Shahira M. Habashy

Accurate Prediction of Advanced Liver Fibrosis Using the Decision Tree Learning Algorithm in Chronic Hepatitis C Egyptian Patients

Background/Aim. Respectively with the prevalence of chronic hepatitis C in the world, using noninvasive methods as an alternative method in staging chronic liver diseases for avoiding the drawbacks of biopsy is significantly increasing. The aim of this study is to combine the serum biomarkers and clinical information to develop a classification model that can predict advanced liver fibrosis. Methods. 39,567 patients with chronic hepatitis C were included and randomly divided into two separate sets. Liver fibrosis was assessed via METAVIR score; patients were categorized as mild to moderate (F0–F2) or advanced (F3-F4) fibrosis stages. Two models were developed using alternating decision tree algorithm. Model 1 uses six parameters, while model 2 uses four, which are similar to FIB-4 features except alpha-fetoprotein instead of alanine aminotransferase. Sensitivity and receiver operating characteristic curve were performed to evaluate the performance of the proposed models. Results. The best model achieved 86.2% negative predictive value and 0.78 ROC with 84.8% accuracy which is better than FIB-4. Conclusions. The risk of advanced liver fibrosis, due to chronic hepatitis C, could be predicted with high accuracy using decision tree learning algorithm that could be used to reduce the need to assess the liver biopsy.

Identification of Diabetic Retinopathy Stages using Fuzzy C-means Classifier

Retinopathy (DR) is globally the primary cause of visual impairment and blindness in diabetic patients. Diabetic retinopathy occurs when the small blood vessels have a high level of glucose in the retina. That causes a change in the retina, which occur over a period of time in diabetics and cause the difficulties with vision. Regular screening is essential in order to detect the early stages of diabetic retinopathy for timely treatment to prevent or delay further deterioration. In this paper, the presences of abnormalities in the retina such as the structure of blood vessels, microaneurysms, and exudates using image processing techniques are detected. These features are processed with the help of Fuzzy C-Means clustering algorithm to detect the different diabetic retinopathy stages. This system intends to help ophthalmologists in DR screening process to detect symptoms faster and more easily. The sensitivity, Precision and accuracy for that Diabetic Retinopathy detection system are 98.01%, 99%, and 97% respectively. Keywordsretinopathy (DR), microaneurysms, exudates and Fuzzy C-Means (FCM), Retinal Image (RI).

Ant Algorithm Modification

Ant algorithm is a metaheuristic used to solve combinatorial optimization problems. As with other metaheuristic, like evolutionary methods, Ant algorithms often- show good optimization behavior but are slow when compared to classical heuristics. This problem happened due to the large number of control parameters used. Those parameters, that produce best performance, may be selected hand-tuned or using a systematic procedure. In this paper, we discuss how to evolve the ant algorithm by reducing the number of those parameters and improve their performance. This modification result in speeding up ant algorithm compared to classical one. A simple implementation of this approach tested on the traveling salesman problem (TSP) and many other problems. The results show that the modified ant algorithms have good performance compared to the original ant algorithm

Evaluation of Whole-Body-Vibration Exposure to Cairo Subway (Metro) Passengers

air, land and water), machinery (for example, those used in industry and agriculture) and industrial activities (such as pilling and blasting), expose people to periodic, random and transient mechanical vibration which can interfere with comfort, activities and health. Metro is one of the important and famous public transportations all over the world. High magnitude of whole-body vibration formed by the Metro may cause diseases and health problems to the human especially a low back pain. It leads to a muscular and bone system disorder of the neck and back. A previous epidemiological study reported that low-back pain (LBP) is spread among people exposed to whole-body-vibration frequently. LBP was significantly related with the levels of uncomfortable road vibrations, and, importantly, increased with total mileage. The aim of this study is to give an account of daily exposure to vibration and vibration dose value exposed to the passengers travelled using Cairo metro by measuring the whole body vibration on the passengers seat pan (seat back and seat surface) and on the floor. The results were evaluated according to the health guidelines of the international standards ISO 2631-1:1997, Directive 2002/44/EC of the European Parliament and ISO 2631-5:2004. damage or physiological change). The presence of oscillatory force with little motion may cause similar effects. The effects of direct vibration on the human body can be serious. Vibration can typically cause blurred vision, loss of balance, loss of concentration etc. In some cases, certain frequencies and levels of vibration can permanently damage internal body organs. After daily exposure over a number of years, these same whole-body vibrations can result in a number of health disorders affecting your entire body including permanent harm to internal organs, muscles, joints and bone structure. Research indicates back disorders are more prevalent and more severe in exposed to vibration versus non-exposed. With short term exposure to vibration in the 2-20 Hz range at 1 m/sec 2 , one can feel several different symptoms like, (16) abdominal pain, general feeling of discomfort, including headaches, chest pain, Loss of equilibrium (balance), muscle contractions with decreased performance in precise manipulation tasks, shortness of breath, and influence on speech.

Comparison of Machine Learning Approaches for Prediction of Advanced Liver Fibrosis in Chronic Hepatitis C Patients

Background/Aim: Using machine learning approaches as non-invasive methods have been used recently as an alternative method in staging chronic liver diseases for avoiding the drawbacks of biopsy. This study aims to evaluate different machine learning techniques in prediction of advanced fibrosis by combining the serum bio-markers and clinical information to develop the classification models. Methods: A prospective cohort of 39,567 patients with chronic hepatitis C was divided into two sets—one categorized as mild to moderate fibrosis (F0-F2), and the other categorized as advanced fibrosis (F3-F4) according to METAVIR score. Decision tree, genetic algorithm, particle swarm optimization, and multi-linear regression models for advanced fibrosis risk prediction were developed. Receiver operating characteristic curve analysis was performed to evaluate the performance of the proposed models. Results: Age, platelet count, AST, and albumin were found to be statistically significant to advanced fibrosis. The machine learning algorithms under study were able to predict advanced fibrosis in patients with HCC with AUROC ranging between 0.73 and 0.76 and accuracy between 66.3 and 84.4 percent. Conclusions: Machine-learning approaches could be used as alternative methods in prediction of the risk of advanced liver fibrosis due to chronic hepatitis C.

Adaptive controller based PSO with virtual sensor for obstacle avoidance in dynamic environments

In this paper, an Adaptation of Advanced Artificial Potential Field (AAPF) controller based on Particle Swarm Optimization (PSO) algorithm is proposed. It plans the robots motion in cluttered and dynamic environments to make the robot reaches to its goal. The PSO is used to optimize the factors of the forces applied on the robot to guide the robot towards to the right path. The optimization process is done by selecting the optimum values of these factors. A measure of smoothness is used to guide the PSO algorithm during the optimization process. The PSO is reused once a change in the environment is occurred. This scheme makes the robot able to reach to its target with shortest path and avoidance of the obstacles whatever changed environment. Shortest path means more smoothness and minimum time. The proposed adaptive AAPF controller uses the concept of virtual sensor. The virtual sensors calculations are modified in this paper. The proposed system is simulated on Windows Vista using MATLAB Software at different workspaces, and compared with another not adaptive system.

C40. Improved potential field controller for obstacle avoidance in mobile robots

In this paper, improved potential field controller suitable for obstacle avoidance is proposed. Genetic algorithms are used to improve the potential field controller by optimizing the forces applied to the robot making the robot path much smoother. A measure of smoothness is used to guide the genetic algorithm optimizer during its search. Of course more smoothing gives less distance and more speed to reach the goal. The optimized controller is simulated on Windows Vista using Matlab Software. Many cases including environments with single obstacle up to three obstacles and multi-knee corridor are simulated. Results are compared to previous work, illustrating the superiority of the proposed work.

Task Graph Generation

There are many intelligent design tools available, which are being used at the highest level of abstraction. These tools are very effective in solving the hardware/software co-synthesis problems. These tools require the input specification of the problem to be in the form of one or more task graph. Currently, one major problem is that many real time embedded system designs are specified in high level programming languages, not task graphs. The designer can manually transform the input specification from the used computer language to a task graph form, but this job has tedious and error prone problems. The task graph generation described in this paper reduces the potential for error and time required by automating the task graph process

Reconfigurable Parallel Processing System Based on A Modified Ant Colony Algorithm

Ant colony optimization is an evolutionary approach where a number of ants search for good solutions. Ant Algorithms often show good optimization results. This paper, discusses number of algorithms built using modified ant colony algorithm which are used to solve the problem of assigning each task in a given task graph to a processor in a reconfigurable multi processor architecture so as to minimize the total overall execution time of the tasks. Each group of ants is working collectively to find the interconnection architecture best suited for the task graph and the best scheduling of that task graph on the chosen interconnection architecture. The total execution time is computed according to the knowledge of individual run times of tasks and the communication requirements among tasks. The inter task communication time is dependent on the interconnection processor architecture. The results of using modified ant colony algorithm in reconfigurable parallel processor system are compared with that of using genetic algorithm for solving the same problem