Ensemble fuzzy belief intrusion detection design

With the rapid growth of the Internet, computer attacks are increasing at a fast pace and can easily cause millions of dollar in damage to an organization. Detecting these attacks is an important issue of computer security. There are many types of attacks and they fall into four main categories, Denial of Service (DoS) attacks, Probe, User to Root (U2R) attacks, and Remote to Local (R2L) attacks. Within these categories, DoS and Probe attacks continuously show up with greater frequency in a short period of time when they attack systems. They are different from the normal traffic data and can be easily separated from normal activities. On the contrary, U2R and R2L attacks are embedded in the data portions of the packets and normally involve only a single connection. It becomes difficult to achieve satisfactory detection accuracy for detecting these two attacks. Therefore, we focus on studying the ambiguity problem between normal activities and U2R/R2L attacks. The goal is to build a detection system that can accurately and quickly detect these two attacks. In this dissertation, we design a two-phase intrusion detection approach. In the first phase, a correlation-based feature selection algorithm is proposed to advance the speed of detection. Features with poor prediction ability for the signatures of attacks and features inter-correlated with one or more other features are considered redundant. Such features are removed and only indispensable information about the original feature space remains. In the second phase, we develop an ensemble intrusion detection system to achieve accurate detection performance. The proposed method includes multiple feature selecting intrusion detectors and a data mining intrusion detector. The former ones consist of a set of detectors, and each of them uses a fuzzy clustering technique and belief theory to solve the ambiguity problem. The latter one applies data mining technique to automatically extract computer users’ normal behavior from training network traffic data. The final decision is a combination of the outputs of feature selecting and data mining detectors. The experimental results indicate that our ensemble approach not only significantly reduces the detection time but also effectively detect U2R and R2L attacks that contain degrees of ambiguous information.

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as ƒ-test is performed during each node's split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.

Ensemble Fuzzy Belief Intrusion Detection Design

With the rapid growth of the Internet, computer attacks are increasing at a fast pace and can easily cause millions of dollar in damage to an organization. Detecting these attacks is an important issue of computer security. There are many types of attacks and they fall into four main categories, Denial of Service (DoS) attacks, Probe, User to Root (U2R) attacks, and Remote to Local (R2L) attacks. Within these categories, DoS and Probe attacks continuously show up with greater frequency in a short period of time when they attack systems. They are different from the normal traffic data and can be easily separated from normal activities. On the contrary, U2R and R2L attacks are embedded in the data portions of the packets and normally involve only a single connection. It becomes difficult to achieve satisfactory detection accuracy for detecting these two attacks. Therefore, we focus on studying the ambiguity problem between normal activities and U2R/R2L attacks. The goal is to build a detection system that can accurately and quickly detect these two attacks. In this dissertation, we design a two-phase intrusion detection approach. In the first phase, a correlation-based feature selection algorithm is proposed to advance the speed of detection. Features with poor prediction ability for the signatures of attacks and features inter-correlated with one or more other features are considered redundant. Such features are removed and only indispensable information about the original feature space remains. In the second phase, we develop an ensemble intrusion detection system to achieve accurate detection performance. The proposed method includes multiple feature selecting intrusion detectors and a data mining intrusion detector. The former ones consist of a set of detectors, and each of them uses a fuzzy clustering technique and belief theory to solve the ambiguity problem. The latter one applies data mining technique to automatically extract computer users’ normal behavior from training network traffic data. The final decision is a combination of the outputs of feature selecting and data mining detectors. The experimental results indicate that our ensemble approach not only significantly reduces the detection time but also effectively detect U2R and R2L attacks that contain degrees of ambiguous information.

The Influence of the Guatemalan Municipal Orchestra's Curriculum on the Social Relations of its Members

The purpose of this case study is to determine the influence of the curriculum used by the Guatemalan Municipal Orchestra (GMO) upon the social interactions of its members. Social interactions include relations with families, teachers, and music colleagues. To determine this influence, the researcher framed the study using three main components: the impact of music in the development of children’s social skills; the curricula forming educational processes; and the characteristics of the Venezuela musical program, El Sistema. These foundations are explored via the tenets of participatory literacy. The data collection included interviews, surveys, and observation of students, parents, teachers, and administrative personnel. Two primary themes emerged from the data analysis: the development of a sense of community and the presence of intrinsic and external motivators implicit in the GMO environment. The final analysis suggests that curricular practices in the GMO positively influenced the development of students’ social interactions.

Hermes, a Concerto for Violoncello and Orchestra

This thesis consists of a large composition for violoncello and orchestra, together with an analytical paper in which I discuss my compositional techniques and some of their historical antecedents. The composition draws on the genres of imaginary musical theater, the symphonic poem, and the concerto. It was also inspired by the story of Hermes, the messenger god from Greek mythology. While the myth partially informs the compositional structure, the work is ultimately meant to showcase the versatility of the cello, the coloristic range of the orchestra (in some cases emulating the orchestral styles of previous composers), the balance of cello and orchestra together, and the eclectic invocation of many compositional techniques separately and simultaneously. These techniques encompass set theory (the use of unordered pitch collections), polytonality, and serialism. It is composed in a post-romantic style.

Zoroastrianism, Cosmology, and Chaos: A Detailed Analysis of the Musical Composition, Druj Aeterni

Druj Aeterni is a large chamber ensemble piece for flute, clarinet, French horn, two trumpets, piano, two percussionists, string quintet, and electric bass. My composition integrates three intellectual pursuits and interests, ancient mythology, cosmology, and mathematics. The title of the piece uses Latin and the language of the Avesta, the holy book of Zoroastrianism, and comments upon a philosophical perspective based in string theory. I abstract the cosmological implications of string theory, apply them to the terminology and theology of Zoroastrianism, and then structure the composition in consideration of a possible reconciliation. The analysis that follows incorporates analytical techniques similar to David Cope’s style of Vectoral Analysis.

Colombian Jazz dance suite : a synthesis of the music of the colombian andes and modern jazz

This thesis is an attempt to unite two distinct and dissimilar musical genres, the music of the Colombian Andes and modem jazz. The compositions to be analyzed in this thesis are meant to function as parts of a whole. Thus, they will be linked by thematic and rhythmic material. In their entirety the pieces will form a suite of dances not unlike those of Baroque composers, with titles that denote the name of the particular air being employed by the composer, who is also the author of this thesis. These individual dances are orchestrated for a jazz ensemble consisting of piano, string bass, drums, alto saxophone, and guitar. The rhythmic underpinning of this work is inspired by the folk music of Colombia and the harmonic content will be derived from the jazz idiom. The purpose of this thesis is to demonstrate the possible product of the fusion of musical disciplines that are on the surface in no way related. This thesis will also attempt to show an example of how cultures can meld socio-artistically.

Ensemble Stream Model for Data-Cleaning in Sensor Networks

Ensemble Stream Modeling and Data-cleaning are sensor information processing systems have different training and testing methods by which their goals are cross-validated. This research examines a mechanism, which seeks to extract novel patterns by generating ensembles from data. The main goal of label-less stream processing is to process the sensed events to eliminate the noises that are uncorrelated, and choose the most likely model without over fitting thus obtaining higher model confidence. Higher quality streams can be realized by combining many short streams into an ensemble which has the desired quality. The framework for the investigation is an existing data mining tool. First, to accommodate feature extraction such as a bush or natural forest-fire event we make an assumption of the burnt area (BA*), sensed ground truth as our target variable obtained from logs. Even though this is an obvious model choice the results are disappointing. The reasons for this are two: One, the histogram of fire activity is highly skewed. Two, the measured sensor parameters are highly correlated. Since using non descriptive features does not yield good results, we resort to temporal features. By doing so we carefully eliminate the averaging effects; the resulting histogram is more satisfactory and conceptual knowledge is learned from sensor streams. Second is the process of feature induction by cross-validating attributes with single or multi-target variables to minimize training error. We use F-measure score, which combines precision and accuracy to determine the false alarm rate of fire events. The multi-target data-cleaning trees use information purity of the target leaf-nodes to learn higher order features. A sensitive variance measure such as f-test is performed during each node’s split to select the best attribute. Ensemble stream model approach proved to improve when using complicated features with a simpler tree classifier. The ensemble framework for data-cleaning and the enhancements to quantify quality of fitness (30% spatial, 10% temporal, and 90% mobility reduction) of sensor led to the formation of streams for sensor-enabled applications. Which further motivates the novelty of stream quality labeling and its importance in solving vast amounts of real-time mobile streams generated today.