Fraud detection in telecommunication industry using Gaussian mixed model

It is of great significance for the safe and stable operation of power system to master the fluctuation characteristics of wind power output. On the basis of analyzing a large number of field measured data, a weighted mixed Gaussian probability model is proposed to simulate short-time wind power fluctuation characteristics of wind farm cluster, that evaluation indices to reflect the short-time maximum fluctuation of wind power output and maximum likelihood estimation algorithm based on Expectation Maximization (EM) to estimate model parameters are put forward. This model is compared with various other kinds of probability distribution model and the simulation results show that the weighted mixed Gaussian probability model possesses the highest precision, so as the effectiveness of the weighted mixed Gaussian probability model is verified.

<p>Presently, many companies are confronted with tribulations while operating in a tempestuous business atmosphere; this is combined with the global pandemic, which is Covid-19, that has deteriorated the potency of the businesses. The telecommunication companies in Malaysia were also affected during these conditions. Therefore, a vital stratagem for the telecommunication firms to attain competitive advantage is through training programs conducted for all its employees throughout the various sections in the organization in order to beat this present obstacle. The objective of this research is to uncover if training influences job performance and job satisfaction which are two critical factors that guarantee the survival and growth of the telecommunication firms. Therefore, to realize the aim of this study, the survey technique is applied to cultivate a detailed profile which will be distributed to employees of three leading telecommunication cooperates in Malaysia. This study will use quantitative methods to generate empirical results and substantiations that responded to the research questions. The literature section scrutinized the areas of training, job performance, and job satisfaction to fill the gap and to determine the influence of training programs on job performance and satisfaction of employees. Therefore, the findings of this study could perhaps aid other corporations in Malaysia to instil continuous and well-planned training programs and not to take for granted the significance of training to improve job performance and satisfaction during the times of environmental turbulence. Thus, this could ensure that competitive strength is unceasingly maintained in the telecommunication firms in Malaysia.</p><p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/edu_01/0646/a.php" alt="Hit counter" /></p>

Many telecommunication companies in Malaysia have been attracted to invest significantly in the development of mobile commerce due to the explosive growth in the usage and market penetration of mobile devices. Eventhough generation X is characterized with high earning power, as they are reluctant on technological advancements, the mobile commerce adoption rate is remaining low in Malaysia. Therefore, this study is intended to explore the resistance factors to understand the reasons for this low adoption among generation X in Malaysia. Innovation Resistance Theory (IRT) and Valence Framework have been employed to examine the barriers, including usage, value, risk, tradition, image, and perceived cost barriers. The results of this study have been derived from data collected from 227 generation X consumers through questionnaire survey. The findings of this study show that, except the cost barrier, all other barriers significantly affect the mobile commerce adoption. These results enable local businesses to develop solutions to eliminate the resistance barriers and act as a means of understanding how to possibly enhance the rate of mobile commerce adoption in Malaysia. This research provides an extended Innovation Resistance Theory model by adding the perceived cost barrier construct, a negative valence factor, for the adoption intention of mobile commerce.

With an increase advancement of technology, fraud phone calls, including spams and malicious calls have become a major concern in telecommunication industry and causes millions of global financial losses every year. Fraudulent phone calls or scams and spams via telephone or mobile phone have become a common threat to individuals and organizations. Artificial Intelligence (AI) and Machine Learning (ML) has emerged as powerful tools in detecting and analyzing fraud or malicious calls. This paper presents an overview of AI-based fraud or spam detection and analysis techniques, along with its challenges and potential solutions. The novel fraud call detection approach is proposed that achieved high accuracy and precision. The Proposed approach was evaluated using a dataset of real-world fraudulent calls. And results demonstrate that the approach achieved high accuracy in detecting malicious calls and identifying potential indicators of frauds or spams. The analysis of fraud calls also provided insights into the tactics and methods employed by fraudsters, which can be used to develop countermeasures.

Online fraud is the well-known dark side of the modern Internet. Unsupervised fraud detection algorithms are widely used to address this problem. However, selecting features, adjusting hyperparameters, evaluating the algorithms, and eliminating false positives all require human expert involvement. In this work, we design and implement an end-to-end interactive visualization system, FDHelper, based on the deep understanding of the mechanism of the black market and fraud detection algorithms. We identify a workflow based on experience from both fraud detection algorithm experts and domain experts. Using a multi-granularity three-layer visualization map embedding an entropy-based distance metric ColDis, analysts can interactively select different feature sets, refine fraud detection algorithms, tune parameters and evaluate the detection result in near real-time. We demonstrate the effectiveness and significance of FDHelper through two case studies with state-of-the-art fraud detection algorithms, interviews with domain experts and algorithm experts, and a user study with eight first-time end users.

Improved Bags-of-Words Algorithm for Scene Recognition

Traditional stochastic power flow calculation assumes that the input variables are uncorrelated and directly used to calculate high-density correlation input variables has certain errors. To this end, this paper proposes a stochastic power flow algorithm based on mixed Gaussian models that takes into account input correlation. First, a mixed Gaussian model is established based on load data, then uniform sampling and Naf transformation are used to process random variables, and the high-density correlation in the original space is converted into independent random variables, and the piecewise linear Monte Carlo method is used to carry out random power flow. Calculation can greatly reduce the calculation time and reduce the truncation error as much as possible. Finally, combined with the actual calculation examples of IEEE-30, the results show that the algorithm can simplify the actual calculation process, improve the calculation efficiency, and has certain practical value in engineering.

Although many major, blockbuster mergers and acquisitions (M&As) in the telecommunications industry have attracted much attention from both the popular press and the media economic research community, small M&A deals in fact constitute the vast majority of business expansion activities in the telecommunications industry. Utilizing the data obtained from the Zephry database for over 2500 M&A cases involving U.S telecommunications companies, this study compares small and large blockbuster M&As in several aspects and analyzes whether several factors that have been shown to influence valuation of large M&As tend to affect small M&As to the same extent. According to the regression analysis, those factors, including financial market dynamics, M&A activity momentum, types of business expansion, and the involvement of foreign companies, influence the valuation of both small and large M&As. However, the direction and magnitude of the influences are quite different among small M&As.

Purpose The purpose of this study is to examine factors, which influence information security culture among employees of telecommunications companies. The motivation for this study was the rise in the number of data breach incidents caused by the organizations’ own employees. Design/methodology/approach A total of 139 usable responses were collected via a Web-based questionnaire survey from employees of Malaysian telecommunications companies. Data were analysed by using SmartPLS 3. Findings Security education, training and awareness (SETA) programmes and information security awareness were found to have a positive and significant impact on Information Security Culture. Additionally, self-reported employees’ security behaviour was found to act as a partial mediator on the relationship between information security awareness and information security culture. Research limitations/implications The study was cross-sectional in nature. Therefore, it could not measure changes in population over time. Practical implications The empirical data provides a new perspective on significant elements that influence information security culture in an emerging market. Organizations in the telecommunications industry can now recognize that SETA programmes and information security awareness have a significant impact on information security culture. Employees’ security behaviour also mediates the relationship between information security awareness and information security culture. Originality/value This is the first study to analyse the mediating effect of employees’ security behaviour on the relationship between information security awareness and information security culture in the Malaysian telecommunications context.

Objective: Churn prediction process on telecom industry is performed using background knowledge such as user information and application oriented constraints with the aim of clustering churn items of telecom communication users. Methods: This paper proposes Semi-supervised Constraint based Churn Clustering (SCCC) method. Semi-supervised learning method identifies different types of churns for labelled data items in telecom industry. PCK Mean based Clusteringwith Expectation Maximization (EM) algorithm finds cluster labels and distance metric for easy grouping of faults set. Similar types of issues are mapped with fast traversal procedure. Constraint based Cluster Membership achieves effective churns clustering by considering relative pairing of users. Findings: The proposed Semi-supervised Constraint based Churn Clustering (SCCC) method is implemented by using JAVA language. This JAVA language uses the code to effectively identify the churns in telecom industry. The SCCC method uses a churn dataset for conducting the experimental work.Experiment is conducted on the factors such as execution time, accuracy, clustering efficiency and support rate on predicting the churns in telecom industry. Experimental results show that the proposed Semi-supervised Constraint based Churn Clustering (SCCC) method out performs than the existing methods. Improvement: Proposed method is able to minimize the execution time, improve accuracy and clustering efficiency and also increase the support rate on predicting churns in telecom industry.Keywords: Cluster Membership, Churn Prediction, Expectation Maximization, Semi-Supervised Clustering

The rise of financial fraud, not only in India but also around the world, is a major problem. Credit card transactions have been steadily increasing in recent years, as have internet payments like Unified Payments Interface and debit card transactions, which have been increasing every day. As a result, fraud is increasing, and it has become easier for fraudsters to commit fraud. Recent research indicates the practicality of machine learning algorithms for recognizing payment fraud. Since credit cards are a common target, online fraudsters simply commit fraud because of excess use of e-commerce and other platforms, which has led to an increase in online payment methods, resulting in a greater risk of online fraud. Many researchers have started using machine learning algorithms to detect fraud. The primary objective of this study is to create a better fraud detection algorithm by analyzing payment transactional data, focusing on customers' transactional data and their payment behavioral patterns. The study proposes a framework that groups cardholders based on the volume of their transactions. Financial fraud is the biggest threat to world economies in terms of financial losses each year. The task of accurately and efficiently detecting fraud is, therefore, very challenging due to the high volume of transaction data and its complex nature. This paper presents a hybrid machine learning approach using logistic regression, decision trees, and random forests that could help enhance the accuracy and reliability of fraud detection systems. The study used an available credit card fraud dataset, with a focus on feature engineering and model evaluation to compare individual algorithms versus their ensemble. Experimental results show that the ensemble outperformed the individual classifiers in terms of precision, recall, and overall accuracy. This paper underlines the potential of hybrid machine learning techniques in improving fraud detection systems and proposes avenues for further research.

Monitoring the dynamics of wetland inundation by random sets on multi-temporal images

An efficient heterogeneous platoon dispersion model for real-time traffic signal control

Vascular age (VA) is the direct index to reflect vascular aging, so it plays a particular role in public health. How to obtain VA conveniently and cheaply has always been a research hotspot. This study proposes a new method to evaluate VA with wrist pulse signal. Firstly, we fit the pulse signal by mixed Gaussian model (MGM) to extract the shape features, and adopt principal component analysis (PCA) to optimize the dimension of the shape features. Secondly, the principal components and chronological age (CA) are respectively taken as the independent variables and dependent variable to establish support vector regression (SVR) model. Thirdly, the principal components are fed into the SVR model to predicted the vascular aging of each subject. The predicted value is regarded as the description of VA. Finally, we compare the correlation coefficients of VA with pulse width (PW), inflection point area ratio (IPA), Ratio b/a (RBA), augmentation index (AIx), diastolic augmentationindex (DAI) and pulse transit time (PTT) with those of CA with these six indices. Compared with the CA, the VA is closer to PW (r = 0.539, P < 0.001 to r = 0.589, P < 0.001 in men; r = 0.325, P < 0.001 to r = 0.400, P < 0.001 in women), IPA (r = - 0.446, P < 0.001 to r = - 0.534, P < 0.001 in men; r = - 0.623, P < 0.001 to r = - 0.660, P < 0.001 in women), RBA (r = 0.328, P < 0.001 to r = 0.371, P < 0.001 in women), AIx (r = 0.659, P < 0.001 to r = 0.738, P < 0.001 in men; r = 0.547, P < 0.001 to r = 0.573, P < 0.001 in women), DAI (r = 0.517, P < 0.001 to r = 0.532, P < 0.001 in men; r = 0.507, P < 0.001 to r = 0.570, P < 0.001 in women) and PTT (r = 0.526, P < 0.001 to r = 0.659, P < 0.001 in men; r = 0.577, P < 0.001 to r = 0.814, P < 0.001 in women). The VA is more representative of vascular aging than CA. The method presented in this study provides a new way to directly and objectively assess vascular aging in public health.

Introduction: Low physical activity (PA) has been identified as a risk factor for development of atrial fibrillation (AF). However, the effect of changes in PA on directly recorded AF burden has not been well studied. The COVID-19 pandemic offered an opportunity to observe whether changes in activity were correlated with changes in AF burden. To determine if reduced PA is associated with higher AF burden, we assessed daily PA and AF burden data from patients with cardiac implantable electronic devices (CIEDs) enrolled in a prospective clinical trial, Targeting Risk Interventions and Metformin for Atrial Fibrillation (TRIM-AF, NCT03603912). Methods: Daily AF burden and activity were determined from implantable cardiac devices with atrial leads. The pandemic lockdown period was analyzed for up to 1 year. Pre-pandemic periods were matched by month to pandemic periods. To test the potential confounding of aging, pre-pre-pandemic periods were matched by month to pre-pandemic periods. To reduce the confounding of study interventions, matched periods were taken on one side of the study enrollment date. For PA and AF burden, Gaussian linear mixed models and a Bayesian mixed effect model were fitted and adjusted for age, sex, and device manufacturers. A Gaussian model was used to correlate daily activity minutes and AF%. Time splines were added to adjust for non-linear time effects. Outcomes are reported as mean activity minutes and daily AF%. Results: Comparing Pandemic vs. Pre-periods (N=82 periods; 55 male, 27 female), daily activity minutes decreased by a mean of 13.16±1.06 minutes/day, and daily AF burden increased by 16% [5%-26%]. Comparing Pre vs. Pre-Pre-Pandemic periods (N=60 periods; 41 male, 19 female), mean activity decreased by 2.28±1.13 mins/day, and AF burden increased by 57% [50%-64%]. A significant negative correlation between activity and AF burden was demonstrated (coefficient -2.0, 95% CI -2.4, -1.6). A decrease in 2.0 activity minutes was associated with a 10% increase in AF burden. Conclusions: This natural history analysis of PA and AF burden demonstrated decreases in activity and increases in AF burden with time and the pandemic. Activity and AF burden were significantly negatively correlated.