasets for quick model evaluation.
 
 In the context of predictive maintenance, explainability is crucial. As such, `CeRULEo` includes two explainable models: one that can select the most relevant features for the model [@lemhadri2021lassonet], and a convolutional model [@fauvel2021xcm] that provides post-hoc explanations of the predictions to understand the reasoning behind the predicted remaining useful life. This helps users better understand and trust the model's predictions.
 
-Moreover, `CeRULEo` provides tools for evaluating and comparing predictive maintenance models based on not only traditional regression metrics, but also on their ability to prevent errors and reduce costs. In many cases, the costs of not accurately detecting or anticipating faults can be much higher than the cost of inspections or maintenance due to reduced efficiency, unplanned downtime, and corrective maintenance expenses. In predictive maintenance, it is particularly important to be accurate about the remaining useful life  of equipment near the end of its lifespan, as an overestimation of RUL can have serious consequences when immediate action is required. `CeRULEo` addresses this issue by providing mechanisms for weighting samples according to their importance and asymmetric losses for training models, as well as visualization tools for understanding model performance in relation to true RUL.
+Moreover, `CeRULEo` provides tools for evaluating and comparing PdM models based on not only traditional regression metrics, but also on their ability to prevent errors and reduce costs. In many cases, the costs of not accurately detecting or anticipating faults can be much higher than the cost of inspections or maintenance due to reduced efficiency, unplanned downtime, and corrective maintenance expenses. In predictive maintenance, it is particularly important to be accurate about the remaining useful life  of equipment near the end of its lifespan, as an overestimation of RUL can have serious consequences when immediate action is required. `CeRULEo` addresses this issue by providing mechanisms for weighting samples according to their importance and asymmetric losses for training models, as well as visualization tools for understanding model performance in relation to true RUL.
 
 
 # Financial Acknowledgement