Failure in Stock Price Prediction: A Comparison bettwen the Curve-Shape-Feature and Non-Curve-Shape-Feature Modes of Existing Machine Learning Algorithms

In the era of artificial intelligence, machine learning methods are successfully used in various fields. Machine learning has attracted extensive attention from investors in the financial market, especially in stock price prediction. However, one argument for the machine learning methods used in stock price prediction is that they are black-box models which are difficult to interpret. In this paper, we focus on the future stock price prediction with the historical stock price by machine learning and deep learning methods, such as support vector machine (SVM), random forest (RF), Bayesian classifier (BC), decision tree (DT), multilayer perceptron (MLP), convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), the embedded CNN, and the embedded BiLSTM. Firstly, we manually design several financial time series where the future price correlates with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future prices can be extracted from the curve shapes of the historical stock prices. Conversely, in the NCSF mode, they can’t. Secondly, we apply various algorithms to those pre-designed and real financial time series. We find that the existing machine learning and deep learning algorithms fail in stock price prediction because in the real financial time series, less information of future prices is contained in the CSF mode, and perhaps more information is contained in the NCSF. Various machine learning and deep learning algorithms are good at handling the CSF in historical data, which are successfully applied in image recognition and natural language processing. However, they are inappropriate for stock price prediction on account of the NCSF. Therefore, accurate stock price prediction is the key to successful investment, and new machine learning algorithms handling the NCSF series are needed.

Detection of Unwanted Odors using Unmasking Odor Algorithm (UOA)

A new approach to detection of the existence of unwanted odors after spraying the smart home and vehicular environment with perfumes is considered in the work. The approach is based on registering the response curve of an array of sensors to perfumes and to odors such as herbs, then using the proposed intersection algorithm to uncover the ability of the perfume to mask specific odors. Three odors (herbs) and three perfumes are tried and resulted in the ability of perfumes to mask two of the herbs, one deeper than the other. The response curve intersection technique (RCIT) provides the ability to unmask unwanted odor existence, thus forms the heart of the unmasking odor algorithms (UOA). Mathematical equations are used to prove the concept with digital logic is further used to support the presented algorithm. The research found that using the proposed technique, an odor masked by spraying of perfumes can be unmasked using the RCIT as the case in herb 3 presented in the work. The work also showed the unique curve shape for both perfumes and herbs and the fact that some herbs can be easily masked and hidden within the response of perfumes. In addition, it is shown that the perfumes response is much more complex compared to herbs

Shape Evolution of the Interest Rate Term Structure

This paper adopts a novel approach to studying the evolution of interest rate term structure over the U.S. business cycles and to predicting recessions. Applying an effective algorithm, I classify the Treasury yield curve into distinct shapes and find the less frequent shapes intrinsically linked to the recessions in the post-WWII data. In forecasting recessions, the median-short yield spread trumps the long-short spread for horizons up to 17 months ahead and the yield curve shape is nearly impressive as the median-short spread. Overall, the yield curve shape is an informative but more succinct indicator than the spreads in studying the term structure. Key words: Business cycle, recession forecast, U.S. Treasury yield curve, yield spreads.

Numerical Simulation of Flow over Bionic Airfoil

In this study, the aerodynamic performance of bionic airfoil was numerically studied by CFD method. The bionic airfoil was represented by the combination of airfoil and a small trailing edge flap. A variety of configurations were calculated to study the effect of flap parameters, such as the flap angle, position, and shape, on the bionic airfoil aerodynamic characteristics based on two layouts which were that (1) there was a tiny gap between the airfoil and the flap and (2) there was no gap between the two. The results showed that the flap angle and position had significant effects on the aerodynamic performance of the airfoil with the two layouts. Compared with the clean airfoil, the maximum lift coefficients of the first layout and the second layout could be increased by 10.9% and 7.9%, respectively. And the effective angle of attack (AoA) range for improving the lift-to-drag ratio could reach 7°. The flap shape also affected the airfoil aerodynamic characteristics, and the flap with the sinusoid curve shape showed ideal performance.

The MOSDEF survey: The dependence of Hα-to-UV SFR ratios on SFR and size at z ∼ 2

We perform an aperture-matched analysis of dust-corrected Hα and UV SFRs using 303 star-forming galaxies with spectroscopic redshifts 1.36 < zspec < 2.66 from the MOSFIRE Deep Evolution Field (MOSDEF) survey. By combining Hα and Hβ emission line measurements with multi-waveband resolved CANDELS/3D-HST imaging, we directly compare dust-corrected Hα and UV SFRs, inferred assuming a fixed attenuation curve shape and constant SFHs, within the spectroscopic aperture. Previous studies have found that Hα and UV SFRs inferred with these assumptions generally agree for typical star-forming galaxies, but become increasingly discrepant for galaxies with higher SFRs (≳100 M⊙ yr−1), with Hα-to-UV SFR ratios being larger for these galaxies. Our analysis shows that this trend persists even after carefully accounting for the apertures over which Hα and UV-based SFRs (and the nebular and stellar continuum reddening) are derived. Furthermore, our results imply that Hα SFRs may be higher in the centers of large galaxies (i.e. where there is coverage by the spectroscopic aperture) compared to their outskirts, which could be indicative of inside-out galaxy growth. Overall, we suggest that the persistent difference between nebular and stellar continuum reddening and high Hα-to-UV SFR ratios at the centers of large galaxies may be indicative of a patchier distribution of dust in galaxies with high SFRs.

Shape of the OGTT glucose response curve: relationship with β-cell function and differences by sex, race, and BMI in adults with early type 2 diabetes treated with metformin

IntroductionThe shape of the glucose curve during an oral glucose tolerance test (OGTT) reflects β-cell function in populations without diabetes but has not been as well studied in those with diabetes. A monophasic shape has been associated with higher risk of diabetes, while a biphasic pattern has been associated with lower risk. We sought to determine if phenotypic or metabolic characteristics were associated with glucose response curve shape in adults with type 2 diabetes treated with metformin alone.Research design and methodsThis is a cross-sectional analysis of 3108 metformin-treated adults with type 2 diabetes diagnosed <10 years who underwent 2-hour 75 g OGTT at baseline as part of the Glycemia Reduction Approaches in Diabetes: A Comparative Effectiveness Study (GRADE). Insulin sensitivity (homeostasis model of insulin sensitivity, HOMA2-S) and β-cell function (early, late, and total incremental insulin and C peptide responses adjusted for HOMA2-S) were calculated. Glucose curve shape was classified as monophasic, biphasic, or continuous rise.ResultsThe monophasic profile was the most common (67.8% monophasic, 5.5% biphasic, 26.7% continuous rise). The monophasic subgroup was younger, more likely male and white, and had higher body mass index (BMI), while the continuous rise subgroup was more likely female and African American/black. HOMA2-S and fasting glucose did not differ among the subgroups. The biphasic subgroup had the highest early, late, and total insulin and C peptide responses (all p<0.05 vs monophasic and continuous rise). Compared with the monophasic subgroup, the continuous rise subgroup had similar early insulin (p=0.3) and C peptide (p=0.6) responses but lower late insulin (p<0.001) and total insulin (p=0.008) and C peptide (p<0.001) responses.ConclusionsBased on the large multiethnic GRADE cohort, sex, race, age, and BMI were found to be important determinants of the shape of the glucose response curve. A pattern of a continuously rising glucose at 2 hours reflected reduced β-cell function and may portend increased glycemic failure rates.Trial registration numberNCT01794143.

Method to Correct the Velocity Variation Information of an Automatic Crash Notification System in Vehicle-to-Rigid Barrier Frontal Collisions

Automatic crash notification systems (ACNSs) play a key role in post-accident safety. To improve the accuracy and efficiency of ACNSs, a method to correct the velocity variation information of ACNSs was established. First, after the acceleration data of sled crash tests were analysed, the factors affecting the accuracy of the velocity variation information were determined, and the influence of the discrimination threshold and acceleration curve shape on the velocity variation information was examined. Second, according to the acceleration data generated by the simulation model of a sled crash, the correlation between the accuracy of the velocity variation information and influencing factors was modelled. Third, an automatic crash notification algorithm involving a velocity variation correction function (VVCF) was proposed based on the correlation model. Finally, to verify its reliability, the improved algorithm was applied to an automatic crash notification system (ACNS) terminal. The validation results show that the ACNS terminal can accurately identify collisions and transmit accident information. Moreover, more accurate velocity variation information can be retrieved.

Clinical validation of an audio-based uroflowmetry app in adult males

Introduction: Uroflowmetry is a common test to evaluate lower urinary tract symptoms. Audio-based uroflowmetry is a novel, alternative approach that determines urine flow by measuring sound. Available as a smartphone application, it has potential for screening and monitoring common urological pathologies, particularly in out-of-office environments. This study is the first to evaluate audio-based uroflowmetry in a clinical setting against the gold standard. Methods: Adult male patients (n=44) attending a general urology clinic were recruited. Audio-based uroflowmetry and conventional uroflowmetry were performed concurrently. Pearson correlation and Bland-Altman analysis were used to compare performance with respect to max flow, time to max flow, and total voiding time. Symmetric mean absolute percentage error (SMAPE) was used to compare curve shapes. Repeatability was evaluated separately in three healthy volunteers using repeat measures correlation. Results: Among urology clinic patients, the correlation for max flow was 0.12. Correlation for time to max flow was 0.46, with limits of agreement of -120–165%. Correlation for total voiding time was 0.91, with limits of agreement of -41–38%. The SMAPE for curve shape was 32.6%, with corresponding accuracy of 67.4%. Among healthy volunteers, the repeat measures correlation for max flow was 0.72. Conclusions: Audio-based uroflowmetry was inconsistent in evaluating flow rate, attributable to high variability and difficult standardization for acoustic signals. Performance improved with respect to temporal variables, as well as flow curve shape. Further work evaluating intra-patient reliability and pathology-specific performance is required to fully evaluate audio-based uroflowmetry as a screening or monitoring tool.

Relationships and Spatial Structure of Soil Physical Properties in a Ten-Year Corn-Cotton Rotation Field

This study quantified the relationships between soil, textural, and hydraulic properties at the field-scale for a conventional tilled Memphis silt loam that had undergone a 10-year corn and cotton rotation and described their spatial variability. Composite soil samples collected from the plow layer at 272 nodes on 15 x 15 m grids were analyzed for texture and bulk density. These values were used as pedotransfer functions to predict unsaturated (Ko) and saturated hydraulic (Ks) conductivities as well as the van Genuchten curve shape parameters α and n. Regression analyses quantified relationships between the measured and model predicted soil properties. While correlations between textural and model predicted soil properties including bulk density were significant (p<0.05), those between sand and clay, clay and n, clay and α were not. Sand and silt appeared to be better predictors of soil hydraulic conductivity and the van Genuchten curve shape parameters for the soil investigated. Spatial dependence was strong for sand, silt, bulk density, Ko, α and n, and moderate for clay and Ks.

Research on Parameters of Wire-Filling Laser Welding and Quenching Process for Joints Microstructure and Mechanical Property of BR1500HS Steel

With the aim to investigate the effect of parameter and quenching process on the joint of hot stamping steel by laser welding, the BR1500HS boron steel was welded by filling-wire laser welding with ER70-G welding wire under different parameters. The welded specimens were heated to 900℃ and held for 5min before water quenching. The universal material test machine, Optical micro-scope, Vickers hardness tester, scanning electron microscope and electron backscatter diffraction (EBSD) were used to characterize. The results showed that the macroscopic morphology of fusion zone (FZ) becomes from funnelform to hyperbolic curve shape when heat input increases and from hyperbolic curve shape to funnelform when wire-feed speed increases. The strength after quenching is more than 1557Mpa at heat input of 1040J/cm, wire feeding speed of 1.6m/min~1.8m/min and welding speed of 1.5m/min. EBSD test showed that the FZ and fine grain zone (FGZ) have more retained austenite (RA) than coarse grain zone (CGZ) before quenching and RA in FZ and heat affect zone (HAZ) decreased and distributed uniformed after quenching. The grain diameter in FZ distribute unevenly, with the maximum grain diameter larger than 40&mu;m before quenching. After quenching, the grain diameter of FZ, HAZ and BM is more even and coarse grains in the FZ was refined. Before quenching, the microhardness of FZ and HAZ is of 450HV~500HV at different heat input and wire-feed speed and all region of joint keeps at 450HV~550HV after quenching. Most dimple and little river pattern in the joint fracture mor-phology before quenching indicates a well plasticity and most cleavage facet is observed after quenching due to the joint combine with martensite.