Number Of Hidden Neurons Research Articles

A Deep Neural Network-Based Multi-Frequency Path Loss Prediction Model from 0.8 GHz to 70 GHz.

Large-scale fading models play an important role in estimating radio coverage, optimizing base station deployments and characterizing the radio environment to quantify the performance of wireless networks. In recent times, multi-frequency path loss models are attracting much interest due to their expected support for both sub-6 GHz and higher frequency bands in future wireless networks. Traditionally, linear multi-frequency path loss models like the ABG model have been considered, however such models lack accuracy. The path loss model based on a deep learning approach is an alternative method to traditional linear path loss models to overcome the time-consuming path loss parameters predictions based on the large dataset at new frequencies and new scenarios. In this paper, we proposed a feed-forward deep neural network (DNN) model to predict path loss of 13 different frequencies from 0.8 GHz to 70 GHz simultaneously in an urban and suburban environment in a non-line-of-sight (NLOS) scenario. We investigated a broad range of possible values for hyperparameters to search for the best set of ones to obtain the optimal architecture of the proposed DNN model. The results show that the proposed DNN-based path loss model improved mean square error (MSE) by about 6 dB and achieved higher prediction accuracy R2 compared to the multi-frequency ABG path loss model. The paper applies the XGBoost algorithm to evaluate the importance of the features for the proposed model and the related impact on the path loss prediction. In addition, the effect of hyperparameters, including activation function, number of hidden neurons in each layer, optimization algorithm, regularization factor, batch size, learning rate, and momentum, on the performance of the proposed model in terms of prediction error and prediction accuracy are also investigated.

A new variant of deep belief network assisted with optimal feature selection for heart disease diagnosis using IoT wearable medical devices

In this paper, the information related to heart disease using IoT wearable devices is collected from any benchmark site, which is publicly available. With the collected data, feature extraction process is performed initially, in which heart rate, zero crossing rate, and higher order statistical features like standard deviation, median, skewness, kurtosis, variance, mean, peak amplitude, and entropy are extracted. For acquiring most significant features, the optimal feature selection process is implemented. As a novel contribution, the feature selection process is done by the hybrid optimization algorithm called PS-GWO by integrating GWO and PSO. Next, the extracted features are subjected to a famous deep learning algorithm named modified DBN, in which the activation function and number of hidden neurons is optimized using the same developed hybrid algorithm to improve the heart diagnosis accuracy. From the analysis, for the test case 1, the accuracy of the developed PS-GWO-DBN is 60%, 52.5%, 35% and 35% increased than NN, KNN, SVM, and DBN. For test case 2, the accuracy of the proposed PS-GWO-DBN is 26%, 24%, 21.6% and 17% increased than NN, KNN, SVM, and DBN, respectively. The accuracy of the designed PS-GWO-DBN is 26% advanced than NN, 24% advanced than KNN, 21.6% advanced than SVM and 17% advanced than DBN for test case 3. Thus, the proposed heart disease prediction model using PS-GWO-DBN performs better than other classifiers.

Artificial neurovascular network (ANVN) to study the accuracy vs. efficiency trade-off in an energy dependent neural network

Artificial feedforward neural networks perform a wide variety of classification and function approximation tasks with high accuracy. Unlike their artificial counterparts, biological neural networks require a supply of adequate energy delivered to single neurons by a network of cerebral microvessels. Since energy is a limited resource, a natural question is whether the cerebrovascular network is capable of ensuring maximum performance of the neural network while consuming minimum energy? Should the cerebrovascular network also be trained, along with the neural network, to achieve such an optimum? In order to answer the above questions in a simplified modeling setting, we constructed an Artificial Neurovascular Network (ANVN) comprising a multilayered perceptron (MLP) connected to a vascular tree structure. The root node of the vascular tree structure is connected to an energy source, and the terminal nodes of the vascular tree supply energy to the hidden neurons of the MLP. The energy delivered by the terminal vascular nodes to the hidden neurons determines the biases of the hidden neurons. The “weights” on the branches of the vascular tree depict the energy distribution from the parent node to the child nodes. The vascular weights are updated by a kind of “backpropagation” of the energy demand error generated by the hidden neurons. We observed that higher performance was achieved at lower energy levels when the vascular network was also trained along with the neural network. This indicates that the vascular network needs to be trained to ensure efficient neural performance. We observed that below a certain network size, the energetic dynamics of the network in the per capita energy consumption vs. classification accuracy space approaches a fixed-point attractor for various initial conditions. Once the number of hidden neurons increases beyond a threshold, the fixed point appears to vanish, giving place to a line of attractors. The model also showed that when there is a limited resource, the energy consumption of neurons is strongly correlated to their individual contribution to the network’s performance.

Artificial intelligence for the compressive strength prediction of novel ductile geopolymer composites

Engineered Geopolymer Composites has proved to be an excellent eco-friendly strain hardening composite materials, as well as, it exhibits high tensile strain capacity. An intelligent computing tool based predictive model to anticipate the compressive strength of ductile geopolymer composites would help various researchers to analyse the material type and its contents; the dosage of fibers; producing tailor-made materials; less time consumption; cost-saving etc., which could suit for various infrastructural applications. This paper attempts to develop a suitable ANN based machine learning model in predicting the compressive strength of strain hardening geopolymer composites with greater accuracy. A simple ANN network with a various number of hidden neurons have been trained, tested and validated. The results revealed that with seventeen inputs and one output parameters respectively for mix design & compressive strength and thirteen hidden neurons in its layer have provided the notable prediction with R2 as 96% with the RMSE of 2.64. It is concluded that a simple ANN model would have the perspective of estimating the compressive strength properties of engineered geopolymer composite to an accuracy level of more than 90%. The sensitivity analysis of ANN model with 13-hidden neurons, also confirms the accuracy of prediction of compressive strength.

COVID-19 Death Risk Assessment in Iran using Artificial Neural Network

Since the pandemic spread of COVID-19, it has posed a unique public health concern worldwide due to its increased death rate all around the world. The pandemic disease is caused by the SARS-CoV-2, which is the main cause of Middle East Respiratory Syndrome (MERS) and severe acute respiratory syndrome (SARS). Risk assessment is a vital action toward disease risk reduction as it increases the understanding of the risk factors associated with the disease and allows existing data to decide on adequate preventive and mitigation measures. Machine learning techniques have gained strength since 2000, as it has crucial role in data analysis and is really helpful to develop standard mortality models. This study aims to find the best model for data analysis using the Artificial Neural Network (ANN) and other risk factors, which contribute to the high mortality and morbidity associated with COVID-19 in Iran, to predict the risk of death for the people with different situation. A systematic review and meta-analysis were examined by using patient risk factor data from studies done by researchers to estimate COVID-19 death risk. Risk factors for the disease were extracted from an existing study. Using ANN, the best risk prediction for the disease is calculated. Assessment of a different number of hidden neurons with a different training function using the Bayesian Regularization algorithm, the best training function for the ANN model with 5 hidden neurons is found to have the most satisfying results. The coefficient of determination (R) and Root Mean Square Error (RMSE) was 9.99999e-1 and 4.54201e-19 respectively.

Hybridization of harmonic search algorithm in training radial basis function with dynamic decay adjustment for condition monitoring

In recent decades, hybridization of superior attributes of few algorithms was proposed to aid in covering more areas of complex application as well as improves performance. Condition monitoring is a major component in predictive maintenance which monitors the condition and identifies significant changes in the machinery parameter to perform early detection and prevent equipment defects that could cause unplanned downtime or incur unnecessary expenditures. An effective condition monitoring model is helpful to reduce the frequency of unexpected breakdown incidents and thus, facilitates in maintenance. ANN has shown effective in various condition monitoring and fault detection applications. ANN is popular due to its capability of identifying the complex nonlinear relationships among features in a large dataset and hence, it can perform with an accurate prediction. However, a drawback is that the performance of ANN is sensitive to the parameters (i.e., number of hidden neurons and the initial values of connection weights) in its architecture where the settings of these parameters are subject to tuning on a trial-and-error basis. Hence, a wide range of studies have been focused on determining the optimal weight values of ANN models and the number of hidden neurons. In this research work, the motivation is to develop an autonomous learning model based on the hybridization of an adaptive ANN and a metaheuristic algorithm for optimizing ANN parameters so that the network could perform learning and adaptation in a more flexible way and handle condition classification tasks more accurately in industries, such as in power systems. This paper presents an intelligent system integrating a Radial Basis Function Network with Dynamic Decay Adjustment (RBFN-DDA) with a Harmony Search (HS) to perform condition monitoring in industrial processes. RBFN-DDA performs incremental learning wherein its structure expands by adding new hidden units to include new information. As such, its training can reach stability in a shorter time compared to the gradient-descent based methods. To achieve optimal RBFN-DDA performance, HS is proposed to optimize the center and the width of each hidden unit in a trained RBFN. By integrating with the HS algorithm, the proposed metaheuristic neural network (RBFN-DDA-HS) can optimize the RBFN-DDA parameters and improve classification performances from the original RBFN-DDA by 2.2% up to 22.5% in two benchmarks datasets, which are numerical records from a bearing and steel plate system and a condition-monitoring system in a power plant (i.e., the circulating water (CW) system). The results also show that the proposed RBFN-DDA-HS is compatible, if not better than, the classification performances of other state-of-the-art machine learning methods.

Dynamic binary neural networks with time-variant parameters and switching of desired periodic orbits

This paper studies 3-layer dynamic binary neural networks characterized by binary connection parameters and the signum activation function. The connection parameters and the number of hidden neurons are time-variant. The dynamics is described by a non-autonomous difference equation of binary state variables and the network can generate various periodic orbits of binary vectors. First, we present a simple synthesis method that guarantees storage of desired multiple periodic orbits and switching of the periodic orbits through desired entrances. Second, as a basic step to engineering applications, we present an FPGA based hardware prototype. The hardware can realize switching of various periodic orbits experimentally and typical examples are demonstrated. The switching of periodic orbits is applicable to switching of walking patterns in robotics and variable output of switching power converters.

Towards Accurate Diagnosis of Skin Lesions Using Feedforward Back Propagation Neural Networks.

In the automatic detection framework, there have been many attempts to develop models for real-time melanoma detection. To effectively discriminate benign and malign skin lesions, this work investigates sixty different architectures of the Feedforward Back Propagation Network (FFBPN), based on shape asymmetry for an optimal structural design that includes both the hidden neuron number and the input data selection. The reason for the choice of shape asymmetry was based on the 5–10% disagreement between dermatologists regarding the efficacy of asymmetry in the diagnosis of malignant melanoma. Asymmetry is quantified based on lesion shape (contour), moment of inertia of the lesion shape and histograms. The FFBPN has a high architecture flexibility, which indicates it as a favorable tool to avoid the over-parameterization of the ANN and, equally, to discard those redundant input datasets that usually result in poor test performance. The FFBPN was tested on four public image datasets containing melanoma, dysplastic nevus and nevus images. Experimental results on multiple benchmark data sets demonstrate that asymmetry A2 is a meaningful feature for skin lesion classification, and FFBPN with 16 neurons in the hidden layer can model the data without compromising prediction accuracy.

Using a 3‐Layer Artificial Neural Network to Predict S‐Nitrosylation

S-nitrosylation is a post-translational modification (PTM) in proteins that is critical for many biochemical processes in cells. Though experimental procedures exist for studying and determining S-nitrosylation, computer modeling presents a more convenient and cost-effective method to determine potential sites of nitrosylation. Previous studies have explored the use of different Machine Learning models to predict S-nitrosylation in proteins; however, the type of Machine Learning methods and the selection of input features that will yield the best predictive performance are still being studied. The goal of this project was to optimize the performance of a 3-layer Artificial Neural Network (ANN) using S-nitrosylation primary protein structure data. Primary structure data was taken from the dbSNO database, with each protein entry processed into instances of cysteines that were and were not S-nitrosylated. This entire dataset contained 4150 S-nitrosylation instances and 18506 non-S-nitrosylation instances, which was then split into a training set and a testing set at a ratio of 70:30, respectively. The performance of the 3-layer ANN was assessed via the Mathew Correlation Coefficient (MCC), Area Under the Receiver Operating Characteristic (AROC) curve, specificity, recall, accuracy, and precision values for the testing set. Mini-batch sizes, iterations per run, number of hidden neurons per layer, and other hyper-parameters were modified between runs to gauge improvements in the ANN performance. The 3-layer ANN was able to achieve an average MCC, AROC, specificity, recall, accuracy, and precision of 0.265, 0.685, 0.784, 0.467, 0.625, and 0.687, respectively with 50 neurons at both hidden layers, 150 iterations, learning rate of 0.05, 64-size mini-batch, and window size of 40. As the ANN's performance cannot be significantly improved beyond the metrics presented above, the addition of secondary structure sequence data from Protein Data Bank (PDB) files may improve the predictive performance of the 3-layer ANN and will be tested. The data presented above demonstrates the 3-layer ANN's predictive performance and suggests that the use of additional data, such as secondary structure, could allow for improvement.

Landslide Hazard Analysis Using a Multilayered Approach Based on Various Input Data Configurations

Landslide is a natural disaster that occurs mostly in hill areas. Landslide hazard mapping is used to classify the prone areas to mitigate the risk of landslide hazards. This paper aims to compare spatial landslide prediction performance using an artificial neural network (ANN) model based on different data input configurations, different numbers of hidden neurons, and two types of normalization techniques on the data set of Penang Island, Malaysia. The data set involves twelve landslide influencing factors in which five factors are in continuous values, while the remaining seven are in categorical/discrete values. These factors are considered in three different configurations, i.e., original (OR), frequency ratio (FR), and mixed-type (MT) data, which act as an input to train the ANN model separately. A significant effect on the final output is the number of hidden neurons in the hidden layer. In addition, three data configurations are processed using two different normalization methods, i.e., mean-standard deviation (Mean-SD) and Min-Max. The landslide causative data often consist of correlated information caused by overlapping of input instances. Therefore, the principal component analysis (PCA) technique is used to eliminate the correlated information. The area under the receiver of characteristics (ROC) curve, i.e., AUC is also applied to verify the produced landslide hazard maps. The best result of AUC for both Mean-SD and Min-Max with PCA schemes are 96.72% and 96.38%, respectively. The results show that Mean-SD with PCA of MT data configuration yields the best validation accuracy, AUC, and lowest AIC at 100 number of hidden neurons. MT data configuration with the Mean-SD normalization and PCA scheme is more robust and stable in the MLP model's training for landslide prediction. 
 Keywords: Landslide; ANN; Hidden Neurons; Normalization; PCA; ROC; Hazard map
 
 Copyright (c) 2021 Geosfera Indonesia and Department of Geography Education, University of Jember
 This work is licensed under a Creative Commons Attribution-Share A like 4.0 International License

Optimal feature selection with hybrid classification for automatic face shape classification using fitness sorted Grey wolf update

Depending on the prevailing researches, the classification of face shapes could be deployed for numerous applications. This paper intends to develop a new method for face shape classification using intelligent approaches. The presented method includes three stages namely, (i) Face Detection (ii) Pre-processing (iii) Feature extraction (iv) Classification. The face detection process is used for identifying the most significant objects in the face, probably eyes, nose, etc. which is done using the Viola-Jones algorithm. Moreover, the pre-processing stage includes the Histogram Equalization (HE) model for enhancing the contrast of the image. The classification of face shapes is performed by a hybrid classifier that links Convolutional Neural Network (CNN) and Neural Network (NN). For performing the CNN-based classification, the images are directly given as input. On the other hand, NN-based classification requires features as input. Hence, the pre-processed image is again subjected to the feature extraction process, where the features are extracted using the Active Appearance Model (AAM) and the Active Shape Model (ASM). For reducing the length of extracted features, the optimal feature selection process is adopted, which is done by improved Grey Wolf Optimization (GWO) algorithm. As the main contribution, the features, number of hidden neurons in the convolutional layer of CNN, and training of NN (weight update) is optimally chosen by improved GWO so-called as Fitness Sorted Grey Wolf Update (FS-GU) model. Finally, the average of two outcomes from both CNN, and NN provides the classified five categories of face shapes like heart, oblong, oval, round, and square. The performance of the proposed classification model is finally validated by comparing over the conventional models by analyzing the relevant performance metrics.

Li-ion battery temperature estimation based on recurrent neural networks

The monitoring of Li-ion battery temperatures is essential to ensure high efficiency and safety. In this work, two types of recurrent neural networks (RNNs), which are long short-term memory-RNN (LSTM-RNN) and gated recurrent unit-RNN (GRU-RNN), are proposed to estimate the surface temperature of 18650 Li-ion batteries during the discharging processes under different ambient temperatures. The datasets acquired from the Prognostics Center of Excellence (PCoE) of NASA are used to train, validate and test the networks. In previous work, temperature has been set as the output of the networks; however, here the temperature difference along the time axis is adopted as the output. The net heat generated results in net temperature change, which is more closely aligned with electrochemical and thermodynamic laws. Extensive simulation results show that the two RNNs can achieve accurate real-time battery temperature estimation. The maximum absolute error in temperature estimation is approximately 0.75°C and the correlation coefficient between the estimated and measured temperature curves is greater than 0.95. The influences of three crucial parameters, which are the number of hidden neurons, initial learning rate and maximum number of iterations, are also assessed in terms of training time, root mean square error and mean absolute error.

ON SOME BOUNDS OF THE MINIMUM EDGE DOMINATING ENERGY OF A GRAPH

Number of hidden neurons is necessary constant for tuning the neural network to achieve superior performance. These parameters are set manually through experimentation. The performance of the network is evaluated repeatedly to choose the best input parameters.Random selection of hidden neurons may cause underfitting or overfitting of the network. We propose a novel fuzzy controller for finding the optimal value of hidden neurons automatically. The hybrid classifier helps to design competent neural network architecture, eliminating manual intervention for setting the input parameters. The effectiveness of tuning the number of hidden neurons automatically on the convergence of a back-propagation neural network, is verified on speech data. The experimental outcomes demonstrate that the proposed Neuro-Fuzzy classifier can be viably utilized for speech recognition with maximum classification accuracy.

Artificial Neural Network Based Amharic Language Speaker Recognition

In this artificial intelligence time, speaker recognition is the most useful biometric recognition technique. Security is a big issue that needs careful attention because of every activities have been becoming automated and internet based. For security purpose, unique features of authorized user are highly needed. Voice is one of the wonderful unique biometric features. So, developing speaker recognition based on scientific research is the most concerned issue. Nowadays, criminal activities are increasing day to day in different clever way. So, every country should have strengthen forensic investigation using such technologies. The study was done by inspiration of contextualizing this concept for our country. In this study, text-independent Amharic language speaker recognition model was developed using Mel-Frequency Cepstral Coefficients to extract features from preprocessed speech signals and Artificial Neural Network to model the feature vector obtained from the Mel-Frequency Cepstral Coefficients and to classify objects while testing. The researcher used 20 sampled speeches of 10 each speaker (total of 200 speech samples) for training and testing separately. By setting the number of hidden neurons to 15, 20, and 25, three different models have been developed and evaluated for accuracy. The fourth-generation high-level programming language and interactive environment MATLAB is used to conduct the overall study implementations. At the end, very promising findings have been obtained. The study achieved better performance than other related researches which used Vector Quantization and Gaussian Mixture Model modelling techniques. Implementable result could obtain for the future by increasing number of speakers and speech samples and including the four Amharic accents.

Enhanced Facial Emotion Recognition by Optimal Descriptor Selection with Neural Network

Facial Emotion Recognition (FER) is the approach of detecting emotions of humans from facial expressions. Emotions are detected automatically by the human brain and hence, many computer aided techniques are implemented for recognizing emotions. Recognition of natural emotions is an exciting area with a broad range of real time applications like automated tutoring models, smart environments computer–human interaction, driver warning systems, and video and image retrieval. The major goal of this paper is to implement an intelligent model for FER. The proposed model involves few steps: (a) Face extraction (b) Image filtering, (c) Extraction of facial components, (d) Descriptor selection, and (d) Classification. Initially, the face is extracted from the input image by the Viola–Jones method, which is generally employed for the detection of object. Further, the noise of the image is filtered by the Gabor Filtering. Further, the facial components are extracted as features via the Affine-Scale-Invariant Feature Transform (ASIFT), which is the modified version of SIFT method. Since the length of the descriptors generated from ASIFT is high; the number of descriptors is reduced by the optimal descriptor selection approach with the aid of hybrid meta-heuristic algorithm termed as MV-WOA. The extracted descriptors are subjected to Neural Network (NN). As a modification to the existing machine learning algorithms, the number of hidden neurons in the NN is optimized by the proposed WOA+MVO algorithm. By conducting experiments, the results demonstrate that the developed system can perform better the recent traditional approaches for emotion recognition for classifying seven emotions like normal, smile, sad, surprise, anger, fear, and disgust.

Intelligent human action recognition using an ensemble model of evolving deep networks with swarm-based optimization

Automatic interpretation of human actions from realistic videos attracts increasing research attention owing to its growing demand in real-world deployments such as biometrics, intelligent robotics, and surveillance. In this research, we propose an ensemble model of evolving deep networks comprising Convolutional Neural Networks (CNNs) and bidirectional Long Short-Term Memory (BLSTM) networks for human action recognition. A swarm intelligence (SI)-based algorithm is also proposed for identifying the optimal hyper-parameters of the deep networks. The SI algorithm plays a crucial role for determining the BLSTM network and learning configurations such as the learning and dropout rates and the number of hidden neurons, in order to establish effective deep features that accurately represent the temporal dynamics of human actions. The proposed SI algorithm incorporates hybrid crossover operators implemented by sine, cosine, and tanh functions for multiple elite offspring signal generation, as well as geometric search coefficients extracted from a three-dimensional super-ellipse surface. Moreover, it employs a versatile search process led by the yielded promising offspring solutions to overcome stagnation. Diverse CNN–BLSTM networks with distinctive hyper-parameter settings are devised. An ensemble model is subsequently constructed by aggregating a set of three optimized CNN–BLSTM​ networks based on the average prediction probabilities. Evaluated using several publicly available human action data sets, our evolving ensemble deep networks illustrate statistically significant superiority over those with default and optimal settings identified by other search methods. The proposed SI algorithm also shows great superiority over several other methods for solving diverse high-dimensional unimodal and multimodal optimization functions with artificial landscapes.

Application of Nonlinear Autoregressive Neural Network to Model and Forecast Time Series Global Price of Bananas

The primary purpose of this study was to apply the nonlinear autoregressive neural network to model the long-term records of monthly global price of bananas from January 1990 to November 2020. The development of the optimal architecture for the nonlinear autoregressive neural network requires determination of time delays, the number of hidden neurons, and an efficient training algorithm. Through training of the nonlinear autoregressive neural network models, the prediction performance of the models was evaluated by its mean squared error value, the average squared difference between the observed and predicted values. In this study, the empirical results revealed that the NAR-BR model with 13 neurons in the hidden layer and 6 time delays provided the best performance at its smaller mean squared error value and yielded higher accuracy than the NAR-LM model with 12 neurons in the hidden layer and 4 time delays and NAR-SCG model with 12 neurons in the hidden layer and 6 time delays. Understanding past global price of bananas is important for the analyses of current and future global price of bananas changes. In order to sustain these observations, research programs utilizing the resulting data should be able to improve our understanding and narrow projections of future global price of bananas significantly.

Intelligent controller Design based on wind-solar system

This paper presents an Intelligent controller designed to mastery the output power flow from the Solar System, the Wind system, the sum of the two systems or from the battery system, according to the Maximum power point tracking algorithm, to ensure the continuity of the output power at fast time response. The proposed controller has been designed using MATLAB m-file and trained with the different number of hidden neurons using two different algorithms to get as fast a response time with minimum Mean Square Error (MSE) as possible which resulted in six hidden neurons using Levenberg-Marquardt training algorithms.

Accurate Prediction of Concentration Changes in Ozone as an Air Pollutant by Multiple Linear Regression and Artificial Neural Networks

This study considers the usage of multilinear regression and artificial neural network modelling to forecast ozone concentrations with regard to weather-related indicators (wind speed, wind direction, relative humidity and temperature). Initial data were obtained by measuring the meteorological parameters using the PC Radio Weather Station. Ozone concentrations near high-voltage lines were measured using RS1003 and at a 220 m distance using ML9811. Neural network models such as the multilayer perceptron and radial basis function neural networks were constructed. The prognostic capacities of the designed models were assessed by comparing the result data by way of the square of the coefficient of multiple correlations (R2) and mean square error (MSE) values. The number of hidden neurons was optimised by decreasing an error function that recorded the number of units in the hidden layers to the precision of the expanded networks. The neural software IBM SPSS 26v was used for artificial neural network (ANN) modelling. The study demonstrated that the linear regression modelling approach was lacking in its capacity to predict the investigated ozone concentrations by used parameters, whereas the use of an ANN offered more precise outcomes. The conducted tests’ results established the strength of the designed artificial neural network models with irrelevant differences between detected and forecasted data.

Influence of conditional holoentropy-based feature selection on automatic recommendation system in E-commerce sector

This paper presents a new contribution to the recommendation system following E-commerce reviews. Here, it implements a dictionary-based sentiment analysis based on four main steps (i) Pre-processing (ii) Semantic word extraction (iii) Feature Extraction (iv) Classification. Initially, the tweets or reviews extracted from the database are subjected to pre-processing, which involves three processes: stop word removal, stemming, and blank space removal. In the semantic word extraction process, the semantic words from the dictionary will be extracted by matching with the extracted keywords. The next process is the feature extraction, which extracts joint holoentropy and cross holoentropy of all keywords, and further proceeds with conditional holoentropy-based feature selection process. Finally, the selected features are subjected to a classification process using Deep Belief Network (DBN), which is a well-performing deep learning algorithm. Moreover, the main contribution of the paper relies on the improvement of DBN architecture, where the number of hidden neurons and activation function is optimally tuned by a hybrid optimization algorithm termed as Grey linked Chick Update-based Chicken Swarm Optimization (GCU-CSO). At last, the comparative analysis of proposed and conventional algorithms in terms of various performance metrics proves the efficacy of the proposed E-commerce recommendation system.