Data Privacy-Preservation: A Method of Machine Learning

Achar, Sandesh

doi:10.18034/abcjar.v7i2.654

Cited by 4 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before a company can successfully leverage information, there needs to be a distinction between information (Achar, 2018a). As such, essential information needs to be made clear.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Innovations in Information Systems for Business Functionality and Operations Management

Amin

2019

ABC res. alert

View full text Add to dashboard Cite

The industrial revolution brought about a smorgasbord of changes in the business environment. A lot of processes could be made more efficient, and productivity could be increased by a factor of a thousand. Nonetheless, after a century, the world's business sector experienced a period of relative stagnation. Later on, the technological revolution and the widespread use of information systems in business became a more significant disruptive force in the business world. Because of the rapid rate at which information technology evolves and is adapted for various applications, there are numerous opportunities to maximize functionality and productivity. The study covered topics such as computing and information technologies, decision analysis, nonlinear complementarity problems, optimization, revenue management, simulation, stochastic models, and stochastic optimization, among other things.

show abstract

“…Before a company can successfully leverage information, there needs to be a distinction between information (Achar, 2018a). As such, essential information needs to be made clear.…”

Section: Review Of Related Literaturementioning

confidence: 99%

Innovations in Information Systems for Business Functionality and Operations Management

Amin

2019

ABC res. alert

View full text Add to dashboard Cite

show abstract

“…Hochreiter and Schmidhuber proposed LSTMs as a form of recurrent neural network (RNN) (1997). Memory cells in LSTMs are equivalent to states in traditional dynamical systems models, making them helpful for mimicking real systems such as watersheds (Achar, 2018a). LSTMs avoid exploding and/or vanishing gradients, which allows them to learn long-term dependencies between input and output features, unlike other forms of recurrent neural networks.…”

Section: Overview Of Lstm Networkmentioning

confidence: 99%

Enhancing Predictions in Ungauged Basins Using Machine Learning to Its Full Potential

Fadziso

2019

Asian j. appl. sci. eng.

View full text Add to dashboard Cite

In ungauged basins, long short-term memory (LSTM) networks provide unparalleled precision in prediction. Using k-fold validation, we trained and tested various LSTMs on 531 basins from the CAMELS data set, allowing us to make predictions in basins with no training data. The training and test data set contained 30 years of daily rainfall-runoff data from US catchments ranging in size from 4 to 2,000 km2, with aridity indexes ranging from 0.22 to 5.20, and 12 of the 13 IGPB vegetated land cover classes. Over a 15-year validation period, this effectively "ungauged" model was compared to the Sacramento Soil Moisture Accounting (SAC-SMA) model as well as the NOAA National Water Model reanalysis. Each basin's SAC-SMA was calibrated separately using 15 years of daily data. Across the 531 basins, the out-of-sample LSTM exhibited greater median Nash-Sutcliffe Efficiencies (0.69) than either the calibrated SAC-SMA (0.64) or the National Water Model (0.64). (0.58). This means that there is usually enough information in available catchment attributes data about similarities and differences between catchment-level rainfall-runoff behaviors to generate out-of-sample simulations that are generally more accurate than current models under ideal (i.e., calibrated) conditions. We discovered evidence that adding physical restrictions to the LSTM models improves simulations, which we believe should be the focus of future physics-guided machine learning research.

show abstract

“…Research is conducted on the dimensionless pressure derivatives of a vertical oil well to find the best possible site for the well that will allow for good oil production while minimizing the impact of any external boundaries that may come into play too soon. Achar (2018a) examined the typical workflow that governs probabilistic evaluation methodologies and proposed a Python script-based approach. This approach enables the user to run a quick and easy mineral components evaluation based on porosity and raw input logs.…”

Section: Introductionmentioning

confidence: 99%

A Commentary on the Applications of Python in Resolving Issues Concerning Energy and the Ecosystems

Fadziso¹

2021

Asia Pac. j. energy environ.

View full text Add to dashboard Cite

The energy industry is just getting started with applying it to problems with energy and ecosystems so they can find solutions. Python's popularity has increased across a variety of sectors, including businesses, academic institutions, government agencies, and research organizations. The true potential it possesses to automate a variety of processes while simultaneously increasing the capabilities of various industries to predict outcomes has been observed. Because of the digital transformation, such as sensors and high-performance computing services, which enable artificial intelligence (AI), machine learning (ML), big data acquisition, and storage in digital oilfields, its popularity has been on the rise in the industry that deals with energy and ecosystems. This is one of the primary reasons why. This can be easily verified by conducting a quick search for the number of publications that have been produced in the field of energy and ecosystems by the Society of Petroleum Engineers over the past few years. Without having to invest in pricey software, the production and reservoir engineers will be able to better manage the production operation thanks to this development. In addition to this, it will lead to a decrease in the overall operating costs and an increase in revenue. As a result, it has been demonstrated to be a promising application that has the potential to bring about a revolutionary change in the industry of energy and ecosystems and to transform the features that are already in place for the purpose of resolving issues related to energy and ecosystems.

show abstract

Data Privacy-Preservation: A Method of Machine Learning

Cited by 4 publications

References 14 publications

Innovations in Information Systems for Business Functionality and Operations Management

Innovations in Information Systems for Business Functionality and Operations Management

Enhancing Predictions in Ungauged Basins Using Machine Learning to Its Full Potential

A Commentary on the Applications of Python in Resolving Issues Concerning Energy and the Ecosystems

Contact Info

Product

Resources

About