Byeong Ho Kang

Investigation and improvement of multi-layer perceptron neural networks for credit scoring

We present an Average Random Choosing method which increases 0.04 classification accuracy.Investigate different MLP models and get the best model with accuracy of 87%.Accuracy increases when the model has more hidden neurons. Multi-Layer Perceptron (MLP) neural networks are widely used in automatic credit scoring systems with high accuracy and efficiency. This paper presents a higher accuracy credit scoring model based on MLP neural networks that have been trained with the back propagation algorithm. Our work focuses on enhancing credit scoring models in three aspects: (i) to optimise the data distribution in datasets using a new method called Average Random Choosing; (ii) to compare effects of training-validation-test instance numbers; and (iii) to find the most suitable number of hidden units. We trained 34 models 20 times with different initial weights and training instances. Each model has 6 to 39 hidden units with one hidden layer. Using the well-known German credit dataset we provide test results and a comparison between models, and we get a model with a classification accuracy of 87%, which is higher by 5% than the best result reported in the relevant literature of recent years. We have also proved that our optimisation of dataset structure can increase a models accuracy significantly in comparison with traditional methods. Finally, we summarise the tendency of scoring accuracy of models when the number of hidden units increases. The results of this work can be applied not only to credit scoring, but also to other MLP neural network applications, especially when the distribution of instances in a dataset is imbalanced.

Verification and validation with ripple-down rules

Abstract Verification to ensure a system s consistency and validation to meet the user s criteria are essential elements in developing knowledge-based systems for real world use. The normal practice is that there will be initial knowledge acquisition attempting to build a complete system which will (should) then be verified and validated. There may be a cycle through these steps till the system is complete. Maintenance is seen as a minor problem requiring the occasional repetition of the three stage process. The implicit assumption is that an expert has complete knowledge and that by a suitable knowledge acquisition process this is acquired. In fact, it seems rather than experts are incapable of recounting how they reach a conclusion. Rather, when asked a question they justify that their conclusion is correct and their justification is tailored to the specific context of the inquiry. Experts are best at justifying why one conclusion is to be preferred over another. This leads to a knowledge acquisition methodology, Ripple-down Rules, in which the knowledge base undergoes on-going development based on correcting errors. Each new correction or justification is considered only in the context of the same mistake being made. The method also constrains the expert s choices to ensure that any new knowledge added is valid while the knowledge base structure ensures the knowledge is verified. Verification and validation are not separate tasks, but constraints on knowledge acquisition which itself continues throughout the life of the system. This provides a closer match with the normal evolution of human knowledge and expertise. The overall approach has itself been validated by the development of a large medical expert system and through simulation studies. The medical system has been developed while in routine use and has only involved experts without any knowledge engineering support or skill in its development.

Development of an intelligent decision support system for medication review.

Background and objective:  The aim was to develop and evaluate a pilot version of a knowledge‐based system that can identify existing and potential medication‐related problems from patient information. This intelligent system could directly support pharmacists and other health professionals providing medication reviews.

Health Fog: a novel framework for health and wellness applications

In the past few years the role of e-health applications has taken a remarkable lead in terms of services and features inviting millions of people with higher motivation and confidence to achieve a healthier lifestyle. Induction of smart gadgetries, people lifestyle equipped with wearables, and development of IoT has revitalized the feature scale of these applications. The landscape of health applications encountering big data need to be replotted on cloud instead of solely relying on limited storage and computational resources of handheld devices. With this transformation, the outcome from certain health applications is significant where precise, user-centric, and personalized recommendations mimic like a personal care-giver round the clock. To maximize the services spectrum from these applications over cloud, certain challenges like data privacy and communication cost need serious attention. Following the existing trend together with an ambition to promote and assist users with healthy lifestyle we propose a framework of Health Fog where Fog computing is used as an intermediary layer between the cloud and end users. The design feature of Health Fog successfully reduces the extra communication cost that is usually found high in similar systems. For enhanced and flexible control of data privacy and security, we also introduce the cloud access security broker (CASB) as an integral component of Health Fog where certain polices can be implemented accordingly. The modular framework design of Health Fog is capable of engaging data from multiple resources together with adequate level of security and privacy using existing cryptographic primitives.

Knowledge Management and Acquisition for Smart Systems and Services

The last decade has seen an increasing interest in the use of 3D virtual environments for educational applications. However, very few studies investigated the influence of the learning context, such as class type and learning type, on learners’ academic performance. This paper studied the impact of class type (i.e. comprehensive or selective) classes, as well as learning type (i.e. guided or challenge and guided), on students’ level of usage of a Virtual Learning Environment (VLE) as well as on their academic performance. The results showed that, unlike class type, there is a significant difference between learners’ in their usage of the VLE. Moreover, the results showed that the levels of using a VLE significantly correlated with learners’ academic performance.

Adaptive Web document classification with MCRDR

With the explosive increase in Web based information, the need for an intelligent agent for automatic classification has also been increased resulting in many research discoveries in this area. Machine learning (ML) based document classification is now the prevalent approach. However, classification by ML may not keep the same performance because the knowledge generated from the training set may not be appropriate for certain types of Web information. People are often concerned more about the newly uploaded information such as Web based online news than information already available. This explains why it is not widely used in real applications. However, the manual classification method, by the domain users, cannot be a solution either until the knowledge acquisition bottleneck issue is resolved. Multiple classification ripple down rules, an incremental knowledge acquisition method, is suggested to overcome this problem with fast learning and low cost maintenance.

The Mining Minds digital health and wellness framework

BackgroundThe provision of health and wellness care is undergoing an enormous transformation. A key element of this revolution consists in prioritizing prevention and proactivity based on the analysis of people’s conducts and the empowerment of individuals in their self-management. Digital technologies are unquestionably destined to be the main engine of this change, with an increasing number of domain-specific applications and devices commercialized every year; however, there is an apparent lack of frameworks capable of orchestrating and intelligently leveraging, all the data, information and knowledge generated through these systems.MethodsThis work presents Mining Minds, a novel framework that builds on the core ideas of the digital health and wellness paradigms to enable the provision of personalized support. Mining Minds embraces some of the most prominent digital technologies, ranging from Big Data and Cloud Computing to Wearables and Internet of Things, as well as modern concepts and methods, such as context-awareness, knowledge bases or analytics, to holistically and continuously investigate on people’s lifestyles and provide a variety of smart coaching and support services.ResultsThis paper comprehensively describes the efficient and rational combination and interoperation of these technologies and methods through Mining Minds, while meeting the essential requirements posed by a framework for personalized health and wellness support. Moreover, this work presents a realization of the key architectural components of Mining Minds, as well as various exemplary user applications and expert tools to illustrate some of the potential services supported by the proposed framework.ConclusionsMining Minds constitutes an innovative holistic means to inspect human behavior and provide personalized health and wellness support. The principles behind this framework uncover new research ideas and may serve as a reference for similar initiatives.

A Maintenance Approach to Case-Based Reasoning

The motivation for CBR is that knowledge comes mainly from experience, from dealing with cases. The goal of CBR is not to find knowledge in the knowledge base that applies to the present problem, but to find a case similar to the current case in a database of cases. This paper describes a methodology, ripple down rules (RDR), which allows a CBR system to be built without either induction or knowledge engineering and is well suited to maintenance. In essence, when the system fails to find the proper case to match with the present problem case, it asks the expert to identify the important features which differentiate the incorrectly retrieved case and the problem case. The problem case is added to the database and is indexed to be retrieved using the identified features only after the same incorrectly retrieved case is reached. This simple approach allows large systems to be easily built by unaided experts. RDR has been used for a large medical expert system (PEIRS) which is in routine use in a major teaching hospitals chemical pathology laboratory, providing clinical interpretations of data for diagnostic reports. PEIRS uses 2000 cases(rules), covers 20% of chemical pathology and is 95% accurate to date. It was built by pathologists without knowledge engineering assistance or skills.

Multimodal hybrid reasoning methodology for personalized wellbeing services

A wellness system provides wellbeing recommendations to support experts in promoting a healthier lifestyle and inducing individuals to adopt healthy habits. Adopting physical activity effectively promotes a healthier lifestyle. A physical activity recommendation system assists users to adopt daily routines to form a best practice of life by involving themselves in healthy physical activities. Traditional physical activity recommendation systems focus on general recommendations applicable to a community of users rather than specific individuals. These recommendations are general in nature and are fit for the community at a certain level, but they are not relevant to every individual based on specific requirements and personal interests. To cover this aspect, we propose a multimodal hybrid reasoning methodology (HRM) that generates personalized physical activity recommendations according to the user׳s specific needs and personal interests. The methodology integrates the rule-based reasoning (RBR), case-based reasoning (CBR), and preference-based reasoning (PBR) approaches in a linear combination that enables personalization of recommendations. RBR uses explicit knowledge rules from physical activity guidelines, CBR uses implicit knowledge from experts׳ past experiences, and PBR uses users׳ personal interests and preferences. To validate the methodology, a weight management scenario is considered and experimented with. The RBR part of the methodology generates goal, weight status, and plan recommendations, the CBR part suggests the top three relevant physical activities for executing the recommended plan, and the PBR part filters out irrelevant recommendations from the suggested ones using the user׳s personal preferences and interests. To evaluate the methodology, a baseline-RBR system is developed, which is improved first using ranged rules and ultimately using a hybrid-CBR. A comparison of the results of these systems shows that hybrid-CBR outperforms the modified-RBR and baseline-RBR systems. Hybrid-CBR yields a 0.94% recall, a 0.97% precision, a 0.95% f-score, and low Type I and Type II errors.

Dynamic Web content filtering based on user's knowledge

This paper focuses on the development of a maintainable information filtering system. The simple and efficient solution to this problem is to block the Web sites by URL, including IP address. However, it is not efficient for unknown Web sites and it is difficult to obtain complete block list. Content based filtering is suggested to overcome this problem as an additional strategy of URL filtering. The manual rule based method is widely applied in current content filtering systems, but they overlook the knowledge acquisition bottleneck problems. To solve this problem, we employed the multiple classification ripple-down rules (MCRDR) knowledge acquisition method, which allows the domain expert to maintain the knowledge base without the help of knowledge engineers. Throughout this study, we prove the MCRDR based information filtering system can easily prevent unknown Web information from being delivered and easily maintain the knowledge base for the filtering system.