KS Resma, GS Sharvani and Ramasubbareddy Somula
Current industrial scenario is largely dependent on cloud computing paradigms. On-demand services provided by cloud data centre are paid as per use. Hence, it is very important to…
Abstract
Purpose
Current industrial scenario is largely dependent on cloud computing paradigms. On-demand services provided by cloud data centre are paid as per use. Hence, it is very important to make use of the allocated resources to the maximum. The resource utilization is highly dependent on the allocation of resources to the incoming request. The allocation of requests is done with respect to the physical machines present in the datacenter. While allocating the tasks to these physical machines, it needs to be allocated in such a way that no physical machine is underutilized or over loaded. To make sure of this, optimal load balancing is very important.
Design/methodology/approach
The paper proposes an algorithm which makes use of the fitness functions and duopoly game theory to allocate the tasks to the physical machines which can handle the resource requirement of the incoming tasks. The major focus of the proposed work is to optimize the load balancing in a datacenter. When optimization happens, none of the physical machine is neither overloaded nor under-utilized, hence resulting in efficient utilization of the resources.
Findings
The performance of the proposed algorithm is compared with different existing load balancing algorithms such as round-robin load (RR) ant colony optimization (ACO), artificial bee colony (ABC) with respect to the selected parameters response time, virtual machine migrations, host shut down and energy consumption. All the four parameters gave a positive result when the algorithm is simulated.
Originality/value
The contribution of this paper is towards the domain of cloud load balancing. The paper is proposing a novel approach to optimize the cloud load balancing process. The results obtained show that response time, virtual machine migrations, host shut down and energy consumption are reduced in comparison to few of the existing algorithms selected for the study. The proposed algorithm based on the duopoly function and fitness function brings in an optimized performance compared to the four algorithms analysed.
Details
Keywords
Kalyan Nagaraj, Biplab Bhattacharjee, Amulyashree Sridhar and Sharvani GS
Phishing is one of the major threats affecting businesses worldwide in current times. Organizations and customers face the hazards arising out of phishing attacks because of…
Abstract
Purpose
Phishing is one of the major threats affecting businesses worldwide in current times. Organizations and customers face the hazards arising out of phishing attacks because of anonymous access to vulnerable details. Such attacks often result in substantial financial losses. Thus, there is a need for effective intrusion detection techniques to identify and possibly nullify the effects of phishing. Classifying phishing and non-phishing web content is a critical task in information security protocols, and full-proof mechanisms have yet to be implemented in practice. The purpose of the current study is to present an ensemble machine learning model for classifying phishing websites.
Design/methodology/approach
A publicly available data set comprising 10,068 instances of phishing and legitimate websites was used to build the classifier model. Feature extraction was performed by deploying a group of methods, and relevant features extracted were used for building the model. A twofold ensemble learner was developed by integrating results from random forest (RF) classifier, fed into a feedforward neural network (NN). Performance of the ensemble classifier was validated using k-fold cross-validation. The twofold ensemble learner was implemented as a user-friendly, interactive decision support system for classifying websites as phishing or legitimate ones.
Findings
Experimental simulations were performed to access and compare the performance of the ensemble classifiers. The statistical tests estimated that RF_NN model gave superior performance with an accuracy of 93.41 per cent and minimal mean squared error of 0.000026.
Research limitations/implications
The research data set used in this study is publically available and easy to analyze. Comparative analysis with other real-time data sets of recent origin must be performed to ensure generalization of the model against various security breaches. Different variants of phishing threats must be detected rather than focusing particularly toward phishing website detection.
Originality/value
The twofold ensemble model is not applied for classification of phishing websites in any previous studies as per the knowledge of authors.
Details
Keywords
Ammara Zamir, Hikmat Ullah Khan, Tassawar Iqbal, Nazish Yousaf, Farah Aslam, Almas Anjum and Maryam Hamdani
This paper aims to present a framework to detect phishing websites using stacking model. Phishing is a type of fraud to access users’ credentials. The attackers access users’…
Abstract
Purpose
This paper aims to present a framework to detect phishing websites using stacking model. Phishing is a type of fraud to access users’ credentials. The attackers access users’ personal and sensitive information for monetary purposes. Phishing affects diverse fields, such as e-commerce, online business, banking and digital marketing, and is ordinarily carried out by sending spam emails and developing identical websites resembling the original websites. As people surf the targeted website, the phishers hijack their personal information.
Design/methodology/approach
Features of phishing data set are analysed by using feature selection techniques including information gain, gain ratio, Relief-F and recursive feature elimination (RFE) for feature selection. Two features are proposed combining the strongest and weakest attributes. Principal component analysis with diverse machine learning algorithms including (random forest [RF], neural network [NN], bagging, support vector machine, Naïve Bayes and k-nearest neighbour) is applied on proposed and remaining features. Afterwards, two stacking models: Stacking1 (RF + NN + Bagging) and Stacking2 (kNN + RF + Bagging) are applied by combining highest scoring classifiers to improve the classification accuracy.
Findings
The proposed features played an important role in improving the accuracy of all the classifiers. The results show that RFE plays an important role to remove the least important feature from the data set. Furthermore, Stacking1 (RF + NN + Bagging) outperformed all other classifiers in terms of classification accuracy to detect phishing website with 97.4% accuracy.
Originality/value
This research is novel in this regard that no previous research focusses on using feed forward NN and ensemble learners for detecting phishing websites.
Details
Keywords
Biplab Bhattacharjee, Kavya Unni and Maheshwar Pratap
Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This…
Abstract
Purpose
Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.
Design/methodology/approach
An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).
Findings
A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.
Research limitations/implications
Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.
Originality/value
There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.
Details
Keywords
Muhammad Hasnain and Sami Ullah
This paper aims to examine the role of Open Artificial Intelligence application (ChatGPT) to identify challenges faced by developers working on React.js libraries.
Abstract
Purpose
This paper aims to examine the role of Open Artificial Intelligence application (ChatGPT) to identify challenges faced by developers working on React.js libraries.
Design/methodology/approach
Scopus and Google Scholar databases were searched for the literature. In addition, ChatGPT application was accessed to extract contents regarding its potential role in identifying challenges and their solutions for developers.
Findings
This paper found that ChatGPT has potential in identifying challenges, faced by learners and developers. ChatGPT enables developers to navigate the projects’ libraries and overcome steep learning curve issue. ChatGPT excels in helping the developers by presenting a range of valuable strengths. These include offering tutorials and document support, providing comprehensive programming challenges solutions, assisting with the configuration and adding in debugging process of React.js application.
Originality/value
To the best of the authors’ knowledge, this is one of the first articles presenting the potential role of ChatGPT in identifying and offering solutions to the challenges of learners and programmers about React.js.
Details
Keywords
Matthew D. Roberts, Matthew A. Douglas and Robert E. Overstreet
To investigate the influence of logistics and transportation workers’ perceptions of their management’s simultaneous safety and operations focus (or lack thereof) on related…
Abstract
Purpose
To investigate the influence of logistics and transportation workers’ perceptions of their management’s simultaneous safety and operations focus (or lack thereof) on related worker safety and operational perceptions and behaviors.
Design/methodology/approach
This multi-method research consisted of two studies. Study 1 aimed to establish correlational relationships by evaluating the impact of individual-level worker perceptions of operationally focused routines (as a moderator) on the relationship between worker perceptions of safety-related routines and workers’ self-reported safety and in-role operational behaviors using a survey. Study 2 aimed to establish causal relationships by evaluating the same conceptual relationships in a behavioral-type experiment utilizing vehicle simulators. After receiving one of four pre-task briefings, participants completed a driving task scenario in a driving simulator.
Findings
In Study 1, the relationship between perceived safety focus and safety behavior/in-role operational behavior was strengthened at higher levels of perceived operations focus. In Study 2, participants who received the balanced pre-task briefing committed significantly fewer safety violations than the other 3 treatment groups. However, in-role driving deviations were not impacted as hypothesized.
Originality/value
This research is conducted at the individual (worker) level of analysis to capture the little-known perspectives of logistics and transportation workers and explore the influence of balanced safety and operational routines from a more micro perspective, thus contributing to a deeper understanding of how balanced routines might influence worker behavior when conducting dynamic tasks to ensure safe, effective outcomes.