Space partitioning strategies for indoor WLAN positioning with cascade-connected ANN structures

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures for indoor WLAN positioning. A set of cascade-connected ANN structures with different space partitioning strategies are compared mutually and to the single ANN structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment, number of subspaces and partitioning strategy. The optimal cascade-connected ANN structures with space partitioning show up to 50% decrease in median error and up to 12% decrease in the average error with respect to the single ANN model. Finally, the single ANN and the optimal cascade-connected ANN model are compared against other well-known positioning techniques.     

Rapid phenotypic characterization of Salmonella enterica strains by pyrolysis metastable atom bombardment mass spectrometry with multivariate statistical and artificial neural network pattern recognition

Pyrolysis mass spectrometry was investigated for rapid characterization of bacteria. Spectra of Salmonella were compared to their serovars, pulsed-field gel electrophoresis (PFGE) patterns, antibiotic resistance profiles, and MIC values. Pyrolysis mass spectra generated via metastable atom bombardment were analyzed by multivariate principal component-discriminant analysis and artificial neural networks (ANNs). Spectral patterns developed by discriminant analysis and tested with Leave-One-Out (LOO) cross-validation distinguished Salmonella strains by serovar (97% correct) and by PFGE groups (49%). An ANN model of the same PFGE groups was cross-validated, using the LOO rule, with 92% agreement. Using an ANN, thirty previously unseen spectra were correctly classified by serotype (97%) and at the PFGE level (67%). Attempts by ANN to model spectra grouped by resistance profile-but ignoring PFGE or serotype-failed (10% correct), but ANNs differentiating ten samples of the same serotype/PFGE class were more successful. To assess the information content of PyMS data serendipitously associated with or directly related to resistance character, the ten isolates were grouped into four, three, or two categories. The four categories corresponded to four resistance profiles. The four class and three class ANNs showed much improved but insufficient modeling power. The two-class ANN and a corresponding multivariate model maximized inferential power for a coarse antibiotic-resistance-related distinction. They each cross-validated by LOO at 90%. This is the first direct correlation of pyrolysis metastable atom bombardment mass spectrometry with immunological (e.g. serology) or molecular biology (e.g. PFGE) based techniques.     

Phosphate uptake in Saccharomyces cerevisiae Hansen wild type and phenotypes exposed to space flight irradiation.

Rates of phosphate uptake were approximately twice as great for Saccharomyces cerevisiae single-cell phenotypic isolates exposed to space parameters as for the wild-type ground control. Quantitative determination of 32P was performed by liquid scintillation spectrometry utilizing Cerenkov radiation counting techniques.     

Assessment of respiratory system mechanics by artificial neural networks: an exploratory study.

We evaluated 1) the performance of an artificial neural network (ANN)-based technology in assessing the respiratory system resistance (Rrs) and compliance (Crs) in a porcine model of acute lung injury and 2) the possibility of using, for ANN training, signals coming from an electrical analog (EA) of the lung. Two differently experienced ANNs were compared. One ANN (ANN(BIO)) was trained on tracings recorded at different time points after the administration of oleic acid in 10 anesthetized and paralyzed pigs during constant-flow mechanical ventilation. A second ANN (ANN(MOD)) was trained on EA simulations. Both ANNs were evaluated prospectively on data coming from four different pigs. Linear regression between ANN output and manually computed mechanics showed a regression coefficient (R) of 0.98 for both ANNs in assessing Crs. On Rrs, ANN(BIO) showed a performance expressed by R = 0.40 and ANN(MOD) by R = 0.61. These results suggest that ANNs can learn to assess the respiratory system mechanics during mechanical ventilation but that the assessment of resistance and compliance by ANNs may require different approaches.     

Phosphate uptake in Saccharomyces cerevisiae Hansen wild type and phenotypes exposed to space flight irradiation.

Rates of phosphate uptake were approximately twice as great for Saccharomyces cerevisiae single-cell phenotypic isolates exposed to space parameters as for the wild-type ground control. Quantitative determination of 32P was performed by liquid scintillation spectrometry utilizing Cerenkov radiation counting techniques.     

Trunk acceleration for neuroprosthetic control of standing: a pilot study

This pilot study investigated the potential of using trunk acceleration feedback control of center of pressure (COP) against postural disturbances with a standing neuroprosthesis following paralysis. Artificial neural networks (ANNs) were trained to use three-dimensional trunk acceleration as input to predict changes in COP for able-bodied subjects undergoing perturbations during bipedal stance. Correlation coefficients between ANN predictions and actual COP ranged from 0.67 to 0.77. An ANN trained across all subject-normalized data was used to drive feedback control of ankle muscle excitation levels for a computer model representing a standing neuroprosthesis user. Feedback control reduced average upper-body loading during perturbation onset and recovery by 42% and peak loading by 29% compared with optimal, constant excitation.     

Verification of electron beam parameters in an intraoperative linear accelerator using dosimetric and radiobiological response methods

BackgroundThe availability of linear accelerators (linac) for research purposes is often limited and therefore alternative radiation sources are needed to conduct radiobiological research. The National Centre for Radiation Research in Poland recently developed an intraoperative mobile linac that enables electron irradiation at energies ranging from 4 to 12 MeV and dose rates of 5 or 10 Gy/min. The present study was conducted to evaluate the electron beam parameters of this intraoperative linac and to verify the set-up to evaluate out-of-field doses in a water phantom, which were determined through dosimetric and biological response measurements.Materials and methodsThe distribution of radiation doses along and across the radiation beam were measured in a water phantom using a semiconductor detector and absolute doses using an ionisation chamber. Two luminal breast cancer cell lines (T-47D and HER2 positive SK-BR-3) were placed in the phantom to study radiation response at doses ranging from 2 to 10 Gy. Cell response was measured by clonogenic assays.Results and ConclusionThe electron beam properties, including depth doses and profiles, were within expected range for the stated energies. These results confirm the viability of this device and set-up as a source of megavoltage electrons to evaluate the radiobiological response of tumour cells.     

Counting of p32 in plant tissues using the Cerenkov effect

Summary A procedure for counting p³² in plant tissues is presented. The method, based on the use of Cerenkov radiation, involves practically no sample preparation. Plant tissue are placed into vials containing water or hexane and counted with a liquid scintillation counter. Counts obtained, using this procedure were found to be linearily related to that obtained with a G.M. tube. The counting efficiency was, however, higher with the proposed method. The use of hexane is advantageous if leakage of p³² from the tissue is possible, or when higher counting efficiency is desireable. The use of different liquids may also enable a discriminative count of different beta emitters. As suggested recently⁸ use of wavelength shifter may further increase efficiency of counting Cerenkov radiation.     

Characterization of ecosystem responses to climatic controls using artificial neural networks

Understanding and modeling ecosystem responses to their climatic controls is one of the major challenges for predicting the effects of global change. Usually, the responses are implemented in models as parameterized functional relationships of a fixed type. In contrast, the inductive approach presented here based on artificial neural networks (ANNs) allows the relationships to be extracted directly from the data. It has been developed to explore large, fragmentary, noisy, and multidimensional datasets, such as the carbon fluxes measured at the ecosystem level with the eddy covariance technique. To illustrate this, our approach has been systematically applied to the daytime carbon flux dataset of the deciduous broadleaf forest Hainich in Germany. The total explainable variability of the half‐hourly carbon fluxes from the driving climatic variables was 93.1%, showing the excellent data mining capability of the ANNs. Total photosynthetic photon flux density was identified as the dominant control of the daytime response, followed by the diffuse radiation. The vapor pressure deficit was the most important nonradiative control. From the ANNs, we were also able to deduce and visualize the dependencies and sensitivities of the response to its climatic controls. With respect to diffuse radiation, the daytime carbon response showed no saturation and the light use efficiency was three times greater for diffuse compared with direct radiation. However, with less potential radiation reaching the forest, the overall effect of diffuse radiation was slightly negative. The optimum uptake of carbon occurred at diffuse fractions between 30% and 40%. By identifying the hierarchy of the climatic controls of the ecosystem response as well as their multidimensional functional relationships, our inductive approach offers a direct interface to the data. This provides instant insight in the underlying ecosystem physiology and links the observational relationships to their representation in the modeling world.     

Environmental radiation as the conditioning factor for the survival of yeast Saccharomyces cerevisiae

Whether natural radiation can be a conditioning factor for the growth and survival of a living organism was investigated using diploid yeast S. cerevisiae D7. Yeast cells were conditioned by growing them continuously for at least 100 generation in 3 different radiation background such as i) ambient radiation (1.1 mSv/y), ii) sub-ambient radiation (0.44 mSv/y, within a shielded chamber) and iii) an elevated background radiation (88 and 880 mSv/y in a gamma-field). At the end, the cells were challenged with 60Co gamma, 100 Gy and the viable fractions were determined. Conditioning the cells in 880 mSv/y and in ambient radiation, enabled the cells to reduce the deleterious effect of the challenging dose significantly (P < 0.05) compared to that of sub-ambient radiation. The cellular viability of yeast cultures seems to be influenced by the prevailing radiation background, apart from starvation. Comparatively, a rapid decline in viability was noticed when the cultures were incubated for 60 days in the shielded chamber. The results indicate that some amount of radiation equivalent to background level or little above is needed to confer fitness in biological systems against stress factors, including radiation. The adaptive dose for the diploid yeast was also determined by single exposure. The priming dose ranged from 0.01 to 1.2 Gy. An adaptive dose of 0.25 or 0.4 Gy, almost nullified the deleterious effect of the challenging dose. The adaptive response may have a greater role in the field of cancer therapy and in radiation risk assessment. Understanding the response of an organism at different radiation-background will be helpful for successful space management.     

“Edge-on” MOSkin detector for stereotactic beam measurement and verification

Dosimetry in small radiation field is challenging and complicated because of dose volume averaging and beam perturbations in a detector. We evaluated the suitability of the “Edge-on” MOSkin (MOSFET) detector in small radiation field measurement. We also tested the feasibility for dosimetric verification in stereotactic radiosurgery (SRS) and stereotactic radiotherapy (SRT). “Edge-on” MOSkin detector was calibrated and the reproducibility and linearity were determined. Lateral dose profiles and output factors were measured using the “Edge-on” MOSkin detector, ionization chamber, SRS diode and EBT2 film. Dosimetric verification was carried out on two SRS and five SRT plans. In dose profile measurements, the “Edge-on” MOSkin measurements concurred with EBT2 film measurements. It showed full width at half maximum of the dose profile with average difference of 0.11 mm and penumbral width with difference of ±0.2 mm for all SRS cones as compared to EBT2 film measurement. For output factor measurements, a 1.1% difference was observed between the “Edge-on” MOSkin detector and EBT2 film for 4 mm SRS cone. The “Edge-on” MOSkin detector provided reproducible measurements for dose verification in real-time. The measured doses concurred with the calculated dose for SRS (within 1%) and SRT (within 3%). A set of output correction factors for the “Edge-on” MOSkin detector for small radiation fields were derived from EBT2 film measurement and presented. This study showed that the “Edge-on” MOSkin detector is a suitable tool for dose verification in small radiation field.     

On the Use of Optically Stimulated Luminescent Dosimeter for Surface Dose Measurement during Radiotherapy

This study was carried out to investigate the suitability of using the optically stimulated luminescence dosimeter (OSLD) in measuring surface dose during radiotherapy. The water equivalent depth (WED) of the OSLD was first determined by comparing the surface dose measured using the OSLD with the percentage depth dose at the buildup region measured using a Markus ionization chamber. Surface doses were measured on a solid water phantom using the OSLD and compared against the Markus ionization chamber and Gafchromic EBT3 film measurements. The effect of incident beam angles on surface dose was also studied. The OSLD was subsequently used to measure surface dose during tangential breast radiotherapy treatments in a phantom study and in the clinical measurement of 10 patients. Surface dose to the treated breast or chest wall, and on the contralateral breast were measured. The WED of the OSLD was found to be at 0.4 mm. For surface dose measurement on a solid water phantom, the Markus ionization chamber measured 15.95% for 6 MV photon beam and 12.64% for 10 MV photon beam followed by EBT3 film (23.79% and 17.14%) and OSLD (37.77% and 25.38%). Surface dose increased with the increase of the incident beam angle. For phantom and patient breast surface dose measurement, the response of the OSLD was higher than EBT3 film. The in-vivo measurements were also compared with the treatment planning system predicted dose. The OSLD measured higher dose values compared to dose at the surface (Hp(0.0)) by a factor of 2.37 for 6 MV and 2.01 for 10 MV photon beams, respectively. The measurement of absorbed dose at the skin depth of 0.4 mm by the OSLD can still be a useful tool to assess radiation effects on the skin dermis layer. This knowledge can be used to prevent and manage potential acute skin reaction and late skin toxicity from radiotherapy treatments.     

Pose estimation in automated visual inspection using ANN

In this paper, we present an accurate and robust pose estimator of rigid, polyhedral objects, based on Artificial Neural Networks (ANN), as suitable for Automated Visual Inspection (AVI) applications. The estimator is novel in the sense that it is trained with different poses of the objects having dimensional deviations within its tolerance range and is therefore robust with respect to within tolerance dimensional errors. The estimation accuracy is scalable and our computer simulation experiments in the existing configurations of ANNs have shown an accuracy better than 4% of the placement error. The ANN based pose estimator offers several advantages over the classical implementations.     

Total nitrogen and ammonia removal prediction in horizontal subsurface flow constructed wetlands: use of artificial neural networks and development of a design equation

The aim of this paper is to examine if artificial neural networks (ANNs) can predict nitrogen removal in horizontal subsurface flow (HSF) constructed wetlands (CWs). ANN development was based on experimental data from five pilot-scale CW units. The proper selection of the components entering the ANN was achieved using principal component analysis (PCA), which identified the main factors affecting TN removal, i.e., porous media porosity, wastewater temperature and hydraulic residence time. Two neural networks were examined: the first included only the three factors selected from the PCA, and the second included in addition meteorological parameters (i.e., barometric pressure, rainfall, wind speed, solar radiation and humidity). The first model could predict TN removal rather satisfactorily (R(2)=0.53), and the second resulted in even better predictions (R(2)=0.69). From the application of the ANNs, a design equation was derived for TN removal prediction, resulting in predictions comparable to those of the ANNs (R(2)=0.47). For the validation of the results of the ANNs and of the design equation, available data from the literature were used and showed a rather satisfactory performance.     

Liquid Scintillation Radioassay in Disposable Microcentrifuge Tubes: Radioimmune Precipitates and Other Applications

A simple, economical radioassay system employing disposable polypropylene microcentrifuge tubes was developed. Plastic adapters permitted automatic operation in liquid scintillation spectrometers. Counting efficiencies of (3)H, (14)C, (32)P, and (125)I in liquid scintillation cocktails and of (32)P by Cerenkov radiation (at lower efficiency in absence of added scintillator) were comparable to those in standard vials. Multipurpose use of the microtubes made the system versatile and expedient, e.g., collection of precipitates and radioassay in the same container. Collection of radioimmune precipitates was aided by a carrier inorganic precipitate, Mg(2)P(2)O(7).     

The use of Cerenkov radiation for monitoring reactions performed in minute volumes: examples from recombinant DNA technology

A method in which minute volumes of initially unknown size are used to monitor reactions has been developed. It is applicable whenever 32P-labeled substrates can be distinguished from 32P-labeled products by a filter assay. Three determinations are required: the Cerenkov radiation emitted (1) by the unknown aliquots affixed to filters and dried; (2) by the identical filters after processing to remove either substrates or products; and (3) by a precisely measured, necessarily much larger, aliquot in solution. Given the value obtained in (3) and the efficiency with which Cerenkov radiation can be detected in the dry state (25%) compared with the liquid state (56%), the unknown volumes, together with their acid-insoluble radioactivity, can be calculated from (1) and (2), respectively. Since the known volume counted in solution is not lost to further manipulations, the entire procedure uses less than 0.5 microliter.     

Estimation of background radiation doses for the Peninsular Malaysia’s population by ESR dosimetry of tooth enamel

Background radiation dose is used in dosimetry for estimating occupational doses of radiation workers or determining radiation dose of an individual following accidental exposure. In the present study, the absorbed dose and the background radiation level are determined using the electron spin resonance (ESR) method on tooth samples. The effect of using different tooth surfaces and teeth exposed with single medical X-rays on the absorbed dose are also evaluated. A total of 48 molars of position 6–8 were collected from 13 district hospitals in Peninsular Malaysia. Thirty-six teeth had not been exposed to any excessive radiation, and 12 teeth had been directly exposed to a single X-ray dose during medical treatment prior to extraction. There was no significant effect of tooth surfaces and exposure with single X-rays on the measured absorbed dose of an individual. The mean measured absorbed dose of the population is 34 ± 6.2 mGy, with an average tooth enamel age of 39 years. From the slope of a regression line, the estimated annual background dose for Peninsular Malaysia is 0.6 ± 0.3 mGy y⁻¹. This value is slightly lower than the yearly background dose for Malaysia, and the radiation background dose is established by ESR tooth measurements on samples from India and Russia.     

Evaluation and amelioration of computer-aided diagnosis with artificial neural networks utilizing small-sized sample sets

Concerns about the specificity and reliability of artificial neural networks (ANNs) impede further application of ANNs in medicine. This is particularly true when developing computer-aided diagnosis (CAD) tools using ANNs for orphan diseases and emerging research areas where only a small-sized sample set is available. It is unreasonable to claim one ANN's performance as better than another simply on the basis of a single output without considering possible output variability due to factors including data noise and ANN training protocols. In this paper, a bootstrap resampling method is proposed to quantitatively analyze ANN output reliability and changing performance as the sample data and training protocols are varied. The method is tested in the area of feature classification for analysis of masses detected on mammograms. Our experiments show that ANNs performance, measured in terms of the area under the receiver operating characteristic (ROC) curve, is not a fixed value, but follows a distribution function sensitive to many factors. We demonstrate that our approach to determining the bootstrap estimates of confidence intervals (CIs) and prediction intervals (PIs) can be used to assure optimal performance in terms of ANN model configuration. We also show that the unintentional inclusion of data noise, which biases ANN results in small task-specific databases, can be accurately detected via the bootstrap estimates.     

Derivation of radiation quality average parameters in neutron-gamma radiation fields with the high-pressure ionization chamber: theory and practice

The established radiation quality parameters in mixed neutron-gamma radiation fields may be measured by applying the initial (columnar) recombination of ions in tissue-equivalent (TE) high-pressure ionization chambers (recombination chambers). The mean quality factor can be determined to within 10-15% for mixed fields with neutrons ranging from thermal to 10 MeV, and the dose mean LET of the proton component can be determined to within 10-15% if the gamma-ray absorbed dose fraction is known. These average parameters are derived by measuring the ratio of the ionization currents collected at two high-field strengths and constant gas pressure applied to the ionization chamber. By utilizing approximate correlations between physical parameters in the neutron energy region from thermal to 10 MeV, the dose mean LET of the heavy ion component, the overall dose mean LET, and the microdosimetric parameter y0,D of the mixed field can also be derived. Experimental verification of the method is presented for various neutron-gamma radiation spectra in air and in water by comparison to theoretical calculations and results from low-pressure proportional counter measurements. Good agreement is shown. The TE high-pressure ionization chamber appears to have wide potential for use as a dose-equivalent meter in radiation protection or as a beam characterization device in radiobiology.