Machine Learning Applications in Baseball: A Systematic Literature Review

Statistical analysis of baseball has long been popular, albeit only in limited capacity until relatively recently. In particular, analysts can now apply machine learning algorithms to large baseball data sets to derive meaningful insights into player and team performance. In the interest of stimulating new research and serving as a go-to resource for academic and industrial analysts, we perform a systematic literature review of machine learning applications in baseball analytics. The approaches employed in literature fall mainly under three problem class umbrellas: Regression, Binary Classification, and Multiclass Classification. We categorize these approaches, provide our insights on possible future applications, and conclude with a summary of our findings. We find two algorithms dominate the literature: (1) Support Vector Machines for classification problems and (2) k-nearest neighbors for both classification and Regression problems. We postulate that recent proliferation of neural networks in general machine learning research will soon carry over into baseball analytics.     

Synthesis and metal ions sorption properties of styrene‐based polymers

Atactic polystyrene (PS) was chemically modified with maleic (MAH), succinic (SAH), and phtalic (PhAH) anhydrides. Styrene was copolymerized with acrylic (AA) and methacrylic acids (MA). Amount of carboxyl groups (%) bound to polymers was determined in the range of 6.9–25.9. Different modified polystyrenes (MPS) and styrene copolymers were used in the experiments to study Cu(II) and Zn(II) ions adsorption probability and their comparison. Sorption capacity of the polymers for the metal ions were investigated in aqueous media containing different amounts of these ions (5–40 mg/L) and at different pH values (2.0–6.0). Adsorption behavior of heavy metal ions could be modeled using both the Langmuir and Freundlich isotherms. It was found that the adsorption capacity is highest at pH value of 6, whereas it decreases as the pH value decreases at temperature 25°C ± 1°C for 240 min. The results obtained from the adsorption capacity experiments for Cu(II) and Zn(II) ions were 3.47–5.45 and 5.42–6.85 mg/g, respectively. The affinity order of polymers for both metal ions was observed as follows: SMAC > SAAC > MPS with MAH > MPS with SAH > MPS with PhAH. The maximum adsorption capacities of SMAC were 6.85mg/g for Zn(II) and 5.45 mg/g for Cu(II). © 2009 Wiley Periodicals, Inc. J Appl Polym Sci, 2009     

Recycling studies of marble processing waste: Composites based on commercial epoxy resin

Marble waste was obtained from marble processing plant wastewater with precipitation using different coagulants, such as sepiolite, zeolite, and pumice in dosages of 0.5–8 g/500 mL and mixed in 20 wt % with commercial epoxy resin. The effects of marble, coagulant type and dosage on the physicomechanical and thermal properties were investigated. The incorporation of marble processing waste particles increases the 10% decomposition temperature of pure epoxy by 5–50°C. Surface hardness, tensile strength, percentage elongation, and stress at maximum load of the composites were higher than those of pure resin, too. The composites reinforced with marble processing waste-pumice showed about 10% increase in elastic modulus, whereas the composite reinforced with marble processing waste-sepiolite or zeolite showed about 76.67–143.33% increase in elastic modulus over the pure epoxy matrix. Scanning electron microscopy (SEM) was used for characterization of surface and cross sections of the composites to verify the results. © 2011 Wiley Periodicals, Inc. J Appl Polym Sci, 2012     

Corrosion and thermal characterization of styrene based copolymers

Films from copolymers with resistance to wear, corrosion and thermal degradation as well as other important functions have been applied in many fields. It is known that the introduction of anionic hydrophilic groups in the polymer enhances its adhesion to substrates and protective function. In the present work, copolymers of styrene with acrylic, methacrylic and itaconic acids were prepared by polymerization in toluene with benzoyl peroxide initiation (BPO) and have been tested as anticorrosive films. The copolymers were analyzed by FTIR and TGA methods. Polarizing microscope images were employed to characterize the anticorrosive properties of the formed films. All copolymers produced in this work show strong adhesion to the substrate.     

Mechanical and thermal studies on epoxy toluene oligomer‐modified epoxy resin/marble waste composites

In this research, marble dust waste was recycled as raw material for the preparation of composite materials. Epoxy toluene oligomer (ETO) was synthesized from toluene and epichlorohydrin, which was used as a comatrix in 50 wt% with commercial epoxy resin (ER). Its chemical structure was characterized with Fourier transform infrared spectroscopy and chemical analyses. The rigid filler used in epoxy polymer matrix was the marble processing waste obtained from wastewater using different coagulants, such as sepiolite, zeolite, or pumice. The thermal and mechanical properties of the composites were evaluated with thermogravimetric and mechanical analyses. The results showed that the marble wastes with all coagulants can significantly improve the thermal stability of an ER–ETO matrix at temperatures above 350°C. Composites exhibited a higher thermal degradation temperature with a much higher char yield. Surface hardness and tensile strength of the composites were higher than those of pure epoxy polymer matrix, as well. Scanning electron microscopy was used for the characterization of surface and cross‐sections of the composites to verify the results. POLYM. COMPOS., 2012. © 2012 Society of Plastics Engineers     

Synthesis of novel brominated bis-tetrahydrophthalimides and bis-nadimides and their possible application as flame-retardant additives for polystyrene composites

Ten tetrabrominated bisimides of which eight were novel were tested as flame-retardant additives. They were prepared from corresponding bisimides by the addition of bromine. Structural properties and related thermal characteristics of these brominated compounds were determined. Flame-retardant properties of tetrabrominated bisimides were tested on high-impact polystyrene, containing various amounts of brominated bisimides, according to ASTM-D-3801, “Standard Test Method for Measuring the Comparative Extinguishing Characteristics of Solid Plastics in a Vertical Position,” and DIN-51960, “Testing of Organic Floor Coverings Assessment of Flammability.” It was observed that tetrabrominated bis-imides had improved flame resistance of high-impact polystyrene. In addition, thermoxi-dative stability of novel three bisimides, 04, 14 , and 05 , were compared with the others. © 1996 John Wiley & Sons, Inc.     

Multi-dimensional students’ evaluation of e-learning systems in the higher education context: An empirical investigation

There has been little research on assessment of learning management systems (LMS) within educational organizations as both a web-based learning system for e-learning and as a supportive tool for blended learning environments. This study proposes a conceptual e-learning assessment model, hexagonal e-learning assessment model (HELAM) suggesting a multi-dimensional approach for LMS evaluation via six dimensions: (1) system quality, (2) service quality, (3) content quality, (4) learner perspective, (5) instructor attitudes, and (6) supportive issues. A survey instrument based on HELAM has been developed and applied to 84 learners. This sample consists of students at both undergraduate and graduate levels who are users of a web-based learning management system, U-Link, at Brunel University, UK. The survey instrument has been tested for content validity, reliability, and criterion-based predictive validity. The analytical results strongly support the appropriateness of the proposed model in evaluating LMSs through learners’ satisfaction. The explanatory factor analysis showed that each of the six dimensions of the proposed model had a significant effect on the learners’ perceived satisfaction. Findings of this research will be valuable for both academics and practitioners of e-learning systems.