Journal of Soft Computing Paradigm - June 2020
Latest Publications


TOTAL DOCUMENTS

54
(FIVE YEARS 54)

H-INDEX

6
(FIVE YEARS 6)

Published By Inventive Research Organization

2582-2640
Updated Saturday, 03 July 2021

2021 ◽  
Vol 3 (2) ◽  
pp. 123-134
Author(s):  
Pasumpon Pandian A.

One of the most common applications of deep learning algorithms is sentiment analysis. This study delivers a better performing and efficient automated feature extraction technique when compared to previous approaches. Traditional methodologies like surface approach will use the complicated manual feature extraction process, which forms the fundamental aspect of feature driven advancements. These methodologies serve as a strong baseline to determine the predictability of the features, and it will also serve as the perfect platform for integrating the deep learning techniques. The proposed research work has introduced a deep learning technique, which can be incorporated with feature-extraction. Moreover, this research work includes three crucial parts. The first step is the development of sentiment classifiers with deep learning, which can be used as the baseline for comparing the performance. This is followed by the use of ensemble techniques and information merger to obtain the final set of sources. As the third step, a combination of ensembles is introduced to categorize various models along with the proposed model. Finally experimental analysis is carried out and the performance is recorded to determine the best model with respect to the deep learning baseline.


2021 ◽  
Vol 3 (2) ◽  
pp. 110-122
Author(s):  
Vivekanadam Balasubramaniam

Facemask has become mandatory in all COVID-infected communities present across the world. However, in real-life situations, checking the facemask code on each individual has become a difficult task. On the other hand, Automation systems are playing a widespread role in human community to automate different applications. As a result, it necessitates the need to develop a dependable automated method to monitor the facemask code to benefit humans. Recently, deep learning algorithms are emerging as a fast growing application, which has been developed for performing huge number of analysis and detection process. Henceforth, this paper proposes a deep learning based facemask detection process for automating the human effort involved in monitoring process. This work utilizes an openly available facemask detection dataset with 7553 images for the training and verification process, which is based on CNN driven EfficientNet architecture with an accuracy of about 97.12%.


2021 ◽  
Vol 3 (2) ◽  
pp. 96-109
Author(s):  
Subarna Shakya

Renewable energy sources are gaining a significant research attention due to their economical and sustainable characteristics. In particular, solar power stations are considered as one of the renewable energy systems that may be used in different locations since it requires a lower installation cost and maintenance than conventional systems, despite the fact that they require less area. In most of the small generating stations, space occupancy is controlled by placing the equipment on an open terrace. However, for large-scale power generating stations, acres of land are required for installation. Human employers face a challenging task in maintaining such a large area of power station. Through IoT and data mining techniques, the proposed algorithm would aid human employers in detecting the regularity of power generation and failure or defective regions in solar power systems. This allows performing a quick action for the fault rectification process, resulting in increased generating station efficiency.


2021 ◽  
Vol 3 (2) ◽  
pp. 83-95

Recently, the feed-forward neural network is functioning with slow computation time and increased gain. The weight vector and biases in the neural network can be tuned based on performing intelligent assignment for simple generalized operation. This drawback of FFNN is solved by using various ELM algorithms based on the applications issues. ELM algorithms have redesigned the existing neural networks with network components such as hidden nodes, weights, and biases. The selection of hidden nodes is randomly determined and leverages good accuracy than conservative methods. The main aim of this research article is to explain variants of ELM advances for different applications. This procedure can be improved and optimized by using the neural network with novel feed-forward algorithm. The nodes will mainly perform due to the above factors, which are tuning for inverse operation. The ELM essence should be incorporated to reach a faster learning speed and less computation time with minimum human intervention. This research article consists of the real essence of ELM and a briefly explained algorithm for classification purpose. This research article provides clear information on the variants of ELM for different classification tasks. Finally, this research article has discussed the future extension of ELM for several applications based on the function approximation.


2021 ◽  
Vol 3 (2) ◽  
pp. 70-82
Author(s):  
Mugunthan S. R. ◽  
Vijayakumar T.

Extreme Learning Machine (ELM) is one of the latest trends in learning algorithm, which can provide a good recognition rate within less computation time. Therefore, the algorithm can sustain for a faster response application by utilizing a feed-forward neural network. In this research article, the ELM method has been designed with the presence of sigmoidal function of biases in the hidden nodes to perform the classification task. The classification task is very challenging with the existing learning algorithm and increased computation time due to the huge amount of dataset. While handling of the stochastic matrix for hidden layer, output provides the lower performance for learning rate and robustness in the determination. To address these issues, the modified version of ELM has been developed to obtain better accuracy and minimize the classification error. This research article includes the mathematical proof of sigmoidal activation function with biases of the hidden nodes present in the networks. The output matrix maintains the column rank in order to improve the speed of the training output weights (β). The proposed improved version of ELM leverages better accuracy and efficacy in classification and regression problems as well. Due to the inclusion of matrix column ranking in mathematical proof, the proposed improved version of ELM solves the slow training speed and over-fitting problems present in the existing learning approach.


2021 ◽  
Vol 3 (2) ◽  
pp. 55-69
Author(s):  
Rajesh Sharma ◽  
Akey Sungheetha

Performing dimensionality reduction in the camera captured images without any loss is remaining as a big challenge in image processing domain. Generally, camera surveillance system is consuming more volume to store video files in the memory. The normally used video stream will not be sufficient for all the sectors. The abnormal conditions should be analyzed carefully for identifying any crime or mistakes in any type of industries, companies, shops, etc. In order to make it comfortable to analyze the video surveillance within a short time period, the storage of abnormal conditions of the video pictures plays a very significant role. Searching unusual events in a day can be incorporated into the existing model, which will be considered as a supreme benefit of the proposed model. The massive video stream is compressed in preprocessing the proposed learning method is the key of our proposed algorithm. The proposed efficient deep learning framework is based on intelligent anomaly detection in video surveillance in a continuous manner and it is used to reduce the time complexity. The dimensionality reduction of the video captured images has been done by preprocessing the learning process. The proposed pre-trained model is used to reduce the dimension of the extracted image features in a sequence of video frames that remain as the valuable and anomalous events in the frame. The selection of special features from each frame of the video and background subtraction process can reduce the dimension in the framework. The proposed method is a combination of CNN and SVM architecture for the detection of abnormal conditions at video surveillance with the help of an image classification procedure. This research article compares various methods such as background subtraction (BS), temporal feature extraction (TFE), and single classifier classification methods.


2021 ◽  
Vol 3 (1) ◽  
pp. 47-54
Author(s):  
Mugunthan S. R.

Wide attention has been acquired by the field of wireless rechargeable sensor networks (WRSNs ) across the globe due to its rapid developments. Addressing the security issues in the WRSNs is a crucial task. The process of reinfection, charging and removal in WRSN is performed with a low-energy infected susceptible epidemic model presented in this paper. A basic reproductive value is attained after which the epidemic equilibrium and disease-free points of global and local stabilities are simulated and analyzed. Relationship between the reproductive value and rate of charging as well as the stability is a unique characteristic exhibited by the proposed model observed from the simulations. The WRSN and malware are built with ideal attack-defense strategies. When the reproductive value is not equal to one, the accumulated cost and non-optimal control group are compared in the sensor node evolution and the optimal strategies are validated and verified.


2021 ◽  
Vol 3 (1) ◽  
pp. 38-46
Author(s):  
Subarna Shakya

Navigation, aviation and several other fields of engineering extensively make use of rotating machinery. The stability and safety of the equipment as well as the personnel are affected by this machinery. Use of deep learning as the basis of intelligent fault diagnosis schemes has and investigation of other relevant fault diagnosis schemes has a large scope for development. Thorough exploration needs to be performed in deep neural network (DNN) based schemes as shallow layer network structure based fault diagnosis schemes that are currently available has several considerable limitations. The nonlinear problems may be processed during intelligent fault diagnosis using deep convolutional neural network, which is a special structure DNN. The convolutional neural network (CNN) based scheme is emphasized in this paper. The principle and basic structure of the model are introduced. In rotating machinery, the fault diagnosis schemes using CNN are analyzed and summarized. Various CNN schemes, the potential mechanisms and performance diagnosis are analyzed. A novel smart fault diagnosis strategy is proposed while highlighting the potential aspects of existing schemes and reviewing the challenges.


2021 ◽  
Vol 3 (1) ◽  
pp. 29-37
Author(s):  
Karuppusamy P

In the recent years, there has been a high surge in the use of convolutional neural networks (CNNs) because of the state-of-the art performance in a number of areas like text, audio and video processing. The field of remote sensing applications is however a field that has not fully incorporated the use of CNN. To address this issue, we introduced a novel CNN that can be used to increase the performance of detectors built that use Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG). Moreover, in this paper, we have also increased the accuracy of the CNN using two improvements. The first improvement involves feature vector transformation with Euler methodology and combining normalized and raw features. Based on the results observed, we have also performed a comparative study using similar methods and it has been identified that the proposed CNN proves to be an improvement over the others.


Export Citation Format

Share Document