| 51. |
- Alam, Md. Eftekhar, et al.
(författare)
-
An IoT-Belief Rule Base Smart System to Assess Autism
- 2018
-
Ingår i: Proceedings of the 4th International Conference on Electrical Engineering and Information & Communication Technology (iCEEiCT 2018). - : IEEE. - 9781538682791 - 9781538682807 ; , s. 671-675
-
Konferensbidrag (refereegranskat)abstract
- An Internet-of-Things (IoT)-Belief Rule Base (BRB) based hybrid system is introduced to assess Autism spectrum disorder (ASD). This smart system can automatically collect sign and symptom data of various autistic children in realtime and classify the autistic children. The BRB subsystem incorporates knowledge representation parameters such as rule weight, attribute weight and degree of belief. The IoT-BRB system classifies the children having autism based on the sign and symptom collected by the pervasive sensing nodes. The classification results obtained from the proposed IoT-BRB smart system is compared with fuzzy and expert based system. The proposed system outperformed the state-of-the-art fuzzy system and expert system.
|
|
| 52. |
- Alberti, M., et al.
(författare)
-
DeepDIVA : A Highly-Functional Python Framework for Reproducible Experiments
- 2018
-
Ingår i: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018. - : IEEE. - 9781538658758 ; , s. 423-428
-
Konferensbidrag (refereegranskat)abstract
- We introduce DeepDIVA: an infrastructure designed to enable quick and intuitive setup of reproducible experiments with a large range of useful analysis functionality. Reproducing scientific results can be a frustrating experience, not only in document image analysis but in machine learning in general. Using DeepDIVA a researcher can either reproduce a given experiment or share their own experiments with others. Moreover, the framework offers a large range of functions, such as boilerplate code, keeping track of experiments, hyper-parameter optimization, and visualization of data and results. To demonstrate the effectiveness of this framework, this paper presents case studies in the area of handwritten document analysis where researchers benefit from the integrated functionality. DeepDIVA is implemented in Python and uses the deep learning framework PyTorch. It is completely open source(1), and accessible as Web Service through DIVAServices(2).
|
|
| 53. |
- Albertsson, Kim, et al.
(författare)
-
Machine Learning in High Energy Physics Community White Paper
- 2018
-
Ingår i: Journal of Physics, Conference Series. - : Institute of Physics (IOP). - 1742-6588 .- 1742-6596. ; 1085
-
Tidskriftsartikel (refereegranskat)abstract
- Machine learning is an important applied research area in particle physics, beginning with applications to high-level physics analysis in the 1990s and 2000s, followed by an explosion of applications in particle and event identification and reconstruction in the 2010s. In this document we discuss promising future research and development areas in machine learning in particle physics with a roadmap for their implementation, software and hardware resource requirements, collaborative initiatives with the data science community, academia and industry, and training the particle physics community in data science. The main objective of the document is to connect and motivate these areas of research and development with the physics drivers of the High-Luminosity Large Hadron Collider and future neutrino experiments and identify the resource needs for their implementation. Additionally we identify areas where collaboration with external communities will be of great benefit.
|
|
| 54. |
|
|
| 55. |
|
|
| 56. |
- Alhashimi, Anas, 1978-, et al.
(författare)
-
Bayesian strategies for calibrating heteroskedastic static sensors with unknown model structures
- 2018
-
Ingår i: 2018 European Control Conference (ECC). - Piscataway, NJ : IEEE. - 9783952426982 - 9781538653036 ; , s. 2447-2453
-
Konferensbidrag (refereegranskat)abstract
- This paper investigates the problem of calibrating sensors affected by (i) heteroskedastic measurement noise and (ii) a polynomial bias, describing a systematic distortion of the measured quantity. First, a set of increasingly complex statistical models for the measurement process was proposed. Then, for each model the authors design a Bayesian parameters estimation method handling heteroskedasticity and capable to exploit prior information about the model parameters. The Bayesian problem is solved using MCMC methods and reconstructing the unknown parameters posterior in sampled form. The authors then test the proposed techniques on a practically relevant case study, the calibration of Light Detection and Ranging (Lidar) sensor, and evaluate the different proposed procedures using both artificial and field data.
|
|
| 57. |
- Alhashimi, Anas, 1978-, et al.
(författare)
-
Modeling and Calibrating Triangulation Lidars for Indoor Applications
- 2018
-
Ingår i: Informatics in Control, Automation and Robotics. - Cham : Springer. - 9783319550107 - 9783319550114 ; , s. 342-366
-
Bokkapitel (refereegranskat)abstract
- We present an improved statistical model of the measurement process of triangulation Light Detection and Rangings (Lidars) that takes into account bias and variance effects coming from two different sources of uncertainty: (i) mechanical imperfections on the geometry and properties of their pinhole lens - CCD camera systems, and (ii) inaccuracies in the measurement of the angular displacement of the sensor due to non ideal measurements from the internal encoder of the sensor. This model extends thus the one presented in [2] by adding this second source of errors. Besides proposing the statistical model, this chapter considers: (i) specialized and dedicated model calibration algorithms that exploit Maximum Likelihood (ML)/Akaike Information Criterion (AIC) concepts and that use training datasets collected in a controlled setup, and (ii) tailored statistical strategies that use the calibration results to statistically process the raw sensor measurements in non controlled but structured environments where there is a high chance for the sensor to be detecting objects with flat surfaces (e.g., walls). These newly proposed algorithms are thus specially designed and optimized for inferring precisely the angular orientation of the Lidar sensor with respect to the detected object, a feature that is beneficial especially for indoor navigation purposes.
|
|
| 58. |
- Alhashimi, Anas, 1978-
(författare)
-
Statistical Sensor Calibration Algorithms
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The use of sensors is ubiquitous in our IT-based society; smartphones, consumer electronics, wearable devices, healthcare systems, industries, and autonomous cars, to name but a few, rely on quantitative measurements for their operations. Measurements require sensors, but sensor readings are corrupted not only by noise but also, in almost all cases, by deviations resulting from the fact that the characteristics of the sensors typically deviate from their ideal characteristics.This thesis presents a set of methodologies to solve the problem of calibrating sensors with statistical estimation algorithms. The methods generally start with an initial statistical sensor modeling phase in which the main objective is to propose meaningful models that are capable of simultaneously explaining recorded evidence and the physical principle for the operation of the sensor. The proposed calibration methods then typically use training datasets to find point estimates of the parameters of these models and to select their structure (particularlyin terms of the model order) using suitable criteria borrowed from the system identification literature. Subsequently, the proposed methods suggest how to process the newly arriving measurements through opportune filtering algorithms that leverage the previously learned models to improve the accuracy and/or precision of the sensor readings.This thesis thus presents a set of statistical sensor models and their corresponding model learning strategies, and it specifically discusses two cases: the first case is when we have a complete training dataset (where “complete” refers to having some ground-truth informationin the training set); the second case is where the training set should be considered incomplete (i.e., not containing information that should be considered ground truth, which implies requiring other sources of information to be used for the calibration process). In doing so, we consider a set of statistical models consisting of both the case where the variance of the measurement error is fixed (i.e., homoskedastic models) and the case where the variance changes with the measured quantity (i.e., heteroskedastic models). We further analyzethe possibility of learning the models using closed-form expressions (for example, when statistically meaningful, Maximum Likelihood (ML) and Weighted Least Squares (WLS) estimation schemes) and the possibility of using numerical techniques such as Expectation Maximization (EM) or Markov chain Monte Carlo (MCMC) methods (when closed-form solutions are not available or problematic from an implementation perspective). We finally discuss the problem formulation using classical (frequentist) and Bayesian frameworks, and we present several field examples where the proposed calibration techniques are applied on sensors typically used in robotics applications (specifically, triangulation Light Detection and Rangings (Lidars) and Time of Flight (ToF) Lidars).
|
|
| 59. |
- AlHayali, Amani
(författare)
-
In vitro-solubility and supersaturation behavior of supersaturating drug delivery systems
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The development of new pharmaceutical products has been challenged by the growing number of poorly water-soluble drugs, which often lead to suboptimal bioavailability. Various approaches, such as the use of amor-phous solid dispersions and cocrystals, have been used to improve the solu-bility, and subsequent bioavailability, of these drug molecules. Supersaturat-ing drug delivery systems (SDDSs) have potential for achieving adequate oral drug bioavailability by increasing the drug solubility and creating a su-persaturated state in the gastrointestinal tract. However, there is a need for better understanding of the supersaturation behavior in SDDSs and of the factors affecting supersaturation. The main objective of this thesis was to improve understanding of the supersaturation solubility behavior in SDDSs with a particular focus on rapidly dissolving solid forms (amorphous forms/cocrystals).In the course of the work, a new formulation for ezetimibe using an amorphous solid dispersion was prepared, cocrystals of tadalafil were pre-pared, and oral films of silodosin were formulated for the first time. These new formulations were thoroughly characterized using a number of solid-state and pharmaceutical characterization techniques.The dissolution and supersaturation behavior of the prepared SDDSs were studied. The effects of various factors on the supersaturation and precipita-tion characteristics were investigated. These factors included the preparation method, the temperature of the dissolution medium, the type of dissolution biorelevant medium (gastric/intestinal) used, the permeability of the relevant gastrointestinal membranes, the addition of polymers, and the addition of surfactants. The amorphous solid dispersions, cocrystals and oral films that were prepared represent new drug formulations that provide significantly higher dissolution rates and supersaturated solubility than crystalline drug forms. Solid dispersions prepared by the melting method had better super-saturation properties than those prepared by spray drying. The precipitation kinetics of the solid dispersion were faster at 37 ̊C than at 25 ̊C in bio-relevant media. Implementation of an absorption tool during in vitro evalua-tion of supersaturation levels could improve the prediction accuracy of su-persaturation and precipitation. A better understanding of the effects of ex-cipients on the supersaturation and precipitation behavior of these types of formulation was obtained in this thesis. The improvement in supersaturation solubility obtained by adding polymers and surfactants was not proportional to the amounts of excipient used.This thesis has made notable contributions to the field of pharmaceutical science by advancing our understanding of the supersaturation solubility behavior of the newly prepared SDDSs.
|
|
| 60. |
- AlHayali, Amani, et al.
(författare)
-
Investigation of supersaturation and in vitro permeation of the poorly water soluble drug ezetimibe
- 2018
-
Ingår i: European Journal of Pharmaceutical Sciences. - : Elsevier. - 0928-0987 .- 1879-0720. ; 117, s. 147-153
-
Tidskriftsartikel (refereegranskat)abstract
- The interplay between supersaturation, precipitation and permeation characteristics of the poorly water-soluble drug ezetimibe (EZ) was investigated. Supersaturation and precipitation characteristics of EZ in the presence of Caco-2 cells were compared to those in a cell-free environment. The effect of the water-soluble polymer polyvinyl pyrrolidone (PVP-K30) on the supersaturation, precipitation and transport of EZ was also investigated and the amount of drug taken up by Caco-2 cells was quantified.A one-compartment setup without Caco-2 cells (i.e. in the wells of cell-culture plates) was used to mimic a non-sink in vitro dissolution chamber. The two-compartment Caco-2 cell monolayer setup (with apical and basolateral compartments) was used to investigate how the absorption of EZ affects supersaturation. EZ in varying degrees of supersaturation (DS; 10, 20, 30 and 40) was introduced into the one-compartment setup or the apical chamber of the two-compartment setup. Samples were collected at specific times to determine supersaturation, precipitation and permeation. At the end of the study, Caco-2 cells were lysed and the intracellular amount of EZ was quantified.In the one-compartment setup, a high DS was associated with rapid precipitation. Supersaturation was maintained for longer time periods and precipitation was lower in the presence of Caco-2 cells. There were no significant differences in the absorption rate of the drug, even at high concentrations on the apical side. Permeability coefficients for all supersaturated solutions (i.e. DS 10–40) were significantly (p < 0.05) different from those when EZ was present in crystalline form. Both concentrations of PVP-K30 (i.e. 0.05% and 0.1% w/v) improved solubility and supersaturation of EZ when added to the apical side, however, the increase in absorption at the higher concentration was not proportional. The amount of intracellular EZ increased with increasing DS in the apical side, until the saturation limit was reached in the cells (i.e. at DS 30 and higher).This study demonstrated that precipitation of EZ could be overestimated when supersaturation was investigated without the implementation of an absorption compartment in vitro, both in the absence and in the presence of polymer.
|
|
