BLAST-SSAHA Hybridization for Credit Card Fraud Detection

A phenomenal growth in the number of credit card transactions, especially for online purchases, has recently led to a substantial rise in fraudulent activities. Implementation of efficient fraud detection systems has thus become imperative for all credit card issuing banks to minimize their losses. In real life, fraudulent transactions are interspersed with genuine transactions and simple pattern matching is not often sufficient to detect them accurately. Thus, there is a need for combining both anomaly detection as well as misuse detection techniques. In this paper, we propose to use two-stage sequence alignment in which a profile analyzer (PA) first determines the similarity of an incoming sequence of transactions on a given credit card with the genuine cardholder's past spending sequences. The unusual transactions traced by the profile analyzer are next passed on to a deviation analyzer (DA) for possible alignment with past fraudulent behavior. The final decision about the nature of a transaction is taken on the basis of the observations by these two analyzers. In order to achieve online response time for both PA and DA, we suggest a new approach for combining two sequence alignment algorithms BLAST and SSAHA.     

uWave: Accelerometer-based personalized gesture recognition and its applications

The proliferation of accelerometers on consumer electronics has brought an opportunity for interaction based on gestures. We present uWave, an efficient recognition algorithm for such interaction using a single three-axis accelerometer. uWave requires a single training sample for each gesture pattern and allows users to employ personalized gestures. We evaluate uWave using a large gesture library with over 4000 samples for eight gesture patterns collected from eight users over one month. uWave achieves 98.6% accuracy, competitive with statistical methods that require significantly more training samples. We also present applications of uWave in gesture-based user authentication and interaction with 3D mobile user interfaces. In particular, we report a series of user studies that evaluates the feasibility and usability of lightweight user authentication. Our evaluation shows both the strength and limitations of gesture-based user authentication.     

BS-SC Model: A Novel Method for Predicting Child Abuse Using Borderline-SMOTE Enabled Stacking Classifier

For a long time, legal entities have developed and used crime prediction methodologies. The techniques are frequently updated based on crime evaluations and responses from scientific communities. There is a need to develop type-based crime prediction methodologies that can be used to address issues at the subgroup level. Child maltreatment is not adequately addressed because children are voiceless. As a result, the possibility of developing a model for predicting child abuse was investigated in this study. Various exploratory analysis methods were used to examine the city of Chicago’s child abuse events. The data set was balanced using the Borderline-SMOTE technique, and then a stacking classifier was employed to ensemble multiple algorithms to predict various types of child abuse. The proposed approach successfully predicted crime types with 93% of accuracy, precision, recall, and F1-Score. The AUC value of the same was 0.989. However, when compared to the Extra Trees model (17.55), which is the second best, the proposed model’s execution time was significantly longer (476.63). We discovered that Machine Learning methods effectively evaluate the demographic and spatial-temporal characteristics of the crimes and predict the occurrences of various subtypes of child abuse. The results indicated that the proposed Borderline-SMOTE enabled Stacking Classifier model (BS-SC Model) would be effective in the real-time child abuse prediction and prevention process.     

Opposition Based Joint Grey Wolf-Whale Optimization Algorithm Based Attribute Based Encryption in Secure Wireless Communication

Wireless Personal Communications - One of the applications of Sparse Linear Wireless Sensor Networks is environmental monitoring. In these networks, sensors are deployed in sensitive and strategic...     

A Deep Learning Approach to Detection and Mitigation of Distributed Denial of Service Attacks in High Availability Intelligent Transport Systems

Mobile Networks and Applications - In the era of Internet of Things (IoT) powered by 5G technologies, Automobile Industry is headed towards a revolution. In Intelligent Transport Systems (ITS),...     

VMI versus information sharing: an analysis under static uncertainty strategy with fill rate constraints

A vendor-managed inventory (VMI) relationship between a downstream retailer and an upstream vendor consists of two distinct components: (i) information sharing (IS) and (ii) a shift in decision-making responsibility. This study compares these two components of VMI in a two-stage serial supply chain based on the ‘static uncertainty’ strategy under dynamic and random demand with fill rate constraints. Numerical experiments are conducted using analytical models to identify the conditions where the incremental value of VMI over IS is significant. The results provide guidelines relevant to academia and supply chain practitioners in taking VMI adoption decision above and beyond IS according to their specific business environment.     

Optimization of A-TIG process parameters using response surface methodology

In the present work, the influence of process parameters such as welding current (I), welding speed (S), and flux coating density (F) on different aspects of weld bead geometry for example depth of penetration (DOP), bead width (BW), depth to width ratio (D/W), and weld fusion zone area (WA) were investigated by using the central composite design (CCD). 9–12% Cr ferritic stainless steel (FSS) plates were welded using A-TIG welding. It was observed that all input variables have a direct influence on the DOP, BW, and D/W. However, flux coating density has no significant effect on WA. Mathematical models were generated from the obtained responses to predict the weld bead geometry. An optimized DOP, BW, D/W, and WA of 6.95?mm, 8.76?mm, 0.80, and 41.99?mm², respectively, were predicted at the welding current of 213.78 A, the welding speed of 96.22?mm/min, and the flux coating density of 1.99?mg/cm². Conformity test was done to check the practicability of the developed models. The conformity test results were in good agreement with the predicted values. Arc constriction and reversal in Marangoni convection were considered as major mechanisms for the deep and narrow weld bead during A-TIG welding.     

Monte Carlo techniques for phrase-based translation

Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative approach of sampling from the posterior distribution defined by a translation model. We define a novel Gibbs sampler for sampling translations given a source sentence and show that it effectively explores this posterior distribution. In doing so we overcome the limitations of heuristic beam search and obtain theoretically sound solutions to inference problems such as finding the maximum probability translation and minimum risk training and decoding.     

Reduced one-against-all method for multiclass SVM classification

We present an improved version of one-against-all method for multiclass SVM classification based on subset sample selection, named reduced one-against-all, to achieve high performance in large multiclass problems. Reduced one-against-all drastically decreases the computing effort involved in training one-against-all classifiers, without any compromise in classification accuracy. Computational comparisons on publicly available datasets indicate that the proposed method has comparable accuracy to that of conventional one-against-all method, but with an order of magnitude faster. On the largest dataset considered, reduced one-against-all method achieved 50% reduction in computing time over one-against-all method for almost the same classification accuracy. We further investigated reduced one-against-all with linear kernel for multi-label text categorization applications. Computational results demonstrate the effectiveness of the proposed method on both the text corpuses considered.     

Supplier behavior modeling and winner determination using parallel MDP

Behavioral uncertainty of a supplier is a major challenge to a buyer operating in e-procurement setting. Modeling suppliers’ behavior from past transactions, estimation of possible future performance and integrating this knowledge with the winner determination process can bring a new dimension to procurement process automation. We propose a states-space model to capture the uncertainty involved in long-term supplier behavior. The states represent the performance level of a supplier. This behavioral aspect is then integrated with the winner determination process of a multi-attribute reverse auction for efficient supplier selection using parallel MDP. We also propose an implementation framework to collect the feedback on supplier, generate an aggregate performance score and integrate it with the winner determination process. The performance aggregation and winner determination with help of Markov decision process effectively uses the past performance information. In addition, it updates performance information in regular invervals and allevates the problem of maintaining a long history. We compare the MDP-based selection with that of performance score-based selection through a simulation experiment. It is observed that our scheme gives better buyer utility, selects best suppliers and fetches better quality product. The benefits realized through these attributes to the buyer increases the efficiency of the MDP-based selection process.