Krasimir Tonchev

Challenges in designing and implementation of an effective Ambient Assisted Living system

In this paper some challenges in the design and realization of an effective Ambient Assisted Living (AAL) system are discussed. Solutions to meet those challenges are proposed. Example of the practical implementation of the architecture of an AAL system - “eWall for Active Long Living” (eWALL) and the related context-aware services are presented.

Recognition of facial images with subspace projection and dissimilarity representation

In this work, we present a framework for face recognition, combining face detection algorithm, dimensionality reduction method and a dissimilarity-based classifier. The face detection algorithm is intended to detect and extract faces in complex scenes, prior to face recognition. The Spectral Regression method, in sparse setting, is used for dimensionality reduction. The classification problem is solved by the Proximity Index ”Shape Coefficient” with SVM decision rules and Prototype Selection based classification. The results with real world experiments encourage us to propose this framework as good alternative to other face recognition methods.

Non-intrusive sleep analyzer for real time detection of sleep anomalies

Solutions for caring for the elderly both efficacious and cost-effective are given by Ambient Assisted Living (AAL) systems that combine the research fields of intelligent systems and communication technologies. These systems are promising for the improvement of the quality of life of elderly and disabled people. One important characteristic of health and well-being is sleep. While sleep quantity is directly measurable, its quality has traditionally been assessed with subjective methods such as questionnaires. In this paper, we propose a non-intrusive sleep analyzer for real time detection of sleep anomalies, part of an effective AAL system. The proposed solution is based on combination of non-invasive sensors and an algorithm for sleep analysis with two stages - low and high level reasoning. It also offers the opportunity to include third party devices. Using the analyzer we can monitor basic sleep behavior and to detect sleep anomalies, which can serve as an important indicator for both mental and physical health.

Human Gaze Tracking With An Active Multi-Camera System

This paper presents a framework for determining the direction of human gaze with an active multi-camera system. A fixed camera is employed in order to estimate the position of the human face and its features, like the eyes. By means of the Supervised Descent Method (SDM) for minimizing a Non-linear Least Squares (NLS) function we can compute correctly the position of the two eyes using 6 landmarks for each of them and the pose of the head. Then an active pan-tilt camera is oriented to one of the users eyes. This way a high precision gaze direction determination is accomplished.

Facial Expression Classification Using Supervised Descent Method Combined With PCA and SVM

It has been well known that there is a correlation between facial expression and person’s internal emotional state. In this paper we use an approach to distinguish between neutral and some other expression: based on the displacement of important facial points (coordinates of edges of the mouth, eyes, eyebrows, etc.). Further the feature vectors are formed by concatenating the landmarks data from Supervised Descent Method, applying PCA and use these data as an input to Support Vector Machine (SVM) classifier. The experimental results show improvement of the recognition rate in comparison to some state-of-the-art facial expression recognition techniques.

Autonomous learning model for achieving multi cell load balancing capabilities in HetNet

Heterogeneous networks (HetNets) have been proposed as a capacity and coverage enabler in LTE-Advanced and beyond communication networks. Their optimal operation requires a significant degree of self-organization. Autonomic Load Balancing (ALB) has been proposed as an important self-organizing (SON) function in the LTE radio access network (RAN). In this work, distributed ALB is achieved by implementing a programmable autonomous learning model. The optimization problem (load balancing) is split into many small optimization problems and tasks, which are solved by using machine learning algorithms. The load conditions of the E-UTRAN NodeB (eNBs) and the measurement reports from the mobile terminals are used for creating a decision map for the load balancing. The simulation results show that by using ALB, the system capacity can be improved significantly.

Face and ECG Based Multi-Modal Biometric Authentication

A biometric system is essentially a pattern recognition system. This system measures and analyses human body physiological characteristics, such as face and facial features, fingerprints, eye, retinas, irises, voice patterns or behavioral characteristic for enrollment, verification or identification (Bolle & Pankanti, 1998). Uni-modal biometric systems have poor performance and accuracy, and over last few decades the multi-modal biometric systems have become very popular. The main objective of multi biometrics is to reduce one or more false accept rate, false reject rate and failure to enroll rate. Face Recognition (FR) is still considered as one of the most challenging problems in pattern recognition. The FR systems try to recognize the human face in video sequences as 3D object (Chang et al., 2003; 2005), in unconstrained conditions, in comparison to the early attempts of 2D frontal faces in controlled conditions. Despite the effort spent on research today there is not a single, clearly defined, solution to the problem of Face Recognition, leaving it an open question. One of the key aspects of FR is its application, which also acts as the major driving force for research in that area. The applications range from law enforcement to human-computer interactions (HCI). The systems used in these applications fall into two major categories: systems for identification and systems for verification (Abate et al., 2007). The first group attempts to identify the person in a database of faces, and extract personal information. These systems are widely used, for instance, in police departments for identifying people in criminal records. The second group finds its main application in security, for example to gain access to a building, where face is used as more convenient biometric. The more general HCI systems include not only identification or verification, but also tracking of a human in a complex environment, interpretation of human behavior and understanding of human emotions. Another biometric modality that we use in our approach is the electrocardiogram (ECG). The modern concept for ECG personal identification is to extract the signal features using transform methods, rather than parameters in time domain (amplitudes, slopes, time intervals). The proper recognition of the extracted features and the problem of combining different biometric modalities in intelligent video surveillance systems are the novel steps that we introduce in this work. 4

Feature selection in affective speech classification

The increasing role of spoken language interfaces in human-computer interaction applications has created conditions to facilitate a new area of research — namely recognizing the emotional state of the speaker through speech signals. This paper proposes a text independent method for emotion classification of speech signals used for the recognition of the emotional state of the speaker. Different feature selection criteria are explored and analyzed, namely Mutual Information Maximization (MIM) feature scoring criterion and its derivatives, to measure how potentially useful a feature or feature subset may be when used in a classifier. The proposed method employs different groups of low-level features, such as energy, zero-crossing rate, frequency bands in Mel scale, fundamental frequency or pitch, the delta- and delta-delta regression and statistical functions such as regression coefficients, extremums, moments etc., to represent the speech signals and a Neural Network classifier for the classification task. For the experiments the EMO-DB dataset is used with seven primary emotions including neutral. Results show that the proposed system yields an average accuracy of over 85% for recognizing 7 emotions with 5 of the best performing feature selection algorithms.

Implementation of Machine Learning for Autonomic Capabilities in Self-Organizing Heterogeneous Networks

The 3GPP’s self-organizing networks (SONs) standards are a huge step towards the autonomic networking concept. They are the response to the increasing complexity and size of the mobile networks. This paper proposes a novel scheme for SONs. This scheme is based on machine learning techniques and additionally adopting the concept of abstraction and modularity. The implementation of these concepts in a machine learning scheme allows the usage of independent vendor and technology algorithms and reusability of the proposed approach for different optimization tasks in a network. The scheme is tested for solving an energy saving optimization problem in a heterogeneous network. The results from simulation experiments show that such an approach could be an appropriate solution for developing a full self-managing future network.

Action Unit recognition in still images using graph-based feature selection

Facial expressions are universal and independent of race, culture, ethnicity, nationality, gender, age, religion, or any other demographic variable. These facts are the main reason for automatic facial expression recognition being one of the hot topics of many research efforts and being useful in so many commercial and scientific fields. The most well-known and probably the most used anatomically based method of defining facial activity is Facial Action Coding System (FACS). In this paper, we propose a Facial Action Unit recognition algorithm using graph-based feature selection in unsupervised and supervised setting. The proposed algorithm is based on a state of the art algorithm for facial key points detection - Supervised Gradient Descent method, the classification is carried out using the well know Support Vector Machines classifier. Built this way, the algorithm works on still images where the human expressions are expected to be in their apex phase. Using leave one person out evaluation methodology we achieve average accuracy of 90.1% for unsupervised and 92.7% for supervised feature selection on 12 Action Units.