Recent Advances in Computer Science and Communications - Volume 15, Issue 3, 2022

Background: Fog computing paradigm has recently emerged and gained increasing attention in the present era of the Internet of Things. The growth of a large number of devices all around, leads to the situation of the flow of packets everywhere on the Internet. To overcome this situation and to provide computations at network edge, fog computing is the need of the present time that enhances traffic management and avoids critical situations of jam, congestion etc. Methods: For research purposes, there are many methods to implement the scenarios of fog computing i.e. real-time implementation, implementation using emulators, implementation using simulators etc. The present study aims to describe the various simulation and emulation tools for implementing fog computing scenarios. Results: The review shows that iFogSim is the simulator that most of the researchers use in their research work. Among emulators, EmuFog is being used at a higher pace than other available emulators. This might be due to ease of implementation and user-friendly nature of these tools and language these tools are based upon. The use of such tools enhance better research experience and leads to improved quality of service parameters (like bandwidth, network, security etc.). Conclusion: There are many fog computing simulators/emulators based on many different platforms that use different programming languages. The paper concludes that the two main simulation and emulation tools in the area of fog computing are iFogSim and EmuFog. Accessibility of these simulation/ emulation tools enhance better research experience and leads to improved quality of service parameters along with the ease of their usage.

Grey wolf optimizer is a recently developed metaheuristic algorithm that mimics hunting and social behaviour. It has been applied in most of the engineering design problems. Grey wolf optimizer and its variants have been effectively used to solve real-life applications. For some complex problems, a grey wolf optimizer has been hybridized with other metaheuristics. This paper summarizes the overview of the grey wolf optimizer and its variants. The pros and cons of these variants have been discussed. The application of a grey wolf optimizer has also been discussed with future research directions. This paper will encourage the researchers to use this algorithm for their real-life problems.

Background: In this paper, a novel hybridisation of the dragonfly algorithm (DFA) with the pattern search (PS) algorithm is applied to the dynamic economic dispatch (DED) problem. The DED problem is non-convex, non-linear, and non-smooth and considering practical constraints such as the loading effect of the valve point and ramp rate limits. The conventional DFA is stuck in the local optima and converges prematurely. Introduction: The characteristics of the optimality of the electric power system are dependent on reliability and high economy. Economic dispatch (ED) significantly contributes in deriving the optimal solutions for the operation of a power system. ED aims to generate electric power at the optimum cost among all generating units in order to satisfy the load demand considering all practical and operational constraints. Practical constraints, such as the effect of steam valves, the dynamic behaviour of ramp rate limits, losses due to transmission of power, and prohibited operating zones, convert the linear and convex problem to a non-convex and non-linear problem. Method: Planning and scheduling of output electric power from committed generating units to fulfill the load demand for a scheduled period are termed as DED. The practical generators of thermal power experience the effect of steam valve, real-time ramp rate limit, and technical constraints. DED satisfies all practical, technical, and operational constraints. The DFA was a newly proposed method taking the inspiration of the behaviour of dragonflies for hunting and migrating towards food. The random movement of dragonfly clusters depicts their static characteristics for exploring in the local search space for exploitation competencies, whereas the dynamic behaviour of swarms is used for exploring the global search space by moving in a single direction for a long distance. Result: The efficiency of the proposed method is validated for six well-known benchmark functions. The hybrid technique is compared with the conventional DFA. The proposed hybrid technique combining of the DFA and PS algorithm is also applied for four different test systems with diverse generating units. The proposed technique shows better efficiency for the optimum cost as compared to other recently applied techniques. Conclusion: To overcome difficulties, a PS method is hybridised with the original DFA. The application of the proposed technique improves the capability of search and convergence property The validation of the proposed method by applying to the DED problem shows its effectiveness for generation scheduling and estimating.

Background: Cloud computing is a multi-tenant model for computation that offers various features for computing and storage based on user demand. With increasing cloud users, the usage increases that highlights the problem of load balancing with limited resource availability based on dynamic cloud environment. In such cases, task scheduling creates fundamental issue in cloud environment. Introduction: Certain problems such as inefficiencies in load balancing latency, throughput ratio, proper utilization of the cloud resources, better energy consumption and response time have been observed. These drawbacks can be efficiently resolved through the incorporation of efficient load balancing and task scheduling strategies. Method: In this paper, we develop an efficient co-operative method to solve the most recent approaches against load balancing and task scheduling that has been proposed using Ant Colony Optimization (ACO). These approaches enable the clear cut identification of the problems associated with the load balancing and task scheduling strategies in the cloud environment. Results: The simulation is conducted to find the efficacy of the improved ACO system for load balancing in cloud than the other methods. The result shows that the proposed method obtains reduced execution time, reduced cost and delay. Conclusion: A unique strategic approach is developed in this paper, Load Balancing, which works with the ACO in relation to the cloud workload balancing task through the incorporation of the ACO technique. The strategy for determining the applicant nodes is based on which the load balancing approach would essentially depend. By incorporating two different approaches: the maximum minute rules and the forward-backward ant, this reliability task can be established. This method is intended to articulate the initialization of the pheromone and thus upgrade the relevant cloud-based physical properties.

Background: The spectrum scarcity plays a vital role in wireless communications. We are in the situation to use it through an efficient methodology. Objective: To identify the holes in the spectrum through an efficient spectrum sensing technique and to allocate the bands to the unlicensed users (Secondary Users - SU). Methods: It has been proposed to make a comparative study among the existing spectrum sensing methods based on the following parameters such as Probability detection (Pd) measurement, Algorithm, Decision fusion method, Network model. Results: A comparative study has been made to find the pros and cons of the existing techniques with their limitations and the field of application. Cooperative Spectrum Sensing (CSS) technique significantly consumes less energy and takes less time to report to Fusion Centre (FC), since it utilizes Log Likelihood Ratio (LLR) Method to find the probability of detection using Chair-Varshney rule in local sensing with parallel report approach in the cluster based network. Conclusion: Through the study and the comparison of parameters in literature, it is found that CSS provides better detection. Therefore, this technique can be considered as an efficient technique to find the holes and to share the frequency with SUs.

Background: The attempt of this research is to propose a novel approach for the efficient prediction of stock prices. The scope of this research extends by including the feature of sentiment analysis using the emotions and opinions carried by social media platforms. The research also analyzes the impact of social media, feeds data and Technical indicators on stock prices for the design of the prediction model. Objectives: The goal of this research is to analyze and compare the models to predict stock trends by adjusting the feature set. Methods: The basic technical and new momentum volatility indicators are calculated for the benchmark index values of the stock. The text summarization was applied on collected day-wise tweets for a particular company and then sentiment analysis was performed to get the sentiment value. All these collected features were integrated to form the final dataset and accuracy comparisons were made by experimenting with the algorithms- Support vector machine (SVM), Backpropogation and Long short-term memory (LSTM). Results: The execution is carried out for each algorithm with 30 epochs. It is observed that the SVM exhibits 2.78%, Backpropogation exhibits 5.02% and LSTM exhibits 10.30 % enhanced performance than the prediction model designed using basic technical indicators. Moreover, along with human sentiment, the SVM provides 5.48%, Backpropogation 5.28% and LSTM 0.07% better accuracy. The standard deviation results are for SVM 1.59, for back propagation 2.46, and LSTM 0.19. Conclusion: The experimental results show that the standard deviation of LSTM is less than the SVM and back propagation algorithms. Hence, obtaining steady accuracy is highly possible with LSTM.

Objectives: The uniform data standard system is built to realize the interconnection between the heterogeneous information systems in hospitals and to solve the problem of data island. Methods: The establishment of the integration platform is started from the aspects such as the establishment of integration platform model, design of platform architecture and data interaction process, promotion of standardization of the data format and prime index construction for patients. Results: The ESB (Enterprise Service Bus) and the SOA (Service Oriented Architecture) are used to achieve the medical multi-source data fusion through the integration platform with two interface methods of MQ (Message Queue) and Web Service. Conclusion: The intelligent decision support system established on the integration platform is used to provide powerful data support to improve data utilization, regulate medical behaviors, advance medical quality and enhance management efficiency.

Background: Mobile Ad hoc Networks (MANET’s) have recently attracted attention as it is independent of any pre-existing network infrastructure or centralized administration. Security in MANET’s thus becomes a major concern due to its open and dynamic architecture. Objectives: We have introduced a dynamic mean field game theoretic approach to enable an individual node in MANETs to make strategic security defense decisions without centralized administration. Methods: The nodes in MANET’s act as a router to forward data packets and exchange routing information. Ad-hoc On demand Distance Vector (AODV) protocol is one of the standard MANET routing protocols which can be easily attacked by the fraudulent nodes. The fraudulent nodes can be deceptive and mislead the transmission of data packets in the network by providing shorter path and highest destination sequence number. Game theory finds wide application as a statistical and mathematical tool to model such dynamic networks and provide security. Results: We have implemented mean field game theory for addressing security issue in MANET’s. Each node in this dynamic distributed network knows the information about its own state as well as the average reflection of the whole mean field. The players can strategically make distributed security defense decisions under adverse conditions. Unlike static threshold-based scheme for security, the threshold is estimated dynamically in this study. Each node checks whether the received Route REPly (RREP) sequence number is higher than a dynamically updated threshold value. Conclusion: The comparative performance analysis of Throughput (TR), Packet Delivery Rate (PDR) and Average Cost (AC) has been demonstrated. Game theory has a vital role to validate and justify the intuitive strategic actions taken by each player to maximize their utility by playing optimal strategy. On the basis of the dynamic threshold calculated, the higher throughput and PDR could be achieved by eliminating the misleading paths. Simulation results corroborate that our dynamic mean field game theoretic scheme outperforms the static scheme. Discussion: A dynamic approach for mobile ad hoc networks is presented in this paper to improve the performance of the network in hostile environment. We have introduced a dynamic mean field game theoretic approach to enable an individual node in MANETs to make strategic security defense decisions without centralized administration. In this dynamic distributed network, each node in the proposed scheme only needs to know its own state information and the average reflection of the whole mean field.

Introduction: Pathologists are majorly concerned with detecting the diseases and helping the patients in their healthcare and well-being. The present method used by pathologists for this purpose is manually viewing the slides using a microscope and other instruments. However, this method has a number of limitations such as there is no standard way of diagnosis, there are certain chances of human errors and besides, it burdenizes the laboratory personnel to diagnose a large number of slides on a daily basis. Method: The slide viewing method is widely used and converted into digital form to produce high resolution images. This enables the area of deep learning and machine learning to get an insight into this field of medical sciences. In the present study, a neural based network has been proposed for classification of blood cells images into various categories. When an input image is passed through the proposed architecture and all the hyper parameters and dropout ratio values are applied in accordance with the proposed algorithm, then the model classifies the blood images with an accuracy of 95.24%. Result: After training the models on 20 epochs. The plots of training accuracy, testing accuracy and corresponding training loss, and testing loss for the proposed model is plotted using matplotlib and trends. Discussion: The performance of the proposed model is better than the existing standard architectures and other works done by various researchers. Thus, the proposed model enables the development of pathological system which will reduce human errors and daily load on laboratory personnel. . This can also in turn help the pathologists in carrying out their work more efficiently and effectively. Conclusion: In the present study, a neural based network has been proposed for classification of blood cells images into various categories. These categories have significance in the medical sciences. When input image is passed through the proposed architecture and all the hyper parameters and dropout ratio values are used in accordance with the proposed algorithm, then the model classifies the images with an accuracy of 95.24%. This accuracy is better than the standard architectures. Further, it can be seen that the proposed neural network performs better than the present related works carried out by various researchers.

Introduction: Stemming is an important preprocessing step in text classification, and could contribute to increasing text classification accuracy. Although many works have proposed stemmers for the English language, few stemmers have been proposed for Arabic text. Arabic language has gained increasing attention in the previous decades and the need to further improve Arabic text classification. Methods: This work combined the use of the recently proposed P-stemmer with various classifiers to find the optimal classifier for the P-stemmer in terms of Arabic text classification. As part of this work, a synthesized dataset was collected. Results: The previous experiments show that the use of P-stemmer has a positive effect on classification. The degree of improvement is classifier-dependent, which is reasonable as classifiers vary in their methodologies. Moreover, the experiments show that the best classifier with the P-Stemmer is NB. This is an interesting result as this classifier is well-known for its fast learning and classification time. Discussion: First, the continuous improvement of the P-stemmer by more optimization steps is necessary to further improve the Arabic text categorization. This can be made by combining more classifiers with the stemmer, by optimizing the other natural language processing steps, and by improving the set of stemming rules. Second, the lack of sufficient Arabic datasets, especially large ones, is still an issue. Conclusion: In this work, an improved P-stemmer was proposed by combining its use with various classifiers. In order to evaluate its performance, and due to the lack of Arabic datasets, a novel Arabic dataset was synthesized from various online news pages. Next, the P-stemmer was combined with Naïve Bayes, Random Forest, Support Vector Machines, K-Nearest Neighbor, and K-Star.

Introduction: The number of vehicles is increasing day by day in our life. The vehicle may violate traffic rules and cause accidents. The Automatic Number Plate Detection System (ANPR) plays a significant role to identify these vehicles. Number plate detection is very difficult sometimes because each country has its own format for representing the number plate and font types and sizes may also vary for different vehicles. A number of ANPR systems are available nowadays but still, it is a big problem to detect the number plate correctly in various scenarios like in a high-speed vehicle, number plate language, etc. Methods: In the development of this method, we mainly used wiener filter for noise removal, morphological operations for number plate localization, connected component algorithm for character segmentation, and template-based matching for character recognition. Results: Our proposed methodology is providing promising results in terms of detection accuracy. Discussion: The Automatic Number Plate Detection System (ANPR) has a wide range of applications because the license number is the crucial, commonly putative and essential identifier of motor vehicles. These applications include ticketless parking fee management, parking access automation, car theft prevention, security guide assistance, motorway road tolling, border control, journey time measurement, law enforcement, etc. Conclusion: In this paper, an enhanced approach of automatic number plate detection system is proposed using some different techniques which not only detect the number plate of the vehicle but also recognize each character present in the detected number plate image.

Introduction: Convolutional Neural Network (CNNet) has proven the indispensable system in order to perform the recognition and classification tasks in different computer vision applications. The purpose of this study was to exploit the marvelous learning ability of CNNet in the image classification field. Methods: In order to circumvent the overfitting issues and to enhance the generalization potential of the proposed FLCNNet, augmentation has been performed on the Flavia dataset that imposes translation and rotation techniques to perform the augmentation with the transformed leaves having the same labels as the original ones. Both the classification models executed; one without augmentation and one with the augmentation data are compared to check the effectiveness of the augmentation hence the aim of the proposed work. Moreover, Edge detection technique has been applied to extract the shape of the leaf images, in order to classify them accordingly. Thereafter, the FLCNNet is trained and tested for the dataset, with and without augmentation. Results: The results are gathered in terms of accuracy and training time for both datasets. The Augmented dataset (dataset 2) has been found effective and more feasible for classification without misguiding the network to learn (avoid overfitting) as compared to the dataset without augmentation (dataset 1). Conclusion: This paper proposed the Five Layer Convolution Neural Network (FLCNNet) method to classify plant leaves based on their shape. This approach can classify 8 types of leaves using automatic feature extraction by utilizing their shape characteristics. To avoid the overfitting condition and make the performance better. We aimed to perform the classification of the augmented leaf dataset. Discussion: We proposed a five Layer CNNet (FLCNNet) to classify the leaf image data into different classes or labels based on the shape characteristics of the leaves.

Introduction: The future of healthcare systems relies on faster communication between sensors and smart devices, which can assist in making decisions for the betterment of patients. The responsiveness of the wireless health care system in case of medical urgencies is a crucial factor for the survival of patient’s life. The routing protocol of infrastructure-less based plays a key role in sending the information in such medical related emergencies. Therefore, it is important to study and identify the best routing protocol in wireless healthcare based system using Mobile Ad-hoc networks (MANETS). Methods: MANET routing protocols such as Ad-hoc On-Demand Vector (AODV), Secure AODV (SAODV) and Hybrid Wireless Mesh Protocol (HWMP) through their routing environment are simulated through this research study. It is essential to highlight the effect of various attacks affecting the routing methodology of these protocols. Since the Distributed Denial of Service (DDoS) attack is popularly talked about and is the most vulnerable attack present in the MANET environment, therefore this research study analyses AODV, SAODV and HWMP under DDoS attack through various simulation parameters. Results: In this research study, most suitable routing protocols to handle DDoS attacks are simulated and estimated in terms of delay and packet delivery ratio in the scenario of changing nodes. This aids in providing implications to enhance existing protocols and alleviate the consequences of DDoS investigation by such attacks. Discussion: For ensuring the optimized routing, privacy and security of patient’s data during transmission in the healthcare sector, MANET could be used as one of the important technology combined with IoT. For dealing with end to end data transmission of patient's sensitive data, MANET protocol plays a vital role in sending the information securely. Conclusion: The performance of AODV, SAODV and HWMP (Hybrid Wireless Mesh Protocol) are compared and tabularized, which are the most popularly utilized protocols in the healthcare environment. The simulation results show that the HWMP outperformed AODV and SAODV routing protocol in terms of evaluation metrics, namely end-to-end delay and Packet Delivery Ratio (PDR), and could be considered as much less vulnerable against DDoS attacks prevailing in the wireless healthcare sector using MANET.

Background: Currently, Machine Learning (ML) is considered a popular and important area in diverse fields of science and technology, image processing, automobiles, banking, finance, health care sector, etc. The easy availability of data and rapid improvements over machine learning techniques have made it more feasible to understand and to work on various channels of real-time health analytics. Methods: In this paper, a health status prediction system is proposed to detect cardiovascular diseases through patients’ tweets. Further analytics is carried on a distributed Apache Spark (AS) framework to reduce the time taken for both training and testing when compared with regular standalone machines. Social media streaming data is considered as one of the major sources for data in the proposed system. In this model, attributes of the incoming user tweets are analyzed, and accordingly, cardiovascular risk is predicted, and the latest health status is tweeted back as a reply to the respective user along with a copy to the family and caretakers. Results: Performance of the proposed framework with Extreme Learning Machine (ELM) - Tree classifier is evaluated on two different corpora. It outperforms other classifiers such as Decision Trees, Naïve Bayes, Linear SVC, DNN, etc. in both accuracy and time. Conclusion: This proposed study hypothesizes a model for an alert-based system for heart status prediction by adding some additional features impacting the accuracy besides reducing the response time by using Big data Apache Spark Distributed Framework.

Background: In grid computing, several computing nodes work together to accomplish a common goal. During computation some nodes get overloaded and some nodes remain idle without any job, which degrades the overall grid performance. For better resource utilization, the load balancing strategy of a grid must be improved. Objective: A good load balancing strategy intelligently perceives grid information and finds the best node to transfer jobs from an overloaded node. In our study, we found that the good load balancing strategies have two prominent needs while decision making, i.e., considering multiple parameters and handling uncertainty present in the grid environment. Methods: This paper proposed a model, an intelligent fuzzy middleware for load balancing in a grid computing environment (IFMLBG) which fulfilled both the needs. The processing of IFMLBG is based on Chang’s extent analysis for the fuzzy analytical hierarchy process (FAHP). FAHP hierarchically structured the load-balancing problem and used the non-crisp input to handle the uncertainty of the grid environment. Chang’s analysis is performed to generate weights to prioritize nodes and find the best one. Results: The results show that the IFMLBG Model assigned more weight to the best-selected node as compared to the AHP model and performs well with prudent nodes and criteria. Conclusion: This paper comprehensively described the design of an Intelligent Fuzzy middleware for Load Balancing in Grid computing (IFMLBG) which used Chang’s extent analysis for FAHP and implemented using four parameters and four computing nodes. The Chang’s extent analysis for FAHP takes triangular fuzzy numbers as input and generates weights for nodes. We compared IFMLBG with the classical AHP model on thirteen datasets and concluded that IFMLBG gives more weight to select the node as compared to the AHP model. The results also show that IFMLBG would work better with the number of parameters and computing nodes.

Introduction: Machine learning is an intelligent technology that works as a bridge between businesses and data science. With the involvement of data science, the business goal focuses on findings to get valuable insights on available data. The large part of Indian Cinema is Bollywood, which is a multi-million dollar industry. This paper attempts to predict whether the upcoming Bollywood Movie would be Blockbuster, Superhit, Hit, Average, or Flop. For this, Machine Learning techniques (classification and prediction) will be applied. To make a classifier or prediction model, the first step is the learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that, different rules are generated, which helps to make a model and predict future trends in different types of organizations. Methods: All the techniques related to classification and prediction, such as Support Vector Machine (SVM), Random Forest, Decision Tree, Naïve Bayes, Logistic Regression, Adaboost, and KNN, will be applied and efficient and effective results will be obtained. All these functionalities can be applied with GUI Based workflows available with various categories such as data, Visualize, Model, and Evaluate. Results: To make a classifier or prediction model, the first step is the learning stage in which we need to give the training data set to train the model by applying some technique or algorithm, and after that, different rules are generated which helps to make a model and predict future trends in different types of organizations. Conclusion: This paper focuses on comparative analysis that would be performed based on different parameters such as Accuracy, Confusion Matrix to identify the best possible model for predicting the movie success. By using Advertisement Propaganda, they can plan for the best time to release the movie according to the predicted success rate to gain higher benefits. Discussion: Data Mining is the process of discovering different patterns from large data sets, and from that, various relationships are also discovered to solve various problems that come in business and help to predict the forthcoming trends. This prediction can help Production Houses for Advertisement Propaganda, and also, they can plan their costs, and by assuring these factors, they can make the movie more profitable.