New advances in electronic commerce systems and communication technologies have made the credit card the potentially most popular method of payment for both regular and online purchases; thus, there is significantly increased fraud associated with such transactions. Fraudulent credit card transactions cost firms and consumers large financial losses every year, and fraudsters continuously attempt to find new technologies and methods for committing fraudulent transactions. The detection of fraudulent transactions has become a significant factor affecting the greater utilization of electronic payment. Thus, there is a need for efficient and effective approaches for detecting fraud in credit card transactions. This paper proposes an intelligent approach for detecting fraud in credit card transactions using an optimized light gradient boosting machine (OLightGBM). In the proposed approach, a Bayesian-based hyperparameter optimization algorithm is intelligently integrated to tune the parameters of a light gradient boosting machine (LightGBM). To demonstrate the effectiveness of our proposed OLightGBM for detecting fraud in credit card transactions, experiments were performed using two real-world public credit card transaction data sets consisting of fraudulent transactions and legitimate ones. Based on a comparison with other approaches using the two data sets, the proposed approach outperformed the other approaches and achieved the highest performance in terms of accuracy (98.40%), Area under receiver operating characteristic curve (AUC) (92.88%), Precision (97.34%) and F1-score (56.95%).

An Intelligent Approach to Credit Card Fraud Detection Using an Optimized Light Gradient Boosting Machine

Techniques for an image-based CAPTCHA for object recognition are described. The disclosure describes adding images to a database by collecting images by querying descriptive keywords to an image search engine or crawling images from the Internet. The disclosure describes generating the image-based CAPTCHA. The image is retrieved from the database, along with objects having significant values. An object is cropped from its image. The portion on the image where the object has been cropped is filled with image inpainting. The process obtains other objects from the database. The object is mixed among the other objects to from a set of candidate objects. A user is asked to select “the object” from the set of candidate objects that fits or matches the image. The image-based CAPTCHA evaluates whether a response, the selection, is from a human or a bot.

Image-Based CAPTCHA Exploiting Context in Object Recognition

Every other field has got some benefit from new technologies as compared to the agricultural field. According to past studies, 42% of agricultural production is in loss and that too only because of the increasing rate of loss due to plant leaf diseases. To overcome this major issue, this plant leaf disease detection technique can be applied to detect a disease from the input images. This process involved steps like image pre-processing, image segmentation, feature extraction. Furthur K Nearest Neighbor (KNN) classification is applied on the outcome of these three stages. Proposed implementation has shown 98.56% of accuracy in predicting plant leaf diseases. It also presents other information regarding a plant leaf disease that is Affected Area, Disease Name, Total Accuracy, Sensitivity and Elapsed Time

Plant Leaf Disease Detection using Machine Learning

The edge computing (EC) paradigm brings computation and storage to the edge of the network where data is both consumed and produced. This variation is necessary to cope with the increasing amount of network-connected devices and data transmitted, that the launch of the new 5G networks will expand. The aim is to avoid the high latency and traffic bottlenecks associated with the use of Cloud Computing in networks where several devices both access and generate high volumes of data. EC also improves network support for mobility, security, and privacy. This paper provides a discussion around EC and summarized the definition and fundamental properties of the EC architectures proposed in the literature (Multi-access Edge Computing, Fog Computing, Cloudlet Computing, and Mobile Cloud Computing). Subsequently, this paper examines significant use cases for each EC architecture and debates some promising future research directions.

Edge computing: current trends, research challenges and future directions

Chinese Character CAPTCHA Recognition and performance estimation via deep neural network

Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs) are the automatic filters that are widely used these days to disallow any automated script that can perform the work of a human. CAPTCHAs are built in such a way that it is very difficult for any automated script to break them. In this paper, an approach to break text based CAPTCHAs has been proposed that first preprocesses the given CAPTCHA, segments its characters, and then recognizes the characters depending on its features. The breaking of CAPTCHA gives strength of CAPTCHA which in turn helps to develop more robust CAPTCHA The testing results shows that the algorithm successfully breaks the CAPCHA. This algorithm will be also helpful to screen reader program. The results show that it is not a trivial task to design a CAPTCHA scheme that is both usable and robust.

Algorithm to Break Visual CAPTCHA

A Framework to analyze the security of Text based CAPTCHA

CAPTCHA stands for Completely Automated Public Turing Tests to Tell Computers and Humans Apart. A CAPTCHA is a program that protects websites against bots –automated scripts by generating and grading tests that humans can pass but current computer programs cannot. For example, humans can read distorted text but current computer programs can't. The threats from bots is growing rapidly and also increasing in technical sophistication causing various types of attacks. These attacks are affecting social aspects of human beings. Human being or legitimate users are cheated by false requests disturbing their social life. This paper aims to provide secured authentification by verifying strength of CAPTCHA. The strength of CAPTCHA can be verified by solving it. The CAPTCHA solving has mainly three steps such as preprocessing, segmentation and character recognition. The input distorted image of CAPTCHA is passed through preprocessing module which removes noise and gives raw image which is then segmented. These segmented characters are recognized using pattern-matching technique achieving 88% accuracy. The result shows that this algorithm provides secured social relevance to avail free Internet services and in turn improve usability of well-claimed CAPTCHA.

Algorithm for Secured Online Authentication Using CAPTCHA

Agriculture growth is the key component in socioeconomic growth of our country due to liberalization and globalization. Gradually with significant increase in technology, advanced telecommunication services assist plant disease treatment at remote locations. Earlier systems were designed for either monocot or dicot plant family disease detection. The paper proposes an integrated approach for monocot and dicot plant disease detection and treatment along with precautionary measurement through smartphone and image processing techniques. The paper mainly focuses on plant disease detection technique based on integrated approach of K-means segmentation algorithm and SVM Classifier. The proposed and developed approach gives 83 % accuracy for plant diseases recognition.

Agri-Guide: An Integrated Approach for Plant Disease Precaution, Detection, and Treatment

There is a large number of credit card payments take place that is targeted by fraudulent activities. Companies which are responsible for the processing of electronic transactions need to efficiently detect the fraudulent activity to maintain customers’ trust and the continuity of their own business. In this paper, the developed algorithm detects credit card fraud. Prediction of any algorithm is based on certain attribute like customer’s buying behavior, a network of merchants that customer usually deals with, the location of the transaction, amount of transaction, etc. But these attribute changes over time. So, the algorithmic model needs to be updated periodically to reduce this kind of errors. Proposed System provides two solutions for handling concept drift. One is an Active solution and another one is Passive. Active solution refers to triggering mechanisms by explicitly detecting a change in statistics. Passive solution suggests updating the model continuously in order to consider newly added records. The proposed and developed system filters 80% fraudulent transactions and acts as a support system for the society at a large.

Anjali Chandavale

Papers

Algorithm to Break Visual CAPTCHA

A Framework to analyze the security of Text based CAPTCHA

Algorithm for Secured Online Authentication Using CAPTCHA

Agri-Guide: An Integrated Approach for Plant Disease Precaution, Detection, and Treatment

Implementation of Credit Card Fraud Detection System with Concept Drifts Adaptation