Search results for "computer.software_genre"
showing 10 items of 3858 documents
Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network
2020
In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural networks compete. The generator tries to produce data that is similar to the measured data, and the discriminator tries to correctly classify the data as fake or real. This is a reinforcement learning model, where both models get reinforcement based on their performance. In the training of the discriminator we use data measured from skin cancer patients. The aim for the study is to develop a generator for augmenting hyperspectral skin cancer imagery. peerReviewed
BlockSee: Blockchain for IoT video surveillance in smart cities
2018
The growing demand for safety in urban environments is supported by monitoring using video surveillance. The need to analyze multiple video-flows from different cameras deployed around the city by heterogeneous owners introduces vulnerabilities and privacy issues. Video frames, timestamps, and camera settings can be digitally manipulated by malicious users; the positions of cameras, their orientation and their mechanical settings can be physically manipulated. Digital and physical manipulations may have several effects, including the change of the observed scene and the potential violation of neighbors' privacy. To face these risks, we introduce BlockSee, a blockchain-based video surveillan…
First results towards building up a reliable in situ measurements database for LST algorithm validations using modular WSN: Northern Morocco campaign…
2012
This article presents a new method sensitivity ∼0.1°C for in situ LST measurements. The results of wide in situ LST campaigns carried out during 2009 in four distant and different sites located in northern Morocco are shown: 1 Kasr-Seghir, 2 Targha, 3 Tangier, and 4 Chefchaouen. For this purpose, we used two calibrated radiometers with thermal infrared bands, OSM101 and TESTO845. Finally, during these campaigns, a total of 28,531 measurements were made with the proposed wireless-LST Wi-LST system. The preliminary results show a wide variability of the measurements, which is in total accordance with the heterogeneity of the targets' nature. This is encouraging for we are interested in buildi…
Evolving Tree Algorithm Modifications
2007
There are many variants of the original self-organizing neural map algorithm proposed by Kohonen. One of the most recent is the Evolving Tree, a tree-shaped self-organizing network which has many interesting characteristics. This network builds a tree structure splitting the input dataset during learning. This paper presents a speed-up modification of the original training algorithm useful when the Evolving Tree network is used with complex data as images or video. After a measurement of the effectiveness an application of the modified algorithm in image segmentation is presented.
Estimating feature discriminant power in decision tree classifiers
1995
Feature Selection is an important phase in pattern recognition system design. Even though there are well established algorithms that are generally applicable, the requirement of using certain type of criteria for some practical problems makes most of the resulting methods highly inefficient. In this work, a method is proposed to rank a given set of features in the particular case of Decision Tree classifiers, using the same information generated while constructing the tree. The preliminary results obtained with both synthetic and real data confirm that the performance is comparable to that of sequential methods with much less computation.
A Novel Web Service for Mammography Images Indexing
2013
Medical community needs to extract precise information from a large amount of data. These data are a collection of different types such as text documents, images and video. Currently medical technology do not provide an intelligent methodology for documents recovery and classification of such documents based on their content. In this work the radiological structured reports are analysed with the corresponding mammographic images. The presented system is composed of an Indexing Engine and a Searching Engine, based on innovative methods for IR (Information Retrieval). The proposed work is useful for physicians as support diagnosis system, for students as learning support system, and finally, …
FINDR: Low-Cost Indoor Positioning Using FM Radio
2009
This paper presents an indoor positioning system based on FM radio. The system is built upon commercially available, short-range FM transmitters. The features of the FM radio which make it distinct from other localisation technologies are discussed. Despite the low cost and off-the-shelf components, the performance of the FM positioning is comparable to that of other positioning technologies (such as Wi-Fi). From our experiments, the median accuracy of the system is around 1.3 m and in 95% of cases the error is below 4.5 m.
Computing Real-Time Dynamic Origin/Destination Matrices from Vehicle-to-Infrastructure Messages Using a Multi-Agent System
2012
Dynamic Origin/Destination matrices are one of the most important parameters for efficient and effective transportation system management. These matrices describe the vehicle flow between different points within a region of interest for a given period of time. Usually, dynamic O/D matrices are estimated from traffic counts provided by induction loop detectors, home interview and/or license plate surveys. Unfortunately, estimation methods take O/D flows as time invariant for a certain number of intervals of time, which cannot be suitable for some traffic applications. However, the advent of information and communication technologies (e.g., vehicle-to-infrastructure dedicated short range comm…
Chairs' welcome message
2004
In this paper we present techniques for comparison between behavioral level and register transfer level (RTL) design descriptions by mapping the designs into virtual controllers and virtual datapaths. We also discuss about how the equivalence between behavioral level and RTL designs can be defined precisely using the proposed "attribute statements" in an interactive fashion. Implementation issues as well as considerations on real life industrial design examples are presented as well.
An Ehrenfeucht-Fraïssé Approach to Collapse Results for First-Order Queries over Embedded Databases
2001
We present a new proof technique for collapse results for first-order queries on databases which are embedded in N or R>o. Our proofs are by means of an explicitly constructed winning strategy for Duplicator in an Ehrenfeucht-FraissE game, and can deal with certain infinite databases where previous, highly involved methods fail. Our main result is that first-order logic has the natural-generic collapse over {N,≤ ,+} for arbitrary (i.e., possibly infinite) databases. Furthermore, a first application of this result shows the natural-generic collapse of first-order logic over {R>o,≤,+} for a certain kind of databases over R>o which consist of a possibly infinite number of regions.