Fraudulent Firm Classification: A Case Study of an External Audit

This paper is a case study of visiting an external audit company to explore the usefulness of machine learning algorithms for improving the quality of an audit work. Annual data of 777 firms from 14 different sectors are collected. The Particle Swarm Optimization (PSO) algorithm is used as a feature selection method. Ten different state-of-the-art classification models are compared in terms of their accuracy, error rate, sensitivity, specificity, F measures, Mathew’s Correlation Coefficient (MCC), Type-I error, Type-II error, and Area Under the Curve (AUC) using Multi-Criteria Decision-Making methods like Simple Additive Weighting (SAW) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The results of Bayes Net and J48 demonstrate an accuracy of 93% for suspicious firm classification. With the appearance of tremendous growth of financial fraud cases, machine learning will play a big part in improving the quality of an audit field work in the future.     

Ontology based E-learning framework: A personalized,adaptive and context aware model

Multimedia Tools and Applications - Enhancing the degree of learner productivity, one of the major challenges in E-Learning systems, may be catered through effective personalization, adaptivity and...     

Polyaniline–13X zeolite composite‐supported platinum electrocatalysts for direct methanol fuel cell applications

We successfully synthesized 13X zeolite using a hydrothermal method. Then, composites of polyaniline (PANI) with 13X zeolite and PANI–13X with platinum were prepared by chemical oxidative polymerization and chemical reduction, respectively. Field emission scanning electron microscopy, X‐ray diffraction, Raman spectroscopy and Brunauer–Emmett–Teller techniques were used to characterize the PANI–Pt and PANI–Pt–13X composites. Further, the electrocatalytic activity towards methanol oxidation of the synthesized catalysts was explored using cyclic voltammetry in 1 mol L^?1 CH₃OH + 0.5 mol L^?1 H₂SO₄ solution. From the obtained results, PANI–Pt–13X shows superior performance compared to PANI–Pt towards methanol oxidation and electrical conductivity. Hence, the 13X zeolite‐incorporated PANI–Pt composite could be an efficient catalyst for direct methanol fuel cell applications. © 2019 Society of Chemical Industry     

Study on micro-patterning process of vertically aligned carbon nanotubes (VACNTs)

Vertically aligned carbon nanotubes (VACNTs) have drawn significant attention by the researchers because of their nanometric size and favorable material properties. Patterning of CNT forests in the micrometric domain is very important for their application in the area of microelectromechanical system (MEMS). For the first time this paper reports, detailed experimental investigation on a post growth μ-patterning process of VACNT forests. The micromechanical bending (M2B) process was locally applied at the targeted area in order to change the alignment of VACNT forests. Interestingly, the VACNT forest was transformed from typical black body absorber to reflective mirror as the M2B process was applied. Several parameters were identified that govern the resultant patterns such as rotational spindle speed, lateral bending speed, step size, tool morphology, and total depth of bend. Optimization of the parameters was carried out experimentally to obtain the best surface roughness and integrity of the microstructure. A minimum average surface roughness of Ra = 15 nm was achieved with 2000 rpm spindle speed, 1 mm/min bending speed and 1 µm step size.     

Relationship between physicochemical and functional properties of amaranth (Amaranthus hypochondriacus) protein isolates

Protein isolates from six amaranth lines/cultivars (APIs) were evaluated to study their physicochemical (hunter colour, protein content and zeta potential), structural (thermal and conformational) and functional (emulsification, foaming, water and fat absorption) properties. APIs had protein content, whiteness index and gel temperature in range of 79.4–85.4%, 41.17–54.26 and 87.8–91.8 °C, respectively. The Fourier‐transform infrared spectra of APIs revealed α‐helix, β‐sheets and random coil conformations in the secondary structure. APIs with higher relative proportion of β‐sheets had higher Differential Scanning Calorimeter denaturation temperature and gel temperature. Minimum protein solubility (PS) was observed at pH 5.0, indicating isoelectric point (pI) of amaranth proteins. The PS, emulsifying activity index (EAI), emulsifying stability index (ESI), foaming capacity (FC) and foam stability (FS) of APIs at neutral pH were related to their zeta potential (ζ). The emulsifying and foaming properties were also determined at different pHs (between 2.0 and 9.0). The EAI‐pH profile of APIs confirmed close relationship between the emulsifying ability and PS.