Current Issue : October - December Volume : 2018 Issue Number : 4 Articles : 5 Articles
Variable techniques have been used to collect traffic data and estimate traffic conditions. In most cases, more than one technology\nis available. A legitimate need for research and application is how to use the heterogeneous data from multiple sources and provide\nreliable and consistent results. This paper aims to integrate the traffic features extracted from the wireless communication records\nand the measurements from the microwave sensors for the state estimation. A state-space model and a Progressive Extended\nKalman Filter (PEKF) method are proposed.The results from the field test exhibit that the proposed method efficiently fuses the\nheterogeneous multisource data and adaptively tracks the variation of traffic conditions. The proposed method is satisfactory and\npromising for future development and implementation....
After demonstrating, in previous works, the proof of concept of adaptive rectifiers with\nactive load modulation to operate simultaneously for short/long range RF Wireless Power Transfer\n(WPT) while maintaining a high Power Conversion Efficiency (PCE), the authors introduced in this\npaper a power link budget of the proposed adaptive rectifier with a compromise between distance\nand efficiency. Then, to further exhibit its capabilities and enhance its performance, this paper first\nintroduced a discussion about the parameters preventing the rectifier from operating over a wide\nrange of input powers was performed. Furthermore, active load modulation was implemented\nand its co-simulation results presented. Finally, an adaptive rectifier was fabricated and its results\nsuccessfully compared to measured data. It exhibits 40% of PCE over a wide dynamic input range of\nincident RF power levels from âË?â??6 to 25 dBm at the 900 MHz in the Industrial Scientific Medical band\n(ISM band), with a maximum PCE of 66% for an input power of 15 dBm. The proposed devices are\ntherefore suitable for WPT applications to harvest energy from a controlled source....
Many supervised classification algorithms have been proposed, however, they\nare rarely evaluated for specific application. This research examines the performance\nof machine learning classifiers support vector machine (SVM),\nneural network (NN), Random Forest (RF) against maximum classifier\n(MLC) (traditional supervised classifier) in forest resources and land cover\ncategorization, based on combination of Advanced Land Observing Satellite\n(ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) and\nLandsat Thematic Mapper (TM) data, in Northern Tanzania. Various data\ncategories based on Landsat TM surface reflectance, ALOS PALSAR backscattering\nand their derivatives were generated for various classification scenarios.\nThen a separate and joint processing of Landsat and ALOS PALSAR\ndata were executed using SVM, NN, RF and ML classifiers. The overall classification\naccuracy (OA), kappa coefficient (KC) and F1 score index values were\ncomputed. The result proves the robustness of SVM and RF in classification of\nforest resource and land cover using mere Landsat data and integration of\nLandsat and PALSAR (average OA = 92% and F1 = 0.7 to 1). A two sample\nt-statistics was utilized to evaluate the performance of the classifiers using different\ndata categories. SVM and RF indicate there is no significance difference\nat 5% significance level. SVM and RF show a significant difference when\ncompared to NN and ML. Generally, the study suggests that parametric classifiers\nindicate better performance compared to parametric classifier....
In the last decade, a large amount of data has been published in different fields\nand can be used as a data source for research and study. However, identifying\na specific type of data requires processing, which involves machine learning\nclassifying techniques. To facilitate this, we propose a general framework that\ncan be applied to any social media content to develop an intelligent system.\nThe framework consists of three main parts: an interface, classifier and analyzer.\nThe analyzer uses media recognition to identify specific features. Then,\nthe classifier uses these features and involves them in the classification\nprocess. The interface organizes the interaction between the system components.\nWe tested the framework and developed a system to be applied to image-\nbased social media networks (Instagram). The system was implemented\nas a mobile application (My Interests ) that works as a recommendation and\nfiltering system for Instagram users and reduces the time they spend on irrelevant\ninformation. It analyzes the images, categorizes them, identifies the interesting\nones, and finally, reports the results. We used the Cloud Vision API\nas a tool to analyze the images and extract their features. Furthermore, we\nadapted support vector machine (SVM), a machine learning method, to\nclassify images and to predict the preferred ones....
The way by which one can make sure the operating mode of the modulation is\nby observing the Comsol results of the designed model of proposed acousto-\noptic modulator (AOM). These results include the pressure distribution,\nsound pressure distribution, stress distribution at piezoelectric, far-field analysis\nthat describes the diffracted light orders, and electric potential versus light\nfrequency. Throughout the simulating process of modulator operating using\nComsol, it begins when the RF is power by a voltage of 100 V, the light is then\nsplit into first ordered diffraction, which implies that the modulator is in the\noperating mode. The use of semiconductor materials is due to its smaller gap\nthat easily transfers the energy that leads to generating first order diffraction\nwhen they provided a voltage power. It mentioned that zero order diffraction\nindicates the modulator does not run; other orders are appearing with increasing\nthe frequency of light leading to decrease of the efficiency of the\nmodulator performance....
Loading....