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.     

Evaluation of Digitally Encoded Layer‐by‐layer Coated Microparticles as Cell Carriers

To obtain more biologically relevant data there is a growing interest in the use of living cells for assaying the biological activity of unknown chemical compounds. Density ‘multiplex’ cell‐based assays, where different cell types are mixed in one well and simultaneously investigated upon exposure to a certain compound are beginning to emerge. To be able to identify the cells they should be attached to microscopic carriers that are encoded. This paper investigates how digitally encoded microparticles can be loaded with cells while keeping the digital code in the microcarriers readable. It turns out that coating the surface of the encoded microcarriers with polyelectrolytes using the layer‐by‐layer (LbL) approach provides the microcarriers with a ‘highly functional’ surface. The polyelectrolyte layer allows the growth of the cells, allows the orientation of the cell loaded microcarriers in a magnetic field, and does not hamper the reading of the code. It has further been shown that the cells growing on the polyelectrolyte layer can become transduced by adenoviral particles hosted by the polyelectrolyte layer. It is concluded that the digitally encoded microparticles are promising materials for use in biomedical and pharmaceutical in‐vitro research where cells are used as tools.     

Coupled-mode theory of overmoded cylindrical metal bragg-reflectors

A coupled-mode theory of overmoded, cylindrical metal Bragg-reflectors is presented. The first-order Bragg coupling constants are derived for TE → TE, TM → TM, TE → TM, and TM → TE mode conversions. Reflectivities and transverse modeQ-factors are computed for a Bragg-reflector resonator. The results illustrate important competition effects between nearly-degenerate-transverse-modes occurring within both the Bragg-reflectors and the resonator.     

Longitudinal bone mineral density changes in early rheumatoid arthritis

A prospective longitudinal study of patients with early RA was performed to examine the influence of disease duration, disease activity and physical activity on bone loss. Sixty-seven patients with non-steroid treated RA of less than 5 yr duration, including 16 patients with disease duration less than 6 months, had BMD measurements of the femoral neck and the lumbar spine over a 12-month period using dual energy X-ray absorptiometry. The BMD changes were compared with values from 72 control patients and were also correlated with serial measurements of disease activity (measured by the Stoke Index) and disability [measured by the Health Assessment Questionnaire (HAQ) score], at 3-monthly intervals over the 12-month period. No significant differences in BMD changes were found between RA patients and controls overall. Patients with disease duration of less than 6 months had significantly greater loss of BMD at the femoral neck (-3.9%, S.E.M. 1.5) than the remainder of the cohort (-0.2%, S.E.M. 0.7) (P = 0.02) and controls (-0.8%, S.E.M. 0.6). Lumbar spine BMD changes correlated with the initial Stoke Index (Rs-0.373, P = 0.01) but not mean Stoke Indices. There was no correlation of BMD changes with age or HAQ scores. These findings suggest that significant bone loss occurs within the first few months of disease in patients with RA.     

Effect of pressure gradient on MHD boundary layer over a flat plate

Summary The magnetohydrodynamic (MHD) boundary layer flow over a flat plate is examined here for two cases, viz. a uniform free-stream velocity and a uniform hydrostatic pressure. The nonlinear boundary layer equations are solved using a reliable finite-difference method. The boundary layer physical parameters such as skin-friction coefficient, displacement, momentum and energy thicknesses of the boundary layer are determined. It is found that the normal surface velocity gradient decreases with the local magnetic interaction parameter for the cases of a uniform hydrostatic pressure, whereas in the case of a uniform free-stream volocity it increases with the interaction parameter.     

Transrectal electrostimulation therapy for neuropathic bowel dysfunction in children with myelomeningocele

PURPOSE: We attempted to evaluate the efficacy of transrectal bowel stimulation for neurogenic bowel dysfunction in children with myelodysplasia. MATERIALS AND METHODS: Daily sessions of transrectal electrostimulation were performed on an outpatient basis for 2 to 3 weeks on children with myelodysplasia and stool incontinence. If benefits were noted, 5 to 10 additional daily sessions were performed. Complete success was defined as improvement in all parameters of interest, including decrease in the frequency of daily bowel movements, increased sensation, increased ability to hold stool and a significant subjective change in bowel habits. Moderate success implied improvement in 1 to 3 parameters and treatment failure was defined as lack of improvement in any parameter. RESULTS: A total of 55 children 2 to 14 years old (mean age 6.7) completed a mean of 18 daily sessions per patient of bowel electrostimulation. Followup ranged from 1 to 6 years. Diapers are no longer required due to defecation problems in 14 children older than 3 years. Complete success was achieved in 20 cases (36.3%) and moderate success in an additional 30 (54.5%, overall success rate 90.8%). Specifically, 89% of the patients reported elimination of stooling accidents, 82% reported increased sensation and 71% were able to hold the bowel movement. Overall 68% of the patients noticed significantly improved bowel function. Complete/moderate success of transrectal electro-stimulation was statistically significant for all 4 parameters (p < 0.05), and complete success was significant for increased sensation, ability to hold and episodes of accidents. Therapy failed in 5 children (9%). There were no untoward effects. CONCLUSIONS: Transrectal electrostimulation is a well tolerated and minimally invasive modality that provides sustainable improvement in stool continence in children with myelomeningocele and neuropathic bowel dysfunction.     

Climate change gains more from nuclear substitution than from conservation

We show the massive reduction achievable, in both emissions and climate change impact, from enhanced nuclear energy use on the forecasts of future world energy use and its associated environmental impacts. A range encompassing the major scenarios for the World's energy demand have been analyzed using the latest version of the climate-modeling MAGICC/SCENGEN software (Version 4.1). We have updated and predicted the impacts of 80% substitution with CO₂-free sources (likely predominantly nuclear) for coal-fired electricity (by 2030) and for transportation fuel (by 2040). For transportation, hydrogen produced by CO₂-free sources would replace gasoline and diesel fuels. In this paper, to bracket the range of futures, we simply focus on two scenarios from the Intergovernmental Panel on Climate Change's (IPCC), one (A1FI) that is energy-profligate and one (B2) that is energy-conserving.The results show that, interestingly, projected average global temperatures for all scenarios are fairly similar until about 2035 (a further rise beyond the 1990 average temperature of +0.75 ± 0.1 K) regardless of energy usage and its sources. However, by 2050, the different IPCC scenarios diverge markedly. Understandably, A1FI is projected to have noticeably stronger effects than B2 on average global temperatures (about 0.3 K more in 2050) but the effect is much stronger over land at mid and high latitudes (up to almost 1 K more). What is most striking is that the substitution of CO₂-free sources gives projected average temperature rises in 2050 over key land areas (North America and China) that are very similar for the two energy-use scenarios—typically 1–1.5 K because A1FI's additional energy is predominantly supplied by nuclear. In contrast, projected rises with the unaltered cases are markedly different being about 2.5 K for A1FI and 1.5–2 K for B2. The projected changes in rainfall distribution show similar patterns, especially for the expected increases in higher latitudes.With the assumption of no additional policies for substitution of energy sources beyond 2040, temperature divergence between the two scenarios of relative energy profligacy or conservation grows in the latter half of the 21st century, even with substitution. However, the early substitution of nuclear energy and hydrogen appears to buy time and is not crucially dependent on severe, near-term curtailment of energy use. Near-term curtailment is too difficult to implement at a time of rapid industrialization of major emerging economies. Of course, proportionately larger deployments of CO₂-free energy sources are needed for more energy-intensive scenarios.Nuclear power must dominate as the source of CO₂-free energy since it is proven, dependable, available on a large scale, and economic. Social objections to nuclear energy in some countries and quarters are seen as well-meaning but misguided distractions from solving the energy and environmental crises that are now facing world sustainability. The time for real technical, social and political action is now.     

Nonlinear superposition in saturation recording of disk media

The magnetic readback signal is generally assumed to be made up of linearly superposed single transition responses. As the transition spacing is reduced, this property is seen not to hold, With particulate disks, we find the head signal can be reconstructed as a linear superposition of variably spaced individual transitions, while with cobalt alloy film disks, both the spacing and the amplitude of individual transitions vary as a function of the data. This behavior is interpreted by a self consistent 2D recording model, linear superposition improves dramatically with lowM_{r}tdisk media.     

A design advisor for the optimal inspection of circularity tolerance

In the wake of growing importance for quality and the need to reduce inspection costs simultaneously, the need for a scientific method of selecting an optimum inspection strategy for coordinate measuring machine (CMM) based inspection has become very important. The inspection error resulting from CMM inspection is greatly affected by the profile irregularities and the sampling strategy, which includes sample size, sampling methods, and algorithms used for form evaluation. This paper describes a system that can recommend an optimal inspection plan based on the needs of the user. A design of experiments (DOE) based approach is used to relate the inspection error with sampling strategies. Surface irregularities are included in the form of lobes formed on the profile. A new two-way model is proposed that works in both directions between the sampling strategy and the performance metrics. The results indicate that the number of lobes and the sampling method used have little impact on the inspection error, while the sample size and form evaluation algorithms have a significant influence. An inspection plan advisor is presented, which provides an inspection plan based on the estimated shape and acceptable measurement error.