Mathematical models of classification algorithm of Machine learning

Abstract

Machine learning algorithm has brought the augmenting change in the field of artificial intelligence which espoused human discerning power in a splendid manner. The algorithm has various categories among which classification is the most popular part. Support vector machine algorithm, logistic regression, naïve bays algorithm, decision tree, boosted tree, random forest and k nearest neighbour algorithm all are under classification algorithms. Classification process needs some pre-defined method which leads the method for choosing the train data from the sample data given by the user. Decision making is the heart of any classification algorithm as supervised learning stands out on the decision of users. So the strong mathematical model based on conditional probability lies behind each algorithm. This paper is the study of those mathematical models and logic behind various classification algorithms which help to create a strong decision for users to make the training dataset based on which machine can predict the proper output. Markov chain model Markov chain model is a statistical and mathematical setup which has some hidden layers and can be represented as the simple Basyian network which is directly visible to the observer. This model has a remarkable contribution in the field of supervised and reinforcement learning and for pattern recognition. If any example is considered for two classes i.e. A and B and it has 4 transitions when the system is in A then it can be considered as a transition of B similarly when a system is in B it can be considered as a transition of A (Fig1). In that way, a transition matrix will be formed which will define the probability of transition of the state. In that way not only in two classes but also with n no of classes or states the model can be built up.

SenseHunger: Machine Learning Approach to Hunger Detection Using Wearable Sensors

“…Our proposed non-invasive multimodal system with carefully selected sensor channels outperformed previous approaches with an accuracy of 93.43% and an average F1 score of 87.86%. Each classification algorithm is based on different mathematical models [ 60 ], and may produce different results for the same dataset. In order to obtain highly accurate results and to select the best classifier for further experiments, we not only conducted experiments with different classifiers, but also with different window sizes and step sizes.…”

“…Each classification algorithm is based on different mathematical models [ 60 ], and may produce different results for the same dataset. In order to obtain highly accurate results and to select the best classifier for further experiments, we not only conducted experiments with different classifiers, but also with different window sizes and step sizes.…”

Identification of Water Hammering for Centrifugal Pump Drive Systems

“…It can handle both large numbers of datasets and small sizes of datasets 5. If this can be implemented in an Internet of Things (IoT)-based system, the whole process can be controlled remotely [25,26] Table 6 shows that predictive control technology-based ML algorithms, mainly regression analysis, can give more accurate results than any other method.…”

“…The experiment was done with the Vib Sensor mobile phone-based app, which is mounted in the impeller of the pumping system and different pressure bars 1, 1.3, 1.5, 2 bars. In this research VFD based pumping system has been used for the experiment [26]. Vibration details are recorded for analysis of the motor and pumping state to predict water hammering.…”

“…The data were recorded at a sample rate of 50 kHz. Fast Fourier transformation (FFT) analysis [26][27][28] was done in a time-frequency pattern, and it was identified that the signal is noisier, and there is the presence of harmonics when there is a fault rather than a threshold condition (Figure 12). With the help of the power spectrum analyzer and with the recorded data, ML algorithms were implemented to predict faulty conditions.…”