Deep learning methods for fingerprint-based indoor positioning: a review

ABSTRACT

Outdoor positioning systems based on the Global Navigation Satellite System have several shortcomings that have deemed their use for indoor positioning impractical. Location fingerprinting, which utilizes machine learning, has emerged as a viable method and solution for indoor positioning due to its simple concept and accurate performance. In the past, shallow learning algorithms were traditionally used in location fingerprinting. Recently, the research community started utilizing deep learning methods for fingerprinting after witnessing the great success and superiority these methods have over traditional/shallow machine learning algorithms. This paper provides a comprehensive review of deep learning methods in indoor positioning. First, the advantages and disadvantages of various fingerprint types for indoor positioning are discussed. The solutions proposed in the literature are then analyzed, categorized, and compared against various performance evaluation metrics. Since data is key in fingerprinting, a detailed review of publicly available indoor positioning datasets is presented. While incorporating deep learning into fingerprinting has resulted in significant improvements, doing so, has also introduced new challenges. These challenges along with the common implementation pitfalls are discussed. Finally, the paper is concluded with some remarks as well as future research trends.     

Transition metal nanoparticles doped carbon paper as a cost-effective anode in a microbial fuel cell powered by pure and mixed biocatalyst cultures

The poor wettability and high cost of the carbonaceous electrodes materials prohibited the practical applications of microbial fuel cells (MFCs) on large scale. Here, a novel nanoparticles of metal sheathed with metal oxide is electrodeposited on carbon paper (CP) to introduce as high-performance anodes of microbial fuel cell (MFC). This thin layer of metal/metal oxide significantly enhance the microbial adhesion, the wettability of the anode surface and decrease the electron transfer resistance. The investigation of the modified CP anodes in an air-cathode MFCs fed by various biocatalyst cultures shows a significant improving in the MFC performance. Where, the generated power and current density was 140% and 210% higher as compared to the pristine CP. Mixed culture of exoelectrogenic microorganism in wastewater exhibited good performance and generated higher power and current density compared to yeast as pure culture. The excellent capacitance with a distinctive nanostructure morphology of the modified-CP open an avenues for practical applications of MFCs.     

Axiomatic design principles in analysing the ergonomics design parameter of a virtual environment

One of the negative side effects experienced by users when interacting with virtual environment is visual symptoms. This paper explores the ergonomics design parameters of the virtual environment to minimize such negative side effect by applying axiomatic design principles. Axiomatic design is a method to provide a systematic way for designing products and large systems. The independence axiom is used to map customer domain (CAs) to functional domain (FRs) and physical domain (DPs). A paper based survey was conducted to identify and define customers' preference in the virtual environment. A virtual robot manufacturing system was developed as a case study to explore ergonomic design parameters that satisfy the independence of FRs and CAs. Results of this study shows that the ergonomic design parameters of virtual environment identified (DP₁₆₁-DP₁₆₂-DP₁₂₁-DP₁₁₁-DP₁₃₁-DP₁₄₁-DP₁₅₁-DP₁₅₂) have satisfied the independence functional requirement and desired visual comfort for users. By uncoupling the design it provides an efficient and effective sequence of design activities FR₁₆₁-FR₁₆₂-FR₁₂₁-FR₁₁₁-FR₁₃₁-FR₁₄₁-FR₁₅₁-FR₁₅₂.     

Participatory Irrigation Management and Transfer: Setting the Guiding Principles for a Sustaining Monitoring & Evaluation System – a Focus on the Mediterranean

A major shortcoming of Participatory Irrigation Management and Irrigation Management Transfer (PIM/IMT) is the absence of Monitoring & Evaluation (M&E) systems that accompany these processes and become a major instrument to correct, improve and learn. Although at the global level some countries have exerted efforts to implement M&E systems, these still present limitations, as the review of the international experiences shows. The Mediterranean situation is even more dramatic since only Tunisia implements an M&E system, whereas Egypt has shyly moved in this direction with a limited practical application. This state of affairs led the authors to develop a set of guiding principles to develop an M&E system to be applied in countries where PIM/IMT is adopted. This paper revises the main international efforts devoted to assess the performance of PIM/IMT and the state of the art of these processes in Southern and Eastern Mediterranean Countries. Moreover, it sets the framework and analyses the main sustaining factors for the development of a new M&E system for these countries.     

On‐line opto‐viscoelastic analysis of polypropylene fibres using multiple‐beam Fizeau fringes in transmission and a modified creep device

A creep device attached to an automated multiple‐beam Fizeau system in transmission was modified with a designed digital ruler. This device allows on‐line measurements of fibre length during creep experiments in terms of an analogue voltage value. The influence of sustained stress values on creep deformation and optical properties (n^||, n^? and Δn) for polypropylene (PP) fibres was studied interferometrically. The opto‐viscoelastic properties of PP fibres were determined for three different values of constant applied stress of 11.536, 18.717 and 25.905 MPa, at room temperature. Also, the variations of the cross‐sectional area and Poisson's ratio were studied during creep extensions. The compliance curves were obtained as a function of both time and applied stresses. Empirical formulae are suggested to describe the creep compliance curves for PP fibres, and the constants of these formulae were determined and described at each applied stress. A Kelvin chain was used to model the mechanical behaviour of the PP fibres under study. The effect of strain on the mean refractive indices, orientation function density and crystallinity was investigated as a result of the recorded data. Microinterferograms are given for illustration. The modified creep device with the designed digital ruler enables one to obtain instantaneous automatic accurate recording of fibre length values during creep experiments. Calculation of refractive indices, orientation function and crystallinity shows a difference in material behaviour at small stresses from that at higher stresses which may be attributed to different strain rates caused by different stresses. Copyright © 2010 Society of Chemical Industry     

Exact analytic solitary wave solutions for the RKL model

Interest in finding exact solitary wave solutions of nonlinear evolution equations by means of different methods has grown steadily in recent years. These exact solutions are important to understand the mechanism of the complicated nonlinear physical phenomena. By use of the Jacobi elliptic function method, we find the exact analytic solitary wave solutions for the RKL model with cubic-quintic non-Kerr terms, describing the propagation of extremely short pulses in optical fibers. These new solutions may be useful for describing the propagation of optical pulses in non-Kerr media.     

Micro-capacitors based on electrochemically grown vertical arrays of gold nanowires as electrodes

This paper describes the development of micro-capacitors with electrodes based on electrochemically grown vertical gold nanowire arrays. A high aspect-ratio anodized aluminum oxide template integrated on silicon dioxide/silicon substrates was exploited for fabricating a vertical array of nanowires with a high surface to volume ratio. Bismuth ferric oxide thin films were deposited to create high dielectric material between the electrodes using room temperature electrodeposition. This nanofabrication process may be compatible with a complementary metal-oxide-semiconductor (CMOS) process, therefore, this capacitor can be used for protecting and regulating the surge voltage biased to the CMOS circuits. This capacitor achieved a high density capacitance of 3.1 μF/m² at 1 MHz, which was measured using a parallel plate set-up.     

Analysis of outdoor solar storage tanks having translucent insulation

A heat transfer model of a parallelepiped tank, full of water and covered with translucent insulation of diffuse material to solar energy, is developed considering the multiple absorptions and reflections to evaluate the heat gain or loss by water. The effect of the optical properties and thickness of insulation on that heat gained or lost by water is investigated. The results of a comparative study show that translucent insulation is more effective than opaque insulation and no insulation as far as the energy gained by water is concerned for outdoor solar storage tanks.     

W-CDMA Uplink Capacity and Interference Statistics of a Long Tunnel Cigar-shaped Microcells Using the Hybrid Model of Propagation with Imperfect Power Control

The uplink capacity and the interference statistics (mean and variance) of the sectors of the cigar-shaped W-CDMA microcell are studied. A model with eighteen sectors is used to analyze the uplink. The microcells are assumed to exist in a long tunnel with at least nine base stations. The hybrid model of propagation is used in the calculations. The capacity and the interference statistics of the sectors are studied in terms of the most important parameters: sector radius, specific attenuation factor, antenna sidelobe levels, bend losses and the power control standard deviation error.     

Comparison of spectral fluorescent signatures-based models to characterize DOM in treated water samples

Statistical procedures enable a multivariate analysis of the measurements to identify specific characteristics of the dissolved organic matter (DOM) fractions in raw natural water, including the concentrations. In this work, three already established models were used to predict the concentrations of fractions of DOM from spectral fluorescent signatures (SFSs): a general linear regression (GLR), loadings and scores of a principal components analysis (PCA), and a partial least squares regression (PLS). Details about the method undertaken to prepare the fractions were given. Water samples from surface water treatment plants in New Jersey were used for the testing. In all cases, PLS have shown much better biases and accuracies than GLR and PCA models. Hydrophilic neutral, however, showed poor performances (bias 33%) due to the isolation technique used. Recommendations were provided in order to improve the DOM characterization through SFS, which linked to PLS make a powerful and cost-effective surrogate parameter to characterize DOM.