Take our hypothetical firm as an example, and you're trying to figure out how well a particular product will perform from a marketing perspective. Customers might be segmented based on their market behaviour. Take note that the amount of data available is enormous, and that cannot process it with our human senses alone. Machine learning algorithms and processing power will be employed. Unsupervised learning has several important uses, one of which is customer segmentation. Identify client segments to focus on the possible user base by using clustering techniques (K-means, Agglomerative, and Mean Shift). As a result, they segment customers into groups based on similar factors such as gender and age as well as interests and spending habits. Gender and age patterns can also be seen using K-means clustering. After that, look at their yearly earnings and expenditure totals. When compared to the current model, which employs Mini Batch K-means, the findings from the projected model are more accurate.

Mall Customer Segmentation Using Machine Learning

Driver sleepiness has become a leading cause of traffic accidents and fatalities in recent years. The goal of this research is to find a way to identify driver fatigue and provide early warning so that people can be saved. Using image processing techniques, a camera captures video of the driver's face and measures the status of their eye and mouth opening ratios and delivers a warning if necessary. This is a real-time system. There are a variety of methods for determining whether a driver is drowsy, but this one is absolutely non-intrusive and has no effect on the driving in any way. The per-closure value of the eye is taken into account for the identification of drowsiness. Consequently, the driver is classified as sleepy if the closing of the eye exceeds a predetermined threshold. Offline testing of various machine learning algorithms has also been conducted. Support Vector Machine-based classification has a sensibility of 95.58 percent and a specificity of 100 percent. 

Drowsy Driver Monitoring Using Machine Learning and Visible Actions

On the ATM, a fingerprint approach is used to make this observation. For the most part, this technology is designed to make online transactions more convenient and user-friendly for customers. Currently, the Biometric era is advancing at a rapid pace. The goal of this profession is to increase the safety and security of human beings in order to facilitate the transaction. Identity is protected through biometrics. The ATM machine uses fingerprint scanning biometrics to gain access. The bank uses an enrolment process to save fingerprint data in a database. When compared to the other ATM technology, fingerprint recognition is superior and more secure. Transactions will continue if the purchaser’s identification matches the database. It is possible to cancel the transaction if the biometric does not match the one that was previously used for verification. With a fingerprint-primarily driven ATM, transactions can be made without any difficulty. 

Pattern Recognition based Fingerprint Authentication for ATM System

Cloud computing seems to be a scalable and realistic distributed computing platform that delivers resources as a service. One of the major difficulties impeding cloud computing development is data security in the cloud. The security vulnerabilities in cloud computing and other cloud services slow down cloud computing growth and difficulties with data protection and privacy. In this new context, cloud service customers must be cautious about data breaches. This article studies a solution to current diverse security challenges that have arisen as a result of the service demonstrating that the offered methods are provably safe and very efficient. The solution comprises a distributed multi-level security scheme for processing the information involved in cloud computing. The proposed scheme evaluates the most significant encryption techniques generally used in various industries like AES (Advanced Encryption Standard), Blowfish, 3DES (Data Encryption Standard), CAST128, and RC4 (Rivest Cipher 4). The proposed model with these encryption techniques ensure minimal energy consumption in cloud computing with maximum speed. Moreover, to increase the security of the data, various cryptographical algorithms are applied, analyzed, and compared in an OpenStack environment. 

Study on Distributed Multi-Level Security Scheme For Cloud Computing

The vehicle's license plate number can be read by an image recognition system, called number plate recognition. The goal is to implement a license plate-based modified authorized vehicle recognized verification system that works smoothly. The system can be implemented at the entry point for controlling access to a highly restricted area, such as a military base or the area around the most important government buildings (such as the Parliament or the Supreme Court). The built system first identifies the car, and then takes a picture of it. The license plate area of the vehicle is then converted to grayscale. At that time, the license plate is taken off the car. After that, a KNN (K- Nearest Neighbors) algorithm is used to identify the numerical and alphabetic sequences. With this information, the vehicle's owner, preferred location, current residence, etc. are tracked. Python is used for the implementation, and the system is tested with real images. The test results show that the proposed framework successfully differentiates between fake and real images of license plates. The purpose of this extension is to develop an illustration capable of correctly selecting a license plate based on a photograph of the plate.

Image Segmentation based Imperative Feature Subset Model for Detection of Vehicle Number Plate using K Nearest Neighbor Model

In recent days cloud domain gains a lot of user attention in order to store and access the data from remote locations connected through the internet. As it is generally known that all the sensitive data come from remote locations will be stored in the centralized storage medium and then try to access the data from that centralized storage space controlled by the cloud server. It is facing a problem like there is no security for the data in terms of user authorization and data authentication from the centralized storage location. Hence, it is required to migrate for a new storage procedure like Decentralized storage of cloud data in which the systems that do not rely on a central authority, so that the collusion resistance can be avoided by maintaining a global identifier. Here, the term de-centralized access means granting multi authorities to control the access for providing more security for the sensitive data. The proposed research study attempts to develop a new scheme by adding a global identifier like Attribute Authority (AA) for providing access keys for the data users who wish to access the sensitive information from the cloud server. The proposed research work attempts to incorporate the composite order bilinear groups scheme for providing access facility for the data users and provide more security for the sensitive data. By conducting various experiments on the proposed model, the obtained result clearly tells that the proposed system is very efficient to access the data in a de-centralized manner by using a global identifier.

Santhi Sri. K

Papers

Multi-Level Authentication Scheme for Improving Privacy and Security of Data in Decentralized Cloud Server