Database security is pertinent to every organisation with the onset of increased traffic over large networks especially the internet and increase in usage of cloud based transactions and interactions. Greater exposure...
详细信息
Database security is pertinent to every organisation with the onset of increased traffic over large networks especially the internet and increase in usage of cloud based transactions and interactions. Greater exposure of organisations to the cloud implies greater risks for the organisational as well as user data. In this paper, we propose a novel approach towards database intrusion detection systems (DIDS) based on expectation maximization clustering and Sequential Pattern Mining (EMSPM). This approach unlike any other does not have records and assumes a predetermined policy to be maintained in an organisational database and can operate seamlessly on databases that follow Role Based Access Control as well as on those which do not conform to any such access control and restrictions. This is achieved by focusing on pre-existing logs for the database and using the expectation maximization clustering algorithm to allot role profiles according to the database user's activities. These clusters and patterns are then processed into an algorithm that prevents generation of unwanted rules followed by prevention of malicious transactions. Assessment into the accuracy of EMSPM over sets of synthetically generated transactions yielded propitious results with accuracies over 93%.
The source codes of a software system are one of the most valuable resources in software development. A developer spends more time and money on development if they start coding from fresh for each similar functionalit...
详细信息
ISBN:
(纸本)9781665416344
The source codes of a software system are one of the most valuable resources in software development. A developer spends more time and money on development if they start coding from fresh for each similar functionality project. Topic modelling is crucial for software reuse since it can be difficult for developers to remove obsolete source code from large software systems with a lot of code. Topic modelling techniques has been used to evaluate and model source codes in several ways. Several studies on this domain have been used to extract topics from source codes using various statistical approaches and methodologies. These topic extraction methods are interconnected, and if software best practices aren't followed in older systems, it may ensue unreliability of the outcome. In response to these findings, the author conducted a study in which he extracted source code using a java parser library and predicted the source code functionality name using an unsupervised learning approach such as K-mean algorithm and expectationmaximization (EM) clustering approach. This is the first effort to develop a clustering model to predict the semantic function name of source code using an unsupervised learning approach and compare the algorithms to get the optimal model.
In recent days, elderly people living alone at home are steadily increasing throughout the world. This situation drives to develop a health care system for monitoring the health parameters of elderly people and help t...
详细信息
ISBN:
(纸本)9781479910243
In recent days, elderly people living alone at home are steadily increasing throughout the world. This situation drives to develop a health care system for monitoring the health parameters of elderly people and help them to lead ahealthy independent life. This paper presents a system that uses wireless sensors for monitoring the health parameters without disturbing the normal activities of elderly people. The proposed system provides a wearable health care solution using the wireless Shimmer sensor device for collecting ECG data in home PC. ECG data anomaly is detected using rule based classifier. Classification rules are generated based on cluster centroids obtained using a novel scheme named Hybrid expectationmaximization and Fuzzy C Means (HEMFCM) clustering. The proposed method is validated using real data collected from different subjects and abnormal data readings from the MIT BIR database. Experimental results show that proposed method achieves 85% classification accuracy which is better than EM and FCM clustering methods.
It is possible for a person to collect mobility trail in a form of positioning data set with portable devices or smart phones. From such set of mobility trail we can construct human mobility model. A mobility trail is...
详细信息
It is possible for a person to collect mobility trail in a form of positioning data set with portable devices or smart phones. From such set of mobility trail we can construct human mobility model. A mobility trail is usually classified as stay states and moving states. Stay states on a specific location can be clustered and be regarded as state of Markov chain. Of course, transition probabilities between stay states can also be calculated. We used expectation maximization clustering technique and constructed Continuous Time Markov Chains representing human mobility model. In addition, we found micro mobility also. Micro mobility is mobility in a restricted area and was represented as subclusters inside a cluster. The identification of micro cluster in small area will raise another topic in human mobility model research.
暂无评论