Maher Qumsiyeh

Extreme learning machine with variance inflation factor for robust pattern recognition

Extreme learning machine (ELM), as a single hidden layer feedforward neural network, has shown very effective performance in pattern analysis and machine intelligence; however, there are some limitations that constrain the performance of ELM, such as data multicollinearity issues. The generalization capability of ELM could be significantly deteriorated when multicollinearity is present in the hidden layer output matrix which causes the matrix to become singular or ill-conditioning. To overcome such a problem, ridge regression can be utilized. The conventional way to avoid multicollinearity in ELM is achieved by precisely adjusting the ridge constant, which may not be a sophisticate solution to obtain the optimal value. In this paper, we present a solution for finding a satisfactory ridge constant by incorporating variance inflation factors (VIF) during calculating output weights in ELM, we termed this technique as ELM-VIF. Experimental results on handwritten digit recognition show that the proposed ELM-VIF, compared with the original ELM, has better stability and generalization performance.

Construction of a twin-pier platform for biological sensing

This paper describes the successful construction of a twin-pier platform for use in biological sensing applications. The two piers are inline and have a tunable gap between them, with gap distance varying between 60-200 nm. The proximal ends of the piers are contiguous with a Co-Planar Waveguide structure that allows for testing. The basic pier structure was created by ablation of a customized MMA/PMMA stack using a JEOL laser system. A layer of Ti-Au was then deposited on silicon using standard electron beam deposition techniques. Electromagnetic testing of the structures was correlated with SEM imagery for characterization of electrical properties and gap integrity. The overall design is to create a biological sensing bridge by tethering molecules across the distal ends of the piers thereby completing the circuit. The type and composition of biological bridge provides sensor selectivity and sensitivity.

Learning Multi-level Local Phase Relationship for Single Image Resolution Enhancement

In this paper, a novel approach for image spatial resolution enhancement based on multi-level local Fourier phase features is proposed. This method uses adaptive kernel regression technique based on multi-level local covariance to estimate the high resolution image from a low resolution input. However, this concept is similar to other regression and covariance based methods, our method uses multi-level Fourier image features to learn the local covariance from geometric similarity between low resolution image and its corresponding high resolution image. For each local region, four weighted integrated directional variances are estimated to adapt the interpolated pixels. This method is tested on various natural and aerial images at higher resolution scales. The results confirm that the proposed technique performs better especially at high resolution scales in comparison with other state of art techniques.

A passive RF sensor platform for chemical-biological sensors

This research introduces a new type of chemical-biological sensor platform. This sensor platform detects different types of chemical or biological agents without the use of probes, wires, active components, or a battery. An interrogator transmits power through radio frequency waves to the embedded device. The embedded device sends back a portion of the power through radio frequency waves with altered amplitude and phase. The characteristics of the received signal contain the information about the agent of interest. The sensor device has a functionalized surface which aids in selectivity to the analyte of interest.

Ferroelectric thin-film characterization through use of coplanar waveguide varactors

This paper investigates the implementation of a least squares estimation of varactor capacitance values across a wafer for reasons of characterizing thin-film ferroelectric Ba0.6Sr0.4TiO3, barium strontium titanate (BST). The varactor design utilized for this characterization as well as an equivalent schematic representation of the device used will be presented. Comparisons between the estimated thin-film performance and those of previously presented results will also be discussed.

A passive wireless sensor platform for chemical and biological agents

Passive wireless sensors can be used to detect chemical or biological agents without the use of probes or wires and without the use of a battery. This paper presents a platform used as a passive wireless sensor to detect certain chemicals of interest. The wireless sensor is powered through an interrogator which sends magnetic/inductive waves to the remote sensor. The sensor converts the power to direct current and then sends back a portion of the power through radio frequency waves with altered frequency, amplitude, and phase. The characteristics of the received signal contain the information about the agent of interest.

An L 2 Comparison Between the Bootstrap and the Empirical Edgeworth Expansion

The Bootstrap estimate for studentized statistics is more accurate than both the normal approximation and the two-term empirical Edgeworth expansion. In this article, it will be shown that the three-term empirical Edgeworth expansion for studentized statistics compares well with the bootstrap. It is also shown that the three-term Edgeworth expansion is superior to the bootstrap in some cases, using more efficient estimators than sample moments in the Edgeworth expansion, such as using maximum likelihood estimators in the one-parameter exponential family.