Search

Digitalization of music is the new trend, and preferences of individuals are highly rated. Millions of songs are being streamed in the music applications. The companies providing these services need to sort and arrange a wide range of music tastes for all of its users. On top of that, fresh music from various artists in a wide spectrum of genres are popping up every day. To keep track of all this, a classification system can be handy. So, we propose an RNN based model based on Natural Language processing to classify the songs based on their lyrics into different genres [1]. Additionally, this tool can be handy to the music lovers for quickly identifying which genre a particular song belongs to. In this paper, we apply Long Short Term Memory (LSTM) model with both Universal Serial Embedder (USE) and Bert embedders. A comparative study is performed to understand which combination of models works based to classify the genres based on lyrics. From our results, on the basis of accuracy of the model, we found that USE embedder with LSTM [2] gives a slightly better performance than Bert embedder. The LSTM model with USE embedding gave the highest accuracy of 83.42% when trained over a range of five folds. [ABSTRACT FROM AUTHOR]

Chatbot is an intelligent system which simply defines human-to-machine interaction and this chatbots are biggest development trend today. Contacting customer centers or going to bank for banking related queries invests lot of time and human effort, further the customer may get insufficient information and may have uncertainty through this process. This paper aims to convey the development of Banking Chatbot that gives guidance regarding the services provided by bank and provides detailed descriptions to the user's query. This Chatbot is user friendly to communicate with and it is an easy way to get response on time. To overcome the difficulty web application using Natural language processing and neural network is developed [1]. NLP is an added advantage to make chatbot understand user queries. The operations in this Banking Chatbot include viewing beneficiaries and post queries regarding banking services. [ABSTRACT FROM AUTHOR]

In this we presented a machine learning technique, which is specifically a deep learning model, for predicting high blood pressure through these following features (Blood pressure Abnormality, Level of Hemoglobin, , Age, BMI, Sex, Genetic Pedigree Coefficient ,Smoking, Physical activity, salt content in the diet, alcohol consumption per day, kidney disease, Adrenal and thyroid disorders). Here, it uses the technique by using a dataset which contains features/factors. Our dataset was spitted into two parts: One for training and one for testing of the neural networks. Neural network algorithm, Binary Classification, is used to construct the prediction system. The predicted accuracy of high blood pressure predictor was about 84%. The results of our model are to show the prediction of blood pressure. This model helps in predicting the high blood pressure which helps in giving the warnings at the early stage. [ABSTRACT FROM AUTHOR]

Economy of any country is investment in stock market. Stock price can be affected by factors which are running in current world and stock market. One of the most important things is to predict the how stock market will do. In stock market prediction machine learning has significant applications. Accurate stock market predication results are biggest challenge, because financial stock markets are volatile in nature. Forecasting stock market price is one of the most popular research areas for researchers. In this article, we had designed a model to predict the stock price of a particular company by analysing its previous data i.e. previous stock prices. We had analysed around 1300 stock prices of company, find the graph of company and created a model to predict present stock price. In this paper, we discussed about what is stock market prediction, how to predict with machine learning, analysed on some set of data and present results of our analysis. [ABSTRACT FROM AUTHOR]

Recommendation systems play a vital role in our day to day lives whether it may provide recommendation on which movie to watch or which item to buy. Most of the popular e-commerce websites are now a day's using recommender system gathering customer preferences like Amazon and Flipkart for selling their products. Similar to that we have music streaming applications like wynk and gaana.com which also provide recommendations to its users. These recommendations systems will benefit both the business and the users, the business are getting benefits and users are getting what they like.In this paper we have investigated music recommendation systems like content based filtering and collaborative filtering which provides music recommendations[1].We also tried to draw correlation between users and songs to provide recommendations as to which user would prefer to listen to which music based on their listening history. For this investigation we used the million song dataset available from kaggle.We used both the content based filtering and collaborate filtering algorithms to provide best music recommendation. Finally we also compared the accuracy levels of both the recommendation systems[2]. [ABSTRACT FROM AUTHOR]

Linguistic Correction is the process of showing the mistakes done by the users while framing a sentence. This includes grammatical errors, spelling errors, phonetic errors, and typing errors. Linguistic Correction helps the user to correct the mistake in their sentence. This allows the user to experiment and figure out the sentence mistakes. As mentioned above, the linguistic Correction helps the user figure out the above errors and answer whether the typed sentence by the user is grammatically correct or incorrect. The model trains the actual set of sentences and their results. One among them was the BERT model, where it reads or interprets the sentences from two ways, left and right, and does analysis, which gives us a trained model that can be put to figure out whether the sentences are grammatically incorrect or correct. [ABSTRACT FROM AUTHOR]

There is a tremendous increment of liver sickness patients as a result of exorbitant utilization of liquor, breathe in of hurtful gases, admission of polluted food, pickles and medications. Therefore lot of burden is put on the doctors to identify a patient whether he is having any liver disease are not.This paper helps to reduce the burden on the doctor by analyzing patients conditions using machine learning techniques[1]. We also make a comparison of few machine learning algorithms like random forest,logistic regression and SVM and compare their accuracy levels in predicting the liver disease. [ABSTRACT FROM AUTHOR]

By using of Internet of Things headways in canny place, savvy clinical stations play an inexorably more basic activity in our consistently life. These consoles can screen our context and acquire many of clinical data in time. For security and sensibility in data, the accumulated tremendous data can be mixed and a short time later set aside on a cloud laborer with the ultimate objective that solitary endorsed customers, for instance, the data owner and the masters, can get to. In any case, clever terminals are commonly obliged in enrolling power and customers' security issues remain. To deal with this troublesome issue, a compelling clinical sharing of data arrangement is given in the paper. To disentangle the security issues in customers' data sharing, to enable data sharing we use credit based encryption. Moreover, we oust the trademark making plans limit and use the credit sprout channel to disguise all the properties within the passage manipulate structure. To refine the capability of encryption, we present the on the web/detached encryption development in the encryption stage. A great deal of work that is required on the encryption step could be done before the information is known. By then, when known message is there, the code text can be made fastly. In addition to presentation period of the system doesn't allow to show the properties. Exactly when all characteristics of the system for customers increase, the structure shouldn't be reinitialized, which will in like manner to refine the efficiency of structure, assessment of security and execution examination show that the data sharing arrangement is ensure about and can upgrade information taking care of limit in IoT based data sharing. [ABSTRACT FROM AUTHOR]