Abdulmotaleb El-Saddik

Collaborative error-reflected models for cold-start recommender systems

Collaborative Filtering (CF), one of the most successful technologies among recommender systems, is a system assisting users to easily find useful information. One notable challenge in practical CF is the cold start problem, which can be divided into cold start items and cold start users. Traditional CF systems are typically unable to make good quality recommendations in the situation where users and items have few opinions. To address these issues, in this paper, we propose a unique method of building models derived from explicit ratings and we apply the models to CF recommender systems. The proposed method first predicts actual ratings and subsequently identifies prediction errors for each user. From this error information, pre-computed models, collectively called the error-reflected model, are built. We then apply the models to new predictions. Experimental results show that our approach obtains significant improvement in dealing with cold start problems, compared to existing work.

Collaborative user modeling for enhanced content filtering in recommender systems

Recommender systems, which have emerged in response to the problem of information overload, provide users with recommendations of content suited to their needs. To provide proper recommendations to users, personalized recommender systems require accurate user models of characteristics, preferences and needs. In this study, we propose a collaborative approach to user modeling for enhancing personalized recommendations to users. Our approach first discovers useful and meaningful user patterns, and then enriches the personal model with collaboration from other similar users. In order to evaluate the performance of our approach, we compare experimental results with those of a probabilistic learning model, a user model based on collaborative filtering approaches, and a vector space model. We present experimental results that show how our model performs better than existing alternatives.

A Cloud-Based Pervasive Serious Game Framework to Support Obesity Treatment

Obesity has become an outstanding public health issue in most countries around the world. Many attempts have been made to address this issue that ranges from taking medication to doing exercise to following a diet plan to playing games. Few approaches combine exercise and game to engage the obese people in playing fun-based games or purposeful games, also known as serious games, while monitoring their biosignals. However, existing work hardly provides a configurable, scalable and context-aware serious game framework that can be used as a support for obesity treatment. In this paper, we take an attempt to propose such a framework. The proposed framework facilitates bio-signal monitoring based on body sensor network, context-awareness based on pervasive sensors, and on-the-spot activity recommendation based on current game-playing context. It uses the cloud computing platform as infrastructural support that ensures the scalability of the framework. In order to demonstrate the suitability of the proposed framework, we developed a sample serious game; deploy it over a cloud platform; and experiment with it by capturing some psycho-physical data while the obese are engaged in game-play. We observed that the obese people were very much engaged in game-play and they had positive experience using the system.

An assistive computerized system for children with moderate intellectual and learning disabilities

We aim in this project to develop a system for children with intellectual and learning disabilities that supports collaboration, data exploration, communication and creativity. The system offers specific tutorials on basic concepts. It can enhance the communications and learning capabilities of the children. The tutorial contents contains multimedia elements that help the children understand effectively the topics. An assessment component is being developed to evaluate the children understanding. Parents can also be involved in the learning process by adding some contents suitable to their children.

Learning games for children with intellectual challenges

This paper discuss the design of the current educational tutorials and games which are developed for children with intellectual challenges who are resident in the Shafallah center for children with special needs in Doha, Qatar. These edutainment games teach the children using multimedia elements to improve their memorization skills and proactivity. Five games have been so far developed and being evaluated. These games teach the children about counting, healthy food, home objects, fruits & vegetables. The designed games characters are selected from the local environment as the children are familiar with them. Whenever the game is completed successfully, the child will get a virtual gift of different values based on the time he/she spent on the game and the number of right selections to reach a solution. This gift will be added to the childs virtual space and can be substituted by a higher value gift whenever the child improves his/her performance and completes the game in a shorter time. This concept challenges the children to try to get always the best gift while learning in a funny and enjoyable way.

Using cyclic redundancy check to eliminate key storage for revocable iris templates

In recent years, with the increased use of biometrics for user authentication, an increase in the demand for the security of the biometric databases has occurred. Public concerns about safety of their biometric templates if the database is compromised as well as fears of cross-referencing among databases had to be addressed to ensure public acceptance of the use of biometric systems in large scale applications. In this paper, we propose a template protection system for iris-based biometric systems. A shuffling algorithm ensures revocability, while a combined Hadamard and Reed Solomon error correction coding ensures security, and as an improvement over previous research, cyclic redundancy check is introduced to eliminate the need to store user keys along with the templates in the database.

Extreme Learning Machines for approximating nonlinear dimensionality reduction mappings: Application to Haptic handwritten signatures.

The abundance of computing and mobile devices makes the problem of user identification and verification an essential requirement for many applications. Haptics devices include the sense of touch in the form of kinesthetic and tactile feedback which provide additional features within handwritten signatures. However, they generate high dimensional data and dimensionality reduction techniques become useful for data mining, machine learning and visualization. Nonlinear transformations have been used for this, but in present day scenarios (Big Data, the Internet of Things, massive data streams, etc.) the computation becomes more complex, time consuming or impractical. Moreover, the relationships between the features of the original and the target spaces are more difficult to uncover. Extreme Learning Machines (ELM) are used for approximating nonlinear manifold learning methods in two ways: as a functional representation for implicit methods, and as simpler surrogate models for explicit mapping techniques. In the context of Haptic handwritten signatures, five implicit and explicit nonlinear transformation methods are investigated. In all cases it was found that ELM approximations to the mappings obtained with the original methods exhibit very good behavior and can be used either as functional representations for the implicit methods or as simpler surrogate models for explicit techniques.

An Arabic-Based Tutorial System for Children with Special Needs

Abstract In spite of the current proliferation of the use of computers in education in the Arab world, complete suites of solutions for students with special needs are very scarce. This paper presents an assistive system managing learning content for children with moderate to mild intellectual disabilities. The system provides educational multimedia contents, inspired from the local environment, in different subjects such as math, science, religion, daily life skills, and others to target specific learning goals suitable for this group of learners. The system tracks the individual student progress against the student individualized learning plan assigned by the specialized teacher and according to the learner abilities. Upon completion of learning a particular task, the system will test the learner to order a set of sub-tasks in its logical sequence necessary to successfully accomplish the main task. The system also facilitates deploying intelligent tutoring algorithms to automatically correct mistakes af...