Samir I. Shaheen

A comparison between neural-network forecasting techniques-case study: river flow forecasting

Estimating the flows of rivers can have significant economic impact, as this can help in agricultural water management and in protection from water shortages and possible flood damage. The first goal of this paper is to apply neural networks to the problem of forecasting the flow of the River Nile in Egypt. The second goal of the paper is to utilize the time series as a benchmark to compare between several neural-network forecasting methods.We compare between four different methods to preprocess the inputs and outputs, including a novel method proposed here based on the discrete Fourier series. We also compare between three different methods for the multistep ahead forecast problem: the direct method, the recursive method, and the recursive method trained using a backpropagation through time scheme. We also include a theoretical comparison between these three methods. The final comparison is between different methods to perform longer horizon forecast, and that includes ways to partition the problem into the several subproblems of forecasting K steps ahead.

A Modular Computer Vision System for Picture Segmentation and Interpretation

The objective of a computer vision system is to outline the objects in a picture and label them with an appropriate interpretation. This paper proposes a new paradigm for a modular computer vision system which is both data directed and knowledge based. The system consists of three different types of units, two of which are associative data memories implemented as relational databases. The short-term memory (STM) contains the raw color picture data and the most current interpretations and deductions about the original scene. The long-term memory (LTM) contains a detailed model of the scene under consideration. A collection of analysis processors, each of which is specialized for a particular task, can communicate with both of these memories. The information in the LTM remains unchanged during the analysis, while the STM is being continually updated and revised by the appropriate processors. The latter may be conceived of as being activated by certain data conditions in the STM, and using the information in both the LTM and STM to alter the status of the STM.

Sign language recognition using a combination of new vision based features

Sign languages are based on four components hand shape, place of articulation, hand orientation, and movement. This paper presents a novel combination of vision based features in order to enhance the recognition of underlying signs. Three features are selected to be mapped to these four components. Two of these features are newly introduced for American sign language recognition: kurtosis position and principal component analysis, PCA. Although PCA has been used before in sign a language as a dimensionality reduction technique, it is used here as a descriptor that represents a global image feature to provide a measure for hand configuration and hand orientation. Kurtosis position is used as a local feature for measuring edges and reflecting the place of articulation recognition. The third feature is motion chain code that represents the hand movement. On the basis of these features a prototype is designed, constructed and its performance is evaluated. It consists of skin color detector, connected component locator and dominant hand tracker, feature extractor and a Hidden Markov Model classifier. The input to the system is a sign from RWTH-BOSTON-50 database and the output is the corresponding word with a recognition error rate of 10.90%.

Landmark identification in computerized posteroanterior cephalometrics

A lack of cognition regarding the reliability of landmark identification in posteroanterior cephalometrics keeps the extracted data questionable. The present study was designed to analyze this problem for the purpose of providing certain insights. An interactive computer graphic package was developed. This package was called EA-PAX (Error Analysis of Postero-Anterior cephalometric X-ray films). A random sample of 40 clear posteroanterior cephalometric head plates was studied. The reliability of landmark identification was established. The skeletal landmarks seemed more reliable than the dental landmarks. The variation in the direction and magnitude of the error was determined for each landmark. Most landmarks had their own characteristic noncircular envelope of error. It is not the philosophy of the present authors to tell the orthodontists what to use. Rather, the philosophy is to be aware of the amount and direction of variation for a particular landmark. Taking this into consideration will enable the orthodontists to look on their cephalometric numbers with a mental awareness of the possible variations. Several clinical and research studies are suggested in the article.

Segmentation and classification of white blood cells

Automated medical image processing and analysis offers a powerful tool for medical diagnosis. In this work we tackle the problem of white blood cell shape analysis based on the morphological characteristics of their outer contour and nuclei. The paper presents a set of preprocessing and segmentation algorithms along with a set of features that are able to recognize and classify different categories of normal white blood cells. The system was tested on gray level images obtained from a CCD camera through a microscope and produced a correct classification rate close to 91%.

An efficient stock market forecasting model using neural networks

Forecasting financial markets has attracted the interest of neural network researchers. It is a challenging problem, where obtaining a 0.5+/spl epsiv/ accuracy is an achievement. Researchers applied neural networks successfully to the problems of forecasting currencies, bonds, the futures markets, real estate, and the stock market. In this paper we develop a method for forecasting the stock market. We use novel aspects, in the sense that we base the forecast on fundamental company information, such as earnings per share, price earning ratio, dividends, sales, profit margin, etc. These indicators and ratios thereof, especially earnings related indicators, are the prime movers of a stock price. The preliminary results we obtain are very promising.

A new algorithm for learning in piecewise-linear neural networks

Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consisting of a single hidden layer. The approach adopted is based upon constructing a continuous PWL error function and developing an efficient algorithm to minimize it. The algorithm consists of two basic stages in searching the weight space. The first stage of the optimization algorithm is used to locate a point in the weight space representing the intersection of N linearly independent hyperplanes, with N being the number of weights in the network. The second stage is then called to use this point as a starting point in order to continue searching by moving along the single-dimension boundaries between the different linear regions of the error function, hopping from one point (representing the intersection of N hyperplanes) to another. The proposed algorithm exhibits significantly accelerated convergence, as compared to standard algorithms such as back-propagation and improved versions of it, such as the conjugate gradient algorithm. In addition, it has the distinct advantage that there are no parameters to adjust, and therefore there is no time-consuming parameters tuning step. The new algorithm is expected to find applications in function approximation, time series prediction and binary classification problems.

Organization of Multi-Agent Systems: An Overview

In complex, open, and heterogeneous environments, agents must be able to reorganize towards the most appropriate organizations to adapt unpredictable environment changes within Multi-Agent Systems (MAS). Types of reorganization can be seen from two different levels. The individual agents level (micro-level) in which an agent changes its behaviors and interactions with other agents to adapt its local environment. And the organizational level (macro-level) in which the whole system changes it structure by adding or removing agents. This chapter is dedicated to overview different aspects of what is called MAS Organization including its motivations, paradigms, models, and techniques adopted for statically or dynamically organizing agents in MAS.

PSOSA: An Optimized Particle Swarm Technique for Solving the Urban Planning Problem

This paper introduces an optimized particle swarm technique (PSOSA) that uses simulated annealing for optimizing the inertia weight. To study the performance of the proposed technique, it has been applied on the urban planning problem involving a multi-objective fitness function that includes non-overlapping constraints as well as relative positioning requirements. Results show that the proposed technique performs much better as regards convergence speed as well as sustainability to increased load of growing number of blocks to be fitted in the urban planning problem

Image indexing using composite regional color channel features

Color indexing is a technique by which images in the database could be retrieved on the basis of their color content. In this paper, we propose a new set of color features for representing color images, and show how they can be computed and used efficiently to retrieve images that possess certain similarity. These features are based on the first three moments of each color channel. Two differences distinguish this work from previous work reported in the literature. First, we compute the third moment of the color channel distribution around the second moment, not around the first moment. The second moment is less sensitive to small luminance changes, than the first moment. Secondly, we combine all three moment values in a single descriptor. This reduces the number of floating point values needed to index the image and, hence, speeds up the search. To give the user flexibility in terns of defining his center of attention during query time, the proposed approach divides the image into five geometrical regions and allows the user of give different weights for each region to designate its importance. The approach has been tested on databases of 205 images of airplanes and natural scenes. It proved to be insensitive to small rotations and small translations in the image and yielded a better hit rate than similar algorithms previously reported in the literature.