Managing Internet of Things based traffic using Software Defined Networking

The current internet architecture cannot manage the massive data volumes produced by the smart IoT-based healthcare systems. Very recently, the idea of Software-Defined Networking (SDN) has surfaced to resolve the issues related to networking. The incorporation of SDN technology in IoT-based healthcare systems can possibly solve the existing quality of service and data management issues. Furthermore, the IoT-based healthcare system can attain enhanced Quality of Service (QoS) through the employment of such schemes that use shortest-path routing algorithms and offer higher bandwidth to lesser delay paths as per the QoS requirements. In this study, the SDN technology is integrated with IoT-based healthcare systems, and the delay is reduced for delay-sensitive applications by using the Bellman-Ford algorithm. The proposed scheme is deployed using the POX controller and can effectively handle the existing QoS issues in the IoT healthcare systems. The simulation results of the proposed scheme show a clear drop in delay values in comparison to the benchmark scheme.

Iterative non-rigid image registration in Brain MRI images

Non-rigid image registration plays a significant role in medical imaging domain. It involves deformations of moving image pixels according to fixed or reference image anatomy. The accurate image registration is required for accurate medical diagnosis and clinical applications. Non-rigid image registration uses optimization technique to find best possible solution. The solution obtained using single run of non-rigid image registration may be optimal but not much accurate. In order to increase accuracy in non-rigid image registration, multiple runs are required to improve the performance. Here in our research methodology, we used Demon algorithm as non-rigid image registration for brain MRI images of patient with tumor. There is significant improvement i.e., average of 66.61% decrease in error of the results of iterative Demon algorithm as compared to non-iterative Demon algorithm.

Context-Aware and Sequential Pattern Mining based recommendations for Research Papers: A Hybrid Approach

The availability of huge volumes of online research papers over scholarly communities has been increasing rapidly with the evolution of the Internet. Meanwhile, several researchers confront troubles while retrieving suitable and relevant research papers according to their research necessities due to information overload. Besides, the research necessities vary from researcher to researcher according to their contextual state and the online behavior in sequential access. Conventional recommendation approaches for instance content-based filtering (CBF) and collaborative filtering (CF) utilize content features and rankings correspondingly, in order to produce recommendations for the researchers. In spite of this, it is inevitable to incorporate scholar’s contextual information and sequential access behavior into the recommendation procedure to generate accurate and personalized recommendations for research papers. Conventional recommender systems do not incorporate such information in the recommended procedure to compute similarities of scholars and provide recommendations; thus, they are more liable to produce an irrelevant list of recommendations in a scholarly environment. Moreover, conventional recommendation approaches generate inaccurate recommendations in presence of a high level of sparsity in the rankings. In this article, we introduce a novel method for research paper recommendations that incorporates the benefits of collective filtering (CF), context-awareness, and sequential pattern mining (SPM) to propose research papers to scholars in a hybrid manner. Context-awareness in our methodology involves the scholar's contextual state, such as skill level and research goals; SPM is used to mine weblogs and reveal sequential access actions of scholars, and CF is used to measure predictions based on correlations between scholars and generate context-aware and sequential trend mining based recommendations for the targeted scholars. Experimental evaluations of our approach indicate the excellence of our approach over other baseline approaches in terms of precision, recall, F1, and mean absolute error (MAE).

AI-Enabled Elderly Care Robot

The increasing average human age and a growing number of old age population over the globe have emerged the need for automation in the health care domain. Eventually, health care robots will contribute to manage the workload of the care providers in the future health care domain. Elderly people face a major challenge to identify and pronounce names of daily use objects and different family and friends due to dementia-related issues. One of the many tasks by AI-Enabled elderly care humanoid robots will be communication with such patients. They will aid them to remember objects and persons they find difficult to identify and recognize due to dementia. This study has investigated the potential of the JD humanoid robot for object identification in such a scenario. The study has presented a prototype AI-Enabled elderly care robot that can aid elder persons to identify different objects. The robot is trained on ImageNet data set for object identification. Further, a personalized data set comprising of faces of different persons labeled by names of family and friends are also used to train robots for family recognition aid. The JD Humanoid robot captures an image of an object/person and also tracks it as the object/face moves. It identifies input images and outputs in audio format the name of the object/person to guide the elderly person. The third feature of the robot is the notifications of daily routine tasks for elder people like reminders for prayer, exercise walk, and medicine intake. Testing results have shown an object and person identification with 95% accuracy.

Design of Half Circular Disc Printed Monopole Antenna for Ultra Wide Band and Super Wide Band Applications

In this paper, a half-circular disc PMA (Printed Monopole Antenna) for SWB (Super Wide Band) applications is presented. The dimensions of the substrate is 40x40x1.7mm. The antenna is printed on Rogers RT5880 dielectric material. The antenna VSWR (Voltage Standing Wave Ratio) has less than 2 between 2.7 and 50 GHz. The antenna S11 has less than -10 between 2.7 and 50GHz. The antenna has a maximum gain of 12.4dBi. The BW (Bandwidth) of the proposed antenna is about 47.3 GHz. The antenna covered the WiMAX ((Worldwide Interoperability for Microwave Access), WLAN (Wireless Local Area Network), X band, Ka band, Ku band, 4G band, and the band of 5G (Fifth Generation) at the same time with nice gain and radiation efficiency. The radiator of the proposed antenna designs from a half-circular disc, rectangle, and triangle. The antenna has a partial ground plane. Three slots are etched in the ground plane for better impedance matching, two are circular slots and one is the rectangular slot. The antenna design is simulated in CST microwave studio 2016. The antenna has good radiation efficiency, other parameters such as VSWR S11, gain, and radiation pattern are discussed in detail.

Design and Implementation of Solar Tracker on Solar Panel

Energy is the necessity having utmost importance, also is a priority factor for the development of modern era countries. Current time calls for the bulk of energy supply as various nations are on the verge of the energy crisis, RE (Renewable Energy) resources like wind systems, solar panels, and tidal wave, etc. are the best options available in the current era for energy supply. The most abundant resource of RE is the solar system which is available from the sun itself. The sun is the source of sufficient energy supply and it can be used throughout the year. Electricity generation due to the reduction of fuels is the biggest challenge that will have adverse effects to be faced in the upcoming future. Electricity generation via solar energy is costly. Energy from PV (Photovoltaic) cells depends on solar insulation. Maximum energy extracted from the sun by the plane of the solar collector should be normal to incident radiation. Improving efficiency by the change in design then implement on solar tracker system to collect maximum solar power extraction with the association of the panels and the sun itself. The system tracks the maximum intensity of light by adjusting the panels to normal to incident light. The sun tracking system uses four light-dependent resistors used as a sensor for finding a brighter point in the sky. Rotating DC Motor can be controlled via signal and data processing based on micro-controller, by doing so the performance parameters of this system are now dependent on features such as solar radiation, hourly electrical power, the maximum gain of energy, additionally short circuit and open circuit current are compared with the fixed-tilt solar collector.

Radiation Pattern Reconfigurable Antenna for 5G Applications

This paper proposes a novel radiation pattern reconfigurable antenna for 5G (Fifth Generation) applications. A rectangular patch is enclosed by a hollow rectangular radiating structure. The patch is connected to the rectangular structure by two switches SW1 and SW2, which will, in turn, provide three different radiation patterns, Modes, depending on the ON and OFF states of the switches. When SW1 is OFF and SW2 is ON, Mode 1, pattern radiates in a direction with an angle of 38o. While SW1 is ON and SW2 is OFF, Mode 2, the pattern radiates in the radiating plane, exactly opposite to Mode 1, with an angle of -38o. In Mode 3, the pattern is directed simultaneously towards the angles of ±41o; for this case, both switches, SW1 and SW2, are turned OFF. The proposed design resonates in the constant 38GHz frequency range which is useful for 5G broadband cellular communication networks. And this design can also be used for 60 GHz resonant frequency with certain adjustments. Additionally, the return loss is -31.5 to -42.5, while directivity is from 5.69-6.76dB, and gain lies in the range of 5.4- to 6.4dBi. Moreover, Voltage Standing Wave Ratio, VSWR, varies from 1.01 to 1.05. The size of the antenna is 3.34x6.73mm2 which is mounted on a 0.381 mm thick, Roger RT5880 having a relative permittivity of 2.2. Central Standard Time, (CST) microwave studio software is used for simulating the design. The miniscule size, a smaller value of the return loss, an ideal value of VSWR with a reasonable value of directivity and gain make the proposed design best for future 5G mobile communications.

SMOTEMultiBoost: Leveraging the SMOTE with MultiBoost to Confront the Class Imbalance in Supervised Learning

Class imbalance problem is being manifoldly confronted by researchers due to the increasing amount of complicated data. Common classification algorithms are impoverished to perform effectively on imbalanced datasets. Larger class cases typically outbalance smaller class cases in class imbalance learning. Common classification algorithms raise larger class performance owing to class imbalance in data and overall improvement in accuracy as their goal while lowering performance on smaller class. Furthermore, these algorithms deal false positive and false negative in an even way and regard equal cost of misclassifying cases. Meanwhile, different ensemble solutions have been proposed over the years for class imbalance learning but these approaches hamper the performance of larger class as emphasizing on the small class cases. The intuition of this overall degraded outcome would be the low diversity in ensemble solutions and overfitting or underfitting in data resampling techniques. To overcome these problems, we suggest a hybrid ensemble method by leveraging MultiBoost ensemble and Synthetic Minority Over-sampling TEchnique (SMOTE). Our suggested solution leverage the effectiveness of its elements. Therefore, it improves the outcome of the smaller class by reinforcing its space and limiting error in prediction. The proposed method shows improved performance as compare to numerous other algorithms and techniques in experiments.