3. Proposed FCM Map-Reduce based adaptive neural network classifier for handling big data in health care

The large amounts of data, driven by record keeping, compliance & regulatory requirements, and patient care will historically render for the healthcare industry. While most data is saved in hard copy form, the current trend is towards quick digitization of these large amounts of data. Driven by mandatory requirements and the potential to develop the quality of healthcare delivery meanwhile minimizing the costs, these massive quantities of data known as 'big data' hold the promise of supporting a wide range of medical and healthcare functions, admitting between others clinical decision support, disease surveillance, and population health management. Some troubles that exist in big data analysis in health care are, i) to succeed, big data analytics in healthcare requires to be packaged so it is menu driven, user-friendly and transparent. ii) The lag among data collection and processing has to be addressed. iii) The crucial managerial issues of ownership, governance and standards have to be conceived. iv) Continuous data acquisition and data cleansing is another issue.

In the increasingly quick generation of large amounts of data, and across several areas of science, technological and conceptual advances are resulting. The collection and organization of data, the volume, variety, and velocity of current 'big data' production inaugurates novel opportunities and challenges in both scale and complexity these are always admitted on research. Also, in health care sector, the dealing of big data has currently get an interesting research topic, as since there are wide amount of medical data's available in cloud storage.

Moreover, the huge number of data records within very large datasets that comprise an extremely high amount of information is conceived to be a very critical issue. Thus processing with sequential algorithm results in greater computational cost in terms of memory space and time complexities. Hence, for discovering the above mentioned issues, a parallel architecture is required to be demonstrated.

In order to minimize the computational complexity and the memory requirement while leading large healthcare data, it is suggested to have a parallel adaptive artificial neural network (AANN) technique applying Map-Reduce programming model for health care analysis from big data in cloud environment. The introduction of abnormality in the medical data records applying the proposed Map-Reduce based Adaptive Artificial Neural Network classification method by the trained data these are determined by suggested approach. The medical data from the cloud has to be first clustered in order to distinguish the similar classes of data associated to any one particular health disorder for better classification of data. Here, the clustering of similar sets of data is done with the help of Fuzzy C means clustering algorithm, so as to develop the classification performance. The dataset separated as sub clusters were afforded to Map-Reducer framework, where AANN is implemented in parallel. Once the clustering is done the normal and abnormal classes of medical data are then learned applying the proposed map decrease programming model based AANN. By training the AANN models, it can be capable to predict for newer data as well.

The map minimized programming model comprises of two phases: (1) Mapper phase and (2) Reducer phase. Data belonging to each cluster are mapped applying separate mappers. Each mapper based AANN receives one training item (i.e. any one data cluster) and then calculates the weights of the network applying the training item in the suggested parallel prediction model. Here, to develop the precision of classification of the data, the proposed AANN method applies the concept of optimization, where the weight factors are maximized by applying Whale Optimization Algorithm. The Reducer separates the test medical record in order to distinguish the health condition established on the mapped data.

Here, the schematic diagram of the proposed healthcare application model for the analysis of large datasets is presented in Figure 1.

The proposed FCM based Map-Reduce AANN approach comprises of the following phases, 1) Fuzzy C-means (FCM) based Data Grouping 2) Mapper phase involving assigning each data groups to separate Mappers and training Data using Adaptive ANN 3) Reducer Phase consisting of Testing Phase. Each of the steps is detailed in the following sections.

### 3.1. Phase 1: Fuzzy C-means (FCM) based data grouping

Established on the membership function, Fuzzy C-means (FCM) is a data clustering technique in which each and every data in that group will comes under one cluster. It will group all the data in to particular number of clusters in high dimensional search space. The degrees of the cluster are determined by the membership function in terms of [0, 1] which affords the flexibility that the data point can belong to more than one cluster.

The proposed method applies FCM for clustering the input large data into smaller groups of similar data. The input data will be grouped into number of clusters randomly and the centroids will be rendered for the clusters during Fuzzy c-means clustering. The clusters are

Adaptive Neural Network Classifier-Based Analysis of Big Data in Health Care

http://dx.doi.org/10.5772/intechopen.77225

129

Figure 1. Schematic diagram.

Figure 1. Schematic diagram.

Moreover, the huge number of data records within very large datasets that comprise an extremely high amount of information is conceived to be a very critical issue. Thus processing with sequential algorithm results in greater computational cost in terms of memory space and time complexities. Hence, for discovering the above mentioned issues, a parallel architecture is

In order to minimize the computational complexity and the memory requirement while leading large healthcare data, it is suggested to have a parallel adaptive artificial neural network (AANN) technique applying Map-Reduce programming model for health care analysis from big data in cloud environment. The introduction of abnormality in the medical data records applying the proposed Map-Reduce based Adaptive Artificial Neural Network classification method by the trained data these are determined by suggested approach. The medical data from the cloud has to be first clustered in order to distinguish the similar classes of data associated to any one particular health disorder for better classification of data. Here, the clustering of similar sets of data is done with the help of Fuzzy C means clustering algorithm, so as to develop the classification performance. The dataset separated as sub clusters were afforded to Map-Reducer framework, where AANN is implemented in parallel. Once the clustering is done the normal and abnormal classes of medical data are then learned applying the proposed map decrease programming model based AANN. By training the AANN

The map minimized programming model comprises of two phases: (1) Mapper phase and (2) Reducer phase. Data belonging to each cluster are mapped applying separate mappers. Each mapper based AANN receives one training item (i.e. any one data cluster) and then calculates the weights of the network applying the training item in the suggested parallel prediction model. Here, to develop the precision of classification of the data, the proposed AANN method applies the concept of optimization, where the weight factors are maximized by applying Whale Optimization Algorithm. The Reducer separates the test medical record in

Here, the schematic diagram of the proposed healthcare application model for the analysis of

The proposed FCM based Map-Reduce AANN approach comprises of the following phases, 1) Fuzzy C-means (FCM) based Data Grouping 2) Mapper phase involving assigning each data groups to separate Mappers and training Data using Adaptive ANN 3) Reducer Phase

Established on the membership function, Fuzzy C-means (FCM) is a data clustering technique in which each and every data in that group will comes under one cluster. It will group all the data in to particular number of clusters in high dimensional search space. The degrees of the cluster are determined by the membership function in terms of [0, 1] which affords the

required to be demonstrated.

128 Data Mining

models, it can be capable to predict for newer data as well.

3.1. Phase 1: Fuzzy C-means (FCM) based data grouping

flexibility that the data point can belong to more than one cluster.

large datasets is presented in Figure 1.

order to distinguish the health condition established on the mapped data.

consisting of Testing Phase. Each of the steps is detailed in the following sections.

The proposed method applies FCM for clustering the input large data into smaller groups of similar data. The input data will be grouped into number of clusters randomly and the centroids will be rendered for the clusters during Fuzzy c-means clustering. The clusters are updated established on the membership grade of the data points and the novel centroid is depicted correspondingly at the each iteration.

Moreover, how the clustering with fuzzy c means algorithm is made for a set of input samples is afforded below.

Let us considering the input sample be,

$$D\_{\mu} \left( \mu = 1, 2, \ldots, n \right) \tag{1}$$

The input data is clustered into data groups of certain similarity for established on the above procedure of FCM. We found the number of cluster set such as C1, C2, C3, …, Cn at the end of the FCM process. For the parallel implementation, all the clusters are aligned to divide the

Adaptive Neural Network Classifier-Based Analysis of Big Data in Health Care

http://dx.doi.org/10.5772/intechopen.77225

131

For large scale mobile data process, the mapper is a programming model and a connected implementation. Programmers only required to specify a Map-Reduce job which is composed of Reducer functions and the mapper. A Mapper function receives a key/value pair and generates a set of intermediate key/value pairs. With the same intermediate key, and a Reducer function merges all intermediate values are connected. Here, in parallel, the Mapper receives the clustered data and trains the AANN. Then established on all the Mappers output network

In the Mapper phase, the clustered data is now processed. Mapper receives several items of the training sets (i.e. data items from the cluster groups) and accomplishes many mapper tasks. Each Mapper receives one training item (i.e. data items from one cluster group) and then performs AANN learning/training task by maximizing the weight values in the network applying this training item; so as to develop the learning efficiency. Through the AANN algorithm, their outputs are the trained network models resulted. The Mapper process (i.e. the AANN training procedure) is accomplished repeatedly until the expected precision is

Artificial neural network is otherwise named as Neural Network (NN). For calculation, it contains of an interconnected collecting of artificial neurons and procedures data applying a connectionist approach. Here a feed forward neural network (FFNN) inaugurated by this work. The data moves in just a single direction, forward, from the input layers, through the hidden layers, and to the output layers by this system. There are no cycles or circles in the system. The information handling can stretch out over numerous (layers of) units, yet no criticism associations are available, that is, an association reaching out from outputs of units to contributions of units in a similar layer or past layers is not present. There are associations among the processing elements (PEs) in every layer that have a weight (parameter) connected with them. Amid preparing this weight is balanced. The proposed adaptive ANN renders the optimal training network aligned by optimally selecting the interconnection weights among

Input information is displayed to the system and proliferated through the system until it attains the output layer in FFNN. A predicted output is delivered by this forward procedure. The desired output is subtracted from the actual output and error esteem for the systems is

model, the Reducers improve an AANN model to predict for unknown/newer data.

3.3. Phase 2(a): assigning each data groups to separate Mappers

3.4. Phase 2(b): training data clusters using parallel adaptive ANN

the hidden and output layers applying Whale Optimization Algorithm.

ascertained. The error function can be characterized as:

mappers.

attained.

3.2. Phase 2: Mapper phase

The input sample is to be separated into 'v' number of clusters. The clustering cannot be exactingly but it will be made by means of the grouping with respective to the grade of membership function.

The objective function of FCM algorithm is effectively explained as follows.

$$ObjecFun = \sum\_{u=1}^{n} \sum\_{v=1}^{C} M\_{uv} \|D\_{u} - c\_{v}\|^2 \tag{2}$$

where,

"Muv" is the membership of uth data (Di) in the vth cluster cv.

"cv" is the vth cluster center.

"Du" is the uth data record.

"n" is the total number of data record.

"C" is the required number of clusters.

"k k Du � cv <sup>2</sup> " is the similarity between uth data record and the center vector of vthcluster. Now the cluster center calculation is done by Eq. (3),

$$\mathcal{L}\_v = \frac{\sum\_{\mu=1}^n M\_{\mu v} D\_{\mu}}{\sum\_{\mu=1}^n M\_{\mu v}} \tag{3}$$

Membership updation is done by Eq. (4),

$$M\_{uv} = \frac{1}{\sum\_{y=1}^{\mathbb{C}} \left(\frac{\|D\_u - c\_v\|}{\|D\_u - c\_y\|}\right)^{\frac{2}{\delta - 1}}} \tag{4}$$

where, 'b' is the fuzziness coefficient. The membership matrix <sup>M</sup>ð Þ<sup>x</sup> <sup>¼</sup> ½ � Muv is calculated for among every iteration. If <sup>M</sup>ð Þ<sup>x</sup> � <sup>M</sup>ð Þ <sup>x</sup>�<sup>1</sup> � � � � < T then stop, Where, "x" denotes the current iteration and "T" is the threshold of termination criterion, which is among 0 and 1.

The input data is clustered into data groups of certain similarity for established on the above procedure of FCM. We found the number of cluster set such as C1, C2, C3, …, Cn at the end of the FCM process. For the parallel implementation, all the clusters are aligned to divide the mappers.

### 3.2. Phase 2: Mapper phase

updated established on the membership grade of the data points and the novel centroid is

Moreover, how the clustering with fuzzy c means algorithm is made for a set of input samples

The input sample is to be separated into 'v' number of clusters. The clustering cannot be exactingly but it will be made by means of the grouping with respective to the grade of

> X C

v¼1

" is the similarity between uth data record and the center vector of vthcluster.

MuvDu

k k Du�cv k k Du�cy � � <sup>2</sup>

where, 'b' is the fuzziness coefficient. The membership matrix <sup>M</sup>ð Þ<sup>x</sup> <sup>¼</sup> ½ � Muv is calculated for

b�1

� < T then stop, Where, "x" denotes the current

cv ¼

Muv <sup>¼</sup> <sup>1</sup> P C y¼1

iteration and "T" is the threshold of termination criterion, which is among 0 and 1.

� �

Pn u¼1

Pn u¼1 Muv

The objective function of FCM algorithm is effectively explained as follows.

Objec Fun <sup>¼</sup> <sup>X</sup><sup>n</sup>

"Muv" is the membership of uth data (Di) in the vth cluster cv.

Now the cluster center calculation is done by Eq. (3),

u¼1

Du ð Þ u ¼ 1; 2;…; n (1)

Muvk k Du � cv <sup>2</sup> (2)

(3)

(4)

depicted correspondingly at the each iteration.

Let us considering the input sample be,

is afforded below.

130 Data Mining

membership function.

"cv" is the vth cluster center.

"Du" is the uth data record.

"n" is the total number of data record. "C" is the required number of clusters.

Membership updation is done by Eq. (4),

among every iteration. If <sup>M</sup>ð Þ<sup>x</sup> � <sup>M</sup>ð Þ <sup>x</sup>�<sup>1</sup> �

where,

"k k Du � cv <sup>2</sup>

For large scale mobile data process, the mapper is a programming model and a connected implementation. Programmers only required to specify a Map-Reduce job which is composed of Reducer functions and the mapper. A Mapper function receives a key/value pair and generates a set of intermediate key/value pairs. With the same intermediate key, and a Reducer function merges all intermediate values are connected. Here, in parallel, the Mapper receives the clustered data and trains the AANN. Then established on all the Mappers output network model, the Reducers improve an AANN model to predict for unknown/newer data.

### 3.3. Phase 2(a): assigning each data groups to separate Mappers

In the Mapper phase, the clustered data is now processed. Mapper receives several items of the training sets (i.e. data items from the cluster groups) and accomplishes many mapper tasks. Each Mapper receives one training item (i.e. data items from one cluster group) and then performs AANN learning/training task by maximizing the weight values in the network applying this training item; so as to develop the learning efficiency. Through the AANN algorithm, their outputs are the trained network models resulted. The Mapper process (i.e. the AANN training procedure) is accomplished repeatedly until the expected precision is attained.

### 3.4. Phase 2(b): training data clusters using parallel adaptive ANN

Artificial neural network is otherwise named as Neural Network (NN). For calculation, it contains of an interconnected collecting of artificial neurons and procedures data applying a connectionist approach. Here a feed forward neural network (FFNN) inaugurated by this work. The data moves in just a single direction, forward, from the input layers, through the hidden layers, and to the output layers by this system. There are no cycles or circles in the system. The information handling can stretch out over numerous (layers of) units, yet no criticism associations are available, that is, an association reaching out from outputs of units to contributions of units in a similar layer or past layers is not present. There are associations among the processing elements (PEs) in every layer that have a weight (parameter) connected with them. Amid preparing this weight is balanced. The proposed adaptive ANN renders the optimal training network aligned by optimally selecting the interconnection weights among the hidden and output layers applying Whale Optimization Algorithm.

Input information is displayed to the system and proliferated through the system until it attains the output layer in FFNN. A predicted output is delivered by this forward procedure. The desired output is subtracted from the actual output and error esteem for the systems is ascertained. The error function can be characterized as:

$$e(w) = \sum \left( desired - actual \, output \right)^2\tag{5}$$

and c) Search the prey. The steps admitted in the proposed Whale optimization algorithm for rendering the optimal network structure by maximizing the interconnection weights of the

The algorithm is showed by arbitrarily generating the solutions (i.e. the interconnection weight values) that communicates to the result. Here the neural network structure comprising the interconnection weights among the hidden layers and the output layers are referred by the

where, f g wm, <sup>1</sup>; ww,m;…; wm,h represents the set of weights among the input and hidden layer and f g wm,h;…; wm,R represents the set of weights among the input and hidden layer. Also, each solution, Wm ¼ f g wm, <sup>1</sup>; wm,2;…; wm, <sup>h</sup>;…; wm,R is a R-dimensional vector where R being the number of optimization parameters. And also start the coefficient vectors of whale such as,

Determine the fitness of the input solutions on the basis of the Eq. (7). To get the best weight

The minimum of mean square error (MSE) determines that, how correct the network predicted targets are (i.e. high classification accuracy) in above equation. Hence, for further develop-

The position of prey (i.e. the current best solution) is distinguished by humpback whale and then it encircles the prey. Towards the best search operator the other search operators will consequently attempt to update their positions when the best search agent is characterized.

> <sup>m</sup> ð Þ� x Wm ! ð Þx

> > ! best

<sup>m</sup> ð Þ�x F ! � N !

 

!

!

and G ! (8)

(9)

denotes a Coeffi-

ð Þx represents a current

ment, the initial solution with minimum error is chosen as best solution and checked.

values, the fitness value of the solutions are computed. It's revealed in below,

Step 3: Update position of current solutions towards the best

The updation method is determined by the below equations:

N ! ¼ G ! �W ! best

Wm !

 

ð Þ¼ x þ 1 W

<sup>m</sup> denotes a position vector for best solution, Wm

ð Þ x þ 1 ' denotes the newer solutions for next iteration, F

Wm ¼ f g wm,1; wm,2; …; wm,h;…; wm,R (6)

Adaptive Neural Network Classifier-Based Analysis of Big Data in Health Care

http://dx.doi.org/10.5772/intechopen.77225

133

FitWm ¼ minð Þ MSE (7)

neurons are afforded as follows,

random value in the search space is afforded as:

Step 1: Initialization.

, and G! . Step 2: Fitness Calculation.

A. Encircling prey

where 'Wm !

cient vector, W

! best

position Vector and jj represents an absolute value.

f ! , F !

For altering weights, a couple of traditional researches has applied Backpropagation learning algorithm. In reverse through the system, the calculation begins with the weights among the output layer PE's and the last hidden layer PE's and works. Once back propagation has fulfilled, the forward procedure begins once more, and this cycle proceeds until the error among is predicted and actual output are reduced. Rather than back propagation algorithm, the Whale Optimization algorithm is displayed because it can acquire valuable output than back propagation calculation.

The proposed Adaptive Artificial Neural Network model is given in below Figure 2.

a. Whale optimization approach

Recently a novel optimization algorithm named whale optimization algorithm (Mirjalili 2016) has been introduced to metaheuristic algorithm by Mirjalili and Lewis. As highly intelligent animals with motion, the whales are conceived. The WOA is inspired by the unique hunting behavior of humpback whales. The humpback whales prefer to hunt krills or small fishes which are close to the surface of sea at normally. Humpback whales use a special unique hunting method named bubble net feeding method. In this method they swim around the prey and produce distinctive bubbles along a circle or 9-shaped path. The mathematical model of WOA is described in the following sections a) Encircling prey b) Bubble net hunting method

Figure 2. Proposed adaptive artificial neural network.

and c) Search the prey. The steps admitted in the proposed Whale optimization algorithm for rendering the optimal network structure by maximizing the interconnection weights of the neurons are afforded as follows,

Step 1: Initialization.

e wð Þ¼ <sup>X</sup>ð Þ desired � actual output <sup>2</sup> (5)

For altering weights, a couple of traditional researches has applied Backpropagation learning algorithm. In reverse through the system, the calculation begins with the weights among the output layer PE's and the last hidden layer PE's and works. Once back propagation has fulfilled, the forward procedure begins once more, and this cycle proceeds until the error among is predicted and actual output are reduced. Rather than back propagation algorithm, the Whale Optimization algorithm is displayed because it can acquire valuable output than

Recently a novel optimization algorithm named whale optimization algorithm (Mirjalili 2016) has been introduced to metaheuristic algorithm by Mirjalili and Lewis. As highly intelligent animals with motion, the whales are conceived. The WOA is inspired by the unique hunting behavior of humpback whales. The humpback whales prefer to hunt krills or small fishes which are close to the surface of sea at normally. Humpback whales use a special unique hunting method named bubble net feeding method. In this method they swim around the prey and produce distinctive bubbles along a circle or 9-shaped path. The mathematical model of WOA is described in the following sections a) Encircling prey b) Bubble net hunting method

The proposed Adaptive Artificial Neural Network model is given in below Figure 2.

back propagation calculation.

132 Data Mining

a. Whale optimization approach

Figure 2. Proposed adaptive artificial neural network.

The algorithm is showed by arbitrarily generating the solutions (i.e. the interconnection weight values) that communicates to the result. Here the neural network structure comprising the interconnection weights among the hidden layers and the output layers are referred by the random value in the search space is afforded as:

$$\mathcal{W}\_{\mathfrak{m}} = \{\mathfrak{w}\_{\mathfrak{m},1}, \mathfrak{w}\_{\mathfrak{m},2}, \dots, \mathfrak{w}\_{\mathfrak{m},h}, \dots, \mathfrak{w}\_{\mathfrak{m},\mathbb{R}}\} \tag{6}$$

where, f g wm, <sup>1</sup>; ww,m;…; wm,h represents the set of weights among the input and hidden layer and f g wm,h;…; wm,R represents the set of weights among the input and hidden layer. Also, each solution, Wm ¼ f g wm, <sup>1</sup>; wm,2;…; wm, <sup>h</sup>;…; wm,R is a R-dimensional vector where R being the number of optimization parameters. And also start the coefficient vectors of whale such as, f ! , F ! , and G! .

Step 2: Fitness Calculation.

Determine the fitness of the input solutions on the basis of the Eq. (7). To get the best weight values, the fitness value of the solutions are computed. It's revealed in below,

$$Fit\_{W\_m} = \min\left(MSE\right) \tag{7}$$

The minimum of mean square error (MSE) determines that, how correct the network predicted targets are (i.e. high classification accuracy) in above equation. Hence, for further development, the initial solution with minimum error is chosen as best solution and checked.

Step 3: Update position of current solutions towards the best

### A. Encircling prey

The position of prey (i.e. the current best solution) is distinguished by humpback whale and then it encircles the prey. Towards the best search operator the other search operators will consequently attempt to update their positions when the best search agent is characterized. The updation method is determined by the below equations:

$$\overrightarrow{\mathbf{N}} = \left| \overrightarrow{\mathbf{G}} \cdot \overrightarrow{\boldsymbol{W}}\_{m}^{\mathrm{best}}(\mathbf{x}) - \overrightarrow{\mathbf{W}}\_{m}(\mathbf{x}) \right| \tag{8}$$

$$
\overrightarrow{W}\_m(\mathbf{x}+\mathbf{1}) = \overrightarrow{W}\_m^{\text{best}}(\mathbf{x}) - \overrightarrow{F} \cdot \overrightarrow{N} \tag{9}
$$

where 'Wm ! ð Þ x þ 1 ' denotes the newer solutions for next iteration, F ! and G ! denotes a Coefficient vector, W ! best <sup>m</sup> denotes a position vector for best solution, Wm ! ð Þx represents a current position Vector and jj represents an absolute value.

The vectors F ! and G ! are calculated as follows:

$$
\overrightarrow{F} = 2\,\,\overrightarrow{f} \cdot \overrightarrow{k} - \overrightarrow{f} \tag{10}
$$

$$
\vec{G} = \mathbf{2} \cdot \vec{k} \tag{11}
$$

than �1. In exploitation phase, the position of the search agent is updated. This mechanism

N ! ¼ G ! �W ! rand

Wm !

from 2 to 0, respectively. A random search agent is selected when F

 

ð Þ¼ x þ 1 W

selected search agent. In order to render exploration and exploitation the parameter 'f

of 'L', WOA is able to switch development either a circular or spiral movement.

on the back propagation error (i.e. the min MSE), which is the fitness function.

<sup>&</sup>gt; 1 emphasize exploration permit the WOA algorithm to perform a global search. The

<sup>m</sup> ð Þ� x Wm ! ð Þx

! rand

positions at each iteration with respect to either the best solution found so far or a randomly

The solutions are updated established on the best search agent between the current solutions found from the fitness evaluation step during each iteration. Again, at each time of generating newer weight values, it is aligned to the network and the fitness is determined and established

Once the optimal weights are generated for all the networks of the Mappers, the training of the networks is finished. Now the AANN becomes a classifier and it can be generalized to predict for newer data also. The output mapped networks are then forwarded to Reducer phase.

To create the optimal network structure, the WOA algorithm is finished when best weight values are found. Also, the satisfaction of a termination criterion is confirmed when the mean square error is decreased to the needed limit or when the maximum iteration is attained.

Once the optimal weights are rendered for all the networks of the Mappers, the training of the networks is completed. Now the AANN gets a classifier and it can be generalized to predict for

A Reducer accepts the data element of each Mapper for each Reducer task. With the same intermediate key, and a Reducer function merges all intermediate values connected. Established on the requirement, the Reducers can be customized. The proposed healthcare analysis model needs only one Reducer for improving a classifier model that must separate the patient's medical records. Here, the Reducer task is to form a robust classifier model from the parallely trained network models. Since the Reducer results in only one classifier network model, it will average all the maximized weight results for each interconnection links found for each training item and find the final optimal weights of the classifier. Here the analyzing

newer data also. The output mapped networks are then forwarded to Reducer phase.

<sup>m</sup> ð Þ�x F ! � N !

rand xð Þ is a current population random position vector. Search agents update their

<sup>&</sup>lt; 1 for the position of the search agents for updating. Depending on the value

 

Adaptive Neural Network Classifier-Based Analysis of Big Data in Health Care

http://dx.doi.org/10.5772/intechopen.77225

!  (14)

135

(15)

!

<sup>&</sup>gt; 1, while the best solution

' is reduced

and F ! 

where, Wm !

is chosen when F

! 

Step 4: Termination criteria.

3.5. Phase 3: Reducer phase

mathematical model is afforded below:

where, f ! is linearly reduced from 2 to 0 during the course of iterations (in both exploration and exploitation phases), k ! ∈ð Þ 0; 1 .

### B. Bubble-net attacking method (exploitation phase)

To model the bubble-net behavior of humpback whales mathematically two approaches developed are a) Shrinking encircling mechanism and b) Spiral updating position

### a. Shrinking encircling mechanism

The value of f ! in the Eq. (10) is reduced to attain this behavior. Note that f ! is applied to reduce the variation range of, F ! . In other words, where f ! is minimized from 2 to 0. The novel position of a search agent can be determined anywhere by setting the random value, F ! from ½ � �1; 1 .

### b. Spiral updating position

A spiral equation among the position of whale and prey is produced to mimic the helix-shaped movement of humpback whales is as follows:

$$\overrightarrow{W}\_{m}\left(\mathbf{x}+\mathbf{1}\right) = N\left.\mathbf{x}\mathbf{p}^{pq}\cdot\cos\left(2\prod\_{i}q\right) + \overrightarrow{W}\_{m}^{\text{best}}\left(\mathbf{x}\right)\right.\tag{12}$$

where N<sup>0</sup> ¼ W ! best <sup>B</sup> ð Þ� x Wm ! ð Þx � � � � � � � � and denotes the distance of the Bth whale (which is the best solution obtained so far) to the prey, q is the random value from, ½ � �1; 1 , p denotes the shape of the logarithmic spiral and it is a constant value. During maximization the position of whales is updated by assuming a probability of 50% by choosing either the spiral model or shrinking encircling mechanism to model this simultaneous behavior. The mathematical model is afforded by Eq. (13).

$$
\overrightarrow{\dot{W}}\_{m}(\mathbf{x}+1) = \begin{cases}
\overrightarrow{\dot{W}}\_{m}^{\text{best}}(\mathbf{x}) - \overrightarrow{\dot{F}} \cdot \overrightarrow{N} \; \mathsf{,} & \text{if } L < 0.5 \\
\text{N}^{'}.\text{exp}^{\text{vq}} \cdot \cos\left(2\prod q\right) + \overrightarrow{\dot{W}}\_{m}^{\text{best}}(\mathbf{x}), & \text{if } L \ge 0.5
\end{cases} \tag{13}
$$

where, L∈½ � 0; 1 . The humpback whales search for prey randomly to form bubble net.

c. Search for prey (exploration phase)

To search for prey in exploration phase, the same search approach applied in the exploitation phase established on the variation of the F ! vector can be applied. In fact, allowing to the position of each other humpback whales search randomly. Therefore, to force search agent to move so far from a reference whale we use F ! with the random values greater than 1 or less than �1. In exploitation phase, the position of the search agent is updated. This mechanism and F ! <sup>&</sup>gt; 1 emphasize exploration permit the WOA algorithm to perform a global search. The mathematical model is afforded below:

$$\stackrel{\rightarrow}{N} = \left| \stackrel{\rightarrow}{G} \cdot \stackrel{\rightarrow}{W}\_{m}^{rand} \left( \mathbf{x} \right) - \stackrel{\rightarrow}{W}\_{m} \left( \mathbf{x} \right) \right| \tag{14}$$

$$
\stackrel{\rightarrow}{W}\_{m}(\mathbf{x}+\mathbf{1}) = \stackrel{\rightarrow}{W}\_{m}^{rand}(\mathbf{x}) - \stackrel{\rightarrow}{F} \cdot \stackrel{\rightarrow}{N} \tag{15}
$$

where, Wm ! rand xð Þ is a current population random position vector. Search agents update their positions at each iteration with respect to either the best solution found so far or a randomly selected search agent. In order to render exploration and exploitation the parameter 'f ! ' is reduced from 2 to 0, respectively. A random search agent is selected when F ! <sup>&</sup>gt; 1, while the best solution is chosen when F ! <sup>&</sup>lt; 1 for the position of the search agents for updating. Depending on the value of 'L', WOA is able to switch development either a circular or spiral movement.

The solutions are updated established on the best search agent between the current solutions found from the fitness evaluation step during each iteration. Again, at each time of generating newer weight values, it is aligned to the network and the fitness is determined and established on the back propagation error (i.e. the min MSE), which is the fitness function.

Step 4: Termination criteria.

The vectors F

134 Data Mining

where, f !

The value of f

where N<sup>0</sup>

!

exploitation phases), k

and G !

!

!

movement of humpback whales is as follows:

<sup>B</sup> ð Þ� x Wm ! ð Þx

> Wm !

c. Search for prey (exploration phase)

phase established on the variation of the F

move so far from a reference whale we use F

Wm !

ð Þ¼ x þ 1

a. Shrinking encircling mechanism

!

b. Spiral updating position

¼ W ! best

� � � �

the variation range of, F

∈ð Þ 0; 1 . B. Bubble-net attacking method (exploitation phase)

are calculated as follows:

F ! ¼ 2 f ! � k ! � f !

oped are a) Shrinking encircling mechanism and b) Spiral updating position

. In other words, where f

ð Þ¼ <sup>x</sup> <sup>þ</sup> <sup>1</sup> <sup>N</sup><sup>0</sup>

W ! best

8 ><

>:

N0

<sup>m</sup> ð Þ�x F ! � N !

where, L∈½ � 0; 1 . The humpback whales search for prey randomly to form bubble net.

� � � �

of a search agent can be determined anywhere by setting the random value, F

G ! ¼ 2� k !

To model the bubble-net behavior of humpback whales mathematically two approaches devel-

!

A spiral equation among the position of whale and prey is produced to mimic the helix-shaped

solution obtained so far) to the prey, q is the random value from, ½ � �1; 1 , p denotes the shape of the logarithmic spiral and it is a constant value. During maximization the position of whales is updated by assuming a probability of 50% by choosing either the spiral model or shrinking encircling mechanism to model this simultaneous behavior. The mathematical model is afforded by Eq. (13).

:exppq � cos 2 <sup>Q</sup>ð Þþ <sup>q</sup> <sup>W</sup>

To search for prey in exploration phase, the same search approach applied in the exploitation

position of each other humpback whales search randomly. Therefore, to force search agent to

!

!

:exppq � cos 2Y<sup>q</sup>

� �

þ W ! best

and denotes the distance of the Bth whale (which is the best

, if L < 0:5

<sup>m</sup> ð Þx , if L ≥ 0:5

vector can be applied. In fact, allowing to the

with the random values greater than 1 or less

! best

in the Eq. (10) is reduced to attain this behavior. Note that f

is linearly reduced from 2 to 0 during the course of iterations (in both exploration and

(10)

(11)

!

!

<sup>m</sup> ð Þ<sup>x</sup> (12)

is minimized from 2 to 0. The novel position

is applied to reduce

from ½ � �1; 1 .

(13)

Once the optimal weights are generated for all the networks of the Mappers, the training of the networks is finished. Now the AANN becomes a classifier and it can be generalized to predict for newer data also. The output mapped networks are then forwarded to Reducer phase.

To create the optimal network structure, the WOA algorithm is finished when best weight values are found. Also, the satisfaction of a termination criterion is confirmed when the mean square error is decreased to the needed limit or when the maximum iteration is attained.

Once the optimal weights are rendered for all the networks of the Mappers, the training of the networks is completed. Now the AANN gets a classifier and it can be generalized to predict for newer data also. The output mapped networks are then forwarded to Reducer phase.

### 3.5. Phase 3: Reducer phase

A Reducer accepts the data element of each Mapper for each Reducer task. With the same intermediate key, and a Reducer function merges all intermediate values connected. Established on the requirement, the Reducers can be customized. The proposed healthcare analysis model needs only one Reducer for improving a classifier model that must separate the patient's medical records. Here, the Reducer task is to form a robust classifier model from the parallely trained network models. Since the Reducer results in only one classifier network model, it will average all the maximized weight results for each interconnection links found for each training item and find the final optimal weights of the classifier. Here the analyzing data's (i.e. the unknown/newer data) are separated in the minimized AANN classifier model found from the Reducer phase.
