Sameh A. Napoleon

Combined empirical mode decomposition and texture features for skin lesion classification using quadratic support vector machine

PurposeBasal cell carcinoma is one of the most common malignant skin lesions. Automated lesion identification and classification using image processing techniques is highly required to reduce the diagnosis errors.MethodsIn this study, a novel technique is applied to classify skin lesion images into two classes, namely the malignant Basal cell carcinoma and the benign nevus. A hybrid combination of bi-dimensional empirical mode decomposition and gray-level difference method features is proposed after hair removal. The combined features are further classified using quadratic support vector machine (Q-SVM).ResultsThe proposed system has achieved outstanding performance of 100% accuracy, sensitivity and specificity compared to other support vector machine procedures as well as with different extracted features.ConclusionBasal Cell Carcinoma is effectively classified using Q-SVM with the proposed combined features.

C5. Time difference of arrival by IEEE 802.11a, g based on practical estimation

Localization and tracking have recently gained a special importance. A common system for positioning in outdoor environment as e.g. the Global Positioning System (GPS) exists already. GPS is useless for indoor positioning because its signals are weakened or even blocked. This motivated the use of another wireless system to accomplish positioning. Wireless Local Area Network (WLAN) Access Points (APs) are already installed inside buildings, making them a suitable replacement for GPS. Many techniques exist for extracting and calculating location information form the WLAN signals. Among them are super resolution algorithms such as Root Multiple Signal Classification (Root-MUSIC), Estimation of Signal Parameters via Rotational Invariance Technique (ESPRIT), and Matrix Pencil (MP). Many researchers applied these techniques on a specially designed WLAN signals. To apply these techniques in real applications, they should be tested on true wireless signals. In this paper, the performance of super resolution techniques is practically tested on a WLAN transceiver using the communication signals without any modifications.

Sensitivity Analysis of a Class of Iris Localization Algorithms to Blurring Effect

This paper presents a study of a class of iris localization algorithms in the presence of blurring. The effect of blurring is a serious problem in most image processing systems. It may originate in iris imaging systems due to out-of-focus effect. It affects the features extracted from the iris images. Hence, the objective of this paper is to study the sensitivity of three popular iris localization algorithms to the presence of blurring. Features are extracted from normal as well as blurred iris images and used for iris localization. Moreover, Wiener filter restoration is used as a tool to combat the effect of blurring. Performance of the compared iris localization algorithms with Wiener filter restoration is also studied. Simulation results reveal that Masek iris localization algorithm has the least sensitivity to the blurring effect. Its accuracy without blurring is 88.2%, and with blurring, it decreases to 68.18%. Moreover, the Wiener filter significantly improves the accuracy of iris localization.

Towards computer vision-based approach for an adaptive traffic control system

ABSTRACT In this paper, an adaptive traffic control system (ATCS) is proposed using the state of the art of video processing techniques. We illustrate how the system controls standard four-way intersections using three parameters; namely, average vehicles flow speed, level of crowdedness of vehicles, and a critical state timer. These parameters are detected from traffic videos using our computer vision algorithm. The ATCS decision-making process has been designed to adapt to predefined priorities over the traffic parameters. The validation of the proposed ATCS has been tested using four synchronized test videos in order to feed the proposed ATCS with different traffic information. Experimental results show a complete adaptation for the traffic flow.

A novel cumulative level difference mean based GLDM and modified ABCD features ranked using eigenvector centrality approach for four skin lesion types classification

BACKGROUND AND OBJECTIVE Melanoma is one of the major death causes while basal cell carcinoma (BCC) is the utmost incident skin lesion type. At their early stages, medical experts may be confused between both types with benign nevus and pigmented benign keratoses (BKL). This inspired the current study to develop an accurate automated, user-friendly skin lesion identification system. METHODS The current work targets a novel discrimination technique of four pre-mentioned skin lesion classes. A novel proposed texture feature, named cumulative level-difference mean (CLDM) based on the gray-level difference method (GLDM) is extracted. The asymmetry, border irregularity, color variation and diameter are summed up as the ABCD rule feature vector is originally used to classify the melanoma from benign lesions. The proposed method improved the ABCD rule to also classify BCC and BKL by using the proposed modified-ABCD feature vector. In the modified set of ABCD features, each border feature, such as compact index, fractal dimension, and edge abruptness is considered a separate feature. Then, the composite feature vector having the pre-mentioned features is ranked using the Eigenvector Centrality (ECFS) feature ranking method. The ranked features are then classified by a cubic support vector machine for different numbers of selected features. RESULTS The proposed CLDM texture features combined with the ranked ABCD features achieved outstanding performance to classify the four targeted classes (melanoma, BCC, nevi and BKL). The results report 100% outstanding performance of the sensitivity, accuracy and specificity per each class compared to other features when using the highest seven ranked features. CONCLUSIONS The proposed system established that Melanoma, BCC, nevus and BKL are efficiently classified using cubic SVM with the new feature set. In addition, the comparative studies proved the superiority of the cubic SVM to classify the four classes.

VAE/MPM/GA Technique for DoA Estimation Using Optimized Antenna Arrays

Many algorithms have been proposed to estimate the direction of arrival for the targets, but through using a large number of snapshots. In real time applications such as automotive radar, this is unacceptable as it causes delay and heavy processing. Instead, if only a small number of snapshots or, optimally, a single snapshot is available for DoA estimation, it will be fast and efficient. Single snapshot algorithms have a drawback as they require a large number of antenna elements, which considered a limiting factor. In this paper, a single snapshot DoA estimation technique is introduced by using optimized antenna arrays. The proposed algorithm is based on utilization of virtual array extension, matrix pencil method, and the genetic algorithm. The use of virtual array extension greatly improves the MPM performance. Furthermore, it exhibits a high DoA estimation accuracy by using a reduced number of antenna elements. The genetic algorithm is employed to determine the minimum number of antenna elements, which are required to estimate the DoAs with minimal root mean square error.

Use of super resolution algorithms for indoor positioning keeping novel designed WLAN signal structure

This paper presents the utilization of super resolution algorithms for the indoor positioning applications in order to estimate Time Difference of Arrival (TDOA) and distances using Orthogonal Frequency Division Multiplexing (OFDM) transceiver. Optimal reduction in Distance Measurement Error (DME) is achieved. We have utilized OFDM/Single Carrier-Decision Feedback Equalizer (OFDM/SC-DFE) signal structure presented in our previous works. The super resolution algorithms Estimation of Signal Parameters via Rotational Invariance Technique (ESPRIT), Root Multiple Signal Classification (Root-MUSIC) and Matrix Pencil (MP) are compared for DME estimation. We have applied Minimum Descriptive Length (MDL) criterion to these algorithms, that provides optimized estimate of the length of actual Channel Impulse Response (CIR) by eliminating the noise component from the dispersive CIR. Our scheme is based on two different antennas used to transmit the pre-half-zero-carriers and post-half-zero-carriers OFDM symbols respectively, mapped to multiple carriers using Wireless Local Area Network (WLAN) system and received by the object to be positioned.