Amin Karami

Bio: Amin Karami is an academic researcher from University of East London. The author has contributed to research in topics: Network packet & Cluster analysis. The author has an hindex of 11, co-authored 19 publications receiving 510 citations. Previous affiliations of Amin Karami include Polytechnic University of Catalonia & University of Skövde.

Choosing DBSCAN Parameters Automatically using Differential Evolution

Abstract: Over the last several years, DBSCAN (Density-Based Spatial Clustering of Applications with Noise) has been widely applied in many areas of science due to its simplicity, robustness against noise (outlier) and ability to discover clusters of arbitrary shapes. However, DBSCAN algorithm requires two initial input parameters, namely Eps (the radius of the cluster) and MinPts (the minimum data objects required inside the cluster) which both have a significant influence on the clustering results. Hence, DBSCAN is sensitive to its input parameters and it is hard to determine them a priori. This paper presents an efficient and effective hybrid clustering method, named BDE-DBSCAN, that combines Binary Differential Evolution and DBSCAN algorithm to simultaneously quickly and automatically specify appropriate parameter values for Eps and MinPts. Since the Eps parameter can largely degrades the efficiency of the DBSCAN algorithm, the combination of an analytical way for estimating Eps and Tournament Selection (TS) method is also employed. Experimental results indicate the proposed method is precise in determining appropriate input parameters of DBSCAN algorithm.

Stock market prediction using machine learning classifiers and social media, news

Abstract: Accurate stock market prediction is of great interest to investors; however, stock markets are driven by volatile factors such as microblogs and news that make it hard to predict stock market index based on merely the historical data. The enormous stock market volatility emphasizes the need to effectively assess the role of external factors in stock prediction. Stock markets can be predicted using machine learning algorithms on information contained in social media and financial news, as this data can change investors’ behavior. In this paper, we use algorithms on social media and financial news data to discover the impact of this data on stock market prediction accuracy for ten subsequent days. For improving performance and quality of predictions, feature selection and spam tweets reduction are performed on the data sets. Moreover, we perform experiments to find such stock markets that are difficult to predict and those that are more influenced by social media and financial news. We compare results of different algorithms to find a consistent classifier. Finally, for achieving maximum prediction accuracy, deep learning is used and some classifiers are ensembled. Our experimental results show that highest prediction accuracies of 80.53% and 75.16% are achieved using social media and financial news, respectively. We also show that New York and Red Hat stock markets are hard to predict, New York and IBM stocks are more influenced by social media, while London and Microsoft stocks by financial news. Random forest classifier is found to be consistent and highest accuracy of 83.22% is achieved by its ensemble.

An Anomaly-based Intrusion Detection System in Presence of Benign Outliers with Visualization Capabilities

Abstract: Abnormal network traffic analysis through Intrusion Detection Systems (IDSs) and visualization techniques has considerably become an important research topic to protect computer networks from intruders. It has been still challenging to design an accurate and a robust IDS with visualization capabilities to discover security threats due to the high volume of network traffic. This research work introduces and describes a novel anomaly-based intrusion detection system in presence of long-range independence data called benign outliers, using a neural projection architecture by a modified Self-Organizing Map (SOM) to not only detect attacks and anomalies accurately, but also provide visualized information and insights to end users. The proposed approach enables better analysis by merging the large amount of network traffic into an easy-to-understand 2D format and a simple user interaction. To show the performance and validate the proposed visualization-based IDS, it has been trained and tested over synthetic and real benchmarking datasets (NSL-KDD, UNSW-NB15, AAGM and VPN-nonVPN) that are widely applied in this domain. The results of the conducted experimental study confirm the advantages and effectiveness of the proposed approach.

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Abstract: Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.