Real Time Face Mask Detection System using Transfer Learning with Machine Learning Method in the Era of Covid-19 Pandemic

Abstract A cyber-physical system (CPS) is one of the key technologies of industry 4.0. It is an integrated system that merges computing, sensors, and actuators, controlled by computer-based algorithms that integrate people and cyberspace. However, CPS performance is limited by its computational complexity. Finding a way to implement CPS with reduced complexity while incorporating more efficient diagnostics, forecasting, and equipment health management in a real-time performance remains a challenge. Therefore, the study proposes an integrative machine-learning method to reduce the computational complexity and to improve the applicability as a virtual subsystem in the CPS environment. This study utilizes random forest (RF) and a time-series deep-learning model based on the long short-term memory (LSTM) networking to achieve real-time monitoring and to enable the faster corrective adjustment of machines. We propose a method in which a fault detection alarm is triggered well before a machine fails, enabling shop-floor engineers to adjust its parameters or perform maintenance to mitigate the impact of its shutdown. As demonstrated in two empirical studies, the proposed method outperforms other times-series techniques. Accuracy reaches 80% or higher 3 h prior to real-time shutdown in the first case, and a significant improvement in the life of the product (281%) during a particular process appears in the second case. The proposed method can be applied to other complex systems to boost the efficiency of machine utilization and productivity.

Download Full-text

Transfer learning features for predicting aesthetics through a novel hybrid machine learning method

Neural Computing and Applications ◽

10.1007/s00521-019-04065-4 ◽

2019 ◽

Vol 32 (10) ◽

pp. 5889-5900 ◽

Cited By ~ 3

Author(s):

Adrian Carballal ◽

Carlos Fernandez-Lozano ◽

Jonathan Heras ◽

Juan Romero

Keyword(s):

Machine Learning ◽

Transfer Learning ◽

Machine Learning Method ◽

Learning Method ◽

Hybrid Machine

Download Full-text

A New Hybrid Analytical-Machine Learning Method for Real-Time ROP Modeling

Biointerface Research in Applied Chemistry ◽

10.33263/briac111.75897604 ◽

2020 ◽

Vol 11 (1) ◽

pp. 7589-7604

Keyword(s):

Machine Learning ◽

Real Time ◽

Machine Learning Method ◽

Learning Method ◽

Real Time Control ◽

Rate Of Penetration ◽

Drilling Operation ◽

Time Control ◽

Constant Coefficients ◽

Drilling Operations

Real-time drilling optimization refers to operations and equipment that could minimize total drilling costs. Drilling speed that is called the rate of penetration (ROP) in the drilling industry can be used as a good indicator for the performance evaluation of the drilling operation. Real-time control for drilling ROP is limited to just a few controllable parameters during drilling operations, that is, WOB, RPM, and hydraulics. These parameters can be controlled from the surface by the driller in real-time. In the traditional methods of ROP modeling, an inflexible equation could be developed between some important effective drilling parameters such as weight on the bit or bit rotational speed and drilling rate of penetration. These models had a low degree of accuracy, and they were not applicable in the newly drilled wells even in the same field with an acceptable degree of accuracy. In this study, a new real-time continues-learning method for ROP modeling was developed. In this method, as the drilling operation gets starts and the drilling data reaches the surface, ROP modeling starts, and as the drilling continues, the model accuracy increases. For the method evaluation, 5 famous existing analytical drilling model was selected. Also, a new ROP model was developed in this work. All of these 6 models contain some constant coefficients that were obtained using a new machine learning method named Rain Optimization Algorithm. In the end, the accuracy of the models was compared. Results show that the presented method for ROP modeling is a very flexible method with a high degree of accuracy that can be easily used in any formation. Also, the newly presented model could increase the accuracy of ROP prediction from 75% to 81%.

Download Full-text

Machine learning method for real-time non-invasive prediction of individual thermal preference in transient conditions

Building and Environment ◽

10.1016/j.buildenv.2018.11.017 ◽

2019 ◽

Vol 148 ◽

pp. 372-383 ◽

Cited By ~ 24

Author(s):

Andrei Claudiu Cosma ◽

Rahul Simha

Keyword(s):

Machine Learning ◽

Real Time ◽

Machine Learning Method ◽

Thermal Preference ◽

Learning Method ◽

Transient Conditions ◽

Non Invasive

Download Full-text

A hybrid machine learning method for increasing the performance of network intrusion detection systems

Journal Of Big Data ◽

10.1186/s40537-021-00531-w ◽

2021 ◽

Vol 8 (1) ◽

Author(s):

Achmad Akbar Megantara ◽

Tohari Ahmad

Keyword(s):

Machine Learning ◽

Intrusion Detection ◽

Intrusion Detection System ◽

Detection System ◽

The Internet ◽

Public Facility ◽

Machine Learning Method ◽

Learning Method ◽

Network Intrusion ◽

Hybrid Machine

AbstractThe internet has grown enormously for many years. It is not just connecting computer networks but also a group of devices worldwide involving big data. The internet provides an opportunity to make various innovations for any sector, such as education, health, public facility, financial technology, and digital commerce. Despite its advantages, the internet may contain dangerous activities and cyber-attacks that may happen to anyone connected through the internet. To detect any cyber-attack intrudes on the network system, an intrusion detection system (IDS) is applied, which can identify those incoming attacks. The intrusion detection system works in two mechanisms: signature-based detection and anomaly-based detection. In anomaly-based detection, the quality of the machine learning model obtained is influenced by the data training process. The biggest challenge of machine learning methods is how to build an appropriate model to represent the dataset. This research proposes a hybrid machine learning method by combining the feature selection method, representing the supervised learning and data reduction method as the unsupervised learning to build an appropriate model. It works by selecting relevant and significant features using feature importance decision tree-based method with recursive feature elimination and detecting anomaly/outlier data using the Local Outlier Factor (LOF) method. The experimental results show that the proposed method achieves the highest accuracy in detecting R2L (i.e., 99.89%) and keeps higher for other attack types than most other research in the NSL-KDD dataset. Therefore, it has a more stable performance than the others. More challenges are experienced in the UNSW-NB15 dataset with binary classes.

Download Full-text