Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

The near-zone field characteristics of an E-polarization plane wavepenetrating through cylindrical multiple apertures (non) coated withlossy and lossless media

The direct integral equation is formulated for describing the current on the multiple perfectly conducting strips in cylindrical geometries for an E-polarization plane wave of normal incidence. By using the Galerkin's method, the surface currents on the conducting strips are expanded in the form of a series of Chebyshev polynomials of the first kind, while the unknown expanding coefficients are solved by a set of matrix equations of finite order with a fast convergence rate and a high accuracy. Furthermore, numerical results are presented to demonstrate the variation of the penetrated near-zone field in the presence of one, two, three, four and six cylindrical apertures, and the hybrid effects of both aperture number and aperture angular widths on the penetrated fields are investigated in detail     

ADI-FDTD Method With Fourth Order Accuracy in Time

This letter presents an unconditionally stable alternating direction implicit finite-difference time-domain (ADI-FDTD) method with fourth order accuracy in time. Analytical proof of unconditional stability and detailed analysis of numerical dispersion are presented. Compared to second order ADI-FDTD and six-steps SS-FDTD, the fourth order ADI-FDTD generally achieves lower phase velocity error for sufficiently fine mesh. Using finer mesh gridding also reduces the phase velocity error floor, which dictates the accuracy limit due to spatial discretization errors when the time step size is reduced further.     

Computer analysis,design and simulation of horizontal ground heat exchangers

This paper presents a new computerized procedure for dealing with the design of horizontal ground heat exchangers (HGHE). The computer program is based on the transient model of coupled nonlinear partial differential equations governing heat and mass flow in soils. The model is two-dimensional and delineates the operation of ground heat storage with the HGHE and such phenomena as freezing/thawing and drying/rewetting of soil moisture. Comprehensive climatological data, such as ambient temperature, solar radiation, wind velocity, rainfall, snowfall, snow characterstics, and water vapour pressure is used to simulate conditions at the ground surface over any required length of time. The package can be applied to any geographical location by changing climatic and soil data input. The designer has the possibility of selecting any of 12 types of soils from sand to clay, 12 commercial heat pumps, nine different configurations of the HGHE, 16 plastic pipes for ground coils, and 13 ground coil fluids. The program, however, does not calculate the length of the HGHE but it evaluates the thermodynamic performance of a ground heat pump system and provides comprehensive data on thermal and hydraulic conditions in ground heat storage. The length of the ground heat exchanger is obtained from a line source theory model or from site dimensions and pipe spacing. Computed results for ground heat exchanger operation correlate fairly well with experimental data. Simulation of temperature and moisture content in the ground for natural conditions (no heat extraction/deposition) showed a fair agreement with field data. The entire computer program is user-friendly, interactive, menu-driven, and written in FORTRAN 77.     

Exploratory analysis of brain connectivity with ICA.

Covariance-based methods of exploration of functional connectivity of the brain from functional magnetic resonance imaging (fMRI) experiments, such as principal component analysis (PCA) and structural equation modeling (SEM), require a priori knowledge such as an anatomical model to infer functional connectivity. In this research, a hybrid method, combining independent component analysis (ICA) and SEM, which is capable of deriving functional connectivity in an exploratory manner without the need of a prior model is introduced. The spatial ICA (SICA) derives independent neural systems or sources involved in task-related brain activation, while an automated method based on the SEM finds the structure of the connectivity among the elements in independent neural systems. Unlike second-order approaches used in earlier studies, the task-related neural systems derived from the ICA provide brain connectivity in the complete statistical sense. The use and efficacy of this approach is illustrated on two fMRI datasets obtained from a visual task and a language reading task.     

Microwave techniques for diagnostic laboratories

Microwaves (MWs) were first introduced as a method of fixation just over 20 years ago. In recent years their use has extended far beyond that of a safe, clean and rapid method of fixation of tissue blocks and large specimens, including brains. MWs accelerate the action of cross-linking fixatives and can greatly accelerate the various stages of tissue processing to produce a paraffin block in 30 min. An extensive range of ultrafast MW-stimulated special stains has been developed, and immunohistochemical procedures can be completed in 20 min by employing MWs. Cellular antigens are distinctly better preserved in tissues fixed by MWs than by conventional cross-linking fixatives. Also, the cytomorphology of cryostat sections irradiated in Wolman's solution is clearly improved. MWs can similarly be applied for fixation and staining of preparations for transmission and scanning electron microscopy, and they also greatly accelerate polymerisation of resins. In the current climate of cost containment, this wide range of applications makes the MW oven an invaluable addition to the diagnostic laboratory.     

Comment on raindrop size distribution model

The parameter set for the exponential raindrop size distribution model presented by Yeo, Kooi and Leong (see ibid. vol.41, P.709, 1993) was derived using a data set measured in Singapore. A limitation to the model is that it is accurate only for small rain rate or when the rain medium consists predominantly of small droplets with diameter D is < λ/π . A new parameter set that enables accurate computation of rain attenuation for droplets with diameter D = λ/π has since been derived using the same data set. This new parameter set has been proven to be more accurate in the computation of rain attenuation     

Designing the MPC105 PCI bridge/memory controller

The MPC105 peripheral component interconnection bridge/memory controller provides a platform-specification-compliant bridge between Power PC microprocessors and the PCI bus. With it, designers can create systems using peripherals already designed for a variety of standard PC interfaces. This bridge chip also integrates a secondary cache controller and high-performance memory controller that supports DRAM or synchronous DRAM and ROM or flash ROM     

Micron-Scale Soft Actuators Fabricated from Multi-Shell Polystyrene Particle-Gold Nanoparticle Nanohybrids

Actuators made of soft matter are needed for a variety of fields ranging from biomedical devices to soft robotics to microelectromechanical systems. While there are a variety of excellent methods of soft actuation known, the field is still an area of intense research activity as new niches and needs emerge with new technology development. Here, a soft actuation system is described, based on a core-multi-shell particle, which moves via photothermal expansion. The system consists of a novel polystyrene-based thermally expandable microsphere, with a secondary shell of a silicate-silane graft copolymer, to which gold nanoparticles are covalently linked. The gold nanoparticles act as photothermal nano-transducers, converting light energy into the thermal energy necessary for microsphere expansion, which in turn results in material movement. Actuation is shown in isolated particles in thermal and photothermal regimes using metal ceramic heaters or 520 nm laser illumination, respectively. Macroscale actuation is demonstrated by making a composite material of particles suspended in the transparent elastomer polydimethylsiloxane. The sample demonstrates an inchworm-like movement by starting from an arched geometry. Overall, this work describes a new particle-based actuation method for soft materials, and demonstrates its utility in driving the movement of a composite elastomer.