Search

This article proposes the modified KNN (K Nearest Neighbor) algorithm which receives a string vector as its input data and is applied to the text summarization. The results from applying the string vector based algorithms to the text categorizations were successful in previous works and the text summarization is able to be viewed into a binary classification where each paragraph is classified into summary or non-summary. In the proposed system, a text which is given as the input is partitioned into a list of paragraphs, each paragraph is classified by the proposed KNN version, and the paragraphs which are classified into summary are extracted ad the output. The proposed KNN version is empirically validated as the better approach in deciding whether each paragraph is essential or not in news articles and opinions. We need to define and characterize mathematically more operations on string vectors for modifying more advanced machine learning algorithms. [ABSTRACT FROM AUTHOR]

This article proposes the modified AHC (Agglomerative Hierarchical Clustering) algorithm which considers the feature similarity and is applied to the text clustering. The words which are given as features for encoding texts into numerical vectors are semantic related entities, rather than independent ones, and the synergy effect between the word clustering and the text clustering is expected by combining both of them with each other. In this research, we define the similarity metric between numerical vectors considering the feature similarity, and modify the AHC algorithm by adopting the proposed similarity metric as the approach to the text clustering. The proposed AHC algorithm is empirically validated as the better approach in clustering texts in news articles and opinions. The significance of this research is to improve the clustering performance by utilizing the feature similarities. [ABSTRACT FROM AUTHOR]

Malware detection have long become a challenge in research. The existing methods rely on malware signature which are proved not to be effective nowadays. The recent researches focus on using probabilistic model such as machine learning to detect the existence of malware. They, however, do not achieve such a good performance. Particularly, machine learning techniques still have an issue of high feature engineering overhead. In this paper, we propose a deep learning method to detect malware based on their malicious behavior. Through experimentation, we show that our method can achieve a very high accuracy rate of 98.75 in F1 measure, compared to state of the art methods. [ABSTRACT FROM AUTHOR]

In this study, we classified emotional responses of a user by measuring the physiological response signals with the Emotion Collector, which is a wearable band equipped with a multi-sensor device. We collected physiological signal data to measure the delicate hand movements, heart rate, and skin tension of the user analysis with a focus on picking out fear among the user's emotions. In experiments classifying fear factors into five categories, we were able to identify the characteristics of the user's physiological responses according to the type of fear. We were also able to find the similarities and differences of physiological and psychological results for fear. The Emotion Collector is very easy to use, robust, and suitable for mobile and long-time logging of data. It can easily be integrated into other systems or applications. The system is designed for use in emotion research as well as in everyday affective applications such as user-centered service and content. [ABSTRACT FROM AUTHOR]

Software Defined Networking (SDN) is an emerging paradigm, which brings the network innovation and attracts both the industries and researchers. SDN is a programmable network model that separates the control logic from the forwarding plane. The centralize control plane takes care of all networking resources. The attackers target the SDN controller, to paralyze the logic plane that is considered as the brain of the network which provides a lot of benefits. However, due to the characteristics the control plane becomes the attractive target of security attacks for the adversaries. One of the most known threats is Distributed Denial-of-Service (DDoS) attacks with the goal to exhausting network resources by sending heavy traffic to them, causing network congestion. Since SDN was proposed, DDoS attack has become a popular research field in SDN security and many researchers have been presented DDoS attacks detection, prevention and mitigation solutions in SDN environment using different methods. This paper surveys the previous researches in DDoS attacks detection and mitigation based methods available in SDN environment. [ABSTRACT FROM AUTHOR]

Wireless sensor network becomes crucial with the appearance of the Internet of Things (IoT). IoT roots in the sensors' data and the technology to transmit the data to the sink. As the importance of IoT arises, the MAC protocols to transmit the data are proposed in many papers. Initially, the sensor devices and the sink remain stationary. As the technology has been advanced, the sensor devices start to move. Accordingly, novel protocols have been proposed for the changing topology. In this paper, we propose Improved-GM-MAC (I-GM-MAC), which means that new algorithms to reconfigure the group number and prevent the endless increasing of group number of the nodes in an isolated area are added to the 3-dimensional group management MAC (3D-GM-MAC). [ABSTRACT FROM AUTHOR]