Jamshid Shanbehzadeh

Chromosome Classification Based on Wavelet Neural Network

Karyotyping, manual chromosome classification is a difficult and time consuming process. Many automated classifiers have been developed to overcome this problem. These classifiers either have high classification accuracy or high training speed. This paper proposes a classifier that performs well in both areas based on wavelet neural network (WNN), combining the wavelet into neural network for classification of chromosomes in group E (chromosomes 16, 17 and 18). The nonlinear characteristic of the network which is derived from wavelet specification improves the training speed and accuracy of the nonlinear chromosome classification. The network inputs are nine dimensional feature space extracted from the chromosome images and the outputs are three classes. The simulation result on the chromosomes in the Laboratory of Biomedical Imaging shows that the success rate of WNN was 0.93%, that is comparable to the traditional neural network (ANN) with 0.85% success rate. The number of iterations for training to reach 0.04% error rate is only 200 where it is 3500 iterations for ANN. According to the experimental results WNN achieves high accuracy with minimum training time, which makes it suitable for real-time chromosome classification in the laboratory.

Affective Tutoring System for Better Learning

Intelligent tutoring systems (ITS) are still not as effective as one-on-one human tutoring. The next generation of intelligent tutors are expected to be able to take into account the emotional state of students. This paper presents research on the development of an Affective Tutoring System (ATS). The system called “Easy with Eve†adapts to students via a lifelike animated agent who is able to detect student emotion through facial expression analysis, and can display emotion herself. Eve’s adaptations are guided by a case-based method for adapting to student states; this method uses data that was generated by an observational study of human tutors. This paper presents an analysis of facial expressions of students engaged in learning with human tutors and how a facial expression recognition system, a life like agent and a case based system based on this analysis have been integrated to develop an ATS for mathematics.

Operating System Virtualization to support E-learning with Affective Intelligent Tutoring Systems

This paper introduces an operating system virtual machine platform for deploying affective intelligent tutoring systems in an e-iearning environment. Managed e-learning environments are often web based and rely on a browser to minimize configuration on the client machine, however even in these scenarios it is not unusual to have very specific requirements of the client machine, browser type and version, Javatrade virtual machine version and even operating system. In the case of affective intelligent tutoring systems there are additional requirements associated with the affective sensors, camera, bio-mouse etc. An operating system virtual machine approach allows the software stack of the client to be pre-configured and distributed in one shot. This minimizes the client side configuration easing the adoption of the technology. This paper identifies some of the key performance issues associated with this approach.

Large-Scale Image Retrieval Using Local Binary Patterns and Iterative Quantization

Hashing algorithm is an efficient approximate searching algorithm for large-scale image retrieval. Learning binary code is a key step to improve its performance and it is still an ongoing challenge. The inputs of Hashing affects its performance. This paper proposes a method to improve the efficiency of learning binary code by improving the suitableness of the Hashing algorithms inputs by employing local binary patterns in extracting image features. This approach results in more compact code, less memory and computational requirement and higher performance. The reasons behind these achievements are the binary nature and high efficiency in feature generation of local binary pattern. The performance analysis consists of using CIFAR-10 and precision vs. recall rate as dataset and evaluation criteria respectively. The simulations compare the new algorithm with three state of the art and along the line algorithms from three points of view; the hashing code size, memory space and computational cost, and the results demonstrate the effectiveness of the new approach.

SWARM INTELLIGENCE BASED CLUSTERING IN WIRELESS SENSOR NETWORKS

One of the main challenges for Wireless Sensor Networks (WSN) is their limited lifetime due to finite node energy. Although we can overcome this problem by optimizing the power consumption of nodes through clustering, optimum clustering of WSN is an NPHard problem. Therefore this paper presents a hybrid algorithm based on Genetic Algorithms and Particle Swarm Optimization (or artificial bee colony) that overcomes clustering problems by finding the best number of cluster heads, the cluster heads themselves and the cluster members. Simulation results reveal that the proposed scheme outperforms the simple Genetic Algorithm based clustering scheme, PEDAP, PEGASIS and LEACH.

A New Method in Coverage for Wireless Sensor Networks

One of the main problems in designing wireless sensor networks is to present a strategy which leads to increasing network lifetime by paying attention to energy resources. One of the most important issues in WSN is covering the region. So, the presented strategy should be able to cover all over the region by using lowest amount of sensor nodes. It is not always necessary that all the network nodes to be turning on, so by using a suitable algorithm, network nodes can be divided into some groups and each group will be in charge of covering its corresponding part of the region by turn on some nodes in some time slices such that full coverage is guaranty. In this paper, we propose a new idea that uses grouping and time scheduling for sensor nodes for turning them on to cover area. According to this method sensing range of all the nodes arent always same, and it is depending to their remained energy. Cluster head denotes the sensing range and also turn on time slice of each node by considering its remained energy and position. Using the mentioned algorithm leads to energy efficiency for better coverage; consequently it is increasing in network life.

Assisting the autistic with real-time facial expression recognition

People with Aspergers Syndrome have difficulty with recognizing other peoples emotions and are therefore not able to react to it. Although there have been many attempts aimed at developing software for teaching autistic children how to deal with social situations, the idea of equipping autistic persons with tools to help them recognize emotions has not been explored. This paper presents the idea of a wearable tool that uses automatic facial expression recognition developed by the authors to assist the autistic deal with social situations. In this paper, we describe a method we have developed for facial expression recognition that operates in real time. Experimental results show that this new method is superior to analysis of only either static images or dynamic videos which are the two methods commonly used. The assistive tool as well as the facial expression recognition system that has been developed for this purpose are presented here.

Innovative technologies for the creative industries: Advanced human-machine interfaces for dynamic performance effects

Technical advances in performing arts and TV production have focused on technologies like sound, special effects, projection and the like. New developments in computer vision have made gesture and facial expression recognition possible. What is missing is the means to link these new technologies and place them under direct control of the performer. Furthermore, performers have limited capacity to interpret and respond to their audience. This research aims to develop new gesture and facial expression recognition technologies to make possible completely new forms of performance that enable performers to directly influence the physical environment and respond to audience reaction. In this article, we focus on a gesture recognition system developed for this purpose and present a novel approach for gesture recognition. We discuss the gesture modelling technique used and its main features. Experiments show accuracy of over 98.71% making the gesture recognizer suitable for our innovative stage interface.