Mohamed F. Chouikha

Attenuation characteristics of high rate home-networking PLC signals

This paper reports on an experimental investigation of the influence of the HF signal attenuation on the load in residences and offices. A laboratory test and actual measurements were performed in a residence and an office. The experiments show that the attenuation characteristics are more dependent on the number of loads than the type of loads connected. Also, the concentration of loads was found to determine where the maximum attenuation of the HF signals would occur. The types and the size of the loads, however, did not affect the attenuation characteristics of the HF signals. Therefore, for a successful high rate PLC home networking, the analysis on the placement of the loads may have to be considered for better understanding of signal attenuation for PLC modems and other PLC-to-media adapters.

Design and analysis of fuzzy controllers for DC-DC converters

A successful implementation of fuzzy controllers for DC-DC converters is presented in this paper. Two different fuzzy logic control topologies are developed and implemented using different types of DC-DC converters such as the buck, the boost, the buck-boost, and the sepic converters. Issues of sudden changes in the load or parametric uncertainties control and communication interface, among many other issues, are discussed and presented. The fundamentals governing the design, control and performance of the DC-DC converters are also illustrated. Properties of the proposed controllers are: 1) robustness around the operating point, 2) good performance of transient responses under varying loading conditions and/or input voltage, and 3) invariant dynamic performance in the presence of varying operating conditions. Simulation results have been obtained using appropriate scaling factors associated with the input variables of the fuzzy controller.

Review of Image Fusion Algorithms for Unconstrained Outdoor Scenes

In this paper, we review some of the recent image fusion algorithms and associated assessment techniques. This paper mainly reviews pixel-level algorithms published in the past five years. These fusion algorithms are experimentally evaluated with quantitative assessment techniques. A new practical assessment paradigm for image fusion is provided

Top-down approach to segmentation of prostate boundaries in ultrasound images

Ultrasound has been increasingly used in surgical procedures of the prostate in recent years. Segmentation of prostate boundaries from ultrasound images is clinically useful in such situations as accurate volume measurement, and tumor margin estimation, and it can also provide real-time targeted image guidance during procedures such as biopsy and ablation. Automatic segmentation of the prostate, however, is a challenging task since the ultrasound images usually have high level of speckle noises due to large amount of random scatters and thus they have a very low signal-to-noise ratio. As a result, physicians have to use manual methods to draw contours of the prostate, slice by slice, in order to calculate prostate volume information. This is a tedious work and apparently it delays the whole clinical procedures. In addition, accuracy of the segmented prostate boundaries cannot be guaranteed due to significant variations among different physicians or with the same physician at different times. In this paper, we present a top-down approach to the segmentation of prostate ultrasound images using a snake model, as compared to most existing bottom-up methods. Special measures were taken to deal with the high speckle noises and complex shapes of prostate boundaries. In general, median filtering proved to be effective in removing speckle noises. We extensively evaluated most of the existing edge detection methods and found that the logic combination of Laplacian of Gaussian (LoG) and Sobel operator provided the best performance in finding the useful image gradients. Parameters of the snake were dynamically optimized, and the shape information of the prostate was used as a strong guidance during the deformation process of the snake model. Experimental results with several ultrasound prostate images with various levels of noises were presented to demonstrate the effectiveness of the proposed approach.

Steepest changes of a probability-based cost function for delineation of mammographic masses: A validation study

Our purpose in this work was to develop an automatic boundary detection method for mammographic masses and to rigorously test this method via statistical analysis. The segmentation method utilized a steepest change analysis technique for determining the mass boundaries based on a composed probability density cost function. Previous investigators have shown that this function can be utilized to determine the border of the mass body. We have further analyzed this method and have discovered that the steepest changes in this function can produce mass delineations that include extended projections. The method was tested on 124 digitized mammograms selected from the University of South Floridas Digital Database for Screening Mammography (DDSM). The segmentation results were validated using overlap, accuracy, sensitivity, and specificity statistics, where the gold standards were manual traces provided by two expert radiologists. We have concluded that the best intensity threshold corresponds to a particular steepest change location within the composed probability density function. We also found that our results are more closely correlated with one expert than with the second expert. These findings were verified via Analysis of Variance (ANOVA) testing. The ANOVA tests obtained p-values ranging from 1.03 x 10(-2)-7.51 x 10(-17) for the single observer studies and 2.03 x 10(-2)-9.43 x 10(-4) for the two observer studies. Results were categorized using three significance levels, i.e., p<0.001 (extremely significant), p <0.01 (very significant), and p <0.05 (significant), respectively.

Automatic segmentation of mammographic masses using fuzzy shadow and maximum-likelihood analysis

This study attempted to accurately segment tumors in mammograms. Although this task is considered to be a preprocessing step in a computer analysis program, it plays an important role for further analysis of breast lesions. The region of interest (ROI) was segmented using the pixel aggregation and region growing techniques combined with maximum likelihood analysis. A fast segmentation algorithm has been developed to facilitate the segmentation process. The algorithm repetitively sweeps the ROI horizontally and vertically to aggregate the pixels that have intensifies higher than a threshold. The ROI is then fuzzified by the Gaussian envelope. With each segmented region for a given threshold step in the original ROI, the likelihood function is computed and is comprised of probability density functions inside and outside of the fuzzified ROI. We have implemented this method to test on 90 mammograms. We found the segmented region with the maximum likelihood corresponds to the body of tumor. However, the segmented region with the maximum change of likelihood corresponds to the tumor and it extended margin.

Segmentation of prostate ultrasound images using an improved snakes model

We have applied an improved deformable 2D snakes modeling technique to the segmentation of prostate ultrasound images. Special measures were taken to deal with the high speckle noises and complex shapes of prostate boundaries. Median filtering proves to be effective in removing speckle noises, and by dynamically changing the rigidity parameters of the snakes model, our implementation has shown satisfactory preliminary segmentation results. We also have experimented with the gradient vector flow (GVF) snakes model with various edge detectors, and a combined LOG & Sobel operator is shown to perform the best in determining the edge map gradient field for the GVF.

Breast cancer detection in mammogram with AM-FM modeling and Gabor filtering

In this paper, we propose to apply an integrated method to the mammography images for breast cancer detection. This method combines AM-FM modeling techniques with image filtering by a bank of specially designed Gabor filters. Cancer features will be extracted from the decomposed or filtered images and projected back to the reconstructed mammography images. We seek to validate our approach by showing that a mammogram can be accurately decomposed, analyzed and reconstructed. Experimental results with a number of mammography images and cancer cases have confirmed our expectations.

Performance assessment of mammography image segmentation algorithms

In this paper, we present a comprehensive validation analysis to evaluate the performance of three existing mammogram segmentation algorithms against manual segmentation results produced by two expert radiologists. These studies are especially important for the development of computer-aided cancer detection (CAD) systems, which will significantly help improve early detection of breast cancer. Three typical segmentation methods were implemented and applied to 50 malignant mammography images chosen from the University of South Floridas Digital Database for Screening Mammography (DDSM): (a) region growing combined with maximum likelihood modeling (Kinnard model), (b) an active deformable contour model (snake model), and (c) a standard potential field model (standard model). A comprehensive statistical validation protocol was applied to evaluate the computer and expert outlined segmentation results; both sets of results were examined from the inter- and intra-observer points of view. Experimental results are presented and discussed in this communication

The Howard University System Submission for the Shared Task in Language Identification in Spanish-English Codeswitching.

This paper describes the Howard University system for the language identification shared task of the Second Workshop on Computational Approaches to Code Switching. Our system is based on prior work on SwahiliEnglish token-level language identification. Our system primarily uses character n-gram, prefix and suffix features, letter case and special character features along with previously existing tools. These are then combined with generated label probabilities of the immediate context of the token for the final system.