With the rapid development and ubiquitous usage of Wireless Local Area Networks (WLAN), Location Based Systems (LBS) employing Signal Strength techniques have become an attractive area of research for location estimation in indoor environments. In this paper we propose a robust fingerprint method for localization based on the traditional KNearest Neighbor (KNN) method. Instead of considering a fixed number of neighbors, our approach uses an adaptive method to determine the optimal number of neighbors to be taken into account. . In order to prove the effectiveness of our method, we compare it with the traditional KNN approaches for a variety of number of Access Points (APs). Simulation results using MultiWall-Floor path loss model show that the proposed method yields an improved accuracy as compared with the traditional methods.

Consequence of thermal and concentration convection on peristaltic pumping of hyperbolic tangent nanofluid in a non-uniform channel and induced magnetic field is discussed in this article. The brief mathematical modeling, along with induced magnetic field, of hyperbolic tangent nanofluid is given. The governing equations are reduced to dimensionless form by using appropriate transformations. Exact solutions are calculated for temperature, nanoparticle volume fraction, and concentration. Numerical technique is manipulated to solve the highly non-linear differential equations. The roll of different variables is graphically analyzed in terms of concentration, temperature, volume fraction of nanoparticles, axial induced magnetic field, magnetic force function, stream functions, pressure rise, and pressure gradient.

The impact of lateral walls and partial slip with different waveforms on peristaltic pumping of couple stress fluid in a rectangular duct with different waveforms has been discussed in the current article. By means of a wave frame of reference the flow is explored travelling away from a fixed frame with velocity c. Peristaltic waves generated on horizontal surface walls of rectangular duct are considered using lubrication technique. Mathematical modelling of couple fluid for three-dimensional flow are first discussed in detail. Lubrication approaches are used to simplify the proposed problem. Exact solutions of pressure gradient, pressure rise, velocity and stream function have been calculated. Numerical and graphical descriptions are displayed to look at the behaviour of diverse emerging parameters.

The effects of induced magnetic field, thermal and concentration convection on the peristaltic flow of Prandtl nanofluids are explored in this study in an inclined asymmetric channel. A detailed mathematical explanation is given for Prandtl nanofluids with double-diffusivity convection and induced magnetic field. To simplify non-linear partial differential equations, the long wavelength and low approximation of the Reynolds number are used. Using numerical technique, the non-linear differential equations are solved. Exact solutions of thermal and concentration are calculated. The impact of the various physical parameters of flow quantities is shown in graphical results.

Adverse drug reactions (ADRs) are the undesirable effects associated with the use of a drug due to some pharmacological action of the drug. During the last few years, social media has become a popular platform where people discuss their health problems and, therefore, has become a popular source to share information related to ADR in the natural language. This paper presents an end-to-end system for modelling ADR detection from the given text by fine-tuning BERT with a highly modular Framework for Adapting Representation Models (FARM). BERT overcame the predominant neural networks bringing remarkable performance gains. However, training BERT is a computationally expensive task which limits its usage for production environments and makes it difficult to determine the most important hyperparameters for the downstream task. Furthermore, developing an end-to-end ADR extraction system comprising two downstream tasks, i.e., text classification for filtering text containing ADRs and extracting ADR mentions from the classified text, is also challenging. The framework used in this work, FARM-BERT, provides support for multitask learning by combining multiple prediction heads which makes training of the end-to-end systems easier and computationally faster. In the proposed model, one prediction head is used for text classification and the other is used for ADR sequence labeling. Experiments are performed on Twitter, PubMed, TwiMed-Twitter, and TwiMed-PubMed datasets. The proposed model is compared with the baseline models and state-of-the-art techniques, and it is shown that it yields better results for the given task with the F -scores of 89.6%, 97.6%, 84.9%, and 95.9% on Twitter, PubMed, TwiMed-Twitter, and TwiMed-PubMed datasets, respectively. Moreover, training time and testing time of the proposed model are compared with BERT’s, and it is shown that the proposed model is computationally faster than BERT.