This paper is concerned with a synthesis study of the fast Fourier transform (FFT) and the wavelet transform in analysing the phonocardiogram signal (PCG). It bas been shown that the wavelet transform provides enough features of the PCG signals that will help clinics to obtain qualitative and quantitative measurements of the time-frequency PCG signal characteristics and consequently aid in diagnosis. Similarly, it bas been shown that the frequency content of such a signal can be determined by the FFT without difficulties. Abnormal heartbeat sounds may contain, in addition to the first and second sounds, S1 and S2, murmurs and aberrations caused by different pathological conditions of the cardiovascular system.
Within academia, wireless sensor networks have witnessed a tremendous upsurge in the last decade, which is mainly attributed to their unprecedented operating conditions and hence unlimited research challenges. Within industry, the projected business opportunities are huge with, e.g. according to Frost & Sullivan, an expected market size of approximately $2b by 2012 at a compound annual growth rate of 41.9%, therefore causing the interest in this technology to augment dramatically. Due to the unique design constraints, however, none of the grand communities - such as computing, telecommunications, physics, biology, etc. - can make such systems work efficiently on their own. The largest cross-community design exercise to-date is hence well underway which is well reflected in the nature of the intellectual property pools created in the past years. The aim of this paper is to expose and discuss a few early milestone as well as latest IT and telecommunications patents in this vibrant area.
Touch-based remote communication is a relatively new field of research. Traditionally, remote communication emphasizes on voice communication. Recently, with the proliferation of the IT sector, video communication is increasingly being used for remote communication. Communication based on touch is especially important for humans and animals to communicate remotely. As humans become increasingly busy at work or away from home, pets are increasingly neglected. Methodologies need to be developed to enable humans to assure their pets and keep in contact with them. Such systems should not only allow humans to see their pets, but also to allow pets to feel the presence of the owner. Patents reviewed here suggest inventions that attempt to bridge this gap, or have methods that can be used to achieve a better remote touch communication for humans and animals.
Identifying moving objects is a critical task for many computer vision applications; it provides a classification of the pixels into either foreground or background. A common approach used to achieve such classification is background removal. Even though there exist numerous of background removal algorithms in the literature, most of them follow a simple flow diagram, passing through four major steps, which are pre-processing, background modelling, foreground detection and data validation. In this paper, we survey many existing schemes in the literature of background removal, surveying the common pre-processing algorithms used in different situations, presenting different background models, and the most commonly used ways to update such models and how they can be initialized. We also survey how to measure the performance of any moving object detection algorithm, whether the ground truth data is available or not, presenting performance metrics commonly used in both cases.
The explosive growth of image data leads to the research and development of Content-Based Image Retrieval (CBIR) systems. CBIR systems extract and retrieve images by their low-level features, such as color, texture, and shape. However, these visual contents do not allow users to query images by semantic meanings. Image annotation systems, a solution to solve the inadequacy of CBIR systems, aim at automatically annotating image with some controlled keywords. Machine learning techniques are used to develop the image annotation systems to map the low-level (visual) features to high-level concepts or semantics. This paper reviews 50 image annotation systems using supervised machine learning techniques to annotate images for image retrieval. Future research issues are provided.