Engineering Commons^™

Gap-Based Estimation: Choosing The Smoothing Parameters For Probabilistic And General Regression Neural Networks, Mingyu Zhong, Dave Coggeshall, Ehsan Ghaneie, Thomas Pope, Mark Rivera, Michael Georgiopoulos, Georgios C. Anagnostopoulos, Mansooreh Mollaghasemi, Samuel Richie

Electrical Engineering and Computer Science Faculty Publications

Probabilistic neural networks (PNN) and general regression neural networks (GRNN) represent knowledge by simple but interpretable models that approximate the optimal classifier or predictor in the sense of expected value of the accuracy. These models require the specification of an important smoothing parameter, which is usually chosen by crossvalidation or clustering. In this article, we demonstrate the problems with the cross-validation and clustering approaches to specify the smoothing parameter, discuss the relationship between this parameter and some of © 2007 Massachusetts Institute of Technology the data statistics, and attempt to develop a fast approach to determine the optimal value of …

H.264 Scalable Video Over Finite-State Markov Chain Wireless Channels, Guogang Hua, Daewon Song, David L. Hench, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

In this paper, a wireless channel is viewed as a heterogeneous network in the time domain, and an adaptive video transmission scheme for H.264 scalable video over wireless channels modeled as a finite-state Markov chain processes is presented. In order to investigate the robustness of adaptive video transmission for H.264 scalable video over wireless channels, statistical channel models can be employed to characterize the error and loss behavior of the video transmission. Among various statistical channel models, a finite-state Markov model has been considered as suitable for both wireless links as Rayleigh fading channels and wireless local area networks as …

Spatio-Temporal Anomaly Detection For Mobile Devices, Guarav Tandon, Philip K. Chan

Electrical Engineering and Computer Science Faculty Publications

With the increase in popularity of mobile devices, there has been a significant rise in mobile related security problems. The biggest threat for a mobile subscriber is lost or stolen device, which can lead to confidential data leakage, identity theft, misuse, impersonation, and high service charges. A significant amount of time may elapse between losing a device and disabling it through the service provider, during which an unauthorized malicious user may gain access and incur severe damage. We propose a probabilistic approach to spatio-temporal anomaly detection and evaluate smoothing techniques for sparse data. Our approach outperforms Markov Chain in experiments …

First Thz And Ir Characterization Of Nanometer-Scaled Antenna-Coupled Ingaas/Inp Schottky-Diode Detectors For Room Temperature Infrared Imaging, Hooman Kazemi, Keisuke Shinohara, Gabor Nagy, Wonill Ha, Brian A. Lail, E. N. Grossman, Guy Zummo, William R. Folks, Javier Alda, Glenn D. Boreman

Electrical Engineering and Computer Science Faculty Publications

Nanometer high performance InP Schottky detectors are scaled to IR wavelengths. The increased cutoff frequency of the Schottky detector was accomplished by both reducing its capacitance to attofarad range and also by reducing the contact resistance. The Schottky detectors were fabricated on InGaAs/InP substrates with the doping level as high as 1 x 10¹⁹ cmˉ². The typical Schottky detector anode size was 0.1 x 1 μm². Planar broadband antennas were designed for LWIR wavelengths to couple the radiation into the nanometer size detector. Several different IR antenna designs were evaluated, including complimentary square spirals, bow ties and crossed dipoles. A …

Signal-To-Noise Ratio For Cross-Sensor Fusion Approach, Samuel Peter Kozaitis, Michel Ouendeno

Electrical Engineering and Computer Science Faculty Publications

We determined the signal-to-noise ratios for an image fusion approach that is suitable for application to systems with disparate sensors. We found there was reconstruction error present when the forward and reverse transforms for image fusion give perfect reconstruction.

Improved Denoising Approach Using Higher-Order Statistics, Samuel Peter Kozaitis

Electrical Engineering and Computer Science Faculty Publications

We presented a method to reduce noise in signals using a higher-order, correlation-based approach. This paper examines the differences between hard and soft thresholds using the higher-order method, and the use of different wavelets in the denoising algorithm. Using a detection algorithm derived from third-order statistics, we determined if a wavelet coefficient was either mostly noise or mostly signal based on third-order statistics. We found that hard thresholding worked best when compared to soft thresholding but there is the possibility of improvement using soft thresholding.

Wavelet-Based Fusion Approach Using Unique Reconstruction Approach, Michel Ouendeno, Samuel Peter Kozaitis

Electrical Engineering and Computer Science Faculty Publications

We used measures based on entropy to evaluate a method designed to fuse imagery from different sensor types. The method uses different forward transforms of input images and a common transform to reconstruct the final result. We attempted to examine the link between the error in a reconstructed result and its associated entropy.

Novel Layered Scalable Video Coding Transmission Over Mimo Wireless Systems With Partial Csi And Adaptive Channel Selection, Daewon Song, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

In this paper, we present a novel layered scalable video transmission scheme over multi-input multi-output (MIMO) wireless systems. The proposed layered scalable video transmission scheme is able to adaptively select the MIMO sub-channels for prioritized delivery of layered video signals based on only estimated partial channel state information (CSI). This scheme is fundamentally different from open loop (OL)-MIMO systems such as V-BLAST in which the CSI is only available at the receiver side. Without CSI at the transmitter, data sequences in OL-MIMO are transmitted simultaneously with equal power via multiple antennas. Therefore, OL-MIMO systems are not appropriate for transmitting compressed …

Dynamic Gop Structure For Scalable Video Coding, Haksoo Kim, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

MPEG is currently developing a new scalable video coding (SVC) standard which should provide compression efficiency similar to current non-scalable video coding standard. The extension of H.264/AVC hybrid video coding using motion-compensated temporal filtering (MCTF) is a current solution. This paper presents a dynamic group of picture (GOP) structure to improve the quality of the SVC coded video by using variable GOP sizes along the video sequences without the restriction of the fixed GOP size or the limited adaptive GOP size. The dynamic GOP structure keeps temporal importance information of frames in the encoded video, which helps in coding efficiency …

Distributed Video Coding Based On Constrained Rate Adaptive Low Density Parity Check Codes, Rong Ke Liu, Guo Gang Hua, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

Distributed video coding is an emerging area of research for digital video driven partly by the widespread use of video acquisition devices by the consumers. In this paper, we present a distributed video coding scheme based on zero motion identification at the decoder and constrained rate adaptive low density parity check (LDPC) codes. Zero-motion-block identification mechanism is introduced at the decoder, which takes the characters of video sequence into account. The constrained error control decoder can use the bits in the zero motion blocks as a constraint to achieve a better decoding performance and further improve the overall video compression …

Progressive Image Transmission With Rcpt Protection, Lei Yao, Lei Cao, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

In this paper, a joint source-channel coding scheme is proposed for progressive image transmission over channels with both random bit errors and packet loss by using rate-compatible punctured Turbo codes (RCPT) protection only. Two technical components which are different from existing methods are presented. First, a data frame is divided into multiple CRC blocks before being coded by a turbo code. This is to secure a high turbo coding gain which is proportional to the data frame size. In the mean time, the beginning blocks in a frame may still be usable although the decoding of the entire frame fails. …

Detecting Anomalies By Learning Weighted Rules, Guarav Tandon, Philip K. Chan

Electrical Engineering and Computer Science Faculty Publications

Anomaly detection focuses on modeling the normal behavior and identifying significant deviations, which could be novel attacks. The previously proposed LERAD algorithm can efficiently learn a succinct set of comprehensible rules for detecting anomalies. We conjecture that LERAD eliminates rules with possibly high coverage, which can lead to missed detections. This study proposes weights that approximate rule confidence and are learned incrementally. We evaluate our algorithm on various network and host datasets. Compared to LERAD, our technique detects more attacks at low false alarm rates with minimal computational overhead.

Dynamics Of Wave-Current Boundary Layers Over Very Rough Boundaries, Marion Bandet-Chavanne

Link Foundation Ocean Engineering and Instrumentation Fellowship Reports

In this study, acoustic profiling techniques are used to resolve the two-dimensional spatial structures of the oscillating boundary layer in a phase-averaged sense over a wave orbital amplitude. The principal objective of this work is to examine the spatial variability of turbulent properties over irregular roughness. Field observations are used to investigate the interaction between bottom roughness, flow structure and turbulent properties within the near-bed flow. The overall focus of the research is to relate wave energy dissipation or friction factor estimates to physical roughness elements and understand the dynamics of such processes in the near-bed flow.

Collaborative Image Coding And Transmission Overwireless Sensor Networks, Min Wu, Chang Wen Chen

Electrical Engineering and Computer Science Faculty Publications

The imaging sensors are able to provide intuitive visual information for quick recognition and decision. However, imaging sensors usually generate vast amount of data. Therefore, processing and coding of image data collected in a sensor network for the purpose of energy efficient transmission poses a significant technical challenge. In particular, multiple sensors may be collecting similar visual information simultaneously. We propose in this paper a novel collaborative image coding and transmission scheme to minimize the energy for data transmission. First, we apply a shape matching method to coarsely register images to find out maximal overlap to exploit the spatial correlation …

Semi-Autonomous Control Of Autonomous Underwater Vehicles, Stephen C. Martin

Link Foundation Ocean Engineering and Instrumentation Fellowship Reports

The goal of my graduate research is to address two engineering science problems whose solution will enable Autonomous Underwater Vehicles (AUVs) to routinely perform semi-autonomous missions presently considered impractical or infeasible. I am pursuing this research under the direction of Professor Whitcomb in the Dynamical Systems and Controls Laboratory at Johns Hopkins University, and in collaboration with the faculty of the Deep Submergence Laboratory of the Woods Hole Oceanographic Institution (WHOI).

In the last decade AUVs have begun to complement Human Occupied Vehicles (HOVs) and Remotely Operated Vehicles (ROVs) as effective platforms for oceanographic exploration. HOVs and ROVs are highly …

Video Transmission Over Mimo-Ofdm System: Mdc And Space-Time Coding-Based Approaches, Haifeng Zheng, Congchong Ru, Chang Wen Chen, Lun Yu

Electrical Engineering and Computer Science Faculty Publications

MIMO-OFDM is a promising technique for the broadband wireless communication system. In this paper, we propose a novel scheme that integrates multiple-description coding (MDC), error-resilient video coding, and unequal error protection strategy with hybrid space-time coding structure for robust video transmission over MIMO-OFDM system. The proposed MDC coder generates multiple bitstreams of equal importance which are very suitable for multiple-antennas system. Furthermore, according to the contribution to the reconstructed video quality, we apply unequal error protection strategy using BLAST and STBC space-time codes for each video bitstream. Experimental results have demonstrated that the proposed scheme can be an excellent alternative …