Identification of the denomination of the currency note to pay physically without UPI is the first step of paying to the seller by the consumer. In this project, we have proposed an approach to detect denominations of Indian currency using Convolutional Neural Networks. Computer Vision and object detection is an area of great interest for research in today’s world. It has several applications like detection of defects in machinery, intruder detection, computer vision for code and character recognition among many others. Through the work we have done, we explored something that could be of great help to people in day-to-day life. In this project we have tried to investigate the approaches to detect currency denominations using Convolutional Neural Networks. The objective is to build a model that would be able to detect Indian currency denominations efficiently. Typically the model will be useful for people with vision impairment. The experimental results show that the use of Convolutional Neural Networks is a good way and the model can further be improved if it is trained in such a way that it could also identify the regions of interest.

Data analytics is an intriguing study due to the fact that an enormous volume of healthcare data is being generated by different smart IOT-based health tracking devices, and the Artificial Intelligent-based applications. Data analytic tools and unsupervised techniques combinedly make it possible to find and comprehend hidden patterns in a dataset that may not be visible through simple data display. Grouping of voluminous data objects into homogenous clusters is a crucial operation in soft computing. Choosing the right clustering technique and the correct number of partitions to divide the healthcare data for effective analysis is complicated and challenging most of the time. This research work examines clustering approaches on the healthcare datasets with the optimum K-clusters, in order to perform the analysis of the data. In this work, the K-means clustering method is examined and the silhouette score is computed to estimate the optimal K-value and the quality of the cluster.

Cross-Lingual Summarizer develops a gist of the extract written in English in the National Language of India Hindi. This helps non-anglophonic people to understand what the text says in Hindi. The extractive method of summarization is being used in this paper for summarizing the article. The summary generated in English is then translated into Hindi and made available for Hindi Readers. The Hindi readers get the heart of the article they want to read. Due to the Internet’s explosive growth, access to a vast amount of information is now efficient but getting harder and harder. An approach to text extraction summarization that captures the aboutness of the text document was discussed in this paper. One of the many uses for natural language processing (NLP) that significantly affects our daily lives is text summarization. Who has the time to read through complete articles, documents, or books to determine whether they are helpful with the expansion of digital media and the profusion of articles published? The technique was created using TextRank, which was determined using the idea of PageRank established for each page on a website. The presented approach builds a graph with sentences as nodes and the weight of the edge connecting two sentences as its nodes. Modified inverse sentence-cosine frequency similarity gives different words in a sentence different weights. The success of the procedure is demonstrated by the performance evaluation that supported the summary technique.

Humans often express themselves through facial expressions. Deep learning techniques are used as an efficient system application process in research on the advancement of artificial intelligence technology in human-computer interactions. As an illustration, let’s say someone tries to communicate by using facial expressions. Some people who see it occasionally cannot foresee the expression or emotion it may evoke. Psychology includes study and evaluation of inferences in interpreting a person’s or group of people’s emotions when interacting in order to recognize emotions or facial expressions. Indeed, a convolutional neural networks (CNN) model may be learned to assess images and recognize facial expressions. This study suggests developing a system that can classify and forecast facial emotions using feature extraction and real-time Convolution Neural Network (CNN) technology from the OpenCV library. We have chosen FER 2013 Dataset as the main dataset for our study. Face detection, extraction of facial features, and facial emotion categorization are the three key procedures that make up the research that was implemented.

Glucose metabolism disorder known as Diabetes Mellitus is a state created by uncontrolled blood sugar that may lead to serious damage to multiple organs in patients. Identifying and predicting this disease will save human life. While designing medical diagnosis software, disease prediction is said to be one of the capricious tasks. In the current scenario, many researchers have provided their ideas on using machine learning and artificial intelligence for automated prediction of Diabetes Mellitus. A set of five popular Naïve Bayes, Random Forest, SVM, KNN and Decision Tree have been identified as well as a set of four rarely used GPC, QDA, LDA and AdaBoost have been identified from literature survey. The study is an effort to make a comparative report of the accuracy of two sets and identify the best performer. In conclusion, Support Vector Machine achieved highest accuracy with 81.00% in popular classifiers whereas Linear Discriminant Analysis achieved highest accuracy with 82.00% in less frequently used classifiers. Hence, more such rarely used classifiers should be explored for the realistic health management of diabetes.

Home buyers looking for a new house tend to be very cautious with their budgets and market strategies. Theyalways try to optimise the budget in such a way that it matches their requirements and needs. Therefore predictionof price becomes a very important thing when it comes to planning a budget and there is a need for a predictiontool. This can be achieved by doing data analysis notably Exploratory Data Analysis (EDA) and by developingMachine Learning models. An ideal home that a customer dreams of is something that matches as well as fulfils thecustomer’s requirements but at the same time with an appropriate budget. So instead of going to the real estateagent and paying an additional expense in the form of commission, the same work of suggesting and predictingthe price after analysing large data, is done by various machine learning models in a more efficient manner.Thus the research on house price prediction is of much significance as it caters to two stakeholders in this realestate market, home buyers will have a better understanding of property value and will be helped in the decisionmaking process and hence stand a better stand at negotiating. The other stakeholder i.e. the home seller will geta better estimate to put selling cost on property.

In a world where 90 percent of people travel by road, the safety of the same becomes of utmost importance. And two of the most major issues a road traveler faces are Potholes and speed breakers. The total number of road accident deaths due to potholes in 2018, 2019, and 2020 stood at 2015, 2140 and 1471, respectively. Although speed breakers are intended to prevent traffic accidents, 49.6 per cent of crashes still happen in areas where there are speed breakers.
 This paper aims to present a method for locating, identifying, and documenting speed breakers and potholes. The suggested method will employ driving information collected by various sensors, such as vibrations, jerks, bumps, changes in distance from the base of the vehicle, etc., to detect and then store the location of the object in an online database. Additionally, a stream of images of the object spotted will be simultaneously taken and uploaded to a server, to analyze using an Image Detection model. This model will facilitate the live detection of potholes and speed breakers more accurately than previous solutions.
 Once this data is added to a database, it will be effectively used by government agencies to repair the roads as well as by daily commuters to avoid the route with more obstacles, when the database is supplied to mapping services like Google Maps.

This study presents a non-orthogonal multiple access (NOMA) solution for 5G that unifies communication betweenmacro-cells via the S-R NOMA link and communication between small cells via the R-D NOMA link. S-R NOMA isused to decode own signal by respective relay. Separate studies of outage performance in S-R and R-D connectionsmay formerly be used to get an accurate definition of system outage likelihood. Our mathematical analysis issupported by simulation findings, which indicate that NOMA-assisted relaying systems outperform OrthogonalMultiple Access systems in terms of lower outage probability and better cumulative capacities (OMA).

Private Banks in India, are owned by individuals or group of limited individual and not by government. Here in India, private banks represent that most of the part of equity or shares are hold by private shares holders and not by government. The locus of control is reflected in terms of the particular degree upto which the private shares holders or the bank employee’s belief that they have power over their private banking events. This research study aims to find out locus of control among bank employees with special reference to private banks based on gender difference as well as two dimensions of locus of control viz. external and internal. Survey method was adopted for this study which covers four private banks within the Nagpur city. Sample size of 200 bank employees consists of bank managers, cashiers, clerks accountant were provided with an online Google form questionnaire. The questionnaire consists of seven questions related to their work, job satisfaction, colleagues clients etc. Initially Cronbach’s alpha test using pilot survey on 50 pre samples of bank employees was used to determine the internal consistency of data model. As second step Explorative statistics gave the trends among the bank employees towards the seven questions. The Descriptive statistics then quantitatively describes the features from a collection of information that can reveal the influence towards the three hypotheses under consideration. Lastly the Inferential statistics based two groups of genders interpret the facts as to accept or reject the three hypotheses under consideration. The study concludes the pro and cons and the prime factors which leads towards the external and internal locus of control among the employees.

IoT-based healthcare systems can ensure better patient health monitoring conditions especially in remote areas as IoT has found its reach in the daily lives of every person let it be in the way of remote messaging, data transfer, wearable devices monitoring your location, health status or any other. Quick and robust Health monitoring systems has again gained popularity with the advent of Corona Virus in recent times. Nearly everyone in today’s world after attaining an appropriate age is using the health monitoring system to measure vital parameters of the body. In rural areas, monitoring systems are not easily available, and even if acquired, they are largely very bulky and require expertise to use. So, the need is for small, remote and easily available and usable devices which have extra features to measure and display vital health parameters that can be integrated with a system to broadcast the live data to central station which can be monitored by experts. In this work, health vital signs like body temperature and pulse are measured using sensors like MAX30102 and the measured data is sent to the IoT cloud for scheduling a patient’s recorded history. We have utilized Wi-Fi convention IEEE 802.11, standard IPv4 address, next to a 3G cellular arrangement to send information from sensors to versatile application “Blynk”. Besides, Node MCU and Arduino UNO microcontrollers are also connected to the facial shield.