Browse Articles
Discover research articles across all indexed journals
RESTAURANT RECOMMENDATION SYSTEM
A recommendation system is a collection of algorithms that learn from data and, after processing, can make recommendations to clients. Because of their application in a variety of fields, recommendation systems have recently gained a lot of attraction. Recommender systems are commonly used to forecast user preferences for objects, and they are popular for assisting users in finding restaurants and other products. The Restaurant Recommendation System's main goal is to recommend the best restaurant in the area, as well as food, based on the user's tastes. This programme considers the users' culinary tastes and ratings while making food recommendations.
NAVIGATOR TO AMBULANCE FOR EMERGENCY SERVICES USING RFID TECHNOLOGY
The Aim of the project is to provide emergency services especially aiming ambulance services. A Route map is provided for Ambulance which contains traffic details along with patient’s address. The driver will have a application in his mobile which shows multiple hospitals along with route maps. The junior doctor is present in the ambulance. He examines the patient and determines the patient’s severity condition, and tells the ambulance driver about the level of severity of the patient. The driver then selects the appropriate hospital based on the severity level. Now the driver will have the route map for selected hospital along with updated traffic details. Traffic jam is cleared at the signals using tags and ambulance is left to move which results the ambulance to move fast to the hospital. This project helps ambulance to reach the patient fast and results in saving lives of the patients.
SMART WEARABLE GADGET FOR VISUALLY IMPAIRED WITH GPS TRACKER
According to the research dispensed by the globe Health Organization (WHO), it absolutely was found that there a minimum of 285 million people across the world who are visually-impaired. This device offers an ETA (Electronic Travel Aids)-smart guiding device in the form of a VR box for providing this group with direction effectively and safely due to the difficulties of travelling. A multimodal fusion-based obstacle-avoiding algorithm is described that differs from prior systems in that it makes use of the Camera to identify people and detect barriers. Through GPS Module we are able to find the placement of user. Once an obstacle on the trail of the user is detected, it alerts the user through the audio messages. Thus, helping the user to navigate safely.
REAL TIME TRAFFIC MANAGEMENT SYSTEM
Every day, there are more cars on the road, and conventional traffic control techniques can't keep up with the volume of traffic. The traditional method only succeeds in the current environment if the number of vehicles is low; if the number of vehicles increases and becomes disproportionately heavier on one side of the road, the method fails. Our objective is to transition the static traffic signal system into a signal switching system that can manage and monitor signals in real-time. As a result, in this research, the signal switching time will be precisely determined in congested traffic utilizing real-time image detection. This approach may be able to relieve backed-up traffic in a quicker and more effective way.
MALARIA DETECTION USING DEEP LEARNING
Every year, hundreds of millions of people throughout the world succumb to the fatal disease known as malaria. If the treatment is not given in a timely manner, disaster may result. The microscopic method is still the most used, despite recent improvements in malaria detection. The speed at which malaria diagnoses may be made is, however, constrained by the precision of microscopic diagnostics, which is reliant on the expertise of the microscopes. Deep learning methodologies can provide a more accurate diagnosis of an illness. Comparing the Adam-based model to earlier models created for recognizing contaminated cells. In a variety of accuracy criteria, the model outperforms the majority of previously produced models. The fact that the model just has a few layers contributes to its simplicity. This uses less computer power and processing time. Moreover, we test our model on two types of datasets infected and uninfected cells.
KRJS SCHOLARSHIP PORTAL
A scholarship can assist you in achieving your higher education goals while reducing your stress levels. Many families may not be able to send their children to higher education institutions, but thanks to scholarships, every student who meets the precise qualifying conditions can pursue higher education. The awards given by scholarship are renewable. The project helps in providing scholarship for only eligible students. Module is completely based on train & test, EDA for regression, missing value treatment, feature selection & scaling, prediction using model. The way to support students to pursue higher study is the Scholarships. Rejecting the deserved students can destroy student’s carrier. So, it is important select deserved candidates for scholarship. The Human based selection is biased, difficult, resource and time consuming. So, we want to automate the task so that we can produce reliable, unbiased, fast results.
BREAST CANCER DETECTION SYSTEM
Machine learning and soft computing methods have been used in several studies to treat breast cancer. Countless groups assert that their algorithms are superior to those of others in terms of speed, simplicity, or accuracy. This study develops a system that can correctly identify between benign and malignant breast tumours using machine learning techniques. The research's aim was to make the learning algorithm better. To select the ideal features and parameter values for machine learning classifiers in this scenario, we used regression. Accuracy, precision and recall were the performance metrics.
VIRTUAL FENCING
The virtual fencing system for animals is explained in this project. The current concept is a way to keep animals under control and track of their health without using obvious physical barriers. Animals can be kept under control by being exposed to one or more sound signals and electric shocks when they try to enter a prohibited area. Animal tracking should be possible with this research. A solution to issues like the high cost of upkeep and repair for actual fences is to create a virtual fence project. A smart collar on animals' necks can be recognized by using a virtual fence app. Each smart collars includes a global location system (GPS), and an electric shocker. On-farm tests with an animal using a smart collar are shown, along with the stimuli and categorization outcomes.
AN ART OF REVIEW IN PREDICTING THE ROSE PLANT DISEASES USING IMAGE PROCESSING WITH MACHINE LEARNING
Rose Plant Horticulture performs a tremendous position in the field of trading in phrases of the enterprise. An overview of art in predicting rose plant leaf diseases using machine learning was considered in this paper. It also investigated various predictive systems mastering strategies developed by the researcher to identify rose plant diseases. Moreover, the researcher's manipulation of experimental outcomes was reviewed by current device requirements. The accuracy of the present methodologies became measured using a confusion matrix to evaluate the overall performance of the study’s work became explored. In the end, the suggestion to are expecting the effective and green predictive device learning techniques to decide the rose plant using image processing was considered.
STOCK AND CRYPTOCURRENCY PREDICTION
In our project, the point is to anticipate long term esteem of the money related stocks of a company and crypto coins individually with fine precision. The future prices of stock and cryptocurrency are predicted by using the past available values. “Buy low, sell high" is a good saying but it is not a good choice for making speculations. Investment is best stock or crypto currency in awful time can have bad results, while investment in best stock or cryptocurrency at right time can have best benefits. Prediction for long term values is easy as compared to day-to-day basis as prices fluctuate a lot. So, our model predicts the price of stocks and cryptocurrencies, which helps the investors to invest in appropriate stocks and cryptocoins. The dataset used is taken from yahoo finance and twelve data using web scraping. The dataset retrieved is in raw format. It consists of collection of values of stock market data of various companies, and also data of various cryptocurrencies. First, raw data is converted into processed data, which is done using feature extraction. Then the dataset is splitted into training and test sets. We use the training dataset to train the model, and use test dataset to predict the future prices of stocks and cryptocurrencies. Now user can gain best knowledge about stock price trends of various companies and also cryptocurrency price trends, and can decide on for best investments in respective fields and gain best benefits.
TEXT SUMMARIZATION USING MACHINE LEARNING AND DEEP NEURAL NETWORK
The creation of summaries and their evaluation have grown in popularity over time. The two primary techniques for creating summaries from a given text corpus are extractive text summarization and abstractive text summarization. To create abstractive and extractive summaries, a variety of techniques and methodologies are available. Using machine learning and deep neural networks, an automatic extractive and abstractive text summarization technique is developed. To produce a summary from a given text, the Extractive model utilizes (Spacy, TF-IDF Vectorizer, and Latent semantic Analysis algorithm (LSA)) and the Abstract model employs (Encoder-decoder RNN with LSTM units and attention mechanism). The goal of the model is to demonstrate the benefits of applying the Extractive and Abstractive approach to text summarization in practical settings.
VIBO: A SMART INTERACTIVE COLLEGE CHATBOT
A Chatbot is a smart agent that interacts with human beings using a digital device. Chatbots play a vital role in the automation of responding to user queries. Chatbots were initially designed with an idea to fool humans. The design today has become one of the most important components of many businesses. The literature presents a smart interactive text-based chatbot VIBO designed to respond to user queries related to a University.
HOME AUTOMATION USING RASPBERRY PI
The home automation system based on the Raspberry Pi and Node MCU leverages household appliances and allows users to control them via the internet from anywhere in the globe. It enables control and operation of appliances and gadgets in a house through communication between hardware and software. Home automation might lead to more effective and intelligent energy saving strategies. The main goal of this project is to build a home automation system using a Raspberry Pi and a Node MCU board, with the internet controlled by the Telegram application. With the IoT idea, all household appliances and electrical equipment may be regulated automatically as well as manually via relay circuits.
SIGN LANGUAGE DETECTION USING LSTM NEURAL NETWORK
The main aim of the project is to create a user-friendly interface between normal people and deaf and dumb people. Humans communicate with one another using natural language channels such as words and writing, or by body language (gestures) such as hand motions, head gestures, facial expression, lip motion, and so forth. Comprehending sign language is equally as vital as understanding natural language. The predominant mode of communication is sign language among the deaf and the hearing-impaired people all over the world. sign language said to have different gestures where each gesture has specific meaning. Hearing-impaired people use sign language as their primary mode of communication. Without a translation, people with hearing impairments have difficulty speaking with other hearing people. As a result, implementing a system that recognises sign language would have a substantial positive impact on the social lives of deaf people. We propose a modified for continuous sequences of gestures, the LSTM model is used. also known as continuous SLD, that detects a series of related motions in this research. It is based on the division the division of a continuous symbol into sub-units and the modelling of these sub-units using neural networks. As a result, different combinations of sub-units are not necessary to be considered in the course of training. The suggestion is that approach has been put to the test with the help of Indian Sign Language signed sentences (ISL). Different sign terms are used to recognise these sign sentences.
PREDICTING SATELLITE TELEMETRY HEALTH PARAMETERS USING MACHINE LEARNING
In this paper, a methodology is used for predicting time series data which can be used for predicting spacecraft health parameters during non-visible period using the last received health parameters from the spacecraft (simulated parameters). Machine Learning based methodology to monitor telemetry parameters for early detection of anomalies and predicting trends is used. Explored different models and comparing them to see which one gives the best accuracy. We have proposed Machine learning using supervised learning algorithms like Long Short-Term Memory (LSTM) approach as it is well suited for solving this type of regression problem. LSTM is a special case of Recurrent Neural Networks (RNN) which is capable of learning long-term dependencies.
VISUAL QUESTIONING AND ANSWERING
In general, a VQA system is an algorithm that takes a picture and natural language query about the image as input and produces natural language response as output. The nature of a multi-discipline research problem necessitates this. This is a diagnostic dataset that assesses a variety of visual reason skills. VQA features few biases and through annotations defining the type of reasoning required for each question. The dataset is used to examine a number of recent visual reasoning systems, revealing new information about their capabilities and limitations.
HIGH RESOLUTION 3D HUMAN DIGITIZATION
Though noticeable development in the recent few years, the availability of 3D subjects is still shadowed by that of its 2D equivalent, many 2D-to-3D images, and video conversion methods have been exposed. Techniques that have human operators are mostly fruitful but also time-consuming and expensive, methods that classically make use of a deterministic 3D model, have not yet attained an equal range of excellence for they depend on hypotheses that are frequently disrupted in practical. In this paper, we put forth a new flair of methods that are based on a profoundly unalike line of attack to learn the 2D-to-3D conversion from paradigms. We demonstrate both the value and the computational efficiency of our methods on abundant 2Dimagesand discuss their limitations and remunerations.
AN ADVERSARIAL ROBUSTNESS ANALYSIS FRAMEWORK FOR CLASSIFICATION MODEL
In the ML/DL algorithms developed by researchers/developers, the only constraint faced by them is the robustness of the model. The model may be experimented with certain data sets but for the model to get tested with all the permutation and combination of data sets under different conditions is a challenge. For the model to give efficient and accurate results under all circumstances, the users are demanding a more robust model that has been analyzed thoroughly. We aim to create an algorithm that is unique, efficient and solves a real-world problem and build an Adversarial Robustness analysis framework that works on reinforcement learning, applies utility metrics of attacks and defense to give a comprehensive robustness report
AIR QUALITY PREDICTION AND ANALYSIS USING MACHINE LEARNING
The proposed system shows different models used for prediction of Air Quality Index (AQI) using various machine learning procedures. The system examines machine learning algorithm for air quality index by computing algorithm accuracy which will bring about the best precision. Moreover, the system shows various machine learning accuracy figures from the dataset values with assessment check report which recognize the proximity index. The results show the importance of ML suggested evaluation techniques which can be contrasted and best appropriateness with accuracy, realness and F1 Score. The air pollution datasets contain data for every state (zone) of India. Several machine learning algorithms like logistic regression, decision tree, support vector machine (SVM), random forest tree, Naïve Bayes theorem and K-nearest neighbor (KNN) are all parallels compared and evaluated.
AN EXPLORATION OF HEART DISEASE PREDICTION ALGORITHM USING MACHINE LEARNING TECHNIQUES
In Digital World, Heart Diseases play a vital role in the medical field. Heart Diseases caused due to pressure or emotional behavior. In developing countries like India, Heart Specialists are needed in semi-urban and rural areas with low financial support. So, Heart Prediction plays an important aspect in using machine learning with a classification algorithm. This paper explores the novelty of researchers’ predictive techniques to determine heart diseases using machine learning. This paper mainly explored three concepts of predictive techniques as Feature Selection, Classification Algorithm, and Evaluation of parameters. Classification of Algorithms for predictive techniques for heart diseases that provide effective and efficient performances.