Monitoring of Casting Quality Using Principal Component Analysis Based Self-Organizing Map

The monitoring of casting quality is very important to ensure the safe operation of casting processes. In this paper, in order to improve the accurate detection of casting defects, a combined method based on Principal Component Analysis (PCA) and Self-Organizing Map (SOM) is presented. The proposed method reduces the dimensionality of the original data by the projection of the data onto a smaller subspace through PCA. It uses Hotelling’s T2 and Q statistics as essential features for characterizing the process functionality. The SOM is used to improve the separation between casting defects. It computes the metric distances based similarity, using the T2 and Q (T2Q) statistics as input. A comparative study between conventional SOM, SOM with reduced data and SOM with selected features is examined. The proposed method is used to identify the running conditions of the low pressure lost foam casting process. The monitoring results indicate that the SOM based on T2Q as feature vectors remains important comparatively to conventional SOM and SOM based on reduced data.

Ultra short time to Echo (UTE) MRI for cephalometric analysis–Potential of an x-ray free fast cephalometric projection technique

Objectives A novel magnetic resonance imaging (MRI) scan protocol is presented on the basis of ultra-short time to echo (UTE). By this MRI cephalometric projections (MCPs) can be acquired without the need of post processing in one shot. Different technical parameterizations of the protocol are performed. Their impact on the performance of MCPs is evaluated in comparison to the gold standard–the lateral cephalometric radiography (LCR) for cephalometric analysis (CA) in orthodontics. Methods Seven MCPs with various scan parameters influencing the scan duration and one LCR are used from one subject. 40 expert assessors performed CA for 14 predefined cephalometric landmarks. Relative metric distances and absolute angular measurements were calculated. Statistical analysis is presented and the deviations are highlighted to demonstrate the potential of the method for further analysis. Results The MCPs are acquired in 5–154 seconds, depending on resolution and contrast. Mean relative distances were 2.4–2.7 mm in MCPs and 1.6 mm in LCR, which demonstrate the accuracy and level of agreement of the expert assessors in identifying anatomical landmarks. In comparison to other studies, the presented MCP performed similar in angular analysis and demonstrated on average deviation of 1.2° ±1.1° in comparison to LCR. Despite the point articulare (Ar) and the related gonial angle the calculate distances and angles show outcomes in the range of ±2°/2mm. Conclusions MCPs can be acquired much faster in comparison to other techniques known from literature for CA. This study demonstrated the potential of the new method and showed first feasible results. Further research is needed to analyze the performance on a broad range of patients.

On Quantum Gravity As A Recorded Quantum Arrow Of Time

I take non-locality to be the Michaelson Morley experiment of the early 21st Century, assume its universal validity, and try to derive its consequences. Spacetime, with its locality, cannot be fundamental, but must somehow be emergent from entangled coherent quantum variables and their behaviors. There are, then, two immediate consequences: i. If we start with non-locality, we need not explain non-locality. We must instead explain an emergence of locality and spacetime. ii. There can be no emergence of spacetime without matter. These propositions flatly contradict General Relativity, which is foundationally local, can be formulated without matter, and in which there is no "emergence" of spacetime.It these be true, then quantum gravity cannot be a minor alteration of General Relativity, but must demand its deep reformulation. This will almost inevitably lead to: Matter not only deforms spacetime, but "creates" spacetime. We will see independent grounds for the assertion that matter both deforms and creates spacetime that may invite a new union of quantum gravity and General Relativity.This quantum creation of spacetime consists in: i. Fully non-local entangled coherent quantum variables. ii. The onset of locality via decoherence. iii. A metric in Hilbert Space among entangled quantum variables by the sub-additive von Neumann Entropy between pairs of variables. iv. Mapping from metric distances in Hilbert Space to metric distances in classical spacetime by episodic actualization events. v. Discrete spacetime is the relations among these discrete actualization events. vi. "Now" is the shared moment of actualization of one among the entangled variables when the amplitudes of the remaining entangled variables change instantaneously. vii. The discrete, successive, episodic, irreversible actualization events constitute a quantum arrow of time. viii. The arrow of time history of these events is recorded in the very structure of the spacetime constructed. ix. Actual Time is a succession of two or more actual events.This quantum creation of spacetime modifies general relativity and may account for Dark Energy, Dark Matter, and the possible elimination of the singularities of General Relativity. Possible experimental tests in both the attractive and repulsive Casimir effect setting are described. A quantum actualization enhancement of repulsive Casimir would be anti-gravitational, and of possible practical use. Relations to Causal Set Theory, faithful Lorentzian manifolds, and past and future light cones joined at ``Actual Now'' are discussed.The ideas and concepts discussed here are not yet a theory, but at most a framework that may be useful.

A Novel Ensemble Machine Learning Approach for Bioarchaeological Sex Prediction

I present a novel machine learning approach to predict sex in the bioarchaeological record. Eighteen cranial interlandmark distances and five maxillary dental metric distances were recorded from n = 420 human skeletons from the necropolises at Alfedena (600–400 BCE) and Campovalano (750–200 BCE and 9–11th Centuries CE) in central Italy. A generalized low rank model (GLRM) was used to impute missing data and Area under the Curve—Receiver Operating Characteristic (AUC-ROC) with 20-fold stratified cross-validation was used to evaluate predictive performance of eight machine learning algorithms on different subsets of the data. Additional perspectives such as this one show strong potential for sex prediction in bioarchaeological and forensic anthropological contexts. Furthermore, GLRMs have the potential to handle missing data in ways previously unexplored in the discipline. Although results of this study look promising (highest AUC-ROC = 0.9722 for predicting binary male/female sex), the main limitation is that the sexes of the individuals included were not known but were estimated using standard macroscopic bioarchaeological methods. However, future research should apply this machine learning approach to known-sex reference samples in order to better understand its value, along with the more general contributions that machine learning can make to the reconstruction of past human lifeways.

Deep Hierarchical Embedding for Simultaneous Modeling of GPCR Proteins in a Unified Metric Space

GPCR proteins belong to diverse families of proteins that are defined at multiple hierarchical levels. Inspecting relationships between GPCR proteins on the hierarchical structure is important, since characteristics of the protein can be inferred from proteins in similar hierarchical information. However, modeling of GPCR families has been performed separately at each level. Relationships between GPCR proteins are ignored in these approaches as they process the information in the proteins with several disconnected models. In this study, we propose a deep learning model to simultaneously learn representations of GPCR family hierarchy from the protein sequences with a unified single model. Novel loss term based on metric learning is introduced to incorporate hierarchical relations between proteins. We tested our approach using a public GPCR sequence dataset. Metric distances in the deep feature space corresponded to the hierarchical family relation between GPCR proteins. Furthermore, we demonstrated that further downstream tasks, like phylogenetic reconstruction and motif discovery, are feasible in the constructed embedding space. These results show that hierarchical relations between sequences were successfully captured in both of technical and biological aspects.

Bioarchaeological sex prediction from central Italy using generalized low rank imputation for cross-validated metric craniodental supervised ensemble machine learning with missing data

I use a novel supervised ensemble machine learning approach to verify sex estimation of archaeological skeletons from central Italian bioarchaeological contexts with large amounts of missing data present. Eighteen cranial interlandmark distances and five maxillary metric distances were recorded from n = 240 estimated males and n = 180 estimated females from four locations at Alfedena (600-400 BCE) and two locations at Campovalano (750-200 BCE and 9-11th Century CE). A generalized low rank model (GLRM) was used to impute missing data and 20-fold external stratified cross-validation was used to fit an ensemble of eight machine learning algorithms to six different subsets of the data: 1) the face, 2) vault, 3) cranial base, 4) combined face/vault/base, 5) dentition, and 6) combined cranianiodental. Area under the receiver operator characteristic curve (AUC) was used to evaluate the predictive performance of six constituent algorithms, the discrete algorithmic winner(s), and the SuperLearner weighted ensemble’s classification of males and females from these six bony regions. This approach is useful for predicting male/female sex from central Italy. AUC for the combined craniodental data was the highest (0.9722), followed by the combined cranial data (0.9644), the face (0.9426), vault (0.9116), base (0.9060), and dentition (0.7421). Cross-validated ensemble machine learning of cranial and dental data shows strong potential for estimating sex in the bioarchaeological record and can contribute additional perspectives to help refine our understanding of human sex estimation. Additionally, GLRMs have the potential to handle missing data in ways previously unexplored in the discipline. The main limitation is that the biological sexes of the individuals estimated in this study are not certain, but were estimated macroscopically using common bioarchaeological methods. However, these methods show great promise for estimation of sex in bioarchaeological and forensic contexts and should be investigated on known-sex reference samples for confirmation.

The Ups and Downs of Camera-Monitor Systems: The Effect of Camera Position on Rearward Distance Perception

Objective This study investigates the effects of different positions of side-mounted rear-view cameras on distance estimation of drivers. Background Camera-monitor systems bring advantages as compared to conventional rear-view mirrors, such as improved aerodynamics and enlarged field-of-view. Applied research has mainly focused on the comparison between cameras and mirrors or on positioning of in-vehicle monitors. However, the positioning of the exterior camera awaits investigation given that the perspective of the observer at does affect depth perception at large. Method In two experiments, a total of 50 students estimated metric distances to static vehicles presented in realistic or 3D-rendered pictures. The pictures depicted the rearward scene of a car following the driver as viewed through a camera at varying vertical and horizontal positions. The following vehicle’s size and environmental information varied among conditions and experiments. Results Lower camera positions led to distance overestimation and higher positions to underestimation. The effect increased as the distance to the following vehicle decreased. Moreover, larger vehicles led to stronger distance underestimation, especially in low camera positions. Interestingly, the main effect of camera position disappeared when the ego-vehicles’ back was visible. Conclusion Different rearward viewpoints affect distance estimation of drivers, especially in close distances. However, a visible reference of one’s own vehicle seems to mostly compensate this effect. Application In general, the rear-view camera should be mounted rather higher and to the front of the vehicle. Also, the vehicle’s back should always be visible. Low camera positions are not recommended.

Characterizing neural coding performance for populations of sensory neurons: comparing a weighted spike distance metrics to other analytical methods

ABSTRACTThe identity of sensory stimuli is encoded in the spatio-temporal patterns of responses of the neural population. For stimuli to be discriminated reliably, differences in population responses must be accurately decoded by downstream networks. Several methods to compare the pattern of responses and their differences have been used by neurophysiologist to characterize the accuracy of the sensory responses studied. Among the most widely used analysis, we note methods based on Euclidian distances or on spike metric distance such as the one proposed by van Rossum. Methods based on artificial neural network and machine learning (such as self-organizing maps) have also gain popularity to recognize and/or classify specific input patterns. In this brief report, we first compare these three strategies using dataset from 3 different sensory systems. We show that the input-weighting procedure inherent to artificial neural network allows the extraction of the information most relevant to the discrimination task and thus the method performs particularly well. To combine the ease of use and rapidity of methods such as spike metric distances and the advantage of weighting the inputs, we propose a measure based on geometric distances were each dimension is weighted proportionally to how informative it is. In each dimension, the overlap between the distributions of responses to the two stimuli is quantified using the Kullback-Leibler divergence measure. We show that the result of this Kullback-Leibler-weighted spike train distance (KLW distance) analysis performs as well or better than the artificial neural network we tested and outperforms the more traditional spike distance metrics. We applied information theoretic analysis to Leaky-Integrate-and-Fire model neuron responses and compare their encoding accuracy with the discrimination accuracy quantified through these distance metrics to show the high degree of correlation between the results of the two approaches for quantifying coding performance. We argue that our proposed measure provides the flexibility, ease of use sought by neurophysiologist while providing a more powerful way to extract the relevant information than more traditional methods.

Content based Retrieval of Liver Images for Computer Aided Diagnosis

Liver cancer is a serious disease caused by a variety of factors that damage the liver region. Early detection of this disease is necessary to diagnose and to cure it completely. Enormous increase in medical database images has lead to development of Content Based Image Retrieval (CBIR) system to retrieve relevant liver images from medical database consisting of abdominal Computed Tomography (CT) images. In the proposed method Content Based Medical Image Retrieval (CBMIR) system is designed to search and retrieve relevant liver images from medical image database. Adaptive Region Growing Algorithm (ARGA) and Simple Linear Iterative Clustering (SLIC) are used for liver and tumor segmentation. Features are extracted using Gray Level Co-occurrence Matrix (GLCM), Average Correction High order Local Autocorrelation Coefficients (ACHLAC) and Legendre Moments (LM). Based on the distance metric, distances between extracted features of query image and images in the database are measured. Euclidean distance metric is used to retrieve relevant medical images.