Publications

Results 1–25 of 29
Skip to search filters

Coordinated machine learning and decision support for situation awareness

Draelos, Timothy J.; Brannon, Nathan B.; Conrad, Gregory N.; Zhang, Pengchu Z.

For applications such as force protection, an effective decision maker needs to maintain an unambiguous grasp of the environment. Opportunities exist to leverage computational mechanisms for the adaptive fusion of diverse information sources. The current research employs neural networks and Markov chains to process information from sources including sensors, weather data, and law enforcement. Furthermore, the system operator's input is used as a point of reference for the machine learning algorithms. More detailed features of the approach are provided, along with an example force protection scenario.

More Details

Profile-based adaptive anomaly detection for network security

Zhang, Pengchu Z.

As information systems become increasingly complex and pervasive, they become inextricably intertwined with the critical infrastructure of national, public, and private organizations. The problem of recognizing and evaluating threats against these complex, heterogeneous networks of cyber and physical components is a difficult one, yet a solution is vital to ensuring security. In this paper we investigate profile-based anomaly detection techniques that can be used to address this problem. We focus primarily on the area of network anomaly detection, but the approach could be extended to other problem domains. We investigate using several data analysis techniques to create profiles of network hosts and perform anomaly detection using those profiles. The ''profiles'' reduce multi-dimensional vectors representing ''normal behavior'' into fewer dimensions, thus allowing pattern and cluster discovery. New events are compared against the profiles, producing a quantitative measure of how ''anomalous'' the event is. Most network intrusion detection systems (IDSs) detect malicious behavior by searching for known patterns in the network traffic. This approach suffers from several weaknesses, including a lack of generalizability, an inability to detect stealthy or novel attacks, and lack of flexibility regarding alarm thresholds. Our research focuses on enhancing current IDS capabilities by addressing some of these shortcomings. We identify and evaluate promising techniques for data mining and machine-learning. The algorithms are ''trained'' by providing them with a series of data-points from ''normal'' network traffic. A successful algorithm can be trained automatically and efficiently, will have a low error rate (low false alarm and miss rates), and will be able to identify anomalies in ''pseudo real-time'' (i.e., while the intrusion is still in progress, rather than after the fact). We also build a prototype anomaly detection tool that demonstrates how the techniques might be integrated into an operational intrusion detection framework.

More Details

Tem Investigation of U6+ and Re7+ reduction by desulfovibrio desulfiiricans, a sulfate-reducing bacterium

Materials Research Society Symposium - Proceedings

Xu, Huifang; Barton, Larry L.; Zhang, Pengchu Z.; Wang, Yifeng

Uranium and its fission product Tc in aerobic environment will be in the forms of UO22+ and TcO4-. Reduced forms of tetravalent U and Tc are sparingly soluble. As determined by transmission electron microscopy, the reduction of uranyl acetate by immobilized cells of Desulfovibrio desulfuricans results in the production of black uraninite nanocrystals precipitated outside the cell. Some nanocrystals are associated with outer membranes of the cell as revealed from cross sections of these metabolic active sulfate-reducing bacteria. The nanocrystals have an average diameter of 5 nm and have anhedral shape. The reduction of Re7+ by cells of Desulfovibrio desulfuricans is fast in the media containing H2 electron donor, and slow in the media containing lactic acid. It is proposed that cytochrome in these cells has an important role in the reduction of uranyl and Re7+ that is a chemical analogue for one uranium fission product Tc7+ through transferring electron from molecular hydrogen or lactic acid to the oxyions of UO22+ and ReO4-. © 2000 Materials Research Society.

More Details

Formation of Chloropyromorphite in a Lead-Contaminated Soil Amended with Hydroxyapatite

Environmental Science and Technology

Zhang, Pengchu Z.; Zhang, Pengchu Z.

To confirm conversion of soil Pb to pyromorphite [Pb{sub 5}(PO{sub 4}){sub 3}Cl], a Pb contaminated soil collected adjacent to a historical smelter was reacted with hydroxyapatite in slurries of soil and hydroxyapatite separated by a dialysis membrane and incubated. A crystalline precipitate formed on the dialysis membrane in the slurry systems was identified as chloropyromorphite. Soluble species measured in the soil slurry indicated that dissolution of solid-phase soil Pb was the rate-limiting step for pyromorphite formation. Additionally samples reacted with hydroxyapatite were incubated at field-capacity moisture content. The sequential chemical extraction used to identify species in the field-moist soil incubation experiment showed that hydroxyapatite treatment reduced the first four fractions of extractable Pb and correspondingly increased the recalcitrant extraction residue fraction by 35% of total Pb at 0 d incubation and by 45% after 240 d incubation. the increase in the extraction residue fraction in the 240 d incubation as compared to the 0 d incubation implies that the reaction occurs in the soil but the increase in the hydroxyapatite amended 0 d incubated soil as compared to the control soil illustrates the chemical extraction procedure caused changes in the extractability. Thus, the chemical extraction procedure cannot easily be utilized to confirm changes occurring in the soil as a result of incubation. Extended x-ray absorption fine structure (EXAFS) spectroscopy indicated that the 240 d incubated hydroxyapatite treatment caused a change in the average, local molecular bonding environment of soil Pb. Low-temperature EXAFS spectra (chi data and radial structure functions - RSFs) showed a high degree of similarity between the chemical extraction residue and synthetic pyromorphite. Thus, confirming that the change of soil Pb to pyromorphite is possible by simple amendments of hydroxyapatite to soil.

More Details
Results 1–25 of 29
Results 1–25 of 29