Generating Time-Series Data Using Generative Adversarial Networks for Mobility Demand Prediction

The increasing penetration rate of electric kickboard vehicles has been popularized and promoted primarily because of its clean and efficient features. Electric kickboards are gradually growing in popularity in tourist and education-centric localities. In the upcoming arrival of electric kickboard vehicles, deploying a customer rental service is essential. Due to its free-floating nature, the shared electric kickboard is a common and practical means of transportation. Relocation plans for shared electric kickboards are required to increase the quality of service, and forecasting demand for their use in a specific region is crucial. Predicting demand accurately with small data is troublesome. Extensive data is necessary for training machine learning algorithms for effective prediction. Data generation is a method for expanding the amount of data that will be further accessible for training. In this work, we proposed a model that takes time-series customers’ electric kickboard demand data as input, pre-processes it, and generates synthetic data according to the original data distribution using generative adversarial networks (GAN). The electric kickboard mobility demand prediction error was reduced when we combined synthetic data with the original data. We proposed Tabular-GAN-Modified-WGAN-GP for generating synthetic data for better prediction results. We modified The Wasserstein GAN-gradient penalty (GP) with the RMSprop optimizer and then employed Spectral Normalization (SN) to improve training stability and faster convergence. Finally, we applied a regression-based blending ensemble technique that can help us to improve performance of demand prediction. We used various evaluation criteria and visual representations to compare our proposed model’s performance. Synthetic data generated by our suggested GAN model is also evaluated. The TGAN-Modified-WGAN-GP model mitigates the overfitting and mode collapse problem, and it also converges faster than previous GAN models for synthetic data creation. The presented model’s performance is compared to existing ensemble and baseline models. The experimental findings imply that combining synthetic and actual data can significantly reduce prediction error rates in the mean absolute percentage error (MAPE) of 4.476 and increase prediction accuracy.     

Single-mode GaAs/AIGaAs W waveguides with a low propagation loss

We have designed a low-loss single-mode GaAs/AIGaAs optical waveguide with a symmetric five-layer heterostructure at the 1.31-μm wavelength by use of an effective-index method. Waveguides with a W-shaped refractive-index profile have been grown by use of a metallo-organic chemical vapor deposition technique and fabricated with a chemical wet-etching method. Propagation loss has been measured by use of the Fabry-Perot resonance method and a sequential-cleaving experiment. The measured loss is as low as 0.19 dB/cm for waveguides with 2.3-μm thickness and 4.3-μm width, which is comparable to the lowest-loss semiconductor waveguides yet reported. These waveguides could be used to make low-loss modulators for guided-wave devices.     

Surface modification of polyetherurethaneureas and their antithrombogenicity

Polyetherurethaneurea (PU) films were treated by oxygen plasma discharge followed by acrylic acid (AA) grafting. The carboxyl groups of the AA-grafted PU (PU-AA) surface were coupled with bovine serum albumin and heparin via water soluble carbodiimide. Surface characterization of the modified PUs was carried out by attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy and electron spectroscopy for chemical analysis (ESCA). The amount of immobilized albumin and heparin on the PU surface was 1.8 and 1.5 g/cm², respectively, as determined by the dye interaction method. Interactions between the surface-modified PUs and blood components such as plasma proteins and platelets were investigated to evaluate the blood compatibility of the samples. Plasma recalcification time (PRT) and activated partial thromboplastin time (APTT) of the albumin-immobilized PU (PU-Al) were almost the same as those of PU, while platelets were less adhered on the PU-Al than on PU. On the other hand, PRT and APTT of the PU-He were significantly longer than those of the PU, PU-AA, and PU-Al. Moreover, adhesion of platelets was effectively suppressed on the PU-He, leading to good in vitro blood compatibility.     

Comprehensive aircraft configuration design tool for Integrated Product and Process Development

This paper describes an efficient aircraft geometry design tool which is necessary for design and analysis applications through Integrated Product and Process Development (IPPD). The design process decomposes aircraft geometry into several components to represent it accurately and realistically with a reduced number of shape control parameters. For this purpose, several configuration representation algorithms are thoroughly investigated and discussed. The proposed configuration generation algorithm employs the super ellipse equation with simple analytic distribution functions, Class function/Shape function Transformation (CST) and can represent and manipulate complex shapes accurately with a small number of control parameters. A model of aircraft geometry, represented in this approach, can be applied to conceptual and preliminary stages of aircraft design and development with realistic and accurate configuration data. A Parameter-based Comprehensive Aircraft Design (PCAD) tool which implements a geometry generation process for aircraft design and optimization using customization of commercial computer-aided design software (CATIA V5) and the Product Data Management (Enovia Smarteam). The proposed configuration design tool could be especially efficient when automation, flexibility and rapid changes of geometry are required in a short time and with low computational resources.     

Constraint-based test generation for automotive operating systems

This work suggests a method for systematically constructing a software-level environment model for safety checking automotive operating systems by introducing a constraint specification language, OSEK_CSL. OSEK_CSL is designed to specify the usage constraints of automotive operating systems using a pre-defined set of constraint types identified from the international standard OSEK/VDX. Each constraint specified in OSEK_CSL is interpreted as either a regular language or a context-free language that can be checked by a finite automaton or a pushdown automaton. The set of usage constraints is used to systematically classify the universal usage model of OSEK-/VDX-based operating systems and to generate test sequences with varying degrees of constraint satisfaction using LTL model checking. With pre-defined constraint patterns and the full support of automation, test engineers can choose the degree of constraint satisfaction and generate test cases using combinatorial intersections of selected constraints that cover all corner cases classified by constraints. A series of experiments on an open-source automotive operating system show that our approach finds safety issues more effectively than conventional specification-based testing, scenario-based testing, and conformance testing.     

Using ridge regression with genetic algorithm to enhance real estate appraisal forecasting

This study considers real estate appraisal forecasting problem. While there is a great deal of literature about use of artificial intelligence and multiple linear regression for the problem, there has been always controversy about which one performs better. Noting that this controversy is due to difficulty finding proper predictor variables in real estate appraisal, we propose a modified version of ridge regression, i.e., ridge regression coupled with genetic algorithm (GA-Ridge). In order to examine the performance of the proposed method, experimental study is done for Korean real estate market, which verifies that GA-Ridge is effective in forecasting real estate appraisal. This study addresses two critical issues regarding the use of ridge regression, i.e., when to use it and how to improve it.     

Electrochemical characteristics of silicon-metals coated graphites for anode materials of lithium secondary batteries

Four kinds of silicon-metals (Cu, Ni, Sn)-graphite composites for anode active materials of lithium secondary batteries were prepared by sequential employment of PECVD (Plasma enhance chemical vapor deposition) and RF(Radio-frequency)-magnetron sputtering method. The silicon-copper-graphite composite showed the highest reversible capacity and cyclability among the silicon-metal composite graphite samples prepared. The enhanced electrochemical performance of silicon-copper-graphite composite is attributed to the formation of copper silicide on the surface of graphite. The copper silicide plays an important role as a buffering layer against volume change of silicon during the intercalation/deintercalation due to the chemical bonding of silicon and copper, and has lower interfacial impedance than that of other silicon-metal-graphite composites which may lead to low irreversible capacity.     

Preparation of AZ91D Slurries for Semi-Solid Forming Using Al8 ( Mn, Fe) 5 Precipitates

During the solidification of the AZ91D-alloys, the Al8(Mn, Fe)5 phase is generally precipitated in the melt in advance of the precipitation of the primary α-Mg. The basic principle for manufacturing AZ91D-alloy slurries for semi solid forming is to use the Al8(Mn, Fe)5 precipitates as the heterogeneous nucleation sites for primary α-Mg phases. Microscopic analysis for the location of the Al8(Mn, Fe)5 precipitate explains that the Al8(Mn, Fe)5 precipitate is the effective heterogeneous nucleation site for the primary α-Mg phase. It was also observed that increase of the Mn content in the melt and the cooling rate below to the solid/liquid two-phase region resulted in smaller and more globular primary α-Mg due to the increase of heterogeneous nucleation sites. It was found that the average α-Mg diameter grew as a function of t0.278, where t is the holding time at the solid/liquid two-phase region. This would be attributed to the Ostwald type ripening and coalescence between primary α-Mg phases. The cooling rate below to the solid/liquid two-phase region, Mn content in AZ91D alloy, and the holding time and temperature affected on the quality of slurry.     

A fast full search motion estimation algorithm using sequentialrejection of candidates from hierarchical decision structure

We propose a new as well as fast full search (FS) motion estimation algorithm for video coding. The computational reduction comes from sequential rejection of impossible candidates with derived formula and subblock norms. Our algorithm reduces more the computations than the FS motion estimation algorithms previously developed     

Generalized Approach towards Secretion-Based Protein Production via Neutralization of Secretion-Preventing Cationic Substrate Residues

Many heterologous proteins can be secreted by bacterial ATP-binding cassette (ABC) transporters, provided that they are fused with the C-terminal signal sequence, but some proteins are not secretable even though they carry the right signal sequence. The invention of a method to secrete these non-secretable proteins would be valuable both for understanding the secretory physiology of ABC transporters and for industrial applications. Herein, we postulate that cationic “supercharged” regions within the target substrate protein block the secretion by ABC transporters. We also suggest that the secretion of such substrate proteins can be rescued by neutralizing those cationic supercharged regions via structure-preserving point mutageneses. Surface-protruding, non-structural cationic amino acids within the cationic supercharged regions were replaced by anionic or neutral hydrophilic amino acids, reducing the cationic charge density. The examples of rescued secretions we provide include the spike protein of SARS-CoV-2, glutathione-S-transferase, streptavidin, lipase, tyrosinase, cutinase, growth factors, etc. In summary, our study provides a method to predict the secretability and a tool to rescue the secretion by correcting the secretion-blocking regions, making a significant step in understanding the physiological properties of ABC transporter-dependent protein secretion and laying the foundation for the development of a secretion-based protein-producing platform.