Knowledge discovery using neural approach for SME’s credit risk analysis problem in Turkey

This study proposes a knowledge discovery method that uses multilayer perceptron (MLP) based neural rule extraction (NRE) approach for credit risk analysis (CRA) of real-life small and medium enterprises (SMEs) in Turkey. A feature selection and extraction stage is followed by neural classification that produces accurate rule sets. In the first stage, the feature selection is achieved by decision tree (DT), recursive feature extraction with support vector machines (RFE-SVM) methods and the feature extraction is performed by factor analysis (FA), principal component analysis (PCA) methods. It is observed that the RFE-SVM approach gave the best result in terms of classification accuracy and minimal input dimension. Among various classifiers k-NN, MLP and SVM are compared in classification experiments. Then, the Continuous/Discrete Rule Extractor via Decision Tree Induction (CRED) algorithm is used to extract rules from the hidden units of a MLP for knowledge discovery. Here, the MLP makes a decision for customers as being “good” or “bad” and reveals the rules obtained at the final decision. In the experiments, Turkish SME database has 512 samples. The proposed approach validates the claim that is a viable alternative to other methods for knowledge discovery.     

Performance, interdependence and coordination in business‐to‐business electronic commerce and supply chain management

After discovering the inadequacy of traditional relationships across the value‐chain, many organizations today are establishing new forms of interorganizational systems with their suppliers and customers in an effort to improve total channel performance. Electronic commerce linkages are being created between independent organizations in multiple industries, including manufacturing, financial services, transportation, and retailing. Efforts to improve channel efficiency using business‐to‐business electronic commerce systems generally require increased interdependence and expanded coordination between independent firms to capture the potential benefits enabled by tighter interorganizational integration of operations. Participating firms can gain dramatic benefits from establishing electronic linkage only when the system is used to increase interdependence and to expand coordination between firms involved in the new interorganizational relationship. Drawing on theoretical and empirical research on electronic communications and inter‐firm designs, we develop and test a model for the relationship between performance, interdependence and coordination of firms involved in interorganizational relations within the US grocery channel. The research design includes qualitative case study analysis and quantitative survey data analysis to validate the key case study findings. Both qualitative and quantitative findings indicate that channel performance, interdependence, and coordination are closely related for firms in interorganizational relationships. This revised version was published online in July 2006 with corrections to the Cover Date.     

Effects of gender grouping on students’ group performance,individual achievements and attitudes in computer-supported collaborative learning

The purpose of this study was to examine the effects of gender grouping on students’ group performance, individual learning achievements and attitudes in computer-supported collaborative learning (CSCL). 588 undergraduate students enrolled in a digital design course were randomly divided into 147 four-student groups that fell into five categories according to the composition of group members’ gender, namely 4M (four males), 3M1F (three males and one female), 2M2F (two males and two females), 1M3F (one male and three females) and 4F (four females). Results indicated that: (1) For group performance, 2M2F and 4F groups significantly outperformed the other groups. (2) For individual learning achievements, no significant difference was found in females among different gender grouping interventions; however, males in mixed-gender groups performed significantly better than those in single-gender groups. (3) In terms of individual attitudes, males preferred mixed-gender, gender-balanced, and gender-majority grouping; however, females preferred single-gender and gender-minority grouping. (4) The effect of gender grouping mainly influences students’ attitudes, rather than performance. These findings provide evidence that female-only and balanced-gender grouping are two kinds of good grouping interventions that could be recommended for CSCL, and male-minority groups should be avoided because they led to the worst group performance and individual attitudes.     

Sense’s standards and machine understanding of texts in the system for computer-aided testing of knowledge

This paper proposes an approach to interpreting a response an answer to a test task of an open form in a system for computer-aided testing of knowledge. The notion of a sense’s standard is introduced; and the method for building it based on the set of semantic equivalent phrases of natural language and use of sense’s standards for compression of a textual knowledge base are described.     

Capturing the symptoms of malicious code in electronic documents by file’s entropy signal combined with machine learning

Email cyber-attacks based on malicious documents have become popular techniques in today’s sophisticated attacks. Persistent efforts have been made to detect such attacks, but there are still some common defects in the existing methods, including the inability to capture unknown attacks, high overhead of resource and time, and only can be used to detect specific formats of documents. This study proposes a new method named Entropy Signal Reflects the Malicious Document (ESRMD), which can identify malicious documents based on the entropy distribution of the file. ESRMD is a machine learning classifier, which differ from the traditional approaches in that ESRMD extracts both global and structural entropy features from the entropy sequence, enduring it the ability to deal with various formats documents and fight against the parser-confusion and obfuscated attacks. To assess the validity of the proposed model, we conducted extensive experiments on a collected dataset which contains 10,381 samples, including malware (51.47%) and benign (48.53%) samples. Through extensive experiments, ESRMD showed its superiority comparing with some leading anti-virus engines and prevalent tools, achieving good performance on the true positive rate and ROC with the value of 96.00% and 99.2% respectively.     

An integrated application of Kano’s model and AHP to Korean online open market services

With the advancement in wireless and mobile technologies, online open markets decrease intermediate distribution margins and play the key intermediary role between sellers and consumers. While offline store sales remain stagnant, online open market sales have been growing steadily. We investigated the service quality of Korean online open market providers such as “Gmarket”, “Auction”, and “11st”, based on an integrated application of Kano’s model and the Analytic Hierarchy Process (AHP). The contributions of this study are as follows: (1) We conducted acritical review of previous literature to develop each analysis method. (2) We categorized the service quality factors of the Korean open market using Kano’s model and identified the most important service quality factor by AHP analysis. (3) Then, we conducted a comparison between the results from the Kano model and AHP analysis. (4) Lastly, based on the results of the integrated application of both Kano model and AHP analysis, this study provided specific implications for improving the service quality of the online open market in Korea.     

How to find people who can help to answer a question? – Analyses of metrics and machine learning in online communities

Online communities have become important places for users to exchange information and build knowledge. In these communities, people ask and answer questions, learn with each other, but some problems may occur such as not getting an answer or getting contradictory ones. In order to increase the responsiveness of the communities, it would be important to identify people who are willing to help and who provide good answers in such communities, whom we call reliable users. We investigated various components of online communities and users’ attributes looking for a correlation between these characteristics and the users’ reputation in these communities. After that, we proposed the usage of two machine learning techniques, artificial neural network and clustering algorithm, with the users’ attributes for finding reliable sources. The results show that the usage of an artificial neural network is a good approach as around 90% of the users were correctly identified while the clustering algorithm makes to find groups of reliable users more easily.     

Satellite-based detection of water surface variation in China’s largest freshwater lake in response to hydro-climatic drought

Poyang Lake, the largest freshwater lake in China, is an important water resource and iconic ecosystem in a region that has been subjected to extreme drought in recent years. The lake’s inundation area is heavily influenced by basin rainfall and also by the Yangtze River’s water flows. Exploring the lake’s inundation variation in response to drought conditions is of great importance for developing effective management planning for local water resources and for mitigating future drought. Here we demonstrate how satellites can reflect the lake’s inundation changes and processes under typical hydro-climatic droughts. Using Moderate Resolution Imaging Spectroradiometer (MODIS) medium-resolution data collected between 2000 and 2011, we documented the tempo-spatial variation characteristics of water inundation areas and two typical droughts in 2006 and 2011. 2006 was a hydrologic drought year, which occurred due to an abnormal change in the Yangtze River’s water flows. A dramatic shrinkage of the inundation area mainly occurred in autumn and winter. In contrast, 2011 was a hydro-climatic drought year, which resulted from the complicated influence of both the Poyang Lake basin and Yangtze River. The lake shrinkage appeared more severe during spring–summer, when about 70% of the inundation area disappeared before July. The results should be valuable for ecological conservation and water resource management in the Poyang Lake region.     

Effects of mental process integrated nursing training using mobile device on students’ cognitive load,learning attitudes,acceptance, and achievements

Clinical nursing training is important to nursing educators and student nurses in nursing education since safe and competent care depends on good clinical problem solving skills. Therefore, developing better cognitive problem-solving strategies or tools are essential for clinical nursing practices. Moreover, learning diagnosis is also a critical determinant in the acquisition, processing, and application of clinical skills in nursing practices. Bearing this in mind, this study aims to develop a mobile interactive learning and diagnosis (MILD) system to support problem-based learning (PBL) in a clinical nursing course based on the testing-based approach. Using mobile devices as a learning tool to integrate both real-world and digital-world resources for students and adopting PBL as a learning strategy to facilitate the development of the clinical problem solving skills. To show the effectiveness of the proposed approach, an experiment was conducted in a foundations of nursing course at a nursing college in Taiwan. The experimental results show that the proposed approach is helpful to students in improving learning performance and reducing cognitive loads. Moreover, it was also found that most students showed positive perceptions toward the usage of the proposed system.     

The impact of mobility,risk, and cost on the users’ intention to adopt mobile payments

Information Systems and e-Business Management - With the development of mobile communication technology and the wide application of intelligent devices, mobile payments with great commercial...     

Utilizing transfer learning of pre-trained AlexNet and relevance vector machine for regression for predicting healthy older adult’s brain age from structural MRI

Multimedia Tools and Applications - Discrepancies between the estimated brain age from brain structural MRI and the chronological age have been associated with a broad spectrum of neurocognitive...     

Analysis over factors of innovation in China’s fast economic growth since its beginning of reform and opening up

The technological progress makes great contribution to the rapid economic growth of China during its past three decades of reform and opening up. An empirical analysis conducted over China’s total factor productivity certifies this conclusion but it also reveals that China’s TFP growth rate is not very high. We further explore the various stages of change of China’s total factor productivity and the causes of these changes and finally take an analytical calculation over the present flaws of China’s innovation system and offer some advices.     

Eliminating bias due to censoring in Kendall’s tau estimators for quasi-independence of truncation and failure

While the currently available estimators for the conditional Kendall’s tau measure of association between truncation and failure are valid for testing the null hypothesis of quasi-independence, they are biased when the null does not hold. This is because they converge to quantities that depend on the censoring distribution. The magnitude of the bias relative to the theoretical Kendall’s tau measure of association between truncation and failure due to censoring has not been studied, and so its importance in real problems is not known. We quantify this bias in order to assess the practical usefulness of the estimators. Furthermore, we propose inverse probability weighted versions of the conditional Kendall’s tau estimators to remove the effects of censoring and provide asymptotic results for the estimators. In simulations, we demonstrate the decrease in bias achieved by these inverse probability weighted estimators. We apply the estimators to the Channing House data set and an AIDS incubation data set.     

Comparison of templates for homology model of ρ1 GABAC receptors: More insights to the orthosteric binding site’s structure and functionality

Five sets of ρ1 GABA_C homology models were generated based on X-ray crystal structures of the acetylcholine binding protein (AChBP), the ion channel from Caenorhabditis elegans (GLIC), the ion channel from Erwinia chrysanthemi (ELIC), the homomeric GABA_A β₃ ion channel, and the homomeric α-subunit of glutamate-gated homopentameric chloride channel (GluCl). The GluCl based model was found to the represent the structure of ρ1 GABA_C receptors. The GABA pose docked in the selected best model was confirmed by QM-polarized ligand docking and induced fit docking protocol, and used to study molecular interactions in the ρ1 GABA binding site. The potential interactions of identified residues are discussed. This study identified several residues with potential ligand interactions located on loops F and G with their side chain oriented toward the binding site such as Ser215 and Gln83. The partial agonists muscimol and imidazole-4-acetic acid (I4AA) were docked into the binding site of the most reliable ‘GABA bound’ homology model. The potency and efficacy of these partial agonists in activating recombinant ρ1 receptors were correlated with their docking results. The model predicts that muscimol resembles GABA in the docking pose with similar interactions. However, I4AA has a very different docking pose to GABA and was predicted by the model to form π–π stacking with aromatic residues in the orthosteric binding site. A set of TPMPA bound ρ1 homology models based on the GluClα ‘apo state’ template was built in order to study a competitive antagonist in the ρ1 orthosteric binding site. The results demonstrated the ability of our model to explain most experimental findings and predict potential roles of residues within the orthosteric binding site.     

Robust design of (s,S) inventory policy parameters in supply chains with demand and lead time uncertainties

Demand and lead time uncertainties have significant effects on supply chain behaviour. In this paper, we present a single-product three-level multi-period supply chain with uncertain demands and lead times by using robust techniques to study the managerial insights of the supply chain inventory system under uncertainty. We formulate this problem as a robust mixed-integer linear program with minimised expected cost and total cost variation to determine the optimal (s, S) values of the inventory parameters. Several numerical studies are performed to investigate the supply chain behaviour. Useful guidelines for the design of a robust supply chain are also provided. Results show that the order variance and the expected cost in a supply chain significantly increase when the manufacturer’s review period is an integer ratio of the distributor’s and the retailer’s review periods.     

A switched optimal control approach to reduce transferring time,energy consumption,and residual vibration of payload’s skew rotation in crane systems

In this paper, nonlinear optimal control schemes are proposed to reduce transferring time, energy consumption, and residual vibration for the payload’s skew rotation process of crane systems. The main contribution of this paper is to reduce the energy consumption without trading-off the sub-optimal transferring time. The novel idea is to use an electro-mechanical clutch to intelligently disengage the connection between the motor and the payload during the motion such that the payload can continue rotating only by its own momentum. As a result, a switched optimal control problem must be realized. Two solutions, namely particular and general schemes are proposed in the paper, where physical constraints of the actuator including bounded velocity and bounded acceleration are explicitly taken into account. Both simulation and experimental results are provided to prove the effectiveness of the proposed optimal control systems. The established schemes can be directly applied to transfer the payload to a desirable skew orientation without any residual oscillation, or can be utilized as a sub-optimal-time reference trajectory planner of the skewing control module in either overhead or rotary crane systems. Furthermore, the hybrid rotation process presented in this paper, which is driven by the engaging/disengaging event of the clutch, can be served as a theoretical benchmark for any newly established switched optimal control method.     

Murray’s law and the bifurcation angle in the arterial micro-circulation system and their application to the design of microfluidics

Murray’s law which is related to the bifurcations of vascular blood vessels states that the cube of a parent vessel’s diameter equals the sum of the cubes of the daughter vessels’ diameters D₀³ = D₁³ + D₂³ , a = D₀³ /( D₁³ + D₂³ ) = 1, D_{0}^{3} = D_{1}^{3} + D_{2}^{3} ,,alpha = D_{0}^{3} /left( {D_{1}^{3} + D_{2}^{3} } right) = 1, where D ₀, D ₁, and D ₂ are the diameters of the parent and two daughter vessels, respectively and α is the ratio). The structural characteristics of the vessels are crucial in the development of the cardiovascular system as well as for the proper functioning of an organism. In order to understand the vascular circulation system, it is essential to understand the design rules or scaling laws of the system under a homeostatic condition. In this study, Murray’s law in the extraembryonic arterial bifurcations and its relationship with the bifurcation angle (θ) using 3-day-old chicken embryos in vivo has been investigated. Bifurcation is an important geometric factor in biological systems, having a significant influence on the circulation in the vascular system. Parameters such as diameter and bifurcation angle of all the 140 vessels tested were measured using image analysis softwares. The experimental results for α (= 1.053 ± 0.188) showed a good agreement with the ratio of 1 for Murray’s law. Furthermore, the diameter relation α approached the theoretical value of 1 as the diameter of parent vessel D ₀ decreased below 100 μm. The bifurcation angle θ decreased as D ₀ increased and vice versa. For the arterial bifurcations of chicken embryos tested in this study, the bifurcation pattern appears to be symmetric (D ₁ = D ₂). The bifurcation angle exhibited a nearly constant value of 77°, close to the theoretical value of 75° for a symmetric bifurcation.