Zein Al Abidin Ibrahim

TV Stream Structuring

TV stream structuring consists in detecting precisely the first and the last frames of all the programs and the breaks (commercials, trailers, station identification, bumpers) of a given stream and then in annotating all these segments with metadata. Usually, breaks are broadcasted several times during a stream. Thus, the detection of these repetitions can be considered as a key tool for stream structuring. After the detection stage, a classification method is applied to separate the repetitions in programs and breaks. In their turn, breaks repetitions are then used to classify the segments which appear only once in the stream. Finally, the stream is aligned with an electronic program guide (EPG), in order to annotate the programs. Our experiments have been applied on a 22-day long TV stream, and results show the efficiency of the proposed method in TV stream structuring.

A Similarity-Based Approach for Audiovisual Document Classification Using Temporal Relation Analysis

We propose a novel approach for video classification that bases on the analysis of the temporal relationships between the basic events in audiovisual documents. Starting from basic segmentation results, we define a new representation method that is called Temporal Relation Matrix (TRM). Each document is then described by a set of TRMs, the analysis of which makes events of a higher level stand out. This representation has been first designed to analyze any audiovisual document in order to find events that may well characterize its content and its structure. The aim of this work is to use this representation to compute a similarity measure between two documents. Approaches for audiovisual documents classification are presented and discussed. Experimentations are done on a set of 242 video documents and the results show the efficiency of our proposals.

ECG classification for sleep apnea detection

Sleep Apnea is a potentially serious sleep disorder in which you have one or more pauses in breathing or shallow breaths while you sleep. It is classified into 3 main types: Obstructive sleep apnea, Central sleep apnea, and Complex sleep apnea syndrome. Obstructive sleep apnea (OSA) represents 80% of the apnea cases which makes it the most common type. Polysomnography is the current traditional method used to diagnose OSA, it is expensive and needs human experts and done in a special laboratories, the need of a more comfortable and cheaper method arises recently to detect and diagnose such type of disorders. Recently researchers focused on signal processing and pattern recognition as alternative methods to detect OSA. In this paper, an automated classification algorithm is presented which processes short duration epochs of ECG data. The automated classification technique is based on three classifiers: Support vector machines (SVM), radial bases function (RBF), and multi-layer perception (MLP). The obtained results showed a high degree of accuracy, approximately 97.55 over passing all the other classifiers that have been already used in the literature. Moreover, the system we developed can be used as a basis for future development of a tool for OSA screening.

Towards the detection and the characterization of conversational speech zones in audiovisual documents

Giving access to the semantically rich content of large amounts of digital audiovisual data using an automatic and generic method is still an important challenge. The aim of our work is to address this issue while focusing on temporal aspects. Our approach is based on a method previously developed for analyzing temporal relations from a data mining point of view. This method is used to detect zones of a document in which two characteristics are active. These characteristics can result from low-level segmentations of the audio or video components, or from more semantic processings. Once ldquoactivity zonesrdquo have been detected, we propose to compute a set of additional descriptors in order to better characterize them. The method is applied in the scope of the EPAC project that focuses on the detection and the characterization of conversational speech.

Audio Data Analysis using Parametric Representation of Temporal Relations

The aim of our work is the automatic analysis of audiovisual documents to retrieve their structure by studying the temporal relations between the events occurring in each of them. Different elementary segmentations of a same document are necessary. Then, starting from a parametric representation of temporal relations, a temporal relation matrix (TRM) is built. In order to analyze its content, a classification step is carried out to identify relevant relation class or to observe predefined relations as the Allens relations. The use of segmentation tools brings in the problem of the segmentation result reliability. Through a first experiment we analyze the effect of segmentation errors on the study of temporal relations. Then, as a second experiment, we apply our parametric method to a TV game document in order to analyze audio events and to see if the observations made can reveal information about the document content or its structure