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. 相似文献
The weighted additivity corresponding to additivity plays a very important role in study of useful information. By using the sum property, the equation satisfied by weighted additivity has been converted to a functional equation, which is further generalized in two ways. The real and continuous solutions of the generalized functional equations have been obtained. In terms of these real and continuous solutions, two new generalized measures of useful information have been characterized and their particular cases have been studied. Some bounds and comparison results have also been obtained. 相似文献
The introduction of automobile catalysts has raised environmental concern, as this pollution control technology is also an emission source for the platinum group elements (PGE). The main aim of this study was to assess the concentrations of Pt, Pd, Rh and Au in soil and grass herbage collected adjacent to 5 roads. Soil and grass samples were collected from 4 fixed distances (0, 1, 2 and 5 m) from the road edge at each site. PGE and Au were determined by ICP-MS in all samples after acid digestion. The maximum soil Pt, Rh and Pd concentrations were measured at the road perimeters. Averaged across the sites, the Pt and Rh concentrations of 15.9+/-7.5 microg Pt kg(-1) and 22.40+/-4.73 microg Rh kg(-1) at 0-m distance decreased to 2.04+/-1.7 microg Pt kg(-1) and 3.51+/-1.96 microg Rh kg(-1), respectively at 5-m away from the roads. Pd concentrations were much higher than Pt or Rh, ranging from 120.8+/-12.0 microg Pd kg(-1) (0-m) to 84.2+/-10.9 microg Pd kg(-1) (5-m), possibly due to differences in its use, emission and/or soil chemistry. Au showed little or no change with distance from the roads. However, the average Au concentration of 18.98+/-0.98 microg Au kg(-1) provides clear evidence of some input possibly due to attrition of automobile electronics. No straightforward influence of traffic flow rates on PGE distribution was found. A combination of dispersal impeding local features and slow moving and stop-and-start traffic conditions or fast moving traffic with flat open spaces may have offset the expected impacts. Rh and Pt soil concentration accounted for 66% and 34% (P<0.01) of the variability observed, respectively in their plant concentrations. Grass Pd and Au concentrations had no relationship with their respective soil concentrations. 相似文献
Multimedia Tools and Applications - Tuberculosis (TB) is an infectious disease that mainly affects the lung region. Its initial screening is mostly performed using chest radiograph, which is also... 相似文献
Journal of Materials Science: Materials in Electronics - The octa-coordinated complexes of Sm(III) with β-diketone and nitrogen-heterocyclic bidentate auxiliary moiety were prepared and... 相似文献
Wireless Personal Communications - Automatic analysis of chest radiographs using computer-aided diagnosis (CAD) systems is pivotal to perform mass screening and detect early signs of various... 相似文献
Pulmonary tuberculosis (PTB) is a contagious disease that affects the lung region. PTB is a life-threatening disease if it is detected late or left untreated. To perform the initial screening of PTB, the World Health Organization has recommended chest radiograph. Till now, the screening process requires either the patients to come to secondary health centers from rural areas or the radiologists to go the remote locations. This process is rejuvenated with the introduction of computer-aided diagnosis (CAD) systems. CAD systems reduce the need for expert radiologists in the screening process. However, the development and deployment are still in the early phases as new methods are being developed to improve the performance of CAD systems in terms of accuracy, specificity and sensitivity. In this study, a deep learning-based PTB classification system has been presented that achieves the state-of-the-art performance for TB classification. Firstly, a proposed architecture based on the blocks is presented and then it is used to create an ensemble. In the proposed ensemble, two standard architectures namely AlexNet, and ResNet have also been used in addition to the proposed architecture. All the architectures are trained and evaluated on a combined dataset formed using publicly available standard datasets. The proposed ensemble attains the accuracy of 90.00% and area under the curve equal to 0.96, which is better than the performance of the existing methods.