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.     

Ecophysiology and niche differentiation of Nitrospira-like bacteria, the key nitrite oxidizers in wastewater treatment plants.

Nitrite-oxidizing bacteria of the genus Nitrospira are key nitrifiers in wastewater treatment plants. Pure cultures of these organisms are unavailable, but cultivation-independent molecular methods make it possible to detect Nitrospira-like bacteria in environmental samples and to investigate their ecophysiology. Comprehensive screening of natural and engineered habitats and of public databases for 16S rRNA sequences of Nitrospira-like bacteria revealed a surprisingly high biodiversity in the genus Nitrospira, which comprises at least four phylogenetic sublineages. All Nitrospira-like bacteria detected in wastewater treatment plants belonged to the sublineages I and II. Subsequently, the population dynamics of different Nitrospira-like bacteria were monitored, by quantitative fluorescence in situ hybridization with rRNA-targeted probes, confocal laser scanning microscopy and digital image analysis, during incubation of nitrifying activated sludge in media containing different nitrite concentrations. These experiments showed that Nitrospira-like bacteria, which were affiliated with the phylogenetic sublineages I or II of the genus Nitrospira, responded differently to nitrite concentration shifts. Previously unknown properties of Nitrospira-like bacteria were discovered in the course of an environmental genomics project. Implications of the obtained results for fundamental understanding of the microbial ecology of nitrite oxidizers as well as for future improvement of nutrient removal in wastewater treatment plants are discussed.     

Analysis of phosphorus removal and anaerobic selector performance in a full-scale activated sludge process in Singapore.

This paper analyses the performance of the anaerobic selector (A/O process) in a full-scale activated sludge process receiving mostly industrial sewage discharge (> 60%) in Singapore. In addition to the sludge settleability, enhanced biological phosphorus removal (EBPR) was studied. The sludge volume index (SVI) reduced from 200 to 80 ml g(-1) and foaming was suppressed significantly, indicating the effectiveness of the anaerobic selector in improving sludge settleability. The phosphorus removal efficiency was 66%, and 7.5 mg HAc-COD was consumed per mg PO4(3-) -P removed. In the anaerobic compartment, 31% of the SCOD and 73% of the acetic acid in the settled sewage were removed with PO4(3-) -P release of 14.1 mg PO4(3-)-P l(-1). The linear correlation between PO4(3-) -P release in the anaerobic compartment and PO4(3-) -P uptake in the aerobic compartment indicates that there is about 0.8 mg PO4(3-) -P release in the anaerobic compartment per mg PO34(3-) -P uptake in the aerobic compartment. The fates of volatile fatty acids (VFAs) and its short chain acids (SCAs) in the process were studied and discussed.     

Using decision analysis to determine optimal experimental design for monitoring sewer exfiltration with tracers.

The tracer methods developed to assess exfiltration from sewers in the European project APUSS (assessment of the performance of sewer systems) have a high degree of freedom with regard to the choice of tracer and the dosing strategy. These can lead to very different degrees of uncertainty in the measured exfiltration ratio. In this study, we demonstrate how to select an optimal experimental design using decision analysis, which accounts for this uncertainty and its associated costs. Although the results are site-specific, we can conclude generally that, when NaCl is used as the tracer, the accuracy of the exfiltration estimate is most sensitive to the amount of tracer used and the starting time of the experiment.     

Tracking influent inorganic suspended solids through wastewater treatment plants.

From an experimental and theoretical investigation of the continuity of influent inorganic suspended solids (ISS) along the links connecting the primary settling tank (PST), fully aerobic or N removal activated sludge (AS) and anaerobic and aerobic sludge digestion unit operations, it was found that the influent wastewater (fixed) ISS concentration is conserved through primary sludge anaerobic digestion, activated sludge and aerobic digestion unit operations. However, the measured ISS flux at different stages through a series of wastewater treatment plant (WWTP) unit operations is not equal to the influent ISS flux, because the ordinary heterotrophic organisms (OHO) biomass contributes to the ISS flux by differing amounts depending on the active fraction of the VSS solids at that stage.     

Sampling for representative micropollutant loads in sewer systems.

Most commercially available auto-sampling devices do not support a continuous flow-proportional sampling mode, which would conceptually be the best for collecting representative composite samples. Instead different discrete sampling modes are available. Household chemicals can show considerable random short-term variations. With the anticorrosive benzotriazole, relating to a middle-frequent household activity, we show that, besides an accurate flow meter, mainly three factors are decisive for the representativeness of a substance's average load: the substance's load pattern, the sampling frequency and the length of the composite sample. When the sampling intervals are 10 minutes or longer, errors in the order of +/-40% (standard deviation) or more have to be accepted, if the substance of interest is contained in a low number of wastewater pulses (i.e., the level of household activity). This particularly holds true for specific pharmaceuticals e.g. carbamazepine. Ammonium would be less critical, because it relates to a larger number of sources in the same catchment.     

Word length and lexical activation: Longer is better.

Many models of spoken word recognition posit the existence of lexical and sublexical representations, with excitatory and inhibitory mechanisms used to affect the activation levels of such representations. Bottom-up evidence provides excitatory input, and inhibition from phonetically similar representations leads to lexical competition. In such a system, long words should produce stronger lexical activation than short words, for 2 reasons: Long words provide more bottom-up evidence than short words, and short words are subject to greater inhibition due to the existence of more similar words. Four experiments provide evidence for this view. In addition, reaction-time-based partitioning of the data shows that long words generate greater activation that is available both earlier and for a longer time than is the case for short words. As a result, lexical influences on phoneme identification are extremely robust for long words but are quite fragile and condition-dependent for short words. Models of word recognition must consider words of all lengths to capture the true dynamics of lexical activation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Aripiprazole as a potential pharmacotherapy for stimulant dependence: Human laboratory studies with d-amphetamine.

Amphetamine and cocaine dependence present significant public health concerns, yet no broadly effective pharmacotherapy for stimulant dependence has been developed. Two human laboratory studies are reviewed that tested the ability of aripiprazole, a novel antipsychotic with partial agonist activity at D2 dopamine receptors, to alter the behavioral effects of stimulants using d-amphetamine as a model agent. In each of these experiments, volunteers learned to discriminate 15 mg d-amphetamine (i.e., ≥80% drug-appropriate responding over 4 consecutive sessions). The effects of a range of doses of d-amphetamine (0, 2.5, 5, 10, and 15 mg) were then tested alone and following pretreatment with aripiprazole (20 mg in Experiment 1; 10 mg in Experiment 2). In Experiment 1, aripiprazole (20 mg) attenuated the discriminative stimulus and many of the subject-rated effects of amphetamine. Aripiprazole alone produced performance decrements. To determine whether a lower dose of aripiprazole would also attenuate the behavioral effects of d-amphetamine without impairing performance, Experiment 2 was conducted. Aripiprazole (10 mg) failed to alter the discriminative-stimulus effects but attenuated some of the subject-rated effects of d-amphetamine. This dose of aripiprazole did not impair performance. The results of these experiments indicate that aripiprazole may have clinical utility in treating stimulant dependence. Future human laboratory research should better model the clinical use of aripiprazole by examining the effects of chronic aripiprazole combined with either methamphetamine or cocaine in dependent individuals. A large-scale clinical trial is also needed to evaluate the efficacy of aripiprazole for the treatment of stimulant dependence. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Atomistic simulations of grain boundary migration in copper

While the motion of twist boundaries can be readily studied by atomistic simulations with molecular dynamics (MD) under the action of an elastic driving force, the approach fails for tilt boundaries. This is due to the interaction of the elastic stress with the grain boundary (GB) structure, which causes plastic strain by GB sliding. A novel concept, the orientation correlated driving force, is introduced to circumvent this problem. It is shown that this concept can be successfully applied to the study of the migration of tilt boundaries. The migration behavior of several twist and tilt GBs was investigated. The transition from low-to high-angle boundaries can be captured, and a structural transition of tilt boundaries was found at high temperatures, which also affected the migration behavior. The results compare well with experimental results of the motion high-angle boundaries, but for low-angle boundaries, the agreement is poor. This article is based on a presentation made in the “Hillert Symposium on Thermodynamics & Kinetics of Migrating Interfaces in Steels and Other Complex Alloys,” December 2–3, 2004, organized by The Royal Institute of Technology in Stockholm, Sweden.     

Reliable eye-diagram analysis of data links via device macromodels

This paper addresses the impact of device macromodels on the accuracy of signal integrity and performance predictions for critical digital interconnecting systems. It exploits nonlinear parametric models for both single-ended and differential devices, including the effects of power supply fluctuations and receiver bit detection. The analysis demonstrates that the use of well-designed macromodels dramatically speeds up the simulation as well it preserves timing accuracy even for long bit sequences.