Facial expression recognition based on active region of interest using deep learning and parallelism

Proposed methodology in general

In completing data processing, the following three phases are needed to work together. The three phases are (a) pre-processing of data; (b) training of classified data, and (c) testing of classified data. Figure 1 shows the flow diagram and illustrates the details of all the used steps. During the recognition process, these are followed. Phase-1 begins by accepting an input image into the system and it ends by detecting AROI. In phase-2, OAROI is detected first from the identified AROIs and then the training data sets are prepared for completing the testing in phase-3. Three operations are carried out in phase-3. The operations are (i) testing based on the OAROI data set, (ii) completion of the feature extraction training data being trained, and finally, (iii) classification of FER is completed.

a. Pre-processing of data

In pre-processing of data, images are being fed as input into the system and the required filtering techniques are applied. We applied weighted vector directional filter (WVDF) (Hossain, Samanta & Sanyal, 2012c) and SPAM filter (Shiqing et al., 2019). The mentioned filters are applied to minimize noises from the image. Moreover, pose estimation and rotation of an image for normalization are done as per requirement. To detect accurate facial expressions, pose estimation is an important aspect. Thus, the famous Adaptive Sinusoidal Head Model (ASHM) (Mohammad & Assiri, 2020) is applied, and it will be explained in detail in ‘Rotation using the Spatial Normalization Method’.

Now, it is necessary to detect landmarks points in the face image. These landmark points are known as POIs and Regions of Interest (ROIs) as shown in Fig. 2. Figure 2 depicts the AROIs. Four AROIs are taken to experiment out results. We gained the maximum accuracy in recognition from these four AROIs.

Then a segmentation method is applied to divide a face image into 4 classes and 8 regions as shown in Fig. 3. The classes are the forehead, eyes, nose, and mouth areas, where every class is divided vertically into two halves.

The face image is segmenting an image into four classes and eight regions. We have chosen AROI from those segmented regions. These AROIs are nose-tip (A), left eye (B), right eye (C), and lip (D) as shown in Fig. 2.

Rotation using the spatial normalization method

It is found that a few images are askew due the motion of the camera. This would have affected the accuracy of recognition. To get rid of this situation and improve the approximation, we apply a head-pose estimation algorithm, called ASHM (Hossain & Assiri, 2020a). It has been shown (Hossain & Assiri, 2020a) that with ASHM, better results are achieved. We applied an adaptive sinusoidal head model (ASHM) to recognize and correct the head pose. We also applied PDF (Probability Density Function) along with ASHM. The Pose Matrix Pm was constructed first from the frame. The pose vector has a Rotation Matrix (Rm) and Transformations Matrix (Tm) for each frame, f. Each pose vector has an Rm and a Tm. i.e., (1)${\displaystyle P_m=\left[\begin{array}{cc}{R}_m\hfill & T_m\hfill \\ {T_m}^T\hfill & 1\hfill \end{array}\right]=\left[P_{m_1}\right]\left[P_{m_2}\right]\left[P_{m_3}\right]\left[P_{m_4}\right]}$ where Rm ∈ Rm_(8×8) and Tm ∈Rm_(8×1) are vectors after transformations by Tm. Pm₁, Pm₂, Pm₃, and Pm₄ are pose vectors.

The ASHM is applied to all frames starting from frame 1. In this way, by accessing all the frames, accurate features are attained from the trained images. We applied the LKT (Lucas Kanade Tracker) algorithm in the process of features extraction. These features have a straight association to the segmented classes. The identified AROIs are directly associated with head motion. However, it is necessary to apply the appropriate projection technique depending on the model of the camera. So a connotation can be established between a 3-D and a 2-D image plane.

Figure 4 illustrates an association among the 3-D points (indicated by a = (x, y, z)^T_m on the sinusoidal area) and its prediction point (indicated by b = (p, q)^T_m) on the image plane. Here (p & q) are evaluated following the Eqs. (2) and (3). (2)${\displaystyle p=d\frac{x}{z}}$ (3)${\displaystyle q=d\frac{y}{z}.}$

where d is the foretold distance from camera. Meanwhile 2-D features ensure different inferences in constructing pose-related information, two factors have a direct relation to feature extraction:

1. Intensity of features.

2. Applied tracking method in 3-D form.

Moreover, to overcome this situation, a rotation correction algorithm is incorporated. The positions of that part of AROIs maybe eyes, maybe lips, or both.

Figure 5 shows the original image without any alteration. Figure 6 shows the image after rotation of 3.1% required for normalization. Figure 7 shows the connection between two eye-lids. They are associated by a red line over the horizontal axis. It is used to achieve the adjusted pose. Figure 8 shows the image after rotation & normalization. Indeed, the angle in the middle of the two lines must be corrected. We applied the rotation and normalization method to gain the proper pose. In this process, 3.1% rotation is required to connect two eyelids. It is as shown through Figs. 5–8 respectively. The process of rotation has been demonstrated in the following paragraph.

Let (x1, y1) and (x2, y2) be left-eye and right-eye centers. Now let us calculate the angle θ by applying the equation no 1. So the image needs to be rotated to the extent of θ. (4)${\displaystyle \theta =tan\left(\frac{y_2-y_1}{x_2-x_1}\right).}$

Equation (4) is for rotation by the angle θ. The face-image size may vary after rotation. In this situation, a difficulty arises in classifying FER with increased accuracy. During rotation, if there exists a huge background part of the face area then a problem may arise. Although, the background part has less significance in recognizing facial expressions. As a consequence, we used the Spatial Normalization Method (SNM) to normalize the AROI areas of the face. The SNM is carried out based on a central point (the nose tip) of the face image. Let the length of the facial AROI be ∞ and the width is β. In this literature, it is set that ∞ = β = 120 pixels. Figure 6 shows the association between both left eyes of the face image and rotation is applied as required. After the SNM, facial POIs and the AROIs are spotted once more.

Figure 9 explains how the AROIs are being scaled. Here ellipse shape is considered. We considered geometric shape because it becomes easy to scale all the required parts of a human face. In this manuscript, three active regions (AROIs) have been taken for our experiment.

Optimized active region of interest (OAROI) searching

The AROIs are detected based on four classes of segregation. The researchers (Hossain & Assiri, 2020a; Clark et al., 2020; Lopes et al., 2017) proposed that few regions are not active at all. Scholars (Lopes et al., 2017) separated a face area into 8*8 patches. They select active regions from 64 patches. These active patches are found within the eyes, nose, and mouth regions. It is a patch-based method only. The identified AROIs are shown in Fig. 9. The strong features are found in the AROIs. The strong features is considered by its feature weight because they yield more trustworthy information. The feature weights are extracted from nose tip, left eye, right eye, and lip regions and they are named FWA, FWB, FWC, and FWD respectively. The achieved feature-weights are as follows:

• Nose-tip FWA (24, 25, 26, 28, 29) = 0.0286943

• Left Eye FWB (30, 31, 32, 33, 34, 35, 36, 37) = 0.0129583

• Right Eye FWC(39,40,41,42,43,44,45,46,47) = 0.0173181

• Lip FWD(48,49,50,51,52,53,54,55) = 0.0319725

In the experiment, similarity amongst the similar AROIs of dissimilar expressions differs based on their sizes. During the choice of AROI, an optimized technique is applied so that those active AROIs should be chosen where maximum similarity is matched with the sizes of the regions. A searching method is applied so that the Optimized AROIs are found directly. In doing this, the hash distance (Lopes et al., 2017) algorithm is applied. There is a well-established rule concerning hash distance. There is a thumb rule that if the hash distance is smaller then similarity should be greater. The algorithm-1 is used to estimate the hash distance between two images.

Algorithm 1: Measurement of Hash Distance

Input: 2 images

Output: Measured Hash Distance between 2 images

1. Find AROIs (Nose-tip, Left-eye, Right-eye and Lip regions)

2. Choose Central-point (Nose-tip)

3. Resize images to 120*80

4. Convert image from RGB to gray.

5. Compute Mean value (MV) from gray image

6. Set POI = 1; if MV > = average, otherwise POI = 0.

7. Output will be the Hamming Distance based on a new gray value (0 or 1).

The following symbols are introduced to illustrate the optimized searching method. Let I = {1, 2, 3, 4,…,7} be the no of subjects in (CK + & JAFFE) image data sets. Here [J = {1, 2, 3, 4, 5}] are five expressions. (i.e., 1 if for Normal; 2 is for Happy; 3 is for Fear; 4 is for Surprise; and 5 is for Disgust). Set Eij, i ∈ I, j ∈ J. This implies that the ith subject with jth expression.

Here [C = {Left-eye, Right-eye, Lip regions}] denotes the classes of AROIs. Lc is equal to {1,2, …, bound_c} where c ∈ C which is taken as radius of AROIs. Its size is c. After measuring size we estimate the boundary as named bound_c. There are four directions D = {1, 2, 3, 4} identified as 1 is on left, 2 is on right, 3 is on top, and 4 is on bottom. Here ${\text{Disc}}_{ij}^{cd}$ ${\text{Disc}}_{ij}^{cd}$ as equal to the distance amongst the midpoint of c on the direction D over Eij. For simplification of ${\text{Disc}}_{ij}^{cd}$ we took c as left eye distance as shown in Fig. 10. Here c (left eye distance) is the distance amongst the midpoint of left eye and around POIs. The ${\text{Disc}}_{ij}^{c2}$, ${\text{Disc}}_{ij}^{c3}$, and ${\text{Disc}}_{ij}^{c4}$ are the distances amongst the midpoint of left eye’s left-edge, right-edge, top-edge and, bottom-edge, respectively. Here c (right eye distance) is the distance amongst the midpoint of right eye and around POIs. The ${\text{Disc}}_{ij}^{c2}$, ${\text{Disc}}_{ij}^{c3}$ and ${\text{Disc}}_{ij}^{c4}$ are the distances amongst the midpoint of right eye’s left-edge, right-edge, top-edge, and bottom-edge, respectively. In case of mouth it is measured by ${\text{Disc}}_{ij}^{cd}$ d ∈ D and the distances amongst the midpoint of mouth and its 4 edges are measured by Eij. The bound_c is measured by Eq. (2). (5)${\displaystyle {\text{bound}}_c=\underset{i,j,d}{min}\left({\text{Disc}}_{ij}^{cd}\right),i\in I,j\in J,d\in D.}$

Let $R_{ij}^{c1},c\in C,1\in L_c$ be the region size which is equal to l. Here $Has{h}_i^{c1},c\in C,1\in L_c$ ${\text{Hash}}_{\mathrm{i}}^{\mathrm{cl}},\mathrm{c}\in \mathrm{C},\mathrm{l}\in {\mathrm{L}}_{\mathrm{c},}$ is the summation of distance amongst all c regions of subject i with a size of l. It is measured by Eq. (3). (6)${\displaystyle {\text{Hash}}_i^{c1}=\sum _{x\ne y}\text{Algorithm}1\left(R_{ix}^{c1},R_{iy}^{c1}\right).}$

Here x & y ∈ J. In order to match the c regions with i and size is l, we incorporated the following equation no 7. (7)${\displaystyle {\text{Sim}}_i^{c1}=\frac{1}{Has{h}_i^{c1}+1},c\in C,1\in L_c.}$

Let Sim^c1 be Sim^cl the average of ${\mathrm{Sim}}_i^{c1}$ among the 4 subjects. Where Sim^c1 Sim^cl is the matching among c regions with size is equal to l. In lieu of individually c ∈ C, we took the size l to have maximum Sim^c1in our experiment.

We have incorporated a searching method in detail is shown in Algorithm 2. During our experiment, we took 35 images from the CK + and 10 JAFFE databases, i.e., Eij, i ∈I, j ∈J. To get proper output, the image sizes are kept the same (640×800) for all kinds of images.

Algorithm 2: Searching for the OAROI

Input: 45 (35 + 10) images selected from CK++ and JAFFE database

Output: the sizes of OAROI

1. for c in C

2. Compute bound_c.

3. for i in I

4. for l in L

5. Compute $Has{h}_i^{c1}$

6. Compute ${\mathrm{Sim}}_i^{c1}$

7. Compute the MV of ${\mathrm{Sim}}_i^{c1}$ ${\mathrm{Sim}}_{\mathrm{i}}^{\mathrm{cl}}$ amongst 7 subjects and acquire Sim^c1.

8. In drawing the picture of Sim^c1, let l be start value of X-axis and Sim^c1 be value of Y-axis.

9. Catch the size l from max value of Sim^c1 andrecord the output.

Based on the Algorithm 2 the required picture will be following the step h. This is shown in Fig. 11. The sizes for the right-eye, left-eye, and lip regions are set to 160 × 120, 160 × 120, and 180 × 80 pixels. We found that the obtained size is half of the edge length of the OAROIs. As an outcome, the edge sizes of 3 kinds of OAROIs have been set to 140 × 80, 140 × 80, and 160 × 60 pixels, respectively. The OAROIs are shown in Fig. 9. It is found almost all active POIs are around the nose regions. For this reason, the nose region is kept aside of our experiment.

Parallel face and facial AROI detection

One of the emergent objectives of this research is to speed up the process of facial expression with improved recognition accuracy. As stated earlier (shown in Fig. 1) the whole process is into three phases: Data processing, training, and testing of classified data. The data processing phase is executed in sequential order. In the first phase, images are recognized and then the following are carried out namely-pre-processing, POI detection, head-pose adjustment using rotation and ASHM method, image segmentation and AROI detection. Lastly, OAROI is identified based on our proposed searching method. The usage of OAROIs rather than the entire face helps us reduce data processing time and speed up processing of the first phase. The last two phases run in parallel since each ORAOI (namely the left-eye, right-eye, and lip region) is identified separately in parallel. This technique reduces the execution time for these two phases by 64% (approx) as shown in the experimental results. As per experimental calculation, only 1% of the total execution time is needed to complete the first phase and the last two phases took 99% (approx) of the total execution time. In applying parallelism, the system is three times faster. In calculating the required time in parallel processing we applied the famous formula of Amdahl’s Law (Gustafson, 1988) as mentioned below through Eq. (8). (8)${\displaystyle \text{Speedup}=\left(\frac{1}{\left(1-P\right)+P/N}\right).}$ Where P is the part that runs in parallel that is 0.99 (in our system), and N is the number of processors i.e., 3. We use only three processors for simplification, as our system has 3 OAROIs and each one of them runs separately. Therefore, our parallel model is 2.94% faster, which is almost three times faster. We incorporated a Decision-Tree-Level Synthesis scheme that helps us to gain enhanced accuracy in recognition.

Classification by decision-tree-level synthesis

An emergent facial expression recognition technique demands a very high accuracy rate for recognition. In our study, the AROI-based CNN method is incorporated to extract features of the FER and their classification. Three OAROIs are chosen namely left-eye, right-eye, and lip regions. These three OAROIs are trained and classified in parallel using CNN. The final classification result is achieved which is remarkably higher by using the decision tree level synthesis technique. The schematic diagram (Fig. 12) depicts the applied technique.

The sizes of the optimized active regions (i.e., the inputs of CNN) are dissimilar for each images. To make the sizes the same, we completed the following actions.

1. Optimized active regions of interest are resized to 120*80 pixels.

2. The CNN-based convolution layers and its connected sub-layers were applied to input images to extract features-weight and features.

3. Lastly, the execution is completed based on fully connected layer.

The feature weights have been applied to the fully-connected-layers to achieve the desired expressions. The One-hot (1) code is applied to detect desired expression. In our experiment we used five classes of expressions (Normal, Happiness, Fear, Surprise, and Disgust) in this study. So the length of one-hot (1) code is equal to five. Individually, one bit of one-hot code represents one expression. The index of 1 resultant from one expression is displayed. The bit zero (0) means False (No) and one (1) means True (Yes).

In the last phase, the final expression recognition result is achieved based on the decision-level synthesis method. This decision-level synthesis method is carried out based on the following: ${\displaystyle \text{Final Output}=\left\{\begin{array}{c}j,if2\text{or more CNNs}\hfill \\ \text{classify the expression}\hfill \\ \text{as}j\forall j\in J\hfill \\ \text{Here CNN result over left\_}\text{eye, right\_}\text{eye}\&\text{lip regions},\hfill \\ \text{otherwise}0\hfill \end{array}\right.}$

In order to classify any expression we need two or more classifiers as stated in the above expression. Here a class is indicated by j for all j ∈ J. The final outcome will be measured based on the j only. On the other hand, it is revealed that the desired classification is completed based on 3 CNNs. We considered 5 expressions (namely-Normal, Smiley, Fear, Surprise, and Disgust) in our experiment. If two classified expressions are “Normal” then the synthesis result will be “Normal”. If the results of the three CNNs are different then we have to choose the CNN result based on the highest accuracy. This has been demonstrated in the “Experimental Section”. Figure 12 shows the schematic flow diagram of the feature weight that we already calculated earlier and have shown mathematically through the decision-level-synthesis method as illustrated above.

Used databases

The CK+ i.e., Extended Cohn-Kanade database contains 327 male and female images, and each of them has seven types of expression. Out of them, we use five (i.e., Normal, Happiness, Fear, Surprise, and Disgust) types in our experiment. To get the proper expression as a sample image, we select one from the last four frames in this experiment. The JAFFE image database comprises 213 facial expressions from 10 females and each of them has seven types of expression. However, we select five, i.e., Normal, Happiness, Fear, Surprise, and Disgust. In the JAFFE database, it is found that for each expression (subject), there are three images. The chosen images are kept in the database. We used all images from the JAFFE database in our experiments.

In this study, we took the images detectable naturally for our experimental work. In deep learning techniques, huge training data sets are needed to achieve better performance. The total volume of available data from both databases was not enough for CNN based training under the deep learning method. To yield more data, firstly the original image is flipped to horizontal. Secondly, histogram equalization is conducted on both flipped and original images. Lastly, they have been converted to gray and the pose estimation algorithm (PEA) is also applied. By applying the above scheme the total volume of data has increased by 8 times. Moreover, we applied the segmentation technique that has divided each image into four classes. In this way, the total volume of images became 32 times that of the original one. The OAROIs of all the images are saved in the info-image-data-mask database for training and testing. In addition, we also took the image sets separately as samples of two databases and trained them to classify them based on by Happy & Routray (2015) method. Our experimental result and the time of execution are better as compared to other researchers.

Tables 1 and 2 illustrate the performance of execution for normal expressions of two databases CK+ and JAFFE. Table 3 shows the average execution accuracy of 5 types of expression based on CK+ images. The last row of each table shows the average accuracy of each OAROI. Table 3 illustrates the performance of recognition for a selected image set of 35 images taken from the CK+ image database and their execution time in milliseconds in the sequential method. Table 4 demonstrates performance in recognition based on the CK+ image measured in millisecond. Table 5 shows the performance of recognition and their execution time in milliseconds by applying parallelism. The accuracy exceeds 91% in all cases and the average accuracy of the whole classification process reaches 96.23%.

Table 6 illustrates the average execution accuracy of Normal, Happiness, Fear, Surprise, and Disgust for JAFFE images and the accuracy of the proposed synthesis method (our model) in the process of OAROI detection. The last row of each table shows the average accuracy of each OAROI. The accuracy exceeds 88% in all cases and the average accuracy of the whole classification process reaches 96.23%.

Table 7 illustrates the performance of recognition for the selected image set of 10 images taken from the JAFFE image database and their execution time in milliseconds in the sequential method has been shown. In Table 8, with the same images, the performance of recognition and their execution time in milliseconds in the parallel method has been shown.

Moreover, Table 8 compares the ET in milliseconds for our proposed synthesis method (parallel execution) with the sequential one for the JAFFE image set. It shows the ET for our proposed parallel method reduces to 36.536% than that of a sequential method.

Used CNN structure and tenfold validation

The proposed CNN structure is shown in Fig. 13. In Fig. 12 it is shown that the system receives gray images as input with a fixed size of 120*80 pixels. Three CNN layers are offered along with AROIs. Here for each of them is interlinked via a sub-sampling layer. A relationship is built up by kernel sizes in CNN layers. The measurement of sub-sampling layers are 5 × 5 and 2 × 2, correspondingly. Every sub-sampling layer should be multiple of 2. In Fig. 13, it is being seen that the size after 1st convolution became 120*80*32. A similar method is applied to the rest of the following layers. There are 1,024 neurons in total. Each of two are fully connected. In this way, CNN helps us to gain better results. The performance is achieved based on the voting score of five dissimilar classified expressions. The output (shown in Fig. 13) is determined based on the number of dissimilar images. The proposed CNN structure (as shown in Fig. 13) illustrates how convolution works with the sub-sampling layer and fully connected layer.

Experiments on ten-fold cross-validation

We applied ten-fold cross-validation to calculate the performance of the proposed synthesis method and it is compared with its original CNN. Tables 9 and 10, Figs. 14 and 15 show the performance accuracy of each AROI. This performance is achieved based the proposed ten-fold cross-validation that we applied on two image datasets. Here we applied our proposed synthesis method. By using the CK+ image set the performance based on three CNNs (on left-eye, right-eye, and lip region) are 92.19%, 93.11%, and 95.86% respectively, whereas by using the JAFFE image set the performances are gained 90.207%, 91.042%, and 92.120% respectively. Our achievement is excellent as compared to other researchers (Zhang & Wang, 2020; Hossain & Sanyal, 2012b; Moghaddam, Akbarizadeh & Kaabi, 2019; Cheon & Kim, 2008; AlBdairi, Zhu & Mohammed, 2020). Moreover, our proposed synthesis method gained an excellent rate of higher accuracy, i.e., 94.499%, 95.439%, and 98.26% respectively in the CK+ set and 92.463%, 93.318%, and 94.423% respectively in the JAFFE image set. In contrast, the researchers (Happy & Routray, 2015) have conducted their experiments based on fused data from the CK+ and JAFFE databases, and their accuracies were 89.64% and 85.06% respectively, which are remarkably less than that of our results. Liu et al. (2016) achieved accuracies of 92.40% and 63.40% respectively. Zhong et al. (2012) used CSPL method and they used MNI and CK+ dataset with the accuracy of 73.53% and 89.89% respectively. Lee, Plataniotis & Ro (2014) applied SRC in their dataset MNI,JAFFE and CK+ and they achieved 93.81%,87.85% and 94.70% respectively. Mollahosseini, Chan & Mahoor (2016) achieved accuracies of 93.20% and 77.90% respectively. In their experimentation, they tried to locate active patches around the nose, mouth, and eye regions. Our achieved result is a robust one as compared to other researchers. Moreover, we can gain 2.8% higher accuracy by introducing a decision-level synthesis method. This confirms the effectiveness and robustness of our proposed method.

Discussion on the experimental results

The experiment was completed using OS-Window 7, Language- Python 3.6, Intel Core (TM) i7 with a CPU processing speed of 3.40 GHz with RAM size is 6 GB. It is a Laptop with 4 physical cores. The maximum amount of experimental time is spent for dataset training. We know that training a dataset in a deep learning method needs a longer time as compared to other techniques. Because training time is correlated with several factors, like the volume of the data, the model of a structure, calculating the power, and so on.

As per the information shown in Table 11, it is clear that the CK+ database takes more time than the JAFFE database because there are more images in the CK+ database with complex conditions. In addition, the same reason is applicable for the training time for the Info-image-data-mask database as compared with the independent databases. Indeed, the Info-image-data-mask database includes both images of two databases. Moreover, ten-fold cross-validation is also applied in our experiment to increase the volume of data sets. As a result of which we have acquired a huge volume of data which is necessary for deep learning methods for better result.

We did not use other dataset like the NVIE (Nada & Heyam, 2020; Cheon & Kim, 2008; Wang & He, 2013; Shen, Wang & Liu, 2013; Rajan et al., 2020) or fused database because of two reasons. Firstly, most of the NVIE image database contains thermal images. Secondly, it is not very reliable as it is found from the performance analysis results of researchers (Cheon & Kim, 2008; Wang & He, 2013; Shen, Wang & Liu, 2013) that results gained from NVIE dataset differ depending on the method used. Their result analysis have been shown with the Table 12. The Table 12 illustrates that the achieved results varies depending on applied methods based on same database i.e., NVIE. Whereas the JAFFE and CK+ are very authentic and filtered. So we have chosen these two image sets in our application. Moreover, we concentrated on the required time for execution, so, for these two reasons, we applied the CK+ and JAFFE datasets.

Due to a diverse experiment setting, it is not easy to make an impartial evaluation of the proficiency of dissimilar methods. AlBdairi, Zhu & Mohammed (2020) have proposed that their CNN-based deep learning method has achieved 96.9% accuracy in the verification of the human face. Rajan et al. (2020) have proposed their CNN and LSTM-based methods where they have used MMI, SFEW, and their dataset. They achieved the accuracy of 81.60%, 56.68%, and 95.21% respectively. Hossain, Samanta & Sanyal (2012c) trained their data for CNN and it took about 20 min. They used the CK+ database in their experiment. Their hardware configuration was an Intel Core i7 CPU of 3.4 GHz. Liu et al. (2016) trained their data by using eight-fold cross-validation. Their hardware configuration was 6 core with a processing speed of 2.4 GHz. Their experiment took about 8 days to complete. The comparison of performance and its result analysis with different researchers are shown in a tabular form. It is shown by the following Table 13.