Wind speed forecasting is the term used for predicting speed of wind to generate wind power. Deep learning, which is the subfield of machine learning and is used to implement on a large data sets and predictions made using deep learning with LSTM can increases the accuracy rate to the great extent. The combination of deep learning with LSTM can enhances the prediction rate as due to the property of LSTM of pattern remembrance for longer duration of time. This survey discusses the existing functionality measures of different approaches by partitioning them into various methodologies: models of very small time gap, small time gap, and longtime gap. All these approaches include certain models with various parameters, advantages and disadvantages are discussed. The focus of this survey is to present a better and efficient evaluation of various approaches to help the researcher to select best model out of all present models.

The term which is used to predict wind speed to produce wind power is wind speed forecasting. Deep learning, is a form of AI, basically indulging in artificial intelligence and thus can greatly increase the precision rate on larger datasets. In this research paper, the two techniques are being used together to obtain the better forecasting results. Both the techniques are forecasting based and combining LSTM and deep learning can increase the forecast rate because of the pattern remembering attribute of LSTM over a longer interval/period of time. If there is the inclusion of the ARIMA model the likelihood of a future value lying between two indicated limits is increased. So, overall if both the techniques are hybridized than it is most probable that the obtained results should be more accurate than both the techniques used separately. So, the main focus of this research article is on the efficiency and evaluation of hybridized LSTM-ARIMA model to predict wind speed forecasting.

A mobile agent is a software application that moves naturally among hosts in a uniform and non-uniform environment; it starts with one host and then moves onto the next in order to divide data between clients. The mobile paradigm is utilized in a wide assortment of medical care applications such as the medical information of a patient, the recovery of clinical information, the incorporation of information pertaining to their wellbeing, dynamic help, telemedicine, obtaining clinical data, patient administration, and so on. The accompanying security issues have grown in tandem with the complexity and improvements in mobile agent technologies. As mobile agents work in an insecure environment, their security is a top priority when communicating and exchanging data and information. Data integrity, data confidentiality and authentication, on-repudiation, denial of service, and access control, are all key security concerns with mobile agent migration. This paper proposes a Verifiable, Secure Mobile Agent Migration model, based on two polynomials (t, n), and an edge secret imparting plan with Blowfish encryption, to enable secure information transmission in clinical medical care.

Electrical load forecasting is an essential feature in power systems planning, operation and control. The non-linearity and non-stationary nature of the data, however, poses a challenge in terms of accuracy. This article explores a deep learning technique, a long short-term memory recurrent neural network-based framework to tackle this tricky issue. The proposed machine learning model framework is tested on real time residential smart meter data showing promising results. A web application has also been developed to allow consumers to have access to greater levels of information and facilitate decision-making at their end. The performance of the proposed model is also comprehensively compared to other methods in the field of load forecasting showing more accurate results for the function of forecasting of load on short term basis.

An Optimized Approach Using Transfer Learning to Detect Drunk Driving: Although the statistics show a slow decline in traffic accidents in many countries over the last few years, drunk or drug-influenced driving still contributes to enough shares in those records to act. Nowadays, breath analysers are used to estimate breath alcohol content (BAC) by law enforcement as a preliminary alcohol screening in many countries. Therefore, since breath analysers or field sobriety testers do not accurately measure BAC, the analysis of blood samples of individuals is required for further action. Many researchers have presented various approaches to detect drunk driving, for example, using sensors, face recognition, and a drivers behaviour to confound the shortcomings of the time-honoured approach using breath analysers. But each one has some limitations. This study proposed a plan to distinguish between drivers states, that is, sober or drunk, by the use of transfer learning from the convolutional neural network (CNN) features to the random forest (RF) features with an accuracy of up to 93, which is higher than that of existing models. With the same dataset, to validate our research, a comparative analysis was performed with other existing model classifiers such as the simple vector machine (SVM) with an accuracy of 65 and the K-nearest neighbour (KNN) with an accuracy of 62, and it was found that our approach is an optimized approach in terms of accuracy, precision, recall, F1-score, AUC-ROC curve, and Matthews correlation coefficient (MCC) with confusion matrix.