Rule-based classifier based on accident frequency and three-stage dimensionality reduction for exploring the factors of road accident injuries.

Road accidents are one of the primary causes of death worldwide; hence, they constitute an important research field. Taiwan is a small country with a high-density population. It particularly has a considerable number of locomotives. Furthermore, Taiwan's traffic accident fatality rate increased by 23.84% in 2019 compared with 2018, primarily because of human factors. Road safety has long been a challenging problem in Taiwanese cities. This study collected public data pertaining to traffic accidents from the Taoyuan city government in Taiwan and generated six datasets based on the various accident frequencies at the same location. To find key attributes, this study proposes a three-stage dimension reduction to filter attributes, which includes removing multicollinear attributes, the integrated attribute selection method, and statistical factor analysis. We applied five rule-based classifiers to classify six different frequency datasets and generate the rules of accident severity. The order of top ten key attributes was hit vehicle > certificate type > vehicle > action type > drive quality > escape > accident type > gender > job > trip purposes in the maximum accident frequency CF ≥ 10 dataset. When locomotives, bicycles, and people collide with other locomotives or trucks, injury or death can easily occur, and the motorcycle riders are at the highest risk. The findings of this study provide a reference for governments and stakeholders to reduce the road accident risk factors.

A Seasonal Time-Series Model Based on Gene Expression Programming for Predicting Financial Distress.

The issue of financial distress prediction plays an important and challenging research topic in the financial field. Currently, there have been many methods for predicting firm bankruptcy and financial crisis, including the artificial intelligence and the traditional statistical methods, and the past studies have shown that the prediction result of the artificial intelligence method is better than the traditional statistical method. Financial statements are quarterly reports; hence, the financial crisis of companies is seasonal time-series data, and the attribute data affecting the financial distress of companies is nonlinear and nonstationary time-series data with fluctuations. Therefore, this study employed the nonlinear attribute selection method to build a nonlinear financial distress prediction model: that is, this paper proposed a novel seasonal time-series gene expression programming model for predicting the financial distress of companies. The proposed model has several advantages including the following: (i) the proposed model is different from the previous models lacking the concept of time series; (ii) the proposed integrated attribute selection method can find the core attributes and reduce high dimensional data; and (iii) the proposed model can generate the rules and mathematical formulas of financial distress for providing references to the investors and decision makers. The result shows that the proposed method is better than the listing classifiers under three criteria; hence, the proposed model has competitive advantages in predicting the financial distress of companies.

A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method.

Reservoirs are important for households and impact the national economy. This paper proposed a time-series forecasting model based on estimating a missing value followed by variable selection to forecast the reservoir's water level. This study collected data from the Taiwan Shimen Reservoir as well as daily atmospheric data from 2008 to 2015. The two datasets are concatenated into an integrated dataset based on ordering of the data as a research dataset. The proposed time-series forecasting model summarily has three foci. First, this study uses five imputation methods to directly delete the missing value. Second, we identified the key variable via factor analysis and then deleted the unimportant variables sequentially via the variable selection method. Finally, the proposed model uses a Random Forest to build the forecasting model of the reservoir's water level. This was done to compare with the listing method under the forecasting error. These experimental results indicate that the Random Forest forecasting model when applied to variable selection with full variables has better forecasting performance than the listing model. In addition, this experiment shows that the proposed variable selection can help determine five forecast methods used here to improve the forecasting capability.

Influence of the drug distribution in electrospun gliadin fibers on drug-release behavior.

Drug distribution within its carrier in a solid dosage form often generates a profound influence on its release profile, particularly when the physicochemical properties of the carrier are exploited to manipulate drug release behavior. In this job, two different types of distributions of a model drug ibuprofen (IBU) within a protein gliadin in their electrospun nanofibers were intentionally created. One was homogeneous distribution in the monolithic fibers fabricated using a modified coaxial process, and the other one was heterogeneous distribution in the core/shell fibers prepared through a traditional coaxial process. SEM observations clearly demonstrated the different distributions of IBU within gliadin in the two kinds of nanofibers although both of them had smooth surfaces and linear morphology. XRD results showed that IBU was amorphously distributed in the monolithic fibers, but that some IBU crystalline lattices presented in the core/shell fibers. FTIR and RM spectra suggested that gliadin had good compatibility with IBU. In vitro dissolution tests verified that the gliadin nanofibers with a heterogeneous drug distribution could provide a better sustained release profile than its counterpart in terms of initial burst release and sustained release time period. Both the fiber formation and drug-controlled release mechanisms are suggested. The present study demonstrated a concept that drug distribution with the medicated nanomaterials can be exploited as a tool to optimize the drug sustained release profile.

Nanosized sustained-release drug depots fabricated using modified tri-axial electrospinning.

Nanoscale drug depots, comprising a drug reservoir surrounded by a carrier membrane, are much sought after in contemporary pharmaceutical research. Using cellulose acetate (CA) as a filament-forming polymeric matrix and ferulic acid (FA) as a model drug, nanoscale drug depots in the form of core-shell fibers were designed and fabricated using a modified tri-axial electrospinning process. This employed a solvent mixture as the outer working fluid, as a result of which a robust and continuous preparation process could be achieved. The fiber-based depots had a linear morphology, smooth surfaces, and an average diameter of 0.62±0.07µm. Electron microscopy data showed them to have clear core-shell structures, with the FA encapsulated inside a CA shell. X-ray diffraction and IR spectroscopy results verified that FA was present in the crystalline physical form. In vitro dissolution tests revealed that the fibers were able to provide close to zero-order release over 36h, with no initial burst release and minimal tailing-off. The release properties of the depot systems were much improved over monolithic CA/FA fibers, which exhibited a significant burst release and also considerable tailing-off at the end of the release experiment. Here we thus demonstrate the concept of using modified tri-axial electrospinning to design and develop new types of heterogeneous nanoscale biomaterials. STATEMENT OF SIGNIFICANCE: Nanoscale drug depots with a drug reservoir surrounded by a carrier are highly attractive in biomedicine. A cellulose acetate based drug depot was investigated in detail, starting with the design of the nanostructure, and moving through its fabrication using a modified tri-axial electrospinning process and a series of characterizations. The core-shell fiber-based drug depots can provide a more sustained release profile with no initial burst effect and less tailing-off than equivalent monolithic drug-loaded fibers. The drug release mechanisms are also distinct in the two systems. This proof-of-concept work can be further expanded to conceive a series of new structural biomaterials with improved or new functional performance.

Influence of Working Temperature on The Formation of Electrospun Polymer Nanofibers.

Temperature is an important parameter during electrospinning, and virtually, all solution electrospinning processes are conducted at ambient temperature. Nanofiber diameters presumably decrease with the elevation of working fluid temperature. The present study investigated the influence of temperature variations on the formation of polymeric nanofibers during single-fluid electrospinning. The surface tension and viscosity of the fluid decreased with increasing working temperature, which led to the formation of high-quality nanofibers. However, the increase in temperature accelerated the evaporation of the solvent and thus terminated the drawing processes prematurely. A balance can be found between the positive and negative influences of temperature elevation. With polyacrylonitrile (PAN, with N,N-dimethylacetamide as the solvent) and polyvinylpyrrolidone (PVP, with ethanol as the solvent) as the polymeric models, relationships between the working temperature (T, K) and nanofiber diameter (D, nm) were established, with D = 12598.6 - 72.9T + 0.11T 2 (R = 0.9988) for PAN fibers and D = 107003.4 - 682.4T + 1.1T 2 (R = 0.9997) for PVP nanofibers. Given the fact that numerous polymers are sensitive to temperature and numerous functional ingredients exhibit temperature-dependent solubility, the present work serves as a valuable reference for creating novel functional nanoproducts by using the elevated temperature electrospinning process.

Nanofibers Fabricated Using Triaxial Electrospinning as Zero Order Drug Delivery Systems.

A new strategy for creating functional trilayer nanofibers through triaxial electrospinning is demonstrated. Ethyl cellulose (EC) was used as the filament-forming matrix in the outer, middle, and inner working solutions and was combined with varied contents of the model active ingredient ketoprofen (KET) in the three fluids. Triaxial electrospinning was successfully carried out to generate medicated nanofibers. The resultant nanofibers had diameters of 0.74 ± 0.06 µm, linear morphologies, smooth surfaces, and clear trilayer nanostructures. The KET concentration in each layer gradually increased from the outer to the inner layer. In vitro dissolution tests demonstrated that the nanofibers could provide linear release of KET over 20 h. The protocol reported in this study thus provides a facile approach to creating functional nanofibers with sophisticated structural features.

Liposomes self-assembled from electrosprayed composite microparticles.

Composite microparticles, consisting of polyvinylpyrrolidone (PVP), naproxen (NAP) and lecithin (PC), have been successfully prepared using an electrospraying process and exploited as templates to manipulate molecular self-assembly for the synthesis of liposomes in situ. Field emission scanning electron microscope (FESEM) and transmission electron microscope (TEM) observations demonstrate that the microparticles have an average diameter of 960 ± 140 nm and a homogeneous structure. X-ray diffraction (XRD) patterns, differential scanning calorimetry (DSC) and attenuated total reflectance-Fourier transform infrared (ATR-FTIR) results verify that the building blocks NAP and PC are scattered in the polymer matrix in a molecular way owing to the very fast drying of the electrospraying process and the favorable secondary interactions among the components. FESEM, scanning probe microscope (SPM) and TEM observations demonstrate that the liposomes can be achieved through molecular self-assembly in situ when the microparticles contact water thanks to 'like prefers like' and by means of the confinement effect of the microparticles. The liposomes have an encapsulation rate of 91.3%, and 80.7% of the drug in the liposomes can be freed into the dissolution medium in a sustained way and by a diffusion mechanism over a period of 24 h. The developed strategy not only provides a new, facile, and effective method to assemble and organize molecules of multiple components into liposomes with electrosprayed microparticles as templates, but also opens a new avenue for nanofabrication in a step-by-step and controllable way.

Polyacrylonitrile nanofibers prepared using coaxial electrospinning with LiCl solution as sheath fluid.

A modified coaxial electrospinning process including an electrolyte solution as sheath fluid was used for preparing high quality polymer nanofibers. A series of polyacrylonitrile (PAN) nanofibers were fabricated utilizing a coaxial electrospinning containing LiCl in N, N-dimethylacetamide (DMAc) as the sheath fluid. FESEM results demonstrated that the sheath LiCl solutions have a significant influence on the quality of PAN nanofibers. Nanofibers with smaller diameters, smoother surfaces and uniform structures were successfully prepared. The diameters of nanofibers were controlled by adjusting the conductivity of the sheath fluid over a suitable range and this was determined by varying LiCl concentrations. The influence of the effect of LiCl on the formation of PAN fibers is discussed and it is concluded that coaxial electrospinning with electrolyte solutions is a convenient and facile process for achieving high quality polymer nanofibers.

Solid dispersions in the form of electrospun core-sheath nanofibers.

BACKGROUND: The objective of this investigation was to develop a new type of solid dispersion in the form of core-sheath nanofibers using coaxial electrospinning for poorly water-soluble drugs. Different functional ingredients can be placed in various parts of core-sheath nanofibers to improve synergistically the dissolution and permeation properties of encapsulated drugs and to enable drugs to exert their actions. METHODS: Using acyclovir as a model drug, polyvinylpyrrolidone as the hydrophilic filament-forming polymer matrix, sodium dodecyl sulfate as a transmembrane enhancer, and sucralose as a sweetener, core-sheath nanofibers were successfully prepared, with the sheath part consisting of polyvinylpyrrolidone, sodium dodecyl sulfate, and sucralose, and the core part composed of polyvinylpyrrolidone and acyclovir. RESULTS: The core-sheath nanofibers had an average diameter of 410 ± 94 nm with a uniform structure and smooth surface. Differential scanning calorimetry and x-ray diffraction results demonstrated that acyclovir, sodium dodecyl sulfate, and sucralose were well distributed in the polyvinylpyrrolidone matrix in an amorphous state due to favoring of second-order interactions. In vitro dissolution and permeation studies showed that the core-sheath nanofiber solid dispersions could rapidly release acyclovir within one minute, with an over six-fold increased permeation rate across the sublingual mucosa compared with that of crude acyclovir particles. CONCLUSION: The study reported here provides an example of the systematic design, preparation, characterization, and application of a novel type of solid dispersion consisting of multiple components and structural characteristics.