International Journal of Modern Education and Computer Science @ijmecs
Статьи журнала - International Journal of Modern Education and Computer Science
Все статьи: 1096
Credit risk prediction using artificial neural network algorithm
Статья научная
Artificial neural network is an information processing system which is influenced by the human brain and works on the same principles of the biological nervous system. They possess the ability to extract meaning from complex and intricate data, by detecting trends and extracting patterns from it. This paper illustrates the ability of neural network model and linear regression model constructed to predict the creditworthiness of an application accurately and precisely with minimal false predictions and errors. The results are shown to be similar for both the models, thus, models are efficient to use depending on the type of application and attributes.
Бесплатно
Criterion for Ranking Interval Alternatives in a Decision-Making Task
Статья научная
The study solves the problem of improving the methodological and algorithmic support of the decision-making process by developing a model of the preference criterion for interval evaluations of alternatives. The aim of the study is to improve the efficiency of decision-making based on interval expert data under conditions of uncertainty and risk by developing a criterion for the preferences of interval evaluations of overlapping alternatives. The object of the study is the decision-making process based on the classical efficiency matrix with interval elements, the subject is the model of decision maker's (DMP) preference criteria for interval evaluations of alternatives. The relevance of the task is stipulated by the urgency of the problem of adapting classical decision-making methods and models to practical problems of gray analysis, in particular, with interval uncertainty of primary expert data. A multifactorial model of the normalized preference criterion for interval evaluations of alternatives is proposed. Due to the additional consideration of the degree of preference of the DMP for the width of interval estimates, it allows ranking interval estimates of alternatives that overlap and are considered classically incomparable. A single analytical form of the normalized criterion model for ranking interval, weighted interval and point estimates makes it possible to increase the degree of automation of processing interval expert estimates in the decision-making process. Recommendations for the practical application of the proposed model are formulated. The developed model and corresponding algorithms can be used in automated expert decision support systems.
Бесплатно
Critical Analysis of Data Mining Techniques on Medical Data
Статья научная
The use of Data mining techniques on medical data is dramatically soar for determining helpful things which are used in decision making and identification. The most extensive data mining techniques which are used in healthcare domain are, classification, clustering, regression, association rule mining, classification and regression tree (CART). The suitable use of data mining algorithm can enhance the quality of prediction, diagnosis and disease classification. Valuation of data mining techniques demand for medical data mining is the major goal here, particularly to examine the local frequent disease like heart ailments, breast cancer, lung cancer and so on. We examine for discovering the locally frequent patterns through data mining technique in terms of cost performance speed and accuracy.
Бесплатно
Cross-domain recommendation model based on hybrid approach
Статья научная
The demand of recommendation has aroused severely since there are huge number of choices available and the end user desires to extract information in least time and with high accuracy. The traditional recommendation systems generate recommendations in the same domain but now cross domain recommendations are gaining importance. The cross domain recommendations address well the limitations of single domain analysis such as data sparsity and cold start problem. Under this research work cross domain recommendation model is designed based on the study of various supervised classification algorithms. 3 domains are under consideration music, movie and book. Model is capable of generating one to many cross domain recommendations exploiting movie domain knowledge to generate recommendations for books and music. Data is collected through survey and data pre-processing has been performed. Study is carried out over K-Nearest Neighbor, Decision Tree, Gaussian Naïve Bayes and Support Vector Machine classifiers and also over majority voting Ensembling, cross validation and data sampling by applying these classifiers to choose the best classifier to form the base of content-based recommendation. Recommendation model uses a hybrid approach of combination of content-based recommendation, user to user collaborative filtering and personalized recommendation techniques. The model perform Twitter sentiment analysis over the recommended entities generated by the model to help the user in decision making by knowing the positive, negative and neutral polarity percentage based on tweets done by people. The designed model achieved good accuracy on testing.
Бесплатно
Cuckoo Search Algorithm using Lèvy Flight: A Review
Статья научная
Cuckoo Search (CS) is a new metaheuristic algorithm. It is being used for solving optimization problem. It was developed in 2009 by Xin- She Yang and Suash Deb. Uniqueness of this algorithm is the obligatory brood parasitism behavior of some cuckoo species along with the Levy Flight behavior of some birds and fruit flies. Cuckoo Hashing to Modified CS have also been discussed in this paper. CS is also validated using some test functions. After that CS performance is compared with those of GAs and PSO. It has been shown that CS is superior with respect to GAs and PSO. At last, the effect of the experimental results are discussed and proposed for future research.
Бесплатно
DPS-AA: Intranet Migration Strategy Model for Clouds
Статья научная
Intranets & Intranet-wares have become a central junction/platform for implementing the organization’s specific work culture like computing, communication and collaboration. In order to ensure smooth and effective communication, computing and collaboration among employees, intranets play an important role. For vertical and horizontal management, we use intranet-wares for directing, reporting, collaborating, socializing, communicating and meeting or discussing the professional and social issues. Today, cloud-based computing, communication, and collaboration have created new frontiers and emerging paradigms towards re-engineering of work cultures in the organizations. In order to enhance the performance with extended features, next-generation computing, communication, and collaboration the intranet needs redesign and migration strategy over alternative technology platforms. This research paper tries to answer the research questions that how an alternative technology strategy or pathway can be explored for enhancing the performance and extending the features of the exiting designs of educational Intranets. Further; how an on-premise intranet can be migrated over cloud platforms with enhanced performance and extended/add-on features. After analysis of collected facts, understanding the issues, challenges and limitations of the existing state of art intranets, a strong need for performance enhancement and add on features was observed for Intranets. The study deeply investigated and analyzed the issues, challenges and limitations i.e. features and performances of the current state of the art of the intranets in general and on-premise Intranet of AMU in specific. Finally, an Intranet Migration Strategy Model over Hybrid Cloud was designed and developed using SaaS (i.e. AMU CloudNet). In this study, the Interact Intranet was used for designing and demonstrating the functional prototype of intranet show that how computing, communication and collaboration services can be enhanced with anytime, anywhere and boundary-less access.
Бесплатно
Dangerous Degree Evaluation System of Mine Debris Flow Based on IGA-BP
Статья научная
Taking the western Qinling Mountain, in the southern Shaanxi Province of china, as an example, based upon comprehensive analysis of geological data for 20 debris flow gullies, the author has put forward a series of indices system and has developed one evaluation system called “dangerous degree evaluation system of mine debris flow based on IGA-BP”. This system adopts Visual Basic 6.0 and Access technology to manage database, adopts immune genetic algorithm to optimize the hidden layer structure and network parameters of BP neural network and adopts sample model of mine debris flow whose dangerous degree has been known to realize the BP neural network evaluation of the debris flow risk which to be determined. The calculating results show that this evaluation method has high reliability and simplicity of operation, and it can make comprehensive evaluation precisely. The evaluation results have important guiding significance in the prevention and reduction mine debris flow.
Бесплатно
Data Clustering by Chaotic Oscillatory Neural Networks with Dipole Synaptic Connections
Статья научная
This article introduces a novel approach to data clustering based on the oscillatory chaotic neural network with dipole synaptic connections. The conducted research affirms that the proposed model effectively facilitates the formation of clusters of objects with similar properties due to the use of a slowly decreasing function of the dipole synaptic strength. The studies demonstrate that the degree of neuron synchronization in networks with dipole synaptic connections surpasses that in networks with Gaussian synaptic connections. The findings also indicate an increase in the interval of the resolution range in the model featuring dipole neurons, underscoring the effectiveness of the proposed method.
Бесплатно
Data Mining based Software Development Communication Pattern Discovery
Статья научная
Smaller time loss and smoother communication pattern is the urgent pursuit in the software development enterprise. However, communication is difficult to control and manage and demands on technical support, due to the uncertainty and complex structure of data appeared in communication. Data mining is a well established framework aiming at intelligently discovering knowledge and principles hidden in massive amounts of original data. Data mining technology together with shared repositories results in an intelligent way to analyze data of communication in software development environment. We propose a data mining based algorithm to tackle the problem, adopting a co-training styled algorithm to discover pattern in software development environment. Decision tree is trained as based learners and a majority voting procedure is then launched to determine labels of unlabeled data. Based learners are then trained again with newly labeled data and such iteration stops when a consistent state is reached. Our method is naturally semi-supervised which can improve generalization ability by making use of unlabeled data. Experimental results on data set gathered from productive environment indicate that the proposed algorithm is effective and outperforms traditional supervised algorithms.
Бесплатно
