Adznan B. Jantan

EXPERIMENTAL BREAST TUMOR DETECTION USING NN-BASED UWB IMAGING

This paper presents a system with experimental comple-ment to a simulation work for early breast tumor detection. The ex-periments are conducted using commercial Ultrawide-Band (UWB) transceivers, Neural Network (NN) based Pattern Recognition (PR) software for imaging and proposed breast phantoms for homogenous and heterogeneous tissues. The proposed breast phantoms (homoge-neous and heterogeneous) and tumor are constructed using available low cost materials and their mixtures with minimal e®ort. A speci¯c glass is used as skin. All the materials and their mixtures are con-sidered according to the ratio of the dielectric properties of the breast tissues. Experiments to detect tumor are performed in regular noisy room environment. The UWB signals are transmitted from one side of the breast phantom (for both cases) and received from opposite side diagonally repeatedly. Using discrete cosine transform (DCT) of these received signals, a Neural Network (NN) module is developed, trained and tested. The tumor existence, size and location detection rates for both cases are highly satisfactory, which are approximately: (i) 100%,95.8% and 94.3% for homogeneous and (ii) 100%, 93.4% and 93.1% for heterogeneous cases respectively. This gives assurance of early de- tection and the practical usefulness of the developed system in near future.

3d experimental detection and discrimination of malignant and benign breast tumor using nn-based uwb imaging system

This paper presents both simulation and experimental study to detect and locate breast tumors along with their classification as malignant and/or benign in three dimensional (3D) breast model. The contrast between the dielectric properties of these two tumor types is the main key. These dielectric properties are mainly controlled by the water and blood content of tumors. For simulation, electromagnetic simulator software is used. The experiment is conducted using commercial Ultrawide-Band (UWB) transceivers, Neural Network (NN) based Pattern Recognition (PR) software for imaging and homogenous breast phantom. The 3D homogeneous breast phantom and tumors are fabricated using pure petroleum jelly and a mixture of wheat flour and water respectively. The simulation and experimental setups are performed by transmitting the UWB signals from one side of the breast model and receiving from opposite side diagonally. Using discrete cosine transform (DCT) of received signals, we have trained and tested the developed experimental Neural Network model. In 3D breast model, the achieved detection accuracy of tumor existence is around 100%, while the locating accuracy in terms of (x, y, z) position of a tumor within the breast reached approximately 89.2% and 86.6% in simulation and experimental works respectively. For classification, the permittivity and conductivity detection accuracy are 98.0% and 99.1% in simulation, and 98.6% and 99.5% in experimental works respectively. Tumor detection and type specification 3D may lead to successful clinical implementation followed by saving of precious human lives in the near future.

Color segmentation using multi layer neural network and the HSV color space

This paper presents the results of studying color segmentation using machine learning algorithm and color space analysis. RGB (red, green, blue) color space data points from an image are projected into HSV (hue, saturation, value) color space to provide data points that are insensitive to the variations of illumination in outdoor environment. Multi layer neural network trained using backpropagation algorithm is used to segment the color image. The results show that the algorithm is able to segment the images reliably with less appearance of small blobs. This will help improve the accuracy and minimize the processing time of the subsequent processes in the robot vision system where real-time issue is of important.

Fuzzy Reasoning Approach for Local Connectivity Management in Mobile Ad Hoc Networks

Routing is an important functional aspect in wireless ad hoc networks that handles discovering and maintaining the paths between nodes within a network. Due to nodes’ mobility, the efficiency of a dynamic ad hoc routing protocol depends highly on updating speed of network topology changes. To achieve continuous updated routing tables, the nodes periodically broadcast short Hello messages to their neighbors. Although benefits of these messages have been proven, many studies show some drawbacks for these messages. In this paper, we adaptively optimize the frequent needs of those messages using a fuzzy logic system. The proposed fuzzy algorithm is used to model the uncertainty measurements for updating local connectivity successfully in time. Extensive performance analysis via simulation proves the effectiveness of the proposed method to improve the accuracy of neighborhood information and, hence, overall network performance.

A UWB imaging system to detect early breast cancer in heterogeneous breast phantom

This paper presents an experimental early breast cancer detection system in terms of heterogeneous breast phantom. The system consists of commercial Ultrawide-Band (UWB) transceivers and our developed Neural Network (NN) based Pattern Recognition (PR) software for imaging. A simple way to construct cancer- tissue and heterogeneous breast phantom using available low cost materials and their mixtures is also proposed here. The materials are: (i) A mixture of petroleum jelly, soy oil, wheat flour and water as heterogeneous tissue; (ii) A particular glass as skin; and (iii) A specific mixture of water and wheat flour as cancer- tissue. All the materials and their mixtures are considered according to the ratio of the dielectric properties of the breast tissues. To experimentally detect cancer, the UWB signals are transmitted from one side of the breast phantom and received from opposite side diagonally. By using discrete cosine transform (DCT) of the received signals, a Neural Network (NN) is trained, tested and interfaced with the UWB transceiver to form the complete system. The achieved detection rate of cancer cells existence, size and location are approximately 100%, 93.1% and 93.3% respectively.

A new scalable reliable multicast transport protocol using perfect buffer management

Hierarchical reliable multicast transport protocols partition group members into local groups and allocate one local repair node for each local group to distribute the task of detecting and recovering lost packets. This repair node uses the data stored in its buffer to retransmit the requested packets to the requesting receivers. The problem is that they keep these packets for a long time until they get acknowledgments from all their children receivers of correctly receiving these packets. Keeping these packets creates a congestion problem which decreases the network throughput. This paper proposes a new scheme to solve this problem, by distributing the required packets between the repair node which we call it here the control receiver and some selected receives that have already received these packets correctly. The distribution of the packets decreases the number of packets in the repair node buffer, thus solve the congestion problem and increase the network throughput.

Intelligent Reasoning Approach for Active Queue Management in Wireless Ad Hoc Networks

Mobile ad hoc network is a network without infrastructure where every node has its own protocols and services for powerful cooperation in the network. Every node also has the ability to handle the congestion in its queues during traffic overflow. Traditionally, this was done through DropTail policy where the node drops the incoming packets to its queues during overflow condition. Many studies showed that early dropping of incoming packet is an effective technique to avoid congestion and to minimize the packet latency. Such approach is known as Active Queue Management (AQM). In this article, an enhanced algorithm called fuzzy-AQM is suggested using a fuzzy logic system to achieve the benefits of AQM. Uncertainty associated with queue congestion estimation and lack of mathematical model for estimating the time to start dropping incoming packets makes the fuzzy-AQM algorithm the best choice. Extensive performance analysis via simulation showed the effectiveness of the proposed method for congestion detection and avoidance improving overall network performance.

Experimental Approximation of Breast Tissue Permittivity and Conductivity Using NN-Based UWB Imaging

This paper presents experimental study to distinguish between malignant and benign tumors in early breast cancer detection using Ultra Wide Band (UWB) imaging. The contrast between dielectric properties of these two tumor types is the main key. Mainly water contents control the dielectric properties. Breast phantom and tumor are fabricated using pure petroleum jelly and a mixture of wheat flour and water respectively. A complete system including Neural Network (NN) model is developed for experimental investigation. Received UWB signals through the tumor embedded breast phantom are fed into the NN model to train, test and determine the tumor type. The accuracy of the experimental data is about 98.6% and 99.5% for permittivity and conductivity respectively. This leads to determine tumor dielectric properties accurately followed by distinguish between malignant and benign tumors. As malignant tumors need immediate further medical action and removal, this findings could contribute to save precious file in near future.

Comparison of 3S multi-thresolding with fuzzy C-means method

The 3S (Shrinking-Search-Space) multi-thresholding method which have been used for segmentation of medical images according to their intensities, now have been implemented and compared with FCM method in terms of segmentation quality and segmentation time as a benchmark in thresholding. The results show that 3S method produced almost the same segmentation quality or in some occasions better quality than FCM, and the computation time of 3S method is much lower than FCM. This is another superiority of this method with respect to others. Also, the performance of C-means has been compared with two other methods. This comparison shows that, C-means is not a reliable clustering algorithm and it needs several run to give us a reliable result.