Mohammed F. Alhamid

Audio-Visual Emotion Recognition Using Big Data Towards 5G

With the advent of future generation mobile communication technologies (5G), there is the potential to allow mobile users to have access to big data processing over different clouds and networks. The increasing numbers of mobile users come with additional expectations for personalized services (e.g., social networking, smart home, health monitoring) at any time, from anywhere, and through any means of connectivity. Because of the expected massive amount of complex data generated by such services and networks from heterogeneous multiple sources, an infrastructure is required to recognize a user’s sentiments (e.g., emotion) and behavioral patterns to provide a high quality mobile user experience. To this end, this paper proposes an infrastructure that combines the potential of emotion-aware big data and cloud technology towards 5G. With this proposed infrastructure, a bimodal system of big data emotion recognition is proposed, where the modalities consist of speech and face video. Experimental results show that the proposed approach achieves 83.10 % emotion recognition accuracy using bimodal inputs. To show the suitability and validity of the proposed approach, Hadoop-based distributed processing is used to speed up the processing for heterogeneous mobile clients.

Exploring Latent Preferences for Context-Aware Personalized Recommendation Systems

Context-aware recommendations offer the potential of exploiting social contents and utilize related tags and rating information to personalize the search for content considering a given context. Recommendation systems tackle the problem of trying to identify relevant resources from the vast number of choices available online. In this study, we propose a new recommendation model that personalizes recommendations and improves the user experience by analyzing the context when a user wishes to access multimedia content. We conducted empirical analysis on a dataset from last.fm to demonstrate the use of latent preferences for ranking items under a given context. Additionally, we use an optimization function to maximize the mean average precision measure of the resulted recommendation. Experimental results show a potential improvement to the quality of the recommendation in terms of accuracy when compared with state-of-the-art algorithms.

Towards context-sensitive collaborative media recommender system

With the rapid increase of social media resources and services, Internet users are overwhelmed by the vast quantity of social media available. Most recommender systems personalize multimedia content to the users by analyzing two main dimensions of input: content (item), and user (consumer). In this study, we address the issue of how to improve the recommendation and the quality of the user experience by analyzing the contextual aspect of the users, at the time when they wish to consume multimedia content. Mainly, we highlight the potential of including a user’s biological signal and leveraging it within an adapted collaborative filtering algorithm. First, the proposed model utilizes existing online social networks by incorporating social tags and rating information in ways that personalize the search for content in a particular detected context. Second, we propose a recommendation algorithm to improve the user experience and satisfaction with the use of a biosignal in the recommendation process. Our experimental results show the feasibility of personalizing the recommendation according to the user’s context, and demonstrate some improvement on cold start situations where relatively little information is known about a user or an item.

Hamon: An activity recognition framework for health monitoring support at home

In this paper, we introduce a Health signs and Activity recognition MONitoring framework (Hamon). Hamon, of German origin meaning a home protector [13], is designed to be an enabling prototype for health monitoring applications. As one of the possible applications, we implemented an activity detection prototype using off-the-shelf sensors. The new activity recognition algorithm we present here is based on accelerometers signals, a K-nearest neighbor (KNN) classifier and a Bayesian network. The framework collects and analyzes sensory data in real-time, and provides different feedback to the users. In addition, it can generate alerts based on the detected events and store the data collected to a medical sever. Context information such as the weather condition, the type of activity, and physiological data collected such as the heart rate, is also integrated in the framework.

An ambient intelligent body sensor network for e-Health applications

Body sensor network (BSN) has played a key role in the rapid advancement of e-Health applications. If it is properly designed, a BSN can act as an ambient intelligent environment by providing us not only time critical human body information but also the context and events mapped with raw sensory data. In this paper, we propose the design of a BSN, which offers two features 1) capability of pushing sensory data and events from ones BSN, and ambient information from surrounding environment to a remote healthcare center and 2) facility of remotely querying any sensory data from ones BSN even if he is at home or outside. As a proof of concept, we created a testbed which can interact with the BSN in both communication ways. Finally, we present some preliminary test results that show the viability of the system.

An Automatic Health Monitoring System for Patients Suffering From Voice Complications in Smart Cities

Current evolutions in the Internet of Things and cloud computing make it believable to build smart cities and homes. Smart cities provide smart technologies to residents for the improved and healthier life, where smart healthcare systems cannot be ignored due to rapidly growing elderly people around the world. Smart healthcare systems can be cost-effective and helpful in the optimal use of healthcare resources. The voice is a primary source of communication and any complication in the production of voice affects the personal as well as professional life of a person. Early screening of voice through an automatic voice disorder detection system may save life of a person. In this paper, an automatic voice disorder detection system to monitor the resident of all age group and professional backgrounds is implemented. The proposed system detects the voice disorder by determining the source signal from the speech through the linear prediction analysis. The analysis calculates the features from normal and disordered subjects. Based on these features, the spectrum is computed, which provided distribution of energy in normal and voice disordered subjects to differentiate between them. It is found that lower frequencies from 1 to 1562 Hz contributes significantly in the detection of voice disorders. The system is developed by using sustained vowel and running speech so that it can be deployed in a real world. The obtained accuracy for the detection of voice disorder with the sustained vowel is 99.94% ± 0.1, and that is for running speech is 99.75% ± 0.8.

Enhanced Living by Assessing Voice Pathology Using a Co-Occurrence Matrix

A large number of the population around the world suffers from various disabilities. Disabilities affect not only children but also adults of different professions. Smart technology can assist the disabled population and lead to a comfortable life in an enhanced living environment (ELE). In this paper, we propose an effective voice pathology assessment system that works in a smart home framework. The proposed system takes input from various sensors, and processes the acquired voice signals and electroglottography (EGG) signals. Co-occurrence matrices in different directions and neighborhoods from the spectrograms of these signals were obtained. Several features such as energy, entropy, contrast, and homogeneity from these matrices were calculated and fed into a Gaussian mixture model-based classifier. Experiments were performed with a publicly available database, namely, the Saarbrucken voice database. The results demonstrate the feasibility of the proposed system in light of its high accuracy and speed. The proposed system can be extended to assess other disabilities in an ELE.

RecAm: a collaborative context-aware framework for multimedia recommendations in an ambient intelligence environment

AbstractWith an ever-increasing accessibility to different multimedia contents in real-time, it is difficult for users to identify the proper resources from such a vast number of choices. By utilizing the user’s context while consuming diverse multimedia contents, we can identify different personal preferences and settings. However, there is a need to reinforce the recommendation process in a systematic way, with context-adaptive information. The contributions of this paper are twofold. First, we propose a framework, called RecAm, which enables the collection of contextual information and the delivery of resulted recommendation by adapting the user’s environment using Ambient Intelligent (AmI) Interfaces. Second, we propose a recommendation model that establishes a bridge between the multimedia resources, user joint preferences, and the detected contextual information. Hence, we obtain a comprehensive view of the user’s context, as well as provide a personalized environment to deliver the feedback. We demonstrate the feasibility of RecAm with two prototypes applications that use contextual information for recommendations. The offline experiment conducted shows the improvement of delivering personalized recommendations based on the user’s context on two real-world datasets.

A multi-modal intelligent system for biofeedback interactions

Biofeedback is an emerging technology being used as a legitimate medical technique for several medical issues such as heart problems, pain, stress, depression, among others. This paper introduces the Multi-Modal Intelligent System for Biofeedback Interactions (MMISBI), an interactive and intelligent biofeedback system using an interactive mirror to facilitate and enhance the users awareness of various physiological functions using biomedical sensors in real-time. The system comprises different biofeedback sensors that collect physiological features; the system also provides intuitive, intelligent, and adaptive user interfaces that promote a natural communication between the user and the biofeedback system. The Ambient Intelligence (AmI) technology is incorporated in the system to provide means for biofeedback responses. The proposed conceptual system is been evaluated by 15 subjects and the results are very stimulating. Ninety percent (90%) of the subjects confirmed that the system is beneficial, deployable, and affordable for personal use. On the other hand, 30% of the subjects have indicated that privacy is the resisting issue for the wide deployment of the system.

Leveraging biosignal and collaborative filtering for context-aware recommendation

Recommender systems are powerful tools that support the user in their quest to find the multimedia they are looking for. Such systems present multimedia contents or provide recommendations by taking into consideration two dimensions of inputs: content (item), and user (consumer). Little attention has been paid to increasing the quality of the experience by understanding the contextual aspect of the user when he/she wants to consume multimedia content. By including users biological signal and leveraging collaborative filtering, we can build a context-aware model that establish the bridge between the multimedia content, and the users context containing physiological parameters. Hence, the proposed model finds the latent preferences of users in a given context from other similar users. The model also finds the latent items consumed in a given context from other similar items. We then map context-based items for a particular user to find most relevant items in that context. Our experimental results have shown the feasibility to personalize the recommendation according to the users context.