Philosophers are motivated to do research concerning pattern recognition because of wide range of its applications. One of the pathfi nders of research in that area was Satosi Watanabe, who has been frequently commented in the literature concerning this subject. The rule of decrease in entropy and the rule of simplicity are described in the context of pattern recognition. Although the concept of entropy had been initially used in the area of thermodynamics, it could be adopted also in the fi eld of pattern recognition. The concept of entropy should be then suitable transformed. A few of examples of the entropy concept application and the relationship between entropy and simplicity are discussed in the article. Simplicity considered by Watanabe should be treated mainly as polynomial curve simplicity, however the issue is described in the wider context.
A variety of algorithms allows gesture recognition in video sequences. Alleviating the need for interpreters is of interest to hearing impaired people, since it allows a great degree of self-sufficiency in communicating their intent to the non-sign language speakers without the need for interpreters. State-of-theart in currently used algorithms in this domain is capable of either real-time recognition of sign language in low resolution videos or non-real-time recognition in high-resolution videos. This paper proposes a novel approach to real-time recognition of fingerspelling alphabet letters of American Sign Language (ASL) in ultra-high-resolution (UHD) video sequences. The proposed approach is based on adaptive Laplacian of Gaussian (LoG) filtering with local extrema detection using Features from Accelerated Segment Test (FAST) algorithm classified by a Convolutional Neural Network (CNN). The recognition rate of our algorithm was verified on real-life data.
The work presented in the paper concerns a very important problem of searching for string alignments. The authors show that the problem of a genome pattern alignment could be interpreted and defined as a measuring task, where the distance between two (or more) patterns is investigated. The problem originates from modern computation biology. Hardware-based implementations have been driving out software solutions in the field recently. The complex programmable devices have become very commonly applied. The paper introduces a new, optimized approach based on the Smith-Waterman dynamic programming algorithm. The original algorithm is modified in order to simplify data-path processing and take advantage of the properties offered by FPGA devices. The results obtained with the proposed methodology allow to reduce the size of the functional block and radically speed up the processing time. This approach is very competitive compared with other related works.
Time-Frequency (t-f) distributions are frequently employed for analysis of new-born EEG signals because of their non-stationary characteristics. Most of the existing time-frequency distributions fail to concentrate energy for a multicomponent signal having multiple directions of energy distribution in the t-f domain. In order to analyse such signals, we propose an Adaptive Directional Time-Frequency Distribution (ADTFD). The ADTFD outperforms other adaptive kernel and fixed kernel TFDs in terms of its ability to achieve high resolution for EEG seizure signals. It is also shown that the ADTFD can be used to define new time-frequency features that can lead to better classification of EEG signals, e.g. the use of the ADTFD leads to 97.5% total accuracy, which is by 2% more than the results achieved by the other methods.
We propose a novel magnetic field sensitive semiconductor device, viz., Horizontally-Split-Drain Magnetic-Field Sensitive Field-Effect Transistor (HSDMAGFET) which can be used to measure or detect steady or variable magnetic fields. Operating principle of the transistor is based on one of the galvanomagnetic phenomena and a Gradual Channel Detachment Effect (GCDE) and is very similar to that of Popovic and Baltes's SDMAGFET. The predicted absolute sensitivity of the new sensor can reach as high value as 1000 V/T. Furthermore, due to its original structure, the spatial resolution of the new MAGFET is very high which makes this device especially useful in reading magnetically encoded data or magnetic pattern recognition.
It is well known that the magnitudes of the coefficients of the discrete Fourier transform (DFT) are invariant under certain operations on the input data. In this paper, the effects of rearranging the elements of an input data on its DFT are studied. In the one-dimensional case, the effects of permuting the elements of a finite sequence of length N on its discrete Fourier transform (DFT) coefficients are investigated. The permutations that leave the unordered collection of Fourier coefficients and their magnitudes invariant are completely characterized. Conditions under which two different permutations give the same DFT coefficient magnitudes are given. The characterizations are based on the automorphism group of the additive group ZN of integers modulo N and the group of translations of ZN. As an application of the results presented, a generalization of the theorem characterizing all permutations that commute with the discrete Fourier transform is given. Numerical examples illustrate the obtained results. Possible generalizations and open problems are discussed. In higher dimensions, results on the effects of certain geometric transformations of an input data array on its DFT are given and illustrated with an example.