The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Many neural architectures including RBF, SVM, FSVC classifiers, or deep-learning solutions require the efficient implementation of neurons layers, each of them having a given number of m neurons, a specific set of parameters and operating on a training or test set of N feature vectors having each a dimension n. Herein we investigate how to allocate the computation on GPU kernels and how to better...
High level synthesis tools offered by either FPGA (Field Programmable Gate Array) vendors or from the public domain are evaluated in order to generate efficient and low complexity computational intelligence modules. This paper reports specific issues and comparative synthesis results in implementing basic modules of the FSVC classifier (Fast Support Vector Classifier) and cellular automata starting...
Recognition of epileptic seizures is an important issue and in certain circumstances it is desirable to have portable equipment implementing the algorithm in order to better monitor the patients. This work considers a widely used EEG database from University of Bonn as reference for comparing our recognition method with other previously reported. In order to perform epileptic seizures we combine a...
SVM (Support Vector Machine), a state of the art classifier model is implemented on a computational mobile platform and its performances are evaluated against a low complexity classifier such as SFSVC (Super Fast Vector Support Classifier) on the same platform. For a better comparison, similar implementation for the two architectures are considered, such as using the same basic linear algebra library...
This paper presents improvements in terms of accuracy for shape object classification using a new low complexity method compared to previous implementation [1]. The method is using echoes generated by a JAVA platform capable of emulate sound propagation in a controlled 2D virtual environment [2][3]. Echoes originate from the ultrasonic waves generated inside a virtual environment which contains geometrical...
The SFSVC (Super Fast Support Vector Classifier) architecture is implemented to a computational mobile platform and its performances are evaluated against its implementation on a classic machine (personal computer). The aim of this article is to prove that the SFSVC architecture can have good performances on an environment with very limited resources by taking advantages of its compact structure and...
Embedded dictation, i.e. recognizing vocal commands in noisy environments, with good accuracy and using low complexity implementations is a desirable task with many applications. Such applications include automotive infotainment solutions particularly when no connectivity is available, personal assistants including embedded dictation solutions for disabled people, and so on. This paper reports our...
This work presents improvements in terms of computational efficiency of a cellular automata based virtual environment for ultra-sound propagation, (previously abbreviated as CANAVI, i.e. Cellular Automata for ultra-sound based robot Navigation). Comparisons with our previous implementations using JAVA indicates good speed-up while using low cost, programming environments based on Python and exploiting...
A novel classifier architecture is introduced and its performances are evaluated against state of the art shallow classifiers. Its main advantage consists in a very fast learning ensured by a novelty detection algorithm, selecting a list of prototypes among the training samples, used as centers in a radial basis functions neurons layer. Only the radius of the basis functions is optimized to improve...
The performance of a simple yet efficient local receptive field feature extractor is evaluated on state of the art handwritten databases showing that after the proper optimization of its parameters, very good accuracy performances can be obtained using a shallow classifier (e.g. the support vector machine), close to the ones achieved using more sophisticated techniques such as deep-learning classifiers...
Cellular nonlinear networks are naturally inspired computing architectures where complex dynamic behaviors may emerge as a result of the local or prescribed connectivity among simple cells. Functionally, much like in biology, each cell is defined by a few bits of information called a gene. Such systems may be used in signal processing applications (intelligent sensors) or may be used to model and...
We propose a method for localization and classification of brand logos in natural images. The system has to overcome multiple challenges such as perspective deformations, warping, variations of the shape and colors, occlusions, background variations. To deal with perspective variation, we rely on homography matching between the SIFT keypoints of logo instances of the same class. To address the changes...
This paper aims to highlight the performances and advantages of three improved and fast AI algorithms that are mainly used in classification problems suitable for various fields. The discussions regarding the benchmark results appeal to the Modified version of Radial Basis Function (RBF-M) mentioned in the paper as Fast Support Vector Classifier (FSVC) or Fast Support Vector Machine, Extreme Learning...
The comparison of two classifiers, the Extreme Learning Machine (ELM) and the Support Vector Machine (SVM) is considered for performance, resources used (neurons or support vector kernels) and computational complexity (speed). Both implementations are of similar type (C++ compiled as Octave .mex files) to have a better evaluation of speed and computational complexity. Our results indicate that ELM...
In this article we present and test a specialized classifier, i.e., Fast Support Vector Classifier (FSVC), which is employed for multiple-instance human retrieval in video surveillance. Thanks to its low complexity and high performance in terms of computation and speed, FSVC is adapted to ease the generalization of the feature space using only a limited number of samples in the training process. To...
This work investigates the geometric object-shape classification using the echoes generated by various kinds of obstacles in a cellular automata based virtual environment for ultra-sound propagation. The virtual environment is implemented as a JAVA platform [1] capable of emulate sound propagation in a controlled 2D environment. The echoes are preprocessed by a Feature Processor Vector Unit (FVPU)...
Herein we consider the comparison of two neural networks: the Extreme Learning Machine (ELM) and the Fast Support Vector Classifier (FSVC, also known as RBF-M). Classification tasks are considered showing that FSVC has similar performance to ELM while having the advantage of a unique radius and of a precise result (no randomness is here involved)
An automated dermoscopy system requires careful data processing and selection of the features used for the classification of images. Steps towards higher degree of integration are made by introducing natural computing techniques of image preprocessing. For feature selection a technique inspired by fractal box counting principle is presented. Nevi classification using this feature show promising results.
A novel platform (hardware and software) for complex systems modeling is proposed. It exploits the newest developments in both software (Continuum's - Anaconda's Numba and Numbapro Python packages) and hardware (the use of parallel computation on GPU provided by the CUDA computing platform) to ensure high-performance, high-productivity and high-portability in developing and simulating models of cellular...
Computational efficiency and several other criteria are investigated from the perspective of using Python and Julia languages when used in natural computing and complexity related algorithms. While such algorithms often require high computational power, portability and easiness of implementing various algorithms, it is important to identify freely available platforms for high performance, high portability...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.